Upload seed1/checkpoint-420

.gitattributes

@@ -91,3 +91,4 @@ seed1/checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed1/checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed1/checkpoint-390/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed1/checkpoint-405/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+seed1/checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text

seed1/checkpoint-420/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

seed1/checkpoint-420/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": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

seed1/checkpoint-420/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c2b1b974fda9ff69efd9014bd6cc9b88dfe0c75dbc3ff474ad0293cc7670d2
+size 80792096

seed1/checkpoint-420/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
+}

seed1/checkpoint-420/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 %}

seed1/checkpoint-420/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a775ee230fdf8b5ba151c312458a7ef6d5ac65c943d3a675333117381de7404a
+size 161816187

seed1/checkpoint-420/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36b852f4c51cebe844c9b946435cbce91e60488691496d8883f9a0b652441ed
+size 14645

seed1/checkpoint-420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4645acd0d1bde409f7171649b9237de4d45ecfd1c932952e3c520d60f7b5b737
+size 1465

seed1/checkpoint-420/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|>"
+}

seed1/checkpoint-420/tokenizer.json

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

seed1/checkpoint-420/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
+}

seed1/checkpoint-420/trainer_state.json

@@ -0,0 +1,2974 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.764835164835165,
+  "eval_steps": 500,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 0.9970224499702454,
+      "learning_rate": 0.0,
+      "loss": 1.0991,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 1.144827127456665,
+      "learning_rate": 9.56e-05,
+      "loss": 1.1545,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 1.1169440746307373,
+      "learning_rate": 0.0001912,
+      "loss": 1.123,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 1.0855385065078735,
+      "learning_rate": 0.0002868,
+      "loss": 0.9259,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 0.8469429016113281,
+      "learning_rate": 0.0003824,
+      "loss": 0.8556,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 0.7604000568389893,
+      "learning_rate": 0.000478,
+      "loss": 0.9009,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 0.5317047834396362,
+      "learning_rate": 0.00047694013303769406,
+      "loss": 0.9281,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 0.47205209732055664,
+      "learning_rate": 0.00047588026607538804,
+      "loss": 0.8713,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 0.2961072027683258,
+      "learning_rate": 0.0004748203991130821,
+      "loss": 0.8788,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.38304176926612854,
+      "learning_rate": 0.00047376053215077607,
+      "loss": 0.816,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 0.5212758779525757,
+      "learning_rate": 0.00047270066518847006,
+      "loss": 0.8274,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.543552577495575,
+      "learning_rate": 0.0004716407982261641,
+      "loss": 0.8489,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.4572776257991791,
+      "learning_rate": 0.00047058093126385814,
+      "loss": 0.8166,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.44755756855010986,
+      "learning_rate": 0.0004695210643015521,
+      "loss": 0.7803,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.5597015023231506,
+      "learning_rate": 0.00046846119733924617,
+      "loss": 0.801,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.39118215441703796,
+      "learning_rate": 0.00046740133037694015,
+      "loss": 0.7196,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.4890790581703186,
+      "learning_rate": 0.00046634146341463414,
+      "loss": 0.7744,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.5199437737464905,
+      "learning_rate": 0.0004652815964523282,
+      "loss": 0.7521,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.4048418402671814,
+      "learning_rate": 0.0004642217294900222,
+      "loss": 0.7232,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.4759422242641449,
+      "learning_rate": 0.0004631618625277162,
+      "loss": 0.7887,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.373710572719574,
+      "learning_rate": 0.00046210199556541025,
+      "loss": 0.7673,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.3180016577243805,
+      "learning_rate": 0.00046104212860310423,
+      "loss": 0.7553,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.43041887879371643,
+      "learning_rate": 0.0004599822616407982,
+      "loss": 0.7573,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.4632937014102936,
+      "learning_rate": 0.00045892239467849226,
+      "loss": 0.7318,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.3658117651939392,
+      "learning_rate": 0.0004578625277161863,
+      "loss": 0.7129,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.39879968762397766,
+      "learning_rate": 0.0004568026607538803,
+      "loss": 0.7212,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.4226565659046173,
+      "learning_rate": 0.00045574279379157433,
+      "loss": 0.7441,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.3761254549026489,
+      "learning_rate": 0.00045468292682926826,
+      "loss": 0.7351,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.3735473155975342,
+      "learning_rate": 0.0004536230598669623,
+      "loss": 0.7274,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.3605045676231384,
+      "learning_rate": 0.00045256319290465634,
+      "loss": 0.7511,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.49938589334487915,
+      "learning_rate": 0.00045150332594235033,
+      "loss": 0.733,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.3388383090496063,
+      "learning_rate": 0.00045044345898004437,
+      "loss": 0.7086,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.6535608768463135,
+      "learning_rate": 0.0004493835920177384,
+      "loss": 0.7686,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.36676231026649475,
+      "learning_rate": 0.00044832372505543234,
+      "loss": 0.6831,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.3847268521785736,
+      "learning_rate": 0.0004472638580931264,
+      "loss": 0.7375,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.37475308775901794,
+      "learning_rate": 0.0004462039911308204,
+      "loss": 0.7084,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.3576759696006775,
+      "learning_rate": 0.0004451441241685144,
+      "loss": 0.7693,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.33207494020462036,
+      "learning_rate": 0.00044408425720620845,
+      "loss": 0.7844,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.4797557592391968,
+      "learning_rate": 0.0004430243902439025,
+      "loss": 0.6863,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.3291913866996765,
+      "learning_rate": 0.0004419645232815964,
+      "loss": 0.6941,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.3354625701904297,
+      "learning_rate": 0.00044090465631929047,
+      "loss": 0.7254,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.3200039267539978,
+      "learning_rate": 0.0004398447893569845,
+      "loss": 0.6928,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.377468079328537,
+      "learning_rate": 0.0004387849223946785,
+      "loss": 0.7907,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.35265693068504333,
+      "learning_rate": 0.00043772505543237253,
+      "loss": 0.6916,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.4030437171459198,
+      "learning_rate": 0.0004366651884700666,
+      "loss": 0.721,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.3848680853843689,
+      "learning_rate": 0.0004356053215077605,
+      "loss": 0.7261,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.3052960932254791,
+      "learning_rate": 0.00043454545454545455,
+      "loss": 0.7063,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.3832049071788788,
+      "learning_rate": 0.0004334855875831486,
+      "loss": 0.7652,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.3644565939903259,
+      "learning_rate": 0.0004324257206208426,
+      "loss": 0.8106,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.3032757639884949,
+      "learning_rate": 0.0004313658536585366,
+      "loss": 0.7162,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.3071494996547699,
