Add checkpoint-212 (excluding optimizer)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: zerofata/MS3.2-PaintedFantasy-24B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "zerofata/MS3.2-PaintedFantasy-24B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b88bc451c9161b40c68d55917001e28540c81e18af53d2205bc4f253f2e30e
+size 369698576

chat_template.jinja

@@ -0,0 +1,51 @@
+{%- set today = strftime_now("%Y-%m-%d") %}
+{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
+
+{{- bos_token }}
+
+{%- if messages[0]['role'] == 'system' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content'] %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text'] %}
+    {%- endif %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = default_system_message %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' }}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and image blocks are supported in message content!') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'system' %}
+        {%- if message['content'] is string %}
+            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+        {%- else %}
+            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if message['content'] is string %}
+            {{- message['content'] + eos_token }}
+        {%- else %}
+            {{- message['content'][0]['text'] + eos_token }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Only user, system and assistant roles are supported!') }}
+    {%- endif %}
+{%- endfor %}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2ef2c259ba7b1310c9ed5d9b7b8cd1db17fbb75bcbccd94c42efd181b2643a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec532b5fd8f7cbc4e6921780ba98a11f321c38e6431c8f8a3436d55918f174fd
+size 1064

special_tokens_map.json

@@ -0,0 +1,1032 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9989fde2ceac79fbb9dcc91947c04e3caad235e80a5e4e8bd3c5c93fe5e102db
+size 17078136

trainer_state.json

@@ -0,0 +1,1518 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 212,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009478672985781991,
+      "grad_norm": 1.1718926429748535,
+      "learning_rate": 0.0,
+      "loss": 2.6629,
+      "step": 1
+    },
+    {
+      "epoch": 0.018957345971563982,
+      "grad_norm": 1.1212024688720703,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 2.5806,
+      "step": 2
+    },
+    {
+      "epoch": 0.02843601895734597,
+      "grad_norm": 1.225563406944275,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 2.6841,
+      "step": 3
+    },
+    {
+      "epoch": 0.037914691943127965,
+      "grad_norm": 1.2255617380142212,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.6513,
+      "step": 4
+    },
+    {
+      "epoch": 0.04739336492890995,
+      "grad_norm": 1.000268578529358,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 2.6722,
+      "step": 5
+    },
+    {
+      "epoch": 0.05687203791469194,
+      "grad_norm": 0.9953453540802002,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.4666,
+      "step": 6
+    },
+    {
+      "epoch": 0.06635071090047394,
+      "grad_norm": 1.158920168876648,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.6296,
+      "step": 7
+    },
+    {
+      "epoch": 0.07582938388625593,
+      "grad_norm": 1.0453510284423828,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 2.599,
+      "step": 8
+    },
+    {
+      "epoch": 0.08530805687203792,
+      "grad_norm": 0.9960002899169922,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 2.6475,
+      "step": 9
+    },
+    {
+      "epoch": 0.0947867298578199,
+      "grad_norm": 1.2907602787017822,
+      "learning_rate": 6e-06,
+      "loss": 2.5586,
+      "step": 10
+    },
+    {
+      "epoch": 0.10426540284360189,
+      "grad_norm": 1.0515801906585693,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.5806,
+      "step": 11
+    },
+    {
+      "epoch": 0.11374407582938388,
+      "grad_norm": 1.070308804512024,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 2.7149,
+      "step": 12
+    },
+    {
+      "epoch": 0.12322274881516587,
+      "grad_norm": 0.9910991191864014,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.6353,
+      "step": 13
+    },
+    {
+      "epoch": 0.13270142180094788,
+      "grad_norm": 0.8306079506874084,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 2.5439,
+      "step": 14
+    },
+    {
+      "epoch": 0.14218009478672985,
+      "grad_norm": 0.945061981678009,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 2.5597,
+      "step": 15
+    },
+    {
+      "epoch": 0.15165876777251186,
+      "grad_norm": 0.8972373604774475,
+      "learning_rate": 1e-05,
+      "loss": 2.4496,
+      "step": 16
+    },
+    {
+      "epoch": 0.16113744075829384,
+      "grad_norm": 0.9250657558441162,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 2.5905,
+      "step": 17
+    },
+    {
+      "epoch": 0.17061611374407584,
