Upload folder using huggingface_hub

.gitattributes

@@ -54,3 +54,4 @@ checkpoint-330/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-345/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-360/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-390/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-390/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-3B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-390/adapter_config.json

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

checkpoint-390/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e9d9e5572e2530f1592234a517075f661761ea5d4436860d4b1ed8469a3f5e
+size 59933632

checkpoint-390/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-390/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-390/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ef9d5e419035984aefb3898b0d09ef04d1ac54ec2cd1bb1155dab9e55dd30b
+size 120166091

checkpoint-390/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0485284af66b3b81ca37e6e905603f5c3f748342583bb7379570c939df5d9f3c
+size 14645

checkpoint-390/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb1a2e28e4e52fd3cf71fcb3edc38d01a9f6973e00bf82bc271f077d9bd23ce
+size 1465

checkpoint-390/special_tokens_map.json

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

checkpoint-390/tokenizer.json

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

checkpoint-390/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-390/trainer_state.json

@@ -0,0 +1,2764 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.567032967032967,
+  "eval_steps": 500,
+  "global_step": 390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 1.7760576009750366,
+      "learning_rate": 0.0,
+      "loss": 2.8624,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 1.627739667892456,
+      "learning_rate": 4e-05,
+      "loss": 2.7707,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 2.411036252975464,
+      "learning_rate": 8e-05,
+      "loss": 3.0115,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 1.5725748538970947,
+      "learning_rate": 0.00012,
+      "loss": 2.578,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 2.3334898948669434,
+      "learning_rate": 0.00016,
+      "loss": 2.8116,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 2.7522525787353516,
+      "learning_rate": 0.0002,
+      "loss": 2.8591,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 2.1036670207977295,
+      "learning_rate": 0.00019955654101995565,
+      "loss": 1.6592,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 1.8711436986923218,
+      "learning_rate": 0.00019911308203991133,
+      "loss": 1.628,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 0.8910020589828491,
+      "learning_rate": 0.00019866962305986697,
+      "loss": 1.2578,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 1.2549653053283691,
+      "learning_rate": 0.00019822616407982261,
+      "loss": 1.2032,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 1.1423015594482422,
+      "learning_rate": 0.00019778270509977829,
+      "loss": 1.3174,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.6086552143096924,
+      "learning_rate": 0.00019733924611973393,
+      "loss": 1.0803,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.38326704502105713,
+      "learning_rate": 0.0001968957871396896,
+      "loss": 1.0704,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.5326745510101318,
+      "learning_rate": 0.00019645232815964525,
+      "loss": 1.0406,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.5318218469619751,
+      "learning_rate": 0.00019600886917960092,
+      "loss": 1.1875,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.4647858440876007,
+      "learning_rate": 0.00019556541019955653,
+      "loss": 1.0578,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.4215516448020935,
+      "learning_rate": 0.0001951219512195122,
+      "loss": 0.8499,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.3335304856300354,
+      "learning_rate": 0.00019467849223946785,
+      "loss": 0.9383,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.3218725621700287,
+      "learning_rate": 0.00019423503325942352,
+      "loss": 0.7817,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.4266487658023834,
+      "learning_rate": 0.00019379157427937917,
+      "loss": 0.9411,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.38664567470550537,
+      "learning_rate": 0.00019334811529933484,
+      "loss": 0.9421,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.38386937975883484,
+      "learning_rate": 0.00019290465631929045,
+      "loss": 0.89,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.34860938787460327,
+      "learning_rate": 0.00019246119733924613,
+      "loss": 1.023,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.36557498574256897,
+      "learning_rate": 0.00019201773835920177,
+      "loss": 1.1004,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.35893023014068604,
+      "learning_rate": 0.00019157427937915744,
+      "loss": 1.0868,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.333647757768631,
+      "learning_rate": 0.00019113082039911309,
+      "loss": 0.8831,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.3089407980442047,
+      "learning_rate": 0.00019068736141906876,
+      "loss": 0.9126,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.3301669657230377,
+      "learning_rate": 0.0001902439024390244,
+      "loss": 0.9857,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.2866484522819519,
+      "learning_rate": 0.00018980044345898005,
+      "loss": 1.0487,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.3685723543167114,
+      "learning_rate": 0.00018935698447893572,
+      "loss": 1.1583,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.36198097467422485,
+      "learning_rate": 0.00018891352549889136,
+      "loss": 1.1913,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.36270424723625183,
+      "learning_rate": 0.00018847006651884703,
+      "loss": 0.9796,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.35049617290496826,
+      "learning_rate": 0.00018802660753880268,
+      "loss": 1.0984,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.30711936950683594,
+      "learning_rate": 0.00018758314855875832,
+      "loss": 0.8514,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.3361266553401947,
+      "learning_rate": 0.00018713968957871397,
+      "loss": 0.7835,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.31940892338752747,
+      "learning_rate": 0.00018669623059866964,
+      "loss": 0.9101,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.32473820447921753,
+      "learning_rate": 0.00018625277161862528,
+      "loss": 1.173,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.2708457410335541,
+      "learning_rate": 0.00018580931263858095,
+      "loss": 1.0028,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.35012125968933105,
+      "learning_rate": 0.0001853658536585366,
+      "loss": 0.9161,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.2810596525669098,
+      "learning_rate": 0.00018492239467849224,
+      "loss": 0.9089,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.326106458902359,
+      "learning_rate": 0.0001844789356984479,
+      "loss": 0.8728,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.2742505669593811,
+      "learning_rate": 0.00018403547671840356,
+      "loss": 0.9115,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.328368604183197,
+      "learning_rate": 0.0001835920177383592,
+      "loss": 0.9528,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.35647979378700256,
+      "learning_rate": 0.00018314855875831487,
+      "loss": 1.2276,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.4501672685146332,
+      "learning_rate": 0.00018270509977827052,
+      "loss": 1.2159,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.5152194499969482,
+      "learning_rate": 0.00018226164079822616,
+      "loss": 1.1993,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.26086127758026123,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.7308,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.34976181387901306,
