upload psa adpter model

.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
+checkpoint-2127/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2127/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ../../models/Qwen/Qwen2.5-Math-7B-Instruct/
+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 0.13.0

checkpoint-2127/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../../models/Qwen/Qwen2.5-Math-7B-Instruct/",
+  "bias": "none",
+  "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_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2127/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3517dced1affca804e1a9bb9ff1fda3e7e4030eaf2a24333d0ee13aff5504e40
+size 10107280

checkpoint-2127/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-2127/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a0c6fdc5f200dee275da69c6f96818c32a23e098c4842eb5f8288342f6c91d5
+size 20279354

checkpoint-2127/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b08762386422a34a85822bb6366858d07df65208e906d2bfa93a7ba19366401
+size 15984

checkpoint-2127/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c4ca88cd901fa449beff9077902223038e3bb23df5bb8a5c7ec1986096d4da
+size 15984

checkpoint-2127/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd57b8d61550bc8c754589f93ed161adb6b7b30b2462a16c45fcb0ea18fff2c
+size 15984

checkpoint-2127/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f3379d81f24a6c22e808aa2ba4f987432e4be8e5db2a7c83b27ffbaa26baaf
+size 15984

checkpoint-2127/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083adb431382b0489925abfb105db5694f517d39a37c4aff664f934ce612881c
+size 15984

checkpoint-2127/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba12ed26fd475f2f322c77b441cd3fac568be3374f9b28eb4f302686d11aa5a
+size 15984

checkpoint-2127/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11613b62c5ac6b810e5e0dabf6736c43d354660bb1b71e2b64429143812ceaf1
+size 15984

checkpoint-2127/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2154461b9736f491d10f7e8abcfd989ce7bca07f29b7910d5dc015dc38747fc6
+size 15984

checkpoint-2127/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dcd6a4453c34e7244f52a3e53ec78cf3c00e24edca6be6ae10b4a957c25343c
+size 1064

checkpoint-2127/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!"
+}

checkpoint-2127/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463b5f18d1fbc4ef3c9bbe405c4f87dbba4de372db9b322238303cc56c4d7a39
+size 11422158

checkpoint-2127/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "!",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2127/trainer_state.json