+      "grad_norm": 0.8590799570083618,
+      "learning_rate": 1.1333333333333334e-05,
+      "loss": 2.4993,
+      "step": 18
+    },
+    {
+      "epoch": 0.18009478672985782,
+      "grad_norm": 0.8903495669364929,
+      "learning_rate": 1.2e-05,
+      "loss": 2.4999,
+      "step": 19
+    },
+    {
+      "epoch": 0.1895734597156398,
+      "grad_norm": 0.9213452935218811,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 2.4677,
+      "step": 20
+    },
+    {
+      "epoch": 0.1990521327014218,
+      "grad_norm": 0.8921183943748474,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.4343,
+      "step": 21
+    },
+    {
+      "epoch": 0.20853080568720378,
+      "grad_norm": 0.767433226108551,
+      "learning_rate": 1.4e-05,
+      "loss": 2.5294,
+      "step": 22
+    },
+    {
+      "epoch": 0.21800947867298578,
+      "grad_norm": 0.8856372237205505,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 2.4663,
+      "step": 23
+    },
+    {
+      "epoch": 0.22748815165876776,
+      "grad_norm": 0.8512458801269531,
+      "learning_rate": 1.5333333333333334e-05,
+      "loss": 2.5763,
+      "step": 24
+    },
+    {
+      "epoch": 0.23696682464454977,
+      "grad_norm": 0.8298342823982239,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.4612,
+      "step": 25
+    },
+    {
+      "epoch": 0.24644549763033174,
+      "grad_norm": 1.0803931951522827,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.515,
+      "step": 26
+    },
+    {
+      "epoch": 0.2559241706161137,
+      "grad_norm": 0.8421900868415833,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 2.5489,
+      "step": 27
+    },
+    {
+      "epoch": 0.26540284360189575,
+      "grad_norm": 0.9771528244018555,
+      "learning_rate": 1.8e-05,
+      "loss": 2.4214,
+      "step": 28
+    },
+    {
+      "epoch": 0.27488151658767773,
+      "grad_norm": 1.0094590187072754,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 2.3959,
+      "step": 29
+    },
+    {
+      "epoch": 0.2843601895734597,
+      "grad_norm": 0.9626856446266174,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 2.4792,
+      "step": 30
+    },
+    {
+      "epoch": 0.2938388625592417,
+      "grad_norm": 0.843460738658905,
+      "learning_rate": 2e-05,
+      "loss": 2.5486,
+      "step": 31
+    },
+    {
+      "epoch": 0.3033175355450237,
+      "grad_norm": 0.8346056342124939,
+      "learning_rate": 1.99994050500015e-05,
+      "loss": 2.3746,
+      "step": 32
+    },
+    {
+      "epoch": 0.3127962085308057,
+      "grad_norm": 0.9779443144798279,
+      "learning_rate": 1.999762027079909e-05,
+      "loss": 2.4543,
+      "step": 33
+    },
+    {
+      "epoch": 0.3222748815165877,
+      "grad_norm": 1.2702308893203735,
+      "learning_rate": 1.9994645874763657e-05,
+      "loss": 2.4247,
+      "step": 34
+    },
+    {
+      "epoch": 0.33175355450236965,
+      "grad_norm": 0.9161669611930847,
+      "learning_rate": 1.999048221581858e-05,
+      "loss": 2.5287,
+      "step": 35
+    },
+    {
+      "epoch": 0.3412322274881517,
+      "grad_norm": 0.8298777937889099,
+      "learning_rate": 1.9985129789397633e-05,
+      "loss": 2.4522,
+      "step": 36
+    },
+    {
+      "epoch": 0.35071090047393366,
+      "grad_norm": 0.8846487402915955,
+      "learning_rate": 1.9978589232386036e-05,
+      "loss": 2.4225,
+      "step": 37
+    },
+    {
+      "epoch": 0.36018957345971564,
+      "grad_norm": 0.7903144955635071,
+      "learning_rate": 1.9970861323044667e-05,
+      "loss": 2.421,
+      "step": 38
+    },
+    {
+      "epoch": 0.3696682464454976,
+      "grad_norm": 0.8443423509597778,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 2.4323,
+      "step": 39
+    },
+    {
+      "epoch": 0.3791469194312796,
+      "grad_norm": 0.9062912464141846,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 2.4179,
+      "step": 40
+    },
+    {
+      "epoch": 0.3886255924170616,
+      "grad_norm": 0.8565083146095276,
+      "learning_rate": 1.9940563382223196e-05,
+      "loss": 2.3007,
+      "step": 41
+    },
+    {
+      "epoch": 0.3981042654028436,
+      "grad_norm": 0.806698739528656,
+      "learning_rate": 1.9928096670090552e-05,
+      "loss": 2.3509,
+      "step": 42
+    },
+    {
+      "epoch": 0.4075829383886256,
+      "grad_norm": 0.8576929569244385,
+      "learning_rate": 1.9914448613738107e-05,
+      "loss": 2.4125,
+      "step": 43
+    },
+    {
+      "epoch": 0.41706161137440756,
+      "grad_norm": 1.650278925895691,
+      "learning_rate": 1.989962083714808e-05,
+      "loss": 2.3508,
+      "step": 44
+    },
+    {
+      "epoch": 0.4265402843601896,
+      "grad_norm": 0.8928993344306946,
+      "learning_rate": 1.988361510467761e-05,
+      "loss": 2.3976,
+      "step": 45
+    },
+    {
+      "epoch": 0.43601895734597157,
+      "grad_norm": 0.8806268572807312,
+      "learning_rate": 1.9866433320848793e-05,
+      "loss": 2.3067,