+      "learning_rate": 0.00018137472283813748,
+      "loss": 1.0843,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.39914363622665405,
+      "learning_rate": 0.00018093126385809312,
+      "loss": 0.9755,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.33914342522621155,
+      "learning_rate": 0.0001804878048780488,
+      "loss": 1.0366,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.3376713693141937,
+      "learning_rate": 0.00018004434589800444,
+      "loss": 0.958,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.3070376515388489,
+      "learning_rate": 0.00017960088691796008,
+      "loss": 0.947,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.2706867754459381,
+      "learning_rate": 0.00017915742793791575,
+      "loss": 0.8023,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.3382069170475006,
+      "learning_rate": 0.0001787139689578714,
+      "loss": 0.9184,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.2898756265640259,
+      "learning_rate": 0.00017827050997782707,
+      "loss": 0.9894,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.3399081528186798,
+      "learning_rate": 0.00017782705099778271,
+      "loss": 0.9053,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.3918396830558777,
+      "learning_rate": 0.00017738359201773839,
+      "loss": 1.0006,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.35674360394477844,
+      "learning_rate": 0.000176940133037694,
+      "loss": 0.9065,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.31635716557502747,
+      "learning_rate": 0.00017649667405764967,
+      "loss": 0.8588,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.29990875720977783,
+      "learning_rate": 0.00017605321507760532,
+      "loss": 0.944,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.4008603096008301,
+      "learning_rate": 0.000175609756097561,
+      "loss": 0.9256,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.3022041916847229,
+      "learning_rate": 0.00017516629711751663,
+      "loss": 0.908,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.26360005140304565,
+      "learning_rate": 0.0001747228381374723,
+      "loss": 0.8749,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.3298325836658478,
+      "learning_rate": 0.00017427937915742792,
+      "loss": 1.1187,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.3574797511100769,
+      "learning_rate": 0.0001738359201773836,
+      "loss": 1.0554,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.32374486327171326,
+      "learning_rate": 0.00017339246119733924,
+      "loss": 0.8371,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.38102686405181885,
+      "learning_rate": 0.0001729490022172949,
+      "loss": 1.0452,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.30039891600608826,
+      "learning_rate": 0.00017250554323725056,
+      "loss": 0.6833,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.3794395327568054,
+      "learning_rate": 0.00017206208425720623,
+      "loss": 0.943,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.3144315779209137,
+      "learning_rate": 0.00017161862527716187,
+      "loss": 0.8897,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.3287697434425354,
+      "learning_rate": 0.00017117516629711752,
+      "loss": 0.7885,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.3307992219924927,
+      "learning_rate": 0.0001707317073170732,
+      "loss": 0.8951,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.31876420974731445,
+      "learning_rate": 0.00017028824833702883,
+      "loss": 1.0449,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.32964083552360535,
+      "learning_rate": 0.0001698447893569845,
+      "loss": 1.0146,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.3033060133457184,
+      "learning_rate": 0.00016940133037694015,
+      "loss": 0.9456,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.39799225330352783,
+      "learning_rate": 0.00016895787139689582,
+      "loss": 1.0701,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.3029780387878418,
+      "learning_rate": 0.00016851441241685144,
+      "loss": 1.0342,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.3820551633834839,
+      "learning_rate": 0.0001680709534368071,
+      "loss": 1.0372,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.2455594688653946,
+      "learning_rate": 0.00016762749445676275,
+      "loss": 0.8209,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.35084041953086853,
+      "learning_rate": 0.00016718403547671842,
+      "loss": 1.1386,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.4059063196182251,
+      "learning_rate": 0.00016674057649667407,
+      "loss": 1.0704,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.28880801796913147,
+      "learning_rate": 0.00016629711751662974,
+      "loss": 0.941,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.2802966833114624,
+      "learning_rate": 0.00016585365853658536,
+      "loss": 0.7446,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.3626139760017395,
+      "learning_rate": 0.00016541019955654103,
+      "loss": 1.2344,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.2894216775894165,
+      "learning_rate": 0.00016496674057649667,
+      "loss": 0.8722,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.33207154273986816,
+      "learning_rate": 0.00016452328159645234,
+      "loss": 0.8346,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.3496438264846802,
+      "learning_rate": 0.000164079822616408,
+      "loss": 0.9866,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.262410968542099,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.8781,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.33365076780319214,
+      "learning_rate": 0.0001631929046563193,
+      "loss": 0.9782,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.38833490014076233,
+      "learning_rate": 0.00016274944567627495,
+      "loss": 0.9261,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3653523325920105,
+      "learning_rate": 0.0001623059866962306,
+      "loss": 0.9241,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.3591654896736145,
+      "learning_rate": 0.00016186252771618626,
+      "loss": 0.8284,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.35526201128959656,
+      "learning_rate": 0.0001614190687361419,
+      "loss": 1.1674,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.3529767394065857,
+      "learning_rate": 0.00016097560975609758,
+      "loss": 0.9327,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.37259340286254883,
+      "learning_rate": 0.00016053215077605322,
+      "loss": 1.0421,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.3770660161972046,
+      "learning_rate": 0.00016008869179600887,
+      "loss": 0.9368,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.38265588879585266,
+      "learning_rate": 0.00015964523281596454,
+      "loss": 0.9695,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.336265504360199,
+      "learning_rate": 0.00015920177383592018,
+      "loss": 0.9045,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.2600400745868683,
+      "learning_rate": 0.00015875831485587586,
+      "loss": 0.7187,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.3092184364795685,
+      "learning_rate": 0.0001583148558758315,
+      "loss": 0.9763,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.31736651062965393,
+      "learning_rate": 0.00015787139689578714,
+      "loss": 0.7791,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.3679843246936798,
+      "learning_rate": 0.0001574279379157428,
+      "loss": 1.0813,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.4214973747730255,
+      "learning_rate": 0.00015698447893569846,
+      "loss": 0.8937,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.3891105353832245,
+      "learning_rate": 0.0001565410199556541,
+      "loss": 1.1075,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.3421161472797394,
