Upload folder using huggingface_hub

.gitattributes

@@ -57,3 +57,4 @@ checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-390/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-405/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-435/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-435/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-3B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.19.1

checkpoint-435/adapter_config.json

@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-435/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ea234b733149ce21a76442a6c6584b853c5dccd86f95e9e75b87e1f7f37314
+size 59933632

checkpoint-435/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|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-435/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-435/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83b35936fafa0efdebdc6deb34ad3909c0d2e837ded9ee864e797c86702d860
+size 120166091

checkpoint-435/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

checkpoint-435/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bbb728be736329685021040dfedc0f68a5329c44a0dd22fc060221e33eac0bc
+size 1465

checkpoint-435/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": "<|PAD_TOKEN|>"
+}

checkpoint-435/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

checkpoint-435/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_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
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-435/trainer_state.json

@@ -0,0 +1,3079 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8637362637362638,
+  "eval_steps": 500,
+  "global_step": 435,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 4.417632102966309,
+      "learning_rate": 0.0,
+      "loss": 4.6066,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 3.824070453643799,
+      "learning_rate": 4e-05,
+      "loss": 4.5809,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 4.764647960662842,
+      "learning_rate": 8e-05,
+      "loss": 4.8428,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 5.026129722595215,
+      "learning_rate": 0.00012,
+      "loss": 5.3246,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 5.568634033203125,
+      "learning_rate": 0.00016,
+      "loss": 5.0766,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 7.791904926300049,
+      "learning_rate": 0.0002,
+      "loss": 4.4789,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 5.971574306488037,
+      "learning_rate": 0.00019955654101995565,
+      "loss": 2.7773,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 3.3475728034973145,
+      "learning_rate": 0.00019911308203991133,
+      "loss": 1.6269,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 2.5669748783111572,
+      "learning_rate": 0.00019866962305986697,
+      "loss": 1.6002,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 2.079508066177368,
+      "learning_rate": 0.00019822616407982261,
+      "loss": 1.561,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 1.5781028270721436,
+      "learning_rate": 0.00019778270509977829,
+      "loss": 1.188,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.8474287390708923,
+      "learning_rate": 0.00019733924611973393,
+      "loss": 1.1719,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.7965599894523621,
+      "learning_rate": 0.0001968957871396896,
+      "loss": 1.0825,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.67277592420578,
+      "learning_rate": 0.00019645232815964525,
+      "loss": 0.991,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.7163275480270386,
+      "learning_rate": 0.00019600886917960092,
+      "loss": 1.1508,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.8085870146751404,
+      "learning_rate": 0.00019556541019955653,
+      "loss": 1.2109,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.7520304322242737,
+      "learning_rate": 0.0001951219512195122,
+      "loss": 1.0903,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.680241048336029,
+      "learning_rate": 0.00019467849223946785,
+      "loss": 0.9543,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.8143166303634644,
+      "learning_rate": 0.00019423503325942352,
+      "loss": 1.2347,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.7142716646194458,
+      "learning_rate": 0.00019379157427937917,
+      "loss": 1.0114,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.5970592498779297,
+      "learning_rate": 0.00019334811529933484,
+      "loss": 1.0567,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.7442165017127991,
+      "learning_rate": 0.00019290465631929045,
+      "loss": 0.8508,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.6935762763023376,
+      "learning_rate": 0.00019246119733924613,
+      "loss": 1.089,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.6430759429931641,
+      "learning_rate": 0.00019201773835920177,
+      "loss": 0.7555,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.610454261302948,
+      "learning_rate": 0.00019157427937915744,
+      "loss": 1.0817,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.6211035847663879,
+      "learning_rate": 0.00019113082039911309,
+      "loss": 0.9037,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.6100361943244934,
+      "learning_rate": 0.00019068736141906876,
+      "loss": 1.0705,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.5219504237174988,
+      "learning_rate": 0.0001902439024390244,
+      "loss": 0.8251,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.5593066811561584,
+      "learning_rate": 0.00018980044345898005,
+      "loss": 1.0416,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.5467231273651123,
+      "learning_rate": 0.00018935698447893572,
+      "loss": 0.9379,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.8338480591773987,
+      "learning_rate": 0.00018891352549889136,
+      "loss": 0.8073,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.6652135848999023,
+      "learning_rate": 0.00018847006651884703,
+      "loss": 0.959,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.6371573805809021,
+      "learning_rate": 0.00018802660753880268,
+      "loss": 1.0453,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.5541828274726868,
+      "learning_rate": 0.00018758314855875832,
+      "loss": 0.8059,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.6239511966705322,
+      "learning_rate": 0.00018713968957871397,
+      "loss": 0.9681,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.6381208896636963,
+      "learning_rate": 0.00018669623059866964,
+      "loss": 0.8827,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.5363917946815491,
+      "learning_rate": 0.00018625277161862528,
+      "loss": 0.989,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.6242470741271973,
+      "learning_rate": 0.00018580931263858095,
+      "loss": 0.6724,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.531095027923584,
+      "learning_rate": 0.0001853658536585366,
+      "loss": 0.7495,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.6587176322937012,
+      "learning_rate": 0.00018492239467849224,
+      "loss": 0.9717,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.5573552250862122,
+      "learning_rate": 0.0001844789356984479,
+      "loss": 0.9977,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.6289750933647156,
+      "learning_rate": 0.00018403547671840356,
+      "loss": 0.9671,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.5671831965446472,
+      "learning_rate": 0.0001835920177383592,
+      "loss": 0.8712,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.603140115737915,
+      "learning_rate": 0.00018314855875831487,
+      "loss": 0.9699,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.5726262927055359,
+      "learning_rate": 0.00018270509977827052,
+      "loss": 1.073,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.57386714220047,
+      "learning_rate": 0.00018226164079822616,
+      "loss": 0.9159,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.5615765452384949,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 1.0575,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.47419869899749756,
+      "learning_rate": 0.00018137472283813748,
+      "loss": 0.8356,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.5028887987136841,
+      "learning_rate": 0.00018093126385809312,
+      "loss": 1.0313,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.5023750066757202,
+      "learning_rate": 0.0001804878048780488,
+      "loss": 0.8376,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.4543537199497223,
+      "learning_rate": 0.00018004434589800444,
+      "loss": 0.7145,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.4374978244304657,
+      "learning_rate": 0.00017960088691796008,
+      "loss": 0.7464,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.47209376096725464,
+      "learning_rate": 0.00017915742793791575,
+      "loss": 0.9299,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.5425230264663696,
