Upload seed2/checkpoint-456

.gitattributes

@@ -125,3 +125,4 @@ seed2/checkpoint-405/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-420/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-435/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+seed2/checkpoint-456/tokenizer.json filter=lfs diff=lfs merge=lfs -text

seed2/checkpoint-456/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

seed2/checkpoint-456/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",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

seed2/checkpoint-456/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba4d8faf10eeb656a79821dd7599dba7cc84ce0b9aede9447e3530506541e34
+size 80792096

seed2/checkpoint-456/added_tokens.json

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

seed2/checkpoint-456/chat_template.jinja

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

seed2/checkpoint-456/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b304c40ca040d27847d9dbaaeb26d8aedd5c205e5d427db4d86b1a8896a863a5
+size 161816187

seed2/checkpoint-456/rng_state.pth

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

seed2/checkpoint-456/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eac3d878d34bed6076620092adea08cf4e89e39061b2fe1588231a583c53f76
+size 1465

seed2/checkpoint-456/special_tokens_map.json

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

seed2/checkpoint-456/tokenizer.json

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

seed2/checkpoint-456/tokenizer_config.json

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

seed2/checkpoint-456/trainer_state.json

@@ -0,0 +1,3226 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 456,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 0.7566928863525391,
+      "learning_rate": 0.0,
+      "loss": 0.8968,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 0.8072069883346558,
+      "learning_rate": 4e-05,
+      "loss": 0.9227,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 0.8303298950195312,
+      "learning_rate": 8e-05,
+      "loss": 0.9508,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 0.9258667826652527,
+      "learning_rate": 0.00012,
+      "loss": 0.9527,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 0.9558561444282532,
+      "learning_rate": 0.00016,
+      "loss": 0.9178,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 0.47254669666290283,
+      "learning_rate": 0.0002,
+      "loss": 0.7227,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 0.5736677646636963,
+      "learning_rate": 0.00019955654101995565,
+      "loss": 0.7945,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 0.6585658192634583,
+      "learning_rate": 0.00019911308203991133,
+      "loss": 0.9034,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 0.6045550107955933,
+      "learning_rate": 0.00019866962305986697,
+      "loss": 0.8399,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.4790070056915283,
+      "learning_rate": 0.00019822616407982261,
+      "loss": 0.8234,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 0.3827012777328491,
+      "learning_rate": 0.00019778270509977829,
+      "loss": 0.8281,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.31580132246017456,
+      "learning_rate": 0.00019733924611973393,
+      "loss": 0.7572,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.2703302502632141,
+      "learning_rate": 0.0001968957871396896,
+      "loss": 0.7605,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.2565660774707794,
+      "learning_rate": 0.00019645232815964525,
+      "loss": 0.8042,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.19942161440849304,
+      "learning_rate": 0.00019600886917960092,
+      "loss": 0.7443,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.21022649109363556,
+      "learning_rate": 0.00019556541019955653,
+      "loss": 0.6641,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.2277892380952835,
+      "learning_rate": 0.0001951219512195122,
+      "loss": 0.7432,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.33732736110687256,
+      "learning_rate": 0.00019467849223946785,
+      "loss": 0.7787,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.27139249444007874,
+      "learning_rate": 0.00019423503325942352,
+      "loss": 0.7951,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.2788768410682678,
+      "learning_rate": 0.00019379157427937917,
+      "loss": 0.719,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.2770022451877594,
+      "learning_rate": 0.00019334811529933484,
+      "loss": 0.7604,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.2961127460002899,
+      "learning_rate": 0.00019290465631929045,