+      "learning_rate": 0.00015609756097560978,
+      "loss": 1.0693,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.3559079170227051,
+      "learning_rate": 0.00015565410199556542,
+      "loss": 1.0473,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.3279852867126465,
+      "learning_rate": 0.00015521064301552106,
+      "loss": 1.0138,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.2687285244464874,
+      "learning_rate": 0.0001547671840354767,
+      "loss": 0.8871,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.29114097356796265,
+      "learning_rate": 0.00015432372505543238,
+      "loss": 0.8594,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.24637137353420258,
+      "learning_rate": 0.00015388026607538802,
+      "loss": 0.7653,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.31702902913093567,
+      "learning_rate": 0.0001534368070953437,
+      "loss": 1.0376,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.3365715742111206,
+      "learning_rate": 0.00015299334811529934,
+      "loss": 0.8419,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.24790500104427338,
+      "learning_rate": 0.00015254988913525498,
+      "loss": 0.7398,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.3369625508785248,
+      "learning_rate": 0.00015210643015521066,
+      "loss": 0.9242,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.30920329689979553,
+      "learning_rate": 0.0001516629711751663,
+      "loss": 0.9772,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.29591354727745056,
+      "learning_rate": 0.00015121951219512197,
+      "loss": 0.7697,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.3208312392234802,
+      "learning_rate": 0.00015077605321507762,
+      "loss": 0.9581,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.5094884037971497,
+      "learning_rate": 0.0001503325942350333,
+      "loss": 0.8935,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.31081950664520264,
+      "learning_rate": 0.0001498891352549889,
+      "loss": 0.906,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.3331546187400818,
+      "learning_rate": 0.00014944567627494458,
+      "loss": 0.881,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.3290092647075653,
+      "learning_rate": 0.00014900221729490022,
+      "loss": 0.8721,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.39708906412124634,
+      "learning_rate": 0.0001485587583148559,
+      "loss": 0.8596,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.39215579628944397,
+      "learning_rate": 0.00014811529933481154,
+      "loss": 1.0112,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.29857560992240906,
+      "learning_rate": 0.0001476718403547672,
+      "loss": 0.8623,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.3981504440307617,
+      "learning_rate": 0.00014722838137472282,
+      "loss": 1.0419,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.3211333155632019,
+      "learning_rate": 0.0001467849223946785,
+      "loss": 0.8397,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.36528724431991577,
+      "learning_rate": 0.00014634146341463414,
+      "loss": 0.9067,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.3442481756210327,
+      "learning_rate": 0.0001458980044345898,
+      "loss": 0.9582,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.6198445558547974,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.8014,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.27763301134109497,
+      "learning_rate": 0.00014501108647450113,
+      "loss": 0.8664,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.29709896445274353,
+      "learning_rate": 0.00014456762749445675,
+      "loss": 0.9891,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.31026434898376465,
+      "learning_rate": 0.00014412416851441242,
+      "loss": 1.0785,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.3447965681552887,
+      "learning_rate": 0.00014368070953436806,
+      "loss": 0.9222,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.32406720519065857,
+      "learning_rate": 0.00014323725055432373,
+      "loss": 1.1169,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.32064133882522583,
+      "learning_rate": 0.00014279379157427938,
+      "loss": 0.8784,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.35375720262527466,
+      "learning_rate": 0.00014235033259423505,
+      "loss": 0.8525,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.3214500844478607,
+      "learning_rate": 0.0001419068736141907,
+      "loss": 1.008,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.4631902575492859,
+      "learning_rate": 0.00014146341463414634,
+      "loss": 1.1509,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.38527289032936096,
+      "learning_rate": 0.000141019955654102,
+      "loss": 0.8499,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.3266928791999817,
+      "learning_rate": 0.00014057649667405765,
+      "loss": 0.8544,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.4089340567588806,
+      "learning_rate": 0.00014013303769401332,
+      "loss": 0.902,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.40980854630470276,
+      "learning_rate": 0.00013968957871396897,
+      "loss": 1.0606,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.2532408833503723,
+      "learning_rate": 0.00013924611973392464,
+      "loss": 0.7975,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.3033108413219452,
+      "learning_rate": 0.00013880266075388026,
+      "loss": 0.7529,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.27384066581726074,
+      "learning_rate": 0.00013835920177383593,
+      "loss": 0.9499,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.3576986789703369,
+      "learning_rate": 0.00013791574279379157,
+      "loss": 1.0271,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.43273797631263733,
+      "learning_rate": 0.00013747228381374724,
+      "loss": 1.0037,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.3956480622291565,
+      "learning_rate": 0.0001370288248337029,
+      "loss": 0.8517,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.3818497061729431,
+      "learning_rate": 0.00013658536585365856,
+      "loss": 0.7679,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.3871268332004547,
+      "learning_rate": 0.00013614190687361418,
+      "loss": 0.9611,
+      "step": 150
+    },
+    {
+      "epoch": 0.9956043956043956,
+      "grad_norm": 0.3284381926059723,
+      "learning_rate": 0.00013569844789356985,
+      "loss": 0.8844,
+      "step": 151
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.39170271158218384,
+      "learning_rate": 0.0001352549889135255,
+      "loss": 0.9012,
+      "step": 152
+    },
+    {
+      "epoch": 1.0065934065934066,
+      "grad_norm": 0.3957328498363495,
+      "learning_rate": 0.00013481152993348116,
+      "loss": 0.7093,
+      "step": 153
+    },
+    {
+      "epoch": 1.0131868131868131,
+      "grad_norm": 0.33722370862960815,
+      "learning_rate": 0.0001343680709534368,
+      "loss": 0.8372,
+      "step": 154
+    },
+    {
+      "epoch": 1.0197802197802197,
+      "grad_norm": 0.34621375799179077,
+      "learning_rate": 0.00013392461197339248,
+      "loss": 0.9421,
+      "step": 155
+    },
+    {
+      "epoch": 1.0263736263736263,
+      "grad_norm": 0.37840408086776733,
+      "learning_rate": 0.00013348115299334812,
+      "loss": 0.776,
+      "step": 156
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.2963997721672058,
+      "learning_rate": 0.00013303769401330377,
+      "loss": 0.7209,
+      "step": 157
+    },
+    {
+      "epoch": 1.0395604395604396,
+      "grad_norm": 0.2885771095752716,
+      "learning_rate": 0.00013259423503325944,
+      "loss": 0.8766,
+      "step": 158
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.3952380120754242,
+      "learning_rate": 0.00013215077605321509,
+      "loss": 0.8928,
+      "step": 159
+    },
+    {
+      "epoch": 1.0527472527472528,
+      "grad_norm": 0.5510688424110413,
+      "learning_rate": 0.00013170731707317076,