+      "step": 46
+    },
+    {
+      "epoch": 0.44549763033175355,
+      "grad_norm": 0.8654487729072571,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 2.4552,
+      "step": 47
+    },
+    {
+      "epoch": 0.4549763033175355,
+      "grad_norm": 1.3034582138061523,
+      "learning_rate": 1.9828549916653013e-05,
+      "loss": 2.3354,
+      "step": 48
+    },
+    {
+      "epoch": 0.46445497630331756,
+      "grad_norm": 0.9486224055290222,
+      "learning_rate": 1.9807852804032306e-05,
+      "loss": 2.4246,
+      "step": 49
+    },
+    {
+      "epoch": 0.47393364928909953,
+      "grad_norm": 0.9173024296760559,
+      "learning_rate": 1.9785988655009386e-05,
+      "loss": 2.4309,
+      "step": 50
+    },
+    {
+      "epoch": 0.4834123222748815,
+      "grad_norm": 0.9614086747169495,
+      "learning_rate": 1.9762960071199334e-05,
+      "loss": 2.1943,
+      "step": 51
+    },
+    {
+      "epoch": 0.4928909952606635,
+      "grad_norm": 0.9894729852676392,
+      "learning_rate": 1.9738769792773338e-05,
+      "loss": 2.3974,
+      "step": 52
+    },
+    {
+      "epoch": 0.5023696682464455,
+      "grad_norm": 0.8646323084831238,
+      "learning_rate": 1.9713420698132614e-05,
+      "loss": 2.3535,
+      "step": 53
+    },
+    {
+      "epoch": 0.5118483412322274,
+      "grad_norm": 0.9549570083618164,
+      "learning_rate": 1.9686915803565934e-05,
+      "loss": 2.3486,
+      "step": 54
+    },
+    {
+      "epoch": 0.5213270142180095,
+      "grad_norm": 0.8866903781890869,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 2.3381,
+      "step": 55
+    },
+    {
+      "epoch": 0.5308056872037915,
+      "grad_norm": 0.8965452909469604,
+      "learning_rate": 1.963045136707763e-05,
+      "loss": 2.3125,
+      "step": 56
+    },
+    {
+      "epoch": 0.5402843601895735,
+      "grad_norm": 1.01371169090271,
+      "learning_rate": 1.960049854385929e-05,
+      "loss": 2.4584,
+      "step": 57
+    },
+    {
+      "epoch": 0.5497630331753555,
+      "grad_norm": 0.9794333577156067,
+      "learning_rate": 1.956940335732209e-05,
+      "loss": 2.4287,
+      "step": 58
+    },
+    {
+      "epoch": 0.5592417061611374,
+      "grad_norm": 1.146530270576477,
+      "learning_rate": 1.953716950748227e-05,
+      "loss": 2.4154,
+      "step": 59
+    },
+    {
+      "epoch": 0.5687203791469194,
+      "grad_norm": 0.9316839575767517,
+      "learning_rate": 1.9503800829845613e-05,
+      "loss": 2.4184,
+      "step": 60
+    },
+    {
+      "epoch": 0.5781990521327014,
+      "grad_norm": 0.8945372700691223,
+      "learning_rate": 1.946930129495106e-05,
+      "loss": 2.3579,
+      "step": 61
+    },
+    {
+      "epoch": 0.5876777251184834,
+      "grad_norm": 0.9607009291648865,
+      "learning_rate": 1.9433675007898255e-05,
+      "loss": 2.4485,
+      "step": 62
+    },
+    {
+      "epoch": 0.5971563981042654,
+      "grad_norm": 0.986282467842102,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 2.4574,
+      "step": 63
+    },
+    {
+      "epoch": 0.6066350710900474,
+      "grad_norm": 0.9698584079742432,
+      "learning_rate": 1.935905926757326e-05,
+      "loss": 2.3278,
+      "step": 64
+    },
+    {
+      "epoch": 0.6161137440758294,
+      "grad_norm": 0.9542692303657532,
+      "learning_rate": 1.932007869282799e-05,
+      "loss": 2.3371,
+      "step": 65
+    },
+    {
+      "epoch": 0.6255924170616114,
+      "grad_norm": 0.9010556936264038,
+      "learning_rate": 1.9279989121921846e-05,
+      "loss": 2.34,
+      "step": 66
+    },
+    {
+      "epoch": 0.6350710900473934,
+      "grad_norm": 0.9130122661590576,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 2.3215,
+      "step": 67
+    },
+    {
+      "epoch": 0.6445497630331753,
+      "grad_norm": 1.236346960067749,
+      "learning_rate": 1.9196502204050925e-05,
+      "loss": 2.3667,
+      "step": 68
+    },
+    {
+      "epoch": 0.6540284360189573,
+      "grad_norm": 1.457154393196106,
+      "learning_rate": 1.9153114791194475e-05,
+      "loss": 2.3762,
+      "step": 69
+    },
+    {
+      "epoch": 0.6635071090047393,
+      "grad_norm": 0.8446010947227478,
+      "learning_rate": 1.910863824921176e-05,
+      "loss": 2.2987,
+      "step": 70
+    },
+    {
+      "epoch": 0.6729857819905213,
+      "grad_norm": 0.9021546840667725,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 2.3261,
+      "step": 71
+    },
+    {
+      "epoch": 0.6824644549763034,
+      "grad_norm": 1.0001662969589233,
+      "learning_rate": 1.901643907588816e-05,
+      "loss": 2.3167,
+      "step": 72
+    },
+    {
+      "epoch": 0.6919431279620853,
+      "grad_norm": 0.9423337578773499,
+      "learning_rate": 1.8968727415326885e-05,
+      "loss": 2.4218,
+      "step": 73
+    },
+    {
+      "epoch": 0.7014218009478673,
+      "grad_norm": 0.9422402381896973,
+      "learning_rate": 1.8919948565893144e-05,