+      "loss": 0.7834,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.42819708585739136,
+      "learning_rate": 0.00019246119733924613,
+      "loss": 0.7302,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.2841340899467468,
+      "learning_rate": 0.00019201773835920177,
+      "loss": 0.7261,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.2913196384906769,
+      "learning_rate": 0.00019157427937915744,
+      "loss": 0.7212,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.3300360143184662,
+      "learning_rate": 0.00019113082039911309,
+      "loss": 0.6494,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.27701273560523987,
+      "learning_rate": 0.00019068736141906876,
+      "loss": 0.6838,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.2448320835828781,
+      "learning_rate": 0.0001902439024390244,
+      "loss": 0.6998,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.2562633454799652,
+      "learning_rate": 0.00018980044345898005,
+      "loss": 0.7449,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.2887221574783325,
+      "learning_rate": 0.00018935698447893572,
+      "loss": 0.6676,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.2212107628583908,
+      "learning_rate": 0.00018891352549889136,
+      "loss": 0.7629,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.26358944177627563,
+      "learning_rate": 0.00018847006651884703,
+      "loss": 0.7497,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.19833838939666748,
+      "learning_rate": 0.00018802660753880268,
+      "loss": 0.7787,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.21352550387382507,
+      "learning_rate": 0.00018758314855875832,
+      "loss": 0.7513,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.2602783739566803,
+      "learning_rate": 0.00018713968957871397,
+      "loss": 0.7423,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.25566816329956055,
+      "learning_rate": 0.00018669623059866964,
+      "loss": 0.7049,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.26156026124954224,
+      "learning_rate": 0.00018625277161862528,
+      "loss": 0.7342,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.2607591450214386,
+      "learning_rate": 0.00018580931263858095,
+      "loss": 0.6492,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.2538753151893616,
+      "learning_rate": 0.0001853658536585366,
+      "loss": 0.6907,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.25195640325546265,
+      "learning_rate": 0.00018492239467849224,
+      "loss": 0.7535,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.2823958098888397,
+      "learning_rate": 0.0001844789356984479,
+      "loss": 0.6653,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.2609056532382965,
+      "learning_rate": 0.00018403547671840356,
+      "loss": 0.6967,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.21727432310581207,
+      "learning_rate": 0.0001835920177383592,
+      "loss": 0.7071,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.28144368529319763,
+      "learning_rate": 0.00018314855875831487,
+      "loss": 0.7169,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.23335450887680054,
+      "learning_rate": 0.00018270509977827052,
+      "loss": 0.7365,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.2892163097858429,
+      "learning_rate": 0.00018226164079822616,
+      "loss": 0.6403,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.2446267455816269,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.6869,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.24830380082130432,
+      "learning_rate": 0.00018137472283813748,
+      "loss": 0.6407,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.32878631353378296,
+      "learning_rate": 0.00018093126385809312,
+      "loss": 0.6962,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.23604710400104523,
+      "learning_rate": 0.0001804878048780488,
+      "loss": 0.7427,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.20495985448360443,
+      "learning_rate": 0.00018004434589800444,
+      "loss": 0.6272,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.21541891992092133,
+      "learning_rate": 0.00017960088691796008,
+      "loss": 0.7157,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.2712082266807556,
+      "learning_rate": 0.00017915742793791575,
+      "loss": 0.7132,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.2737255096435547,
+      "learning_rate": 0.0001787139689578714,
+      "loss": 0.7115,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.3590952455997467,
+      "learning_rate": 0.00017827050997782707,
+      "loss": 0.7041,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.22194194793701172,