+      "learning_rate": 0.0001787139689578714,
+      "loss": 0.8528,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.5343915820121765,
+      "learning_rate": 0.00017827050997782707,
+      "loss": 0.7878,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.5154897570610046,
+      "learning_rate": 0.00017782705099778271,
+      "loss": 0.8451,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.48188620805740356,
+      "learning_rate": 0.00017738359201773839,
+      "loss": 0.9204,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.42773884534835815,
+      "learning_rate": 0.000176940133037694,
+      "loss": 0.7443,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.6305500268936157,
+      "learning_rate": 0.00017649667405764967,
+      "loss": 1.0036,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.571887731552124,
+      "learning_rate": 0.00017605321507760532,
+      "loss": 0.8989,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.5789161324501038,
+      "learning_rate": 0.000175609756097561,
+      "loss": 0.9057,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.5388776063919067,
+      "learning_rate": 0.00017516629711751663,
+      "loss": 0.9811,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.5069330334663391,
+      "learning_rate": 0.0001747228381374723,
+      "loss": 0.8072,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.6007671356201172,
+      "learning_rate": 0.00017427937915742792,
+      "loss": 0.9287,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.5581125020980835,
+      "learning_rate": 0.0001738359201773836,
+      "loss": 0.9263,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.6751324534416199,
+      "learning_rate": 0.00017339246119733924,
+      "loss": 0.8119,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.4773782789707184,
+      "learning_rate": 0.0001729490022172949,
+      "loss": 0.6753,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.6136070489883423,
+      "learning_rate": 0.00017250554323725056,
+      "loss": 0.8526,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.6497328281402588,
+      "learning_rate": 0.00017206208425720623,
+      "loss": 0.7758,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.6036306023597717,
+      "learning_rate": 0.00017161862527716187,
+      "loss": 0.941,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.5378339290618896,
+      "learning_rate": 0.00017117516629711752,
+      "loss": 0.9566,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.4954136908054352,
+      "learning_rate": 0.0001707317073170732,
+      "loss": 0.9078,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.5501747727394104,
+      "learning_rate": 0.00017028824833702883,
+      "loss": 0.8474,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.5908843874931335,
+      "learning_rate": 0.0001698447893569845,
+      "loss": 0.9218,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.4488467574119568,
+      "learning_rate": 0.00016940133037694015,
+      "loss": 0.8638,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.5528292059898376,
+      "learning_rate": 0.00016895787139689582,
+      "loss": 1.1412,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.4880754351615906,
+      "learning_rate": 0.00016851441241685144,
+      "loss": 0.7314,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.5529576539993286,
+      "learning_rate": 0.0001680709534368071,
+      "loss": 1.0243,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.5193362832069397,
+      "learning_rate": 0.00016762749445676275,
+      "loss": 0.9398,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.5076447129249573,
+      "learning_rate": 0.00016718403547671842,
+      "loss": 0.6084,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.5762174129486084,
+      "learning_rate": 0.00016674057649667407,
+      "loss": 0.9232,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.5628107786178589,
+      "learning_rate": 0.00016629711751662974,
+      "loss": 0.9185,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.5657719969749451,
+      "learning_rate": 0.00016585365853658536,
+      "loss": 0.8769,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.676673173904419,
+      "learning_rate": 0.00016541019955654103,
+      "loss": 0.9929,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.5039803981781006,
+      "learning_rate": 0.00016496674057649667,
+      "loss": 0.88,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.5343524217605591,
+      "learning_rate": 0.00016452328159645234,
+      "loss": 0.7667,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.6614826917648315,
+      "learning_rate": 0.000164079822616408,
+      "loss": 0.7338,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.6496767997741699,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.0196,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.5414061546325684,
+      "learning_rate": 0.0001631929046563193,
+      "loss": 0.9439,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.5283159017562866,
+      "learning_rate": 0.00016274944567627495,
+      "loss": 0.6371,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6610089540481567,
+      "learning_rate": 0.0001623059866962306,
+      "loss": 0.9329,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.6365460157394409,
+      "learning_rate": 0.00016186252771618626,
+      "loss": 0.888,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.5431596636772156,
+      "learning_rate": 0.0001614190687361419,
+      "loss": 0.6909,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.6583664417266846,
+      "learning_rate": 0.00016097560975609758,
+      "loss": 1.0547,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.7014925479888916,
+      "learning_rate": 0.00016053215077605322,
+      "loss": 0.9537,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.5222604870796204,
+      "learning_rate": 0.00016008869179600887,
+      "loss": 0.797,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.5794833898544312,
+      "learning_rate": 0.00015964523281596454,
+      "loss": 0.7284,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.5662128329277039,
+      "learning_rate": 0.00015920177383592018,
+      "loss": 0.815,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.5566934943199158,
+      "learning_rate": 0.00015875831485587586,
+      "loss": 0.7433,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.6824548244476318,
+      "learning_rate": 0.0001583148558758315,
+      "loss": 0.8538,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.506364643573761,
+      "learning_rate": 0.00015787139689578714,
+      "loss": 0.8519,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.531067430973053,
+      "learning_rate": 0.0001574279379157428,
+      "loss": 0.811,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.5699226260185242,
+      "learning_rate": 0.00015698447893569846,
+      "loss": 0.9107,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.6745486855506897,
+      "learning_rate": 0.0001565410199556541,
+      "loss": 0.9513,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.5856108665466309,
+      "learning_rate": 0.00015609756097560978,
+      "loss": 0.87,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.5589944124221802,
+      "learning_rate": 0.00015565410199556542,
+      "loss": 0.9231,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.5654696226119995,
+      "learning_rate": 0.00015521064301552106,
+      "loss": 0.9256,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.6465855836868286,
+      "learning_rate": 0.0001547671840354767,
+      "loss": 0.8539,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.6349661350250244,
+      "learning_rate": 0.00015432372505543238,
+      "loss": 0.9793,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.5383194088935852,
+      "learning_rate": 0.00015388026607538802,
+      "loss": 0.8916,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.5718663930892944,
+      "learning_rate": 0.0001534368070953437,
+      "loss": 0.9586,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.5511415600776672,
+      "learning_rate": 0.00015299334811529934,
+      "loss": 0.876,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.5277529358863831,
+      "learning_rate": 0.00015254988913525498,
+      "loss": 0.9305,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.5491341352462769,
+      "learning_rate": 0.00015210643015521066,
+      "loss": 0.869,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.5900211334228516,
+      "learning_rate": 0.0001516629711751663,
+      "loss": 0.9411,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.5197898149490356,
+      "learning_rate": 0.00015121951219512197,
+      "loss": 0.8905,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.511114239692688,
+      "learning_rate": 0.00015077605321507762,
+      "loss": 0.8522,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.5591258406639099,
+      "learning_rate": 0.0001503325942350333,
+      "loss": 0.8849,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.49140432476997375,