+      "loss": 2.3388,
+      "step": 74
+    },
+    {
+      "epoch": 0.7109004739336493,
+      "grad_norm": 0.9633351564407349,
+      "learning_rate": 1.887010833178222e-05,
+      "loss": 2.3728,
+      "step": 75
+    },
+    {
+      "epoch": 0.7203791469194313,
+      "grad_norm": 0.9586493968963623,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 2.3689,
+      "step": 76
+    },
+    {
+      "epoch": 0.7298578199052133,
+      "grad_norm": 0.8738155961036682,
+      "learning_rate": 1.876726755707508e-05,
+      "loss": 2.2707,
+      "step": 77
+    },
+    {
+      "epoch": 0.7393364928909952,
+      "grad_norm": 0.9077432751655579,
+      "learning_rate": 1.8714279253502616e-05,
+      "loss": 2.385,
+      "step": 78
+    },
+    {
+      "epoch": 0.7488151658767772,
+      "grad_norm": 0.8949682116508484,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 2.2765,
+      "step": 79
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "grad_norm": 0.8834524750709534,
+      "learning_rate": 1.860519833856079e-05,
+      "loss": 2.274,
+      "step": 80
+    },
+    {
+      "epoch": 0.7677725118483413,
+      "grad_norm": 1.1563708782196045,
+      "learning_rate": 1.854911870672947e-05,
+      "loss": 2.3958,
+      "step": 81
+    },
+    {
+      "epoch": 0.7772511848341233,
+      "grad_norm": 0.914176881313324,
+      "learning_rate": 1.849202181526579e-05,
+      "loss": 2.2595,
+      "step": 82
+    },
+    {
+      "epoch": 0.7867298578199052,
+      "grad_norm": 1.2525924444198608,
+      "learning_rate": 1.843391445812886e-05,
+      "loss": 2.3114,
+      "step": 83
+    },
+    {
+      "epoch": 0.7962085308056872,
+      "grad_norm": 0.9277448654174805,
+      "learning_rate": 1.837480354951308e-05,
+      "loss": 2.2949,
+      "step": 84
+    },
+    {
+      "epoch": 0.8056872037914692,
+      "grad_norm": 0.9295048117637634,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 2.2778,
+      "step": 85
+    },
+    {
+      "epoch": 0.8151658767772512,
+      "grad_norm": 0.9221338033676147,
+      "learning_rate": 1.8253599330848638e-05,
+      "loss": 2.35,
+      "step": 86
+    },
+    {
+      "epoch": 0.8246445497630331,
+      "grad_norm": 0.910460889339447,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 2.2655,
+      "step": 87
+    },
+    {
+      "epoch": 0.8341232227488151,
+      "grad_norm": 1.0350533723831177,
+      "learning_rate": 1.8128466845916156e-05,
+      "loss": 2.4712,
+      "step": 88
+    },
+    {
+      "epoch": 0.8436018957345972,
+      "grad_norm": 1.0058749914169312,
+      "learning_rate": 1.806444604267483e-05,
+      "loss": 2.4232,
+      "step": 89
+    },
+    {
+      "epoch": 0.8530805687203792,
+      "grad_norm": 0.8652654886245728,
+      "learning_rate": 1.7999465651001297e-05,
+      "loss": 2.3399,
+      "step": 90
+    },
+    {
+      "epoch": 0.8625592417061612,
+      "grad_norm": 0.9553002119064331,
+      "learning_rate": 1.7933533402912354e-05,
+      "loss": 2.2772,
+      "step": 91
+    },
+    {
+      "epoch": 0.8720379146919431,
+      "grad_norm": 0.9334009885787964,
+      "learning_rate": 1.786665714368617e-05,
+      "loss": 2.3421,
+      "step": 92
+    },
+    {
+      "epoch": 0.8815165876777251,
+      "grad_norm": 0.9072061777114868,
+      "learning_rate": 1.7798844830928818e-05,
+      "loss": 2.2691,
+      "step": 93
+    },
+    {
+      "epoch": 0.8909952606635071,
+      "grad_norm": 0.9546661376953125,
+      "learning_rate": 1.773010453362737e-05,
+      "loss": 2.3345,
+      "step": 94
+    },
+    {
+      "epoch": 0.9004739336492891,
+      "grad_norm": 1.0151286125183105,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 2.2977,
+      "step": 95
+    },
+    {
+      "epoch": 0.909952606635071,
+      "grad_norm": 0.8759846687316895,
+      "learning_rate": 1.758987281247162e-05,
+      "loss": 2.3405,
+      "step": 96
+    },
+    {
+      "epoch": 0.919431279620853,
+      "grad_norm": 1.0017191171646118,
+      "learning_rate": 1.7518398074789776e-05,
+      "loss": 2.3445,
+      "step": 97
+    },
+    {
+      "epoch": 0.9289099526066351,
+      "grad_norm": 0.9899027943611145,
+      "learning_rate": 1.7446028722923266e-05,
+      "loss": 2.3084,
+      "step": 98
+    },
+    {
+      "epoch": 0.9383886255924171,
+      "grad_norm": 0.9640536904335022,
+      "learning_rate": 1.737277336810124e-05,
+      "loss": 2.2341,
+      "step": 99
+    },
+    {
+      "epoch": 0.9478672985781991,
+      "grad_norm": 0.917986273765564,
+      "learning_rate": 1.7298640726978357e-05,
+      "loss": 2.3085,
+      "step": 100
+    },
+    {
+      "epoch": 0.957345971563981,
+      "grad_norm": 0.9574633240699768,
+      "learning_rate": 1.7223639620597556e-05,
+      "loss": 2.3822,
+      "step": 101
+    },
+    {
+      "epoch": 0.966824644549763,
+      "grad_norm": 0.9915265440940857,
+      "learning_rate": 1.7147778973340466e-05,