+      "learning_rate": 0.00017782705099778271,
+      "loss": 0.6017,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.2181357890367508,
+      "learning_rate": 0.00017738359201773839,
+      "loss": 0.7292,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.2543794512748718,
+      "learning_rate": 0.000176940133037694,
+      "loss": 0.7028,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.33169296383857727,
+      "learning_rate": 0.00017649667405764967,
+      "loss": 0.6646,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.27475646138191223,
+      "learning_rate": 0.00017605321507760532,
+      "loss": 0.7889,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.2369152307510376,
+      "learning_rate": 0.000175609756097561,
+      "loss": 0.7018,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.21613454818725586,
+      "learning_rate": 0.00017516629711751663,
+      "loss": 0.6715,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.20882739126682281,
+      "learning_rate": 0.0001747228381374723,
+      "loss": 0.6892,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.2187095731496811,
+      "learning_rate": 0.00017427937915742792,
+      "loss": 0.6436,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.2040148377418518,
+      "learning_rate": 0.0001738359201773836,
+      "loss": 0.6512,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.2536020874977112,
+      "learning_rate": 0.00017339246119733924,
+      "loss": 0.7019,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.24403820931911469,
+      "learning_rate": 0.0001729490022172949,
+      "loss": 0.6723,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.2113356590270996,
+      "learning_rate": 0.00017250554323725056,
+      "loss": 0.7119,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.2046196013689041,
+      "learning_rate": 0.00017206208425720623,
+      "loss": 0.7191,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.22032175958156586,
+      "learning_rate": 0.00017161862527716187,
+      "loss": 0.7159,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.2522450387477875,
+      "learning_rate": 0.00017117516629711752,
+      "loss": 0.7039,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.2568543553352356,
+      "learning_rate": 0.0001707317073170732,
+      "loss": 0.6842,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.21719902753829956,
+      "learning_rate": 0.00017028824833702883,
+      "loss": 0.6942,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.22592927515506744,
+      "learning_rate": 0.0001698447893569845,
+      "loss": 0.7966,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.241453617811203,
+      "learning_rate": 0.00016940133037694015,
+      "loss": 0.7412,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.23723702132701874,
+      "learning_rate": 0.00016895787139689582,
+      "loss": 0.7148,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.20009562373161316,
+      "learning_rate": 0.00016851441241685144,
+      "loss": 0.7143,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.2050897777080536,
+      "learning_rate": 0.0001680709534368071,
+      "loss": 0.6766,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.22315199673175812,
+      "learning_rate": 0.00016762749445676275,
+      "loss": 0.7,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.20680196583271027,
+      "learning_rate": 0.00016718403547671842,
+      "loss": 0.6356,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.23944680392742157,
+      "learning_rate": 0.00016674057649667407,
+      "loss": 0.6559,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.22115568816661835,
+      "learning_rate": 0.00016629711751662974,
+      "loss": 0.6644,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.2396654337644577,
+      "learning_rate": 0.00016585365853658536,
+      "loss": 0.6972,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.2545161545276642,
+      "learning_rate": 0.00016541019955654103,
+      "loss": 0.7242,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.2548670172691345,
+      "learning_rate": 0.00016496674057649667,
+      "loss": 0.756,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.2570771872997284,
+      "learning_rate": 0.00016452328159645234,
+      "loss": 0.7392,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.25188854336738586,
+      "learning_rate": 0.000164079822616408,
+      "loss": 0.7504,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.24089300632476807,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.6831,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.21377258002758026,
+      "learning_rate": 0.0001631929046563193,
