Upload seed2/checkpoint-453

.gitattributes

@@ -125,3 +125,4 @@ seed2/checkpoint-405/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-435/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+seed2/checkpoint-453/tokenizer.json filter=lfs diff=lfs merge=lfs -text

seed2/checkpoint-453/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-7B-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 0.18.1

seed2/checkpoint-453/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "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/Qwen2.5-7B-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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

seed2/checkpoint-453/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ff11e717d8c37e13a44b77269a49f64986ce0e2731ef0b17165a430738279e
+size 80792096

seed2/checkpoint-453/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
+}

seed2/checkpoint-453/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 %}

seed2/checkpoint-453/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee045ba7764ea1474ceb83374e625207b13b2f078071999e1658145a5582b24
+size 161816187

seed2/checkpoint-453/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3f3335af7bca960f4bf4e86542ce290e65051bf83c58abfe5d7c28c6e65174
+size 14645

seed2/checkpoint-453/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e8a718bbe1c39b3ed29c8f8300ca589190504c4ee2f74413078f1ca602f0ee
+size 1465

seed2/checkpoint-453/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|>"
+}

seed2/checkpoint-453/tokenizer.json

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

seed2/checkpoint-453/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
+}

seed2/checkpoint-453/trainer_state.json

@@ -0,0 +1,3205 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 453,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0066518847006651885,
+      "grad_norm": 0.8310242891311646,
+      "learning_rate": 0.0,
+      "loss": 0.915,
+      "step": 1
+    },
+    {
+      "epoch": 0.013303769401330377,
+      "grad_norm": 0.8229848146438599,
+      "learning_rate": 4e-05,
+      "loss": 0.9886,
+      "step": 2
+    },
+    {
+      "epoch": 0.019955654101995565,
+      "grad_norm": 0.7515509724617004,
+      "learning_rate": 8e-05,
+      "loss": 0.961,
+      "step": 3
+    },
+    {
+      "epoch": 0.026607538802660754,
+      "grad_norm": 0.9603739380836487,
+      "learning_rate": 0.00012,
+      "loss": 1.0453,
+      "step": 4
+    },
+    {
+      "epoch": 0.03325942350332594,
+      "grad_norm": 1.0088942050933838,
+      "learning_rate": 0.00016,
+      "loss": 0.9475,
+      "step": 5
+    },
+    {
+      "epoch": 0.03991130820399113,
+      "grad_norm": 0.5193823575973511,
+      "learning_rate": 0.0002,
+      "loss": 0.787,
+      "step": 6
+    },
+    {
+      "epoch": 0.04656319290465632,
+      "grad_norm": 0.5896372199058533,
+      "learning_rate": 0.00019955357142857142,
+      "loss": 0.8621,
+      "step": 7
+    },
+    {
+      "epoch": 0.05321507760532151,
+      "grad_norm": 0.631470799446106,
+      "learning_rate": 0.00019910714285714288,
+      "loss": 0.8619,
+      "step": 8
+    },
+    {
+      "epoch": 0.0598669623059867,
+      "grad_norm": 0.48881030082702637,
+      "learning_rate": 0.0001986607142857143,
+      "loss": 0.8215,
+      "step": 9
+    },
+    {
+      "epoch": 0.06651884700665188,
+      "grad_norm": 0.5458150506019592,
+      "learning_rate": 0.00019821428571428572,
+      "loss": 0.9085,
+      "step": 10
+    },
+    {
+      "epoch": 0.07317073170731707,
+      "grad_norm": 0.4026842713356018,
+      "learning_rate": 0.00019776785714285716,
+      "loss": 0.872,
+      "step": 11
+    },
+    {
+      "epoch": 0.07982261640798226,
+      "grad_norm": 0.3792957663536072,
+      "learning_rate": 0.0001973214285714286,
+      "loss": 0.8473,
+      "step": 12
+    },
+    {
+      "epoch": 0.08647450110864745,
+      "grad_norm": 0.27567577362060547,
+      "learning_rate": 0.000196875,
+      "loss": 0.9062,
+      "step": 13
+    },
+    {
+      "epoch": 0.09312638580931264,
+      "grad_norm": 0.2435707002878189,
+      "learning_rate": 0.00019642857142857144,
+      "loss": 0.7227,
+      "step": 14
+    },
+    {
+      "epoch": 0.09977827050997783,
+      "grad_norm": 0.22440966963768005,
+      "learning_rate": 0.00019598214285714287,
+      "loss": 0.801,
+      "step": 15
+    },
+    {
+      "epoch": 0.10643015521064302,
+      "grad_norm": 0.23030349612236023,
+      "learning_rate": 0.00019553571428571428,
+      "loss": 0.7241,
+      "step": 16
+    },
+    {
+      "epoch": 0.1130820399113082,
+      "grad_norm": 0.27144089341163635,
+      "learning_rate": 0.00019508928571428574,
+      "loss": 0.7637,
+      "step": 17
+    },
+    {
+      "epoch": 0.1197339246119734,
+      "grad_norm": 0.25010475516319275,
+      "learning_rate": 0.00019464285714285715,
+      "loss": 0.7532,
+      "step": 18
+    },
+    {
+      "epoch": 0.12638580931263857,
+      "grad_norm": 0.32318007946014404,
+      "learning_rate": 0.00019419642857142859,
+      "loss": 0.7818,
+      "step": 19
+    },
+    {
+      "epoch": 0.13303769401330376,
+      "grad_norm": 0.3001633286476135,
+      "learning_rate": 0.00019375000000000002,
+      "loss": 0.7224,
+      "step": 20
+    },
+    {
+      "epoch": 0.13968957871396895,
+      "grad_norm": 0.29987436532974243,
+      "learning_rate": 0.00019330357142857143,
+      "loss": 0.7245,
+      "step": 21
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.33017081022262573,
+      "learning_rate": 0.00019285714285714286,
+      "loss": 0.7795,
+      "step": 22
+    },
+    {
+      "epoch": 0.15299334811529933,
+      "grad_norm": 0.33305326104164124,
+      "learning_rate": 0.0001924107142857143,
+      "loss": 0.712,
+      "step": 23
+    },
+    {
+      "epoch": 0.15964523281596452,
+      "grad_norm": 0.28796514868736267,
+      "learning_rate": 0.00019196428571428573,
+      "loss": 0.7983,
+      "step": 24
+    },
+    {
+      "epoch": 0.1662971175166297,
+      "grad_norm": 0.29620444774627686,
+      "learning_rate": 0.00019151785714285714,
+      "loss": 0.6854,
+      "step": 25
+    },
+    {
+      "epoch": 0.1729490022172949,
+      "grad_norm": 0.24983270466327667,
+      "learning_rate": 0.00019107142857142858,
+      "loss": 0.7032,
+      "step": 26
+    },
+    {
+      "epoch": 0.17960088691796008,
+      "grad_norm": 0.2487979531288147,
+      "learning_rate": 0.000190625,
+      "loss": 0.7518,
+      "step": 27
+    },
+    {
+      "epoch": 0.18625277161862527,
+      "grad_norm": 0.2762643098831177,
+      "learning_rate": 0.00019017857142857142,
+      "loss": 0.7366,
+      "step": 28
+    },
+    {
+      "epoch": 0.19290465631929046,
+      "grad_norm": 0.2557331621646881,
+      "learning_rate": 0.00018973214285714288,
+      "loss": 0.7233,
+      "step": 29
+    },
+    {
+      "epoch": 0.19955654101995565,
+      "grad_norm": 0.2430887371301651,
+      "learning_rate": 0.0001892857142857143,
+      "loss": 0.7625,
+      "step": 30
+    },
+    {
+      "epoch": 0.20620842572062084,
+      "grad_norm": 0.2325478047132492,
+      "learning_rate": 0.00018883928571428573,
+      "loss": 0.695,
+      "step": 31
+    },
+    {
+      "epoch": 0.21286031042128603,
+      "grad_norm": 0.23921388387680054,
+      "learning_rate": 0.00018839285714285716,
+      "loss": 0.6894,
+      "step": 32
+    },
+    {
+      "epoch": 0.21951219512195122,
+      "grad_norm": 0.21801581978797913,
+      "learning_rate": 0.0001879464285714286,
+      "loss": 0.7557,
+      "step": 33
+    },
+    {
+      "epoch": 0.2261640798226164,
+      "grad_norm": 0.24342158436775208,
+      "learning_rate": 0.0001875,
+      "loss": 0.7648,
+      "step": 34
+    },
+    {
+      "epoch": 0.2328159645232816,
+      "grad_norm": 0.2618267834186554,
+      "learning_rate": 0.00018705357142857144,
+      "loss": 0.7035,
+      "step": 35
+    },
+    {
+      "epoch": 0.2394678492239468,
+      "grad_norm": 0.27009889483451843,
+      "learning_rate": 0.00018660714285714287,
+      "loss": 0.778,
+      "step": 36
+    },
+    {
+      "epoch": 0.24611973392461198,
+      "grad_norm": 0.2976726293563843,
+      "learning_rate": 0.00018616071428571428,
+      "loss": 0.6925,
+      "step": 37
+    },
+    {
+      "epoch": 0.25277161862527714,
+      "grad_norm": 0.257468581199646,
+      "learning_rate": 0.00018571428571428572,
+      "loss": 0.7086,
+      "step": 38
+    },
+    {
+      "epoch": 0.25942350332594233,
+      "grad_norm": 0.2403031587600708,
+      "learning_rate": 0.00018526785714285715,
+      "loss": 0.734,
+      "step": 39
+    },
+    {
+      "epoch": 0.2660753880266075,
+      "grad_norm": 0.2366427481174469,
+      "learning_rate": 0.0001848214285714286,
+      "loss": 0.7754,
+      "step": 40
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.25827541947364807,
+      "learning_rate": 0.000184375,
+      "loss": 0.7655,
+      "step": 41
+    },
+    {
+      "epoch": 0.2793791574279379,
+      "grad_norm": 0.2734667658805847,
+      "learning_rate": 0.00018392857142857143,
+      "loss": 0.6918,
+      "step": 42
+    },
+    {
+      "epoch": 0.2860310421286031,
+      "grad_norm": 0.25957050919532776,
+      "learning_rate": 0.00018348214285714287,
+      "loss": 0.7921,
+      "step": 43
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.3197234272956848,
+      "learning_rate": 0.0001830357142857143,
+      "loss": 0.7207,
+      "step": 44
+    },
+    {
+      "epoch": 0.29933481152993346,
+      "grad_norm": 0.22218957543373108,
+      "learning_rate": 0.00018258928571428574,
+      "loss": 0.7539,
+      "step": 45
+    },
+    {
+      "epoch": 0.30598669623059865,
+      "grad_norm": 0.2633613348007202,
+      "learning_rate": 0.00018214285714285714,
+      "loss": 0.7316,
+      "step": 46
+    },
+    {
+      "epoch": 0.31263858093126384,
+      "grad_norm": 0.22838076949119568,
+      "learning_rate": 0.00018169642857142858,
+      "loss": 0.6999,
+      "step": 47
+    },
+    {
+      "epoch": 0.31929046563192903,
+      "grad_norm": 0.232499361038208,
+      "learning_rate": 0.00018125000000000001,
+      "loss": 0.7206,
+      "step": 48
+    },
+    {
+      "epoch": 0.3259423503325942,