+      "loss": 1.1429,
+      "step": 160
+    },
+    {
+      "epoch": 1.0593406593406594,
+      "grad_norm": 0.3398037552833557,
+      "learning_rate": 0.0001312638580931264,
+      "loss": 0.8041,
+      "step": 161
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.42766690254211426,
+      "learning_rate": 0.00013082039911308205,
+      "loss": 0.8584,
+      "step": 162
+    },
+    {
+      "epoch": 1.0725274725274725,
+      "grad_norm": 0.32769519090652466,
+      "learning_rate": 0.0001303769401330377,
+      "loss": 0.8662,
+      "step": 163
+    },
+    {
+      "epoch": 1.079120879120879,
+      "grad_norm": 0.6417312026023865,
+      "learning_rate": 0.00012993348115299336,
+      "loss": 1.0259,
+      "step": 164
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.3797471821308136,
+      "learning_rate": 0.000129490022172949,
+      "loss": 0.8839,
+      "step": 165
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 0.3755091428756714,
+      "learning_rate": 0.00012904656319290468,
+      "loss": 0.9373,
+      "step": 166
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.3206093907356262,
+      "learning_rate": 0.00012860310421286032,
+      "loss": 0.8622,
+      "step": 167
+    },
+    {
+      "epoch": 1.1054945054945056,
+      "grad_norm": 0.32275456190109253,
+      "learning_rate": 0.00012815964523281597,
+      "loss": 0.629,
+      "step": 168
+    },
+    {
+      "epoch": 1.1120879120879121,
+      "grad_norm": 0.3738497197628021,
+      "learning_rate": 0.0001277161862527716,
+      "loss": 0.8694,
+      "step": 169
+    },
+    {
+      "epoch": 1.1186813186813187,
+      "grad_norm": 0.4368719160556793,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.9391,
+      "step": 170
+    },
+    {
+      "epoch": 1.1252747252747253,
+      "grad_norm": 0.42176002264022827,
+      "learning_rate": 0.00012682926829268293,
+      "loss": 0.8449,
+      "step": 171
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 0.488160103559494,
+      "learning_rate": 0.0001263858093126386,
+      "loss": 0.9092,
+      "step": 172
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 0.350964218378067,
+      "learning_rate": 0.00012594235033259424,
+      "loss": 0.8073,
+      "step": 173
+    },
+    {
+      "epoch": 1.145054945054945,
+      "grad_norm": 0.3741450011730194,
+      "learning_rate": 0.00012549889135254989,
+      "loss": 0.9783,
+      "step": 174
+    },
+    {
+      "epoch": 1.1516483516483516,
+      "grad_norm": 0.34723031520843506,
+      "learning_rate": 0.00012505543237250553,
+      "loss": 0.8514,
+      "step": 175
+    },
+    {
+      "epoch": 1.1582417582417581,
+      "grad_norm": 0.45587000250816345,
+      "learning_rate": 0.0001246119733924612,
+      "loss": 0.9958,
+      "step": 176
+    },
+    {
+      "epoch": 1.164835164835165,
+      "grad_norm": 0.408667653799057,
+      "learning_rate": 0.00012416851441241685,
+      "loss": 0.8807,
+      "step": 177
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 0.4318036437034607,
+      "learning_rate": 0.00012372505543237252,
+      "loss": 0.7479,
+      "step": 178
+    },
+    {
+      "epoch": 1.178021978021978,
+      "grad_norm": 0.3212646543979645,
+      "learning_rate": 0.00012328159645232816,
+      "loss": 0.7516,
+      "step": 179
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.44655075669288635,
+      "learning_rate": 0.0001228381374722838,
+      "loss": 0.8449,
+      "step": 180
+    },
+    {
+      "epoch": 1.1912087912087912,
+      "grad_norm": 0.5123524069786072,
+      "learning_rate": 0.00012239467849223948,
+      "loss": 0.7861,
+      "step": 181
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 0.4530896246433258,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.9505,
+      "step": 182
+    },
+    {
+      "epoch": 1.2043956043956043,
+      "grad_norm": 0.4333910644054413,
+      "learning_rate": 0.00012150776053215078,
+      "loss": 0.5938,
+      "step": 183
+    },
+    {
+      "epoch": 1.210989010989011,
+      "grad_norm": 0.44526106119155884,
+      "learning_rate": 0.00012106430155210644,
+      "loss": 0.643,
+      "step": 184
+    },
+    {
+      "epoch": 1.2175824175824177,
+      "grad_norm": 0.5061396956443787,
+      "learning_rate": 0.0001206208425720621,
+      "loss": 0.9521,
+      "step": 185
+    },
+    {
+      "epoch": 1.2241758241758243,
+      "grad_norm": 0.4099973738193512,
+      "learning_rate": 0.00012017738359201774,
+      "loss": 0.8654,
+      "step": 186
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.49964645504951477,
+      "learning_rate": 0.0001197339246119734,
+      "loss": 1.0918,
+      "step": 187
+    },
+    {
+      "epoch": 1.2373626373626374,
+      "grad_norm": 0.46140962839126587,
+      "learning_rate": 0.00011929046563192906,
+      "loss": 0.8441,
+      "step": 188
+    },
+    {
+      "epoch": 1.243956043956044,
+      "grad_norm": 0.4616827666759491,
+      "learning_rate": 0.00011884700665188471,
+      "loss": 0.9791,
+      "step": 189
+    },
+    {
+      "epoch": 1.2505494505494505,
+      "grad_norm": 0.4869212210178375,
+      "learning_rate": 0.00011840354767184036,
+      "loss": 0.9499,
+      "step": 190
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.42071664333343506,
+      "learning_rate": 0.00011796008869179602,
+      "loss": 0.9136,
+      "step": 191
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 0.47641825675964355,
+      "learning_rate": 0.00011751662971175166,
+      "loss": 0.7896,
+      "step": 192
+    },
+    {
+      "epoch": 1.2703296703296703,
+      "grad_norm": 0.47582077980041504,
+      "learning_rate": 0.00011707317073170732,
+      "loss": 0.9358,
+      "step": 193
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 0.4727775454521179,
+      "learning_rate": 0.00011662971175166298,
+      "loss": 0.8661,
+      "step": 194
+    },
+    {
+      "epoch": 1.2835164835164834,
+      "grad_norm": 0.41393131017684937,
+      "learning_rate": 0.00011618625277161863,
+      "loss": 0.6776,
+      "step": 195
+    },
+    {
+      "epoch": 1.2901098901098902,
+      "grad_norm": 0.4379728138446808,
+      "learning_rate": 0.00011574279379157429,
+      "loss": 0.8247,
+      "step": 196
+    },
+    {
+      "epoch": 1.2967032967032968,
+      "grad_norm": 0.5635690689086914,
+      "learning_rate": 0.00011529933481152995,
+      "loss": 0.9256,
+      "step": 197
+    },
+    {
+      "epoch": 1.3032967032967033,
+      "grad_norm": 0.3925686478614807,
+      "learning_rate": 0.00011485587583148558,
+      "loss": 0.7342,
+      "step": 198
+    },
+    {
+      "epoch": 1.30989010989011,
+      "grad_norm": 0.3573673963546753,
+      "learning_rate": 0.00011441241685144124,
+      "loss": 0.7671,
+      "step": 199
+    },
+    {
+      "epoch": 1.3164835164835165,
+      "grad_norm": 0.41582292318344116,
+      "learning_rate": 0.0001139689578713969,
+      "loss": 0.6863,
+      "step": 200
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 0.46710050106048584,
+      "learning_rate": 0.00011352549889135255,
+      "loss": 0.9075,
+      "step": 201
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 0.5143976211547852,
+      "learning_rate": 0.00011308203991130821,
+      "loss": 0.7918,
+      "step": 202
+    },
+    {
+      "epoch": 1.3362637362637364,
+      "grad_norm": 0.4758606553077698,
+      "learning_rate": 0.00011263858093126387,
+      "loss": 0.9227,
+      "step": 203
+    },
+    {
+      "epoch": 1.342857142857143,
+      "grad_norm": 0.5033617615699768,
+      "learning_rate": 0.00011219512195121953,
+      "loss": 0.7077,
+      "step": 204
+    },
+    {
+      "epoch": 1.3494505494505495,
+      "grad_norm": 0.4335341453552246,
+      "learning_rate": 0.00011175166297117516,
+      "loss": 0.9327,
+      "step": 205
+    },
+    {
+      "epoch": 1.3560439560439561,
+      "grad_norm": 0.4649682641029358,
+      "learning_rate": 0.00011130820399113082,
+      "loss": 0.6918,
+      "step": 206
+    },
+    {
+      "epoch": 1.3626373626373627,
+      "grad_norm": 0.5441789031028748,