+      "learning_rate": 0.0001498891352549889,
+      "loss": 0.8749,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.5272778272628784,
+      "learning_rate": 0.00014944567627494458,
+      "loss": 0.7527,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.5844745635986328,
+      "learning_rate": 0.00014900221729490022,
+      "loss": 0.9937,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.5546406507492065,
+      "learning_rate": 0.0001485587583148559,
+      "loss": 1.0046,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.5028824210166931,
+      "learning_rate": 0.00014811529933481154,
+      "loss": 0.8752,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.4766760766506195,
+      "learning_rate": 0.0001476718403547672,
+      "loss": 0.6806,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.5514656901359558,
+      "learning_rate": 0.00014722838137472282,
+      "loss": 0.896,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.6014825701713562,
+      "learning_rate": 0.0001467849223946785,
+      "loss": 0.8438,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.5003427863121033,
+      "learning_rate": 0.00014634146341463414,
+      "loss": 0.894,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.5340179204940796,
+      "learning_rate": 0.0001458980044345898,
+      "loss": 0.7952,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.5958055257797241,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.8895,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.663881778717041,
+      "learning_rate": 0.00014501108647450113,
+      "loss": 0.9227,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.7118547558784485,
+      "learning_rate": 0.00014456762749445675,
+      "loss": 1.2685,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.6181128025054932,
+      "learning_rate": 0.00014412416851441242,
+      "loss": 0.9934,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.5530040264129639,
+      "learning_rate": 0.00014368070953436806,
+      "loss": 0.6678,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.5773662328720093,
+      "learning_rate": 0.00014323725055432373,
+      "loss": 0.7822,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.6204919219017029,
+      "learning_rate": 0.00014279379157427938,
+      "loss": 0.8531,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.5235987901687622,
+      "learning_rate": 0.00014235033259423505,
+      "loss": 0.9034,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.5405385494232178,
+      "learning_rate": 0.0001419068736141907,
+      "loss": 0.8628,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.5767109394073486,
+      "learning_rate": 0.00014146341463414634,
+      "loss": 0.9248,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.6193376779556274,
+      "learning_rate": 0.000141019955654102,
+      "loss": 0.9899,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.5930230617523193,
+      "learning_rate": 0.00014057649667405765,
+      "loss": 0.9528,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.6145725846290588,
+      "learning_rate": 0.00014013303769401332,
+      "loss": 0.8576,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.5589808821678162,
+      "learning_rate": 0.00013968957871396897,
+      "loss": 0.6813,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.5464595556259155,
+      "learning_rate": 0.00013924611973392464,
+      "loss": 0.8162,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.5102654695510864,
+      "learning_rate": 0.00013880266075388026,
+      "loss": 0.6105,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.6438682675361633,
+      "learning_rate": 0.00013835920177383593,
+      "loss": 0.8576,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.7712976932525635,
+      "learning_rate": 0.00013791574279379157,
+      "loss": 0.932,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.6082596778869629,
+      "learning_rate": 0.00013747228381374724,
+      "loss": 0.9235,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.5627255439758301,
+      "learning_rate": 0.0001370288248337029,
+      "loss": 0.7996,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.5708767175674438,
+      "learning_rate": 0.00013658536585365856,
+      "loss": 0.6233,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.5511801838874817,
+      "learning_rate": 0.00013614190687361418,
+      "loss": 0.7211,
+      "step": 150
+    },
+    {
+      "epoch": 0.9956043956043956,
+      "grad_norm": 0.5675956010818481,
+      "learning_rate": 0.00013569844789356985,
+      "loss": 0.7203,
+      "step": 151
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.841576099395752,
+      "learning_rate": 0.0001352549889135255,
+      "loss": 0.7334,
+      "step": 152
+    },
+    {
+      "epoch": 1.0065934065934066,
+      "grad_norm": 0.6041272878646851,
+      "learning_rate": 0.00013481152993348116,
+      "loss": 0.7238,
+      "step": 153
+    },
+    {
+      "epoch": 1.0131868131868131,
+      "grad_norm": 0.48842668533325195,
+      "learning_rate": 0.0001343680709534368,
+      "loss": 0.8418,
+      "step": 154
+    },
+    {
+      "epoch": 1.0197802197802197,
+      "grad_norm": 0.5356717705726624,
+      "learning_rate": 0.00013392461197339248,
+      "loss": 0.6318,
+      "step": 155
+    },
+    {
+      "epoch": 1.0263736263736263,
+      "grad_norm": 0.5651488304138184,
+      "learning_rate": 0.00013348115299334812,
+      "loss": 0.6607,
+      "step": 156
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.5447269082069397,
+      "learning_rate": 0.00013303769401330377,
+      "loss": 0.7638,
+      "step": 157
+    },
+    {
+      "epoch": 1.0395604395604396,
+      "grad_norm": 0.5723810195922852,
+      "learning_rate": 0.00013259423503325944,
+      "loss": 1.0065,
+      "step": 158
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.5228806734085083,
+      "learning_rate": 0.00013215077605321509,
+      "loss": 0.6397,
+      "step": 159
+    },
+    {
+      "epoch": 1.0527472527472528,
+      "grad_norm": 0.5963119268417358,
+      "learning_rate": 0.00013170731707317076,
+      "loss": 0.91,
+      "step": 160
+    },
+    {
+      "epoch": 1.0593406593406594,
+      "grad_norm": 0.5306135416030884,
+      "learning_rate": 0.0001312638580931264,
+      "loss": 0.7778,
+      "step": 161
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.5146408677101135,
+      "learning_rate": 0.00013082039911308205,
+      "loss": 0.7719,
+      "step": 162
+    },
+    {
+      "epoch": 1.0725274725274725,
+      "grad_norm": 0.5158949494361877,
+      "learning_rate": 0.0001303769401330377,
+      "loss": 0.7203,
+      "step": 163
+    },
+    {
+      "epoch": 1.079120879120879,
+      "grad_norm": 0.5516198873519897,
+      "learning_rate": 0.00012993348115299336,
+      "loss": 0.4801,
+      "step": 164
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.5656818747520447,
+      "learning_rate": 0.000129490022172949,
+      "loss": 0.6675,
+      "step": 165
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 0.5386690497398376,
+      "learning_rate": 0.00012904656319290468,
+      "loss": 0.7166,
+      "step": 166
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.5922750234603882,
+      "learning_rate": 0.00012860310421286032,
+      "loss": 0.6271,
+      "step": 167
+    },
+    {
+      "epoch": 1.1054945054945056,
+      "grad_norm": 0.5892629623413086,
+      "learning_rate": 0.00012815964523281597,
+      "loss": 0.614,
+      "step": 168
+    },
+    {
+      "epoch": 1.1120879120879121,
+      "grad_norm": 0.5477419495582581,
+      "learning_rate": 0.0001277161862527716,
+      "loss": 0.6421,
+      "step": 169
+    },
+    {
+      "epoch": 1.1186813186813187,
+      "grad_norm": 0.6130991578102112,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.6938,
+      "step": 170
+    },
+    {
+      "epoch": 1.1252747252747253,
+      "grad_norm": 0.7019168734550476,
+      "learning_rate": 0.00012682926829268293,
+      "loss": 0.8087,
+      "step": 171
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 0.6180416941642761,
+      "learning_rate": 0.0001263858093126386,
+      "loss": 0.7819,
+      "step": 172
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 0.6685227751731873,
+      "learning_rate": 0.00012594235033259424,
+      "loss": 0.7466,
+      "step": 173
+    },
+    {
+      "epoch": 1.145054945054945,
+      "grad_norm": 0.5855250358581543,
+      "learning_rate": 0.00012549889135254989,
+      "loss": 0.5945,
+      "step": 174
+    },
+    {
+      "epoch": 1.1516483516483516,
+      "grad_norm": 0.582728385925293,
+      "learning_rate": 0.00012505543237250553,
+      "loss": 0.8723,
+      "step": 175
+    },
+    {
+      "epoch": 1.1582417582417581,
+      "grad_norm": 0.6902685761451721,
+      "learning_rate": 0.0001246119733924612,
+      "loss": 0.5879,
+      "step": 176
+    },
+    {
+      "epoch": 1.164835164835165,
+      "grad_norm": 0.6733485460281372,
+      "learning_rate": 0.00012416851441241685,