+      "grad_norm": 0.2578747272491455,
+      "learning_rate": 0.00018080357142857142,
+      "loss": 0.6735,
+      "step": 49
+    },
+    {
+      "epoch": 0.3325942350332594,
+      "grad_norm": 0.2639673352241516,
+      "learning_rate": 0.00018035714285714286,
+      "loss": 0.7357,
+      "step": 50
+    },
+    {
+      "epoch": 0.3392461197339246,
+      "grad_norm": 0.21550391614437103,
+      "learning_rate": 0.0001799107142857143,
+      "loss": 0.6824,
+      "step": 51
+    },
+    {
+      "epoch": 0.3458980044345898,
+      "grad_norm": 0.24625086784362793,
+      "learning_rate": 0.00017946428571428573,
+      "loss": 0.6843,
+      "step": 52
+    },
+    {
+      "epoch": 0.352549889135255,
+      "grad_norm": 0.24856697022914886,
+      "learning_rate": 0.00017901785714285714,
+      "loss": 0.7064,
+      "step": 53
+    },
+    {
+      "epoch": 0.35920177383592017,
+      "grad_norm": 0.30134060978889465,
+      "learning_rate": 0.0001785714285714286,
+      "loss": 0.7121,
+      "step": 54
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "grad_norm": 0.23369382321834564,
+      "learning_rate": 0.000178125,
+      "loss": 0.6376,
+      "step": 55
+    },
+    {
+      "epoch": 0.37250554323725055,
+      "grad_norm": 0.2367129772901535,
+      "learning_rate": 0.00017767857142857141,
+      "loss": 0.6901,
+      "step": 56
+    },
+    {
+      "epoch": 0.37915742793791574,
+      "grad_norm": 0.22280298173427582,
+      "learning_rate": 0.00017723214285714288,
+      "loss": 0.6617,
+      "step": 57
+    },
+    {
+      "epoch": 0.3858093126385809,
+      "grad_norm": 0.23296040296554565,
+      "learning_rate": 0.00017678571428571428,
+      "loss": 0.7251,
+      "step": 58
+    },
+    {
+      "epoch": 0.3924611973392461,
+      "grad_norm": 0.31288206577301025,
+      "learning_rate": 0.00017633928571428572,
+      "loss": 0.7122,
+      "step": 59
+    },
+    {
+      "epoch": 0.3991130820399113,
+      "grad_norm": 0.2509160041809082,
+      "learning_rate": 0.00017589285714285716,
+      "loss": 0.6626,
+      "step": 60
+    },
+    {
+      "epoch": 0.4057649667405765,
+      "grad_norm": 0.2707154154777527,
+      "learning_rate": 0.0001754464285714286,
+      "loss": 0.7154,
+      "step": 61
+    },
+    {
+      "epoch": 0.4124168514412417,
+      "grad_norm": 0.2429010570049286,
+      "learning_rate": 0.000175,
+      "loss": 0.6365,
+      "step": 62
+    },
+    {
+      "epoch": 0.4190687361419069,
+      "grad_norm": 0.2430657297372818,
+      "learning_rate": 0.00017455357142857143,
+      "loss": 0.7107,
+      "step": 63
+    },
+    {
+      "epoch": 0.42572062084257206,
+      "grad_norm": 0.27802643179893494,
+      "learning_rate": 0.00017410714285714287,
+      "loss": 0.7709,
+      "step": 64
+    },
+    {
+      "epoch": 0.43237250554323725,
+      "grad_norm": 0.24998636543750763,
+      "learning_rate": 0.00017366071428571428,
+      "loss": 0.6872,
+      "step": 65
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "grad_norm": 0.26437339186668396,
+      "learning_rate": 0.00017321428571428574,
+      "loss": 0.6821,
+      "step": 66
+    },
+    {
+      "epoch": 0.44567627494456763,
+      "grad_norm": 0.24539315700531006,
+      "learning_rate": 0.00017276785714285715,
+      "loss": 0.6839,
+      "step": 67
+    },
+    {
+      "epoch": 0.4523281596452328,
+      "grad_norm": 0.2541864514350891,
+      "learning_rate": 0.00017232142857142858,
+      "loss": 0.6656,
+      "step": 68
+    },
+    {
+      "epoch": 0.458980044345898,
+      "grad_norm": 0.23381195962429047,
+      "learning_rate": 0.00017187500000000002,
+      "loss": 0.6934,
+      "step": 69
+    },
+    {
+      "epoch": 0.4656319290465632,
+      "grad_norm": 0.2819974422454834,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 0.729,
+      "step": 70
+    },
+    {
+      "epoch": 0.4722838137472284,
+      "grad_norm": 0.24130022525787354,
+      "learning_rate": 0.00017098214285714286,
+      "loss": 0.6191,
+      "step": 71
+    },
+    {
+      "epoch": 0.4789356984478936,
+      "grad_norm": 0.25198131799697876,
+      "learning_rate": 0.0001705357142857143,
+      "loss": 0.69,
+      "step": 72
+    },
+    {
+      "epoch": 0.48558758314855877,
+      "grad_norm": 0.2732310891151428,
+      "learning_rate": 0.00017008928571428573,
+      "loss": 0.6948,
+      "step": 73
+    },
+    {
+      "epoch": 0.49223946784922396,
+      "grad_norm": 0.2318546324968338,
+      "learning_rate": 0.00016964285714285714,
+      "loss": 0.7505,
+      "step": 74
+    },
+    {
+      "epoch": 0.49889135254988914,
+      "grad_norm": 0.24327890574932098,
+      "learning_rate": 0.0001691964285714286,
+      "loss": 0.6712,
+      "step": 75
+    },
+    {
+      "epoch": 0.5055432372505543,
+      "grad_norm": 0.26212042570114136,
+      "learning_rate": 0.00016875,
+      "loss": 0.7711,
+      "step": 76
+    },
+    {
+      "epoch": 0.5121951219512195,
+      "grad_norm": 0.23978066444396973,
+      "learning_rate": 0.00016830357142857142,
+      "loss": 0.6944,
+      "step": 77
+    },
+    {
+      "epoch": 0.5188470066518847,
+      "grad_norm": 0.2625705301761627,
+      "learning_rate": 0.00016785714285714288,
+      "loss": 0.6458,
+      "step": 78
+    },
+    {
+      "epoch": 0.5254988913525499,
+      "grad_norm": 0.21966618299484253,
+      "learning_rate": 0.0001674107142857143,
+      "loss": 0.654,
+      "step": 79
+    },
+    {
+      "epoch": 0.532150776053215,
+      "grad_norm": 0.24314966797828674,
+      "learning_rate": 0.00016696428571428572,
+      "loss": 0.7762,
+      "step": 80
+    },
+    {
+      "epoch": 0.5388026607538803,
+      "grad_norm": 0.23685602843761444,
+      "learning_rate": 0.00016651785714285716,
+      "loss": 0.6867,
+      "step": 81
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.24048812687397003,
+      "learning_rate": 0.0001660714285714286,
+      "loss": 0.6997,
+      "step": 82
+    },
+    {
+      "epoch": 0.5521064301552107,
+      "grad_norm": 0.2475586235523224,
+      "learning_rate": 0.000165625,
+      "loss": 0.6646,
+      "step": 83
+    },
+    {
+      "epoch": 0.5587583148558758,
+      "grad_norm": 0.2549313008785248,
+      "learning_rate": 0.00016517857142857144,
+      "loss": 0.6725,
+      "step": 84
+    },
+    {
+      "epoch": 0.565410199556541,
+      "grad_norm": 0.2550356686115265,
+      "learning_rate": 0.00016473214285714287,
+      "loss": 0.6514,
+      "step": 85
+    },
+    {
+      "epoch": 0.5720620842572062,
+      "grad_norm": 0.261750727891922,
+      "learning_rate": 0.00016428571428571428,
+      "loss": 0.6585,
+      "step": 86
+    },
+    {
+      "epoch": 0.5787139689578714,
+      "grad_norm": 0.2562209665775299,
+      "learning_rate": 0.00016383928571428574,
+      "loss": 0.7481,
+      "step": 87
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.27665528655052185,
+      "learning_rate": 0.00016339285714285715,
+      "loss": 0.7238,
+      "step": 88
+    },
+    {
+      "epoch": 0.5920177383592018,
+      "grad_norm": 0.2530658543109894,
+      "learning_rate": 0.00016294642857142858,
+      "loss": 0.6856,
+      "step": 89
+    },
+    {
+      "epoch": 0.5986696230598669,
+      "grad_norm": 0.23601174354553223,
+      "learning_rate": 0.00016250000000000002,
+      "loss": 0.6876,
+      "step": 90
+    },
+    {
+      "epoch": 0.6053215077605322,
+      "grad_norm": 0.24731314182281494,
+      "learning_rate": 0.00016205357142857143,
+      "loss": 0.7247,
+      "step": 91
+    },
+    {
+      "epoch": 0.6119733924611973,
+      "grad_norm": 0.23446723818778992,
+      "learning_rate": 0.00016160714285714286,
+      "loss": 0.6351,
+      "step": 92
+    },
+    {
+      "epoch": 0.6186252771618626,
+      "grad_norm": 0.25239667296409607,
+      "learning_rate": 0.0001611607142857143,
+      "loss": 0.7226,
+      "step": 93
+    },
+    {
+      "epoch": 0.6252771618625277,
+      "grad_norm": 0.21660372614860535,
+      "learning_rate": 0.00016071428571428573,
+      "loss": 0.682,
+      "step": 94
+    },
+    {
+      "epoch": 0.6319290465631929,
+      "grad_norm": 0.20815734565258026,
+      "learning_rate": 0.00016026785714285714,
+      "loss": 0.632,
+      "step": 95
+    },
+    {
+      "epoch": 0.6385809312638581,
+      "grad_norm": 0.21154125034809113,
+      "learning_rate": 0.00015982142857142858,
+      "loss": 0.6863,
+      "step": 96
+    },
+    {
+      "epoch": 0.6452328159645233,
+      "grad_norm": 0.22342722117900848,
+      "learning_rate": 0.000159375,
+      "loss": 0.7141,
+      "step": 97
+    },
+    {
+      "epoch": 0.6518847006651884,
+      "grad_norm": 0.22494326531887054,
+      "learning_rate": 0.00015892857142857142,
+      "loss": 0.7591,
+      "step": 98
+    },
+    {
+      "epoch": 0.6585365853658537,
+      "grad_norm": 0.2285061627626419,
+      "learning_rate": 0.00015848214285714285,
+      "loss": 0.7111,
+      "step": 99
+    },
+    {
+      "epoch": 0.6651884700665188,
+      "grad_norm": 0.22321440279483795,
+      "learning_rate": 0.0001580357142857143,
+      "loss": 0.7955,
+      "step": 100
+    },
+    {
+      "epoch": 0.6718403547671841,
+      "grad_norm": 0.26761552691459656,
+      "learning_rate": 0.00015758928571428572,
+      "loss": 0.6992,
+      "step": 101
+    },
+    {
+      "epoch": 0.6784922394678492,
+      "grad_norm": 0.2566603124141693,
+      "learning_rate": 0.00015714285714285716,
+      "loss": 0.6276,
+      "step": 102
+    },
+    {
+      "epoch": 0.6851441241685144,
+      "grad_norm": 0.24117478728294373,
+      "learning_rate": 0.0001566964285714286,
+      "loss": 0.6952,
+      "step": 103
+    },
+    {
+      "epoch": 0.6917960088691796,
+      "grad_norm": 0.24709926545619965,
+      "learning_rate": 0.00015625,
+      "loss": 0.7355,
+      "step": 104
+    },
+    {
+      "epoch": 0.6984478935698448,
+      "grad_norm": 0.30473804473876953,
+      "learning_rate": 0.00015580357142857144,
+      "loss": 0.6933,
+      "step": 105
+    },
+    {
+      "epoch": 0.70509977827051,
+      "grad_norm": 0.2340686172246933,
+      "learning_rate": 0.00015535714285714287,
+      "loss": 0.7523,
+      "step": 106
+    },
+    {
+      "epoch": 0.7117516629711752,