+      "learning_rate": 0.00043030598669623066,
+      "loss": 0.7907,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.32176244258880615,
+      "learning_rate": 0.0004292461197339246,
+      "loss": 0.7865,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.3945949375629425,
+      "learning_rate": 0.00042818625277161863,
+      "loss": 0.8038,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.2989363968372345,
+      "learning_rate": 0.00042712638580931267,
+      "loss": 0.7172,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.317256361246109,
+      "learning_rate": 0.00042606651884700666,
+      "loss": 0.7325,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.27640077471733093,
+      "learning_rate": 0.0004250066518847007,
+      "loss": 0.765,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.3094281256198883,
+      "learning_rate": 0.00042394678492239474,
+      "loss": 0.7391,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.30334004759788513,
+      "learning_rate": 0.00042288691796008867,
+      "loss": 0.7486,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.3377019166946411,
+      "learning_rate": 0.0004218270509977827,
+      "loss": 0.7444,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.34436339139938354,
+      "learning_rate": 0.00042076718403547675,
+      "loss": 0.7041,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.27596402168273926,
+      "learning_rate": 0.00041970731707317074,
+      "loss": 0.6926,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.3022932708263397,
+      "learning_rate": 0.0004186474501108648,
+      "loss": 0.7138,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.2816564738750458,
+      "learning_rate": 0.0004175875831485588,
+      "loss": 0.7261,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.3032025992870331,
+      "learning_rate": 0.00041652771618625275,
+      "loss": 0.6791,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.26954764127731323,
+      "learning_rate": 0.0004154678492239468,
+      "loss": 0.7032,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.3011576235294342,
+      "learning_rate": 0.00041440798226164083,
+      "loss": 0.7512,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.33316031098365784,
+      "learning_rate": 0.0004133481152993348,
+      "loss": 0.7345,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.3042667508125305,
+      "learning_rate": 0.00041228824833702886,
+      "loss": 0.7834,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.28509846329689026,
+      "learning_rate": 0.00041122838137472285,
+      "loss": 0.7127,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.3400508761405945,
+      "learning_rate": 0.00041016851441241683,
+      "loss": 0.7382,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.3198228180408478,
+      "learning_rate": 0.00040910864745011087,
+      "loss": 0.7625,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.32544252276420593,
+      "learning_rate": 0.00040804878048780486,
+      "loss": 0.7485,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.345786988735199,
+      "learning_rate": 0.0004069889135254989,
+      "loss": 0.7448,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.2966018319129944,
+      "learning_rate": 0.00040592904656319294,
+      "loss": 0.6449,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.27237051725387573,
+      "learning_rate": 0.0004048691796008869,
+      "loss": 0.6467,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.332011342048645,
+      "learning_rate": 0.00040380931263858097,
+      "loss": 0.7323,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.32000380754470825,
+      "learning_rate": 0.00040274944567627495,
+      "loss": 0.7653,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.34098610281944275,
+      "learning_rate": 0.00040168957871396894,
+      "loss": 0.7202,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.2874126732349396,
+      "learning_rate": 0.000400629711751663,
+      "loss": 0.7367,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.322229266166687,
+      "learning_rate": 0.000399569844789357,
+      "loss": 0.6588,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.3342168927192688,
+      "learning_rate": 0.000398509977827051,
+      "loss": 0.7579,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.3295648396015167,
+      "learning_rate": 0.00039745011086474505,
+      "loss": 0.7388,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.2803487479686737,
+      "learning_rate": 0.00039639024390243904,
+      "loss": 0.7614,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.32823750376701355,
+      "learning_rate": 0.000395330376940133,
+      "loss": 0.7479,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.32557007670402527,
+      "learning_rate": 0.00039427050997782706,
+      "loss": 0.7527,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.33845341205596924,
+      "learning_rate": 0.0003932106430155211,
+      "loss": 0.7203,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.39683398604393005,
+      "learning_rate": 0.0003921507760532151,
+      "loss": 0.7576,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.3514403998851776,
+      "learning_rate": 0.00039109090909090913,
+      "loss": 0.7556,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.3493777811527252,
+      "learning_rate": 0.0003900310421286031,
+      "loss": 0.6633,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.28230881690979004,
+      "learning_rate": 0.0003889711751662971,
+      "loss": 0.7153,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.31960365176200867,
+      "learning_rate": 0.00038791130820399114,
+      "loss": 0.7101,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.3226240575313568,
+      "learning_rate": 0.0003868514412416852,
+      "loss": 0.6795,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.37568366527557373,
+      "learning_rate": 0.00038579157427937917,
+      "loss": 0.6586,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.3764398992061615,
+      "learning_rate": 0.0003847317073170732,
+      "loss": 0.8014,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.32533973455429077,
+      "learning_rate": 0.0003836718403547672,
+      "loss": 0.7237,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.28496646881103516,
+      "learning_rate": 0.0003826119733924612,
+      "loss": 0.7134,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.29689112305641174,
+      "learning_rate": 0.0003815521064301552,
+      "loss": 0.7035,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.31590795516967773,
+      "learning_rate": 0.00038049223946784927,
+      "loss": 0.7087,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.2947428822517395,
+      "learning_rate": 0.00037943237250554325,
+      "loss": 0.6697,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.27264344692230225,
+      "learning_rate": 0.0003783725055432373,
+      "loss": 0.6232,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.38913288712501526,
+      "learning_rate": 0.0003773126385809313,
+      "loss": 0.6705,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.3600233793258667,
+      "learning_rate": 0.00037625277161862527,
+      "loss": 0.69,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.36744818091392517,
+      "learning_rate": 0.0003751929046563193,
+      "loss": 0.7739,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.33523765206336975,
+      "learning_rate": 0.00037413303769401335,
+      "loss": 0.7414,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.33133506774902344,
+      "learning_rate": 0.00037307317073170733,
+      "loss": 0.7447,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.38341405987739563,
+      "learning_rate": 0.0003720133037694014,
+      "loss": 0.7693,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.3323330283164978,
+      "learning_rate": 0.00037095343680709536,
+      "loss": 0.7502,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.3311186730861664,
+      "learning_rate": 0.00036989356984478935,
+      "loss": 0.6478,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.32154369354248047,
+      "learning_rate": 0.0003688337028824834,
+      "loss": 0.689,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.33734986186027527,
+      "learning_rate": 0.0003677738359201774,
+      "loss": 0.7497,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.29922378063201904,
+      "learning_rate": 0.0003667139689578714,
+      "loss": 0.6458,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.35878702998161316,
+      "learning_rate": 0.00036565410199556546,
+      "loss": 0.6826,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.4202096462249756,
+      "learning_rate": 0.0003645942350332594,
+      "loss": 0.7508,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.34974202513694763,