+      "loss": 2.3087,
+      "step": 102
+    },
+    {
+      "epoch": 0.976303317535545,
+      "grad_norm": 0.9175536632537842,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 2.3098,
+      "step": 103
+    },
+    {
+      "epoch": 0.985781990521327,
+      "grad_norm": 0.9363272190093994,
+      "learning_rate": 1.699351526403367e-05,
+      "loss": 2.3394,
+      "step": 104
+    },
+    {
+      "epoch": 0.995260663507109,
+      "grad_norm": 1.0321186780929565,
+      "learning_rate": 1.6915130557822698e-05,
+      "loss": 2.1852,
+      "step": 105
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5194014310836792,
+      "learning_rate": 1.6835923020228714e-05,
+      "loss": 2.3883,
+      "step": 106
+    },
+    {
+      "epoch": 1.009478672985782,
+      "grad_norm": 0.9262144565582275,
+      "learning_rate": 1.6755902076156606e-05,
+      "loss": 2.299,
+      "step": 107
+    },
+    {
+      "epoch": 1.018957345971564,
+      "grad_norm": 0.943099319934845,
+      "learning_rate": 1.6675077247298475e-05,
+      "loss": 2.3014,
+      "step": 108
+    },
+    {
+      "epoch": 1.028436018957346,
+      "grad_norm": 0.9212830066680908,
+      "learning_rate": 1.659345815100069e-05,
+      "loss": 2.2374,
+      "step": 109
+    },
+    {
+      "epoch": 1.037914691943128,
+      "grad_norm": 0.9187367558479309,
+      "learning_rate": 1.6511054499119493e-05,
+      "loss": 2.2557,
+      "step": 110
+    },
+    {
+      "epoch": 1.04739336492891,
+      "grad_norm": 0.9865244626998901,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 2.2526,
+      "step": 111
+    },
+    {
+      "epoch": 1.0568720379146919,
+      "grad_norm": 0.9716766476631165,
+      "learning_rate": 1.6343932841636455e-05,
+      "loss": 2.252,
+      "step": 112
+    },
+    {
+      "epoch": 1.066350710900474,
+      "grad_norm": 0.9111779928207397,
+      "learning_rate": 1.6259234721840595e-05,
+      "loss": 2.3602,
+      "step": 113
+    },
+    {
+      "epoch": 1.0758293838862558,
+      "grad_norm": 1.201020359992981,
+      "learning_rate": 1.6173791815707053e-05,
+      "loss": 2.2086,
+      "step": 114
+    },
+    {
+      "epoch": 1.085308056872038,
+      "grad_norm": 0.9832363724708557,
+      "learning_rate": 1.608761429008721e-05,
+      "loss": 2.2785,
+      "step": 115
+    },
+    {
+      "epoch": 1.09478672985782,
+      "grad_norm": 1.136888027191162,
+      "learning_rate": 1.6000712399244813e-05,
+      "loss": 2.169,
+      "step": 116
+    },
+    {
+      "epoch": 1.1042654028436019,
+      "grad_norm": 1.6922038793563843,
+      "learning_rate": 1.5913096483635827e-05,
+      "loss": 2.3197,
+      "step": 117
+    },
+    {
+      "epoch": 1.113744075829384,
+      "grad_norm": 0.9305840730667114,
+      "learning_rate": 1.5824776968678024e-05,
+      "loss": 2.3094,
+      "step": 118
+    },
+    {
+      "epoch": 1.1232227488151658,
+      "grad_norm": 0.9827175140380859,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 2.2807,
+      "step": 119
+    },
+    {
+      "epoch": 1.132701421800948,
+      "grad_norm": 1.0022766590118408,
+      "learning_rate": 1.5646069259743007e-05,
+      "loss": 2.246,
+      "step": 120
+    },
+    {
+      "epoch": 1.1421800947867298,
+      "grad_norm": 1.0958722829818726,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 2.3214,
+      "step": 121
+    },
+    {
+      "epoch": 1.1516587677725119,
+      "grad_norm": 1.084460973739624,
+      "learning_rate": 1.5464674327630437e-05,
+      "loss": 2.2418,
+      "step": 122
+    },
+    {
+      "epoch": 1.161137440758294,
+      "grad_norm": 1.0701860189437866,
+      "learning_rate": 1.5372996083468242e-05,
+      "loss": 2.4143,
+      "step": 123
+    },
+    {
+      "epoch": 1.1706161137440758,
+      "grad_norm": 0.9905973672866821,
+      "learning_rate": 1.528067850650368e-05,
+      "loss": 2.2589,
+      "step": 124
+    },
+    {
+      "epoch": 1.180094786729858,
+      "grad_norm": 1.046353816986084,
+      "learning_rate": 1.5187732581605217e-05,
+      "loss": 2.2511,
+      "step": 125
+    },
+    {
+      "epoch": 1.1895734597156398,
+      "grad_norm": 1.0096780061721802,
+      "learning_rate": 1.509416936840842e-05,
+      "loss": 2.2505,
+      "step": 126
+    },
+    {
+      "epoch": 1.1990521327014219,
+      "grad_norm": 1.0571825504302979,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.3112,
+      "step": 127
+    },
+    {
+      "epoch": 1.2085308056872037,
+      "grad_norm": 1.090767741203308,
+      "learning_rate": 1.4905235681593079e-05,
+      "loss": 2.1126,
+      "step": 128
+    },
+    {
+      "epoch": 1.2180094786729858,
+      "grad_norm": 1.2226624488830566,
+      "learning_rate": 1.4809887689193878e-05,
+      "loss": 2.2798,
+      "step": 129
+    },
+    {
+      "epoch": 1.2274881516587677,
+      "grad_norm": 1.1004244089126587,
+      "learning_rate": 1.4713967368259981e-05,
+      "loss": 2.3454,