+      "learning_rate": 0.00011086474501108647,
+      "loss": 0.8769,
+      "step": 207
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.4930907189846039,
+      "learning_rate": 0.00011042128603104213,
+      "loss": 0.7457,
+      "step": 208
+    },
+    {
+      "epoch": 1.3758241758241758,
+      "grad_norm": 0.5102672576904297,
+      "learning_rate": 0.00010997782705099779,
+      "loss": 0.9105,
+      "step": 209
+    },
+    {
+      "epoch": 1.3824175824175824,
+      "grad_norm": 0.5926874279975891,
+      "learning_rate": 0.00010953436807095345,
+      "loss": 0.8868,
+      "step": 210
+    },
+    {
+      "epoch": 1.389010989010989,
+      "grad_norm": 0.4858846664428711,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 1.0297,
+      "step": 211
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.5197011828422546,
+      "learning_rate": 0.00010864745011086475,
+      "loss": 0.8067,
+      "step": 212
+    },
+    {
+      "epoch": 1.402197802197802,
+      "grad_norm": 0.5156332850456238,
+      "learning_rate": 0.00010820399113082041,
+      "loss": 0.7277,
+      "step": 213
+    },
+    {
+      "epoch": 1.4087912087912087,
+      "grad_norm": 0.5321180820465088,
+      "learning_rate": 0.00010776053215077607,
+      "loss": 0.73,
+      "step": 214
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 0.5257755517959595,
+      "learning_rate": 0.00010731707317073172,
+      "loss": 0.7144,
+      "step": 215
+    },
+    {
+      "epoch": 1.421978021978022,
+      "grad_norm": 0.6032314896583557,
+      "learning_rate": 0.00010687361419068738,
+      "loss": 0.9976,
+      "step": 216
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.45169249176979065,
+      "learning_rate": 0.00010643015521064301,
+      "loss": 0.8853,
+      "step": 217
+    },
+    {
+      "epoch": 1.4351648351648352,
+      "grad_norm": 0.5587141513824463,
+      "learning_rate": 0.00010598669623059867,
+      "loss": 1.0161,
+      "step": 218
+    },
+    {
+      "epoch": 1.4417582417582417,
+      "grad_norm": 0.5740451812744141,
+      "learning_rate": 0.00010554323725055433,
+      "loss": 0.863,
+      "step": 219
+    },
+    {
+      "epoch": 1.4483516483516483,
+      "grad_norm": 0.5098332166671753,
+      "learning_rate": 0.00010509977827050999,
+      "loss": 0.9388,
+      "step": 220
+    },
+    {
+      "epoch": 1.4549450549450549,
+      "grad_norm": 0.5485484004020691,
+      "learning_rate": 0.00010465631929046564,
+      "loss": 0.9548,
+      "step": 221
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.5916206240653992,
+      "learning_rate": 0.0001042128603104213,
+      "loss": 0.7981,
+      "step": 222
+    },
+    {
+      "epoch": 1.4681318681318682,
+      "grad_norm": 0.5425648093223572,
+      "learning_rate": 0.00010376940133037693,
+      "loss": 0.9014,
+      "step": 223
+    },
+    {
+      "epoch": 1.4747252747252748,
+      "grad_norm": 0.4891108572483063,
+      "learning_rate": 0.00010332594235033259,
+      "loss": 0.7525,
+      "step": 224
+    },
+    {
+      "epoch": 1.4813186813186814,
+      "grad_norm": 0.5040621161460876,
+      "learning_rate": 0.00010288248337028825,
+      "loss": 0.8638,
+      "step": 225
+    },
+    {
+      "epoch": 1.487912087912088,
+      "grad_norm": 0.6001086235046387,
+      "learning_rate": 0.0001024390243902439,
+      "loss": 0.7581,
+      "step": 226
+    },
+    {
+      "epoch": 1.4945054945054945,
+      "grad_norm": 0.5209348201751709,
+      "learning_rate": 0.00010199556541019956,
+      "loss": 0.9061,
+      "step": 227
+    },
+    {
+      "epoch": 1.501098901098901,
+      "grad_norm": 0.4675174653530121,
+      "learning_rate": 0.00010155210643015522,
+      "loss": 0.791,
+      "step": 228
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 0.4987642467021942,
+      "learning_rate": 0.00010110864745011087,
+      "loss": 0.8265,
+      "step": 229
+    },
+    {
+      "epoch": 1.5142857142857142,
+      "grad_norm": 0.46665462851524353,
+      "learning_rate": 0.00010066518847006652,
+      "loss": 0.7417,
+      "step": 230
+    },
+    {
+      "epoch": 1.5208791208791208,
+      "grad_norm": 0.49864843487739563,
+      "learning_rate": 0.00010022172949002218,
+      "loss": 0.8673,
+      "step": 231
+    },
+    {
+      "epoch": 1.5274725274725274,
+      "grad_norm": 0.4965820610523224,
+      "learning_rate": 9.977827050997783e-05,
+      "loss": 0.7783,
+      "step": 232
+    },
+    {
+      "epoch": 1.534065934065934,
+      "grad_norm": 0.49824950098991394,
+      "learning_rate": 9.933481152993348e-05,
+      "loss": 0.8426,
+      "step": 233
+    },
+    {
+      "epoch": 1.5406593406593405,
+      "grad_norm": 0.3843424916267395,
+      "learning_rate": 9.889135254988914e-05,
+      "loss": 0.5979,
+      "step": 234
+    },
+    {
+      "epoch": 1.5472527472527473,
+      "grad_norm": 0.4150248169898987,
+      "learning_rate": 9.84478935698448e-05,
+      "loss": 0.7875,
+      "step": 235
+    },
+    {
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.6643748879432678,
+      "learning_rate": 9.800443458980046e-05,
+      "loss": 0.873,
+      "step": 236
+    },
+    {
+      "epoch": 1.5604395604395604,
+      "grad_norm": 0.44432327151298523,
+      "learning_rate": 9.75609756097561e-05,
+      "loss": 0.7749,
+      "step": 237
+    },
+    {
+      "epoch": 1.567032967032967,
+      "grad_norm": 0.5393898487091064,
+      "learning_rate": 9.711751662971176e-05,
+      "loss": 0.8211,
+      "step": 238
+    },
+    {
+      "epoch": 1.5736263736263736,
+      "grad_norm": 0.5137620568275452,
+      "learning_rate": 9.667405764966742e-05,
+      "loss": 0.7194,
+      "step": 239
+    },
+    {
+      "epoch": 1.5802197802197804,
+      "grad_norm": 0.4648851752281189,
+      "learning_rate": 9.623059866962306e-05,
+      "loss": 0.6642,
+      "step": 240
+    },
+    {
+      "epoch": 1.586813186813187,
+      "grad_norm": 0.552086591720581,
+      "learning_rate": 9.578713968957872e-05,
+      "loss": 0.8506,
+      "step": 241
+    },
+    {
+      "epoch": 1.5934065934065935,
+      "grad_norm": 0.4900858700275421,
+      "learning_rate": 9.534368070953438e-05,
+      "loss": 0.9412,
+      "step": 242
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.483670175075531,
+      "learning_rate": 9.490022172949002e-05,
+      "loss": 0.8543,
+      "step": 243
+    },
+    {
+      "epoch": 1.6065934065934067,
+      "grad_norm": 0.48369061946868896,
+      "learning_rate": 9.445676274944568e-05,
+      "loss": 0.9233,
+      "step": 244
+    },
+    {
+      "epoch": 1.6131868131868132,
+      "grad_norm": 0.5265663266181946,
+      "learning_rate": 9.401330376940134e-05,
+      "loss": 0.794,
+      "step": 245
+    },
+    {
+      "epoch": 1.6197802197802198,
+      "grad_norm": 0.6508758664131165,
+      "learning_rate": 9.356984478935698e-05,
+      "loss": 0.8753,
+      "step": 246
+    },
+    {
+      "epoch": 1.6263736263736264,
+      "grad_norm": 0.4415636658668518,
+      "learning_rate": 9.312638580931264e-05,
+      "loss": 0.6766,
+      "step": 247
+    },
+    {
+      "epoch": 1.632967032967033,
+      "grad_norm": 0.4743358790874481,
+      "learning_rate": 9.26829268292683e-05,
+      "loss": 0.8493,
+      "step": 248
+    },
+    {
+      "epoch": 1.6395604395604395,
+      "grad_norm": 0.5788202285766602,
+      "learning_rate": 9.223946784922394e-05,
+      "loss": 0.8217,
+      "step": 249
+    },
+    {
+      "epoch": 1.646153846153846,
+      "grad_norm": 0.5858858227729797,
+      "learning_rate": 9.17960088691796e-05,
+      "loss": 0.9554,
+      "step": 250
+    },
+    {
+      "epoch": 1.6527472527472526,
+      "grad_norm": 0.5231529474258423,
+      "learning_rate": 9.135254988913526e-05,
+      "loss": 0.7351,
+      "step": 251
+    },
+    {
+      "epoch": 1.6593406593406592,
+      "grad_norm": 0.5712476968765259,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.8893,
+      "step": 252
+    },
+    {
+      "epoch": 1.6659340659340658,
+      "grad_norm": 0.5055428147315979,
+      "learning_rate": 9.046563192904656e-05,