+      "learning_rate": 0.00036353436807095343,
+      "loss": 0.6995,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.3248356878757477,
+      "learning_rate": 0.00036247450110864747,
+      "loss": 0.7133,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.3106825649738312,
+      "learning_rate": 0.00036141463414634146,
+      "loss": 0.7873,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.3386942148208618,
+      "learning_rate": 0.0003603547671840355,
+      "loss": 0.674,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.31210097670555115,
+      "learning_rate": 0.00035929490022172954,
+      "loss": 0.761,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.3049944043159485,
+      "learning_rate": 0.00035823503325942347,
+      "loss": 0.6974,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.2945634722709656,
+      "learning_rate": 0.0003571751662971175,
+      "loss": 0.7786,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.334928423166275,
+      "learning_rate": 0.00035611529933481155,
+      "loss": 0.7759,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.33794817328453064,
+      "learning_rate": 0.00035505543237250554,
+      "loss": 0.7268,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.34872716665267944,
+      "learning_rate": 0.0003539955654101996,
+      "loss": 0.6964,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.27211689949035645,
+      "learning_rate": 0.0003529356984478936,
+      "loss": 0.7026,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.303218811750412,
+      "learning_rate": 0.00035187583148558755,
+      "loss": 0.7113,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.28027018904685974,
+      "learning_rate": 0.0003508159645232816,
+      "loss": 0.7727,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.2782959043979645,
+      "learning_rate": 0.00034975609756097563,
+      "loss": 0.7235,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.27962350845336914,
+      "learning_rate": 0.0003486962305986696,
+      "loss": 0.7115,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.28686633706092834,
+      "learning_rate": 0.00034763636363636366,
+      "loss": 0.7398,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.3914222717285156,
+      "learning_rate": 0.0003465764966740577,
+      "loss": 0.7521,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.30597811937332153,
+      "learning_rate": 0.00034551662971175163,
+      "loss": 0.718,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.2956196069717407,
+      "learning_rate": 0.00034445676274944567,
+      "loss": 0.6925,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.3160248398780823,
+      "learning_rate": 0.0003433968957871397,
+      "loss": 0.7046,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.2987951338291168,
+      "learning_rate": 0.0003423370288248337,
+      "loss": 0.6252,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.3024667501449585,
+      "learning_rate": 0.00034127716186252774,
+      "loss": 0.778,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.2868024408817291,
+      "learning_rate": 0.0003402172949002218,
+      "loss": 0.6807,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.29994046688079834,
+      "learning_rate": 0.00033915742793791577,
+      "loss": 0.711,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.3246282935142517,
+      "learning_rate": 0.00033809756097560975,
+      "loss": 0.7606,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.3361048698425293,
+      "learning_rate": 0.0003370376940133038,
+      "loss": 0.6995,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.3376304507255554,
+      "learning_rate": 0.0003359778270509978,
+      "loss": 0.71,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.29205799102783203,
+      "learning_rate": 0.0003349179600886918,
+      "loss": 0.6685,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.30635398626327515,
+      "learning_rate": 0.00033385809312638586,
+      "loss": 0.7522,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.3423284590244293,
+      "learning_rate": 0.00033279822616407985,
+      "loss": 0.6769,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.30614131689071655,
+      "learning_rate": 0.00033173835920177384,
+      "loss": 0.6788,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.3104928433895111,
+      "learning_rate": 0.0003306784922394679,
+      "loss": 0.6591,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.33305084705352783,
+      "learning_rate": 0.00032961862527716186,
+      "loss": 0.6966,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.3775268495082855,
+      "learning_rate": 0.0003285587583148559,
+      "loss": 0.7447,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.3366539776325226,
+      "learning_rate": 0.00032749889135254994,
+      "loss": 0.7501,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.38443613052368164,
+      "learning_rate": 0.00032643902439024393,
+      "loss": 0.645,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.3002435863018036,
+      "learning_rate": 0.0003253791574279379,
+      "loss": 0.7398,
+      "step": 150
+    },
+    {
+      "epoch": 0.9956043956043956,
+      "grad_norm": 0.34713083505630493,
+      "learning_rate": 0.0003243192904656319,
+      "loss": 0.7262,
+      "step": 151
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.35023507475852966,
+      "learning_rate": 0.00032325942350332594,
+      "loss": 0.6768,
+      "step": 152
+    },
+    {
+      "epoch": 1.0065934065934066,
+      "grad_norm": 0.38305485248565674,
+      "learning_rate": 0.00032219955654102,
+      "loss": 0.6883,
+      "step": 153
+    },
+    {
+      "epoch": 1.0131868131868131,
+      "grad_norm": 0.3572325110435486,
+      "learning_rate": 0.00032113968957871397,
+      "loss": 0.6868,
+      "step": 154
+    },
+    {
+      "epoch": 1.0197802197802197,
+      "grad_norm": 0.31668391823768616,
+      "learning_rate": 0.000320079822616408,
+      "loss": 0.6352,
+      "step": 155
+    },
+    {
+      "epoch": 1.0263736263736263,
+      "grad_norm": 0.3431554436683655,
+      "learning_rate": 0.000319019955654102,
+      "loss": 0.6212,
+      "step": 156
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.3789862394332886,
+      "learning_rate": 0.000317960088691796,
+      "loss": 0.6692,
+      "step": 157
+    },
+    {
+      "epoch": 1.0395604395604396,
+      "grad_norm": 0.304165780544281,
+      "learning_rate": 0.00031690022172949,
+      "loss": 0.6753,
+      "step": 158
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.3196735382080078,
+      "learning_rate": 0.00031584035476718407,
+      "loss": 0.6402,
+      "step": 159
+    },
+    {
+      "epoch": 1.0527472527472528,
+      "grad_norm": 0.3539210259914398,
+      "learning_rate": 0.00031478048780487805,
+      "loss": 0.637,
+      "step": 160
+    },
+    {
+      "epoch": 1.0593406593406594,
+      "grad_norm": 0.41358649730682373,
+      "learning_rate": 0.0003137206208425721,
+      "loss": 0.7002,
+      "step": 161
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.3271334767341614,
+      "learning_rate": 0.0003126607538802661,
+      "loss": 0.6182,
+      "step": 162
+    },
+    {
+      "epoch": 1.0725274725274725,
+      "grad_norm": 0.4126374423503876,
+      "learning_rate": 0.00031160088691796007,
+      "loss": 0.6383,
+      "step": 163
+    },
+    {
+      "epoch": 1.079120879120879,
+      "grad_norm": 0.3880680799484253,
+      "learning_rate": 0.0003105410199556541,
+      "loss": 0.6802,
+      "step": 164
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.32755038142204285,
+      "learning_rate": 0.00030948115299334815,
+      "loss": 0.6573,
+      "step": 165
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 0.3592837154865265,
+      "learning_rate": 0.00030842128603104213,
+      "loss": 0.6518,
+      "step": 166
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.42520859837532043,
+      "learning_rate": 0.0003073614190687362,
+      "loss": 0.5939,
+      "step": 167
+    },
+    {
+      "epoch": 1.1054945054945056,
+      "grad_norm": 0.3364773988723755,
+      "learning_rate": 0.00030630155210643016,
+      "loss": 0.6153,
+      "step": 168
+    },
+    {
+      "epoch": 1.1120879120879121,
+      "grad_norm": 0.3265248239040375,
+      "learning_rate": 0.00030524168514412415,
+      "loss": 0.6962,
+      "step": 169
+    },
+    {
+      "epoch": 1.1186813186813187,
+      "grad_norm": 0.34393543004989624,
+      "learning_rate": 0.0003041818181818182,
+      "loss": 0.6184,
+      "step": 170
+    },
+    {
+      "epoch": 1.1252747252747253,
+      "grad_norm": 0.3520282506942749,
+      "learning_rate": 0.00030312195121951223,
+      "loss": 0.6726,
+      "step": 171