+      "loss": 0.6904,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.22940956056118011,
+      "learning_rate": 0.00016274944567627495,
+      "loss": 0.7223,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.23013509809970856,
+      "learning_rate": 0.0001623059866962306,
+      "loss": 0.6743,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.2341698855161667,
+      "learning_rate": 0.00016186252771618626,
+      "loss": 0.6031,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.21239612996578217,
+      "learning_rate": 0.0001614190687361419,
+      "loss": 0.6043,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.21493980288505554,
+      "learning_rate": 0.00016097560975609758,
+      "loss": 0.6019,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.2181602418422699,
+      "learning_rate": 0.00016053215077605322,
+      "loss": 0.6601,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.2473670393228531,
+      "learning_rate": 0.00016008869179600887,
+      "loss": 0.7301,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.23289376497268677,
+      "learning_rate": 0.00015964523281596454,
+      "loss": 0.7493,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.22319060564041138,
+      "learning_rate": 0.00015920177383592018,
+      "loss": 0.7057,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.24551022052764893,
+      "learning_rate": 0.00015875831485587586,
+      "loss": 0.6467,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.21545983850955963,
+      "learning_rate": 0.0001583148558758315,
+      "loss": 0.7107,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.2510841190814972,
+      "learning_rate": 0.00015787139689578714,
+      "loss": 0.658,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.23200248181819916,
+      "learning_rate": 0.0001574279379157428,
+      "loss": 0.7351,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.2180459201335907,
+      "learning_rate": 0.00015698447893569846,
+      "loss": 0.6992,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.23387350142002106,
+      "learning_rate": 0.0001565410199556541,
+      "loss": 0.7398,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.22272081673145294,
+      "learning_rate": 0.00015609756097560978,
+      "loss": 0.6528,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.22667521238327026,
+      "learning_rate": 0.00015565410199556542,
+      "loss": 0.76,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.2085743099451065,
+      "learning_rate": 0.00015521064301552106,
+      "loss": 0.6842,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.24620012938976288,
+      "learning_rate": 0.0001547671840354767,
+      "loss": 0.738,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.23256433010101318,
+      "learning_rate": 0.00015432372505543238,
+      "loss": 0.6475,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.2518521249294281,
+      "learning_rate": 0.00015388026607538802,
+      "loss": 0.6764,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.22852903604507446,
+      "learning_rate": 0.0001534368070953437,
+      "loss": 0.6797,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.22933068871498108,
+      "learning_rate": 0.00015299334811529934,
+      "loss": 0.7095,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.22621572017669678,
+      "learning_rate": 0.00015254988913525498,
+      "loss": 0.6587,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.24995188415050507,
+      "learning_rate": 0.00015210643015521066,
+      "loss": 0.7068,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.25118041038513184,
+      "learning_rate": 0.0001516629711751663,
+      "loss": 0.6904,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.21053656935691833,
+      "learning_rate": 0.00015121951219512197,
+      "loss": 0.549,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.2095535695552826,
+      "learning_rate": 0.00015077605321507762,
+      "loss": 0.6875,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.21824686229228973,
+      "learning_rate": 0.0001503325942350333,
+      "loss": 0.6729,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.2307584136724472,
+      "learning_rate": 0.0001498891352549889,
+      "loss": 0.6493,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.22242283821105957,
+      "learning_rate": 0.00014944567627494458,
+      "loss": 0.668,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.22179292142391205,
+      "learning_rate": 0.00014900221729490022,
+      "loss": 0.6386,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.23222969472408295,
+      "learning_rate": 0.0001485587583148559,
+      "loss": 0.6712,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.2495681792497635,