+      "step": 130
+    },
+    {
+      "epoch": 1.2369668246445498,
+      "grad_norm": 0.963148295879364,
+      "learning_rate": 1.4617486132350343e-05,
+      "loss": 2.2193,
+      "step": 131
+    },
+    {
+      "epoch": 1.2464454976303316,
+      "grad_norm": 1.0694116353988647,
+      "learning_rate": 1.45204554617672e-05,
+      "loss": 2.146,
+      "step": 132
+    },
+    {
+      "epoch": 1.2559241706161137,
+      "grad_norm": 1.0674649477005005,
+      "learning_rate": 1.4422886902190014e-05,
+      "loss": 2.3284,
+      "step": 133
+    },
+    {
+      "epoch": 1.2654028436018958,
+      "grad_norm": 1.1457089185714722,
+      "learning_rate": 1.4324792063301662e-05,
+      "loss": 2.2393,
+      "step": 134
+    },
+    {
+      "epoch": 1.2748815165876777,
+      "grad_norm": 1.0317751169204712,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 2.2869,
+      "step": 135
+    },
+    {
+      "epoch": 1.2843601895734598,
+      "grad_norm": 1.0415928363800049,
+      "learning_rate": 1.4127070298043949e-05,
+      "loss": 2.231,
+      "step": 136
+    },
+    {
+      "epoch": 1.2938388625592416,
+      "grad_norm": 1.224968433380127,
+      "learning_rate": 1.4027466898587375e-05,
+      "loss": 2.1672,
+      "step": 137
+    },
+    {
+      "epoch": 1.3033175355450237,
+      "grad_norm": 1.0224634408950806,
+      "learning_rate": 1.3927384270845744e-05,
+      "loss": 2.3001,
+      "step": 138
+    },
+    {
+      "epoch": 1.3127962085308056,
+      "grad_norm": 1.098523497581482,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 2.2753,
+      "step": 139
+    },
+    {
+      "epoch": 1.3222748815165877,
+      "grad_norm": 1.060198426246643,
+      "learning_rate": 1.372582902144103e-05,
+      "loss": 2.2222,
+      "step": 140
+    },
+    {
+      "epoch": 1.3317535545023698,
+      "grad_norm": 1.015621304512024,
+      "learning_rate": 1.3624380382837017e-05,
+      "loss": 2.2784,
+      "step": 141
+    },
+    {
+      "epoch": 1.3412322274881516,
+      "grad_norm": 1.0406889915466309,
+      "learning_rate": 1.3522500479212337e-05,
+      "loss": 2.2017,
+      "step": 142
+    },
+    {
+      "epoch": 1.3507109004739337,
+      "grad_norm": 1.1058852672576904,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 2.3003,
+      "step": 143
+    },
+    {
+      "epoch": 1.3601895734597156,
+      "grad_norm": 1.0425012111663818,
+      "learning_rate": 1.3317495417533523e-05,
+      "loss": 2.2575,
+      "step": 144
+    },
+    {
+      "epoch": 1.3696682464454977,
+      "grad_norm": 1.1006783246994019,
+      "learning_rate": 1.3214394653031616e-05,
+      "loss": 2.242,
+      "step": 145
+    },
+    {
+      "epoch": 1.3791469194312795,
+      "grad_norm": 2.838590145111084,
+      "learning_rate": 1.3110911407710909e-05,
+      "loss": 2.263,
+      "step": 146
+    },
+    {
+      "epoch": 1.3886255924170616,
+      "grad_norm": 1.3155434131622314,
+      "learning_rate": 1.300705799504273e-05,
+      "loss": 2.2381,
+      "step": 147
+    },
+    {
+      "epoch": 1.3981042654028437,
+      "grad_norm": 0.9725741147994995,
+      "learning_rate": 1.2902846772544625e-05,
+      "loss": 2.1814,
+      "step": 148
+    },
+    {
+      "epoch": 1.4075829383886256,
+      "grad_norm": 1.072764277458191,
+      "learning_rate": 1.2798290140309924e-05,
+      "loss": 2.2758,
+      "step": 149
+    },
+    {
+      "epoch": 1.4170616113744074,
+      "grad_norm": 1.0916640758514404,
+      "learning_rate": 1.2693400539532263e-05,
+      "loss": 2.1405,
+      "step": 150
+    },
+    {
+      "epoch": 1.4265402843601895,
+      "grad_norm": 1.2010222673416138,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 2.2559,
+      "step": 151
+    },
+    {
+      "epoch": 1.4360189573459716,
+      "grad_norm": 1.0151344537734985,
+      "learning_rate": 1.2482672393737164e-05,
+      "loss": 2.1031,
+      "step": 152
+    },
+    {
+      "epoch": 1.4454976303317535,
+      "grad_norm": 1.0264817476272583,
+      "learning_rate": 1.2376858923261732e-05,
+      "loss": 2.2273,
+      "step": 153
+    },
+    {
+      "epoch": 1.4549763033175356,
+      "grad_norm": 1.0587806701660156,
+      "learning_rate": 1.2270762630343734e-05,
+      "loss": 2.2498,
+      "step": 154
+    },
+    {
+      "epoch": 1.4644549763033177,
+      "grad_norm": 2.114945411682129,
+      "learning_rate": 1.2164396139381029e-05,
+      "loss": 2.2337,
+      "step": 155
+    },
+    {
+      "epoch": 1.4739336492890995,
+      "grad_norm": 1.2019884586334229,
+      "learning_rate": 1.205777210692235e-05,
+      "loss": 2.2812,
+      "step": 156
+    },
+    {
+      "epoch": 1.4834123222748814,
+      "grad_norm": 2.341759443283081,
+      "learning_rate": 1.1950903220161286e-05,
+      "loss": 2.3088,
+      "step": 157
+    },
+    {
+      "epoch": 1.4928909952606635,
+      "grad_norm": 1.7187213897705078,
