Upload fine-tuned Qwen3-ASR from checkpoint-14934
Browse files- .gitattributes +1 -0
- README.md +48 -0
- added_tokens.json +64 -0
- chat_template.json +1 -0
- config.json +222 -0
- generation_config.json +9 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- model.safetensors.index.json +715 -0
- preprocessor_config.json +14 -0
- rng_state.pth +3 -0
- special_tokens_map.json +44 -0
- tokenizer.json +3 -0
- tokenizer_config.json +549 -0
- trainer_state.json +1144 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ar
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: Qwen/Qwen3-ASR-1.7B
|
| 6 |
+
tags:
|
| 7 |
+
- automatic-speech-recognition
|
| 8 |
+
- arabic
|
| 9 |
+
- qwen3
|
| 10 |
+
- moulasot
|
| 11 |
+
- fine-tuned
|
| 12 |
+
datasets:
|
| 13 |
+
- atlasia/MoulSot-Full
|
| 14 |
+
pipeline_tag: automatic-speech-recognition
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Qwen3-ASR-1.7B — Fine-tuned on MoulSot-Full (Arabic / Moroccan Darija)
|
| 18 |
+
|
| 19 |
+
Fine-tuned version of [Qwen/Qwen3-ASR-1.7B](https://huggingface.co/Qwen/Qwen3-ASR-1.7B)
|
| 20 |
+
on the [atlasia/MoulSot-Full](https://huggingface.co/datasets/atlasia/MoulSot-Full) dataset.
|
| 21 |
+
|
| 22 |
+
## Usage
|
| 23 |
+
|
| 24 |
+
```python
|
| 25 |
+
from qwen_asr import Qwen3ASRModel
|
| 26 |
+
|
| 27 |
+
model = Qwen3ASRModel.from_pretrained(
|
| 28 |
+
"01Yassine/moulsot.v0.3",
|
| 29 |
+
dtype="bfloat16",
|
| 30 |
+
device_map="cuda",
|
| 31 |
+
)
|
| 32 |
+
|
| 33 |
+
result = model.transcribe(audio="your_audio.wav", language="Arabic")
|
| 34 |
+
print(result.text)
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
## Details
|
| 38 |
+
|
| 39 |
+
| Property | Value |
|
| 40 |
+
|---|---|
|
| 41 |
+
| Base model | `Qwen/Qwen3-ASR-1.7B` |
|
| 42 |
+
| Checkpoint | `output_moulasot_l40/1.7B/checkpoint-14934` |
|
| 43 |
+
| Language | Arabic / Moroccan Darija |
|
| 44 |
+
| Task | Automatic Speech Recognition |
|
| 45 |
+
|
| 46 |
+
## License
|
| 47 |
+
|
| 48 |
+
Apache 2.0 — same as the base model.
|
added_tokens.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<asr_text>": 151704,
|
| 6 |
+
"<blank10>": 151686,
|
| 7 |
+
"<blank11>": 151687,
|
| 8 |
+
"<blank12>": 151688,
|
| 9 |
+
"<blank13>": 151689,
|
| 10 |
+
"<blank14>": 151690,
|
| 11 |
+
"<blank15>": 151691,
|
| 12 |
+
"<blank16>": 151692,
|
| 13 |
+
"<blank17>": 151693,
|
| 14 |
+
"<blank18>": 151694,
|
| 15 |
+
"<blank19>": 151695,
|
| 16 |
+
"<blank1>": 151677,
|
| 17 |
+
"<blank20>": 151696,
|
| 18 |
+
"<blank21>": 151697,
|
| 19 |
+
"<blank22>": 151698,
|
| 20 |
+
"<blank23>": 151699,
|
| 21 |
+
"<blank24>": 151700,
|
| 22 |
+
"<blank25>": 151701,
|
| 23 |
+
"<blank26>": 151702,
|
| 24 |
+
"<blank27>": 151703,
|
| 25 |
+
"<blank2>": 151678,
|
| 26 |
+
"<blank3>": 151679,
|
| 27 |
+
"<blank4>": 151680,
|
| 28 |
+
"<blank5>": 151681,
|
| 29 |
+
"<blank6>": 151682,
|
| 30 |
+
"<blank7>": 151683,
|
| 31 |
+
"<blank8>": 151684,
|
| 32 |
+
"<blank9>": 151685,
|
| 33 |
+
"<non_speech>": 151675,
|
| 34 |
+
"<think>": 151667,
|
| 35 |
+
"<tool_call>": 151657,
|
| 36 |
+
"<tool_response>": 151665,
|
| 37 |
+
"<tts_pad>": 151671,
|
| 38 |
+
"<tts_text_bos>": 151672,
|
| 39 |
+
"<tts_text_bos_single>": 151674,
|
| 40 |
+
"<tts_text_eod>": 151673,
|
| 41 |
+
"<|audio_end|>": 151670,
|
| 42 |
+
"<|audio_pad|>": 151676,
|
| 43 |
+
"<|audio_start|>": 151669,
|
| 44 |
+
"<|box_end|>": 151649,
|
| 45 |
+
"<|box_start|>": 151648,
|
| 46 |
+
"<|endoftext|>": 151643,
|
| 47 |
+
"<|file_sep|>": 151664,
|
| 48 |
+
"<|fim_middle|>": 151660,
|
| 49 |
+
"<|fim_pad|>": 151662,
|
| 50 |
+
"<|fim_prefix|>": 151659,
|
| 51 |
+
"<|fim_suffix|>": 151661,
|
| 52 |
+
"<|im_end|>": 151645,
|
| 53 |
+
"<|im_start|>": 151644,
|
| 54 |
+
"<|image_pad|>": 151655,
|
| 55 |
+
"<|object_ref_end|>": 151647,
|
| 56 |
+
"<|object_ref_start|>": 151646,
|
| 57 |
+
"<|quad_end|>": 151651,
|
| 58 |
+
"<|quad_start|>": 151650,
|
| 59 |
+
"<|repo_name|>": 151663,
|
| 60 |
+
"<|video_pad|>": 151656,
|
| 61 |
+
"<|vision_end|>": 151653,
|
| 62 |
+
"<|vision_pad|>": 151654,
|
| 63 |
+
"<|vision_start|>": 151652
|
| 64 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n {%- if m.role == 'system' -%}\n {%- if m.content is string -%}\n {%- set ns.system_text = ns.system_text + m.content -%}\n {%- else -%}\n {%- for c in m.content -%}\n {%- if c.type == 'text' and (c.text is defined) -%}\n {%- set ns.system_text = ns.system_text + c.text -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n {%- if m.content is not string -%}\n {%- for c in m.content -%}\n {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"}
|
config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ASRForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"model_type": "qwen3_asr",
|
| 7 |
+
"support_languages": [
|
| 8 |
+
"Chinese",
|
| 9 |
+
"English",
|
| 10 |
+
"Cantonese",
|
| 11 |
+
"Arabic",
|
| 12 |
+
"German",
|
| 13 |
+
"French",
|
| 14 |
+
"Spanish",
|
| 15 |
+
"Portuguese",
|
| 16 |
+
"Indonesian",
|
| 17 |
+
"Italian",
|
| 18 |
+
"Korean",
|
| 19 |
+
"Russian",
|
| 20 |
+
"Thai",
|
| 21 |
+
"Vietnamese",
|
| 22 |
+
"Japanese",
|
| 23 |
+
"Turkish",
|
| 24 |
+
"Hindi",
|
| 25 |
+
"Malay",
|
| 26 |
+
"Dutch",
|
| 27 |
+
"Swedish",
|
| 28 |
+
"Danish",
|
| 29 |
+
"Finnish",
|
| 30 |
+
"Polish",
|
| 31 |
+
"Czech",
|
| 32 |
+
"Filipino",
|
| 33 |
+
"Persian",
|
| 34 |
+
"Greek",
|
| 35 |
+
"Romanian",
|
| 36 |
+
"Hungarian",
|
| 37 |
+
"Macedonian"
|
| 38 |
+
],
|
| 39 |
+
"thinker_config": {
|
| 40 |
+
"architectures": [
|
| 41 |
+
"Qwen3ASRForConditionalGeneration"
|
| 42 |
+
],
|
| 43 |
+
"audio_config": {
|
| 44 |
+
"_name_or_path": "",
|
| 45 |
+
"activation_dropout": 0,
|
| 46 |
+
"activation_function": "gelu",
|
| 47 |
+
"add_cross_attention": false,
|
| 48 |
+
"architectures": null,
|
| 49 |
+
"attention_dropout": 0,
|
| 50 |
+
"bad_words_ids": null,
|
| 51 |
+
"begin_suppress_tokens": null,
|
| 52 |
+
"bos_token_id": null,
|
| 53 |
+
"chunk_size_feed_forward": 0,
|
| 54 |
+
"conv_chunksize": 500,
|
| 55 |
+
"cross_attention_hidden_size": null,
|
| 56 |
+
"d_model": 1024,
|
| 57 |
+
"decoder_start_token_id": null,
|
| 58 |
+
"diversity_penalty": 0.0,
|
| 59 |
+
"do_sample": false,
|
| 60 |
+
"downsample_hidden_size": 480,
|
| 61 |
+
"dropout": 0,
|
| 62 |
+
"dtype": null,
|
| 63 |
+
"early_stopping": false,
|
| 64 |
+
"encoder_attention_heads": 16,
|
| 65 |
+
"encoder_ffn_dim": 4096,
|
| 66 |
+
"encoder_layers": 24,
|
| 67 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 68 |
+
"eos_token_id": null,
|
| 69 |
+
"exponential_decay_length_penalty": null,
|
| 70 |
+
"finetuning_task": null,
|
| 71 |
+
"forced_bos_token_id": null,
|
| 72 |
+
"forced_eos_token_id": null,
|
| 73 |
+
"id2label": {
|
| 74 |
+
"0": "LABEL_0",
|
| 75 |
+
"1": "LABEL_1"
|
| 76 |
+
},
|
| 77 |
+
"initializer_range": 0.02,
|
| 78 |
+
"is_decoder": false,
|
| 79 |
+
"is_encoder_decoder": false,
|
| 80 |
+
"label2id": {
|
| 81 |
+
"LABEL_0": 0,
|
| 82 |
+
"LABEL_1": 1
|
| 83 |
+
},
|
| 84 |
+
"length_penalty": 1.0,
|
| 85 |
+
"max_length": 20,
|
| 86 |
+
"max_source_positions": 1500,
|
| 87 |
+
"min_length": 0,
|
| 88 |
+
"model_type": "qwen3_asr_audio_encoder",
|
| 89 |
+
"n_window": 50,
|
| 90 |
+
"n_window_infer": 800,
|
| 91 |
+
"no_repeat_ngram_size": 0,
|
| 92 |
+
"num_beam_groups": 1,
|
| 93 |
+
"num_beams": 1,
|
| 94 |
+
"num_hidden_layers": 24,
|
| 95 |
+
"num_mel_bins": 128,
|
| 96 |
+
"num_return_sequences": 1,
|
| 97 |
+
"output_attentions": false,
|
| 98 |
+
"output_dim": 2048,
|
| 99 |
+
"output_hidden_states": false,
|
| 100 |
+
"output_scores": false,
|
| 101 |
+
"pad_token_id": null,
|
| 102 |
+
"prefix": null,
|
| 103 |
+
"problem_type": null,
|
| 104 |
+
"pruned_heads": {},
|
| 105 |
+
"remove_invalid_values": false,
|
| 106 |
+
"repetition_penalty": 1.0,
|
| 107 |
+
"return_dict": true,
|
| 108 |
+
"return_dict_in_generate": false,
|
| 109 |
+
"scale_embedding": false,
|
| 110 |
+
"sep_token_id": null,
|
| 111 |
+
"suppress_tokens": null,
|
| 112 |
+
"task_specific_params": null,
|
| 113 |
+
"temperature": 1.0,
|
| 114 |
+
"tf_legacy_loss": false,
|
| 115 |
+
"tie_encoder_decoder": false,
|
| 116 |
+
"tie_word_embeddings": true,
|
| 117 |
+
"tokenizer_class": null,
|
| 118 |
+
"top_k": 50,
|
| 119 |
+
"top_p": 1.0,
|
| 120 |
+
"torchscript": false,
|
| 121 |
+
"typical_p": 1.0,
|
| 122 |
+
"use_bfloat16": false
|
| 123 |
+
},
|
| 124 |
+
"audio_end_token_id": 151670,
|
| 125 |
+
"audio_start_token_id": 151669,
|
| 126 |
+
"audio_token_id": 151676,
|
| 127 |
+
"dtype": "bfloat16",
|
| 128 |
+
"initializer_range": 0.02,
|
| 129 |
+
"model_type": "qwen3_asr_thinker",
|
| 130 |
+
"text_config": {
|
| 131 |
+
"_name_or_path": "",
|
| 132 |
+
"add_cross_attention": false,
|
| 133 |
+
"architectures": null,
|
| 134 |
+
"attention_bias": false,
|
| 135 |
+
"attention_dropout": 0.0,
|
| 136 |
+
"bad_words_ids": null,
|
| 137 |
+
"begin_suppress_tokens": null,
|
| 138 |
+
"bos_token_id": null,
|
| 139 |
+
"chunk_size_feed_forward": 0,
|
| 140 |
+
"cross_attention_hidden_size": null,
|
| 141 |
+
"decoder_start_token_id": null,
|
| 142 |
+
"diversity_penalty": 0.0,
|
| 143 |
+
"do_sample": false,
|
| 144 |
+
"dtype": null,
|
| 145 |
+
"early_stopping": false,
|
| 146 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 147 |
+
"eos_token_id": null,
|
| 148 |
+
"exponential_decay_length_penalty": null,
|
| 149 |
+
"finetuning_task": null,
|
| 150 |
+
"forced_bos_token_id": null,
|
| 151 |
+
"forced_eos_token_id": null,
|
| 152 |
+
"head_dim": 128,
|
| 153 |
+
"hidden_act": "silu",
|
| 154 |
+
"hidden_size": 2048,
|
| 155 |
+
"id2label": {
|
| 156 |
+
"0": "LABEL_0",
|
| 157 |
+
"1": "LABEL_1"
|
| 158 |
+
},
|
| 159 |
+
"initializer_range": 0.02,
|
| 160 |
+
"intermediate_size": 6144,
|
| 161 |
+
"is_decoder": false,
|
| 162 |
+
"is_encoder_decoder": false,
|
| 163 |
+
"label2id": {
|
| 164 |
+
"LABEL_0": 0,
|
| 165 |
+
"LABEL_1": 1
|
| 166 |
+
},
|
| 167 |
+
"length_penalty": 1.0,
|
| 168 |
+
"max_length": 20,
|
| 169 |
+
"max_position_embeddings": 65536,
|
| 170 |
+
"min_length": 0,
|
| 171 |
+
"model_type": "qwen3_asr_text",
|
| 172 |
+
"no_repeat_ngram_size": 0,
|
| 173 |
+
"num_attention_heads": 16,
|
| 174 |
+
"num_beam_groups": 1,
|
| 175 |
+
"num_beams": 1,
|
| 176 |
+
"num_hidden_layers": 28,
|
| 177 |
+
"num_key_value_heads": 8,
|
| 178 |
+
"num_return_sequences": 1,
|
| 179 |
+
"output_attentions": false,
|
| 180 |
+
"output_hidden_states": false,
|
| 181 |
+
"output_scores": false,
|
| 182 |
+
"pad_token_id": null,
|
| 183 |
+
"prefix": null,
|
| 184 |
+
"problem_type": null,
|
| 185 |
+
"pruned_heads": {},
|
| 186 |
+
"remove_invalid_values": false,
|
| 187 |
+
"repetition_penalty": 1.0,
|
| 188 |
+
"return_dict": true,
|
| 189 |
+
"return_dict_in_generate": false,
|
| 190 |
+
"rms_norm_eps": 1e-06,
|
| 191 |
+
"rope_scaling": {
|
| 192 |
+
"interleaved": true,
|
| 193 |
+
"mrope_interleaved": true,
|
| 194 |
+
"mrope_section": [
|
| 195 |
+
24,
|
| 196 |
+
20,
|
| 197 |
+
20
|
| 198 |
+
],
|
| 199 |
+
"rope_type": "default",
|
| 200 |
+
"type": "default"
|
| 201 |
+
},
|
| 202 |
+
"rope_theta": 1000000,
|
| 203 |
+
"sep_token_id": null,
|
| 204 |
+
"suppress_tokens": null,
|
| 205 |
+
"task_specific_params": null,
|
| 206 |
+
"temperature": 1.0,
|
| 207 |
+
"tf_legacy_loss": false,
|
| 208 |
+
"tie_encoder_decoder": false,
|
| 209 |
+
"tie_word_embeddings": true,
|
| 210 |
+
"tokenizer_class": null,
|
| 211 |
+
"top_k": 50,
|
| 212 |
+
"top_p": 1.0,
|
| 213 |
+
"torchscript": false,
|
| 214 |
+
"typical_p": 1.0,
|
| 215 |
+
"use_bfloat16": false,
|
| 216 |
+
"use_cache": true,
|
| 217 |
+
"vocab_size": 151936
|
| 218 |
+
},
|
| 219 |
+
"user_token_id": 872
|
| 220 |
+
},
|
| 221 |
+
"transformers_version": "4.57.6"
|
| 222 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151643,
|
| 5 |
+
151645
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"transformers_version": "4.57.6"
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ff6bd50201fc8df494d2f6b2b7c559eabbdc8510f0618d78d7c0ec8949c1e0
|
| 3 |
+
size 4076191640
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,715 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"format": "pt"
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"thinker.audio_tower.conv2d1.bias": "model-00001-of-00002.safetensors",
|
| 7 |
+
"thinker.audio_tower.conv2d1.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"thinker.audio_tower.conv2d2.bias": "model-00001-of-00002.safetensors",
|
| 9 |
+
"thinker.audio_tower.conv2d2.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"thinker.audio_tower.conv2d3.bias": "model-00001-of-00002.safetensors",
|
| 11 |
+
"thinker.audio_tower.conv2d3.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"thinker.audio_tower.conv_out.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"thinker.audio_tower.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"thinker.audio_tower.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"thinker.audio_tower.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