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 0.4375007450580597,
+      "learning_rate": 0.0003020620842572062,
+      "loss": 0.6876,
+      "step": 172
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 0.35851043462753296,
+      "learning_rate": 0.00030100221729490026,
+      "loss": 0.6282,
+      "step": 173
+    },
+    {
+      "epoch": 1.145054945054945,
+      "grad_norm": 0.3228410482406616,
+      "learning_rate": 0.00029994235033259424,
+      "loss": 0.7026,
+      "step": 174
+    },
+    {
+      "epoch": 1.1516483516483516,
+      "grad_norm": 0.36233118176460266,
+      "learning_rate": 0.00029888248337028823,
+      "loss": 0.6905,
+      "step": 175
+    },
+    {
+      "epoch": 1.1582417582417581,
+      "grad_norm": 0.3298339247703552,
+      "learning_rate": 0.00029782261640798227,
+      "loss": 0.6957,
+      "step": 176
+    },
+    {
+      "epoch": 1.164835164835165,
+      "grad_norm": 0.3960157334804535,
+      "learning_rate": 0.0002967627494456763,
+      "loss": 0.643,
+      "step": 177
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 0.4046969711780548,
+      "learning_rate": 0.0002957028824833703,
+      "loss": 0.6738,
+      "step": 178
+    },
+    {
+      "epoch": 1.178021978021978,
+      "grad_norm": 0.3787284791469574,
+      "learning_rate": 0.00029464301552106434,
+      "loss": 0.6648,
+      "step": 179
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.4840444028377533,
+      "learning_rate": 0.0002935831485587583,
+      "loss": 0.6528,
+      "step": 180
+    },
+    {
+      "epoch": 1.1912087912087912,
+      "grad_norm": 0.35219264030456543,
+      "learning_rate": 0.0002925232815964523,
+      "loss": 0.7295,
+      "step": 181
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 0.33763912320137024,
+      "learning_rate": 0.00029146341463414635,
+      "loss": 0.5904,
+      "step": 182
+    },
+    {
+      "epoch": 1.2043956043956043,
+      "grad_norm": 0.4614327847957611,
+      "learning_rate": 0.0002904035476718404,
+      "loss": 0.6324,
+      "step": 183
+    },
+    {
+      "epoch": 1.210989010989011,
+      "grad_norm": 0.410922110080719,
+      "learning_rate": 0.0002893436807095344,
+      "loss": 0.6963,
+      "step": 184
+    },
+    {
+      "epoch": 1.2175824175824177,
+      "grad_norm": 0.33478567004203796,
+      "learning_rate": 0.0002882838137472284,
+      "loss": 0.6746,
+      "step": 185
+    },
+    {
+      "epoch": 1.2241758241758243,
+      "grad_norm": 0.38460463285446167,
+      "learning_rate": 0.0002872239467849224,
+      "loss": 0.7287,
+      "step": 186
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.41470155119895935,
+      "learning_rate": 0.0002861640798226164,
+      "loss": 0.7065,
+      "step": 187
+    },
+    {
+      "epoch": 1.2373626373626374,
+      "grad_norm": 0.40113189816474915,
+      "learning_rate": 0.00028510421286031043,
+      "loss": 0.635,
+      "step": 188
+    },
+    {
+      "epoch": 1.243956043956044,
+      "grad_norm": 0.35355815291404724,
+      "learning_rate": 0.0002840443458980045,
+      "loss": 0.7256,
+      "step": 189
+    },
+    {
+      "epoch": 1.2505494505494505,
+      "grad_norm": 0.3277815580368042,
+      "learning_rate": 0.00028298447893569846,
+      "loss": 0.6529,
+      "step": 190
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.37198781967163086,
+      "learning_rate": 0.0002819246119733925,
+      "loss": 0.6507,
+      "step": 191
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 0.33678582310676575,
+      "learning_rate": 0.00028086474501108643,
+      "loss": 0.6389,
+      "step": 192
+    },
+    {
+      "epoch": 1.2703296703296703,
+      "grad_norm": 0.34777119755744934,
+      "learning_rate": 0.0002798048780487805,
+      "loss": 0.6804,
+      "step": 193
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 0.3285517692565918,
+      "learning_rate": 0.0002787450110864745,
+      "loss": 0.648,
+      "step": 194
+    },
+    {
+      "epoch": 1.2835164835164834,
+      "grad_norm": 0.33483248949050903,
+      "learning_rate": 0.0002776851441241685,
+      "loss": 0.6687,
+      "step": 195
+    },
+    {
+      "epoch": 1.2901098901098902,
+      "grad_norm": 0.37951233983039856,
+      "learning_rate": 0.00027662527716186254,
+      "loss": 0.6466,
+      "step": 196
+    },
+    {
+      "epoch": 1.2967032967032968,
+      "grad_norm": 0.35914433002471924,
+      "learning_rate": 0.0002755654101995566,
+      "loss": 0.6814,
+      "step": 197
+    },
+    {
+      "epoch": 1.3032967032967033,
+      "grad_norm": 0.3615425229072571,
+      "learning_rate": 0.0002745055432372505,
+      "loss": 0.7048,
+      "step": 198
+    },
+    {
+      "epoch": 1.30989010989011,
+      "grad_norm": 0.37614500522613525,
+      "learning_rate": 0.00027344567627494455,
+      "loss": 0.631,
+      "step": 199
+    },
+    {
+      "epoch": 1.3164835164835165,
+      "grad_norm": 0.3917557895183563,
+      "learning_rate": 0.0002723858093126386,
+      "loss": 0.6921,
+      "step": 200
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 0.3767569661140442,
+      "learning_rate": 0.0002713259423503326,
+      "loss": 0.6566,
+      "step": 201
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 0.3442741930484772,
+      "learning_rate": 0.0002702660753880266,
+      "loss": 0.6354,
+      "step": 202
+    },
+    {
+      "epoch": 1.3362637362637364,
+      "grad_norm": 0.31562164425849915,
+      "learning_rate": 0.00026920620842572066,
+      "loss": 0.6291,
+      "step": 203
+    },
+    {
+      "epoch": 1.342857142857143,
+      "grad_norm": 0.3532516658306122,
+      "learning_rate": 0.00026814634146341465,
+      "loss": 0.6796,
+      "step": 204
+    },
+    {
+      "epoch": 1.3494505494505495,
+      "grad_norm": 0.3777218759059906,
+      "learning_rate": 0.00026708647450110864,
+      "loss": 0.6734,
+      "step": 205
+    },
+    {
+      "epoch": 1.3560439560439561,
+      "grad_norm": 0.35049760341644287,
+      "learning_rate": 0.0002660266075388027,
+      "loss": 0.6792,
+      "step": 206
+    },
+    {
+      "epoch": 1.3626373626373627,
+      "grad_norm": 0.37494373321533203,
+      "learning_rate": 0.00026496674057649666,
+      "loss": 0.757,
+      "step": 207
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.37660735845565796,
+      "learning_rate": 0.0002639068736141907,
+      "loss": 0.7308,
+      "step": 208
+    },
+    {
+      "epoch": 1.3758241758241758,
+      "grad_norm": 0.4234360158443451,
+      "learning_rate": 0.00026284700665188474,
+      "loss": 0.6798,
+      "step": 209
+    },
+    {
+      "epoch": 1.3824175824175824,
+      "grad_norm": 0.3924785852432251,
+      "learning_rate": 0.00026178713968957873,
+      "loss": 0.6312,
+      "step": 210
+    },
+    {
+      "epoch": 1.389010989010989,
+      "grad_norm": 0.35264280438423157,
+      "learning_rate": 0.0002607272727272727,
+      "loss": 0.6692,
+      "step": 211
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.3955014646053314,
+      "learning_rate": 0.00025966740576496676,
+      "loss": 0.6219,
+      "step": 212
+    },
+    {
+      "epoch": 1.402197802197802,
+      "grad_norm": 0.36072415113449097,
+      "learning_rate": 0.00025860753880266074,
+      "loss": 0.6306,
+      "step": 213
+    },
+    {
+      "epoch": 1.4087912087912087,
+      "grad_norm": 0.3578793704509735,
+      "learning_rate": 0.0002575476718403548,
+      "loss": 0.6307,
+      "step": 214
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 0.38820844888687134,
+      "learning_rate": 0.0002564878048780488,
+      "loss": 0.6426,
+      "step": 215
+    },
+    {
+      "epoch": 1.421978021978022,
+      "grad_norm": 0.3640262186527252,
+      "learning_rate": 0.0002554279379157428,
+      "loss": 0.6798,
+      "step": 216
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.355820894241333,
+      "learning_rate": 0.0002543680709534368,
+      "loss": 0.6732,
+      "step": 217
+    },
+    {
+      "epoch": 1.4351648351648352,
+      "grad_norm": 0.358778715133667,
+      "learning_rate": 0.00025330820399113084,
+      "loss": 0.6162,
+      "step": 218
+    },
+    {
+      "epoch": 1.4417582417582417,
+      "grad_norm": 0.40246081352233887,
+      "learning_rate": 0.0002522483370288248,
+      "loss": 0.6655,
+      "step": 219
+    },
+    {
+      "epoch": 1.4483516483516483,
+      "grad_norm": 0.37145930528640747,
+      "learning_rate": 0.00025118847006651887,
+      "loss": 0.627,
+      "step": 220
+    },
+    {
+      "epoch": 1.4549450549450549,
+      "grad_norm": 0.3811812400817871,
+      "learning_rate": 0.0002501286031042129,
+      "loss": 0.6546,
+      "step": 221
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.3838576376438141,
+      "learning_rate": 0.0002490687361419069,
+      "loss": 0.6268,