+      "learning_rate": 1.1843802195426634e-05,
+      "loss": 2.2101,
+      "step": 158
+    },
+    {
+      "epoch": 1.5023696682464456,
+      "grad_norm": 1.2256115674972534,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 2.2221,
+      "step": 159
+    },
+    {
+      "epoch": 1.5118483412322274,
+      "grad_norm": 1.133819580078125,
+      "learning_rate": 1.162895473394589e-05,
+      "loss": 2.2709,
+      "step": 160
+    },
+    {
+      "epoch": 1.5213270142180095,
+      "grad_norm": 1.2712329626083374,
+      "learning_rate": 1.1521233861899168e-05,
+      "loss": 2.3259,
+      "step": 161
+    },
+    {
+      "epoch": 1.5308056872037916,
+      "grad_norm": 1.1242793798446655,
+      "learning_rate": 1.1413331978235677e-05,
+      "loss": 2.2541,
+      "step": 162
+    },
+    {
+      "epoch": 1.5402843601895735,
+      "grad_norm": 1.1369976997375488,
+      "learning_rate": 1.130526192220052e-05,
+      "loss": 2.3066,
+      "step": 163
+    },
+    {
+      "epoch": 1.5497630331753554,
+      "grad_norm": 1.1637866497039795,
+      "learning_rate": 1.1197036553049626e-05,
+      "loss": 2.2572,
+      "step": 164
+    },
+    {
+      "epoch": 1.5592417061611374,
+      "grad_norm": 1.1549181938171387,
+      "learning_rate": 1.1088668748519646e-05,
+      "loss": 2.3492,
+      "step": 165
+    },
+    {
+      "epoch": 1.5687203791469195,
+      "grad_norm": 1.8263827562332153,
+      "learning_rate": 1.098017140329561e-05,
+      "loss": 2.2654,
+      "step": 166
+    },
+    {
+      "epoch": 1.5781990521327014,
+      "grad_norm": 2.184051036834717,
+      "learning_rate": 1.0871557427476585e-05,
+      "loss": 2.1792,
+      "step": 167
+    },
+    {
+      "epoch": 1.5876777251184833,
+      "grad_norm": 1.0918291807174683,
+      "learning_rate": 1.0762839745039526e-05,
+      "loss": 2.3085,
+      "step": 168
+    },
+    {
+      "epoch": 1.5971563981042654,
+      "grad_norm": 1.1960687637329102,
+      "learning_rate": 1.0654031292301432e-05,
+      "loss": 2.2613,
+      "step": 169
+    },
+    {
+      "epoch": 1.6066350710900474,
+      "grad_norm": 1.1339130401611328,
+      "learning_rate": 1.0545145016380065e-05,
+      "loss": 2.2101,
+      "step": 170
+    },
+    {
+      "epoch": 1.6161137440758293,
+      "grad_norm": 1.076588749885559,
+      "learning_rate": 1.0436193873653362e-05,
+      "loss": 2.2652,
+      "step": 171
+    },
+    {
+      "epoch": 1.6255924170616114,
+      "grad_norm": 1.0522938966751099,
+      "learning_rate": 1.0327190828217763e-05,
+      "loss": 2.2018,
+      "step": 172
+    },
+    {
+      "epoch": 1.6350710900473935,
+      "grad_norm": 1.137953758239746,
+      "learning_rate": 1.0218148850345613e-05,
+      "loss": 2.1993,
+      "step": 173
+    },
+    {
+      "epoch": 1.6445497630331753,
+      "grad_norm": 1.147080898284912,
+      "learning_rate": 1.0109080914941825e-05,
+      "loss": 2.2474,
+      "step": 174
+    },
+    {
+      "epoch": 1.6540284360189572,
+      "grad_norm": 1.111204981803894,
+      "learning_rate": 1e-05,
+      "loss": 2.258,
+      "step": 175
+    },
+    {
+      "epoch": 1.6635071090047393,
+      "grad_norm": 1.1011035442352295,
+      "learning_rate": 9.890919085058179e-06,
+      "loss": 2.2643,
+      "step": 176
+    },
+    {
+      "epoch": 1.6729857819905214,
+      "grad_norm": 1.18864107131958,
+      "learning_rate": 9.78185114965439e-06,
+      "loss": 2.3374,
+      "step": 177
+    },
+    {
+      "epoch": 1.6824644549763033,
+      "grad_norm": 1.4493237733840942,
+      "learning_rate": 9.67280917178224e-06,
+      "loss": 2.2591,
+      "step": 178
+    },
+    {
+      "epoch": 1.6919431279620853,
+      "grad_norm": 1.218247413635254,
+      "learning_rate": 9.563806126346643e-06,
+      "loss": 2.2945,
+      "step": 179
+    },
+    {
+      "epoch": 1.7014218009478674,
+      "grad_norm": 1.1910370588302612,
+      "learning_rate": 9.454854983619936e-06,
+      "loss": 2.2092,
+      "step": 180
+    },
+    {
+      "epoch": 1.7109004739336493,
+      "grad_norm": 1.2177734375,
+      "learning_rate": 9.34596870769857e-06,
+      "loss": 2.3225,
+      "step": 181
+    },
+    {
+      "epoch": 1.7203791469194312,
+      "grad_norm": 1.3048025369644165,
+      "learning_rate": 9.237160254960477e-06,
+      "loss": 2.3232,
+      "step": 182
+    },
+    {
+      "epoch": 1.7298578199052133,
+      "grad_norm": 1.2348284721374512,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 2.2683,
+      "step": 183
+    },
+    {
+      "epoch": 1.7393364928909953,
+      "grad_norm": 1.0725488662719727,
+      "learning_rate": 9.019828596704394e-06,
+      "loss": 2.1446,
+      "step": 184
+    },
+    {
+      "epoch": 1.7488151658767772,
+      "grad_norm": 1.0923892259597778,
+      "learning_rate": 8.911331251480357e-06,
+      "loss": 2.197,
+      "step": 185
+    },
+    {
+      "epoch": 1.758293838862559,
+      "grad_norm": 1.2618827819824219,