|
| 16 |
+
"thinker.audio_tower.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"thinker.audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"thinker.audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"thinker.audio_tower.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"thinker.audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"thinker.audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 22 |
+
"thinker.audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"thinker.audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 24 |
+
"thinker.audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"thinker.audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"thinker.audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"thinker.audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 28 |
+
"thinker.audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"thinker.audio_tower.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"thinker.audio_tower.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"thinker.audio_tower.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
|
| 32 |
+
"thinker.audio_tower.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"thinker.audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 34 |
+
"thinker.audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"thinker.audio_tower.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 36 |
+
"thinker.audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"thinker.audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"thinker.audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"thinker.audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"thinker.audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"thinker.audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"thinker.audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"thinker.audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"thinker.audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"thinker.audio_tower.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
|
| 46 |
+
"thinker.audio_tower.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"thinker.audio_tower.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
|
| 48 |
+
"thinker.audio_tower.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"thinker.audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"thinker.audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"thinker.audio_tower.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"thinker.audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"thinker.audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"thinker.audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"thinker.audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 56 |
+
"thinker.audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"thinker.audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 58 |
+
"thinker.audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"thinker.audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 60 |
+
"thinker.audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"thinker.audio_tower.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"thinker.audio_tower.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"thinker.audio_tower.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"thinker.audio_tower.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"thinker.audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"thinker.audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"thinker.audio_tower.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"thinker.audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"thinker.audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 70 |
+
"thinker.audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"thinker.audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 72 |
+
"thinker.audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"thinker.audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"thinker.audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"thinker.audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"thinker.audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"thinker.audio_tower.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"thinker.audio_tower.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"thinker.audio_tower.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"thinker.audio_tower.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"thinker.audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 82 |
+
"thinker.audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"thinker.audio_tower.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 84 |
+
"thinker.audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"thinker.audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"thinker.audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"thinker.audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 88 |
+
"thinker.audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"thinker.audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"thinker.audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"thinker.audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"thinker.audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"thinker.audio_tower.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
|
| 94 |
+
"thinker.audio_tower.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"thinker.audio_tower.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
|
| 96 |
+
"thinker.audio_tower.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"thinker.audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"thinker.audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"thinker.audio_tower.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"thinker.audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"thinker.audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"thinker.audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"thinker.audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"thinker.audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"thinker.audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 106 |
+
"thinker.audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"thinker.audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 108 |
+
"thinker.audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"thinker.audio_tower.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"thinker.audio_tower.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"thinker.audio_tower.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"thinker.audio_tower.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"thinker.audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"thinker.audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"thinker.audio_tower.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"thinker.audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"thinker.audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"thinker.audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"thinker.audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 120 |
+
"thinker.audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"thinker.audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"thinker.audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"thinker.audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 124 |
+
"thinker.audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"thinker.audio_tower.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"thinker.audio_tower.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"thinker.audio_tower.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"thinker.audio_tower.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"thinker.audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 130 |
+
"thinker.audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"thinker.audio_tower.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 132 |
+
"thinker.audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"thinker.audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"thinker.audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"thinker.audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
+
"thinker.audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"thinker.audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"thinker.audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"thinker.audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"thinker.audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"thinker.audio_tower.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
|
| 142 |
+
"thinker.audio_tower.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"thinker.audio_tower.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
|
| 144 |
+
"thinker.audio_tower.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"thinker.audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"thinker.audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"thinker.audio_tower.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 148 |
+
"thinker.audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"thinker.audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 150 |
+
"thinker.audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"thinker.audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"thinker.audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"thinker.audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 154 |
+
"thinker.audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"thinker.audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 156 |
+
"thinker.audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"thinker.audio_tower.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"thinker.audio_tower.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"thinker.audio_tower.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"thinker.audio_tower.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"thinker.audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"thinker.audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"thinker.audio_tower.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"thinker.audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"thinker.audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 166 |
+
"thinker.audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"thinker.audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 168 |
+
"thinker.audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"thinker.audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"thinker.audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"thinker.audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 172 |
+
"thinker.audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"thinker.audio_tower.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
|
| 174 |
+
"thinker.audio_tower.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"thinker.audio_tower.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
|
| 176 |
+
"thinker.audio_tower.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"thinker.audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 178 |
+
"thinker.audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"thinker.audio_tower.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 180 |
+
"thinker.audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"thinker.audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"thinker.audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"thinker.audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 184 |
+
"thinker.audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"thinker.audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 186 |
+
"thinker.audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"thinker.audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"thinker.audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"thinker.audio_tower.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
|
| 190 |
+
"thinker.audio_tower.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"thinker.audio_tower.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
|
| 192 |
+
"thinker.audio_tower.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"thinker.audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 194 |
+
"thinker.audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"thinker.audio_tower.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 196 |
+
"thinker.audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"thinker.audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"thinker.audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"thinker.audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"thinker.audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"thinker.audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 202 |