+      "loss": 0.789,
+      "step": 253
+    },
+    {
+      "epoch": 1.6725274725274726,
+      "grad_norm": 0.47239893674850464,
+      "learning_rate": 9.002217294900222e-05,
+      "loss": 0.8292,
+      "step": 254
+    },
+    {
+      "epoch": 1.6791208791208792,
+      "grad_norm": 0.4644710421562195,
+      "learning_rate": 8.957871396895788e-05,
+      "loss": 0.7597,
+      "step": 255
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.5218475461006165,
+      "learning_rate": 8.913525498891354e-05,
+      "loss": 0.7757,
+      "step": 256
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.5673181414604187,
+      "learning_rate": 8.869179600886919e-05,
+      "loss": 0.8051,
+      "step": 257
+    },
+    {
+      "epoch": 1.6989010989010989,
+      "grad_norm": 0.5175471901893616,
+      "learning_rate": 8.824833702882484e-05,
+      "loss": 0.8824,
+      "step": 258
+    },
+    {
+      "epoch": 1.7054945054945057,
+      "grad_norm": 0.5638793110847473,
+      "learning_rate": 8.78048780487805e-05,
+      "loss": 0.8587,
+      "step": 259
+    },
+    {
+      "epoch": 1.7120879120879122,
+      "grad_norm": 0.5608967542648315,
+      "learning_rate": 8.736141906873615e-05,
+      "loss": 0.9257,
+      "step": 260
+    },
+    {
+      "epoch": 1.7186813186813188,
+      "grad_norm": 0.5013980865478516,
+      "learning_rate": 8.69179600886918e-05,
+      "loss": 0.7703,
+      "step": 261
+    },
+    {
+      "epoch": 1.7252747252747254,
+      "grad_norm": 0.5988092422485352,
+      "learning_rate": 8.647450110864746e-05,
+      "loss": 0.8994,
+      "step": 262
+    },
+    {
+      "epoch": 1.731868131868132,
+      "grad_norm": 0.5517004132270813,
+      "learning_rate": 8.603104212860311e-05,
+      "loss": 0.7151,
+      "step": 263
+    },
+    {
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.48853349685668945,
+      "learning_rate": 8.558758314855876e-05,
+      "loss": 0.9759,
+      "step": 264
+    },
+    {
+      "epoch": 1.745054945054945,
+      "grad_norm": 0.5336124300956726,
+      "learning_rate": 8.514412416851442e-05,
+      "loss": 1.0082,
+      "step": 265
+    },
+    {
+      "epoch": 1.7516483516483516,
+      "grad_norm": 0.5961282253265381,
+      "learning_rate": 8.470066518847007e-05,
+      "loss": 0.88,
+      "step": 266
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 0.5203912854194641,
+      "learning_rate": 8.425720620842572e-05,
+      "loss": 0.6812,
+      "step": 267
+    },
+    {
+      "epoch": 1.7648351648351648,
+      "grad_norm": 0.6138539910316467,
+      "learning_rate": 8.381374722838138e-05,
+      "loss": 0.9026,
+      "step": 268
+    },
+    {
+      "epoch": 1.7714285714285714,
+      "grad_norm": 0.6027534604072571,
+      "learning_rate": 8.337028824833703e-05,
+      "loss": 0.9873,
+      "step": 269
+    },
+    {
+      "epoch": 1.778021978021978,
+      "grad_norm": 0.4913184940814972,
+      "learning_rate": 8.292682926829268e-05,
+      "loss": 0.6914,
+      "step": 270
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 0.6246024966239929,
+      "learning_rate": 8.248337028824834e-05,
+      "loss": 0.8791,
+      "step": 271
+    },
+    {
+      "epoch": 1.791208791208791,
+      "grad_norm": 0.482337087392807,
+      "learning_rate": 8.2039911308204e-05,
+      "loss": 0.8333,
+      "step": 272
+    },
+    {
+      "epoch": 1.7978021978021979,
+      "grad_norm": 0.6155971884727478,
+      "learning_rate": 8.159645232815965e-05,
+      "loss": 1.0156,
+      "step": 273
+    },
+    {
+      "epoch": 1.8043956043956044,
+      "grad_norm": 0.43273109197616577,
+      "learning_rate": 8.11529933481153e-05,
+      "loss": 0.7059,
+      "step": 274
+    },
+    {
+      "epoch": 1.810989010989011,
+      "grad_norm": 0.4931391775608063,
+      "learning_rate": 8.070953436807095e-05,
+      "loss": 0.7598,
+      "step": 275
+    },
+    {
+      "epoch": 1.8175824175824176,
+      "grad_norm": 0.6000128388404846,
+      "learning_rate": 8.026607538802661e-05,
+      "loss": 0.7599,
+      "step": 276
+    },
+    {
+      "epoch": 1.8241758241758241,
+      "grad_norm": 0.6107720136642456,
+      "learning_rate": 7.982261640798227e-05,
+      "loss": 0.8721,
+      "step": 277
+    },
+    {
+      "epoch": 1.830769230769231,
+      "grad_norm": 0.6427117586135864,
+      "learning_rate": 7.937915742793793e-05,
+      "loss": 0.9309,
+      "step": 278
+    },
+    {
+      "epoch": 1.8373626373626375,
+      "grad_norm": 0.5098176598548889,
+      "learning_rate": 7.893569844789357e-05,
+      "loss": 0.8295,
+      "step": 279
+    },
+    {
+      "epoch": 1.843956043956044,
+      "grad_norm": 0.4736887812614441,
+      "learning_rate": 7.849223946784923e-05,
+      "loss": 0.7205,
+      "step": 280
+    },
+    {
+      "epoch": 1.8505494505494506,
+      "grad_norm": 0.6344575881958008,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 0.9811,
+      "step": 281
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.5645753145217896,
+      "learning_rate": 7.760532150776053e-05,
+      "loss": 0.6785,
+      "step": 282
+    },
+    {
+      "epoch": 1.8637362637362638,
+      "grad_norm": 0.4798728823661804,
+      "learning_rate": 7.716186252771619e-05,
+      "loss": 0.6676,
+      "step": 283
+    },
+    {
+      "epoch": 1.8703296703296703,
+      "grad_norm": 0.48211291432380676,
+      "learning_rate": 7.671840354767185e-05,
+      "loss": 0.7828,
+      "step": 284
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 0.5278794765472412,
+      "learning_rate": 7.627494456762749e-05,
+      "loss": 0.7416,
+      "step": 285
+    },
+    {
+      "epoch": 1.8835164835164835,
+      "grad_norm": 0.5028746128082275,
+      "learning_rate": 7.583148558758315e-05,
+      "loss": 0.6292,
+      "step": 286
+    },
+    {
+      "epoch": 1.89010989010989,
+      "grad_norm": 0.5608091950416565,
+      "learning_rate": 7.538802660753881e-05,
+      "loss": 0.7548,
+      "step": 287
+    },
+    {
+      "epoch": 1.8967032967032966,
+      "grad_norm": 0.6226504445075989,
+      "learning_rate": 7.494456762749445e-05,
+      "loss": 0.8782,
+      "step": 288
+    },
+    {
+      "epoch": 1.9032967032967032,
+      "grad_norm": 0.5175797939300537,
+      "learning_rate": 7.450110864745011e-05,
+      "loss": 0.8792,
+      "step": 289
+    },
+    {
+      "epoch": 1.9098901098901098,
+      "grad_norm": 0.42134514451026917,
+      "learning_rate": 7.405764966740577e-05,
+      "loss": 0.7574,
+      "step": 290
+    },
+    {
+      "epoch": 1.9164835164835163,
+      "grad_norm": 0.5301500558853149,
+      "learning_rate": 7.361419068736141e-05,
+      "loss": 0.8317,
+      "step": 291
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.6237330436706543,
+      "learning_rate": 7.317073170731707e-05,
+      "loss": 0.7418,
+      "step": 292
+    },
+    {
+      "epoch": 1.9296703296703297,
+      "grad_norm": 0.6518726944923401,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 1.0458,
+      "step": 293
+    },
+    {
+      "epoch": 1.9362637362637363,
+      "grad_norm": 0.5591306686401367,
+      "learning_rate": 7.228381374722837e-05,
+      "loss": 0.8401,
+      "step": 294
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 0.5810967683792114,
+      "learning_rate": 7.184035476718403e-05,
+      "loss": 0.8364,
+      "step": 295
+    },
+    {
+      "epoch": 1.9494505494505494,
+      "grad_norm": 0.5487116575241089,
+      "learning_rate": 7.139689578713969e-05,
+      "loss": 0.7712,
+      "step": 296
+    },
+    {
+      "epoch": 1.9560439560439562,
+      "grad_norm": 0.6465400457382202,
+      "learning_rate": 7.095343680709535e-05,
+      "loss": 0.8577,
+      "step": 297
+    },
+    {
+      "epoch": 1.9626373626373628,
+      "grad_norm": 0.5806722640991211,
+      "learning_rate": 7.0509977827051e-05,
+      "loss": 0.9107,
+      "step": 298
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 0.6059687733650208,
+      "learning_rate": 7.006651884700666e-05,
+      "loss": 0.8147,
+      "step": 299
+    },
+    {
+      "epoch": 1.975824175824176,