+      "step": 222
+    },
+    {
+      "epoch": 1.4681318681318682,
+      "grad_norm": 0.3758513033390045,
+      "learning_rate": 0.0002480088691796009,
+      "loss": 0.6633,
+      "step": 223
+    },
+    {
+      "epoch": 1.4747252747252748,
+      "grad_norm": 0.3423100411891937,
+      "learning_rate": 0.0002469490022172949,
+      "loss": 0.5918,
+      "step": 224
+    },
+    {
+      "epoch": 1.4813186813186814,
+      "grad_norm": 0.38100165128707886,
+      "learning_rate": 0.0002458891352549889,
+      "loss": 0.6865,
+      "step": 225
+    },
+    {
+      "epoch": 1.487912087912088,
+      "grad_norm": 0.4081498384475708,
+      "learning_rate": 0.00024482926829268295,
+      "loss": 0.7151,
+      "step": 226
+    },
+    {
+      "epoch": 1.4945054945054945,
+      "grad_norm": 0.3668079376220703,
+      "learning_rate": 0.00024376940133037696,
+      "loss": 0.5827,
+      "step": 227
+    },
+    {
+      "epoch": 1.501098901098901,
+      "grad_norm": 0.40372422337532043,
+      "learning_rate": 0.00024270953436807097,
+      "loss": 0.6658,
+      "step": 228
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 0.3988126218318939,
+      "learning_rate": 0.00024164966740576496,
+      "loss": 0.5753,
+      "step": 229
+    },
+    {
+      "epoch": 1.5142857142857142,
+      "grad_norm": 0.398112028837204,
+      "learning_rate": 0.00024058980044345897,
+      "loss": 0.687,
+      "step": 230
+    },
+    {
+      "epoch": 1.5208791208791208,
+      "grad_norm": 0.4017437994480133,
+      "learning_rate": 0.000239529933481153,
+      "loss": 0.6603,
+      "step": 231
+    },
+    {
+      "epoch": 1.5274725274725274,
+      "grad_norm": 0.40356186032295227,
+      "learning_rate": 0.00023847006651884703,
+      "loss": 0.6526,
+      "step": 232
+    },
+    {
+      "epoch": 1.534065934065934,
+      "grad_norm": 0.40809166431427,
+      "learning_rate": 0.00023741019955654104,
+      "loss": 0.6537,
+      "step": 233
+    },
+    {
+      "epoch": 1.5406593406593405,
+      "grad_norm": 0.3994799852371216,
+      "learning_rate": 0.00023635033259423503,
+      "loss": 0.6892,
+      "step": 234
+    },
+    {
+      "epoch": 1.5472527472527473,
+      "grad_norm": 0.3911482095718384,
+      "learning_rate": 0.00023529046563192907,
+      "loss": 0.6855,
+      "step": 235
+    },
+    {
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.40330222249031067,
+      "learning_rate": 0.00023423059866962308,
+      "loss": 0.5921,
+      "step": 236
+    },
+    {
+      "epoch": 1.5604395604395604,
+      "grad_norm": 0.37935584783554077,
+      "learning_rate": 0.00023317073170731707,
+      "loss": 0.6465,
+      "step": 237
+    },
+    {
+      "epoch": 1.567032967032967,
+      "grad_norm": 0.3929573893547058,
+      "learning_rate": 0.0002321108647450111,
+      "loss": 0.6346,
+      "step": 238
+    },
+    {
+      "epoch": 1.5736263736263736,
+      "grad_norm": 0.38034695386886597,
+      "learning_rate": 0.00023105099778270512,
+      "loss": 0.6796,
+      "step": 239
+    },
+    {
+      "epoch": 1.5802197802197804,
+      "grad_norm": 0.32818010449409485,
+      "learning_rate": 0.0002299911308203991,
+      "loss": 0.6635,
+      "step": 240
+    },
+    {
+      "epoch": 1.586813186813187,
+      "grad_norm": 0.35218796133995056,
+      "learning_rate": 0.00022893126385809315,
+      "loss": 0.7231,
+      "step": 241
+    },
+    {
+      "epoch": 1.5934065934065935,
+      "grad_norm": 0.36161521077156067,
+      "learning_rate": 0.00022787139689578716,
+      "loss": 0.6457,
+      "step": 242
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.35236117243766785,
+      "learning_rate": 0.00022681152993348115,
+      "loss": 0.6446,
+      "step": 243
+    },
+    {
+      "epoch": 1.6065934065934067,
+      "grad_norm": 0.41815316677093506,
+      "learning_rate": 0.00022575166297117516,
+      "loss": 0.6849,
+      "step": 244
+    },
+    {
+      "epoch": 1.6131868131868132,
+      "grad_norm": 0.36881476640701294,
+      "learning_rate": 0.0002246917960088692,
+      "loss": 0.6419,
+      "step": 245
+    },
+    {
+      "epoch": 1.6197802197802198,
+      "grad_norm": 0.36567461490631104,
+      "learning_rate": 0.0002236319290465632,
+      "loss": 0.6977,
+      "step": 246
+    },
+    {
+      "epoch": 1.6263736263736264,
+      "grad_norm": 0.374749094247818,
+      "learning_rate": 0.0002225720620842572,
+      "loss": 0.6615,
+      "step": 247
+    },
+    {
+      "epoch": 1.632967032967033,
+      "grad_norm": 0.3468921482563019,
+      "learning_rate": 0.00022151219512195125,
+      "loss": 0.7002,
+      "step": 248
+    },
+    {
+      "epoch": 1.6395604395604395,
+      "grad_norm": 0.41083279252052307,
+      "learning_rate": 0.00022045232815964523,
+      "loss": 0.5928,
+      "step": 249
+    },
+    {
+      "epoch": 1.646153846153846,
+      "grad_norm": 0.37868770956993103,
+      "learning_rate": 0.00021939246119733925,
+      "loss": 0.7236,
+      "step": 250
+    },
+    {
+      "epoch": 1.6527472527472526,
+      "grad_norm": 0.3629273474216461,
+      "learning_rate": 0.0002183325942350333,
+      "loss": 0.633,
+      "step": 251
+    },
+    {
+      "epoch": 1.6593406593406592,
+      "grad_norm": 0.35424259305000305,
+      "learning_rate": 0.00021727272727272727,
+      "loss": 0.6305,
+      "step": 252
+    },
+    {
+      "epoch": 1.6659340659340658,
+      "grad_norm": 0.439231276512146,
+      "learning_rate": 0.0002162128603104213,
+      "loss": 0.7461,
+      "step": 253
+    },
+    {
+      "epoch": 1.6725274725274726,
+      "grad_norm": 0.4257543385028839,
+      "learning_rate": 0.00021515299334811533,
+      "loss": 0.6634,
+      "step": 254
+    },
+    {
+      "epoch": 1.6791208791208792,
+      "grad_norm": 0.3998747766017914,
+      "learning_rate": 0.00021409312638580931,
+      "loss": 0.6854,
+      "step": 255
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.3800191879272461,
+      "learning_rate": 0.00021303325942350333,
+      "loss": 0.6449,
+      "step": 256
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.4337719976902008,
+      "learning_rate": 0.00021197339246119737,
+      "loss": 0.671,
+      "step": 257
+    },
+    {
+      "epoch": 1.6989010989010989,
+      "grad_norm": 0.44184720516204834,
+      "learning_rate": 0.00021091352549889135,
+      "loss": 0.527,
+      "step": 258
+    },
+    {
+      "epoch": 1.7054945054945057,
+      "grad_norm": 0.33520013093948364,
+      "learning_rate": 0.00020985365853658537,
+      "loss": 0.7268,
+      "step": 259
+    },
+    {
+      "epoch": 1.7120879120879122,
+      "grad_norm": 0.3855791985988617,
+      "learning_rate": 0.0002087937915742794,
+      "loss": 0.5909,
+      "step": 260
+    },
+    {
+      "epoch": 1.7186813186813188,
+      "grad_norm": 0.3870508074760437,
+      "learning_rate": 0.0002077339246119734,
+      "loss": 0.6634,
+      "step": 261
+    },
+    {
+      "epoch": 1.7252747252747254,
+      "grad_norm": 0.4269031882286072,
+      "learning_rate": 0.0002066740576496674,
+      "loss": 0.6776,
+      "step": 262
+    },
+    {
+      "epoch": 1.731868131868132,
+      "grad_norm": 0.37803956866264343,
+      "learning_rate": 0.00020561419068736142,
+      "loss": 0.6311,
+      "step": 263
+    },
+    {
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.39058563113212585,
+      "learning_rate": 0.00020455432372505544,
+      "loss": 0.599,
+      "step": 264
+    },
+    {
+      "epoch": 1.745054945054945,
+      "grad_norm": 0.4414854943752289,
+      "learning_rate": 0.00020349445676274945,
+      "loss": 0.6691,
+      "step": 265
+    },
+    {
+      "epoch": 1.7516483516483516,
+      "grad_norm": 0.4004284143447876,
+      "learning_rate": 0.00020243458980044346,
+      "loss": 0.6383,
+      "step": 266
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 0.3992699086666107,
+      "learning_rate": 0.00020137472283813748,
+      "loss": 0.6672,
+      "step": 267
+    },
+    {
+      "epoch": 1.7648351648351648,
+      "grad_norm": 0.358350545167923,
+      "learning_rate": 0.0002003148558758315,
+      "loss": 0.6446,
+      "step": 268
+    },
+    {
+      "epoch": 1.7714285714285714,
+      "grad_norm": 0.4032428562641144,
+      "learning_rate": 0.0001992549889135255,
+      "loss": 0.6778,
+      "step": 269
+    },
+    {
+      "epoch": 1.778021978021978,
+      "grad_norm": 0.3804583251476288,
+      "learning_rate": 0.00019819512195121952,
+      "loss": 0.6544,
+      "step": 270
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 0.3812550902366638,
+      "learning_rate": 0.00019713525498891353,
+      "loss": 0.6647,
+      "step": 271
+    },
+    {
+      "epoch": 1.791208791208791,
+      "grad_norm": 0.3965335786342621,
+      "learning_rate": 0.00019607538802660754,