+      "loss": 0.6244,
+      "step": 177
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 0.6403049826622009,
+      "learning_rate": 0.00012372505543237252,
+      "loss": 0.7442,
+      "step": 178
+    },
+    {
+      "epoch": 1.178021978021978,
+      "grad_norm": 0.6300265789031982,
+      "learning_rate": 0.00012328159645232816,
+      "loss": 0.7412,
+      "step": 179
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.5773813724517822,
+      "learning_rate": 0.0001228381374722838,
+      "loss": 0.6802,
+      "step": 180
+    },
+    {
+      "epoch": 1.1912087912087912,
+      "grad_norm": 0.64751136302948,
+      "learning_rate": 0.00012239467849223948,
+      "loss": 0.7256,
+      "step": 181
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 0.6257942318916321,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.6448,
+      "step": 182
+    },
+    {
+      "epoch": 1.2043956043956043,
+      "grad_norm": 0.6436994075775146,
+      "learning_rate": 0.00012150776053215078,
+      "loss": 0.8134,
+      "step": 183
+    },
+    {
+      "epoch": 1.210989010989011,
+      "grad_norm": 0.7222681641578674,
+      "learning_rate": 0.00012106430155210644,
+      "loss": 0.8496,
+      "step": 184
+    },
+    {
+      "epoch": 1.2175824175824177,
+      "grad_norm": 0.5950624942779541,
+      "learning_rate": 0.0001206208425720621,
+      "loss": 0.601,
+      "step": 185
+    },
+    {
+      "epoch": 1.2241758241758243,
+      "grad_norm": 0.7700217962265015,
+      "learning_rate": 0.00012017738359201774,
+      "loss": 0.9038,
+      "step": 186
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.698784351348877,
+      "learning_rate": 0.0001197339246119734,
+      "loss": 0.6952,
+      "step": 187
+    },
+    {
+      "epoch": 1.2373626373626374,
+      "grad_norm": 0.803534984588623,
+      "learning_rate": 0.00011929046563192906,
+      "loss": 0.5598,
+      "step": 188
+    },
+    {
+      "epoch": 1.243956043956044,
+      "grad_norm": 0.810663104057312,
+      "learning_rate": 0.00011884700665188471,
+      "loss": 0.8977,
+      "step": 189
+    },
+    {
+      "epoch": 1.2505494505494505,
+      "grad_norm": 0.7135093212127686,
+      "learning_rate": 0.00011840354767184036,
+      "loss": 0.7501,
+      "step": 190
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.9062169790267944,
+      "learning_rate": 0.00011796008869179602,
+      "loss": 0.7618,
+      "step": 191
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 0.6200124025344849,
+      "learning_rate": 0.00011751662971175166,
+      "loss": 0.6832,
+      "step": 192
+    },
+    {
+      "epoch": 1.2703296703296703,
+      "grad_norm": 0.7953326106071472,
+      "learning_rate": 0.00011707317073170732,
+      "loss": 0.7149,
+      "step": 193
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 0.7229250073432922,
+      "learning_rate": 0.00011662971175166298,
+      "loss": 0.6501,
+      "step": 194
+    },
+    {
+      "epoch": 1.2835164835164834,
+      "grad_norm": 0.7693234086036682,
+      "learning_rate": 0.00011618625277161863,
+      "loss": 0.7875,
+      "step": 195
+    },
+    {
+      "epoch": 1.2901098901098902,
+      "grad_norm": 1.03544020652771,
+      "learning_rate": 0.00011574279379157429,
+      "loss": 0.9469,
+      "step": 196
+    },
+    {
+      "epoch": 1.2967032967032968,
+      "grad_norm": 0.7549523115158081,
+      "learning_rate": 0.00011529933481152995,
+      "loss": 0.5158,
+      "step": 197
+    },
+    {
+      "epoch": 1.3032967032967033,
+      "grad_norm": 0.6752796173095703,
+      "learning_rate": 0.00011485587583148558,
+      "loss": 0.6001,
+      "step": 198
+    },
+    {
+      "epoch": 1.30989010989011,
+      "grad_norm": 0.7703771591186523,
+      "learning_rate": 0.00011441241685144124,
+      "loss": 0.711,
+      "step": 199
+    },
+    {
+      "epoch": 1.3164835164835165,
+      "grad_norm": 0.7333843111991882,
+      "learning_rate": 0.0001139689578713969,
+      "loss": 0.7516,
+      "step": 200
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 0.7859432101249695,
+      "learning_rate": 0.00011352549889135255,
+      "loss": 0.9336,
+      "step": 201
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 0.77800053358078,
+      "learning_rate": 0.00011308203991130821,
+      "loss": 0.8772,
+      "step": 202
+    },
+    {
+      "epoch": 1.3362637362637364,
+      "grad_norm": 0.8271440267562866,
+      "learning_rate": 0.00011263858093126387,
+      "loss": 0.6986,
+      "step": 203
+    },
+    {
+      "epoch": 1.342857142857143,
+      "grad_norm": 0.6502723693847656,
+      "learning_rate": 0.00011219512195121953,
+      "loss": 0.4378,
+      "step": 204
+    },
+    {
+      "epoch": 1.3494505494505495,
+      "grad_norm": 0.8076328635215759,
+      "learning_rate": 0.00011175166297117516,
+      "loss": 0.6504,
+      "step": 205
+    },
+    {
+      "epoch": 1.3560439560439561,
+      "grad_norm": 0.8068559765815735,
+      "learning_rate": 0.00011130820399113082,
+      "loss": 0.6608,
+      "step": 206
+    },
+    {
+      "epoch": 1.3626373626373627,
+      "grad_norm": 0.7107000350952148,
+      "learning_rate": 0.00011086474501108647,
+      "loss": 0.6953,
+      "step": 207
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.7289706468582153,
+      "learning_rate": 0.00011042128603104213,
+      "loss": 0.6603,
+      "step": 208
+    },
+    {
+      "epoch": 1.3758241758241758,
+      "grad_norm": 0.8543151617050171,
+      "learning_rate": 0.00010997782705099779,
+      "loss": 0.8272,
+      "step": 209
+    },
+    {
+      "epoch": 1.3824175824175824,
+      "grad_norm": 0.748634934425354,
+      "learning_rate": 0.00010953436807095345,
+      "loss": 0.681,
+      "step": 210
+    },
+    {
+      "epoch": 1.389010989010989,
+      "grad_norm": 0.6797105073928833,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.5805,
+      "step": 211
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.9264088869094849,
+      "learning_rate": 0.00010864745011086475,
+      "loss": 0.6196,
+      "step": 212
+    },
+    {
+      "epoch": 1.402197802197802,
+      "grad_norm": 0.8796908259391785,
+      "learning_rate": 0.00010820399113082041,
+      "loss": 0.8333,
+      "step": 213
+    },
+    {
+      "epoch": 1.4087912087912087,
+      "grad_norm": 0.7682700157165527,
+      "learning_rate": 0.00010776053215077607,
+      "loss": 0.6805,
+      "step": 214
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 0.7117056250572205,
+      "learning_rate": 0.00010731707317073172,
+      "loss": 0.5846,
+      "step": 215
+    },
+    {
+      "epoch": 1.421978021978022,
+      "grad_norm": 0.8295667171478271,
+      "learning_rate": 0.00010687361419068738,
+      "loss": 0.563,
+      "step": 216
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.7516017556190491,
+      "learning_rate": 0.00010643015521064301,
+      "loss": 0.6103,
+      "step": 217
+    },
+    {
+      "epoch": 1.4351648351648352,
+      "grad_norm": 0.7708144187927246,
+      "learning_rate": 0.00010598669623059867,
+      "loss": 0.706,
+      "step": 218
+    },
+    {
+      "epoch": 1.4417582417582417,
+      "grad_norm": 0.7590659260749817,
+      "learning_rate": 0.00010554323725055433,
+      "loss": 0.756,
+      "step": 219
+    },
+    {
+      "epoch": 1.4483516483516483,
+      "grad_norm": 0.8152827024459839,
+      "learning_rate": 0.00010509977827050999,
+      "loss": 0.6396,
+      "step": 220
+    },
+    {
+      "epoch": 1.4549450549450549,
+      "grad_norm": 0.8612132668495178,
+      "learning_rate": 0.00010465631929046564,
+      "loss": 0.614,
+      "step": 221
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.8408886194229126,
+      "learning_rate": 0.0001042128603104213,
+      "loss": 0.741,
+      "step": 222
+    },
+    {
+      "epoch": 1.4681318681318682,
+      "grad_norm": 0.7959259748458862,
+      "learning_rate": 0.00010376940133037693,
+      "loss": 0.7306,
+      "step": 223
+    },
+    {
+      "epoch": 1.4747252747252748,
+      "grad_norm": 0.8105316162109375,
+      "learning_rate": 0.00010332594235033259,
+      "loss": 0.7496,
+      "step": 224
+    },
+    {
+      "epoch": 1.4813186813186814,
+      "grad_norm": 0.7634991407394409,
+      "learning_rate": 0.00010288248337028825,
+      "loss": 0.4973,
+      "step": 225
+    },
+    {
+      "epoch": 1.487912087912088,
+      "grad_norm": 0.86619633436203,
+      "learning_rate": 0.0001024390243902439,
+      "loss": 0.6977,
+      "step": 226
+    },
+    {
+      "epoch": 1.4945054945054945,
+      "grad_norm": 0.9370027780532837,
+      "learning_rate": 0.00010199556541019956,
+      "loss": 0.9136,
+      "step": 227
+    },
+    {
+      "epoch": 1.501098901098901,
+      "grad_norm": 0.8094936013221741,
+      "learning_rate": 0.00010155210643015522,
+      "loss": 0.6651,
+      "step": 228
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 0.9540297985076904,
+      "learning_rate": 0.00010110864745011087,
+      "loss": 0.76,
+      "step": 229
+    },
+    {
+      "epoch": 1.5142857142857142,