+      "grad_norm": 0.2649092972278595,
+      "learning_rate": 0.00015491071428571428,
+      "loss": 0.6585,
+      "step": 107
+    },
+    {
+      "epoch": 0.7184035476718403,
+      "grad_norm": 0.23826628923416138,
+      "learning_rate": 0.00015446428571428572,
+      "loss": 0.6862,
+      "step": 108
+    },
+    {
+      "epoch": 0.7250554323725056,
+      "grad_norm": 0.22304418683052063,
+      "learning_rate": 0.00015401785714285715,
+      "loss": 0.7508,
+      "step": 109
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.27665385603904724,
+      "learning_rate": 0.0001535714285714286,
+      "loss": 0.744,
+      "step": 110
+    },
+    {
+      "epoch": 0.738359201773836,
+      "grad_norm": 0.2688440978527069,
+      "learning_rate": 0.000153125,
+      "loss": 0.7,
+      "step": 111
+    },
+    {
+      "epoch": 0.7450110864745011,
+      "grad_norm": 0.24250338971614838,
+      "learning_rate": 0.00015267857142857143,
+      "loss": 0.7264,
+      "step": 112
+    },
+    {
+      "epoch": 0.7516629711751663,
+      "grad_norm": 0.24538597464561462,
+      "learning_rate": 0.00015223214285714287,
+      "loss": 0.7161,
+      "step": 113
+    },
+    {
+      "epoch": 0.7583148558758315,
+      "grad_norm": 0.2735412120819092,
+      "learning_rate": 0.00015178571428571427,
+      "loss": 0.6717,
+      "step": 114
+    },
+    {
+      "epoch": 0.7649667405764967,
+      "grad_norm": 0.25732821226119995,
+      "learning_rate": 0.00015133928571428574,
+      "loss": 0.6793,
+      "step": 115
+    },
+    {
+      "epoch": 0.7716186252771619,
+      "grad_norm": 0.26913580298423767,
+      "learning_rate": 0.00015089285714285714,
+      "loss": 0.6919,
+      "step": 116
+    },
+    {
+      "epoch": 0.7782705099778271,
+      "grad_norm": 0.24305739998817444,
+      "learning_rate": 0.00015044642857142858,
+      "loss": 0.7338,
+      "step": 117
+    },
+    {
+      "epoch": 0.7849223946784922,
+      "grad_norm": 0.2606489956378937,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6662,
+      "step": 118
+    },
+    {
+      "epoch": 0.7915742793791575,
+      "grad_norm": 0.23980078101158142,
+      "learning_rate": 0.00014955357142857142,
+      "loss": 0.6853,
+      "step": 119
+    },
+    {
+      "epoch": 0.7982261640798226,
+      "grad_norm": 0.24457889795303345,
+      "learning_rate": 0.00014910714285714286,
+      "loss": 0.6599,
+      "step": 120
+    },
+    {
+      "epoch": 0.8048780487804879,
+      "grad_norm": 0.26142486929893494,
+      "learning_rate": 0.0001486607142857143,
+      "loss": 0.7094,
+      "step": 121
+    },
+    {
+      "epoch": 0.811529933481153,
+      "grad_norm": 0.2364434003829956,
+      "learning_rate": 0.00014821428571428573,
+      "loss": 0.7146,
+      "step": 122
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.23260164260864258,
+      "learning_rate": 0.00014776785714285714,
+      "loss": 0.6675,
+      "step": 123
+    },
+    {
+      "epoch": 0.8248337028824834,
+      "grad_norm": 0.2651958763599396,
+      "learning_rate": 0.0001473214285714286,
+      "loss": 0.7473,
+      "step": 124
+    },
+    {
+      "epoch": 0.8314855875831486,
+      "grad_norm": 0.25085121393203735,
+      "learning_rate": 0.000146875,
+      "loss": 0.7091,
+      "step": 125
+    },
+    {
+      "epoch": 0.8381374722838137,
+      "grad_norm": 0.23270738124847412,
+      "learning_rate": 0.00014642857142857141,
+      "loss": 0.7106,
+      "step": 126
+    },
+    {
+      "epoch": 0.844789356984479,
+      "grad_norm": 0.2743501663208008,
+      "learning_rate": 0.00014598214285714288,
+      "loss": 0.6802,
+      "step": 127
+    },
+    {
+      "epoch": 0.8514412416851441,
+      "grad_norm": 0.2497551292181015,
+      "learning_rate": 0.00014553571428571428,
+      "loss": 0.7007,
+      "step": 128
+    },
+    {
+      "epoch": 0.8580931263858093,
+      "grad_norm": 0.21985895931720734,
+      "learning_rate": 0.00014508928571428572,
+      "loss": 0.6605,
+      "step": 129
+    },
+    {
+      "epoch": 0.8647450110864745,
+      "grad_norm": 0.24338969588279724,
+      "learning_rate": 0.00014464285714285715,
+      "loss": 0.674,
+      "step": 130
+    },
+    {
+      "epoch": 0.8713968957871396,
+      "grad_norm": 0.2482798993587494,
+      "learning_rate": 0.0001441964285714286,
+      "loss": 0.6976,
+      "step": 131
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.24717016518115997,
+      "learning_rate": 0.00014375,
+      "loss": 0.732,
+      "step": 132
+    },
+    {
+      "epoch": 0.88470066518847,
+      "grad_norm": 0.23548655211925507,
+      "learning_rate": 0.00014330357142857143,
+      "loss": 0.7054,
+      "step": 133
+    },
+    {
+      "epoch": 0.8913525498891353,
+      "grad_norm": 0.2271115630865097,
+      "learning_rate": 0.00014285714285714287,
+      "loss": 0.7455,
+      "step": 134
+    },
+    {
+      "epoch": 0.8980044345898004,
+      "grad_norm": 0.221357524394989,
+      "learning_rate": 0.00014241071428571428,
+      "loss": 0.7087,
+      "step": 135
+    },
+    {
+      "epoch": 0.9046563192904656,
+      "grad_norm": 0.2530597746372223,
+      "learning_rate": 0.00014196428571428574,
+      "loss": 0.6911,
+      "step": 136
+    },
+    {
+      "epoch": 0.9113082039911308,
+      "grad_norm": 0.235321506857872,
+      "learning_rate": 0.00014151785714285715,
+      "loss": 0.6901,
+      "step": 137
+    },
+    {
+      "epoch": 0.917960088691796,
+      "grad_norm": 0.20477552711963654,
+      "learning_rate": 0.00014107142857142858,
+      "loss": 0.7139,
+      "step": 138
+    },
+    {
+      "epoch": 0.9246119733924612,
+      "grad_norm": 0.23540641367435455,
+      "learning_rate": 0.00014062500000000002,
+      "loss": 0.7213,
+      "step": 139
+    },
+    {
+      "epoch": 0.9312638580931264,
+      "grad_norm": 0.2498025745153427,
+      "learning_rate": 0.00014017857142857142,
+      "loss": 0.7575,
+      "step": 140
+    },
+    {
+      "epoch": 0.9379157427937915,
+      "grad_norm": 0.25040483474731445,
+      "learning_rate": 0.00013973214285714286,
+      "loss": 0.7099,
+      "step": 141
+    },
+    {
+      "epoch": 0.9445676274944568,
+      "grad_norm": 0.28463059663772583,
+      "learning_rate": 0.0001392857142857143,
+      "loss": 0.6667,
+      "step": 142
+    },
+    {
+      "epoch": 0.9512195121951219,
+      "grad_norm": 0.23660527169704437,
+      "learning_rate": 0.00013883928571428573,
+      "loss": 0.7037,
+      "step": 143
+    },
+    {
+      "epoch": 0.9578713968957872,
+      "grad_norm": 0.2693856954574585,
+      "learning_rate": 0.00013839285714285714,
+      "loss": 0.7346,
+      "step": 144
+    },
+    {
+      "epoch": 0.9645232815964523,
+      "grad_norm": 0.23629894852638245,
+      "learning_rate": 0.0001379464285714286,
+      "loss": 0.71,
+      "step": 145
+    },
+    {
+      "epoch": 0.9711751662971175,
+      "grad_norm": 0.2417481541633606,
+      "learning_rate": 0.0001375,
+      "loss": 0.6831,
+      "step": 146
+    },
+    {
+      "epoch": 0.9778270509977827,
+      "grad_norm": 0.2229100465774536,
+      "learning_rate": 0.00013705357142857142,
+      "loss": 0.6866,
+      "step": 147
+    },
+    {
+      "epoch": 0.9844789356984479,
+      "grad_norm": 0.25636398792266846,
+      "learning_rate": 0.00013660714285714288,
+      "loss": 0.6947,
+      "step": 148
+    },
+    {
+      "epoch": 0.991130820399113,
+      "grad_norm": 0.24808306992053986,
+      "learning_rate": 0.0001361607142857143,
+      "loss": 0.6989,
+      "step": 149
+    },
+    {
+      "epoch": 0.9977827050997783,
+      "grad_norm": 0.2657802700996399,
+      "learning_rate": 0.00013571428571428572,
+      "loss": 0.7776,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4232129454612732,
+      "learning_rate": 0.00013526785714285716,
+      "loss": 0.7157,
+      "step": 151
+    },
+    {
+      "epoch": 1.0066518847006651,
+      "grad_norm": 0.21353031694889069,
+      "learning_rate": 0.0001348214285714286,
+      "loss": 0.6564,
+      "step": 152
+    },
+    {
+      "epoch": 1.0133037694013303,
+      "grad_norm": 0.2523258328437805,
+      "learning_rate": 0.000134375,
+      "loss": 0.6655,
+      "step": 153
+    },
+    {
+      "epoch": 1.0199556541019956,
+      "grad_norm": 0.22559764981269836,
+      "learning_rate": 0.00013392857142857144,
+      "loss": 0.672,
+      "step": 154
+    },
+    {
+      "epoch": 1.0266075388026608,
+      "grad_norm": 0.2568952739238739,
+      "learning_rate": 0.00013348214285714287,
+      "loss": 0.6888,
+      "step": 155
+    },
+    {
+      "epoch": 1.033259423503326,
+      "grad_norm": 0.269492506980896,
+      "learning_rate": 0.00013303571428571428,
+      "loss": 0.6795,
+      "step": 156
+    },
+    {
+      "epoch": 1.039911308203991,
+      "grad_norm": 0.24207216501235962,
+      "learning_rate": 0.00013258928571428571,
+      "loss": 0.6068,
+      "step": 157
+    },
+    {
+      "epoch": 1.0465631929046564,
+      "grad_norm": 0.23466601967811584,
+      "learning_rate": 0.00013214285714285715,
+      "loss": 0.6375,
+      "step": 158
+    },
+    {
+      "epoch": 1.0532150776053215,
+      "grad_norm": 0.277636855840683,
+      "learning_rate": 0.00013169642857142858,
+      "loss": 0.6388,
+      "step": 159
+    },
+    {
+      "epoch": 1.0598669623059866,
+      "grad_norm": 0.2524043023586273,
+      "learning_rate": 0.00013125000000000002,
+      "loss": 0.6811,
+      "step": 160
+    },
+    {
+      "epoch": 1.0665188470066518,
+      "grad_norm": 0.26518797874450684,
+      "learning_rate": 0.00013080357142857143,
+      "loss": 0.6522,
+      "step": 161
+    },
+    {
+      "epoch": 1.0731707317073171,
+      "grad_norm": 0.2519301474094391,
+      "learning_rate": 0.00013035714285714286,
+      "loss": 0.6756,
+      "step": 162
+    },
+    {
+      "epoch": 1.0798226164079823,
+      "grad_norm": 0.2775301933288574,
+      "learning_rate": 0.0001299107142857143,
+      "loss": 0.6547,
+      "step": 163
+    },
+    {
+      "epoch": 1.0864745011086474,
+      "grad_norm": 0.26175275444984436,
+      "learning_rate": 0.00012946428571428573,
+      "loss": 0.643,
+      "step": 164
+    },
+    {
+      "epoch": 1.0931263858093125,