@@ -0,0 +1,1517 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998824773768951,
+  "eval_steps": 500,
+  "global_step": 2127,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004700904924197908,
+      "grad_norm": 4.338921070098877,
+      "learning_rate": 9.984328475160634e-05,
+      "loss": 10.2575,
+      "step": 10
+    },
+    {
+      "epoch": 0.009401809848395816,
+      "grad_norm": 7.385047435760498,
+      "learning_rate": 9.968656950321266e-05,
+      "loss": 8.7185,
+      "step": 20
+    },
+    {
+      "epoch": 0.014102714772593724,
+      "grad_norm": 8.822163581848145,
+      "learning_rate": 9.9529854254819e-05,
+      "loss": 6.0204,
+      "step": 30
+    },
+    {
+      "epoch": 0.018803619696791632,
+      "grad_norm": 5.8417487144470215,
+      "learning_rate": 9.937313900642533e-05,
+      "loss": 3.0597,
+      "step": 40
+    },
+    {
+      "epoch": 0.02350452462098954,
+      "grad_norm": 1.655334711074829,
+      "learning_rate": 9.921642375803167e-05,
+      "loss": 1.1494,
+      "step": 50
+    },
+    {
+      "epoch": 0.028205429545187448,
+      "grad_norm": 1.3080294132232666,
+      "learning_rate": 9.905970850963799e-05,
+      "loss": 0.6757,
+      "step": 60
+    },
+    {
+      "epoch": 0.03290633446938536,
+      "grad_norm": 3.848752975463867,
+      "learning_rate": 9.890299326124433e-05,
+      "loss": 0.6138,
+      "step": 70
+    },
+    {
+      "epoch": 0.037607239393583264,
+      "grad_norm": 1.6154791116714478,
+      "learning_rate": 9.874627801285066e-05,
+      "loss": 0.5528,
+      "step": 80
+    },
+    {
+      "epoch": 0.042308144317781175,
+      "grad_norm": 2.7457191944122314,
+      "learning_rate": 9.858956276445698e-05,
+      "loss": 0.5178,
+      "step": 90
+    },
+    {
+      "epoch": 0.04700904924197908,
+      "grad_norm": 1.5741740465164185,
+      "learning_rate": 9.843284751606332e-05,
+      "loss": 0.4926,
+      "step": 100
+    },
+    {
+      "epoch": 0.05170995416617699,
+      "grad_norm": 1.9329739809036255,
+      "learning_rate": 9.827613226766966e-05,
+      "loss": 0.5021,
+      "step": 110
+    },
+    {
+      "epoch": 0.056410859090374896,
+      "grad_norm": 2.349841594696045,
+      "learning_rate": 9.811941701927598e-05,
+      "loss": 0.4663,
+      "step": 120
+    },
+    {
+      "epoch": 0.06111176401457281,
+      "grad_norm": 1.533464789390564,
+      "learning_rate": 9.796270177088231e-05,
+      "loss": 0.4732,
+      "step": 130
+    },
+    {
+      "epoch": 0.06581266893877072,
+      "grad_norm": 3.456256866455078,
+      "learning_rate": 9.780598652248865e-05,
+      "loss": 0.4624,
+      "step": 140
+    },
+    {
+      "epoch": 0.07051357386296862,
+      "grad_norm": 2.1807849407196045,
+      "learning_rate": 9.764927127409498e-05,
+      "loss": 0.4604,
+      "step": 150
+    },
+    {
+      "epoch": 0.07521447878716653,
+      "grad_norm": 2.223006010055542,
+      "learning_rate": 9.74925560257013e-05,
+      "loss": 0.4526,
+      "step": 160
+    },
+    {
+      "epoch": 0.07991538371136443,
+      "grad_norm": 1.5491483211517334,
+      "learning_rate": 9.733584077730764e-05,
+      "loss": 0.4454,
+      "step": 170
+    },
+    {
+      "epoch": 0.08461628863556235,
+      "grad_norm": 0.9801793694496155,
+      "learning_rate": 9.717912552891398e-05,
+      "loss": 0.4565,
+      "step": 180
+    },
+    {
+      "epoch": 0.08931719355976026,
+      "grad_norm": 1.4270861148834229,
+      "learning_rate": 9.70224102805203e-05,
+      "loss": 0.4499,
+      "step": 190
+    },
+    {
+      "epoch": 0.09401809848395816,
+      "grad_norm": 1.1395397186279297,
+      "learning_rate": 9.686569503212663e-05,
+      "loss": 0.4452,
+      "step": 200
+    },
+    {
+      "epoch": 0.09871900340815606,
+      "grad_norm": 4.200931072235107,
+      "learning_rate": 9.670897978373297e-05,
+      "loss": 0.4351,
+      "step": 210
+    },
+    {
+      "epoch": 0.10341990833235398,
+      "grad_norm": 0.9431071281433105,
+      "learning_rate": 9.655226453533929e-05,
+      "loss": 0.4445,
+      "step": 220
+    },
+    {
+      "epoch": 0.10812081325655189,
+      "grad_norm": 1.4455124139785767,
+      "learning_rate": 9.639554928694561e-05,
+      "loss": 0.4287,
+      "step": 230
+    },
+    {
+      "epoch": 0.11282171818074979,
+      "grad_norm": 0.823145866394043,
+      "learning_rate": 9.623883403855195e-05,
+      "loss": 0.4267,
+      "step": 240
+    },
+    {
+      "epoch": 0.1175226231049477,
+      "grad_norm": 1.3632913827896118,
+      "learning_rate": 9.608211879015829e-05,
+      "loss": 0.4237,
+      "step": 250
+    },
+    {
+      "epoch": 0.12222352802914561,
+      "grad_norm": 2.7535300254821777,
+      "learning_rate": 9.592540354176461e-05,
+      "loss": 0.4515,
+      "step": 260
+    },
+    {
+      "epoch": 0.12692443295334352,
+      "grad_norm": 2.66774320602417,
+      "learning_rate": 9.576868829337094e-05,
+      "loss": 0.433,
+      "step": 270
+    },
+    {
+      "epoch": 0.13162533787754144,
+      "grad_norm": 1.775460958480835,
+      "learning_rate": 9.561197304497728e-05,
+      "loss": 0.4218,
+      "step": 280
+    },
+    {
+      "epoch": 0.13632624280173933,
+      "grad_norm": 0.793785810470581,
+      "learning_rate": 9.545525779658361e-05,
+      "loss": 0.4276,
+      "step": 290
+    },
+    {
+      "epoch": 0.14102714772593725,
+      "grad_norm": 3.0376343727111816,
+      "learning_rate": 9.529854254818994e-05,