+
"thinker.audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"thinker.audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 204 |
+
"thinker.audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"thinker.audio_tower.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
|
| 206 |
+
"thinker.audio_tower.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"thinker.audio_tower.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
|
| 208 |
+
"thinker.audio_tower.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"thinker.audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"thinker.audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"thinker.audio_tower.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"thinker.audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"thinker.audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 214 |
+
"thinker.audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"thinker.audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 216 |
+
"thinker.audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"thinker.audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 218 |
+
"thinker.audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"thinker.audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"thinker.audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"thinker.audio_tower.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"thinker.audio_tower.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"thinker.audio_tower.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"thinker.audio_tower.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"thinker.audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 226 |
+
"thinker.audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"thinker.audio_tower.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 228 |
+
"thinker.audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"thinker.audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 230 |
+
"thinker.audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"thinker.audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 232 |
+
"thinker.audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"thinker.audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"thinker.audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"thinker.audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 236 |
+
"thinker.audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"thinker.audio_tower.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
|
| 238 |
+
"thinker.audio_tower.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"thinker.audio_tower.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
|
| 240 |
+
"thinker.audio_tower.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"thinker.audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 242 |
+
"thinker.audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"thinker.audio_tower.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
+
"thinker.audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"thinker.audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"thinker.audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"thinker.audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"thinker.audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"thinker.audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 250 |
+
"thinker.audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"thinker.audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"thinker.audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"thinker.audio_tower.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"thinker.audio_tower.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"thinker.audio_tower.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"thinker.audio_tower.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"thinker.audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"thinker.audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"thinker.audio_tower.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"thinker.audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"thinker.audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"thinker.audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"thinker.audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"thinker.audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"thinker.audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"thinker.audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"thinker.audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"thinker.audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"thinker.audio_tower.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"thinker.audio_tower.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"thinker.audio_tower.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"thinker.audio_tower.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"thinker.audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"thinker.audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"thinker.audio_tower.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 276 |
+
"thinker.audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"thinker.audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"thinker.audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"thinker.audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 280 |
+
"thinker.audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"thinker.audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"thinker.audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"thinker.audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"thinker.audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"thinker.audio_tower.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"thinker.audio_tower.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"thinker.audio_tower.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"thinker.audio_tower.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"thinker.audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"thinker.audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"thinker.audio_tower.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"thinker.audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"thinker.audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"thinker.audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"thinker.audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"thinker.audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"thinker.audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 298 |
+
"thinker.audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"thinker.audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 300 |
+
"thinker.audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"thinker.audio_tower.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"thinker.audio_tower.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"thinker.audio_tower.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
|
| 304 |
+
"thinker.audio_tower.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"thinker.audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"thinker.audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"thinker.audio_tower.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"thinker.audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"thinker.audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 310 |
+
"thinker.audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"thinker.audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 312 |
+
"thinker.audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"thinker.audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"thinker.audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"thinker.audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 316 |
+
"thinker.audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"thinker.audio_tower.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"thinker.audio_tower.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"thinker.audio_tower.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"thinker.audio_tower.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"thinker.audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 322 |
+
"thinker.audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"thinker.audio_tower.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 324 |
+
"thinker.audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"thinker.audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"thinker.audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"thinker.audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 328 |
+
"thinker.audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"thinker.audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 330 |
+
"thinker.audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"thinker.audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"thinker.audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"thinker.audio_tower.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
|
| 334 |
+
"thinker.audio_tower.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"thinker.audio_tower.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
|
| 336 |
+
"thinker.audio_tower.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"thinker.audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"thinker.audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"thinker.audio_tower.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 340 |
+
"thinker.audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"thinker.audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"thinker.audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"thinker.audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"thinker.audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"thinker.audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 346 |
+
"thinker.audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"thinker.audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 348 |
+
"thinker.audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"thinker.audio_tower.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
|
| 350 |
+
"thinker.audio_tower.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"thinker.audio_tower.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
|
| 352 |
+
"thinker.audio_tower.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"thinker.audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 354 |
+
"thinker.audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"thinker.audio_tower.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 356 |
+
"thinker.audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"thinker.audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 358 |
+
"thinker.audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"thinker.audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 360 |
+
"thinker.audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"thinker.audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 362 |
+
"thinker.audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"thinker.audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 364 |
+
"thinker.audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"thinker.audio_tower.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
|
| 366 |
+
"thinker.audio_tower.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"thinker.audio_tower.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
|
| 368 |
+
"thinker.audio_tower.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"thinker.audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 370 |
+
"thinker.audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"thinker.audio_tower.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 372 |
+
"thinker.audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"thinker.audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 374 |
+
"thinker.audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"thinker.audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"thinker.audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"thinker.audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"thinker.audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"thinker.audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"thinker.audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"thinker.audio_tower.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
|
| 382 |
+