+      "grad_norm": 0.2586042881011963,
+      "learning_rate": 0.00012901785714285714,
+      "loss": 0.5884,
+      "step": 165
+    },
+    {
+      "epoch": 1.099778270509978,
+      "grad_norm": 0.26773908734321594,
+      "learning_rate": 0.00012857142857142858,
+      "loss": 0.6459,
+      "step": 166
+    },
+    {
+      "epoch": 1.106430155210643,
+      "grad_norm": 0.23962655663490295,
+      "learning_rate": 0.000128125,
+      "loss": 0.647,
+      "step": 167
+    },
+    {
+      "epoch": 1.1130820399113082,
+      "grad_norm": 0.25309571623802185,
+      "learning_rate": 0.00012767857142857142,
+      "loss": 0.6262,
+      "step": 168
+    },
+    {
+      "epoch": 1.1197339246119733,
+      "grad_norm": 0.25661855936050415,
+      "learning_rate": 0.00012723214285714285,
+      "loss": 0.6673,
+      "step": 169
+    },
+    {
+      "epoch": 1.1263858093126387,
+      "grad_norm": 0.24667981266975403,
+      "learning_rate": 0.0001267857142857143,
+      "loss": 0.7293,
+      "step": 170
+    },
+    {
+      "epoch": 1.1330376940133038,
+      "grad_norm": 0.2857082486152649,
+      "learning_rate": 0.00012633928571428572,
+      "loss": 0.6941,
+      "step": 171
+    },
+    {
+      "epoch": 1.139689578713969,
+      "grad_norm": 0.2508741617202759,
+      "learning_rate": 0.00012589285714285713,
+      "loss": 0.6958,
+      "step": 172
+    },
+    {
+      "epoch": 1.146341463414634,
+      "grad_norm": 0.2335047870874405,
+      "learning_rate": 0.0001254464285714286,
+      "loss": 0.6195,
+      "step": 173
+    },
+    {
+      "epoch": 1.1529933481152994,
+      "grad_norm": 0.25716137886047363,
+      "learning_rate": 0.000125,
+      "loss": 0.673,
+      "step": 174
+    },
+    {
+      "epoch": 1.1596452328159645,
+      "grad_norm": 0.2669331133365631,
+      "learning_rate": 0.00012455357142857144,
+      "loss": 0.7066,
+      "step": 175
+    },
+    {
+      "epoch": 1.1662971175166297,
+      "grad_norm": 0.2677348554134369,
+      "learning_rate": 0.00012410714285714287,
+      "loss": 0.6374,
+      "step": 176
+    },
+    {
+      "epoch": 1.1729490022172948,
+      "grad_norm": 0.3009944260120392,
+      "learning_rate": 0.00012366071428571428,
+      "loss": 0.6001,
+      "step": 177
+    },
+    {
+      "epoch": 1.1796008869179602,
+      "grad_norm": 0.28409549593925476,
+      "learning_rate": 0.00012321428571428572,
+      "loss": 0.6667,
+      "step": 178
+    },
+    {
+      "epoch": 1.1862527716186253,
+      "grad_norm": 0.3382788598537445,
+      "learning_rate": 0.00012276785714285715,
+      "loss": 0.7136,
+      "step": 179
+    },
+    {
+      "epoch": 1.1929046563192904,
+      "grad_norm": 0.2897425591945648,
+      "learning_rate": 0.00012232142857142859,
+      "loss": 0.6626,
+      "step": 180
+    },
+    {
+      "epoch": 1.1995565410199556,
+      "grad_norm": 0.27875712513923645,
+      "learning_rate": 0.00012187500000000001,
+      "loss": 0.6631,
+      "step": 181
+    },
+    {
+      "epoch": 1.206208425720621,
+      "grad_norm": 0.27191057801246643,
+      "learning_rate": 0.00012142857142857143,
+      "loss": 0.6815,
+      "step": 182
+    },
+    {
+      "epoch": 1.212860310421286,
+      "grad_norm": 0.26906609535217285,
+      "learning_rate": 0.00012098214285714286,
+      "loss": 0.6606,
+      "step": 183
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 0.25622498989105225,
+      "learning_rate": 0.00012053571428571429,
+      "loss": 0.6149,
+      "step": 184
+    },
+    {
+      "epoch": 1.2261640798226163,
+      "grad_norm": 0.2828701436519623,
+      "learning_rate": 0.00012008928571428572,
+      "loss": 0.7355,
+      "step": 185
+    },
+    {
+      "epoch": 1.2328159645232817,
+      "grad_norm": 0.2763717770576477,
+      "learning_rate": 0.00011964285714285714,
+      "loss": 0.696,
+      "step": 186
+    },
+    {
+      "epoch": 1.2394678492239468,
+      "grad_norm": 0.24653829634189606,
+      "learning_rate": 0.00011919642857142859,
+      "loss": 0.6117,
+      "step": 187
+    },
+    {
+      "epoch": 1.246119733924612,
+      "grad_norm": 0.2785421311855316,
+      "learning_rate": 0.00011875,
+      "loss": 0.6597,
+      "step": 188
+    },
+    {
+      "epoch": 1.252771618625277,
+      "grad_norm": 0.299787312746048,
+      "learning_rate": 0.00011830357142857142,
+      "loss": 0.7422,
+      "step": 189
+    },
+    {
+      "epoch": 1.2594235033259422,
+      "grad_norm": 0.26260530948638916,
+      "learning_rate": 0.00011785714285714287,
+      "loss": 0.7253,
+      "step": 190
+    },
+    {
+      "epoch": 1.2660753880266076,
+      "grad_norm": 0.2572118639945984,
+      "learning_rate": 0.00011741071428571429,
+      "loss": 0.6447,
+      "step": 191
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.28681686520576477,
+      "learning_rate": 0.00011696428571428573,
+      "loss": 0.635,
+      "step": 192
+    },
+    {
+      "epoch": 1.2793791574279378,
+      "grad_norm": 0.27183982729911804,
+      "learning_rate": 0.00011651785714285715,
+      "loss": 0.6755,
+      "step": 193
+    },
+    {
+      "epoch": 1.2860310421286032,
+      "grad_norm": 0.26490578055381775,
+      "learning_rate": 0.00011607142857142858,
+      "loss": 0.6361,
+      "step": 194
+    },
+    {
+      "epoch": 1.2926829268292683,
+      "grad_norm": 0.2605070173740387,
+      "learning_rate": 0.000115625,
+      "loss": 0.6692,
+      "step": 195
+    },
+    {
+      "epoch": 1.2993348115299335,
+      "grad_norm": 0.3332277536392212,
+      "learning_rate": 0.00011517857142857143,
+      "loss": 0.6896,
+      "step": 196
+    },
+    {
+      "epoch": 1.3059866962305986,
+      "grad_norm": 0.2624150216579437,
+      "learning_rate": 0.00011473214285714286,
+      "loss": 0.666,
+      "step": 197
+    },
+    {
+      "epoch": 1.3126385809312637,
+      "grad_norm": 0.2687854766845703,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 0.6584,
+      "step": 198
+    },
+    {
+      "epoch": 1.319290465631929,
+      "grad_norm": 0.27849000692367554,
+      "learning_rate": 0.00011383928571428573,
+      "loss": 0.6669,
+      "step": 199
+    },
+    {
+      "epoch": 1.3259423503325942,
+      "grad_norm": 0.2959786355495453,
+      "learning_rate": 0.00011339285714285714,
+      "loss": 0.715,
+      "step": 200
+    },
+    {
+      "epoch": 1.3325942350332594,
+      "grad_norm": 0.270611435174942,
+      "learning_rate": 0.00011294642857142859,
+      "loss": 0.6433,
+      "step": 201
+    },
+    {
+      "epoch": 1.3392461197339247,
+      "grad_norm": 0.30523768067359924,
+      "learning_rate": 0.00011250000000000001,
+      "loss": 0.6709,
+      "step": 202
+    },
+    {
+      "epoch": 1.3458980044345898,
+      "grad_norm": 0.2812907099723816,
+      "learning_rate": 0.00011205357142857142,
+      "loss": 0.693,
+      "step": 203
+    },
+    {
+      "epoch": 1.352549889135255,
+      "grad_norm": 0.26484444737434387,
+      "learning_rate": 0.00011160714285714287,
+      "loss": 0.6595,
+      "step": 204
+    },
+    {
+      "epoch": 1.3592017738359201,
+      "grad_norm": 0.2772507667541504,
+      "learning_rate": 0.00011116071428571429,
+      "loss": 0.6656,
+      "step": 205
+    },
+    {
+      "epoch": 1.3658536585365852,
+      "grad_norm": 0.3104967772960663,
+      "learning_rate": 0.00011071428571428572,
+      "loss": 0.6739,
+      "step": 206
+    },
+    {
+      "epoch": 1.3725055432372506,
+      "grad_norm": 0.27060478925704956,
+      "learning_rate": 0.00011026785714285715,
+      "loss": 0.6904,
+      "step": 207
+    },
+    {
+      "epoch": 1.3791574279379157,
+      "grad_norm": 0.2941751182079315,
+      "learning_rate": 0.00010982142857142858,
+      "loss": 0.6616,
+      "step": 208
+    },
+    {
+      "epoch": 1.3858093126385809,
+      "grad_norm": 0.24937930703163147,
+      "learning_rate": 0.000109375,
+      "loss": 0.6828,
+      "step": 209
+    },
+    {
+      "epoch": 1.3924611973392462,
+      "grad_norm": 0.27118411660194397,
+      "learning_rate": 0.00010892857142857142,
+      "loss": 0.6597,
+      "step": 210
+    },
+    {
+      "epoch": 1.3991130820399114,
+      "grad_norm": 0.2885172963142395,
+      "learning_rate": 0.00010848214285714286,
+      "loss": 0.7168,
+      "step": 211
+    },
+    {
+      "epoch": 1.4057649667405765,
+      "grad_norm": 0.29566511511802673,
+      "learning_rate": 0.00010803571428571428,
+      "loss": 0.7525,
+      "step": 212
+    },
+    {
+      "epoch": 1.4124168514412416,
+      "grad_norm": 0.2805855870246887,
+      "learning_rate": 0.00010758928571428573,
+      "loss": 0.6166,
+      "step": 213
+    },
+    {
+      "epoch": 1.4190687361419068,
+      "grad_norm": 0.29762670397758484,
+      "learning_rate": 0.00010714285714285715,
+      "loss": 0.6515,
+      "step": 214
+    },
+    {
+      "epoch": 1.4257206208425721,
+      "grad_norm": 0.30412253737449646,
+      "learning_rate": 0.00010669642857142859,
+      "loss": 0.663,
+      "step": 215
+    },
+    {
+      "epoch": 1.4323725055432373,
+      "grad_norm": 0.2980710566043854,
+      "learning_rate": 0.00010625000000000001,
+      "loss": 0.7356,
+      "step": 216
+    },
+    {
+      "epoch": 1.4390243902439024,
+      "grad_norm": 0.2928237318992615,
+      "learning_rate": 0.00010580357142857143,
+      "loss": 0.6687,
+      "step": 217
+    },
+    {
+      "epoch": 1.4456762749445677,
+      "grad_norm": 0.29801151156425476,
+      "learning_rate": 0.00010535714285714286,
+      "loss": 0.6436,
+      "step": 218
+    },
+    {
+      "epoch": 1.4523281596452329,
+      "grad_norm": 0.30041205883026123,
+      "learning_rate": 0.00010491071428571429,
+      "loss": 0.5948,
+      "step": 219
+    },
+    {
+      "epoch": 1.458980044345898,
+      "grad_norm": 0.29268884658813477,
+      "learning_rate": 0.00010446428571428572,
+      "loss": 0.7081,
+      "step": 220
+    },
+    {
+      "epoch": 1.4656319290465631,
+      "grad_norm": 0.2952764928340912,
+      "learning_rate": 0.00010401785714285714,
+      "loss": 0.7167,
+      "step": 221
+    },
+    {
+      "epoch": 1.4722838137472283,
+      "grad_norm": 0.3013139069080353,
+      "learning_rate": 0.00010357142857142859,
+      "loss": 0.5986,
+      "step": 222