+      "learning_rate": 8.802963446950378e-06,
+      "loss": 2.2826,
+      "step": 186
+    },
+    {
+      "epoch": 1.7677725118483414,
+      "grad_norm": 1.2491176128387451,
+      "learning_rate": 8.694738077799487e-06,
+      "loss": 2.3177,
+      "step": 187
+    },
+    {
+      "epoch": 1.7772511848341233,
+      "grad_norm": 1.2089641094207764,
+      "learning_rate": 8.586668021764328e-06,
+      "loss": 2.2569,
+      "step": 188
+    },
+    {
+      "epoch": 1.7867298578199051,
+      "grad_norm": 1.1279925107955933,
+      "learning_rate": 8.478766138100834e-06,
+      "loss": 2.2282,
+      "step": 189
+    },
+    {
+      "epoch": 1.7962085308056872,
+      "grad_norm": 1.251165747642517,
+      "learning_rate": 8.371045266054114e-06,
+      "loss": 2.2188,
+      "step": 190
+    },
+    {
+      "epoch": 1.8056872037914693,
+      "grad_norm": 1.268534541130066,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 2.342,
+      "step": 191
+    },
+    {
+      "epoch": 1.8151658767772512,
+      "grad_norm": 1.401013970375061,
+      "learning_rate": 8.156197804573368e-06,
+      "loss": 2.2666,
+      "step": 192
+    },
+    {
+      "epoch": 1.824644549763033,
+      "grad_norm": 1.194873332977295,
+      "learning_rate": 8.04909677983872e-06,
+      "loss": 2.3066,
+      "step": 193
+    },
+    {
+      "epoch": 1.8341232227488151,
+      "grad_norm": 1.1607239246368408,
+      "learning_rate": 7.942227893077652e-06,
+      "loss": 2.1649,
+      "step": 194
+    },
+    {
+      "epoch": 1.8436018957345972,
+      "grad_norm": 1.2142109870910645,
+      "learning_rate": 7.835603860618973e-06,
+      "loss": 2.247,
+      "step": 195
+    },
+    {
+      "epoch": 1.853080568720379,
+      "grad_norm": 1.1745545864105225,
+      "learning_rate": 7.72923736965627e-06,
+      "loss": 2.2399,
+      "step": 196
+    },
+    {
+      "epoch": 1.8625592417061612,
+      "grad_norm": 1.1588683128356934,
+      "learning_rate": 7.623141076738271e-06,
+      "loss": 2.2041,
+      "step": 197
+    },
+    {
+      "epoch": 1.8720379146919433,
+      "grad_norm": 1.2988152503967285,
+      "learning_rate": 7.5173276062628364e-06,
+      "loss": 2.2678,
+      "step": 198
+    },
+    {
+      "epoch": 1.8815165876777251,
+      "grad_norm": 1.1855872869491577,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 2.2461,
+      "step": 199
+    },
+    {
+      "epoch": 1.890995260663507,
+      "grad_norm": 1.379715919494629,
+      "learning_rate": 7.306599460467741e-06,
+      "loss": 2.2438,
+      "step": 200
+    },
+    {
+      "epoch": 1.900473933649289,
+      "grad_norm": 1.2153151035308838,
+      "learning_rate": 7.201709859690081e-06,
+      "loss": 2.3228,
+      "step": 201
+    },
+    {
+      "epoch": 1.9099526066350712,
+      "grad_norm": 1.2174468040466309,
+      "learning_rate": 7.097153227455379e-06,
+      "loss": 2.3403,
+      "step": 202
+    },
+    {
+      "epoch": 1.919431279620853,
+      "grad_norm": 1.1492794752120972,
+      "learning_rate": 6.992942004957271e-06,
+      "loss": 2.2773,
+      "step": 203
+    },
+    {
+      "epoch": 1.9289099526066351,
+      "grad_norm": 1.3066004514694214,
+      "learning_rate": 6.889088592289092e-06,
+      "loss": 2.1981,
+      "step": 204
+    },
+    {
+      "epoch": 1.9383886255924172,
+      "grad_norm": 2.041125774383545,
+      "learning_rate": 6.785605346968387e-06,
+      "loss": 2.2094,
+      "step": 205
+    },
+    {
+      "epoch": 1.947867298578199,
+      "grad_norm": 1.2032493352890015,
+      "learning_rate": 6.682504582466482e-06,
+      "loss": 2.2519,
+      "step": 206
+    },
+    {
+      "epoch": 1.957345971563981,
+      "grad_norm": 1.9550625085830688,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 2.3024,
+      "step": 207
+    },
+    {
+      "epoch": 1.966824644549763,
+      "grad_norm": 1.1052924394607544,
+      "learning_rate": 6.4774995207876654e-06,
+      "loss": 2.2448,
+      "step": 208
+    },
+    {
+      "epoch": 1.9763033175355451,
+      "grad_norm": 1.244057059288025,
+      "learning_rate": 6.375619617162985e-06,
+      "loss": 2.2521,
+      "step": 209
+    },
+    {
+      "epoch": 1.985781990521327,
+      "grad_norm": 1.2490400075912476,
+      "learning_rate": 6.274170978558971e-06,
+      "loss": 2.2775,
+      "step": 210
+    },
+    {
+      "epoch": 1.9952606635071088,
+      "grad_norm": 1.2607371807098389,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 2.2871,
+      "step": 211
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.732487440109253,
+      "learning_rate": 6.072615729154261e-06,
+      "loss": 2.3964,
+      "step": 212
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 318,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3818863769915392e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a808b1a76bc9dc7d9db19cc2f690af09bf5132a302d7020448c02a55865d7c3b
+size 5752