"thinker.audio_tower.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"thinker.audio_tower.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"thinker.audio_tower.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"thinker.audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"thinker.audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"thinker.audio_tower.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"thinker.audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"thinker.audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"thinker.audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"thinker.audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"thinker.audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"thinker.audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"thinker.audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"thinker.audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"thinker.audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"thinker.audio_tower.ln_post.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"thinker.audio_tower.ln_post.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"thinker.audio_tower.proj1.bias": "model-00001-of-00002.safetensors",
|
| 400 |
+
"thinker.audio_tower.proj1.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"thinker.audio_tower.proj2.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"thinker.audio_tower.proj2.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"thinker.lm_head.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"thinker.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"thinker.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"thinker.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"thinker.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"thinker.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"thinker.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"thinker.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"thinker.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"thinker.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"thinker.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"thinker.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"thinker.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"thinker.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"thinker.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"thinker.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"thinker.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"thinker.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"thinker.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"thinker.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"thinker.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"thinker.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"thinker.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"thinker.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"thinker.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"thinker.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"thinker.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"thinker.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"thinker.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"thinker.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"thinker.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"thinker.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"thinker.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"thinker.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"thinker.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"thinker.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"thinker.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"thinker.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"thinker.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"thinker.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"thinker.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"thinker.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"thinker.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"thinker.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"thinker.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"thinker.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"thinker.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"thinker.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"thinker.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"thinker.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"thinker.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"thinker.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"thinker.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"thinker.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"thinker.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"thinker.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 459 |
+
"thinker.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"thinker.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 461 |
+
"thinker.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"thinker.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 463 |
+
"thinker.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"thinker.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"thinker.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"thinker.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 467 |
+
"thinker.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"thinker.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 469 |
+
"thinker.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"thinker.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"thinker.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"thinker.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 473 |
+
"thinker.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"thinker.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"thinker.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"thinker.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 477 |
+
"thinker.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"thinker.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 479 |
+
"thinker.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"thinker.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 481 |
+
"thinker.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"thinker.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 483 |
+
"thinker.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"thinker.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 485 |
+
"thinker.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"thinker.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 487 |
+
"thinker.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"thinker.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 489 |
+
"thinker.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"thinker.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"thinker.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"thinker.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 493 |
+
"thinker.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"thinker.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 495 |
+
"thinker.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"thinker.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"thinker.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"thinker.model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 499 |
+
"thinker.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"thinker.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"thinker.model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"thinker.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 503 |
+
"thinker.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"thinker.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 505 |
+
"thinker.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"thinker.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 507 |
+
"thinker.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"thinker.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 509 |
+
"thinker.model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"thinker.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 511 |
+
"thinker.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"thinker.model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 513 |
+
"thinker.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"thinker.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 515 |
+
"thinker.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"thinker.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"thinker.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"thinker.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 519 |
+
"thinker.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"thinker.model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 521 |
+
"thinker.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"thinker.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"thinker.model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"thinker.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 525 |
+
"thinker.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"thinker.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"thinker.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"thinker.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 529 |
+
"thinker.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"thinker.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 531 |
+
"thinker.model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"thinker.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 533 |
+
"thinker.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"thinker.model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 535 |
+
"thinker.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"thinker.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 537 |
+
"thinker.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"thinker.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 539 |
+
"thinker.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"thinker.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 541 |
+
"thinker.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"thinker.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"thinker.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"thinker.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 545 |
+
"thinker.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"thinker.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 547 |
+
"thinker.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"thinker.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"thinker.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"thinker.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 551 |
+
"thinker.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"thinker.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"thinker.model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"thinker.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 555 |
+
"thinker.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"thinker.model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 557 |
+
"thinker.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"thinker.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 559 |
+
"thinker.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"thinker.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 561 |
+
"thinker.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"thinker.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 563 |
+
"thinker.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"thinker.model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 565 |
+
"thinker.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"thinker.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 567 |
+
"thinker.model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"thinker.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"thinker.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"thinker.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 571 |
+
"thinker.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"thinker.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 573 |
+
"thinker.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"thinker.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"thinker.model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"thinker.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 577 |
+
"thinker.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"thinker.model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"thinker.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"thinker.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 581 |
+
"thinker.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"thinker.model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 583 |
+
"thinker.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"thinker.model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 585 |
+