+      "grad_norm": 0.9854940176010132,
+      "learning_rate": 0.00010066518847006652,
+      "loss": 0.8393,
+      "step": 230
+    },
+    {
+      "epoch": 1.5208791208791208,
+      "grad_norm": 0.8038029074668884,
+      "learning_rate": 0.00010022172949002218,
+      "loss": 0.709,
+      "step": 231
+    },
+    {
+      "epoch": 1.5274725274725274,
+      "grad_norm": 0.8540597558021545,
+      "learning_rate": 9.977827050997783e-05,
+      "loss": 0.6907,
+      "step": 232
+    },
+    {
+      "epoch": 1.534065934065934,
+      "grad_norm": 0.7940883040428162,
+      "learning_rate": 9.933481152993348e-05,
+      "loss": 0.7181,
+      "step": 233
+    },
+    {
+      "epoch": 1.5406593406593405,
+      "grad_norm": 0.799118161201477,
+      "learning_rate": 9.889135254988914e-05,
+      "loss": 0.6442,
+      "step": 234
+    },
+    {
+      "epoch": 1.5472527472527473,
+      "grad_norm": 0.7642391920089722,
+      "learning_rate": 9.84478935698448e-05,
+      "loss": 0.7556,
+      "step": 235
+    },
+    {
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.7873114347457886,
+      "learning_rate": 9.800443458980046e-05,
+      "loss": 0.7719,
+      "step": 236
+    },
+    {
+      "epoch": 1.5604395604395604,
+      "grad_norm": 0.7426925301551819,
+      "learning_rate": 9.75609756097561e-05,
+      "loss": 0.5357,
+      "step": 237
+    },
+    {
+      "epoch": 1.567032967032967,
+      "grad_norm": 0.8319903612136841,
+      "learning_rate": 9.711751662971176e-05,
+      "loss": 0.7869,
+      "step": 238
+    },
+    {
+      "epoch": 1.5736263736263736,
+      "grad_norm": 0.868106484413147,
+      "learning_rate": 9.667405764966742e-05,
+      "loss": 0.6447,
+      "step": 239
+    },
+    {
+      "epoch": 1.5802197802197804,
+      "grad_norm": 0.7776063084602356,
+      "learning_rate": 9.623059866962306e-05,
+      "loss": 0.6502,
+      "step": 240
+    },
+    {
+      "epoch": 1.586813186813187,
+      "grad_norm": 0.830654501914978,
+      "learning_rate": 9.578713968957872e-05,
+      "loss": 0.5277,
+      "step": 241
+    },
+    {
+      "epoch": 1.5934065934065935,
+      "grad_norm": 0.9006453156471252,
+      "learning_rate": 9.534368070953438e-05,
+      "loss": 0.6608,
+      "step": 242
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7525179982185364,
+      "learning_rate": 9.490022172949002e-05,
+      "loss": 0.5303,
+      "step": 243
+    },
+    {
+      "epoch": 1.6065934065934067,
+      "grad_norm": 0.9502760171890259,
+      "learning_rate": 9.445676274944568e-05,
+      "loss": 0.7432,
+      "step": 244
+    },
+    {
+      "epoch": 1.6131868131868132,
+      "grad_norm": 0.8728800415992737,
+      "learning_rate": 9.401330376940134e-05,
+      "loss": 0.7455,
+      "step": 245
+    },
+    {
+      "epoch": 1.6197802197802198,
+      "grad_norm": 0.9959251284599304,
+      "learning_rate": 9.356984478935698e-05,
+      "loss": 0.8085,
+      "step": 246
+    },
+    {
+      "epoch": 1.6263736263736264,
+      "grad_norm": 0.8873069286346436,
+      "learning_rate": 9.312638580931264e-05,
+      "loss": 0.715,
+      "step": 247
+    },
+    {
+      "epoch": 1.632967032967033,
+      "grad_norm": 0.9150330424308777,
+      "learning_rate": 9.26829268292683e-05,
+      "loss": 0.7303,
+      "step": 248
+    },
+    {
+      "epoch": 1.6395604395604395,
+      "grad_norm": 0.941971480846405,
+      "learning_rate": 9.223946784922394e-05,
+      "loss": 0.7047,
+      "step": 249
+    },
+    {
+      "epoch": 1.646153846153846,
+      "grad_norm": 0.930797278881073,
+      "learning_rate": 9.17960088691796e-05,
+      "loss": 0.7444,
+      "step": 250
+    },
+    {
+      "epoch": 1.6527472527472526,
+      "grad_norm": 0.7805498242378235,
+      "learning_rate": 9.135254988913526e-05,
+      "loss": 0.5222,
+      "step": 251
+    },
+    {
+      "epoch": 1.6593406593406592,
+      "grad_norm": 0.8771283030509949,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.7402,
+      "step": 252
+    },
+    {
+      "epoch": 1.6659340659340658,
+      "grad_norm": 0.8311415314674377,
+      "learning_rate": 9.046563192904656e-05,
+      "loss": 0.6303,
+      "step": 253
+    },
+    {
+      "epoch": 1.6725274725274726,
+      "grad_norm": 0.7850191593170166,
+      "learning_rate": 9.002217294900222e-05,
+      "loss": 0.6332,
+      "step": 254
+    },
+    {
+      "epoch": 1.6791208791208792,
+      "grad_norm": 0.9208539128303528,
+      "learning_rate": 8.957871396895788e-05,
+      "loss": 0.6125,
+      "step": 255
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.9065554738044739,
+      "learning_rate": 8.913525498891354e-05,
+      "loss": 0.5773,
+      "step": 256
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.8763704895973206,
+      "learning_rate": 8.869179600886919e-05,
+      "loss": 0.7468,
+      "step": 257
+    },
+    {
+      "epoch": 1.6989010989010989,
+      "grad_norm": 0.9041984677314758,
+      "learning_rate": 8.824833702882484e-05,
+      "loss": 0.6812,
+      "step": 258
+    },
+    {
+      "epoch": 1.7054945054945057,
+      "grad_norm": 0.9354036450386047,
+      "learning_rate": 8.78048780487805e-05,
+      "loss": 0.7098,
+      "step": 259
+    },
+    {
+      "epoch": 1.7120879120879122,
+      "grad_norm": 0.8626531362533569,
+      "learning_rate": 8.736141906873615e-05,
+      "loss": 0.642,
+      "step": 260
+    },
+    {
+      "epoch": 1.7186813186813188,
+      "grad_norm": 0.8664013147354126,
+      "learning_rate": 8.69179600886918e-05,
+      "loss": 0.6896,
+      "step": 261
+    },
+    {
+      "epoch": 1.7252747252747254,
+      "grad_norm": 0.9084680676460266,
+      "learning_rate": 8.647450110864746e-05,
+      "loss": 0.7758,
+      "step": 262
+    },
+    {
+      "epoch": 1.731868131868132,
+      "grad_norm": 0.8910940289497375,
+      "learning_rate": 8.603104212860311e-05,
+      "loss": 0.6635,
+      "step": 263
+    },
+    {
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.9874815940856934,
+      "learning_rate": 8.558758314855876e-05,
+      "loss": 0.8084,
+      "step": 264
+    },
+    {
+      "epoch": 1.745054945054945,
+      "grad_norm": 0.8843784928321838,
+      "learning_rate": 8.514412416851442e-05,
+      "loss": 0.672,
+      "step": 265
+    },
+    {
+      "epoch": 1.7516483516483516,
+      "grad_norm": 0.8756618499755859,
+      "learning_rate": 8.470066518847007e-05,
+      "loss": 0.6339,
+      "step": 266
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 0.9353803396224976,
+      "learning_rate": 8.425720620842572e-05,
+      "loss": 0.8084,
+      "step": 267
+    },
+    {
+      "epoch": 1.7648351648351648,
+      "grad_norm": 0.9331267476081848,
+      "learning_rate": 8.381374722838138e-05,
+      "loss": 0.5766,
+      "step": 268
+    },
+    {
+      "epoch": 1.7714285714285714,
+      "grad_norm": 0.9532290101051331,
+      "learning_rate": 8.337028824833703e-05,
+      "loss": 0.6346,
+      "step": 269
+    },
+    {
+      "epoch": 1.778021978021978,
+      "grad_norm": 0.8746224045753479,
+      "learning_rate": 8.292682926829268e-05,
+      "loss": 0.767,
+      "step": 270
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 0.9629987478256226,
+      "learning_rate": 8.248337028824834e-05,
+      "loss": 0.7119,
+      "step": 271
+    },
+    {
+      "epoch": 1.791208791208791,
+      "grad_norm": 0.9313672184944153,
+      "learning_rate": 8.2039911308204e-05,
+      "loss": 0.666,
+      "step": 272
+    },
+    {
+      "epoch": 1.7978021978021979,
+      "grad_norm": 0.9044557213783264,
+      "learning_rate": 8.159645232815965e-05,
+      "loss": 0.6763,
+      "step": 273
+    },
+    {
+      "epoch": 1.8043956043956044,
+      "grad_norm": 0.9292275309562683,
+      "learning_rate": 8.11529933481153e-05,
+      "loss": 0.7549,
+      "step": 274
+    },
+    {
+      "epoch": 1.810989010989011,
+      "grad_norm": 0.9684752225875854,
+      "learning_rate": 8.070953436807095e-05,
+      "loss": 0.7161,
+      "step": 275
+    },
+    {
+      "epoch": 1.8175824175824176,
+      "grad_norm": 0.9943110942840576,
+      "learning_rate": 8.026607538802661e-05,
+      "loss": 0.7042,
+      "step": 276
+    },
+    {
+      "epoch": 1.8241758241758241,
+      "grad_norm": 0.8513030409812927,
+      "learning_rate": 7.982261640798227e-05,
+      "loss": 0.5113,
+      "step": 277
+    },
+    {
+      "epoch": 1.830769230769231,
+      "grad_norm": 1.060212254524231,
+      "learning_rate": 7.937915742793793e-05,
+      "loss": 0.6123,
+      "step": 278
+    },
+    {
+      "epoch": 1.8373626373626375,
+      "grad_norm": 0.9077796936035156,
+      "learning_rate": 7.893569844789357e-05,
+      "loss": 0.64,
+      "step": 279
+    },
+    {
+      "epoch": 1.843956043956044,
+      "grad_norm": 1.0187773704528809,
+      "learning_rate": 7.849223946784923e-05,
+      "loss": 0.6664,
+      "step": 280
+    },
+    {
+      "epoch": 1.8505494505494506,
+      "grad_norm": 0.9494662880897522,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 0.685,
+      "step": 281