+    },
+    {
+      "epoch": 1.4789356984478936,
+      "grad_norm": 0.2932202219963074,
+      "learning_rate": 0.000103125,
+      "loss": 0.6724,
+      "step": 223
+    },
+    {
+      "epoch": 1.4855875831485588,
+      "grad_norm": 0.2913295030593872,
+      "learning_rate": 0.00010267857142857142,
+      "loss": 0.6968,
+      "step": 224
+    },
+    {
+      "epoch": 1.492239467849224,
+      "grad_norm": 0.2942708134651184,
+      "learning_rate": 0.00010223214285714287,
+      "loss": 0.6506,
+      "step": 225
+    },
+    {
+      "epoch": 1.4988913525498893,
+      "grad_norm": 0.3095633387565613,
+      "learning_rate": 0.00010178571428571428,
+      "loss": 0.6919,
+      "step": 226
+    },
+    {
+      "epoch": 1.5055432372505542,
+      "grad_norm": 0.2938249707221985,
+      "learning_rate": 0.00010133928571428573,
+      "loss": 0.6567,
+      "step": 227
+    },
+    {
+      "epoch": 1.5121951219512195,
+      "grad_norm": 0.2744443714618683,
+      "learning_rate": 0.00010089285714285715,
+      "loss": 0.6623,
+      "step": 228
+    },
+    {
+      "epoch": 1.5188470066518847,
+      "grad_norm": 0.3065742552280426,
+      "learning_rate": 0.00010044642857142858,
+      "loss": 0.6909,
+      "step": 229
+    },
+    {
+      "epoch": 1.5254988913525498,
+      "grad_norm": 0.29452386498451233,
+      "learning_rate": 0.0001,
+      "loss": 0.689,
+      "step": 230
+    },
+    {
+      "epoch": 1.5321507760532151,
+      "grad_norm": 0.2925872206687927,
+      "learning_rate": 9.955357142857144e-05,
+      "loss": 0.6362,
+      "step": 231
+    },
+    {
+      "epoch": 1.5388026607538803,
+      "grad_norm": 0.25674131512641907,
+      "learning_rate": 9.910714285714286e-05,
+      "loss": 0.6743,
+      "step": 232
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.2697190046310425,
+      "learning_rate": 9.86607142857143e-05,
+      "loss": 0.6445,
+      "step": 233
+    },
+    {
+      "epoch": 1.5521064301552108,
+      "grad_norm": 0.3426855504512787,
+      "learning_rate": 9.821428571428572e-05,
+      "loss": 0.6364,
+      "step": 234
+    },
+    {
+      "epoch": 1.5587583148558757,
+      "grad_norm": 0.2987474203109741,
+      "learning_rate": 9.776785714285714e-05,
+      "loss": 0.7016,
+      "step": 235
+    },
+    {
+      "epoch": 1.565410199556541,
+      "grad_norm": 0.2825179994106293,
+      "learning_rate": 9.732142857142858e-05,
+      "loss": 0.678,
+      "step": 236
+    },
+    {
+      "epoch": 1.5720620842572062,
+      "grad_norm": 0.2907421588897705,
+      "learning_rate": 9.687500000000001e-05,
+      "loss": 0.6874,
+      "step": 237
+    },
+    {
+      "epoch": 1.5787139689578713,
+      "grad_norm": 0.30288076400756836,
+      "learning_rate": 9.642857142857143e-05,
+      "loss": 0.75,
+      "step": 238
+    },
+    {
+      "epoch": 1.5853658536585367,
+      "grad_norm": 0.35595637559890747,
+      "learning_rate": 9.598214285714287e-05,
+      "loss": 0.7508,
+      "step": 239
+    },
+    {
+      "epoch": 1.5920177383592018,
+      "grad_norm": 0.3115308880805969,
+      "learning_rate": 9.553571428571429e-05,
+      "loss": 0.5835,
+      "step": 240
+    },
+    {
+      "epoch": 1.598669623059867,
+      "grad_norm": 0.29829543828964233,
+      "learning_rate": 9.508928571428571e-05,
+      "loss": 0.6948,
+      "step": 241
+    },
+    {
+      "epoch": 1.6053215077605323,
+      "grad_norm": 0.302970290184021,
+      "learning_rate": 9.464285714285715e-05,
+      "loss": 0.7369,
+      "step": 242
+    },
+    {
+      "epoch": 1.6119733924611972,
+      "grad_norm": 0.2732544243335724,
+      "learning_rate": 9.419642857142858e-05,
+      "loss": 0.7067,
+      "step": 243
+    },
+    {
+      "epoch": 1.6186252771618626,
+      "grad_norm": 0.27571314573287964,
+      "learning_rate": 9.375e-05,
+      "loss": 0.6761,
+      "step": 244
+    },
+    {
+      "epoch": 1.6252771618625277,
+      "grad_norm": 0.3008634150028229,
+      "learning_rate": 9.330357142857144e-05,
+      "loss": 0.5971,
+      "step": 245
+    },
+    {
+      "epoch": 1.6319290465631928,
+      "grad_norm": 0.3190212845802307,
+      "learning_rate": 9.285714285714286e-05,
+      "loss": 0.7796,
+      "step": 246
+    },
+    {
+      "epoch": 1.6385809312638582,
+      "grad_norm": 0.2897483706474304,
+      "learning_rate": 9.24107142857143e-05,
+      "loss": 0.6576,
+      "step": 247
+    },
+    {
+      "epoch": 1.6452328159645233,
+      "grad_norm": 0.30384308099746704,
+      "learning_rate": 9.196428571428572e-05,
+      "loss": 0.642,
+      "step": 248
+    },
+    {
+      "epoch": 1.6518847006651884,
+      "grad_norm": 0.2879965007305145,
+      "learning_rate": 9.151785714285715e-05,
+      "loss": 0.5834,
+      "step": 249
+    },
+    {
+      "epoch": 1.6585365853658538,
+      "grad_norm": 0.2864130735397339,
+      "learning_rate": 9.107142857142857e-05,
+      "loss": 0.6379,
+      "step": 250
+    },
+    {
+      "epoch": 1.6651884700665187,
+      "grad_norm": 0.3132689893245697,
+      "learning_rate": 9.062500000000001e-05,
+      "loss": 0.7008,
+      "step": 251
+    },
+    {
+      "epoch": 1.671840354767184,
+      "grad_norm": 0.2902945280075073,
+      "learning_rate": 9.017857142857143e-05,
+      "loss": 0.638,
+      "step": 252
+    },
+    {
+      "epoch": 1.6784922394678492,
+      "grad_norm": 0.2899770736694336,
+      "learning_rate": 8.973214285714286e-05,
+      "loss": 0.6787,
+      "step": 253
+    },
+    {
+      "epoch": 1.6851441241685143,
+      "grad_norm": 0.33625850081443787,
+      "learning_rate": 8.92857142857143e-05,
+      "loss": 0.6537,
+      "step": 254
+    },
+    {
+      "epoch": 1.6917960088691797,
+      "grad_norm": 0.3040412366390228,
+      "learning_rate": 8.883928571428571e-05,
+      "loss": 0.6393,
+      "step": 255
+    },
+    {
+      "epoch": 1.6984478935698448,
+      "grad_norm": 0.2943258583545685,
+      "learning_rate": 8.839285714285714e-05,
+      "loss": 0.6991,
+      "step": 256
+    },
+    {
+      "epoch": 1.70509977827051,
+      "grad_norm": 0.2967449724674225,
+      "learning_rate": 8.794642857142858e-05,
+      "loss": 0.6416,
+      "step": 257
+    },
+    {
+      "epoch": 1.7117516629711753,
+      "grad_norm": 0.30491599440574646,
+      "learning_rate": 8.75e-05,
+      "loss": 0.6377,
+      "step": 258
+    },
+    {
+      "epoch": 1.7184035476718402,
+      "grad_norm": 0.29514333605766296,
+      "learning_rate": 8.705357142857143e-05,
+      "loss": 0.6482,
+      "step": 259
+    },
+    {
+      "epoch": 1.7250554323725056,
+      "grad_norm": 0.29838770627975464,
+      "learning_rate": 8.660714285714287e-05,
+      "loss": 0.6442,
+      "step": 260
+    },
+    {
+      "epoch": 1.7317073170731707,
+      "grad_norm": 0.30713504552841187,
+      "learning_rate": 8.616071428571429e-05,
+      "loss": 0.7324,
+      "step": 261
+    },
+    {
+      "epoch": 1.7383592017738358,
+      "grad_norm": 0.28630495071411133,
+      "learning_rate": 8.571428571428571e-05,
+      "loss": 0.6923,
+      "step": 262
+    },
+    {
+      "epoch": 1.7450110864745012,
+      "grad_norm": 0.2708995044231415,
+      "learning_rate": 8.526785714285715e-05,
+      "loss": 0.6973,
+      "step": 263
+    },
+    {
+      "epoch": 1.7516629711751663,
+      "grad_norm": 0.2751605808734894,
+      "learning_rate": 8.482142857142857e-05,
+      "loss": 0.6947,
+      "step": 264
+    },
+    {
+      "epoch": 1.7583148558758315,
+      "grad_norm": 0.27955448627471924,
+      "learning_rate": 8.4375e-05,
+      "loss": 0.6782,
+      "step": 265
+    },
+    {
+      "epoch": 1.7649667405764968,
+      "grad_norm": 0.28193265199661255,
+      "learning_rate": 8.392857142857144e-05,
+      "loss": 0.6821,
+      "step": 266
+    },
+    {
+      "epoch": 1.7716186252771617,
+      "grad_norm": 0.2943415343761444,
+      "learning_rate": 8.348214285714286e-05,
+      "loss": 0.6746,
+      "step": 267
+    },
+    {
+      "epoch": 1.778270509977827,
+      "grad_norm": 0.270734965801239,
+      "learning_rate": 8.30357142857143e-05,
+      "loss": 0.6604,
+      "step": 268
+    },
+    {
+      "epoch": 1.7849223946784922,
+      "grad_norm": 0.30203959345817566,
+      "learning_rate": 8.258928571428572e-05,
+      "loss": 0.6011,
+      "step": 269
+    },
+    {
+      "epoch": 1.7915742793791574,
+      "grad_norm": 0.2829052805900574,
+      "learning_rate": 8.214285714285714e-05,
+      "loss": 0.6929,
+      "step": 270
+    },
+    {
+      "epoch": 1.7982261640798227,
+      "grad_norm": 0.29843759536743164,
+      "learning_rate": 8.169642857142857e-05,
+      "loss": 0.7022,
+      "step": 271
+    },
+    {
+      "epoch": 1.8048780487804879,
+      "grad_norm": 0.3182222247123718,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 0.7382,
+      "step": 272
+    },
+    {
+      "epoch": 1.811529933481153,
+      "grad_norm": 0.34339556097984314,
+      "learning_rate": 8.080357142857143e-05,
+      "loss": 0.66,
+      "step": 273
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.2827399671077728,
+      "learning_rate": 8.035714285714287e-05,
+      "loss": 0.649,
+      "step": 274
+    },
+    {
+      "epoch": 1.8248337028824833,
+      "grad_norm": 0.3233022391796112,
+      "learning_rate": 7.991071428571429e-05,
+      "loss": 0.7234,
+      "step": 275
+    },
+    {
+      "epoch": 1.8314855875831486,
+      "grad_norm": 0.2928791046142578,
+      "learning_rate": 7.946428571428571e-05,
+      "loss": 0.6629,
+      "step": 276
+    },
+    {
+      "epoch": 1.8381374722838137,
+      "grad_norm": 0.2922433912754059,
+      "learning_rate": 7.901785714285714e-05,
+      "loss": 0.686,
+      "step": 277
+    },
+    {
+      "epoch": 1.8447893569844789,
+      "grad_norm": 0.30393847823143005,
+      "learning_rate": 7.857142857142858e-05,
+      "loss": 0.6172,
+      "step": 278
+    },
+    {
+      "epoch": 1.8514412416851442,
+      "grad_norm": 0.27950766682624817,
+      "learning_rate": 7.8125e-05,
+      "loss": 0.5613,
+      "step": 279
+    },
+    {
+      "epoch": 1.8580931263858091,
+      "grad_norm": 0.3037584722042084,
+      "learning_rate": 7.767857142857144e-05,
+      "loss": 0.6784,
+      "step": 280
+    },