"thinker.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"thinker.model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 587 |
+
"thinker.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"thinker.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 589 |
+
"thinker.model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"thinker.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 591 |
+
"thinker.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"thinker.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 593 |
+
"thinker.model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"thinker.model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"thinker.model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"thinker.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 597 |
+
"thinker.model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"thinker.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 599 |
+
"thinker.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"thinker.model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"thinker.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"thinker.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 603 |
+
"thinker.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"thinker.model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"thinker.model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"thinker.model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 607 |
+
"thinker.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"thinker.model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 609 |
+
"thinker.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"thinker.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 611 |
+
"thinker.model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"thinker.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 613 |
+
"thinker.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"thinker.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 615 |
+
"thinker.model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"thinker.model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 617 |
+
"thinker.model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"thinker.model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 619 |
+
"thinker.model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"thinker.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"thinker.model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"thinker.model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 623 |
+
"thinker.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"thinker.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 625 |
+
"thinker.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"thinker.model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"thinker.model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"thinker.model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 629 |
+
"thinker.model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"thinker.model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"thinker.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"thinker.model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 633 |
+
"thinker.model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"thinker.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 635 |
+
"thinker.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"thinker.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 637 |
+
"thinker.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"thinker.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 639 |
+
"thinker.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"thinker.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 641 |
+
"thinker.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"thinker.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 643 |
+
"thinker.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"thinker.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 645 |
+
"thinker.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"thinker.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"thinker.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"thinker.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 649 |
+
"thinker.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"thinker.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 651 |
+
"thinker.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"thinker.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"thinker.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"thinker.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 655 |
+
"thinker.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"thinker.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"thinker.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"thinker.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 659 |
+
"thinker.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"thinker.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 661 |
+
"thinker.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 662 |
+
"thinker.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 663 |
+
"thinker.model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 664 |
+
"thinker.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 665 |
+
"thinker.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 666 |
+
"thinker.model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 667 |
+
"thinker.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 668 |
+
"thinker.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 669 |
+
"thinker.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 670 |
+
"thinker.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 671 |
+
"thinker.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 672 |
+
"thinker.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 673 |
+
"thinker.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 674 |
+
"thinker.model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 675 |
+
"thinker.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 676 |
+
"thinker.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 677 |
+
"thinker.model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 678 |
+
"thinker.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 679 |
+
"thinker.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 680 |
+
"thinker.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 681 |
+
"thinker.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 682 |
+
"thinker.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 683 |
+
"thinker.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 684 |
+
"thinker.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 685 |
+
"thinker.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 686 |
+
"thinker.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 687 |
+
"thinker.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 688 |
+
"thinker.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 689 |
+
"thinker.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 690 |
+
"thinker.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 691 |
+
"thinker.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 692 |
+
"thinker.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 693 |
+
"thinker.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 694 |
+
"thinker.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 695 |
+
"thinker.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 696 |
+
"thinker.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 697 |
+
"thinker.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 698 |
+
"thinker.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 699 |
+
"thinker.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 700 |
+
"thinker.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 701 |
+
"thinker.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 702 |
+
"thinker.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 703 |
+
"thinker.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 704 |
+
"thinker.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 705 |
+
"thinker.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 706 |
+
"thinker.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 707 |
+
"thinker.model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 708 |
+
"thinker.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 709 |
+
"thinker.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 710 |
+
"thinker.model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 711 |
+
"thinker.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 712 |
+
"thinker.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 713 |
+
"thinker.model.norm.weight": "model-00002-of-00002.safetensors"
|
| 714 |
+
}
|
| 715 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 128,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "Qwen3ASRProcessor",
|
| 13 |
+
"return_attention_mask": true
|
| 14 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
|
| 3 |
+
size 14645
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>",
|
| 16 |
+
"<|audio_start|>",
|
| 17 |
+
"<|audio_end|>",
|
| 18 |
+
"<tts_pad>",
|
| 19 |
+
"<tts_text_bos>",
|
| 20 |
+
"<tts_text_bos_single>",
|
| 21 |
+
"<|audio_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"audio_bos_token": "<|audio_start|>",
|
| 24 |
+
"audio_eos_token": "<|audio_end|>",
|
| 25 |
+
"audio_token": "<|audio_pad|>",
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|im_end|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"image_token": "<|image_pad|>",
|
| 34 |
+
"pad_token": {
|
| 35 |
+
"content": "<|endoftext|>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false
|
| 40 |
+
},
|
| 41 |
+
"video_token": "<|video_pad|>",
|
| 42 |
+
"vision_bos_token": "<|vision_start|>",
|
| 43 |
+
"vision_eos_token": "<|vision_end|>"
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd2a97b55c8f7f9c328c73ee9b9178771037e9f566dfca8e238a063d41cbac92
|
| 3 |
+
size 11429377
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,549 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"151669": {
|
| 214 |
+
"content": "<|audio_start|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"151670": {
|
| 222 |
+
"content": "<|audio_end|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"151671": {
|
| 230 |
+
"content": "<tts_pad>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"151672": {
|
| 238 |
+
"content": "<tts_text_bos>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"151673": {
|
| 246 |
+
"content": "<tts_text_eod>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"151674": {
|
| 254 |
+
"content": "<tts_text_bos_single>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"151675": {
|
| 262 |
+
"content": "<non_speech>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"151676": {
|
| 270 |
+
"content": "<|audio_pad|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"151677": {
|
| 278 |
+
"content": "<blank1>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"151678": {
|
| 286 |
+
"content": "<blank2>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"151679": {
|
| 294 |
+
"content": "<blank3>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"151680": {
|
| 302 |
+
"content": "<blank4>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"151681": {
|
| 310 |
+
"content": "<blank5>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"151682": {
|
| 318 |
+
"content": "<blank6>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"151683": {
|
| 326 |
+
"content": "<blank7>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
},
|
| 333 |
+
"151684": {
|
| 334 |
+
"content": "<blank8>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": true
|
| 340 |
+
},
|
| 341 |
+
"151685": {
|
| 342 |
+
"content": "<blank9>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": true
|
| 348 |
+
},
|
| 349 |
+
"151686": {
|
| 350 |
+
"content": "<blank10>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"151687": {
|
| 358 |
+
"content": "<blank11>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"151688": {
|
| 366 |
+
"content": "<blank12>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"151689": {
|
| 374 |
+
"content": "<blank13>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"151690": {
|
| 382 |
+
"content": "<blank14>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"151691": {
|
| 390 |
+
"content": "<blank15>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"151692": {
|
| 398 |
+
"content": "<blank16>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"151693": {
|
| 406 |
+
"content": "<blank17>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"151694": {
|
| 414 |
+
"content": "<blank18>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"151695": {
|
| 422 |
+
"content": "<blank19>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"151696": {
|
| 430 |
+
"content": "<blank20>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"151697": {