+      "learning_rate": 0.00014811529933481154,
+      "loss": 0.6295,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.2647445797920227,
+      "learning_rate": 0.0001476718403547672,
+      "loss": 0.7005,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.24217277765274048,
+      "learning_rate": 0.00014722838137472282,
+      "loss": 0.6311,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.2461085021495819,
+      "learning_rate": 0.0001467849223946785,
+      "loss": 0.6446,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.2610090970993042,
+      "learning_rate": 0.00014634146341463414,
+      "loss": 0.7045,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.2201678454875946,
+      "learning_rate": 0.0001458980044345898,
+      "loss": 0.6436,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.22592248022556305,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.6608,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.22529453039169312,
+      "learning_rate": 0.00014501108647450113,
+      "loss": 0.6401,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.2538209855556488,
+      "learning_rate": 0.00014456762749445675,
+      "loss": 0.6788,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.22796444594860077,
+      "learning_rate": 0.00014412416851441242,
+      "loss": 0.7022,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.20975171029567719,
+      "learning_rate": 0.00014368070953436806,
+      "loss": 0.6779,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.22414448857307434,
+      "learning_rate": 0.00014323725055432373,
+      "loss": 0.7459,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.270942747592926,
+      "learning_rate": 0.00014279379157427938,
+      "loss": 0.6682,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.25628402829170227,
+      "learning_rate": 0.00014235033259423505,
+      "loss": 0.6759,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.2702762484550476,
+      "learning_rate": 0.0001419068736141907,
+      "loss": 0.7287,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.23527158796787262,
+      "learning_rate": 0.00014146341463414634,
+      "loss": 0.6365,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.2638787031173706,
+      "learning_rate": 0.000141019955654102,
+      "loss": 0.7456,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.2431294023990631,
+      "learning_rate": 0.00014057649667405765,
+      "loss": 0.655,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.26322004199028015,
+      "learning_rate": 0.00014013303769401332,
+      "loss": 0.6694,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.22624383866786957,
+      "learning_rate": 0.00013968957871396897,
+      "loss": 0.6025,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.20489341020584106,
+      "learning_rate": 0.00013924611973392464,
+      "loss": 0.6544,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.23127716779708862,
+      "learning_rate": 0.00013880266075388026,
+      "loss": 0.748,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.23263822495937347,
+      "learning_rate": 0.00013835920177383593,
+      "loss": 0.674,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.23276172578334808,
+      "learning_rate": 0.00013791574279379157,
+      "loss": 0.7082,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.2461167722940445,
+      "learning_rate": 0.00013747228381374724,
+      "loss": 0.7059,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.24031785130500793,
+      "learning_rate": 0.0001370288248337029,
+      "loss": 0.6732,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.21587732434272766,
+      "learning_rate": 0.00013658536585365856,
+      "loss": 0.6605,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.22994357347488403,
+      "learning_rate": 0.00013614190687361418,
+      "loss": 0.6609,
+      "step": 150
+    },
+    {
+      "epoch": 0.9956043956043956,
+      "grad_norm": 0.2200823873281479,
+      "learning_rate": 0.00013569844789356985,
+      "loss": 0.7032,
+      "step": 151
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.26850587129592896,
+      "learning_rate": 0.0001352549889135255,
+      "loss": 0.7507,
+      "step": 152
+    },
+    {
+      "epoch": 1.0065934065934066,
+      "grad_norm": 0.23838046193122864,
+      "learning_rate": 0.00013481152993348116,
+      "loss": 0.6686,
+      "step": 153
+    },
+    {
+      "epoch": 1.0131868131868131,
+      "grad_norm": 0.21873874962329865,
+      "learning_rate": 0.0001343680709534368,
+      "loss": 0.759,
+      "step": 154
+    },
+    {
+      "epoch": 1.0197802197802197,
+      "grad_norm": 0.22888495028018951,