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.9622290134429932,
+      "learning_rate": 7.760532150776053e-05,
+      "loss": 0.7884,
+      "step": 282
+    },
+    {
+      "epoch": 1.8637362637362638,
+      "grad_norm": 0.939732015132904,
+      "learning_rate": 7.716186252771619e-05,
+      "loss": 0.6902,
+      "step": 283
+    },
+    {
+      "epoch": 1.8703296703296703,
+      "grad_norm": 0.9728253483772278,
+      "learning_rate": 7.671840354767185e-05,
+      "loss": 0.7,
+      "step": 284
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 0.9850935935974121,
+      "learning_rate": 7.627494456762749e-05,
+      "loss": 0.618,
+      "step": 285
+    },
+    {
+      "epoch": 1.8835164835164835,
+      "grad_norm": 0.9265382885932922,
+      "learning_rate": 7.583148558758315e-05,
+      "loss": 0.6769,
+      "step": 286
+    },
+    {
+      "epoch": 1.89010989010989,
+      "grad_norm": 1.0201243162155151,
+      "learning_rate": 7.538802660753881e-05,
+      "loss": 0.8073,
+      "step": 287
+    },
+    {
+      "epoch": 1.8967032967032966,
+      "grad_norm": 1.014296293258667,
+      "learning_rate": 7.494456762749445e-05,
+      "loss": 0.859,
+      "step": 288
+    },
+    {
+      "epoch": 1.9032967032967032,
+      "grad_norm": 0.9371362328529358,
+      "learning_rate": 7.450110864745011e-05,
+      "loss": 0.7705,
+      "step": 289
+    },
+    {
+      "epoch": 1.9098901098901098,
+      "grad_norm": 0.8587055802345276,
+      "learning_rate": 7.405764966740577e-05,
+      "loss": 0.5554,
+      "step": 290
+    },
+    {
+      "epoch": 1.9164835164835163,
+      "grad_norm": 1.0286493301391602,
+      "learning_rate": 7.361419068736141e-05,
+      "loss": 0.6229,
+      "step": 291
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.9900080561637878,
+      "learning_rate": 7.317073170731707e-05,
+      "loss": 0.6241,
+      "step": 292
+    },
+    {
+      "epoch": 1.9296703296703297,
+      "grad_norm": 0.9019253253936768,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.6709,
+      "step": 293
+    },
+    {
+      "epoch": 1.9362637362637363,
+      "grad_norm": 0.8667879700660706,
+      "learning_rate": 7.228381374722837e-05,
+      "loss": 0.7175,
+      "step": 294
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 0.919500470161438,
+      "learning_rate": 7.184035476718403e-05,
+      "loss": 0.6906,
+      "step": 295
+    },
+    {
+      "epoch": 1.9494505494505494,
+      "grad_norm": 1.0102620124816895,
+      "learning_rate": 7.139689578713969e-05,
+      "loss": 0.7658,
+      "step": 296
+    },
+    {
+      "epoch": 1.9560439560439562,
+      "grad_norm": 1.0042073726654053,
+      "learning_rate": 7.095343680709535e-05,
+      "loss": 0.9426,
+      "step": 297
+    },
+    {
+      "epoch": 1.9626373626373628,
+      "grad_norm": 0.9186024069786072,
+      "learning_rate": 7.0509977827051e-05,
+      "loss": 0.6363,
+      "step": 298
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 0.9052286148071289,
+      "learning_rate": 7.006651884700666e-05,
+      "loss": 0.743,
+      "step": 299
+    },
+    {
+      "epoch": 1.975824175824176,
+      "grad_norm": 0.8644838929176331,
+      "learning_rate": 6.962305986696232e-05,
+      "loss": 0.6386,
+      "step": 300
+    },
+    {
+      "epoch": 1.9824175824175825,
+      "grad_norm": 0.9243000745773315,
+      "learning_rate": 6.917960088691796e-05,
+      "loss": 0.8679,
+      "step": 301
+    },
+    {
+      "epoch": 1.989010989010989,
+      "grad_norm": 0.8866783380508423,
+      "learning_rate": 6.873614190687362e-05,
+      "loss": 0.6027,
+      "step": 302
+    },
+    {
+      "epoch": 1.9956043956043956,
+      "grad_norm": 0.9236951470375061,
+      "learning_rate": 6.829268292682928e-05,
+      "loss": 0.7557,
+      "step": 303
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4078657627105713,
+      "learning_rate": 6.784922394678492e-05,
+      "loss": 0.9554,
+      "step": 304
+    },
+    {
+      "epoch": 2.0065934065934066,
+      "grad_norm": 0.8188623785972595,
+      "learning_rate": 6.740576496674058e-05,
+      "loss": 0.4444,
+      "step": 305
+    },
+    {
+      "epoch": 2.013186813186813,
+      "grad_norm": 0.8209565281867981,
+      "learning_rate": 6.696230598669624e-05,
+      "loss": 0.4394,
+      "step": 306
+    },
+    {
+      "epoch": 2.0197802197802197,
+      "grad_norm": 0.9053224325180054,
+      "learning_rate": 6.651884700665188e-05,
+      "loss": 0.56,
+      "step": 307
+    },
+    {
+      "epoch": 2.0263736263736263,
+      "grad_norm": 0.7447941303253174,
+      "learning_rate": 6.607538802660754e-05,
+      "loss": 0.4407,
+      "step": 308
+    },
+    {
+      "epoch": 2.032967032967033,
+      "grad_norm": 1.0495209693908691,
+      "learning_rate": 6.56319290465632e-05,
+      "loss": 0.6685,
+      "step": 309
+    },
+    {
+      "epoch": 2.0395604395604394,
+      "grad_norm": 0.8547461628913879,
+      "learning_rate": 6.518847006651884e-05,
+      "loss": 0.6651,
+      "step": 310
+    },
+    {
+      "epoch": 2.046153846153846,
+      "grad_norm": 0.8023438453674316,
+      "learning_rate": 6.47450110864745e-05,
+      "loss": 0.4911,
+      "step": 311
+    },
+    {
+      "epoch": 2.0527472527472526,
+      "grad_norm": 0.7967114448547363,
+      "learning_rate": 6.430155210643016e-05,
+      "loss": 0.462,
+      "step": 312
+    },
+    {
+      "epoch": 2.059340659340659,
+      "grad_norm": 0.7307035326957703,
+      "learning_rate": 6.38580931263858e-05,
+      "loss": 0.4417,
+      "step": 313
+    },
+    {
+      "epoch": 2.065934065934066,
+      "grad_norm": 0.9502585530281067,
+      "learning_rate": 6.341463414634146e-05,
+      "loss": 0.5023,
+      "step": 314
+    },
+    {
+      "epoch": 2.0725274725274727,
+      "grad_norm": 0.7941933274269104,
+      "learning_rate": 6.297117516629712e-05,
+      "loss": 0.4788,
+      "step": 315
+    },
+    {
+      "epoch": 2.0791208791208793,
+      "grad_norm": 0.8505730628967285,
+      "learning_rate": 6.252771618625277e-05,
+      "loss": 0.5223,
+      "step": 316
+    },
+    {
+      "epoch": 2.085714285714286,
+      "grad_norm": 1.002892017364502,
+      "learning_rate": 6.208425720620842e-05,
+      "loss": 0.5459,
+      "step": 317
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": 0.909084141254425,
+      "learning_rate": 6.164079822616408e-05,
+      "loss": 0.4608,
+      "step": 318
+    },
+    {
+      "epoch": 2.098901098901099,
+      "grad_norm": 0.931983470916748,
+      "learning_rate": 6.119733924611974e-05,
+      "loss": 0.4575,
+      "step": 319
+    },
+    {
+      "epoch": 2.1054945054945056,
+      "grad_norm": 0.895256757736206,
+      "learning_rate": 6.075388026607539e-05,
+      "loss": 0.5253,
+      "step": 320
+    },
+    {
+      "epoch": 2.112087912087912,
+      "grad_norm": 0.9337331056594849,
+      "learning_rate": 6.031042128603105e-05,
+      "loss": 0.4682,
+      "step": 321
+    },
+    {
+      "epoch": 2.1186813186813187,
+      "grad_norm": 0.9336774349212646,
+      "learning_rate": 5.98669623059867e-05,
+      "loss": 0.4865,
+      "step": 322
+    },
+    {
+      "epoch": 2.1252747252747253,
+      "grad_norm": 1.0054444074630737,
+      "learning_rate": 5.942350332594236e-05,
+      "loss": 0.4287,
+      "step": 323
+    },
+    {
+      "epoch": 2.131868131868132,
+      "grad_norm": 1.1408913135528564,
+      "learning_rate": 5.898004434589801e-05,
+      "loss": 0.6338,
+      "step": 324
+    },
+    {
+      "epoch": 2.1384615384615384,
+      "grad_norm": 1.0122843980789185,
+      "learning_rate": 5.853658536585366e-05,
+      "loss": 0.4526,
+      "step": 325
+    },
+    {
+      "epoch": 2.145054945054945,
+      "grad_norm": 0.8692342042922974,
+      "learning_rate": 5.809312638580932e-05,
+      "loss": 0.3374,
+      "step": 326
+    },
+    {
+      "epoch": 2.1516483516483516,
+      "grad_norm": 0.9748994708061218,
+      "learning_rate": 5.7649667405764975e-05,
+      "loss": 0.4917,
+      "step": 327
+    },
+    {
+      "epoch": 2.158241758241758,
+      "grad_norm": 1.2369434833526611,
+      "learning_rate": 5.720620842572062e-05,
+      "loss": 0.6221,
+      "step": 328
+    },
+    {
+      "epoch": 2.1648351648351647,
+      "grad_norm": 1.24856436252594,
+      "learning_rate": 5.676274944567628e-05,
+      "loss": 0.5077,
+      "step": 329
+    },
+    {
+      "epoch": 2.1714285714285713,
+      "grad_norm": 1.050184726715088,
+      "learning_rate": 5.6319290465631935e-05,
+      "loss": 0.5424,
+      "step": 330
+    },
+    {
+      "epoch": 2.178021978021978,
+      "grad_norm": 1.1445530652999878,
+      "learning_rate": 5.587583148558758e-05,
+      "loss": 0.6429,
+      "step": 331
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 1.2428981065750122,
+      "learning_rate": 5.543237250554324e-05,
+      "loss": 0.4412,
+      "step": 332
+    },
+    {
+      "epoch": 2.1912087912087914,
+      "grad_norm": 1.0997766256332397,
+      "learning_rate": 5.4988913525498895e-05,
+      "loss": 0.4942,