|
| 438 |
+
"content": "<blank21>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"151698": {
|
| 446 |
+
"content": "<blank22>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"151699": {
|
| 454 |
+
"content": "<blank23>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"151700": {
|
| 462 |
+
"content": "<blank24>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
},
|
| 469 |
+
"151701": {
|
| 470 |
+
"content": "<blank25>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": true
|
| 476 |
+
},
|
| 477 |
+
"151702": {
|
| 478 |
+
"content": "<blank26>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": true
|
| 484 |
+
},
|
| 485 |
+
"151703": {
|
| 486 |
+
"content": "<blank27>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": true
|
| 492 |
+
},
|
| 493 |
+
"151704": {
|
| 494 |
+
"content": "<asr_text>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
}
|
| 501 |
+
},
|
| 502 |
+
"additional_special_tokens": [
|
| 503 |
+
"<|im_start|>",
|
| 504 |
+
"<|im_end|>",
|
| 505 |
+
"<|object_ref_start|>",
|
| 506 |
+
"<|object_ref_end|>",
|
| 507 |
+
"<|box_start|>",
|
| 508 |
+
"<|box_end|>",
|
| 509 |
+
"<|quad_start|>",
|
| 510 |
+
"<|quad_end|>",
|
| 511 |
+
"<|vision_start|>",
|
| 512 |
+
"<|vision_end|>",
|
| 513 |
+
"<|vision_pad|>",
|
| 514 |
+
"<|image_pad|>",
|
| 515 |
+
"<|video_pad|>",
|
| 516 |
+
"<|audio_start|>",
|
| 517 |
+
"<|audio_end|>",
|
| 518 |
+
"<tts_pad>",
|
| 519 |
+
"<tts_text_bos>",
|
| 520 |
+
"<tts_text_bos_single>",
|
| 521 |
+
"<|audio_pad|>"
|
| 522 |
+
],
|
| 523 |
+
"audio_bos_token": "<|audio_start|>",
|
| 524 |
+
"audio_eos_token": "<|audio_end|>",
|
| 525 |
+
"audio_token": "<|audio_pad|>",
|
| 526 |
+
"bos_token": null,
|
| 527 |
+
"clean_up_tokenization_spaces": false,
|
| 528 |
+
"eos_token": "<|im_end|>",
|
| 529 |
+
"errors": "replace",
|
| 530 |
+
"extra_special_tokens": {
|
| 531 |
+
"audio_bos_token": "<|audio_start|>",
|
| 532 |
+
"audio_eos_token": "<|audio_end|>",
|
| 533 |
+
"audio_token": "<|audio_pad|>",
|
| 534 |
+
"image_token": "<|image_pad|>",
|
| 535 |
+
"video_token": "<|video_pad|>",
|
| 536 |
+
"vision_bos_token": "<|vision_start|>",
|
| 537 |
+
"vision_eos_token": "<|vision_end|>"
|
| 538 |
+
},
|
| 539 |
+
"image_token": "<|image_pad|>",
|
| 540 |
+
"model_max_length": 131072,
|
| 541 |
+
"pad_token": "<|endoftext|>",
|
| 542 |
+
"processor_class": "Qwen3ASRProcessor",
|
| 543 |
+
"split_special_tokens": false,
|
| 544 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 545 |
+
"unk_token": null,
|
| 546 |
+
"video_token": "<|video_pad|>",
|
| 547 |
+
"vision_bos_token": "<|vision_start|>",
|
| 548 |
+
"vision_eos_token": "<|vision_end|>"
|
| 549 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 200,
|
| 7 |
+
"global_step": 14934,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.040176777822418644,
|
| 14 |
+
"grad_norm": 178.0,
|
| 15 |
+
"learning_rate": 7.991967871485945e-06,
|
| 16 |
+
"loss": 13.2817,
|
| 17 |
+
"step": 200
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.040176777822418644,
|
| 21 |
+
"eval_loss": 2.0163986682891846,
|
| 22 |
+
"eval_runtime": 51.4206,
|
| 23 |
+
"eval_samples_per_second": 38.156,
|
| 24 |
+
"eval_steps_per_second": 4.784,
|
| 25 |
+
"step": 200
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.08035355564483729,
|
| 29 |
+
"grad_norm": 11.5625,
|
| 30 |
+
"learning_rate": 1.602409638554217e-05,
|
| 31 |
+
"loss": 1.3221,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08035355564483729,
|
| 36 |
+
"eval_loss": 0.5200865864753723,
|
| 37 |
+
"eval_runtime": 40.2594,
|
| 38 |
+
"eval_samples_per_second": 48.734,
|
| 39 |
+
"eval_steps_per_second": 6.11,
|
| 40 |
+
"step": 400
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.12053033346725593,
|
| 44 |
+
"grad_norm": 10.6875,
|
| 45 |
+
"learning_rate": 2.4056224899598397e-05,
|
| 46 |
+
"loss": 0.6527,
|
| 47 |
+
"step": 600
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.12053033346725593,
|
| 51 |
+
"eval_loss": 0.4557928740978241,
|
| 52 |
+
"eval_runtime": 40.4333,
|
| 53 |
+
"eval_samples_per_second": 48.524,
|
| 54 |
+
"eval_steps_per_second": 6.084,
|
| 55 |
+
"step": 600
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.16070711128967458,
|
| 59 |
+
"grad_norm": 10.25,
|
| 60 |
+
"learning_rate": 3.208835341365462e-05,
|
| 61 |
+
"loss": 0.6243,
|
| 62 |
+
"step": 800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.16070711128967458,
|
| 66 |
+
"eval_loss": 0.4576485753059387,
|
| 67 |
+
"eval_runtime": 40.2178,
|
| 68 |
+
"eval_samples_per_second": 48.784,
|
| 69 |
+
"eval_steps_per_second": 6.117,
|
| 70 |
+
"step": 800
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.2008838891120932,
|
| 74 |
+
"grad_norm": 9.5,
|
| 75 |
+
"learning_rate": 4.012048192771085e-05,
|
| 76 |
+
"loss": 0.6059,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.2008838891120932,
|
| 81 |
+
"eval_loss": 0.46009403467178345,
|
| 82 |
+
"eval_runtime": 40.2382,
|
| 83 |
+
"eval_samples_per_second": 48.76,
|
| 84 |
+
"eval_steps_per_second": 6.114,
|
| 85 |
+
"step": 1000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.24106066693451186,
|
| 89 |
+
"grad_norm": 8.625,
|
| 90 |
+
"learning_rate": 4.815261044176707e-05,
|
| 91 |
+
"loss": 0.6171,
|
| 92 |
+
"step": 1200
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.24106066693451186,
|
| 96 |
+
"eval_loss": 0.4689507484436035,
|
| 97 |
+
"eval_runtime": 40.3013,
|
| 98 |
+
"eval_samples_per_second": 48.683,
|
| 99 |
+
"eval_steps_per_second": 6.104,
|
| 100 |
+
"step": 1200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2812374447569305,
|
| 104 |
+
"grad_norm": 9.3125,
|
| 105 |
+
"learning_rate": 4.999476691954866e-05,
|
| 106 |
+
"loss": 0.5954,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2812374447569305,
|
| 111 |
+
"eval_loss": 0.45582765340805054,
|
| 112 |
+
"eval_runtime": 40.6487,
|
| 113 |
+
"eval_samples_per_second": 48.267,
|
| 114 |
+
"eval_steps_per_second": 6.052,
|
| 115 |
+
"step": 1400
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.32141422257934915,
|
| 119 |
+
"grad_norm": 8.75,
|
| 120 |
+
"learning_rate": 4.9972352390837575e-05,
|
| 121 |
+
"loss": 0.585,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.32141422257934915,
|
| 126 |
+
"eval_loss": 0.42706185579299927,
|
| 127 |
+
"eval_runtime": 40.3385,
|
| 128 |
+
"eval_samples_per_second": 48.638,
|
| 129 |
+
"eval_steps_per_second": 6.098,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.3615910004017678,
|
| 134 |
+
"grad_norm": 8.875,
|
| 135 |
+
"learning_rate": 4.993230531719831e-05,
|
| 136 |
+
"loss": 0.5548,
|
| 137 |
+
"step": 1800
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.3615910004017678,
|
| 141 |
+
"eval_loss": 0.4254651367664337,
|
| 142 |
+
"eval_runtime": 40.2971,
|
| 143 |
+
"eval_samples_per_second": 48.688,
|
| 144 |
+
"eval_steps_per_second": 6.105,
|
| 145 |
+
"step": 1800
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.4017677782241864,
|
| 149 |
+
"grad_norm": 11.6875,
|
| 150 |
+
"learning_rate": 4.9874653975175036e-05,
|
| 151 |
+
"loss": 0.5429,
|
| 152 |
+
"step": 2000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.4017677782241864,
|
| 156 |
+
"eval_loss": 0.4014296531677246,
|
| 157 |
+
"eval_runtime": 40.3845,
|
| 158 |
+
"eval_samples_per_second": 48.583,
|
| 159 |
+
"eval_steps_per_second": 6.091,
|
| 160 |
+
"step": 2000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.44194455604660504,
|
| 164 |
+
"grad_norm": 5.875,
|
| 165 |
+
"learning_rate": 4.979943907138049e-05,
|
| 166 |
+
"loss": 0.5137,
|
| 167 |
+
"step": 2200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.44194455604660504,
|
| 171 |
+
"eval_loss": 0.39921146631240845,
|
| 172 |
+
"eval_runtime": 40.1294,
|
| 173 |
+
"eval_samples_per_second": 48.892,
|
| 174 |
+
"eval_steps_per_second": 6.13,
|
| 175 |
+
"step": 2200
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.4821213338690237,
|
| 179 |
+
"grad_norm": 6.34375,
|
| 180 |
+
"learning_rate": 4.97067137137538e-05,
|
| 181 |
+
"loss": 0.5141,
|
| 182 |
+
"step": 2400
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.4821213338690237,
|
| 186 |
+
"eval_loss": 0.3842703700065613,
|
| 187 |
+
"eval_runtime": 40.2191,
|
| 188 |
+
"eval_samples_per_second": 48.783,
|
| 189 |
+
"eval_steps_per_second": 6.116,
|
| 190 |
+
"step": 2400
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.5222981116914424,
|
| 194 |
+
"grad_norm": 11.4375,
|
| 195 |
+
"learning_rate": 4.959654337406187e-05,
|
| 196 |
+
"loss": 0.4953,
|
| 197 |
+
"step": 2600
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.5222981116914424,
|
| 201 |
+
"eval_loss": 0.37524962425231934,
|
| 202 |
+
"eval_runtime": 40.3546,
|
| 203 |
+
"eval_samples_per_second": 48.619,
|
| 204 |
+
"eval_steps_per_second": 6.096,
|
| 205 |
+
"step": 2600
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.562474889513861,
|
| 209 |
+
"grad_norm": 6.3125,
|
| 210 |
+
"learning_rate": 4.946900584167086e-05,
|
| 211 |
+
"loss": 0.4938,
|
| 212 |
+
"step": 2800
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.562474889513861,
|
| 216 |
+
"eval_loss": 0.37083181738853455,
|
| 217 |
+
"eval_runtime": 40.0762,
|
| 218 |
+
"eval_samples_per_second": 48.957,
|
| 219 |
+
"eval_steps_per_second": 6.138,
|
| 220 |
+
"step": 2800
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.6026516673362796,
|
| 224 |
+
"grad_norm": 7.5625,
|
| 225 |
+
"learning_rate": 4.93241911686205e-05,
|
| 226 |
+
"loss": 0.4739,
|
| 227 |
+
"step": 3000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.6026516673362796,
|
| 231 |
+
"eval_loss": 0.3582882583141327,
|
| 232 |
+
"eval_runtime": 40.2624,
|
| 233 |
+
"eval_samples_per_second": 48.73,
|
| 234 |
+
"eval_steps_per_second": 6.11,
|
| 235 |
+
"step": 3000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.6428284451586983,
|
| 239 |
+
"grad_norm": 7.375,
|
| 240 |
+
"learning_rate": 4.916220160603993e-05,
|
| 241 |
+
"loss": 0.4722,
|
| 242 |
+
"step": 3200
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.6428284451586983,
|
| 246 |
+
"eval_loss": 0.3533416986465454,
|
| 247 |
+
"eval_runtime": 40.054,
|
| 248 |
+
"eval_samples_per_second": 48.984,
|
| 249 |
+
"eval_steps_per_second": 6.142,
|
| 250 |
+
"step": 3200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.6830052229811169,
|
| 254 |
+
"grad_norm": 6.3125,
|
| 255 |
+
"learning_rate": 4.89831515319499e-05,
|
| 256 |
+
"loss": 0.4603,
|
| 257 |
+
"step": 3400
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.6830052229811169,
|
| 261 |
+
"eval_loss": 0.3541873097419739,
|
| 262 |
+
"eval_runtime": 40.1148,
|
| 263 |
+
"eval_samples_per_second": 48.91,
|
| 264 |
+
"eval_steps_per_second": 6.132,
|
| 265 |
+
"step": 3400
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.7231820008035356,
|
| 269 |
+
"grad_norm": 7.40625,
|
| 270 |
+
"learning_rate": 4.878716737050246e-05,
|
| 271 |
+
"loss": 0.4417,
|
| 272 |
+
"step": 3600
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.7231820008035356,
|
| 276 |
+
"eval_loss": 0.34198856353759766,
|
| 277 |
+
"eval_runtime": 40.2884,
|
| 278 |
+
"eval_samples_per_second": 48.699,
|
| 279 |
+
"eval_steps_per_second": 6.106,
|
| 280 |
+
"step": 3600
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.7633587786259542,
|
| 284 |
+
"grad_norm": 5.625,
|
| 285 |
+
"learning_rate": 4.8574387502715055e-05,
|
| 286 |
+
"loss": 0.4464,
|
| 287 |
+
"step": 3800
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.7633587786259542,
|
| 291 |
+
"eval_loss": 0.33911019563674927,
|
| 292 |
+
"eval_runtime": 40.2619,
|
| 293 |
+
"eval_samples_per_second": 48.731,
|
| 294 |
+
"eval_steps_per_second": 6.11,
|
| 295 |
+
"step": 3800
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.8035355564483728,
|
| 299 |
+
"grad_norm": 6.4375,
|
| 300 |
+
"learning_rate": 4.8344962168762114e-05,
|
| 301 |
+
"loss": 0.4362,
|
| 302 |
+
"step": 4000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.8035355564483728,
|
| 306 |
+
"eval_loss": 0.3308402895927429,
|
| 307 |
+
"eval_runtime": 40.2069,
|
| 308 |
+
"eval_samples_per_second": 48.798,
|
| 309 |
+
"eval_steps_per_second": 6.118,
|
| 310 |
+
"step": 4000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8437123342707915,
|
| 314 |
+
"grad_norm": 5.90625,
|
| 315 |
+
"learning_rate": 4.8099053361893e-05,
|
| 316 |
+
"loss": 0.4239,
|
| 317 |
+
"step": 4200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8437123342707915,
|
| 321 |
+
"eval_loss": 0.332675039768219,
|
| 322 |
+
"eval_runtime": 40.2019,
|
| 323 |
+
"eval_samples_per_second": 48.804,
|
| 324 |
+
"eval_steps_per_second": 6.119,
|
| 325 |
+
"step": 4200
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8838891120932101,
|
| 329 |
+
"grad_norm": 4.9375,
|
| 330 |
+
"learning_rate": 4.783683471405146e-05,
|
| 331 |
+
"loss": 0.4213,
|
| 332 |
+
"step": 4400
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8838891120932101,
|
| 336 |
+
"eval_loss": 0.32235413789749146,
|
| 337 |
+