+      "loss": 0.4304,
+      "step": 300
+    },
+    {
+      "epoch": 0.14572805265013516,
+      "grad_norm": 1.9679210186004639,
+      "learning_rate": 9.514182729979627e-05,
+      "loss": 0.4298,
+      "step": 310
+    },
+    {
+      "epoch": 0.15042895757433306,
+      "grad_norm": 1.2378153800964355,
+      "learning_rate": 9.498511205140261e-05,
+      "loss": 0.4092,
+      "step": 320
+    },
+    {
+      "epoch": 0.15512986249853097,
+      "grad_norm": 1.2181652784347534,
+      "learning_rate": 9.482839680300893e-05,
+      "loss": 0.4088,
+      "step": 330
+    },
+    {
+      "epoch": 0.15983076742272886,
+      "grad_norm": 1.3195668458938599,
+      "learning_rate": 9.467168155461526e-05,
+      "loss": 0.4027,
+      "step": 340
+    },
+    {
+      "epoch": 0.16453167234692678,
+      "grad_norm": 1.101954460144043,
+      "learning_rate": 9.45149663062216e-05,
+      "loss": 0.4299,
+      "step": 350
+    },
+    {
+      "epoch": 0.1692325772711247,
+      "grad_norm": 3.099776029586792,
+      "learning_rate": 9.435825105782794e-05,
+      "loss": 0.4082,
+      "step": 360
+    },
+    {
+      "epoch": 0.1739334821953226,
+      "grad_norm": 0.898208737373352,
+      "learning_rate": 9.420153580943426e-05,
+      "loss": 0.4148,
+      "step": 370
+    },
+    {
+      "epoch": 0.1786343871195205,
+      "grad_norm": 1.2357901334762573,
+      "learning_rate": 9.404482056104059e-05,
+      "loss": 0.4085,
+      "step": 380
+    },
+    {
+      "epoch": 0.18333529204371843,
+      "grad_norm": 1.5340213775634766,
+      "learning_rate": 9.388810531264693e-05,
+      "loss": 0.4186,
+      "step": 390
+    },
+    {
+      "epoch": 0.18803619696791632,
+      "grad_norm": 0.8089154958724976,
+      "learning_rate": 9.373139006425325e-05,
+      "loss": 0.4114,
+      "step": 400
+    },
+    {
+      "epoch": 0.19273710189211424,
+      "grad_norm": 1.6185780763626099,
+      "learning_rate": 9.357467481585959e-05,
+      "loss": 0.411,
+      "step": 410
+    },
+    {
+      "epoch": 0.19743800681631213,
+      "grad_norm": 0.8345431089401245,
+      "learning_rate": 9.341795956746592e-05,
+      "loss": 0.41,
+      "step": 420
+    },
+    {
+      "epoch": 0.20213891174051005,
+      "grad_norm": 2.1437103748321533,
+      "learning_rate": 9.326124431907224e-05,
+      "loss": 0.4085,
+      "step": 430
+    },
+    {
+      "epoch": 0.20683981666470797,
+      "grad_norm": 6.498870372772217,
+      "learning_rate": 9.310452907067858e-05,
+      "loss": 0.4038,
+      "step": 440
+    },
+    {
+      "epoch": 0.21154072158890586,
+      "grad_norm": 1.2205309867858887,
+      "learning_rate": 9.294781382228491e-05,
+      "loss": 0.4008,
+      "step": 450
+    },
+    {
+      "epoch": 0.21624162651310377,
+      "grad_norm": 1.253982424736023,
+      "learning_rate": 9.279109857389125e-05,
+      "loss": 0.3977,
+      "step": 460
+    },
+    {
+      "epoch": 0.2209425314373017,
+      "grad_norm": 3.27243971824646,
+      "learning_rate": 9.263438332549757e-05,
+      "loss": 0.4178,
+      "step": 470
+    },
+    {
+      "epoch": 0.22564343636149958,
+      "grad_norm": 2.4955010414123535,
+      "learning_rate": 9.247766807710391e-05,
+      "loss": 0.3986,
+      "step": 480
+    },
+    {
+      "epoch": 0.2303443412856975,
+      "grad_norm": 1.344426155090332,
+      "learning_rate": 9.232095282871024e-05,
+      "loss": 0.3956,
+      "step": 490
+    },
+    {
+      "epoch": 0.2350452462098954,
+      "grad_norm": 1.3640114068984985,
+      "learning_rate": 9.216423758031657e-05,
+      "loss": 0.3976,
+      "step": 500
+    },
+    {
+      "epoch": 0.2397461511340933,
+      "grad_norm": 0.8424949645996094,
+      "learning_rate": 9.20075223319229e-05,
+      "loss": 0.3913,
+      "step": 510
+    },
+    {
+      "epoch": 0.24444705605829123,
+      "grad_norm": 1.0781666040420532,
+      "learning_rate": 9.185080708352924e-05,
+      "loss": 0.4075,
+      "step": 520
+    },
+    {
+      "epoch": 0.24914796098248912,
+      "grad_norm": 0.9005725979804993,
+      "learning_rate": 9.169409183513556e-05,
+      "loss": 0.4197,
+      "step": 530
+    },
+    {
+      "epoch": 0.25384886590668704,
+      "grad_norm": 1.195514440536499,
+      "learning_rate": 9.15373765867419e-05,
+      "loss": 0.4066,
+      "step": 540
+    },
+    {
+      "epoch": 0.25854977083088493,
+      "grad_norm": 1.9088181257247925,
+      "learning_rate": 9.138066133834823e-05,
+      "loss": 0.4091,
+      "step": 550
+    },
+    {
+      "epoch": 0.2632506757550829,
+      "grad_norm": 0.9328345060348511,
+      "learning_rate": 9.122394608995457e-05,
+      "loss": 0.3988,
+      "step": 560
+    },
+    {
+      "epoch": 0.26795158067928077,
+      "grad_norm": 2.4227659702301025,
+      "learning_rate": 9.106723084156089e-05,
+      "loss": 0.391,
+      "step": 570
+    },
+    {
+      "epoch": 0.27265248560347866,
+      "grad_norm": 1.7708094120025635,
+      "learning_rate": 9.091051559316722e-05,
+      "loss": 0.3982,
+      "step": 580
+    },
+    {
+      "epoch": 0.2773533905276766,
+      "grad_norm": 1.006110668182373,
+      "learning_rate": 9.075380034477356e-05,
+      "loss": 0.394,
+      "step": 590
+    },
+    {
+      "epoch": 0.2820542954518745,
+      "grad_norm": 0.9397707581520081,
+      "learning_rate": 9.059708509637988e-05,
+      "loss": 0.3898,
+      "step": 600
+    },
+    {
+      "epoch": 0.2867552003760724,