+      "step": 333
+    },
+    {
+      "epoch": 2.197802197802198,
+      "grad_norm": 1.0919004678726196,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.5455,
+      "step": 334
+    },
+    {
+      "epoch": 2.2043956043956046,
+      "grad_norm": 1.2210663557052612,
+      "learning_rate": 5.4101995565410204e-05,
+      "loss": 0.5745,
+      "step": 335
+    },
+    {
+      "epoch": 2.210989010989011,
+      "grad_norm": 1.127824068069458,
+      "learning_rate": 5.365853658536586e-05,
+      "loss": 0.5094,
+      "step": 336
+    },
+    {
+      "epoch": 2.2175824175824177,
+      "grad_norm": 1.0630571842193604,
+      "learning_rate": 5.3215077605321506e-05,
+      "loss": 0.42,
+      "step": 337
+    },
+    {
+      "epoch": 2.2241758241758243,
+      "grad_norm": 1.1563777923583984,
+      "learning_rate": 5.2771618625277164e-05,
+      "loss": 0.7547,
+      "step": 338
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 1.10713529586792,
+      "learning_rate": 5.232815964523282e-05,
+      "loss": 0.6206,
+      "step": 339
+    },
+    {
+      "epoch": 2.2373626373626374,
+      "grad_norm": 1.0907244682312012,
+      "learning_rate": 5.1884700665188466e-05,
+      "loss": 0.4727,
+      "step": 340
+    },
+    {
+      "epoch": 2.243956043956044,
+      "grad_norm": 1.0859978199005127,
+      "learning_rate": 5.1441241685144124e-05,
+      "loss": 0.462,
+      "step": 341
+    },
+    {
+      "epoch": 2.2505494505494505,
+      "grad_norm": 1.178173542022705,
+      "learning_rate": 5.099778270509978e-05,
+      "loss": 0.5036,
+      "step": 342
+    },
+    {
+      "epoch": 2.257142857142857,
+      "grad_norm": 1.0109366178512573,
+      "learning_rate": 5.0554323725055433e-05,
+      "loss": 0.4557,
+      "step": 343
+    },
+    {
+      "epoch": 2.2637362637362637,
+      "grad_norm": 1.023767352104187,
+      "learning_rate": 5.011086474501109e-05,
+      "loss": 0.4147,
+      "step": 344
+    },
+    {
+      "epoch": 2.2703296703296703,
+      "grad_norm": 1.0584118366241455,
+      "learning_rate": 4.966740576496674e-05,
+      "loss": 0.5006,
+      "step": 345
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": 1.1728785037994385,
+      "learning_rate": 4.92239467849224e-05,
+      "loss": 0.4093,
+      "step": 346
+    },
+    {
+      "epoch": 2.2835164835164834,
+      "grad_norm": 1.095776081085205,
+      "learning_rate": 4.878048780487805e-05,
+      "loss": 0.5031,
+      "step": 347
+    },
+    {
+      "epoch": 2.29010989010989,
+      "grad_norm": 1.0550340414047241,
+      "learning_rate": 4.833702882483371e-05,
+      "loss": 0.4582,
+      "step": 348
+    },
+    {
+      "epoch": 2.2967032967032965,
+      "grad_norm": 1.088047742843628,
+      "learning_rate": 4.789356984478936e-05,
+      "loss": 0.5495,
+      "step": 349
+    },
+    {
+      "epoch": 2.303296703296703,
+      "grad_norm": 1.0444499254226685,
+      "learning_rate": 4.745011086474501e-05,
+      "loss": 0.366,
+      "step": 350
+    },
+    {
+      "epoch": 2.3098901098901097,
+      "grad_norm": 1.1363768577575684,
+      "learning_rate": 4.700665188470067e-05,
+      "loss": 0.4373,
+      "step": 351
+    },
+    {
+      "epoch": 2.3164835164835162,
+      "grad_norm": 1.1664003133773804,
+      "learning_rate": 4.656319290465632e-05,
+      "loss": 0.3863,
+      "step": 352
+    },
+    {
+      "epoch": 2.3230769230769233,
+      "grad_norm": 1.0671169757843018,
+      "learning_rate": 4.611973392461197e-05,
+      "loss": 0.391,
+      "step": 353
+    },
+    {
+      "epoch": 2.32967032967033,
+      "grad_norm": 1.162846565246582,
+      "learning_rate": 4.567627494456763e-05,
+      "loss": 0.5029,
+      "step": 354
+    },
+    {
+      "epoch": 2.3362637362637364,
+      "grad_norm": 1.0342671871185303,
+      "learning_rate": 4.523281596452328e-05,
+      "loss": 0.4461,
+      "step": 355
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 1.0766485929489136,
+      "learning_rate": 4.478935698447894e-05,
+      "loss": 0.3981,
+      "step": 356
+    },
+    {
+      "epoch": 2.3494505494505495,
+      "grad_norm": 1.2582656145095825,
+      "learning_rate": 4.4345898004434597e-05,
+      "loss": 0.5223,
+      "step": 357
+    },
+    {
+      "epoch": 2.356043956043956,
+      "grad_norm": 1.13029146194458,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 0.4884,
+      "step": 358
+    },
+    {
+      "epoch": 2.3626373626373627,
+      "grad_norm": 1.2363770008087158,
+      "learning_rate": 4.34589800443459e-05,
+      "loss": 0.5851,
+      "step": 359
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 1.2439428567886353,
+      "learning_rate": 4.301552106430156e-05,
+      "loss": 0.6521,
+      "step": 360
+    },
+    {
+      "epoch": 2.375824175824176,
+      "grad_norm": 1.0968564748764038,
+      "learning_rate": 4.257206208425721e-05,
+      "loss": 0.456,
+      "step": 361
+    },
+    {
+      "epoch": 2.3824175824175824,
+      "grad_norm": 1.2433748245239258,
+      "learning_rate": 4.212860310421286e-05,
+      "loss": 0.3991,
+      "step": 362
+    },
+    {
+      "epoch": 2.389010989010989,
+      "grad_norm": 1.164085030555725,
+      "learning_rate": 4.168514412416852e-05,
+      "loss": 0.4912,
+      "step": 363
+    },
+    {
+      "epoch": 2.3956043956043955,
+      "grad_norm": 1.1060277223587036,
+      "learning_rate": 4.124168514412417e-05,
+      "loss": 0.4292,
+      "step": 364
+    },
+    {
+      "epoch": 2.402197802197802,
+      "grad_norm": 1.1612398624420166,
+      "learning_rate": 4.0798226164079826e-05,
+      "loss": 0.4769,
+      "step": 365
+    },
+    {
+      "epoch": 2.4087912087912087,
+      "grad_norm": 1.203786849975586,
+      "learning_rate": 4.035476718403548e-05,
+      "loss": 0.4396,
+      "step": 366
+    },
+    {
+      "epoch": 2.4153846153846152,
+      "grad_norm": 1.2423393726348877,
+      "learning_rate": 3.9911308203991135e-05,
+      "loss": 0.6294,
+      "step": 367
+    },
+    {
+      "epoch": 2.421978021978022,
+      "grad_norm": 1.1764495372772217,
+      "learning_rate": 3.9467849223946786e-05,
+      "loss": 0.466,
+      "step": 368
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.9935222864151001,
+      "learning_rate": 3.9024390243902444e-05,
+      "loss": 0.3693,
+      "step": 369
+    },
+    {
+      "epoch": 2.4351648351648354,
+      "grad_norm": 1.0912505388259888,
+      "learning_rate": 3.8580931263858095e-05,
+      "loss": 0.5242,
+      "step": 370
+    },
+    {
+      "epoch": 2.441758241758242,
+      "grad_norm": 1.2459967136383057,
+      "learning_rate": 3.8137472283813746e-05,
+      "loss": 0.4565,
+      "step": 371
+    },
+    {
+      "epoch": 2.4483516483516485,
+      "grad_norm": 1.3454749584197998,
+      "learning_rate": 3.7694013303769404e-05,
+      "loss": 0.4823,
+      "step": 372
+    },
+    {
+      "epoch": 2.454945054945055,
+      "grad_norm": 1.1659845113754272,
+      "learning_rate": 3.7250554323725055e-05,
+      "loss": 0.4796,
+      "step": 373
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 1.3952912092208862,
+      "learning_rate": 3.6807095343680706e-05,
+      "loss": 0.5487,
+      "step": 374
+    },
+    {
+      "epoch": 2.4681318681318682,
+      "grad_norm": 1.1365119218826294,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.3849,
+      "step": 375
+    },
+    {
+      "epoch": 2.474725274725275,
+      "grad_norm": 1.3167695999145508,
+      "learning_rate": 3.5920177383592015e-05,
+      "loss": 0.4682,
+      "step": 376
+    },
+    {
+      "epoch": 2.4813186813186814,
+      "grad_norm": 1.1612582206726074,
+      "learning_rate": 3.547671840354767e-05,
+      "loss": 0.4126,
+      "step": 377
+    },
+    {
+      "epoch": 2.487912087912088,
+      "grad_norm": 1.3263533115386963,
+      "learning_rate": 3.503325942350333e-05,
+      "loss": 0.5872,
+      "step": 378
+    },
+    {
+      "epoch": 2.4945054945054945,
+      "grad_norm": 1.1602787971496582,
+      "learning_rate": 3.458980044345898e-05,
+      "loss": 0.4198,
+      "step": 379
+    },
+    {
+      "epoch": 2.501098901098901,
+      "grad_norm": 1.4288383722305298,
+      "learning_rate": 3.414634146341464e-05,
+      "loss": 0.6402,
+      "step": 380
+    },
+    {
+      "epoch": 2.5076923076923077,
+      "grad_norm": 1.3304764032363892,
+      "learning_rate": 3.370288248337029e-05,
+      "loss": 0.5998,
+      "step": 381
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 1.2399685382843018,
+      "learning_rate": 3.325942350332594e-05,
+      "loss": 0.6481,
+      "step": 382
+    },
+    {
+      "epoch": 2.520879120879121,
+      "grad_norm": 1.2732019424438477,
+      "learning_rate": 3.28159645232816e-05,
+      "loss": 0.4519,
+      "step": 383
+    },
+    {
+      "epoch": 2.5274725274725274,
+      "grad_norm": 1.1038541793823242,
+      "learning_rate": 3.237250554323725e-05,
+      "loss": 0.452,
+      "step": 384
+    },
+    {
+      "epoch": 2.534065934065934,
+      "grad_norm": 1.3610213994979858,
+      "learning_rate": 3.19290465631929e-05,