+      "grad_norm": 0.6416262984275818,
+      "learning_rate": 6.962305986696232e-05,
+      "loss": 0.7725,
+      "step": 300
+    },
+    {
+      "epoch": 1.9824175824175825,
+      "grad_norm": 0.5913785696029663,
+      "learning_rate": 6.917960088691796e-05,
+      "loss": 0.7343,
+      "step": 301
+    },
+    {
+      "epoch": 1.989010989010989,
+      "grad_norm": 0.49936139583587646,
+      "learning_rate": 6.873614190687362e-05,
+      "loss": 0.6181,
+      "step": 302
+    },
+    {
+      "epoch": 1.9956043956043956,
+      "grad_norm": 0.5001626014709473,
+      "learning_rate": 6.829268292682928e-05,
+      "loss": 0.7552,
+      "step": 303
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.623162567615509,
+      "learning_rate": 6.784922394678492e-05,
+      "loss": 0.7647,
+      "step": 304
+    },
+    {
+      "epoch": 2.0065934065934066,
+      "grad_norm": 0.5086246728897095,
+      "learning_rate": 6.740576496674058e-05,
+      "loss": 0.7998,
+      "step": 305
+    },
+    {
+      "epoch": 2.013186813186813,
+      "grad_norm": 0.5474497079849243,
+      "learning_rate": 6.696230598669624e-05,
+      "loss": 0.695,
+      "step": 306
+    },
+    {
+      "epoch": 2.0197802197802197,
+      "grad_norm": 0.5316715836524963,
+      "learning_rate": 6.651884700665188e-05,
+      "loss": 0.6837,
+      "step": 307
+    },
+    {
+      "epoch": 2.0263736263736263,
+      "grad_norm": 0.4834229648113251,
+      "learning_rate": 6.607538802660754e-05,
+      "loss": 0.8283,
+      "step": 308
+    },
+    {
+      "epoch": 2.032967032967033,
+      "grad_norm": 0.6220597624778748,
+      "learning_rate": 6.56319290465632e-05,
+      "loss": 0.8962,
+      "step": 309
+    },
+    {
+      "epoch": 2.0395604395604394,
+      "grad_norm": 0.5098103880882263,
+      "learning_rate": 6.518847006651884e-05,
+      "loss": 0.6478,
+      "step": 310
+    },
+    {
+      "epoch": 2.046153846153846,
+      "grad_norm": 0.5539897680282593,
+      "learning_rate": 6.47450110864745e-05,
+      "loss": 0.8605,
+      "step": 311
+    },
+    {
+      "epoch": 2.0527472527472526,
+      "grad_norm": 0.5447985529899597,
+      "learning_rate": 6.430155210643016e-05,
+      "loss": 0.8441,
+      "step": 312
+    },
+    {
+      "epoch": 2.059340659340659,
+      "grad_norm": 0.5799476504325867,
+      "learning_rate": 6.38580931263858e-05,
+      "loss": 0.7852,
+      "step": 313
+    },
+    {
+      "epoch": 2.065934065934066,
+      "grad_norm": 0.5092344284057617,
+      "learning_rate": 6.341463414634146e-05,
+      "loss": 0.5713,
+      "step": 314
+    },
+    {
+      "epoch": 2.0725274725274727,
+      "grad_norm": 0.6201569437980652,
+      "learning_rate": 6.297117516629712e-05,
+      "loss": 0.8749,
+      "step": 315
+    },
+    {
+      "epoch": 2.0791208791208793,
+      "grad_norm": 0.6235813498497009,
+      "learning_rate": 6.252771618625277e-05,
+      "loss": 0.663,
+      "step": 316
+    },
+    {
+      "epoch": 2.085714285714286,
+      "grad_norm": 0.5923457741737366,
+      "learning_rate": 6.208425720620842e-05,
+      "loss": 0.6611,
+      "step": 317
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": 0.6124222278594971,
+      "learning_rate": 6.164079822616408e-05,
+      "loss": 0.7197,
+      "step": 318
+    },
+    {
+      "epoch": 2.098901098901099,
+      "grad_norm": 0.5578252077102661,
+      "learning_rate": 6.119733924611974e-05,
+      "loss": 0.7826,
+      "step": 319
+    },
+    {
+      "epoch": 2.1054945054945056,
+      "grad_norm": 0.6830889582633972,
+      "learning_rate": 6.075388026607539e-05,
+      "loss": 0.7197,
+      "step": 320
+    },
+    {
+      "epoch": 2.112087912087912,
+      "grad_norm": 0.597091794013977,
+      "learning_rate": 6.031042128603105e-05,
+      "loss": 0.6783,
+      "step": 321
+    },
+    {
+      "epoch": 2.1186813186813187,
+      "grad_norm": 0.7658618092536926,
+      "learning_rate": 5.98669623059867e-05,
+      "loss": 0.8206,
+      "step": 322
+    },
+    {
+      "epoch": 2.1252747252747253,
+      "grad_norm": 0.6010746359825134,
+      "learning_rate": 5.942350332594236e-05,
+      "loss": 0.7703,
+      "step": 323
+    },
+    {
+      "epoch": 2.131868131868132,
+      "grad_norm": 0.5366610288619995,
+      "learning_rate": 5.898004434589801e-05,
+      "loss": 0.608,
+      "step": 324
+    },
+    {
+      "epoch": 2.1384615384615384,
+      "grad_norm": 0.5113595724105835,
+      "learning_rate": 5.853658536585366e-05,
+      "loss": 0.5216,
+      "step": 325
+    },
+    {
+      "epoch": 2.145054945054945,
+      "grad_norm": 0.697272777557373,
+      "learning_rate": 5.809312638580932e-05,
+      "loss": 0.7268,
+      "step": 326
+    },
+    {
+      "epoch": 2.1516483516483516,
+      "grad_norm": 0.646862804889679,
+      "learning_rate": 5.7649667405764975e-05,
+      "loss": 0.7088,
+      "step": 327
+    },
+    {
+      "epoch": 2.158241758241758,
+      "grad_norm": 0.5883638858795166,
+      "learning_rate": 5.720620842572062e-05,
+      "loss": 0.6224,
+      "step": 328
+    },
+    {
+      "epoch": 2.1648351648351647,
+      "grad_norm": 0.6262251734733582,
+      "learning_rate": 5.676274944567628e-05,
+      "loss": 0.6666,
+      "step": 329
+    },
+    {
+      "epoch": 2.1714285714285713,
+      "grad_norm": 0.6185147762298584,
+      "learning_rate": 5.6319290465631935e-05,
+      "loss": 0.6609,
+      "step": 330
+    },
+    {
+      "epoch": 2.178021978021978,
+      "grad_norm": 0.6790482997894287,
+      "learning_rate": 5.587583148558758e-05,
+      "loss": 0.7512,
+      "step": 331
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 0.6065536141395569,
+      "learning_rate": 5.543237250554324e-05,
+      "loss": 0.6666,
+      "step": 332
+    },
+    {
+      "epoch": 2.1912087912087914,
+      "grad_norm": 0.7000298500061035,
+      "learning_rate": 5.4988913525498895e-05,
+      "loss": 0.7296,
+      "step": 333
+    },
+    {
+      "epoch": 2.197802197802198,
+      "grad_norm": 0.6307154297828674,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.7144,
+      "step": 334
+    },
+    {
+      "epoch": 2.2043956043956046,
+      "grad_norm": 0.6317764520645142,
+      "learning_rate": 5.4101995565410204e-05,
+      "loss": 0.7384,
+      "step": 335
+    },
+    {
+      "epoch": 2.210989010989011,
+      "grad_norm": 0.559666633605957,
+      "learning_rate": 5.365853658536586e-05,
+      "loss": 0.5746,
+      "step": 336
+    },
+    {
+      "epoch": 2.2175824175824177,
+      "grad_norm": 0.6625390648841858,
+      "learning_rate": 5.3215077605321506e-05,
+      "loss": 0.8374,
+      "step": 337
+    },
+    {
+      "epoch": 2.2241758241758243,
+      "grad_norm": 0.5989534258842468,
+      "learning_rate": 5.2771618625277164e-05,
+      "loss": 0.6365,
+      "step": 338
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 0.6747904419898987,
+      "learning_rate": 5.232815964523282e-05,
+      "loss": 0.6462,
+      "step": 339
+    },
+    {
+      "epoch": 2.2373626373626374,
+      "grad_norm": 0.5615343451499939,
+      "learning_rate": 5.1884700665188466e-05,
+      "loss": 0.7342,
+      "step": 340
+    },
+    {
+      "epoch": 2.243956043956044,
+      "grad_norm": 0.6264040470123291,
+      "learning_rate": 5.1441241685144124e-05,
+      "loss": 0.7069,
+      "step": 341
+    },
+    {
+      "epoch": 2.2505494505494505,
+      "grad_norm": 0.6493216753005981,
+      "learning_rate": 5.099778270509978e-05,
+      "loss": 0.6655,
+      "step": 342
+    },
+    {
+      "epoch": 2.257142857142857,
+      "grad_norm": 0.7726837992668152,
+      "learning_rate": 5.0554323725055433e-05,
+      "loss": 0.803,
+      "step": 343
+    },
+    {
+      "epoch": 2.2637362637362637,
+      "grad_norm": 0.7679490447044373,
+      "learning_rate": 5.011086474501109e-05,
+      "loss": 0.5529,
+      "step": 344
+    },
+    {
+      "epoch": 2.2703296703296703,
+      "grad_norm": 0.683829665184021,
+      "learning_rate": 4.966740576496674e-05,
+      "loss": 0.6351,
+      "step": 345
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": 0.6780131459236145,