+      "grad_norm": 1.3863813877105713,
+      "learning_rate": 9.044036984798622e-05,
+      "loss": 0.3898,
+      "step": 610
+    },
+    {
+      "epoch": 0.29145610530027033,
+      "grad_norm": 1.7617021799087524,
+      "learning_rate": 9.028365459959255e-05,
+      "loss": 0.3957,
+      "step": 620
+    },
+    {
+      "epoch": 0.2961570102244682,
+      "grad_norm": 1.261723518371582,
+      "learning_rate": 9.012693935119887e-05,
+      "loss": 0.3964,
+      "step": 630
+    },
+    {
+      "epoch": 0.3008579151486661,
+      "grad_norm": 0.7548590302467346,
+      "learning_rate": 8.997022410280521e-05,
+      "loss": 0.3995,
+      "step": 640
+    },
+    {
+      "epoch": 0.305558820072864,
+      "grad_norm": 1.4837889671325684,
+      "learning_rate": 8.981350885441154e-05,
+      "loss": 0.3729,
+      "step": 650
+    },
+    {
+      "epoch": 0.31025972499706195,
+      "grad_norm": 1.868475317955017,
+      "learning_rate": 8.965679360601788e-05,
+      "loss": 0.3701,
+      "step": 660
+    },
+    {
+      "epoch": 0.31496062992125984,
+      "grad_norm": 0.9629729390144348,
+      "learning_rate": 8.95000783576242e-05,
+      "loss": 0.399,
+      "step": 670
+    },
+    {
+      "epoch": 0.31966153484545773,
+      "grad_norm": 1.5730236768722534,
+      "learning_rate": 8.934336310923054e-05,
+      "loss": 0.3854,
+      "step": 680
+    },
+    {
+      "epoch": 0.3243624397696557,
+      "grad_norm": 1.4589276313781738,
+      "learning_rate": 8.918664786083686e-05,
+      "loss": 0.3879,
+      "step": 690
+    },
+    {
+      "epoch": 0.32906334469385357,
+      "grad_norm": 4.129764080047607,
+      "learning_rate": 8.90299326124432e-05,
+      "loss": 0.3868,
+      "step": 700
+    },
+    {
+      "epoch": 0.33376424961805146,
+      "grad_norm": 1.2538539171218872,
+      "learning_rate": 8.887321736404952e-05,
+      "loss": 0.4014,
+      "step": 710
+    },
+    {
+      "epoch": 0.3384651545422494,
+      "grad_norm": 2.5101168155670166,
+      "learning_rate": 8.871650211565585e-05,
+      "loss": 0.3855,
+      "step": 720
+    },
+    {
+      "epoch": 0.3431660594664473,
+      "grad_norm": 2.11893630027771,
+      "learning_rate": 8.855978686726219e-05,
+      "loss": 0.3847,
+      "step": 730
+    },
+    {
+      "epoch": 0.3478669643906452,
+      "grad_norm": 2.154590129852295,
+      "learning_rate": 8.840307161886851e-05,
+      "loss": 0.3726,
+      "step": 740
+    },
+    {
+      "epoch": 0.35256786931484313,
+      "grad_norm": 0.9320923686027527,
+      "learning_rate": 8.824635637047485e-05,
+      "loss": 0.3876,
+      "step": 750
+    },
+    {
+      "epoch": 0.357268774239041,
+      "grad_norm": 1.1086455583572388,
+      "learning_rate": 8.808964112208118e-05,
+      "loss": 0.3813,
+      "step": 760
+    },
+    {
+      "epoch": 0.3619696791632389,
+      "grad_norm": 1.0036139488220215,
+      "learning_rate": 8.793292587368752e-05,
+      "loss": 0.3802,
+      "step": 770
+    },
+    {
+      "epoch": 0.36667058408743686,
+      "grad_norm": 1.2812787294387817,
+      "learning_rate": 8.777621062529384e-05,
+      "loss": 0.383,
+      "step": 780
+    },
+    {
+      "epoch": 0.37137148901163475,
+      "grad_norm": 1.9546316862106323,
+      "learning_rate": 8.761949537690017e-05,
+      "loss": 0.3775,
+      "step": 790
+    },
+    {
+      "epoch": 0.37607239393583264,
+      "grad_norm": 0.9139639139175415,
+      "learning_rate": 8.746278012850651e-05,
+      "loss": 0.3725,
+      "step": 800
+    },
+    {
+      "epoch": 0.38077329886003053,
+      "grad_norm": 1.282999038696289,
+      "learning_rate": 8.730606488011283e-05,
+      "loss": 0.382,
+      "step": 810
+    },
+    {
+      "epoch": 0.3854742037842285,
+      "grad_norm": 1.0331751108169556,
+      "learning_rate": 8.714934963171917e-05,
+      "loss": 0.3765,
+      "step": 820
+    },
+    {
+      "epoch": 0.39017510870842637,
+      "grad_norm": 3.0494372844696045,
+      "learning_rate": 8.69926343833255e-05,
+      "loss": 0.3773,
+      "step": 830
+    },
+    {
+      "epoch": 0.39487601363262426,
+      "grad_norm": 1.0024981498718262,
+      "learning_rate": 8.683591913493183e-05,
+      "loss": 0.3889,
+      "step": 840
+    },
+    {
+      "epoch": 0.3995769185568222,
+      "grad_norm": 1.606170892715454,
+      "learning_rate": 8.667920388653816e-05,
+      "loss": 0.3585,
+      "step": 850
+    },
+    {
+      "epoch": 0.4042778234810201,
+      "grad_norm": 1.0149178504943848,
+      "learning_rate": 8.65224886381445e-05,
+      "loss": 0.3893,
+      "step": 860
+    },
+    {
+      "epoch": 0.408978728405218,
+      "grad_norm": 1.744429588317871,
+      "learning_rate": 8.636577338975083e-05,
+      "loss": 0.3788,
+      "step": 870
+    },
+    {
+      "epoch": 0.41367963332941593,
+      "grad_norm": 2.3995683193206787,
+      "learning_rate": 8.620905814135715e-05,
+      "loss": 0.3594,
+      "step": 880
+    },
+    {
+      "epoch": 0.4183805382536138,
+      "grad_norm": 2.227412700653076,
+      "learning_rate": 8.605234289296349e-05,
+      "loss": 0.3853,
+      "step": 890
+    },
+    {
+      "epoch": 0.4230814431778117,
+      "grad_norm": 1.6415226459503174,
+      "learning_rate": 8.589562764456982e-05,
+      "loss": 0.3835,
+      "step": 900
+    },
+    {
+      "epoch": 0.42778234810200966,
+      "grad_norm": 1.140038251876831,
+      "learning_rate": 8.573891239617615e-05,
+      "loss": 0.3742,