+    {
+      "epoch": 1.8647450110864745,
+      "grad_norm": 0.3072577118873596,
+      "learning_rate": 7.723214285714286e-05,
+      "loss": 0.7064,
+      "step": 281
+    },
+    {
+      "epoch": 1.8713968957871396,
+      "grad_norm": 0.29332172870635986,
+      "learning_rate": 7.67857142857143e-05,
+      "loss": 0.6277,
+      "step": 282
+    },
+    {
+      "epoch": 1.8780487804878048,
+      "grad_norm": 0.31345027685165405,
+      "learning_rate": 7.633928571428572e-05,
+      "loss": 0.7052,
+      "step": 283
+    },
+    {
+      "epoch": 1.8847006651884701,
+      "grad_norm": 0.3036707043647766,
+      "learning_rate": 7.589285714285714e-05,
+      "loss": 0.6719,
+      "step": 284
+    },
+    {
+      "epoch": 1.8913525498891353,
+      "grad_norm": 0.2989391088485718,
+      "learning_rate": 7.544642857142857e-05,
+      "loss": 0.6736,
+      "step": 285
+    },
+    {
+      "epoch": 1.8980044345898004,
+      "grad_norm": 0.2907038927078247,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.6414,
+      "step": 286
+    },
+    {
+      "epoch": 1.9046563192904657,
+      "grad_norm": 0.3108704090118408,
+      "learning_rate": 7.455357142857143e-05,
+      "loss": 0.6123,
+      "step": 287
+    },
+    {
+      "epoch": 1.9113082039911307,
+      "grad_norm": 0.31437984108924866,
+      "learning_rate": 7.410714285714286e-05,
+      "loss": 0.6804,
+      "step": 288
+    },
+    {
+      "epoch": 1.917960088691796,
+      "grad_norm": 0.30342158675193787,
+      "learning_rate": 7.36607142857143e-05,
+      "loss": 0.6955,
+      "step": 289
+    },
+    {
+      "epoch": 1.9246119733924612,
+      "grad_norm": 0.281202495098114,
+      "learning_rate": 7.321428571428571e-05,
+      "loss": 0.6148,
+      "step": 290
+    },
+    {
+      "epoch": 1.9312638580931263,
+      "grad_norm": 0.2889295816421509,
+      "learning_rate": 7.276785714285714e-05,
+      "loss": 0.6684,
+      "step": 291
+    },
+    {
+      "epoch": 1.9379157427937916,
+      "grad_norm": 0.2937774360179901,
+      "learning_rate": 7.232142857142858e-05,
+      "loss": 0.6353,
+      "step": 292
+    },
+    {
+      "epoch": 1.9445676274944568,
+      "grad_norm": 0.2863958179950714,
+      "learning_rate": 7.1875e-05,
+      "loss": 0.6599,
+      "step": 293
+    },
+    {
+      "epoch": 1.951219512195122,
+      "grad_norm": 0.3254477083683014,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 0.7482,
+      "step": 294
+    },
+    {
+      "epoch": 1.9578713968957873,
+      "grad_norm": 0.2770182192325592,
+      "learning_rate": 7.098214285714287e-05,
+      "loss": 0.6955,
+      "step": 295
+    },
+    {
+      "epoch": 1.9645232815964522,
+      "grad_norm": 0.2831432819366455,
+      "learning_rate": 7.053571428571429e-05,
+      "loss": 0.6485,
+      "step": 296
+    },
+    {
+      "epoch": 1.9711751662971175,
+      "grad_norm": 0.2820065915584564,
+      "learning_rate": 7.008928571428571e-05,
+      "loss": 0.6876,
+      "step": 297
+    },
+    {
+      "epoch": 1.9778270509977827,
+      "grad_norm": 0.31168416142463684,
+      "learning_rate": 6.964285714285715e-05,
+      "loss": 0.613,
+      "step": 298
+    },
+    {
+      "epoch": 1.9844789356984478,
+      "grad_norm": 0.3082287311553955,
+      "learning_rate": 6.919642857142857e-05,
+      "loss": 0.65,
+      "step": 299
+    },
+    {
+      "epoch": 1.9911308203991132,
+      "grad_norm": 0.26807934045791626,
+      "learning_rate": 6.875e-05,
+      "loss": 0.6316,
+      "step": 300
+    },
+    {
+      "epoch": 1.9977827050997783,
+      "grad_norm": 0.3018947243690491,
+      "learning_rate": 6.830357142857144e-05,
+      "loss": 0.6547,
+      "step": 301
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5487756729125977,
+      "learning_rate": 6.785714285714286e-05,
+      "loss": 0.8145,
+      "step": 302
+    },
+    {
+      "epoch": 2.0066518847006654,
+      "grad_norm": 0.308287650346756,
+      "learning_rate": 6.74107142857143e-05,
+      "loss": 0.6264,
+      "step": 303
+    },
+    {
+      "epoch": 2.0133037694013303,
+      "grad_norm": 0.31158947944641113,
+      "learning_rate": 6.696428571428572e-05,
+      "loss": 0.6506,
+      "step": 304
+    },
+    {
+      "epoch": 2.0199556541019956,
+      "grad_norm": 0.28500011563301086,
+      "learning_rate": 6.651785714285714e-05,
+      "loss": 0.7174,
+      "step": 305
+    },
+    {
+      "epoch": 2.0266075388026605,
+      "grad_norm": 0.29018962383270264,
+      "learning_rate": 6.607142857142857e-05,
+      "loss": 0.6201,
+      "step": 306
+    },
+    {
+      "epoch": 2.033259423503326,
+      "grad_norm": 0.28562304377555847,
+      "learning_rate": 6.562500000000001e-05,
+      "loss": 0.5918,
+      "step": 307
+    },
+    {
+      "epoch": 2.0399113082039912,
+      "grad_norm": 0.31676334142684937,
+      "learning_rate": 6.517857142857143e-05,
+      "loss": 0.5949,
+      "step": 308
+    },
+    {
+      "epoch": 2.046563192904656,
+      "grad_norm": 0.3222840130329132,
+      "learning_rate": 6.473214285714287e-05,
+      "loss": 0.7027,
+      "step": 309
+    },
+    {
+      "epoch": 2.0532150776053215,
+      "grad_norm": 0.3101438879966736,
+      "learning_rate": 6.428571428571429e-05,
+      "loss": 0.675,
+      "step": 310
+    },
+    {
+      "epoch": 2.059866962305987,
+      "grad_norm": 0.3392826020717621,
+      "learning_rate": 6.383928571428571e-05,
+      "loss": 0.623,
+      "step": 311
+    },
+    {
+      "epoch": 2.066518847006652,
+      "grad_norm": 0.3528847396373749,
+      "learning_rate": 6.339285714285714e-05,
+      "loss": 0.6446,
+      "step": 312
+    },
+    {
+      "epoch": 2.073170731707317,
+      "grad_norm": 0.34839993715286255,
+      "learning_rate": 6.294642857142857e-05,
+      "loss": 0.5389,
+      "step": 313
+    },
+    {
+      "epoch": 2.079822616407982,
+      "grad_norm": 0.3775246739387512,
+      "learning_rate": 6.25e-05,
+      "loss": 0.6674,
+      "step": 314
+    },
+    {
+      "epoch": 2.0864745011086474,
+      "grad_norm": 0.3442479372024536,
+      "learning_rate": 6.205357142857144e-05,
+      "loss": 0.6248,
+      "step": 315
+    },
+    {
+      "epoch": 2.0931263858093128,
+      "grad_norm": 0.3442973494529724,
+      "learning_rate": 6.160714285714286e-05,
+      "loss": 0.6291,
+      "step": 316
+    },
+    {
+      "epoch": 2.0997782705099777,
+      "grad_norm": 0.31466370820999146,
+      "learning_rate": 6.116071428571429e-05,
+      "loss": 0.7098,
+      "step": 317
+    },
+    {
+      "epoch": 2.106430155210643,
+      "grad_norm": 0.33682629466056824,
+      "learning_rate": 6.0714285714285715e-05,
+      "loss": 0.6494,
+      "step": 318
+    },
+    {
+      "epoch": 2.1130820399113084,
+      "grad_norm": 0.33227798342704773,
+      "learning_rate": 6.026785714285714e-05,
+      "loss": 0.6551,
+      "step": 319
+    },
+    {
+      "epoch": 2.1197339246119733,
+      "grad_norm": 0.33480921387672424,
+      "learning_rate": 5.982142857142857e-05,
+      "loss": 0.6337,
+      "step": 320
+    },
+    {
+      "epoch": 2.1263858093126387,
+      "grad_norm": 0.3307223320007324,
+      "learning_rate": 5.9375e-05,
+      "loss": 0.6127,
+      "step": 321
+    },
+    {
+      "epoch": 2.1330376940133036,
+      "grad_norm": 0.3276672065258026,
+      "learning_rate": 5.8928571428571435e-05,
+      "loss": 0.6283,
+      "step": 322
+    },
+    {
+      "epoch": 2.139689578713969,
+      "grad_norm": 0.3314298093318939,
+      "learning_rate": 5.8482142857142863e-05,
+      "loss": 0.6287,
+      "step": 323
+    },
+    {
+      "epoch": 2.1463414634146343,
+      "grad_norm": 0.34654736518859863,
+      "learning_rate": 5.803571428571429e-05,
+      "loss": 0.663,
+      "step": 324
+    },
+    {
+      "epoch": 2.152993348115299,
+      "grad_norm": 0.3725448250770569,
+      "learning_rate": 5.758928571428571e-05,
+      "loss": 0.5967,
+      "step": 325
+    },
+    {
+      "epoch": 2.1596452328159645,
+      "grad_norm": 0.3618411719799042,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 0.6251,
+      "step": 326
+    },
+    {
+      "epoch": 2.16629711751663,
+      "grad_norm": 0.36651697754859924,
+      "learning_rate": 5.669642857142857e-05,
+      "loss": 0.5577,
+      "step": 327
+    },
+    {
+      "epoch": 2.172949002217295,
+      "grad_norm": 0.3677833378314972,
+      "learning_rate": 5.6250000000000005e-05,
+      "loss": 0.5721,
+      "step": 328
+    },
+    {
+      "epoch": 2.17960088691796,
+      "grad_norm": 0.3813767731189728,
+      "learning_rate": 5.5803571428571434e-05,
+      "loss": 0.5808,
+      "step": 329
+    },
+    {
+      "epoch": 2.186252771618625,
+      "grad_norm": 0.33853745460510254,
+      "learning_rate": 5.535714285714286e-05,
+      "loss": 0.6444,
+      "step": 330
+    },
+    {
+      "epoch": 2.1929046563192904,
+      "grad_norm": 0.4041629433631897,
+      "learning_rate": 5.491071428571429e-05,
+      "loss": 0.5946,
+      "step": 331
+    },
+    {
+      "epoch": 2.199556541019956,
+      "grad_norm": 0.34588849544525146,
+      "learning_rate": 5.446428571428571e-05,
+      "loss": 0.5796,
+      "step": 332
+    },
+    {
+      "epoch": 2.2062084257206207,
+      "grad_norm": 0.3851901590824127,
+      "learning_rate": 5.401785714285714e-05,
+      "loss": 0.7003,
+      "step": 333
+    },
+    {
+      "epoch": 2.212860310421286,
+      "grad_norm": 0.34573057293891907,
+      "learning_rate": 5.3571428571428575e-05,
+      "loss": 0.6334,
+      "step": 334
+    },
+    {
+      "epoch": 2.2195121951219514,
+      "grad_norm": 0.3602820336818695,
+      "learning_rate": 5.3125000000000004e-05,
+      "loss": 0.6193,
+      "step": 335
+    },
+    {
+      "epoch": 2.2261640798226163,
+      "grad_norm": 0.37075817584991455,
+      "learning_rate": 5.267857142857143e-05,
+      "loss": 0.5975,
+      "step": 336
+    },
+    {
+      "epoch": 2.2328159645232817,
+      "grad_norm": 0.36711254715919495,
+      "learning_rate": 5.223214285714286e-05,
+      "loss": 0.6191,
+      "step": 337
+    },
+    {
+      "epoch": 2.2394678492239466,
+      "grad_norm": 0.3793788254261017,
+      "learning_rate": 5.1785714285714296e-05,
+      "loss": 0.6588,
+      "step": 338