+      "loss": 0.5469,
+      "step": 385
+    },
+    {
+      "epoch": 2.5406593406593405,
+      "grad_norm": 1.0704257488250732,
+      "learning_rate": 3.148558758314856e-05,
+      "loss": 0.5371,
+      "step": 386
+    },
+    {
+      "epoch": 2.547252747252747,
+      "grad_norm": 1.3428083658218384,
+      "learning_rate": 3.104212860310421e-05,
+      "loss": 0.4344,
+      "step": 387
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 1.285402774810791,
+      "learning_rate": 3.059866962305987e-05,
+      "loss": 0.569,
+      "step": 388
+    },
+    {
+      "epoch": 2.5604395604395602,
+      "grad_norm": 1.29883873462677,
+      "learning_rate": 3.0155210643015524e-05,
+      "loss": 0.5639,
+      "step": 389
+    },
+    {
+      "epoch": 2.567032967032967,
+      "grad_norm": 1.152541995048523,
+      "learning_rate": 2.971175166297118e-05,
+      "loss": 0.467,
+      "step": 390
+    },
+    {
+      "epoch": 2.5736263736263734,
+      "grad_norm": 1.094746708869934,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 0.3988,
+      "step": 391
+    },
+    {
+      "epoch": 2.5802197802197804,
+      "grad_norm": 1.1134113073349,
+      "learning_rate": 2.8824833702882487e-05,
+      "loss": 0.5539,
+      "step": 392
+    },
+    {
+      "epoch": 2.586813186813187,
+      "grad_norm": 1.2066001892089844,
+      "learning_rate": 2.838137472283814e-05,
+      "loss": 0.5297,
+      "step": 393
+    },
+    {
+      "epoch": 2.5934065934065935,
+      "grad_norm": 1.0876188278198242,
+      "learning_rate": 2.793791574279379e-05,
+      "loss": 0.4342,
+      "step": 394
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.305462121963501,
+      "learning_rate": 2.7494456762749448e-05,
+      "loss": 0.5276,
+      "step": 395
+    },
+    {
+      "epoch": 2.6065934065934067,
+      "grad_norm": 1.0165784358978271,
+      "learning_rate": 2.7050997782705102e-05,
+      "loss": 0.3881,
+      "step": 396
+    },
+    {
+      "epoch": 2.6131868131868132,
+      "grad_norm": 1.1773567199707031,
+      "learning_rate": 2.6607538802660753e-05,
+      "loss": 0.37,
+      "step": 397
+    },
+    {
+      "epoch": 2.61978021978022,
+      "grad_norm": 1.4506839513778687,
+      "learning_rate": 2.616407982261641e-05,
+      "loss": 0.6639,
+      "step": 398
+    },
+    {
+      "epoch": 2.6263736263736264,
+      "grad_norm": 1.318416714668274,
+      "learning_rate": 2.5720620842572062e-05,
+      "loss": 0.4487,
+      "step": 399
+    },
+    {
+      "epoch": 2.632967032967033,
+      "grad_norm": 1.2602953910827637,
+      "learning_rate": 2.5277161862527717e-05,
+      "loss": 0.4994,
+      "step": 400
+    },
+    {
+      "epoch": 2.6395604395604395,
+      "grad_norm": 1.1881996393203735,
+      "learning_rate": 2.483370288248337e-05,
+      "loss": 0.5215,
+      "step": 401
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": 1.216118335723877,
+      "learning_rate": 2.4390243902439026e-05,
+      "loss": 0.488,
+      "step": 402
+    },
+    {
+      "epoch": 2.6527472527472526,
+      "grad_norm": 1.3304966688156128,
+      "learning_rate": 2.394678492239468e-05,
+      "loss": 0.6547,
+      "step": 403
+    },
+    {
+      "epoch": 2.659340659340659,
+      "grad_norm": 1.181434154510498,
+      "learning_rate": 2.3503325942350335e-05,
+      "loss": 0.5166,
+      "step": 404
+    },
+    {
+      "epoch": 2.665934065934066,
+      "grad_norm": 1.2073309421539307,
+      "learning_rate": 2.3059866962305986e-05,
+      "loss": 0.5226,
+      "step": 405
+    },
+    {
+      "epoch": 2.672527472527473,
+      "grad_norm": 1.2751001119613647,
+      "learning_rate": 2.261640798226164e-05,
+      "loss": 0.5828,
+      "step": 406
+    },
+    {
+      "epoch": 2.6791208791208794,
+      "grad_norm": 1.2410969734191895,
+      "learning_rate": 2.2172949002217298e-05,
+      "loss": 0.5744,
+      "step": 407
+    },
+    {
+      "epoch": 2.685714285714286,
+      "grad_norm": 1.3055206537246704,
+      "learning_rate": 2.172949002217295e-05,
+      "loss": 0.4636,
+      "step": 408
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 1.1220375299453735,
+      "learning_rate": 2.1286031042128604e-05,
+      "loss": 0.3735,
+      "step": 409
+    },
+    {
+      "epoch": 2.698901098901099,
+      "grad_norm": 1.1999492645263672,
+      "learning_rate": 2.084257206208426e-05,
+      "loss": 0.6794,
+      "step": 410
+    },
+    {
+      "epoch": 2.7054945054945057,
+      "grad_norm": 1.3364157676696777,
+      "learning_rate": 2.0399113082039913e-05,
+      "loss": 0.4814,
+      "step": 411
+    },
+    {
+      "epoch": 2.7120879120879122,
+      "grad_norm": 1.1284774541854858,
+      "learning_rate": 1.9955654101995567e-05,
+      "loss": 0.4965,
+      "step": 412
+    },
+    {
+      "epoch": 2.718681318681319,
+      "grad_norm": 1.164880633354187,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 0.4251,
+      "step": 413
+    },
+    {
+      "epoch": 2.7252747252747254,
+      "grad_norm": 1.1765766143798828,
+      "learning_rate": 1.9068736141906873e-05,
+      "loss": 0.4431,
+      "step": 414
+    },
+    {
+      "epoch": 2.731868131868132,
+      "grad_norm": 1.2489506006240845,
+      "learning_rate": 1.8625277161862528e-05,
+      "loss": 0.579,
+      "step": 415
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "grad_norm": 1.2493239641189575,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.5102,
+      "step": 416
+    },
+    {
+      "epoch": 2.745054945054945,
+      "grad_norm": 1.2093948125839233,
+      "learning_rate": 1.7738359201773837e-05,
+      "loss": 0.4576,
+      "step": 417
+    },
+    {
+      "epoch": 2.7516483516483516,
+      "grad_norm": 1.2248109579086304,
+      "learning_rate": 1.729490022172949e-05,
+      "loss": 0.4565,
+      "step": 418
+    },
+    {
+      "epoch": 2.758241758241758,
+      "grad_norm": 1.2510703802108765,
+      "learning_rate": 1.6851441241685146e-05,
+      "loss": 0.5101,
+      "step": 419
+    },
+    {
+      "epoch": 2.764835164835165,
+      "grad_norm": 1.1197317838668823,
+      "learning_rate": 1.64079822616408e-05,
+      "loss": 0.3932,
+      "step": 420
+    },
+    {
+      "epoch": 2.7714285714285714,
+      "grad_norm": 1.1093721389770508,
+      "learning_rate": 1.596452328159645e-05,
+      "loss": 0.4619,
+      "step": 421
+    },
+    {
+      "epoch": 2.778021978021978,
+      "grad_norm": 1.0948904752731323,
+      "learning_rate": 1.5521064301552106e-05,
+      "loss": 0.3213,
+      "step": 422
+    },
+    {
+      "epoch": 2.7846153846153845,
+      "grad_norm": 1.1975831985473633,
+      "learning_rate": 1.5077605321507762e-05,
+      "loss": 0.4201,
+      "step": 423
+    },
+    {
+      "epoch": 2.791208791208791,
+      "grad_norm": 1.3361371755599976,
+      "learning_rate": 1.4634146341463415e-05,
+      "loss": 0.7144,
+      "step": 424
+    },
+    {
+      "epoch": 2.7978021978021976,
+      "grad_norm": 1.2981891632080078,
+      "learning_rate": 1.419068736141907e-05,
+      "loss": 0.4705,
+      "step": 425
+    },
+    {
+      "epoch": 2.804395604395604,
+      "grad_norm": 1.187825322151184,
+      "learning_rate": 1.3747228381374724e-05,
+      "loss": 0.4792,
+      "step": 426
+    },
+    {
+      "epoch": 2.8109890109890108,
+      "grad_norm": 1.2194219827651978,
+      "learning_rate": 1.3303769401330377e-05,
+      "loss": 0.4515,
+      "step": 427
+    },
+    {
+      "epoch": 2.8175824175824173,
+      "grad_norm": 1.1892176866531372,
+      "learning_rate": 1.2860310421286031e-05,
+      "loss": 0.5071,
+      "step": 428
+    },
+    {
+      "epoch": 2.824175824175824,
+      "grad_norm": 1.322208285331726,
+      "learning_rate": 1.2416851441241686e-05,
+      "loss": 0.5249,
+      "step": 429
+    },
+    {
+      "epoch": 2.830769230769231,
+      "grad_norm": 1.270622968673706,
+      "learning_rate": 1.197339246119734e-05,
+      "loss": 0.6015,
+      "step": 430
+    },
+    {
+      "epoch": 2.8373626373626375,
+      "grad_norm": 1.2021064758300781,
+      "learning_rate": 1.1529933481152993e-05,
+      "loss": 0.4098,
+      "step": 431
+    },
+    {
+      "epoch": 2.843956043956044,
+      "grad_norm": 1.2847568988800049,
+      "learning_rate": 1.1086474501108649e-05,
+      "loss": 0.4508,
+      "step": 432
+    },
+    {
+      "epoch": 2.8505494505494506,
+      "grad_norm": 1.1565632820129395,
+      "learning_rate": 1.0643015521064302e-05,
+      "loss": 0.3805,
+      "step": 433
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.0236175060272217,
+      "learning_rate": 1.0199556541019956e-05,
+      "loss": 0.3792,
+      "step": 434
+    },
+    {
+      "epoch": 2.8637362637362638,
+      "grad_norm": 1.1567318439483643,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 0.4034,
+      "step": 435
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.542642769728307e+16,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-435/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f767c9955992f932274c4815a2a904b6da669e24ec9e19f0ab3bb70f1dc495b2
+size 6417