+      "step": 910
+    },
+    {
+      "epoch": 0.43248325302620755,
+      "grad_norm": 2.5346789360046387,
+      "learning_rate": 8.558219714778248e-05,
+      "loss": 0.3886,
+      "step": 920
+    },
+    {
+      "epoch": 0.43718415795040544,
+      "grad_norm": 1.060520887374878,
+      "learning_rate": 8.542548189938882e-05,
+      "loss": 0.3852,
+      "step": 930
+    },
+    {
+      "epoch": 0.4418850628746034,
+      "grad_norm": 2.0687763690948486,
+      "learning_rate": 8.526876665099514e-05,
+      "loss": 0.3782,
+      "step": 940
+    },
+    {
+      "epoch": 0.4465859677988013,
+      "grad_norm": 3.9409232139587402,
+      "learning_rate": 8.511205140260148e-05,
+      "loss": 0.3907,
+      "step": 950
+    },
+    {
+      "epoch": 0.45128687272299917,
+      "grad_norm": 2.1936776638031006,
+      "learning_rate": 8.495533615420781e-05,
+      "loss": 0.3758,
+      "step": 960
+    },
+    {
+      "epoch": 0.4559877776471971,
+      "grad_norm": 0.9638668298721313,
+      "learning_rate": 8.479862090581415e-05,
+      "loss": 0.3812,
+      "step": 970
+    },
+    {
+      "epoch": 0.460688682571395,
+      "grad_norm": 1.0724684000015259,
+      "learning_rate": 8.464190565742047e-05,
+      "loss": 0.3649,
+      "step": 980
+    },
+    {
+      "epoch": 0.4653895874955929,
+      "grad_norm": 1.2330756187438965,
+      "learning_rate": 8.44851904090268e-05,
+      "loss": 0.3878,
+      "step": 990
+    },
+    {
+      "epoch": 0.4700904924197908,
+      "grad_norm": 1.3528395891189575,
+      "learning_rate": 8.432847516063314e-05,
+      "loss": 0.3795,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47479139734398873,
+      "grad_norm": 1.3239601850509644,
+      "learning_rate": 8.417175991223946e-05,
+      "loss": 0.3881,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4794923022681866,
+      "grad_norm": 0.8255568146705627,
+      "learning_rate": 8.40150446638458e-05,
+      "loss": 0.3712,
+      "step": 1020
+    },
+    {
+      "epoch": 0.4841932071923845,
+      "grad_norm": 1.9237899780273438,
+      "learning_rate": 8.385832941545213e-05,
+      "loss": 0.3652,
+      "step": 1030
+    },
+    {
+      "epoch": 0.48889411211658246,
+      "grad_norm": 1.6184757947921753,
+      "learning_rate": 8.370161416705847e-05,
+      "loss": 0.3646,
+      "step": 1040
+    },
+    {
+      "epoch": 0.49359501704078035,
+      "grad_norm": 1.17612886428833,
+      "learning_rate": 8.354489891866479e-05,
+      "loss": 0.3751,
+      "step": 1050
+    },
+    {
+      "epoch": 0.49829592196497824,
+      "grad_norm": 1.3280194997787476,
+      "learning_rate": 8.338818367027113e-05,
+      "loss": 0.3873,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5029968268891761,
+      "grad_norm": 1.4673656225204468,
+      "learning_rate": 8.323146842187746e-05,
+      "loss": 0.3651,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5076977318133741,
+      "grad_norm": 1.5769989490509033,
+      "learning_rate": 8.307475317348378e-05,
+      "loss": 0.3751,
+      "step": 1080
+    },
+    {
+      "epoch": 0.512398636737572,
+      "grad_norm": 3.041260242462158,
+      "learning_rate": 8.291803792509012e-05,
+      "loss": 0.3754,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5170995416617699,
+      "grad_norm": 0.922623336315155,
+      "learning_rate": 8.276132267669645e-05,
+      "loss": 0.3722,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5218004465859678,
+      "grad_norm": 0.8527415990829468,
+      "learning_rate": 8.260460742830278e-05,
+      "loss": 0.3816,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5265013515101657,
+      "grad_norm": 1.1660065650939941,
+      "learning_rate": 8.244789217990911e-05,
+      "loss": 0.3844,
+      "step": 1120
+    },
+    {
+      "epoch": 0.5312022564343636,
+      "grad_norm": 2.7265124320983887,
+      "learning_rate": 8.229117693151545e-05,
+      "loss": 0.3579,
+      "step": 1130
+    },
+    {
+      "epoch": 0.5359031613585615,
+      "grad_norm": 0.9204573035240173,
+      "learning_rate": 8.213446168312177e-05,
+      "loss": 0.3848,
+      "step": 1140
+    },
+    {
+      "epoch": 0.5406040662827595,
+      "grad_norm": 1.0934752225875854,
+      "learning_rate": 8.197774643472809e-05,
+      "loss": 0.3652,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5453049712069573,
+      "grad_norm": 0.9822810888290405,
+      "learning_rate": 8.182103118633443e-05,
+      "loss": 0.3784,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5500058761311553,
+      "grad_norm": 1.0165129899978638,
+      "learning_rate": 8.166431593794076e-05,
+      "loss": 0.3728,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5547067810553532,
+      "grad_norm": 1.2013338804244995,
+      "learning_rate": 8.15076006895471e-05,
+      "loss": 0.3552,
+      "step": 1180
+    },
+    {
+      "epoch": 0.559407685979551,
+      "grad_norm": 1.170253872871399,
+      "learning_rate": 8.135088544115342e-05,
+      "loss": 0.3725,
+      "step": 1190
+    },
+    {
+      "epoch": 0.564108590903749,
+      "grad_norm": 0.8883313536643982,
+      "learning_rate": 8.119417019275976e-05,
+      "loss": 0.3504,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5688094958279469,
+      "grad_norm": 2.107287883758545,
+      "learning_rate": 8.103745494436609e-05,
+      "loss": 0.3586,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5735104007521448,
+      "grad_norm": 1.9556785821914673,