+      "learning_rate": 0.00013392461197339248,
+      "loss": 0.5565,
+      "step": 155
+    },
+    {
+      "epoch": 1.0263736263736263,
+      "grad_norm": 0.21489110589027405,
+      "learning_rate": 0.00013348115299334812,
+      "loss": 0.6417,
+      "step": 156
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.23249667882919312,
+      "learning_rate": 0.00013303769401330377,
+      "loss": 0.6282,
+      "step": 157
+    },
+    {
+      "epoch": 1.0395604395604396,
+      "grad_norm": 0.2237980216741562,
+      "learning_rate": 0.00013259423503325944,
+      "loss": 0.68,
+      "step": 158
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.2389901876449585,
+      "learning_rate": 0.00013215077605321509,
+      "loss": 0.6522,
+      "step": 159
+    },
+    {
+      "epoch": 1.0527472527472528,
+      "grad_norm": 0.23192445933818817,
+      "learning_rate": 0.00013170731707317076,
+      "loss": 0.6478,
+      "step": 160
+    },
+    {
+      "epoch": 1.0593406593406594,
+      "grad_norm": 0.25663626194000244,
+      "learning_rate": 0.0001312638580931264,
+      "loss": 0.7291,
+      "step": 161
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.22465288639068604,
+      "learning_rate": 0.00013082039911308205,
+      "loss": 0.6243,
+      "step": 162
+    },
+    {
+      "epoch": 1.0725274725274725,
+      "grad_norm": 0.22050045430660248,
+      "learning_rate": 0.0001303769401330377,
+      "loss": 0.6577,
+      "step": 163
+    },
+    {
+      "epoch": 1.079120879120879,
+      "grad_norm": 0.2221308797597885,
+      "learning_rate": 0.00012993348115299336,
+      "loss": 0.6401,
+      "step": 164
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.24798862636089325,
+      "learning_rate": 0.000129490022172949,
+      "loss": 0.6871,
+      "step": 165
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 0.23916630446910858,
+      "learning_rate": 0.00012904656319290468,
+      "loss": 0.665,
+      "step": 166
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.24509520828723907,
+      "learning_rate": 0.00012860310421286032,
+      "loss": 0.6868,
+      "step": 167
+    },
+    {
+      "epoch": 1.1054945054945056,
+      "grad_norm": 0.2539862096309662,
+      "learning_rate": 0.00012815964523281597,
+      "loss": 0.6517,
+      "step": 168
+    },
+    {
+      "epoch": 1.1120879120879121,
+      "grad_norm": 0.229658305644989,
+      "learning_rate": 0.0001277161862527716,
+      "loss": 0.6478,
+      "step": 169
+    },
+    {
+      "epoch": 1.1186813186813187,
+      "grad_norm": 0.24706101417541504,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.6242,
+      "step": 170
+    },
+    {
+      "epoch": 1.1252747252747253,
+      "grad_norm": 0.25188955664634705,
+      "learning_rate": 0.00012682926829268293,
+      "loss": 0.644,
+      "step": 171
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 0.24681685864925385,
+      "learning_rate": 0.0001263858093126386,
+      "loss": 0.6251,
+      "step": 172
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 0.2579716444015503,
+      "learning_rate": 0.00012594235033259424,
+      "loss": 0.6627,
+      "step": 173
+    },
+    {
+      "epoch": 1.145054945054945,
+      "grad_norm": 0.2671927511692047,
+      "learning_rate": 0.00012549889135254989,
+      "loss": 0.667,
+      "step": 174
+    },
+    {
+      "epoch": 1.1516483516483516,
+      "grad_norm": 0.25410088896751404,
+      "learning_rate": 0.00012505543237250553,
+      "loss": 0.6801,
+      "step": 175
+    },
+    {
+      "epoch": 1.1582417582417581,
+      "grad_norm": 0.2630886733531952,
+      "learning_rate": 0.0001246119733924612,
+      "loss": 0.625,
+      "step": 176
+    },
+    {
+      "epoch": 1.164835164835165,
+      "grad_norm": 0.2547929584980011,
+      "learning_rate": 0.00012416851441241685,
+      "loss": 0.6651,
+      "step": 177
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 0.26386600732803345,
+      "learning_rate": 0.00012372505543237252,
+      "loss": 0.6801,
+      "step": 178
+    },
+    {
+      "epoch": 1.178021978021978,
+      "grad_norm": 0.25373655557632446,
+      "learning_rate": 0.00012328159645232816,
+      "loss": 0.6703,
+      "step": 179
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.2492551952600479,
+      "learning_rate": 0.0001228381374722838,
+      "loss": 0.6194,
+      "step": 180
+    },
+    {
+      "epoch": 1.1912087912087912,
+      "grad_norm": 0.2771320939064026,
+      "learning_rate": 0.00012239467849223948,
+      "loss": 0.6941,
+      "step": 181
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 0.25620630383491516,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.6702,
+      "step": 182
+    },
+    {