+      "loss": 0.6015,
+      "step": 272
+    },
+    {
+      "epoch": 1.7978021978021979,
+      "grad_norm": 0.3880223333835602,
+      "learning_rate": 0.00019501552106430156,
+      "loss": 0.661,
+      "step": 273
+    },
+    {
+      "epoch": 1.8043956043956044,
+      "grad_norm": 0.3955674171447754,
+      "learning_rate": 0.00019395565410199557,
+      "loss": 0.5993,
+      "step": 274
+    },
+    {
+      "epoch": 1.810989010989011,
+      "grad_norm": 0.427304208278656,
+      "learning_rate": 0.00019289578713968959,
+      "loss": 0.6222,
+      "step": 275
+    },
+    {
+      "epoch": 1.8175824175824176,
+      "grad_norm": 0.43342676758766174,
+      "learning_rate": 0.0001918359201773836,
+      "loss": 0.6385,
+      "step": 276
+    },
+    {
+      "epoch": 1.8241758241758241,
+      "grad_norm": 0.38551008701324463,
+      "learning_rate": 0.0001907760532150776,
+      "loss": 0.6297,
+      "step": 277
+    },
+    {
+      "epoch": 1.830769230769231,
+      "grad_norm": 0.34939613938331604,
+      "learning_rate": 0.00018971618625277163,
+      "loss": 0.6703,
+      "step": 278
+    },
+    {
+      "epoch": 1.8373626373626375,
+      "grad_norm": 0.3339291214942932,
+      "learning_rate": 0.00018865631929046564,
+      "loss": 0.6689,
+      "step": 279
+    },
+    {
+      "epoch": 1.843956043956044,
+      "grad_norm": 0.32809391617774963,
+      "learning_rate": 0.00018759645232815965,
+      "loss": 0.6801,
+      "step": 280
+    },
+    {
+      "epoch": 1.8505494505494506,
+      "grad_norm": 0.3705151081085205,
+      "learning_rate": 0.00018653658536585367,
+      "loss": 0.6401,
+      "step": 281
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.3831600546836853,
+      "learning_rate": 0.00018547671840354768,
+      "loss": 0.6629,
+      "step": 282
+    },
+    {
+      "epoch": 1.8637362637362638,
+      "grad_norm": 0.3629395663738251,
+      "learning_rate": 0.0001844168514412417,
+      "loss": 0.7061,
+      "step": 283
+    },
+    {
+      "epoch": 1.8703296703296703,
+      "grad_norm": 0.40745213627815247,
+      "learning_rate": 0.0001833569844789357,
+      "loss": 0.675,
+      "step": 284
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 0.4040345251560211,
+      "learning_rate": 0.0001822971175166297,
+      "loss": 0.6418,
+      "step": 285
+    },
+    {
+      "epoch": 1.8835164835164835,
+      "grad_norm": 0.38781166076660156,
+      "learning_rate": 0.00018123725055432373,
+      "loss": 0.6584,
+      "step": 286
+    },
+    {
+      "epoch": 1.89010989010989,
+      "grad_norm": 0.4350965917110443,
+      "learning_rate": 0.00018017738359201775,
+      "loss": 0.6696,
+      "step": 287
+    },
+    {
+      "epoch": 1.8967032967032966,
+      "grad_norm": 0.3712170124053955,
+      "learning_rate": 0.00017911751662971173,
+      "loss": 0.6406,
+      "step": 288
+    },
+    {
+      "epoch": 1.9032967032967032,
+      "grad_norm": 0.3749583959579468,
+      "learning_rate": 0.00017805764966740578,
+      "loss": 0.6281,
+      "step": 289
+    },
+    {
+      "epoch": 1.9098901098901098,
+      "grad_norm": 0.39066019654273987,
+      "learning_rate": 0.0001769977827050998,
+      "loss": 0.5958,
+      "step": 290
+    },
+    {
+      "epoch": 1.9164835164835163,
+      "grad_norm": 0.32838478684425354,
+      "learning_rate": 0.00017593791574279378,
+      "loss": 0.6969,
+      "step": 291
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.34712207317352295,
+      "learning_rate": 0.00017487804878048782,
+      "loss": 0.6894,
+      "step": 292
+    },
+    {
+      "epoch": 1.9296703296703297,
+      "grad_norm": 0.41427138447761536,
+      "learning_rate": 0.00017381818181818183,
+      "loss": 0.6919,
+      "step": 293
+    },
+    {
+      "epoch": 1.9362637362637363,
+      "grad_norm": 0.36579301953315735,
+      "learning_rate": 0.00017275831485587582,
+      "loss": 0.7193,
+      "step": 294
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 0.4437645971775055,
+      "learning_rate": 0.00017169844789356986,
+      "loss": 0.7467,
+      "step": 295
+    },
+    {
+      "epoch": 1.9494505494505494,
+      "grad_norm": 0.367373526096344,
+      "learning_rate": 0.00017063858093126387,
+      "loss": 0.6547,
+      "step": 296
+    },
+    {
+      "epoch": 1.9560439560439562,
+      "grad_norm": 0.3570501208305359,
+      "learning_rate": 0.00016957871396895788,
+      "loss": 0.6587,
+      "step": 297
+    },
+    {
+      "epoch": 1.9626373626373628,
+      "grad_norm": 0.3444426953792572,
+      "learning_rate": 0.0001685188470066519,
+      "loss": 0.7691,
+      "step": 298
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 0.3180396258831024,
+      "learning_rate": 0.0001674589800443459,
+      "loss": 0.6942,
+      "step": 299
+    },
+    {
+      "epoch": 1.975824175824176,
+      "grad_norm": 0.34924229979515076,
+      "learning_rate": 0.00016639911308203992,
+      "loss": 0.6569,
+      "step": 300
+    },
+    {
+      "epoch": 1.9824175824175825,
+      "grad_norm": 0.36888396739959717,
+      "learning_rate": 0.00016533924611973394,
+      "loss": 0.6636,
+      "step": 301
+    },
+    {
+      "epoch": 1.989010989010989,
+      "grad_norm": 0.3853783905506134,
+      "learning_rate": 0.00016427937915742795,
+      "loss": 0.6572,
+      "step": 302
+    },
+    {
+      "epoch": 1.9956043956043956,
+      "grad_norm": 0.3830152451992035,
+      "learning_rate": 0.00016321951219512197,
+      "loss": 0.6726,
+      "step": 303
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4932275116443634,
+      "learning_rate": 0.00016215964523281595,
+      "loss": 0.6578,
+      "step": 304
+    },
+    {
+      "epoch": 2.0065934065934066,
+      "grad_norm": 0.392809122800827,
+      "learning_rate": 0.00016109977827051,
+      "loss": 0.6292,
+      "step": 305
+    },
+    {
+      "epoch": 2.013186813186813,
+      "grad_norm": 0.38704097270965576,
+      "learning_rate": 0.000160039911308204,
+      "loss": 0.5903,
+      "step": 306
+    },
+    {
+      "epoch": 2.0197802197802197,
+      "grad_norm": 0.37722790241241455,
+      "learning_rate": 0.000158980044345898,
+      "loss": 0.5874,
+      "step": 307
+    },
+    {
+      "epoch": 2.0263736263736263,
+      "grad_norm": 0.3986051380634308,
+      "learning_rate": 0.00015792017738359203,
+      "loss": 0.5913,
+      "step": 308
+    },
+    {
+      "epoch": 2.032967032967033,
+      "grad_norm": 0.42364734411239624,
+      "learning_rate": 0.00015686031042128605,
+      "loss": 0.5503,
+      "step": 309
+    },
+    {
+      "epoch": 2.0395604395604394,
+      "grad_norm": 0.5147843956947327,
+      "learning_rate": 0.00015580044345898003,
+      "loss": 0.6069,
+      "step": 310
+    },
+    {
+      "epoch": 2.046153846153846,
+      "grad_norm": 0.4635319113731384,
+      "learning_rate": 0.00015474057649667407,
+      "loss": 0.5821,
+      "step": 311
+    },
+    {
+      "epoch": 2.0527472527472526,
+      "grad_norm": 0.4730147123336792,
+      "learning_rate": 0.0001536807095343681,
+      "loss": 0.5704,
+      "step": 312
+    },
+    {
+      "epoch": 2.059340659340659,
+      "grad_norm": 0.4122169017791748,
+      "learning_rate": 0.00015262084257206207,
+      "loss": 0.5875,
+      "step": 313
+    },
+    {
+      "epoch": 2.065934065934066,
+      "grad_norm": 0.4188688397407532,
+      "learning_rate": 0.00015156097560975611,
+      "loss": 0.591,
+      "step": 314
+    },
+    {
+      "epoch": 2.0725274725274727,
+      "grad_norm": 0.40339216589927673,
+      "learning_rate": 0.00015050110864745013,
+      "loss": 0.5964,
+      "step": 315
+    },
+    {
+      "epoch": 2.0791208791208793,
+      "grad_norm": 0.4176221191883087,
+      "learning_rate": 0.00014944124168514411,
+      "loss": 0.5653,
+      "step": 316
+    },
+    {
+      "epoch": 2.085714285714286,
+      "grad_norm": 0.46824681758880615,
+      "learning_rate": 0.00014838137472283816,
+      "loss": 0.5551,
+      "step": 317
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": 0.4593164026737213,
+      "learning_rate": 0.00014732150776053217,
+      "loss": 0.5832,
+      "step": 318
+    },
+    {
+      "epoch": 2.098901098901099,
+      "grad_norm": 0.4187844395637512,
+      "learning_rate": 0.00014626164079822616,
+      "loss": 0.5358,
+      "step": 319
+    },
+    {
+      "epoch": 2.1054945054945056,
+      "grad_norm": 0.45083922147750854,
+      "learning_rate": 0.0001452017738359202,
+      "loss": 0.5912,
+      "step": 320
+    },
+    {
+      "epoch": 2.112087912087912,
+      "grad_norm": 0.39994415640830994,
+      "learning_rate": 0.0001441419068736142,
+      "loss": 0.5225,
+      "step": 321
+    },
+    {
+      "epoch": 2.1186813186813187,
+      "grad_norm": 0.4392825961112976,