+      "learning_rate": 8.088073969597241e-05,
+      "loss": 0.3596,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5782113056763427,
+      "grad_norm": 1.024415373802185,
+      "learning_rate": 8.072402444757875e-05,
+      "loss": 0.3642,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5829122106005407,
+      "grad_norm": 3.524789333343506,
+      "learning_rate": 8.056730919918508e-05,
+      "loss": 0.3695,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5876131155247385,
+      "grad_norm": 1.3371467590332031,
+      "learning_rate": 8.04105939507914e-05,
+      "loss": 0.3736,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5923140204489364,
+      "grad_norm": 1.91169011592865,
+      "learning_rate": 8.025387870239774e-05,
+      "loss": 0.3653,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.9362313747406006,
+      "learning_rate": 8.009716345400408e-05,
+      "loss": 0.3813,
+      "step": 1270
+    },
+    {
+      "epoch": 0.6017158302973322,
+      "grad_norm": 2.3379788398742676,
+      "learning_rate": 7.994044820561041e-05,
+      "loss": 0.3606,
+      "step": 1280
+    },
+    {
+      "epoch": 0.6064167352215302,
+      "grad_norm": 1.9221323728561401,
+      "learning_rate": 7.978373295721674e-05,
+      "loss": 0.3706,
+      "step": 1290
+    },
+    {
+      "epoch": 0.611117640145728,
+      "grad_norm": 2.1025121212005615,
+      "learning_rate": 7.962701770882307e-05,
+      "loss": 0.3585,
+      "step": 1300
+    },
+    {
+      "epoch": 0.615818545069926,
+      "grad_norm": 1.7160892486572266,
+      "learning_rate": 7.94703024604294e-05,
+      "loss": 0.3849,
+      "step": 1310
+    },
+    {
+      "epoch": 0.6205194499941239,
+      "grad_norm": 1.290818691253662,
+      "learning_rate": 7.931358721203573e-05,
+      "loss": 0.377,
+      "step": 1320
+    },
+    {
+      "epoch": 0.6252203549183217,
+      "grad_norm": 0.9813281297683716,
+      "learning_rate": 7.915687196364206e-05,
+      "loss": 0.365,
+      "step": 1330
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 0.9623616933822632,
+      "learning_rate": 7.90001567152484e-05,
+      "loss": 0.3496,
+      "step": 1340
+    },
+    {
+      "epoch": 0.6346221647667176,
+      "grad_norm": 1.3078798055648804,
+      "learning_rate": 7.884344146685473e-05,
+      "loss": 0.3643,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6393230696909155,
+      "grad_norm": 0.9925209879875183,
+      "learning_rate": 7.868672621846106e-05,
+      "loss": 0.3608,
+      "step": 1360
+    },
+    {
+      "epoch": 0.6440239746151134,
+      "grad_norm": 1.515331745147705,
+      "learning_rate": 7.853001097006739e-05,
+      "loss": 0.388,
+      "step": 1370
+    },
+    {
+      "epoch": 0.6487248795393113,
+      "grad_norm": 2.109877586364746,
+      "learning_rate": 7.837329572167373e-05,
+      "loss": 0.3605,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6534257844635092,
+      "grad_norm": 1.320446491241455,
+      "learning_rate": 7.821658047328005e-05,
+      "loss": 0.3729,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6581266893877071,
+      "grad_norm": 1.2624431848526,
+      "learning_rate": 7.805986522488639e-05,
+      "loss": 0.3637,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6628275943119051,
+      "grad_norm": 1.3101025819778442,
+      "learning_rate": 7.790314997649272e-05,
+      "loss": 0.3738,
+      "step": 1410
+    },
+    {
+      "epoch": 0.6675284992361029,
+      "grad_norm": 1.3762035369873047,
+      "learning_rate": 7.774643472809904e-05,
+      "loss": 0.364,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6722294041603009,
+      "grad_norm": 1.7407734394073486,
+      "learning_rate": 7.758971947970538e-05,
+      "loss": 0.3405,
+      "step": 1430
+    },
+    {
+      "epoch": 0.6769303090844988,
+      "grad_norm": 1.209085464477539,
+      "learning_rate": 7.743300423131171e-05,
+      "loss": 0.3621,
+      "step": 1440
+    },
+    {
+      "epoch": 0.6816312140086966,
+      "grad_norm": 2.3257131576538086,
+      "learning_rate": 7.727628898291805e-05,
+      "loss": 0.3524,
+      "step": 1450
+    },
+    {
+      "epoch": 0.6863321189328946,
+      "grad_norm": 1.5234692096710205,
+      "learning_rate": 7.711957373452437e-05,
+      "loss": 0.3556,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6910330238570925,
+      "grad_norm": 2.3267507553100586,
+      "learning_rate": 7.696285848613071e-05,
+      "loss": 0.3589,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6957339287812904,
+      "grad_norm": 1.8741614818572998,
+      "learning_rate": 7.680614323773704e-05,
+      "loss": 0.3651,
+      "step": 1480
+    },
+    {
+      "epoch": 0.7004348337054883,
+      "grad_norm": 2.3814918994903564,
+      "learning_rate": 7.664942798934336e-05,
+      "loss": 0.3568,
+      "step": 1490
+    },
+    {
+      "epoch": 0.7051357386296863,
+      "grad_norm": 3.497832775115967,
+      "learning_rate": 7.64927127409497e-05,
+      "loss": 0.3723,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7098366435538841,
+      "grad_norm": 2.1036434173583984,
+      "learning_rate": 7.633599749255604e-05,
+      "loss": 0.3708,
+      "step": 1510
+    },
+    {
+      "epoch": 0.714537548478082,
+      "grad_norm": 2.3688840866088867,
+      "learning_rate": 7.617928224416236e-05,
+      "loss": 0.3673,
+      "step": 1520
+    },
+    {
+      "epoch": 0.71923845340228,
+      "grad_norm": 1.6410322189331055,