"eval_runtime": 40.1595,
|
| 338 |
+
"eval_samples_per_second": 48.855,
|
| 339 |
+
"eval_steps_per_second": 6.126,
|
| 340 |
+
"step": 4400
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.9240658899156288,
|
| 344 |
+
"grad_norm": 5.03125,
|
| 345 |
+
"learning_rate": 4.7558491373277083e-05,
|
| 346 |
+
"loss": 0.4296,
|
| 347 |
+
"step": 4600
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.9240658899156288,
|
| 351 |
+
"eval_loss": 0.31966790556907654,
|
| 352 |
+
"eval_runtime": 40.1565,
|
| 353 |
+
"eval_samples_per_second": 48.859,
|
| 354 |
+
"eval_steps_per_second": 6.126,
|
| 355 |
+
"step": 4600
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.9642426677380475,
|
| 359 |
+
"grad_norm": 5.9375,
|
| 360 |
+
"learning_rate": 4.726421987297549e-05,
|
| 361 |
+
"loss": 0.4089,
|
| 362 |
+
"step": 4800
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.9642426677380475,
|
| 366 |
+
"eval_loss": 0.3144192695617676,
|
| 367 |
+
"eval_runtime": 40.1017,
|
| 368 |
+
"eval_samples_per_second": 48.926,
|
| 369 |
+
"eval_steps_per_second": 6.134,
|
| 370 |
+
"step": 4800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.004419445560466,
|
| 374 |
+
"grad_norm": 5.40625,
|
| 375 |
+
"learning_rate": 4.695422799314949e-05,
|
| 376 |
+
"loss": 0.393,
|
| 377 |
+
"step": 5000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.004419445560466,
|
| 381 |
+
"eval_loss": 0.3213293254375458,
|
| 382 |
+
"eval_runtime": 40.1818,
|
| 383 |
+
"eval_samples_per_second": 48.828,
|
| 384 |
+
"eval_steps_per_second": 6.122,
|
| 385 |
+
"step": 5000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.0445962233828847,
|
| 389 |
+
"grad_norm": 6.375,
|
| 390 |
+
"learning_rate": 4.662873461368926e-05,
|
| 391 |
+
"loss": 0.301,
|
| 392 |
+
"step": 5200
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.0445962233828847,
|
| 396 |
+
"eval_loss": 0.32283082604408264,
|
| 397 |
+
"eval_runtime": 40.071,
|
| 398 |
+
"eval_samples_per_second": 48.963,
|
| 399 |
+
"eval_steps_per_second": 6.139,
|
| 400 |
+
"step": 5200
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.0847730012053034,
|
| 404 |
+
"grad_norm": 4.78125,
|
| 405 |
+
"learning_rate": 4.6287969559824996e-05,
|
| 406 |
+
"loss": 0.2883,
|
| 407 |
+
"step": 5400
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.0847730012053034,
|
| 411 |
+
"eval_loss": 0.32108554244041443,
|
| 412 |
+
"eval_runtime": 39.916,
|
| 413 |
+
"eval_samples_per_second": 49.153,
|
| 414 |
+
"eval_steps_per_second": 6.163,
|
| 415 |
+
"step": 5400
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 1.1249497790277219,
|
| 419 |
+
"grad_norm": 5.125,
|
| 420 |
+
"learning_rate": 4.5932173439851355e-05,
|
| 421 |
+
"loss": 0.29,
|
| 422 |
+
"step": 5600
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.1249497790277219,
|
| 426 |
+
"eval_loss": 0.3121967613697052,
|
| 427 |
+
"eval_runtime": 39.6694,
|
| 428 |
+
"eval_samples_per_second": 49.459,
|
| 429 |
+
"eval_steps_per_second": 6.201,
|
| 430 |
+
"step": 5600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.1651265568501405,
|
| 434 |
+
"grad_norm": 6.03125,
|
| 435 |
+
"learning_rate": 4.5561597475238094e-05,
|
| 436 |
+
"loss": 0.2808,
|
| 437 |
+
"step": 5800
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.1651265568501405,
|
| 441 |
+
"eval_loss": 0.3169782757759094,
|
| 442 |
+
"eval_runtime": 40.1646,
|
| 443 |
+
"eval_samples_per_second": 48.849,
|
| 444 |
+
"eval_steps_per_second": 6.125,
|
| 445 |
+
"step": 5800
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.2053033346725592,
|
| 449 |
+
"grad_norm": 5.4375,
|
| 450 |
+
"learning_rate": 4.517650332324692e-05,
|
| 451 |
+
"loss": 0.2836,
|
| 452 |
+
"step": 6000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.2053033346725592,
|
| 456 |
+
"eval_loss": 0.30975210666656494,
|
| 457 |
+
"eval_runtime": 40.0547,
|
| 458 |
+
"eval_samples_per_second": 48.983,
|
| 459 |
+
"eval_steps_per_second": 6.142,
|
| 460 |
+
"step": 6000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.245480112494978,
|
| 464 |
+
"grad_norm": 6.375,
|
| 465 |
+
"learning_rate": 4.477716289217989e-05,
|
| 466 |
+
"loss": 0.2916,
|
| 467 |
+
"step": 6200
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.245480112494978,
|
| 471 |
+
"eval_loss": 0.30826571583747864,
|
| 472 |
+
"eval_runtime": 40.0909,
|
| 473 |
+
"eval_samples_per_second": 48.939,
|
| 474 |
+
"eval_steps_per_second": 6.136,
|
| 475 |
+
"step": 6200
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.2856568903173966,
|
| 479 |
+
"grad_norm": 4.09375,
|
| 480 |
+
"learning_rate": 4.436385814938962e-05,
|
| 481 |
+
"loss": 0.2819,
|
| 482 |
+
"step": 6400
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.2856568903173966,
|
| 486 |
+
"eval_loss": 0.3041566014289856,
|
| 487 |
+
"eval_runtime": 40.1919,
|
| 488 |
+
"eval_samples_per_second": 48.816,
|
| 489 |
+
"eval_steps_per_second": 6.121,
|
| 490 |
+
"step": 6400
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.3258336681398153,
|
| 494 |
+
"grad_norm": 6.3125,
|
| 495 |
+
"learning_rate": 4.393688092218706e-05,
|
| 496 |
+
"loss": 0.284,
|
| 497 |
+
"step": 6600
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.3258336681398153,
|
| 501 |
+
"eval_loss": 0.30126050114631653,
|
| 502 |
+
"eval_runtime": 39.9508,
|
| 503 |
+
"eval_samples_per_second": 49.11,
|
| 504 |
+
"eval_steps_per_second": 6.158,
|
| 505 |
+
"step": 6600
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.3660104459622338,
|
| 509 |
+
"grad_norm": 4.1875,
|
| 510 |
+
"learning_rate": 4.349653269178727e-05,
|
| 511 |
+
"loss": 0.2807,
|
| 512 |
+
"step": 6800
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.3660104459622338,
|
| 516 |
+
"eval_loss": 0.30023491382598877,
|
| 517 |
+
"eval_runtime": 39.7798,
|
| 518 |
+
"eval_samples_per_second": 49.321,
|
| 519 |
+
"eval_steps_per_second": 6.184,
|
| 520 |
+
"step": 6800
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.4061872237846524,
|
| 524 |
+
"grad_norm": 6.125,
|
| 525 |
+
"learning_rate": 4.3043124380438804e-05,
|
| 526 |
+
"loss": 0.2775,
|
| 527 |
+
"step": 7000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.4061872237846524,
|
| 531 |
+
"eval_loss": 0.29702138900756836,
|
| 532 |
+
"eval_runtime": 40.0167,
|
| 533 |
+
"eval_samples_per_second": 49.03,
|
| 534 |
+
"eval_steps_per_second": 6.147,
|
| 535 |
+
"step": 7000
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.4463640016070711,
|
| 539 |
+
"grad_norm": 4.40625,
|
| 540 |
+
"learning_rate": 4.257697613188684e-05,
|
| 541 |
+
"loss": 0.2743,
|
| 542 |
+
"step": 7200
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.4463640016070711,
|
| 546 |
+
"eval_loss": 0.29679545760154724,
|
| 547 |
+
"eval_runtime": 40.3896,
|
| 548 |
+
"eval_samples_per_second": 48.577,
|
| 549 |
+
"eval_steps_per_second": 6.091,
|
| 550 |
+
"step": 7200
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.4865407794294898,
|
| 554 |
+
"grad_norm": 5.90625,
|
| 555 |
+
"learning_rate": 4.209841708532529e-05,
|
| 556 |
+
"loss": 0.2772,
|
| 557 |
+
"step": 7400
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.4865407794294898,
|
| 561 |
+
"eval_loss": 0.2939276695251465,
|
| 562 |
+
"eval_runtime": 40.042,
|
| 563 |
+
"eval_samples_per_second": 48.999,
|
| 564 |
+
"eval_steps_per_second": 6.144,
|
| 565 |
+
"step": 7400
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 1.5267175572519083,
|
| 569 |
+
"grad_norm": 7.375,
|
| 570 |
+
"learning_rate": 4.160778514299728e-05,
|
| 571 |
+
"loss": 0.2677,
|
| 572 |
+
"step": 7600
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.5267175572519083,
|
| 576 |
+
"eval_loss": 0.29747524857521057,
|
| 577 |
+
"eval_runtime": 40.0213,
|
| 578 |
+
"eval_samples_per_second": 49.024,
|
| 579 |
+
"eval_steps_per_second": 6.147,
|
| 580 |
+
"step": 7600
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.566894335074327,
|
| 584 |
+
"grad_norm": 4.8125,
|
| 585 |
+
"learning_rate": 4.110542673160829e-05,
|
| 586 |
+
"loss": 0.2683,
|
| 587 |
+
"step": 7800
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.566894335074327,
|
| 591 |
+
"eval_loss": 0.2939266860485077,
|
| 592 |
+
"eval_runtime": 40.0323,
|
| 593 |
+
"eval_samples_per_second": 49.01,
|
| 594 |
+
"eval_steps_per_second": 6.145,
|
| 595 |
+
"step": 7800
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.6070711128967456,
|
| 599 |
+
"grad_norm": 5.46875,
|
| 600 |
+
"learning_rate": 4.059169655772018e-05,
|
| 601 |
+
"loss": 0.2645,
|
| 602 |
+
"step": 8000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.6070711128967456,
|
| 606 |
+
"eval_loss": 0.29068824648857117,
|
| 607 |
+
"eval_runtime": 40.0918,
|
| 608 |
+
"eval_samples_per_second": 48.938,
|
| 609 |
+
"eval_steps_per_second": 6.136,
|
| 610 |
+
"step": 8000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.6472478907191643,
|
| 614 |
+
"grad_norm": 5.46875,
|
| 615 |
+
"learning_rate": 4.006695735729914e-05,
|
| 616 |
+
"loss": 0.2722,
|
| 617 |
+
"step": 8200
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.6472478907191643,
|
| 621 |
+
"eval_loss": 0.29028597474098206,
|
| 622 |
+
"eval_runtime": 40.324,
|
| 623 |
+
"eval_samples_per_second": 48.656,
|
| 624 |
+
"eval_steps_per_second": 6.101,
|
| 625 |
+
"step": 8200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.687424668541583,
|
| 629 |
+
"grad_norm": 4.84375,
|
| 630 |
+
"learning_rate": 3.953157963959404e-05,
|
| 631 |
+
"loss": 0.268,
|
| 632 |
+
"step": 8400
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.687424668541583,
|
| 636 |
+
"eval_loss": 0.285940945148468,
|
| 637 |
+
"eval_runtime": 40.1268,
|
| 638 |
+
"eval_samples_per_second": 48.895,
|
| 639 |
+
"eval_steps_per_second": 6.131,
|
| 640 |
+
"step": 8400
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.7276014463640017,
|
| 644 |
+
"grad_norm": 6.59375,
|
| 645 |
+
"learning_rate": 3.8985941425526314e-05,
|
| 646 |
+
"loss": 0.2681,
|
| 647 |
+
"step": 8600
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.7276014463640017,
|
| 651 |
+
"eval_loss": 0.2845953702926636,
|
| 652 |
+
"eval_runtime": 40.1554,
|
| 653 |
+
"eval_samples_per_second": 48.86,
|
| 654 |
+
"eval_steps_per_second": 6.126,
|
| 655 |
+
"step": 8600
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.7677782241864204,
|
| 659 |
+
"grad_norm": 3.625,
|
| 660 |
+
"learning_rate": 3.843042798077592e-05,
|
| 661 |
+
"loss": 0.2607,
|
| 662 |
+
"step": 8800
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.7677782241864204,
|
| 666 |
+
"eval_loss": 0.28649890422821045,
|
| 667 |
+
"eval_runtime": 40.2527,
|
| 668 |
+
"eval_samples_per_second": 48.742,
|
| 669 |
+
"eval_steps_per_second": 6.111,
|
| 670 |
+
"step": 8800
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.8079550020088389,
|
| 674 |
+
"grad_norm": 5.84375,
|
| 675 |
+
"learning_rate": 3.786543154375193e-05,
|
| 676 |
+
"loss": 0.2641,
|
| 677 |
+
"step": 9000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 1.8079550020088389,
|
| 681 |
+
"eval_loss": 0.2839067280292511,
|
| 682 |
+
"eval_runtime": 40.0206,
|
| 683 |
+
"eval_samples_per_second": 49.025,
|
| 684 |
+
"eval_steps_per_second": 6.147,
|
| 685 |
+
"step": 9000
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.8481317798312575,
|
| 689 |
+
"grad_norm": 3.890625,
|
| 690 |
+
"learning_rate": 3.729135104863981e-05,
|
| 691 |
+
"loss": 0.2611,
|
| 692 |
+
"step": 9200
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.8481317798312575,
|
| 696 |
+
"eval_loss": 0.2817397117614746,
|
| 697 |
+
"eval_runtime": 40.0332,
|
| 698 |
+
"eval_samples_per_second": 49.009,
|
| 699 |
+
"eval_steps_per_second": 6.145,
|
| 700 |
+
"step": 9200
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.8883085576536762,
|
| 704 |
+
"grad_norm": 10.5,
|
| 705 |
+
"learning_rate": 3.6708591843720904e-05,
|
| 706 |
+
"loss": 0.263,
|
| 707 |
+
"step": 9400
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 1.8883085576536762,
|
| 711 |
+
"eval_loss": 0.28167155385017395,
|
| 712 |
+
"eval_runtime": 40.1441,
|
| 713 |
+
"eval_samples_per_second": 48.874,
|
| 714 |
+
"eval_steps_per_second": 6.128,
|
| 715 |
+
"step": 9400
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 1.9284853354760947,
|
| 719 |
+
"grad_norm": 5.71875,
|
| 720 |
+
"learning_rate": 3.6117565405163e-05,
|
| 721 |
+
"loss": 0.2627,
|
| 722 |
+
"step": 9600
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 1.9284853354760947,
|
| 726 |
+
"eval_loss": 0.2811395525932312,
|
| 727 |
+
"eval_runtime": 40.1752,
|
| 728 |
+
"eval_samples_per_second": 48.836,
|
| 729 |
+
"eval_steps_per_second": 6.123,
|
| 730 |
+
"step": 9600
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.9686621132985134,
|
| 734 |
+
"grad_norm": 4.8125,
|
| 735 |
+
"learning_rate": 3.551868904648423e-05,
|
| 736 |
+
"loss": 0.2655,
|
| 737 |
+
"step": 9800
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.9686621132985134,
|
| 741 |
+
"eval_loss": 0.2818823754787445,
|
| 742 |
+
"eval_runtime": 40.0154,
|
| 743 |
+
"eval_samples_per_second": 49.031,