+    },
+    {
+      "epoch": 2.246119733924612,
+      "grad_norm": 0.396540105342865,
+      "learning_rate": 5.133928571428571e-05,
+      "loss": 0.6517,
+      "step": 339
+    },
+    {
+      "epoch": 2.2527716186252773,
+      "grad_norm": 0.3680330812931061,
+      "learning_rate": 5.089285714285714e-05,
+      "loss": 0.6392,
+      "step": 340
+    },
+    {
+      "epoch": 2.259423503325942,
+      "grad_norm": 0.38850072026252747,
+      "learning_rate": 5.0446428571428574e-05,
+      "loss": 0.5704,
+      "step": 341
+    },
+    {
+      "epoch": 2.2660753880266076,
+      "grad_norm": 0.38575878739356995,
+      "learning_rate": 5e-05,
+      "loss": 0.5751,
+      "step": 342
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.38471731543540955,
+      "learning_rate": 4.955357142857143e-05,
+      "loss": 0.5833,
+      "step": 343
+    },
+    {
+      "epoch": 2.279379157427938,
+      "grad_norm": 0.37552642822265625,
+      "learning_rate": 4.910714285714286e-05,
+      "loss": 0.5948,
+      "step": 344
+    },
+    {
+      "epoch": 2.286031042128603,
+      "grad_norm": 0.3940044045448303,
+      "learning_rate": 4.866071428571429e-05,
+      "loss": 0.6014,
+      "step": 345
+    },
+    {
+      "epoch": 2.292682926829268,
+      "grad_norm": 0.3945384621620178,
+      "learning_rate": 4.8214285714285716e-05,
+      "loss": 0.5628,
+      "step": 346
+    },
+    {
+      "epoch": 2.2993348115299335,
+      "grad_norm": 0.40789172053337097,
+      "learning_rate": 4.7767857142857144e-05,
+      "loss": 0.6185,
+      "step": 347
+    },
+    {
+      "epoch": 2.305986696230599,
+      "grad_norm": 0.4115988314151764,
+      "learning_rate": 4.732142857142857e-05,
+      "loss": 0.5893,
+      "step": 348
+    },
+    {
+      "epoch": 2.3126385809312637,
+      "grad_norm": 0.39673107862472534,
+      "learning_rate": 4.6875e-05,
+      "loss": 0.6507,
+      "step": 349
+    },
+    {
+      "epoch": 2.319290465631929,
+      "grad_norm": 0.37107840180397034,
+      "learning_rate": 4.642857142857143e-05,
+      "loss": 0.6101,
+      "step": 350
+    },
+    {
+      "epoch": 2.3259423503325944,
+      "grad_norm": 0.40348756313323975,
+      "learning_rate": 4.598214285714286e-05,
+      "loss": 0.5849,
+      "step": 351
+    },
+    {
+      "epoch": 2.3325942350332594,
+      "grad_norm": 0.4037018418312073,
+      "learning_rate": 4.5535714285714286e-05,
+      "loss": 0.7019,
+      "step": 352
+    },
+    {
+      "epoch": 2.3392461197339247,
+      "grad_norm": 0.4175129532814026,
+      "learning_rate": 4.5089285714285714e-05,
+      "loss": 0.6221,
+      "step": 353
+    },
+    {
+      "epoch": 2.3458980044345896,
+      "grad_norm": 0.3899692893028259,
+      "learning_rate": 4.464285714285715e-05,
+      "loss": 0.6076,
+      "step": 354
+    },
+    {
+      "epoch": 2.352549889135255,
+      "grad_norm": 0.4122084081172943,
+      "learning_rate": 4.419642857142857e-05,
+      "loss": 0.657,
+      "step": 355
+    },
+    {
+      "epoch": 2.3592017738359203,
+      "grad_norm": 0.4386710524559021,
+      "learning_rate": 4.375e-05,
+      "loss": 0.6295,
+      "step": 356
+    },
+    {
+      "epoch": 2.3658536585365852,
+      "grad_norm": 0.41807928681373596,
+      "learning_rate": 4.3303571428571435e-05,
+      "loss": 0.5973,
+      "step": 357
+    },
+    {
+      "epoch": 2.3725055432372506,
+      "grad_norm": 0.4542185068130493,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.6076,
+      "step": 358
+    },
+    {
+      "epoch": 2.3791574279379155,
+      "grad_norm": 0.41947460174560547,
+      "learning_rate": 4.2410714285714285e-05,
+      "loss": 0.6455,
+      "step": 359
+    },
+    {
+      "epoch": 2.385809312638581,
+      "grad_norm": 0.4425618350505829,
+      "learning_rate": 4.196428571428572e-05,
+      "loss": 0.6214,
+      "step": 360
+    },
+    {
+      "epoch": 2.3924611973392462,
+      "grad_norm": 0.39528754353523254,
+      "learning_rate": 4.151785714285715e-05,
+      "loss": 0.6205,
+      "step": 361
+    },
+    {
+      "epoch": 2.399113082039911,
+      "grad_norm": 0.4570913314819336,
+      "learning_rate": 4.107142857142857e-05,
+      "loss": 0.6107,
+      "step": 362
+    },
+    {
+      "epoch": 2.4057649667405765,
+      "grad_norm": 0.43899545073509216,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.6837,
+      "step": 363
+    },
+    {
+      "epoch": 2.412416851441242,
+      "grad_norm": 0.44106388092041016,
+      "learning_rate": 4.017857142857143e-05,
+      "loss": 0.6187,
+      "step": 364
+    },
+    {
+      "epoch": 2.4190687361419068,
+      "grad_norm": 0.43455469608306885,
+      "learning_rate": 3.9732142857142855e-05,
+      "loss": 0.6618,
+      "step": 365
+    },
+    {
+      "epoch": 2.425720620842572,
+      "grad_norm": 0.4708061218261719,
+      "learning_rate": 3.928571428571429e-05,
+      "loss": 0.6801,
+      "step": 366
+    },
+    {
+      "epoch": 2.4323725055432375,
+      "grad_norm": 0.4523415267467499,
+      "learning_rate": 3.883928571428572e-05,
+      "loss": 0.5872,
+      "step": 367
+    },
+    {
+      "epoch": 2.4390243902439024,
+      "grad_norm": 0.47292423248291016,
+      "learning_rate": 3.839285714285715e-05,
+      "loss": 0.5787,
+      "step": 368
+    },
+    {
+      "epoch": 2.4456762749445677,
+      "grad_norm": 0.4636482894420624,
+      "learning_rate": 3.794642857142857e-05,
+      "loss": 0.6372,
+      "step": 369
+    },
+    {
+      "epoch": 2.4523281596452327,
+      "grad_norm": 0.45604145526885986,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.56,
+      "step": 370
+    },
+    {
+      "epoch": 2.458980044345898,
+      "grad_norm": 0.45063337683677673,
+      "learning_rate": 3.705357142857143e-05,
+      "loss": 0.5386,
+      "step": 371
+    },
+    {
+      "epoch": 2.4656319290465634,
+      "grad_norm": 0.44801199436187744,
+      "learning_rate": 3.6607142857142853e-05,
+      "loss": 0.5888,
+      "step": 372
+    },
+    {
+      "epoch": 2.4722838137472283,
+      "grad_norm": 0.47819772362709045,
+      "learning_rate": 3.616071428571429e-05,
+      "loss": 0.599,
+      "step": 373
+    },
+    {
+      "epoch": 2.4789356984478936,
+      "grad_norm": 0.46308666467666626,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.5773,
+      "step": 374
+    },
+    {
+      "epoch": 2.4855875831485585,
+      "grad_norm": 0.4224989712238312,
+      "learning_rate": 3.5267857142857145e-05,
+      "loss": 0.6201,
+      "step": 375
+    },
+    {
+      "epoch": 2.492239467849224,
+      "grad_norm": 0.46462488174438477,
+      "learning_rate": 3.4821428571428574e-05,
+      "loss": 0.5943,
+      "step": 376
+    },
+    {
+      "epoch": 2.4988913525498893,
+      "grad_norm": 0.43969860672950745,
+      "learning_rate": 3.4375e-05,
+      "loss": 0.6452,
+      "step": 377
+    },
+    {
+      "epoch": 2.505543237250554,
+      "grad_norm": 0.49005064368247986,
+      "learning_rate": 3.392857142857143e-05,
+      "loss": 0.6011,
+      "step": 378
+    },
+    {
+      "epoch": 2.5121951219512195,
+      "grad_norm": 0.491343230009079,
+      "learning_rate": 3.348214285714286e-05,
+      "loss": 0.6057,
+      "step": 379
+    },
+    {
+      "epoch": 2.5188470066518844,
+      "grad_norm": 0.46646034717559814,
+      "learning_rate": 3.303571428571429e-05,
+      "loss": 0.5785,
+      "step": 380
+    },
+    {
+      "epoch": 2.52549889135255,
+      "grad_norm": 0.4732291102409363,
+      "learning_rate": 3.2589285714285716e-05,
+      "loss": 0.6319,
+      "step": 381
+    },
+    {
+      "epoch": 2.532150776053215,
+      "grad_norm": 0.4858185052871704,
+      "learning_rate": 3.2142857142857144e-05,
+      "loss": 0.6268,
+      "step": 382
+    },
+    {
+      "epoch": 2.5388026607538805,
+      "grad_norm": 0.4568738639354706,
+      "learning_rate": 3.169642857142857e-05,
+      "loss": 0.5823,
+      "step": 383
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.4347289204597473,
+      "learning_rate": 3.125e-05,
+      "loss": 0.6026,
+      "step": 384
+    },
+    {
+      "epoch": 2.5521064301552108,
+      "grad_norm": 0.48688504099845886,
+      "learning_rate": 3.080357142857143e-05,
+      "loss": 0.7049,
+      "step": 385
+    },
+    {
+      "epoch": 2.5587583148558757,
+      "grad_norm": 0.4816850423812866,
+      "learning_rate": 3.0357142857142857e-05,
+      "loss": 0.6216,
+      "step": 386
+    },
+    {
+      "epoch": 2.565410199556541,
+      "grad_norm": 0.45580005645751953,
+      "learning_rate": 2.9910714285714286e-05,
+      "loss": 0.6799,
+      "step": 387
+    },
+    {
+      "epoch": 2.5720620842572064,
+      "grad_norm": 0.480389803647995,
+      "learning_rate": 2.9464285714285718e-05,
+      "loss": 0.6137,
+      "step": 388
+    },
+    {
+      "epoch": 2.5787139689578713,
+      "grad_norm": 0.4696180820465088,
+      "learning_rate": 2.9017857142857146e-05,
+      "loss": 0.6559,
+      "step": 389
+    },
+    {
+      "epoch": 2.5853658536585367,
+      "grad_norm": 0.4532281756401062,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.6317,
+      "step": 390
+    },
+    {
+      "epoch": 2.5920177383592016,
+      "grad_norm": 0.44541651010513306,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 0.5897,
+      "step": 391
+    },
+    {
+      "epoch": 2.598669623059867,
+      "grad_norm": 0.43191802501678467,
+      "learning_rate": 2.767857142857143e-05,
+      "loss": 0.5826,
+      "step": 392
+    },
+    {
+      "epoch": 2.6053215077605323,
+      "grad_norm": 0.40122276544570923,
+      "learning_rate": 2.7232142857142856e-05,
+      "loss": 0.5577,
+      "step": 393
+    },
+    {
+      "epoch": 2.611973392461197,
+      "grad_norm": 0.4712787866592407,
+      "learning_rate": 2.6785714285714288e-05,
+      "loss": 0.5991,
+      "step": 394
+    },
+    {
+      "epoch": 2.6186252771618626,
+      "grad_norm": 0.5054537653923035,
+      "learning_rate": 2.6339285714285716e-05,
+      "loss": 0.5609,
+      "step": 395
+    },
+    {
+      "epoch": 2.6252771618625275,
+      "grad_norm": 0.4568025767803192,
+      "learning_rate": 2.5892857142857148e-05,
+      "loss": 0.6148,
+      "step": 396
+    },
+    {
+      "epoch": 2.631929046563193,