+      "learning_rate": 7.60225669957687e-05,
+      "loss": 0.3727,
+      "step": 1530
+    },
+    {
+      "epoch": 0.7239393583264778,
+      "grad_norm": 1.0293692350387573,
+      "learning_rate": 7.586585174737503e-05,
+      "loss": 0.3751,
+      "step": 1540
+    },
+    {
+      "epoch": 0.7286402632506758,
+      "grad_norm": 1.794756293296814,
+      "learning_rate": 7.570913649898136e-05,
+      "loss": 0.3612,
+      "step": 1550
+    },
+    {
+      "epoch": 0.7333411681748737,
+      "grad_norm": 2.0058727264404297,
+      "learning_rate": 7.555242125058769e-05,
+      "loss": 0.3734,
+      "step": 1560
+    },
+    {
+      "epoch": 0.7380420730990715,
+      "grad_norm": 1.8430676460266113,
+      "learning_rate": 7.539570600219402e-05,
+      "loss": 0.3533,
+      "step": 1570
+    },
+    {
+      "epoch": 0.7427429780232695,
+      "grad_norm": 1.2136273384094238,
+      "learning_rate": 7.523899075380036e-05,
+      "loss": 0.3398,
+      "step": 1580
+    },
+    {
+      "epoch": 0.7474438829474674,
+      "grad_norm": 0.9999972581863403,
+      "learning_rate": 7.508227550540668e-05,
+      "loss": 0.3322,
+      "step": 1590
+    },
+    {
+      "epoch": 0.7521447878716653,
+      "grad_norm": 1.4663593769073486,
+      "learning_rate": 7.4925560257013e-05,
+      "loss": 0.3588,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7568456927958632,
+      "grad_norm": 0.8715286254882812,
+      "learning_rate": 7.476884500861934e-05,
+      "loss": 0.3566,
+      "step": 1610
+    },
+    {
+      "epoch": 0.7615465977200611,
+      "grad_norm": 1.7180976867675781,
+      "learning_rate": 7.461212976022567e-05,
+      "loss": 0.3544,
+      "step": 1620
+    },
+    {
+      "epoch": 0.766247502644259,
+      "grad_norm": 2.3892838954925537,
+      "learning_rate": 7.4455414511832e-05,
+      "loss": 0.3537,
+      "step": 1630
+    },
+    {
+      "epoch": 0.770948407568457,
+      "grad_norm": 1.2725646495819092,
+      "learning_rate": 7.429869926343833e-05,
+      "loss": 0.3575,
+      "step": 1640
+    },
+    {
+      "epoch": 0.7756493124926548,
+      "grad_norm": 1.1861917972564697,
+      "learning_rate": 7.414198401504467e-05,
+      "loss": 0.3588,
+      "step": 1650
+    },
+    {
+      "epoch": 0.7803502174168527,
+      "grad_norm": 1.6121189594268799,
+      "learning_rate": 7.398526876665099e-05,
+      "loss": 0.3554,
+      "step": 1660
+    },
+    {
+      "epoch": 0.7850511223410507,
+      "grad_norm": 1.183447003364563,
+      "learning_rate": 7.382855351825732e-05,
+      "loss": 0.3399,
+      "step": 1670
+    },
+    {
+      "epoch": 0.7897520272652485,
+      "grad_norm": 0.9614543318748474,
+      "learning_rate": 7.367183826986366e-05,
+      "loss": 0.3505,
+      "step": 1680
+    },
+    {
+      "epoch": 0.7944529321894465,
+      "grad_norm": 2.463824510574341,
+      "learning_rate": 7.351512302147e-05,
+      "loss": 0.3535,
+      "step": 1690
+    },
+    {
+      "epoch": 0.7991538371136444,
+      "grad_norm": 1.1036416292190552,
+      "learning_rate": 7.335840777307632e-05,
+      "loss": 0.3492,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8038547420378422,
+      "grad_norm": 1.4613536596298218,
+      "learning_rate": 7.320169252468265e-05,
+      "loss": 0.351,
+      "step": 1710
+    },
+    {
+      "epoch": 0.8085556469620402,
+      "grad_norm": 1.2614613771438599,
+      "learning_rate": 7.304497727628899e-05,
+      "loss": 0.3505,
+      "step": 1720
+    },
+    {
+      "epoch": 0.8132565518862381,
+      "grad_norm": 1.1639400720596313,
+      "learning_rate": 7.288826202789531e-05,
+      "loss": 0.3657,
+      "step": 1730
+    },
+    {
+      "epoch": 0.817957456810436,
+      "grad_norm": 1.6838788986206055,
+      "learning_rate": 7.273154677950165e-05,
+      "loss": 0.3503,
+      "step": 1740
+    },
+    {
+      "epoch": 0.8226583617346339,
+      "grad_norm": 1.0945839881896973,
+      "learning_rate": 7.257483153110798e-05,
+      "loss": 0.3551,
+      "step": 1750
+    },
+    {
+      "epoch": 0.8273592666588319,
+      "grad_norm": 1.1545921564102173,
+      "learning_rate": 7.241811628271432e-05,
+      "loss": 0.3488,
+      "step": 1760
+    },
+    {
+      "epoch": 0.8320601715830297,
+      "grad_norm": 0.9361588954925537,
+      "learning_rate": 7.226140103432064e-05,
+      "loss": 0.3454,
+      "step": 1770
+    },
+    {
+      "epoch": 0.8367610765072276,
+      "grad_norm": 0.959794819355011,
+      "learning_rate": 7.210468578592697e-05,
+      "loss": 0.3571,
+      "step": 1780
+    },
+    {
+      "epoch": 0.8414619814314256,
+      "grad_norm": 1.1152044534683228,
+      "learning_rate": 7.194797053753331e-05,
+      "loss": 0.3713,
+      "step": 1790
+    },
+    {
+      "epoch": 0.8461628863556234,
+      "grad_norm": 1.7348166704177856,
+      "learning_rate": 7.179125528913963e-05,
+      "loss": 0.3407,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8508637912798214,
+      "grad_norm": 2.3188705444335938,
+      "learning_rate": 7.163454004074597e-05,
+      "loss": 0.3489,
+      "step": 1810
+    },
+    {
+      "epoch": 0.8555646962040193,
+      "grad_norm": 1.529905915260315,
+      "learning_rate": 7.14778247923523e-05,
+      "loss": 0.3385,
+      "step": 1820
+    },
+    {
+      "epoch": 0.8602656011282171,
+      "grad_norm": 1.2101613283157349,
+      "learning_rate": 7.132110954395862e-05,
+      "loss": 0.355,
+      "step": 1830