+      "learning_rate": 0.0001430820399113082,
+      "loss": 0.4883,
+      "step": 322
+    },
+    {
+      "epoch": 2.1252747252747253,
+      "grad_norm": 0.4866951107978821,
+      "learning_rate": 0.00014202217294900224,
+      "loss": 0.5112,
+      "step": 323
+    },
+    {
+      "epoch": 2.131868131868132,
+      "grad_norm": 0.49154168367385864,
+      "learning_rate": 0.00014096230598669625,
+      "loss": 0.5608,
+      "step": 324
+    },
+    {
+      "epoch": 2.1384615384615384,
+      "grad_norm": 0.48593759536743164,
+      "learning_rate": 0.00013990243902439024,
+      "loss": 0.6128,
+      "step": 325
+    },
+    {
+      "epoch": 2.145054945054945,
+      "grad_norm": 0.48297789692878723,
+      "learning_rate": 0.00013884257206208425,
+      "loss": 0.4796,
+      "step": 326
+    },
+    {
+      "epoch": 2.1516483516483516,
+      "grad_norm": 0.4775952398777008,
+      "learning_rate": 0.0001377827050997783,
+      "loss": 0.5012,
+      "step": 327
+    },
+    {
+      "epoch": 2.158241758241758,
+      "grad_norm": 0.4983569085597992,
+      "learning_rate": 0.00013672283813747228,
+      "loss": 0.5573,
+      "step": 328
+    },
+    {
+      "epoch": 2.1648351648351647,
+      "grad_norm": 0.4817213714122772,
+      "learning_rate": 0.0001356629711751663,
+      "loss": 0.5503,
+      "step": 329
+    },
+    {
+      "epoch": 2.1714285714285713,
+      "grad_norm": 0.4505611062049866,
+      "learning_rate": 0.00013460310421286033,
+      "loss": 0.5458,
+      "step": 330
+    },
+    {
+      "epoch": 2.178021978021978,
+      "grad_norm": 0.4732796549797058,
+      "learning_rate": 0.00013354323725055432,
+      "loss": 0.5078,
+      "step": 331
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 0.4510941803455353,
+      "learning_rate": 0.00013248337028824833,
+      "loss": 0.5108,
+      "step": 332
+    },
+    {
+      "epoch": 2.1912087912087914,
+      "grad_norm": 0.5138033628463745,
+      "learning_rate": 0.00013142350332594237,
+      "loss": 0.5883,
+      "step": 333
+    },
+    {
+      "epoch": 2.197802197802198,
+      "grad_norm": 0.44492408633232117,
+      "learning_rate": 0.00013036363636363636,
+      "loss": 0.5029,
+      "step": 334
+    },
+    {
+      "epoch": 2.2043956043956046,
+      "grad_norm": 0.48559048771858215,
+      "learning_rate": 0.00012930376940133037,
+      "loss": 0.6139,
+      "step": 335
+    },
+    {
+      "epoch": 2.210989010989011,
+      "grad_norm": 0.4987350404262543,
+      "learning_rate": 0.0001282439024390244,
+      "loss": 0.5149,
+      "step": 336
+    },
+    {
+      "epoch": 2.2175824175824177,
+      "grad_norm": 0.4999798536300659,
+      "learning_rate": 0.0001271840354767184,
+      "loss": 0.5593,
+      "step": 337
+    },
+    {
+      "epoch": 2.2241758241758243,
+      "grad_norm": 0.4927052855491638,
+      "learning_rate": 0.0001261241685144124,
+      "loss": 0.5782,
+      "step": 338
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 0.4854503571987152,
+      "learning_rate": 0.00012506430155210645,
+      "loss": 0.5479,
+      "step": 339
+    },
+    {
+      "epoch": 2.2373626373626374,
+      "grad_norm": 0.4964471757411957,
+      "learning_rate": 0.00012400443458980044,
+      "loss": 0.5526,
+      "step": 340
+    },
+    {
+      "epoch": 2.243956043956044,
+      "grad_norm": 0.5352777242660522,
+      "learning_rate": 0.00012294456762749445,
+      "loss": 0.5871,
+      "step": 341
+    },
+    {
+      "epoch": 2.2505494505494505,
+      "grad_norm": 0.523512065410614,
+      "learning_rate": 0.00012188470066518848,
+      "loss": 0.5555,
+      "step": 342
+    },
+    {
+      "epoch": 2.257142857142857,
+      "grad_norm": 0.5086607336997986,
+      "learning_rate": 0.00012082483370288248,
+      "loss": 0.5613,
+      "step": 343
+    },
+    {
+      "epoch": 2.2637362637362637,
+      "grad_norm": 0.4900534152984619,
+      "learning_rate": 0.0001197649667405765,
+      "loss": 0.5573,
+      "step": 344
+    },
+    {
+      "epoch": 2.2703296703296703,
+      "grad_norm": 0.4950725734233856,
+      "learning_rate": 0.00011870509977827052,
+      "loss": 0.595,
+      "step": 345
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": 0.5022088289260864,
+      "learning_rate": 0.00011764523281596453,
+      "loss": 0.5874,
+      "step": 346
+    },
+    {
+      "epoch": 2.2835164835164834,
+      "grad_norm": 0.45746737718582153,
+      "learning_rate": 0.00011658536585365853,
+      "loss": 0.4917,
+      "step": 347
+    },
+    {
+      "epoch": 2.29010989010989,
+      "grad_norm": 0.5075504183769226,
+      "learning_rate": 0.00011552549889135256,
+      "loss": 0.5384,
+      "step": 348
+    },
+    {
+      "epoch": 2.2967032967032965,
+      "grad_norm": 0.5442312359809875,
+      "learning_rate": 0.00011446563192904658,
+      "loss": 0.4812,
+      "step": 349
+    },
+    {
+      "epoch": 2.303296703296703,
+      "grad_norm": 0.5608155131340027,
+      "learning_rate": 0.00011340576496674058,
+      "loss": 0.6096,
+      "step": 350
+    },
+    {
+      "epoch": 2.3098901098901097,
+      "grad_norm": 0.5366541147232056,
+      "learning_rate": 0.0001123458980044346,
+      "loss": 0.5106,
+      "step": 351
+    },
+    {
+      "epoch": 2.3164835164835162,
+      "grad_norm": 0.49404338002204895,
+      "learning_rate": 0.0001112860310421286,
+      "loss": 0.5278,
+      "step": 352
+    },
+    {
+      "epoch": 2.3230769230769233,
+      "grad_norm": 0.6068124175071716,
+      "learning_rate": 0.00011022616407982262,
+      "loss": 0.6571,
+      "step": 353
+    },
+    {
+      "epoch": 2.32967032967033,
+      "grad_norm": 0.5820615887641907,
+      "learning_rate": 0.00010916629711751664,
+      "loss": 0.581,
+      "step": 354
+    },
+    {
+      "epoch": 2.3362637362637364,
+      "grad_norm": 0.5663152933120728,
+      "learning_rate": 0.00010810643015521064,
+      "loss": 0.5844,
+      "step": 355
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 0.5166468620300293,
+      "learning_rate": 0.00010704656319290466,
+      "loss": 0.5552,
+      "step": 356
+    },
+    {
+      "epoch": 2.3494505494505495,
+      "grad_norm": 0.5312271118164062,
+      "learning_rate": 0.00010598669623059868,
+      "loss": 0.5455,
+      "step": 357
+    },
+    {
+      "epoch": 2.356043956043956,
+      "grad_norm": 0.5037778615951538,
+      "learning_rate": 0.00010492682926829268,
+      "loss": 0.5654,
+      "step": 358
+    },
+    {
+      "epoch": 2.3626373626373627,
+      "grad_norm": 0.49427491426467896,
+      "learning_rate": 0.0001038669623059867,
+      "loss": 0.5594,
+      "step": 359
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 0.5866952538490295,
+      "learning_rate": 0.00010280709534368071,
+      "loss": 0.5496,
+      "step": 360
+    },
+    {
+      "epoch": 2.375824175824176,
+      "grad_norm": 0.49420681595802307,
+      "learning_rate": 0.00010174722838137472,
+      "loss": 0.5635,
+      "step": 361
+    },
+    {
+      "epoch": 2.3824175824175824,
+      "grad_norm": 0.5386004447937012,
+      "learning_rate": 0.00010068736141906874,
+      "loss": 0.4676,
+      "step": 362
+    },
+    {
+      "epoch": 2.389010989010989,
+      "grad_norm": 0.537954568862915,
+      "learning_rate": 9.962749445676275e-05,
+      "loss": 0.5089,
+      "step": 363
+    },
+    {
+      "epoch": 2.3956043956043955,
+      "grad_norm": 0.5067974328994751,
+      "learning_rate": 9.856762749445677e-05,
+      "loss": 0.4888,
+      "step": 364
+    },
+    {
+      "epoch": 2.402197802197802,
+      "grad_norm": 0.5251851677894592,
+      "learning_rate": 9.750776053215078e-05,
+      "loss": 0.5792,
+      "step": 365
+    },
+    {
+      "epoch": 2.4087912087912087,
+      "grad_norm": 0.4998987019062042,
+      "learning_rate": 9.644789356984479e-05,
+      "loss": 0.4791,
+      "step": 366
+    },
+    {
+      "epoch": 2.4153846153846152,
+      "grad_norm": 0.48381221294403076,
+      "learning_rate": 9.53880266075388e-05,
+      "loss": 0.5432,
+      "step": 367
+    },
+    {
+      "epoch": 2.421978021978022,
+      "grad_norm": 0.49845534563064575,
+      "learning_rate": 9.432815964523282e-05,
+      "loss": 0.5555,
+      "step": 368
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.5069863200187683,
+      "learning_rate": 9.326829268292683e-05,
+      "loss": 0.5123,
+      "step": 369
+    },
+    {
+      "epoch": 2.4351648351648354,
+      "grad_norm": 0.5241045951843262,
+      "learning_rate": 9.220842572062085e-05,
+      "loss": 0.558,
+      "step": 370
+    },
+    {
+      "epoch": 2.441758241758242,
+      "grad_norm": 0.5024011135101318,
+      "learning_rate": 9.114855875831485e-05,
+      "loss": 0.5578,
+      "step": 371
+    },
+    {
+      "epoch": 2.4483516483516485,
+      "grad_norm": 0.483919620513916,