|
| 744 |
+
"eval_steps_per_second": 6.148,
|
| 745 |
+
"step": 9800
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.008838891120932,
|
| 749 |
+
"grad_norm": 4.75,
|
| 750 |
+
"learning_rate": 3.491238562389514e-05,
|
| 751 |
+
"loss": 0.2427,
|
| 752 |
+
"step": 10000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.008838891120932,
|
| 756 |
+
"eval_loss": 0.2955799698829651,
|
| 757 |
+
"eval_runtime": 39.9851,
|
| 758 |
+
"eval_samples_per_second": 49.068,
|
| 759 |
+
"eval_steps_per_second": 6.152,
|
| 760 |
+
"step": 10000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.0490156689433507,
|
| 764 |
+
"grad_norm": 3.984375,
|
| 765 |
+
"learning_rate": 3.429908323772732e-05,
|
| 766 |
+
"loss": 0.1537,
|
| 767 |
+
"step": 10200
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.0490156689433507,
|
| 771 |
+
"eval_loss": 0.2996705174446106,
|
| 772 |
+
"eval_runtime": 39.9497,
|
| 773 |
+
"eval_samples_per_second": 49.112,
|
| 774 |
+
"eval_steps_per_second": 6.158,
|
| 775 |
+
"step": 10200
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.0891924467657694,
|
| 779 |
+
"grad_norm": 4.28125,
|
| 780 |
+
"learning_rate": 3.3679214930159134e-05,
|
| 781 |
+
"loss": 0.1538,
|
| 782 |
+
"step": 10400
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.0891924467657694,
|
| 786 |
+
"eval_loss": 0.29936379194259644,
|
| 787 |
+
"eval_runtime": 40.1128,
|
| 788 |
+
"eval_samples_per_second": 48.912,
|
| 789 |
+
"eval_steps_per_second": 6.133,
|
| 790 |
+
"step": 10400
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 2.129369224588188,
|
| 794 |
+
"grad_norm": 5.15625,
|
| 795 |
+
"learning_rate": 3.305321837945223e-05,
|
| 796 |
+
"loss": 0.1495,
|
| 797 |
+
"step": 10600
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 2.129369224588188,
|
| 801 |
+
"eval_loss": 0.30408579111099243,
|
| 802 |
+
"eval_runtime": 39.7023,
|
| 803 |
+
"eval_samples_per_second": 49.418,
|
| 804 |
+
"eval_steps_per_second": 6.196,
|
| 805 |
+
"step": 10600
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.169546002410607,
|
| 809 |
+
"grad_norm": 2.453125,
|
| 810 |
+
"learning_rate": 3.242153559091438e-05,
|
| 811 |
+
"loss": 0.1575,
|
| 812 |
+
"step": 10800
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.169546002410607,
|
| 816 |
+
"eval_loss": 0.30324921011924744,
|
| 817 |
+
"eval_runtime": 40.2225,
|
| 818 |
+
"eval_samples_per_second": 48.779,
|
| 819 |
+
"eval_steps_per_second": 6.116,
|
| 820 |
+
"step": 10800
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.2097227802330255,
|
| 824 |
+
"grad_norm": 4.71875,
|
| 825 |
+
"learning_rate": 3.1784612584807336e-05,
|
| 826 |
+
"loss": 0.1522,
|
| 827 |
+
"step": 11000
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 2.2097227802330255,
|
| 831 |
+
"eval_loss": 0.30149009823799133,
|
| 832 |
+
"eval_runtime": 39.9204,
|
| 833 |
+
"eval_samples_per_second": 49.148,
|
| 834 |
+
"eval_steps_per_second": 6.162,
|
| 835 |
+
"step": 11000
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.2498995580554437,
|
| 839 |
+
"grad_norm": 4.625,
|
| 840 |
+
"learning_rate": 3.1142899081419545e-05,
|
| 841 |
+
"loss": 0.1515,
|
| 842 |
+
"step": 11200
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.2498995580554437,
|
| 846 |
+
"eval_loss": 0.30561012029647827,
|
| 847 |
+
"eval_runtime": 40.0923,
|
| 848 |
+
"eval_samples_per_second": 48.937,
|
| 849 |
+
"eval_steps_per_second": 6.136,
|
| 850 |
+
"step": 11200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.2900763358778624,
|
| 854 |
+
"grad_norm": 4.59375,
|
| 855 |
+
"learning_rate": 3.049684818352655e-05,
|
| 856 |
+
"loss": 0.1505,
|
| 857 |
+
"step": 11400
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.2900763358778624,
|
| 861 |
+
"eval_loss": 0.2993142306804657,
|
| 862 |
+
"eval_runtime": 39.8653,
|
| 863 |
+
"eval_samples_per_second": 49.216,
|
| 864 |
+
"eval_steps_per_second": 6.171,
|
| 865 |
+
"step": 11400
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.330253113700281,
|
| 869 |
+
"grad_norm": 3.578125,
|
| 870 |
+
"learning_rate": 2.9846916056462875e-05,
|
| 871 |
+
"loss": 0.1459,
|
| 872 |
+
"step": 11600
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.330253113700281,
|
| 876 |
+
"eval_loss": 0.3043794631958008,
|
| 877 |
+
"eval_runtime": 39.9146,
|
| 878 |
+
"eval_samples_per_second": 49.155,
|
| 879 |
+
"eval_steps_per_second": 6.163,
|
| 880 |
+
"step": 11600
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.3704298915227,
|
| 884 |
+
"grad_norm": 5.15625,
|
| 885 |
+
"learning_rate": 2.9193561606031705e-05,
|
| 886 |
+
"loss": 0.1534,
|
| 887 |
+
"step": 11800
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 2.3704298915227,
|
| 891 |
+
"eval_loss": 0.30010586977005005,
|
| 892 |
+
"eval_runtime": 39.8993,
|
| 893 |
+
"eval_samples_per_second": 49.174,
|
| 894 |
+
"eval_steps_per_second": 6.166,
|
| 895 |
+
"step": 11800
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 2.4106066693451185,
|
| 899 |
+
"grad_norm": 5.625,
|
| 900 |
+
"learning_rate": 2.8537246154479376e-05,
|
| 901 |
+
"loss": 0.1507,
|
| 902 |
+
"step": 12000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 2.4106066693451185,
|
| 906 |
+
"eval_loss": 0.29873979091644287,
|
| 907 |
+
"eval_runtime": 39.98,
|
| 908 |
+
"eval_samples_per_second": 49.074,
|
| 909 |
+
"eval_steps_per_second": 6.153,
|
| 910 |
+
"step": 12000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.450783447167537,
|
| 914 |
+
"grad_norm": 5.78125,
|
| 915 |
+
"learning_rate": 2.7878433114763743e-05,
|
| 916 |
+
"loss": 0.1524,
|
| 917 |
+
"step": 12200
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 2.450783447167537,
|
| 921 |
+
"eval_loss": 0.2999976873397827,
|
| 922 |
+
"eval_runtime": 40.1057,
|
| 923 |
+
"eval_samples_per_second": 48.921,
|
| 924 |
+
"eval_steps_per_second": 6.134,
|
| 925 |
+
"step": 12200
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 2.490960224989956,
|
| 929 |
+
"grad_norm": 5.28125,
|
| 930 |
+
"learning_rate": 2.7217587663346385e-05,
|
| 931 |
+
"loss": 0.1454,
|
| 932 |
+
"step": 12400
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 2.490960224989956,
|
| 936 |
+
"eval_loss": 0.30179864168167114,
|
| 937 |
+
"eval_runtime": 39.8557,
|
| 938 |
+
"eval_samples_per_second": 49.228,
|
| 939 |
+
"eval_steps_per_second": 6.172,
|
| 940 |
+
"step": 12400
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.5311370028123745,
|
| 944 |
+
"grad_norm": 5.15625,
|
| 945 |
+
"learning_rate": 2.6555176411739518e-05,
|
| 946 |
+
"loss": 0.1512,
|
| 947 |
+
"step": 12600
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.5311370028123745,
|
| 951 |
+
"eval_loss": 0.3000730872154236,
|
| 952 |
+
"eval_runtime": 40.0032,
|
| 953 |
+
"eval_samples_per_second": 49.046,
|
| 954 |
+
"eval_steps_per_second": 6.15,
|
| 955 |
+
"step": 12600
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.571313780634793,
|
| 959 |
+
"grad_norm": 5.59375,
|
| 960 |
+
"learning_rate": 2.589166707703972e-05,
|
| 961 |
+
"loss": 0.1441,
|
| 962 |
+
"step": 12800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.571313780634793,
|
| 966 |
+
"eval_loss": 0.29769018292427063,
|
| 967 |
+
"eval_runtime": 39.946,
|
| 968 |
+
"eval_samples_per_second": 49.116,
|
| 969 |
+
"eval_steps_per_second": 6.158,
|
| 970 |
+
"step": 12800
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.611490558457212,
|
| 974 |
+
"grad_norm": 3.765625,
|
| 975 |
+
"learning_rate": 2.522752815168098e-05,
|
| 976 |
+
"loss": 0.1439,
|
| 977 |
+
"step": 13000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.611490558457212,
|
| 981 |
+
"eval_loss": 0.29854264855384827,
|
| 982 |
+
"eval_runtime": 39.8913,
|
| 983 |
+
"eval_samples_per_second": 49.184,
|
| 984 |
+
"eval_steps_per_second": 6.167,
|
| 985 |
+
"step": 13000
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 2.6516673362796306,
|
| 989 |
+
"grad_norm": 3.875,
|
| 990 |
+
"learning_rate": 2.4563228572640353e-05,
|
| 991 |
+
"loss": 0.1564,
|
| 992 |
+
"step": 13200
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.6516673362796306,
|
| 996 |
+
"eval_loss": 0.29687148332595825,
|
| 997 |
+
"eval_runtime": 39.6942,
|
| 998 |
+
"eval_samples_per_second": 49.428,
|
| 999 |
+
"eval_steps_per_second": 6.197,
|
| 1000 |
+
"step": 13200
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.6918441141020493,
|
| 1004 |
+
"grad_norm": 5.53125,
|
| 1005 |
+
"learning_rate": 2.3899237390329673e-05,
|
| 1006 |
+
"loss": 0.1495,
|
| 1007 |
+
"step": 13400
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 2.6918441141020493,
|
| 1011 |
+
"eval_loss": 0.29626649618148804,
|
| 1012 |
+
"eval_runtime": 39.4226,
|
| 1013 |
+
"eval_samples_per_second": 49.768,
|
| 1014 |
+
"eval_steps_per_second": 6.24,
|
| 1015 |
+
"step": 13400
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 2.7320208919244675,
|
| 1019 |
+
"grad_norm": 5.53125,
|
| 1020 |
+
"learning_rate": 2.323602343740718e-05,
|
| 1021 |
+
"loss": 0.1565,
|
| 1022 |
+
"step": 13600
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.7320208919244675,
|
| 1026 |
+
"eval_loss": 0.3002982437610626,
|
| 1027 |
+
"eval_runtime": 39.7242,
|
| 1028 |
+
"eval_samples_per_second": 49.391,
|
| 1029 |
+
"eval_steps_per_second": 6.193,
|
| 1030 |
+
"step": 13600
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 2.772197669746886,
|
| 1034 |
+
"grad_norm": 4.09375,
|
| 1035 |
+
"learning_rate": 2.2574054997742913e-05,
|
| 1036 |
+
"loss": 0.1438,
|
| 1037 |
+
"step": 13800
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 2.772197669746886,
|
| 1041 |
+
"eval_loss": 0.29700466990470886,
|
| 1042 |
+
"eval_runtime": 39.8693,
|
| 1043 |
+
"eval_samples_per_second": 49.211,
|
| 1044 |
+
"eval_steps_per_second": 6.17,
|
| 1045 |
+
"step": 13800
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.812374447569305,
|
| 1049 |
+
"grad_norm": 7.28125,
|
| 1050 |
+
"learning_rate": 2.191379947577163e-05,
|
| 1051 |
+
"loss": 0.1487,
|
| 1052 |
+
"step": 14000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.812374447569305,
|
| 1056 |
+
"eval_loss": 0.29598772525787354,
|
| 1057 |
+
"eval_runtime": 39.4433,
|
| 1058 |
+
"eval_samples_per_second": 49.742,
|
| 1059 |
+
"eval_steps_per_second": 6.237,
|
| 1060 |
+
"step": 14000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.8525512253917236,
|
| 1064 |
+
"grad_norm": 5.40625,
|
| 1065 |
+
"learning_rate": 2.1255723066466597e-05,
|
| 1066 |
+
"loss": 0.1449,
|
| 1067 |
+
"step": 14200
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.8525512253917236,
|
| 1071 |
+
"eval_loss": 0.29710152745246887,
|
| 1072 |
+
"eval_runtime": 39.8912,
|
| 1073 |
+
"eval_samples_per_second": 49.184,
|
| 1074 |
+
"eval_steps_per_second": 6.167,
|
| 1075 |
+
"step": 14200
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 2.8927280032141423,
|
| 1079 |
+
"grad_norm": 3.453125,
|
| 1080 |
+
"learning_rate": 2.0600290426167408e-05,
|
| 1081 |
+
"loss": 0.1462,
|
| 1082 |
+
"step": 14400
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.8927280032141423,
|
| 1086 |
+
"eval_loss": 0.2962632179260254,
|
| 1087 |
+
"eval_runtime": 39.6885,
|
| 1088 |
+
"eval_samples_per_second": 49.435,
|
| 1089 |
+
"eval_steps_per_second": 6.198,
|
| 1090 |
+
"step": 14400
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.932904781036561,
|
| 1094 |
+
"grad_norm": 3.3125,
|
| 1095 |
+
"learning_rate": 1.9947964344494233e-05,
|
| 1096 |
+
"loss": 0.1373,
|
| 1097 |
+
"step": 14600
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 2.932904781036561,
|
| 1101 |
+
"eval_loss": 0.2984876036643982,
|
| 1102 |
+
"eval_runtime": 39.5307,
|
| 1103 |
+
"eval_samples_per_second": 49.632,
|
| 1104 |
+
"eval_steps_per_second": 6.223,
|
| 1105 |
+
"step": 14600
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 2.9730815588589796,
|
| 1109 |
+
"grad_norm": 4.53125,
|
| 1110 |
+
"learning_rate": 1.9299205417580064e-05,
|
| 1111 |
+
"loss": 0.1506,
|
| 1112 |
+
"step": 14800
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.9730815588589796,
|
| 1116 |
+
"eval_loss": 0.2969134449958801,
|
| 1117 |
+
"eval_runtime": 39.7386,
|
| 1118 |
+
"eval_samples_per_second": 49.373,
|
| 1119 |
+
"eval_steps_per_second": 6.19,
|
| 1120 |
+
"step": 14800
|
| 1121 |
+
}
|
| 1122 |
+
],
|
| 1123 |
+
"logging_steps": 200,
|
| 1124 |
+
"max_steps": 24890,
|
| 1125 |
+
"num_input_tokens_seen": 0,
|
| 1126 |
+
"num_train_epochs": 5,
|
| 1127 |
+
"save_steps": 200,
|
| 1128 |
+
"stateful_callbacks": {
|
| 1129 |
+
"TrainerControl": {
|
| 1130 |
+
"args": {
|
| 1131 |
+
"should_epoch_stop": false,
|
| 1132 |
+
"should_evaluate": false,
|
| 1133 |
+
"should_log": false,
|
| 1134 |
+
"should_save": true,
|
| 1135 |
+
"should_training_stop": false
|
| 1136 |
+
},
|
| 1137 |
+
"attributes": {}
|
| 1138 |
+
}
|
| 1139 |
+
},
|
| 1140 |
+
"total_flos": 5.1496266530001946e+17,
|
| 1141 |
+
"train_batch_size": 8,
|
| 1142 |
+
"trial_name": null,
|
| 1143 |
+
"trial_params": null
|
| 1144 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|