+    },
+    {
+      "epoch": 0.8649665060524151,
+      "grad_norm": 1.4338616132736206,
+      "learning_rate": 7.116439429556496e-05,
+      "loss": 0.3534,
+      "step": 1840
+    },
+    {
+      "epoch": 0.869667410976613,
+      "grad_norm": 1.2460179328918457,
+      "learning_rate": 7.10076790471713e-05,
+      "loss": 0.3537,
+      "step": 1850
+    },
+    {
+      "epoch": 0.8743683159008109,
+      "grad_norm": 1.6369551420211792,
+      "learning_rate": 7.085096379877763e-05,
+      "loss": 0.3514,
+      "step": 1860
+    },
+    {
+      "epoch": 0.8790692208250088,
+      "grad_norm": 2.6983251571655273,
+      "learning_rate": 7.069424855038395e-05,
+      "loss": 0.348,
+      "step": 1870
+    },
+    {
+      "epoch": 0.8837701257492068,
+      "grad_norm": 1.2817703485488892,
+      "learning_rate": 7.053753330199029e-05,
+      "loss": 0.3505,
+      "step": 1880
+    },
+    {
+      "epoch": 0.8884710306734046,
+      "grad_norm": 1.0121359825134277,
+      "learning_rate": 7.038081805359662e-05,
+      "loss": 0.344,
+      "step": 1890
+    },
+    {
+      "epoch": 0.8931719355976026,
+      "grad_norm": 0.9417720437049866,
+      "learning_rate": 7.022410280520295e-05,
+      "loss": 0.3462,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8978728405218005,
+      "grad_norm": 1.0144025087356567,
+      "learning_rate": 7.006738755680928e-05,
+      "loss": 0.3416,
+      "step": 1910
+    },
+    {
+      "epoch": 0.9025737454459983,
+      "grad_norm": 2.533620834350586,
+      "learning_rate": 6.991067230841562e-05,
+      "loss": 0.3543,
+      "step": 1920
+    },
+    {
+      "epoch": 0.9072746503701963,
+      "grad_norm": 1.5756601095199585,
+      "learning_rate": 6.975395706002194e-05,
+      "loss": 0.368,
+      "step": 1930
+    },
+    {
+      "epoch": 0.9119755552943942,
+      "grad_norm": 1.2900676727294922,
+      "learning_rate": 6.959724181162828e-05,
+      "loss": 0.3368,
+      "step": 1940
+    },
+    {
+      "epoch": 0.9166764602185921,
+      "grad_norm": 1.2235045433044434,
+      "learning_rate": 6.944052656323461e-05,
+      "loss": 0.3428,
+      "step": 1950
+    },
+    {
+      "epoch": 0.92137736514279,
+      "grad_norm": 1.0844625234603882,
+      "learning_rate": 6.928381131484095e-05,
+      "loss": 0.365,
+      "step": 1960
+    },
+    {
+      "epoch": 0.9260782700669878,
+      "grad_norm": 2.585019588470459,
+      "learning_rate": 6.912709606644727e-05,
+      "loss": 0.3394,
+      "step": 1970
+    },
+    {
+      "epoch": 0.9307791749911858,
+      "grad_norm": 1.402716040611267,
+      "learning_rate": 6.89703808180536e-05,
+      "loss": 0.3513,
+      "step": 1980
+    },
+    {
+      "epoch": 0.9354800799153837,
+      "grad_norm": 1.6604111194610596,
+      "learning_rate": 6.881366556965994e-05,
+      "loss": 0.3514,
+      "step": 1990
+    },
+    {
+      "epoch": 0.9401809848395816,
+      "grad_norm": 1.0885512828826904,
+      "learning_rate": 6.865695032126626e-05,
+      "loss": 0.3504,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 3.016390562057495,
+      "learning_rate": 6.85002350728726e-05,
+      "loss": 0.3607,
+      "step": 2010
+    },
+    {
+      "epoch": 0.9495827946879775,
+      "grad_norm": 1.5509752035140991,
+      "learning_rate": 6.834351982447893e-05,
+      "loss": 0.3373,
+      "step": 2020
+    },
+    {
+      "epoch": 0.9542836996121753,
+      "grad_norm": 1.8190217018127441,
+      "learning_rate": 6.818680457608527e-05,
+      "loss": 0.3412,
+      "step": 2030
+    },
+    {
+      "epoch": 0.9589846045363732,
+      "grad_norm": 2.373183250427246,
+      "learning_rate": 6.803008932769159e-05,
+      "loss": 0.3455,
+      "step": 2040
+    },
+    {
+      "epoch": 0.9636855094605712,
+      "grad_norm": 1.4944651126861572,
+      "learning_rate": 6.787337407929793e-05,
+      "loss": 0.3467,
+      "step": 2050
+    },
+    {
+      "epoch": 0.968386414384769,
+      "grad_norm": 2.2049689292907715,
+      "learning_rate": 6.771665883090425e-05,
+      "loss": 0.3552,
+      "step": 2060
+    },
+    {
+      "epoch": 0.973087319308967,
+      "grad_norm": 1.044244647026062,
+      "learning_rate": 6.755994358251058e-05,
+      "loss": 0.3475,
+      "step": 2070
+    },
+    {
+      "epoch": 0.9777882242331649,
+      "grad_norm": 1.0703078508377075,
+      "learning_rate": 6.74032283341169e-05,
+      "loss": 0.3424,
+      "step": 2080
+    },
+    {
+      "epoch": 0.9824891291573628,
+      "grad_norm": 1.2599198818206787,
+      "learning_rate": 6.724651308572324e-05,
+      "loss": 0.3513,
+      "step": 2090
+    },
+    {
+      "epoch": 0.9871900340815607,
+      "grad_norm": 0.9976306557655334,
+      "learning_rate": 6.708979783732958e-05,
+      "loss": 0.3499,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9918909390057586,
+      "grad_norm": 1.1676925420761108,
+      "learning_rate": 6.69330825889359e-05,
+      "loss": 0.3362,
+      "step": 2110
+    },
+    {
+      "epoch": 0.9965918439299565,
+      "grad_norm": 1.5144907236099243,
+      "learning_rate": 6.677636734054223e-05,
+      "loss": 0.3323,
+      "step": 2120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6381,
+  "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": 4.7331697868700385e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2127/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c713aa4ce14645621132900bade7e9ea63b6b79a02e40dc980b0d7fbd39dc6a
+size 5176