+      "learning_rate": 9.008869179600887e-05,
+      "loss": 0.5306,
+      "step": 372
+    },
+    {
+      "epoch": 2.454945054945055,
+      "grad_norm": 0.49662140011787415,
+      "learning_rate": 8.902882483370289e-05,
+      "loss": 0.6093,
+      "step": 373
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.4392881691455841,
+      "learning_rate": 8.796895787139689e-05,
+      "loss": 0.4936,
+      "step": 374
+    },
+    {
+      "epoch": 2.4681318681318682,
+      "grad_norm": 0.538955569267273,
+      "learning_rate": 8.690909090909091e-05,
+      "loss": 0.6058,
+      "step": 375
+    },
+    {
+      "epoch": 2.474725274725275,
+      "grad_norm": 0.4928183853626251,
+      "learning_rate": 8.584922394678493e-05,
+      "loss": 0.591,
+      "step": 376
+    },
+    {
+      "epoch": 2.4813186813186814,
+      "grad_norm": 0.5093295574188232,
+      "learning_rate": 8.478935698447894e-05,
+      "loss": 0.4802,
+      "step": 377
+    },
+    {
+      "epoch": 2.487912087912088,
+      "grad_norm": 0.5130084753036499,
+      "learning_rate": 8.372949002217296e-05,
+      "loss": 0.5445,
+      "step": 378
+    },
+    {
+      "epoch": 2.4945054945054945,
+      "grad_norm": 0.4813501834869385,
+      "learning_rate": 8.266962305986697e-05,
+      "loss": 0.431,
+      "step": 379
+    },
+    {
+      "epoch": 2.501098901098901,
+      "grad_norm": 0.5460867285728455,
+      "learning_rate": 8.160975609756098e-05,
+      "loss": 0.5782,
+      "step": 380
+    },
+    {
+      "epoch": 2.5076923076923077,
+      "grad_norm": 0.5475112795829773,
+      "learning_rate": 8.0549889135255e-05,
+      "loss": 0.6434,
+      "step": 381
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.4766271412372589,
+      "learning_rate": 7.9490022172949e-05,
+      "loss": 0.5384,
+      "step": 382
+    },
+    {
+      "epoch": 2.520879120879121,
+      "grad_norm": 0.48498964309692383,
+      "learning_rate": 7.843015521064302e-05,
+      "loss": 0.5401,
+      "step": 383
+    },
+    {
+      "epoch": 2.5274725274725274,
+      "grad_norm": 0.49676525592803955,
+      "learning_rate": 7.737028824833704e-05,
+      "loss": 0.5575,
+      "step": 384
+    },
+    {
+      "epoch": 2.534065934065934,
+      "grad_norm": 0.5234948396682739,
+      "learning_rate": 7.631042128603104e-05,
+      "loss": 0.5575,
+      "step": 385
+    },
+    {
+      "epoch": 2.5406593406593405,
+      "grad_norm": 0.47666624188423157,
+      "learning_rate": 7.525055432372506e-05,
+      "loss": 0.5514,
+      "step": 386
+    },
+    {
+      "epoch": 2.547252747252747,
+      "grad_norm": 0.5363499522209167,
+      "learning_rate": 7.419068736141908e-05,
+      "loss": 0.5681,
+      "step": 387
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 0.5204386711120605,
+      "learning_rate": 7.313082039911308e-05,
+      "loss": 0.5238,
+      "step": 388
+    },
+    {
+      "epoch": 2.5604395604395602,
+      "grad_norm": 0.47873154282569885,
+      "learning_rate": 7.20709534368071e-05,
+      "loss": 0.5724,
+      "step": 389
+    },
+    {
+      "epoch": 2.567032967032967,
+      "grad_norm": 0.4853995740413666,
+      "learning_rate": 7.101108647450112e-05,
+      "loss": 0.4805,
+      "step": 390
+    },
+    {
+      "epoch": 2.5736263736263734,
+      "grad_norm": 0.5275874733924866,
+      "learning_rate": 6.995121951219512e-05,
+      "loss": 0.5646,
+      "step": 391
+    },
+    {
+      "epoch": 2.5802197802197804,
+      "grad_norm": 0.5434504151344299,
+      "learning_rate": 6.889135254988915e-05,
+      "loss": 0.5322,
+      "step": 392
+    },
+    {
+      "epoch": 2.586813186813187,
+      "grad_norm": 0.5450798273086548,
+      "learning_rate": 6.783148558758315e-05,
+      "loss": 0.5446,
+      "step": 393
+    },
+    {
+      "epoch": 2.5934065934065935,
+      "grad_norm": 0.4962395429611206,
+      "learning_rate": 6.677161862527716e-05,
+      "loss": 0.563,
+      "step": 394
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.5108164548873901,
+      "learning_rate": 6.571175166297119e-05,
+      "loss": 0.5763,
+      "step": 395
+    },
+    {
+      "epoch": 2.6065934065934067,
+      "grad_norm": 0.5823172330856323,
+      "learning_rate": 6.465188470066519e-05,
+      "loss": 0.5175,
+      "step": 396
+    },
+    {
+      "epoch": 2.6131868131868132,
+      "grad_norm": 0.5125748515129089,
+      "learning_rate": 6.35920177383592e-05,
+      "loss": 0.5524,
+      "step": 397
+    },
+    {
+      "epoch": 2.61978021978022,
+      "grad_norm": 0.5462682843208313,
+      "learning_rate": 6.253215077605323e-05,
+      "loss": 0.5007,
+      "step": 398
+    },
+    {
+      "epoch": 2.6263736263736264,
+      "grad_norm": 0.5074661374092102,
+      "learning_rate": 6.147228381374723e-05,
+      "loss": 0.5074,
+      "step": 399
+    },
+    {
+      "epoch": 2.632967032967033,
+      "grad_norm": 0.5667728781700134,
+      "learning_rate": 6.041241685144124e-05,
+      "loss": 0.6082,
+      "step": 400
+    },
+    {
+      "epoch": 2.6395604395604395,
+      "grad_norm": 0.4912700653076172,
+      "learning_rate": 5.935254988913526e-05,
+      "loss": 0.4778,
+      "step": 401
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": 0.5548485517501831,
+      "learning_rate": 5.829268292682927e-05,
+      "loss": 0.5075,
+      "step": 402
+    },
+    {
+      "epoch": 2.6527472527472526,
+      "grad_norm": 0.6190904378890991,
+      "learning_rate": 5.723281596452329e-05,
+      "loss": 0.5975,
+      "step": 403
+    },
+    {
+      "epoch": 2.659340659340659,
+      "grad_norm": 0.5317597389221191,
+      "learning_rate": 5.61729490022173e-05,
+      "loss": 0.5658,
+      "step": 404
+    },
+    {
+      "epoch": 2.665934065934066,
+      "grad_norm": 0.5087029933929443,
+      "learning_rate": 5.511308203991131e-05,
+      "loss": 0.5842,
+      "step": 405
+    },
+    {
+      "epoch": 2.672527472527473,
+      "grad_norm": 0.5105840563774109,
+      "learning_rate": 5.405321507760532e-05,
+      "loss": 0.5218,
+      "step": 406
+    },
+    {
+      "epoch": 2.6791208791208794,
+      "grad_norm": 0.6558890342712402,
+      "learning_rate": 5.299334811529934e-05,
+      "loss": 0.4973,
+      "step": 407
+    },
+    {
+      "epoch": 2.685714285714286,
+      "grad_norm": 0.5352252125740051,
+      "learning_rate": 5.193348115299335e-05,
+      "loss": 0.4684,
+      "step": 408
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 0.5125372409820557,
+      "learning_rate": 5.087361419068736e-05,
+      "loss": 0.6464,
+      "step": 409
+    },
+    {
+      "epoch": 2.698901098901099,
+      "grad_norm": 0.5604701042175293,
+      "learning_rate": 4.9813747228381376e-05,
+      "loss": 0.5537,
+      "step": 410
+    },
+    {
+      "epoch": 2.7054945054945057,
+      "grad_norm": 0.4909667372703552,
+      "learning_rate": 4.875388026607539e-05,
+      "loss": 0.5354,
+      "step": 411
+    },
+    {
+      "epoch": 2.7120879120879122,
+      "grad_norm": 0.54693204164505,
+      "learning_rate": 4.76940133037694e-05,
+      "loss": 0.5119,
+      "step": 412
+    },
+    {
+      "epoch": 2.718681318681319,
+      "grad_norm": 0.5739659070968628,
+      "learning_rate": 4.663414634146342e-05,
+      "loss": 0.5889,
+      "step": 413
+    },
+    {
+      "epoch": 2.7252747252747254,
+      "grad_norm": 0.5877783298492432,
+      "learning_rate": 4.5574279379157423e-05,
+      "loss": 0.5631,
+      "step": 414
+    },
+    {
+      "epoch": 2.731868131868132,
+      "grad_norm": 0.5598376393318176,
+      "learning_rate": 4.4514412416851444e-05,
+      "loss": 0.5262,
+      "step": 415
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "grad_norm": 0.5463292002677917,
+      "learning_rate": 4.345454545454546e-05,
+      "loss": 0.5434,
+      "step": 416
+    },
+    {
+      "epoch": 2.745054945054945,
+      "grad_norm": 0.5373561978340149,
+      "learning_rate": 4.239467849223947e-05,
+      "loss": 0.5189,
+      "step": 417
+    },
+    {
+      "epoch": 2.7516483516483516,
+      "grad_norm": 0.5417702794075012,
+      "learning_rate": 4.1334811529933485e-05,
+      "loss": 0.5693,
+      "step": 418
+    },
+    {
+      "epoch": 2.758241758241758,
+      "grad_norm": 0.5045818090438843,
+      "learning_rate": 4.02749445676275e-05,
+      "loss": 0.5586,
+      "step": 419
+    },
+    {
+      "epoch": 2.764835164835165,
+      "grad_norm": 0.506395697593689,
+      "learning_rate": 3.921507760532151e-05,
+      "loss": 0.4578,
+      "step": 420
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.915149356584612e+17,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

seed1/checkpoint-420/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:857d075bed34d41b2ae6988957cb37bb1361ceed21a83af0add59814ad099c33
+size 6289