+      "learning_rate": 4.92239467849224e-05,
+      "loss": 0.7213,
+      "step": 346
+    },
+    {
+      "epoch": 2.2835164835164834,
+      "grad_norm": 0.7721289992332458,
+      "learning_rate": 4.878048780487805e-05,
+      "loss": 0.7425,
+      "step": 347
+    },
+    {
+      "epoch": 2.29010989010989,
+      "grad_norm": 0.5743035078048706,
+      "learning_rate": 4.833702882483371e-05,
+      "loss": 0.6277,
+      "step": 348
+    },
+    {
+      "epoch": 2.2967032967032965,
+      "grad_norm": 0.6229271292686462,
+      "learning_rate": 4.789356984478936e-05,
+      "loss": 0.798,
+      "step": 349
+    },
+    {
+      "epoch": 2.303296703296703,
+      "grad_norm": 0.5208544731140137,
+      "learning_rate": 4.745011086474501e-05,
+      "loss": 0.587,
+      "step": 350
+    },
+    {
+      "epoch": 2.3098901098901097,
+      "grad_norm": 0.7631279826164246,
+      "learning_rate": 4.700665188470067e-05,
+      "loss": 0.6937,
+      "step": 351
+    },
+    {
+      "epoch": 2.3164835164835162,
+      "grad_norm": 0.6805886626243591,
+      "learning_rate": 4.656319290465632e-05,
+      "loss": 0.7857,
+      "step": 352
+    },
+    {
+      "epoch": 2.3230769230769233,
+      "grad_norm": 0.5648025870323181,
+      "learning_rate": 4.611973392461197e-05,
+      "loss": 0.4774,
+      "step": 353
+    },
+    {
+      "epoch": 2.32967032967033,
+      "grad_norm": 0.6559226512908936,
+      "learning_rate": 4.567627494456763e-05,
+      "loss": 0.6166,
+      "step": 354
+    },
+    {
+      "epoch": 2.3362637362637364,
+      "grad_norm": 0.6404967904090881,
+      "learning_rate": 4.523281596452328e-05,
+      "loss": 0.5812,
+      "step": 355
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 0.7111555933952332,
+      "learning_rate": 4.478935698447894e-05,
+      "loss": 0.6562,
+      "step": 356
+    },
+    {
+      "epoch": 2.3494505494505495,
+      "grad_norm": 0.6145789623260498,
+      "learning_rate": 4.4345898004434597e-05,
+      "loss": 0.6396,
+      "step": 357
+    },
+    {
+      "epoch": 2.356043956043956,
+      "grad_norm": 0.6875724792480469,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 0.6657,
+      "step": 358
+    },
+    {
+      "epoch": 2.3626373626373627,
+      "grad_norm": 0.7203099131584167,
+      "learning_rate": 4.34589800443459e-05,
+      "loss": 0.6217,
+      "step": 359
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 0.6922796964645386,
+      "learning_rate": 4.301552106430156e-05,
+      "loss": 0.7715,
+      "step": 360
+    },
+    {
+      "epoch": 2.375824175824176,
+      "grad_norm": 0.7671994566917419,
+      "learning_rate": 4.257206208425721e-05,
+      "loss": 0.7853,
+      "step": 361
+    },
+    {
+      "epoch": 2.3824175824175824,
+      "grad_norm": 0.7448363900184631,
+      "learning_rate": 4.212860310421286e-05,
+      "loss": 0.5796,
+      "step": 362
+    },
+    {
+      "epoch": 2.389010989010989,
+      "grad_norm": 0.6881489157676697,
+      "learning_rate": 4.168514412416852e-05,
+      "loss": 0.7036,
+      "step": 363
+    },
+    {
+      "epoch": 2.3956043956043955,
+      "grad_norm": 0.7796825170516968,
+      "learning_rate": 4.124168514412417e-05,
+      "loss": 0.8383,
+      "step": 364
+    },
+    {
+      "epoch": 2.402197802197802,
+      "grad_norm": 0.8089492917060852,
+      "learning_rate": 4.0798226164079826e-05,
+      "loss": 0.7395,
+      "step": 365
+    },
+    {
+      "epoch": 2.4087912087912087,
+      "grad_norm": 0.6907708048820496,
+      "learning_rate": 4.035476718403548e-05,
+      "loss": 0.6379,
+      "step": 366
+    },
+    {
+      "epoch": 2.4153846153846152,
+      "grad_norm": 0.9457873702049255,
+      "learning_rate": 3.9911308203991135e-05,
+      "loss": 0.9187,
+      "step": 367
+    },
+    {
+      "epoch": 2.421978021978022,
+      "grad_norm": 0.761772871017456,
+      "learning_rate": 3.9467849223946786e-05,
+      "loss": 0.8554,
+      "step": 368
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.7692601680755615,
+      "learning_rate": 3.9024390243902444e-05,
+      "loss": 0.7953,
+      "step": 369
+    },
+    {
+      "epoch": 2.4351648351648354,
+      "grad_norm": 0.6602999567985535,
+      "learning_rate": 3.8580931263858095e-05,
+      "loss": 0.6455,
+      "step": 370
+    },
+    {
+      "epoch": 2.441758241758242,
+      "grad_norm": 0.7305328845977783,
+      "learning_rate": 3.8137472283813746e-05,
+      "loss": 0.603,
+      "step": 371
+    },
+    {
+      "epoch": 2.4483516483516485,
+      "grad_norm": 0.844531238079071,
+      "learning_rate": 3.7694013303769404e-05,
+      "loss": 0.7204,
+      "step": 372
+    },
+    {
+      "epoch": 2.454945054945055,
+      "grad_norm": 0.7686405777931213,
+      "learning_rate": 3.7250554323725055e-05,
+      "loss": 0.8078,
+      "step": 373
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.6386904120445251,
+      "learning_rate": 3.6807095343680706e-05,
+      "loss": 0.606,
+      "step": 374
+    },
+    {
+      "epoch": 2.4681318681318682,
+      "grad_norm": 0.8585508465766907,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.8089,
+      "step": 375
+    },
+    {
+      "epoch": 2.474725274725275,
+      "grad_norm": 0.6785935163497925,
+      "learning_rate": 3.5920177383592015e-05,
+      "loss": 0.6537,
+      "step": 376
+    },
+    {
+      "epoch": 2.4813186813186814,
+      "grad_norm": 0.5910032391548157,
+      "learning_rate": 3.547671840354767e-05,
+      "loss": 0.5658,
+      "step": 377
+    },
+    {
+      "epoch": 2.487912087912088,
+      "grad_norm": 0.8728800415992737,
+      "learning_rate": 3.503325942350333e-05,
+      "loss": 0.7586,
+      "step": 378
+    },
+    {
+      "epoch": 2.4945054945054945,
+      "grad_norm": 0.6362790465354919,
+      "learning_rate": 3.458980044345898e-05,
+      "loss": 0.6661,
+      "step": 379
+    },
+    {
+      "epoch": 2.501098901098901,
+      "grad_norm": 0.8050955533981323,
+      "learning_rate": 3.414634146341464e-05,
+      "loss": 0.7105,
+      "step": 380
+    },
+    {
+      "epoch": 2.5076923076923077,
+      "grad_norm": 0.7559526562690735,
+      "learning_rate": 3.370288248337029e-05,
+      "loss": 0.6963,
+      "step": 381
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.6788583993911743,
+      "learning_rate": 3.325942350332594e-05,
+      "loss": 0.7007,
+      "step": 382
+    },
+    {
+      "epoch": 2.520879120879121,
+      "grad_norm": 0.8417208790779114,
+      "learning_rate": 3.28159645232816e-05,
+      "loss": 0.7481,
+      "step": 383
+    },
+    {
+      "epoch": 2.5274725274725274,
+      "grad_norm": 0.568612277507782,
+      "learning_rate": 3.237250554323725e-05,
+      "loss": 0.6735,
+      "step": 384
+    },
+    {
+      "epoch": 2.534065934065934,
+      "grad_norm": 0.7989943623542786,
+      "learning_rate": 3.19290465631929e-05,
+      "loss": 0.6596,
+      "step": 385
+    },
+    {
+      "epoch": 2.5406593406593405,
+      "grad_norm": 0.7331807613372803,
+      "learning_rate": 3.148558758314856e-05,
+      "loss": 0.6264,
+      "step": 386
+    },
+    {
+      "epoch": 2.547252747252747,
+      "grad_norm": 0.8965657949447632,
+      "learning_rate": 3.104212860310421e-05,
+      "loss": 0.6325,
+      "step": 387
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 0.7124624848365784,
+      "learning_rate": 3.059866962305987e-05,
+      "loss": 0.5838,
+      "step": 388
+    },
+    {
+      "epoch": 2.5604395604395602,
+      "grad_norm": 0.6805167198181152,
+      "learning_rate": 3.0155210643015524e-05,
+      "loss": 0.6264,
+      "step": 389
+    },
+    {
+      "epoch": 2.567032967032967,
+      "grad_norm": 0.7305182218551636,
+      "learning_rate": 2.971175166297118e-05,
+      "loss": 0.627,
+      "step": 390
+    }
+  ],
+  "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": 6.327499799543808e+16,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-390/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10c6987e591247eb33eb8e00ecb3db8333e8f362910ced1d008fadc0e14c9444
+size 6417