+      "grad_norm": 0.4544684588909149,
+      "learning_rate": 2.544642857142857e-05,
+      "loss": 0.5765,
+      "step": 397
+    },
+    {
+      "epoch": 2.638580931263858,
+      "grad_norm": 0.5238617062568665,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6413,
+      "step": 398
+    },
+    {
+      "epoch": 2.6452328159645235,
+      "grad_norm": 0.46520912647247314,
+      "learning_rate": 2.455357142857143e-05,
+      "loss": 0.6665,
+      "step": 399
+    },
+    {
+      "epoch": 2.6518847006651884,
+      "grad_norm": 0.48193562030792236,
+      "learning_rate": 2.4107142857142858e-05,
+      "loss": 0.6441,
+      "step": 400
+    },
+    {
+      "epoch": 2.658536585365854,
+      "grad_norm": 0.5027042627334595,
+      "learning_rate": 2.3660714285714286e-05,
+      "loss": 0.6392,
+      "step": 401
+    },
+    {
+      "epoch": 2.6651884700665187,
+      "grad_norm": 0.47919410467147827,
+      "learning_rate": 2.3214285714285715e-05,
+      "loss": 0.6134,
+      "step": 402
+    },
+    {
+      "epoch": 2.671840354767184,
+      "grad_norm": 0.4763931632041931,
+      "learning_rate": 2.2767857142857143e-05,
+      "loss": 0.6465,
+      "step": 403
+    },
+    {
+      "epoch": 2.6784922394678494,
+      "grad_norm": 0.4499167501926422,
+      "learning_rate": 2.2321428571428575e-05,
+      "loss": 0.6349,
+      "step": 404
+    },
+    {
+      "epoch": 2.6851441241685143,
+      "grad_norm": 0.4401226341724396,
+      "learning_rate": 2.1875e-05,
+      "loss": 0.6348,
+      "step": 405
+    },
+    {
+      "epoch": 2.6917960088691797,
+      "grad_norm": 0.5277270674705505,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.6026,
+      "step": 406
+    },
+    {
+      "epoch": 2.6984478935698446,
+      "grad_norm": 0.4905240833759308,
+      "learning_rate": 2.098214285714286e-05,
+      "loss": 0.6175,
+      "step": 407
+    },
+    {
+      "epoch": 2.70509977827051,
+      "grad_norm": 0.5013618469238281,
+      "learning_rate": 2.0535714285714285e-05,
+      "loss": 0.6226,
+      "step": 408
+    },
+    {
+      "epoch": 2.7117516629711753,
+      "grad_norm": 0.4880474805831909,
+      "learning_rate": 2.0089285714285717e-05,
+      "loss": 0.623,
+      "step": 409
+    },
+    {
+      "epoch": 2.7184035476718402,
+      "grad_norm": 0.46920067071914673,
+      "learning_rate": 1.9642857142857145e-05,
+      "loss": 0.5365,
+      "step": 410
+    },
+    {
+      "epoch": 2.7250554323725056,
+      "grad_norm": 0.4643353521823883,
+      "learning_rate": 1.9196428571428573e-05,
+      "loss": 0.5626,
+      "step": 411
+    },
+    {
+      "epoch": 2.7317073170731705,
+      "grad_norm": 0.49955999851226807,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.6115,
+      "step": 412
+    },
+    {
+      "epoch": 2.738359201773836,
+      "grad_norm": 0.44651520252227783,
+      "learning_rate": 1.8303571428571427e-05,
+      "loss": 0.6197,
+      "step": 413
+    },
+    {
+      "epoch": 2.745011086474501,
+      "grad_norm": 0.47436055541038513,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.6069,
+      "step": 414
+    },
+    {
+      "epoch": 2.7516629711751666,
+      "grad_norm": 0.503542959690094,
+      "learning_rate": 1.7410714285714287e-05,
+      "loss": 0.6381,
+      "step": 415
+    },
+    {
+      "epoch": 2.7583148558758315,
+      "grad_norm": 0.4744454026222229,
+      "learning_rate": 1.6964285714285715e-05,
+      "loss": 0.61,
+      "step": 416
+    },
+    {
+      "epoch": 2.764966740576497,
+      "grad_norm": 0.4794369041919708,
+      "learning_rate": 1.6517857142857144e-05,
+      "loss": 0.6174,
+      "step": 417
+    },
+    {
+      "epoch": 2.7716186252771617,
+      "grad_norm": 0.4655187726020813,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.6527,
+      "step": 418
+    },
+    {
+      "epoch": 2.778270509977827,
+      "grad_norm": 0.4897002875804901,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.6898,
+      "step": 419
+    },
+    {
+      "epoch": 2.7849223946784925,
+      "grad_norm": 0.5058550238609314,
+      "learning_rate": 1.5178571428571429e-05,
+      "loss": 0.6797,
+      "step": 420
+    },
+    {
+      "epoch": 2.7915742793791574,
+      "grad_norm": 0.4861222505569458,
+      "learning_rate": 1.4732142857142859e-05,
+      "loss": 0.5982,
+      "step": 421
+    },
+    {
+      "epoch": 2.7982261640798227,
+      "grad_norm": 0.5127925872802734,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.6455,
+      "step": 422
+    },
+    {
+      "epoch": 2.8048780487804876,
+      "grad_norm": 0.5286306142807007,
+      "learning_rate": 1.3839285714285715e-05,
+      "loss": 0.5654,
+      "step": 423
+    },
+    {
+      "epoch": 2.811529933481153,
+      "grad_norm": 0.4822687804698944,
+      "learning_rate": 1.3392857142857144e-05,
+      "loss": 0.6013,
+      "step": 424
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.5384005904197693,
+      "learning_rate": 1.2946428571428574e-05,
+      "loss": 0.6219,
+      "step": 425
+    },
+    {
+      "epoch": 2.8248337028824833,
+      "grad_norm": 0.47531265020370483,
+      "learning_rate": 1.25e-05,
+      "loss": 0.5894,
+      "step": 426
+    },
+    {
+      "epoch": 2.8314855875831486,
+      "grad_norm": 0.4719056785106659,
+      "learning_rate": 1.2053571428571429e-05,
+      "loss": 0.555,
+      "step": 427
+    },
+    {
+      "epoch": 2.8381374722838135,
+      "grad_norm": 0.46995440125465393,
+      "learning_rate": 1.1607142857142857e-05,
+      "loss": 0.5982,
+      "step": 428
+    },
+    {
+      "epoch": 2.844789356984479,
+      "grad_norm": 0.49806344509124756,
+      "learning_rate": 1.1160714285714287e-05,
+      "loss": 0.6163,
+      "step": 429
+    },
+    {
+      "epoch": 2.8514412416851442,
+      "grad_norm": 0.516968309879303,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.6196,
+      "step": 430
+    },
+    {
+      "epoch": 2.858093126385809,
+      "grad_norm": 0.4779220223426819,
+      "learning_rate": 1.0267857142857142e-05,
+      "loss": 0.655,
+      "step": 431
+    },
+    {
+      "epoch": 2.8647450110864745,
+      "grad_norm": 0.46849313378334045,
+      "learning_rate": 9.821428571428573e-06,
+      "loss": 0.6214,
+      "step": 432
+    },
+    {
+      "epoch": 2.8713968957871394,
+      "grad_norm": 0.5084152221679688,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.6505,
+      "step": 433
+    },
+    {
+      "epoch": 2.8780487804878048,
+      "grad_norm": 0.4465777277946472,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 0.5913,
+      "step": 434
+    },
+    {
+      "epoch": 2.88470066518847,
+      "grad_norm": 0.4799346923828125,
+      "learning_rate": 8.482142857142858e-06,
+      "loss": 0.5277,
+      "step": 435
+    },
+    {
+      "epoch": 2.8913525498891355,
+      "grad_norm": 0.4635719358921051,
+      "learning_rate": 8.035714285714286e-06,
+      "loss": 0.5869,
+      "step": 436
+    },
+    {
+      "epoch": 2.8980044345898004,
+      "grad_norm": 0.47485411167144775,
+      "learning_rate": 7.589285714285714e-06,
+      "loss": 0.5806,
+      "step": 437
+    },
+    {
+      "epoch": 2.9046563192904657,
+      "grad_norm": 0.487113893032074,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.5703,
+      "step": 438
+    },
+    {
+      "epoch": 2.9113082039911307,
+      "grad_norm": 0.49744752049446106,
+      "learning_rate": 6.696428571428572e-06,
+      "loss": 0.5517,
+      "step": 439
+    },
+    {
+      "epoch": 2.917960088691796,
+      "grad_norm": 0.47925910353660583,
+      "learning_rate": 6.25e-06,
+      "loss": 0.5826,
+      "step": 440
+    },
+    {
+      "epoch": 2.9246119733924614,
+      "grad_norm": 0.4984948933124542,
+      "learning_rate": 5.803571428571429e-06,
+      "loss": 0.6255,
+      "step": 441
+    },
+    {
+      "epoch": 2.9312638580931263,
+      "grad_norm": 0.47989895939826965,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.5756,
+      "step": 442
+    },
+    {
+      "epoch": 2.9379157427937916,
+      "grad_norm": 0.48715052008628845,
+      "learning_rate": 4.910714285714286e-06,
+      "loss": 0.5595,
+      "step": 443
+    },
+    {
+      "epoch": 2.9445676274944566,
+      "grad_norm": 0.49329787492752075,
+      "learning_rate": 4.464285714285715e-06,
+      "loss": 0.5843,
+      "step": 444
+    },
+    {
+      "epoch": 2.951219512195122,
+      "grad_norm": 0.48121991753578186,
+      "learning_rate": 4.017857142857143e-06,
+      "loss": 0.5953,
+      "step": 445
+    },
+    {
+      "epoch": 2.9578713968957873,
+      "grad_norm": 0.49234673380851746,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 0.5911,
+      "step": 446
+    },
+    {
+      "epoch": 2.964523281596452,
+      "grad_norm": 0.4730541408061981,
+      "learning_rate": 3.125e-06,
+      "loss": 0.6467,
+      "step": 447
+    },
+    {
+      "epoch": 2.9711751662971175,
+      "grad_norm": 0.5518438816070557,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 0.6008,
+      "step": 448
+    },
+    {
+      "epoch": 2.9778270509977824,
+      "grad_norm": 0.5029024481773376,
+      "learning_rate": 2.2321428571428573e-06,
+      "loss": 0.6694,
+      "step": 449
+    },
+    {
+      "epoch": 2.984478935698448,
+      "grad_norm": 0.47128358483314514,
+      "learning_rate": 1.7857142857142857e-06,
+      "loss": 0.6876,
+      "step": 450
+    },
+    {
+      "epoch": 2.991130820399113,
+      "grad_norm": 0.4688984453678131,
+      "learning_rate": 1.3392857142857143e-06,
+      "loss": 0.5647,
+      "step": 451
+    },
+    {
+      "epoch": 2.9977827050997785,
+      "grad_norm": 0.4817278981208801,
+      "learning_rate": 8.928571428571428e-07,
+      "loss": 0.5364,
+      "step": 452
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9951188564300537,
+      "learning_rate": 4.464285714285714e-07,
+      "loss": 0.5632,
+      "step": 453
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 453,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.088120449399685e+17,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

seed2/checkpoint-453/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebc4337b8882ab993011f98e040dbbc2f1ee8ced24d083bd5d1dc3da15b5daf
+size 6289