+      "epoch": 1.2043956043956043,
+      "grad_norm": 0.29603561758995056,
+      "learning_rate": 0.00012150776053215078,
+      "loss": 0.6822,
+      "step": 183
+    },
+    {
+      "epoch": 1.210989010989011,
+      "grad_norm": 0.2567739486694336,
+      "learning_rate": 0.00012106430155210644,
+      "loss": 0.6695,
+      "step": 184
+    },
+    {
+      "epoch": 1.2175824175824177,
+      "grad_norm": 0.24866175651550293,
+      "learning_rate": 0.0001206208425720621,
+      "loss": 0.65,
+      "step": 185
+    },
+    {
+      "epoch": 1.2241758241758243,
+      "grad_norm": 0.2531645894050598,
+      "learning_rate": 0.00012017738359201774,
+      "loss": 0.6078,
+      "step": 186
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.2500450611114502,
+      "learning_rate": 0.0001197339246119734,
+      "loss": 0.7071,
+      "step": 187
+    },
+    {
+      "epoch": 1.2373626373626374,
+      "grad_norm": 0.2909831702709198,
+      "learning_rate": 0.00011929046563192906,
+      "loss": 0.7142,
+      "step": 188
+    },
+    {
+      "epoch": 1.243956043956044,
+      "grad_norm": 0.290924996137619,
+      "learning_rate": 0.00011884700665188471,
+      "loss": 0.6608,
+      "step": 189
+    },
+    {
+      "epoch": 1.2505494505494505,
+      "grad_norm": 0.28154683113098145,
+      "learning_rate": 0.00011840354767184036,
+      "loss": 0.6522,
+      "step": 190
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.2484731376171112,
+      "learning_rate": 0.00011796008869179602,
+      "loss": 0.708,
+      "step": 191
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 0.2834712862968445,
+      "learning_rate": 0.00011751662971175166,
+      "loss": 0.6284,
+      "step": 192
+    },
+    {
+      "epoch": 1.2703296703296703,
+      "grad_norm": 0.2461405247449875,
+      "learning_rate": 0.00011707317073170732,
+      "loss": 0.6422,
+      "step": 193
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 0.2527882754802704,
+      "learning_rate": 0.00011662971175166298,
+      "loss": 0.6107,
+      "step": 194
+    },
+    {
+      "epoch": 1.2835164835164834,
+      "grad_norm": 0.24974150955677032,
+      "learning_rate": 0.00011618625277161863,
+      "loss": 0.6002,
+      "step": 195
+    },
+    {
+      "epoch": 1.2901098901098902,
+      "grad_norm": 0.2708195745944977,
+      "learning_rate": 0.00011574279379157429,
+      "loss": 0.5828,
+      "step": 196
+    },
+    {
+      "epoch": 1.2967032967032968,
+      "grad_norm": 0.26116371154785156,
+      "learning_rate": 0.00011529933481152995,
+      "loss": 0.7109,
+      "step": 197
+    },
+    {
+      "epoch": 1.3032967032967033,
+      "grad_norm": 0.2596125900745392,
+      "learning_rate": 0.00011485587583148558,
+      "loss": 0.6316,
+      "step": 198
+    },
+    {
+      "epoch": 1.30989010989011,
+      "grad_norm": 0.2532707154750824,
+      "learning_rate": 0.00011441241685144124,
+      "loss": 0.6294,
+      "step": 199
+    },
+    {
+      "epoch": 1.3164835164835165,
+      "grad_norm": 0.26848992705345154,
+      "learning_rate": 0.0001139689578713969,
+      "loss": 0.6565,
+      "step": 200
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 0.28303253650665283,
+      "learning_rate": 0.00011352549889135255,
+      "loss": 0.6423,
+      "step": 201
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 0.2455137073993683,
+      "learning_rate": 0.00011308203991130821,
+      "loss": 0.6353,
+      "step": 202
+    },
+    {
+      "epoch": 1.3362637362637364,
+      "grad_norm": 0.25358811020851135,
+      "learning_rate": 0.00011263858093126387,
+      "loss": 0.6913,
+      "step": 203
+    },
+    {
+      "epoch": 1.342857142857143,
+      "grad_norm": 0.2945426106452942,
+      "learning_rate": 0.00011219512195121953,
+      "loss": 0.6294,
+      "step": 204
+    },
+    {
+      "epoch": 1.3494505494505495,
+      "grad_norm": 0.288709819316864,
+      "learning_rate": 0.00011175166297117516,
+      "loss": 0.6463,
+      "step": 205
+    },
+    {
+      "epoch": 1.3560439560439561,
+      "grad_norm": 0.28171539306640625,
+      "learning_rate": 0.00011130820399113082,
+      "loss": 0.6697,
+      "step": 206
+    },
+    {
+      "epoch": 1.3626373626373627,
+      "grad_norm": 0.26656296849250793,
+      "learning_rate": 0.00011086474501108647,
+      "loss": 0.6404,
+      "step": 207
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.2690280079841614,
+      "learning_rate": 0.00011042128603104213,
+      "loss": 0.6819,
+      "step": 208
+    },
+    {
+      "epoch": 1.3758241758241758,
+      "grad_norm": 0.2921794652938843,
+      "learning_rate": 0.00010997782705099779,
+      "loss": 0.7364,
+      "step": 209
+    },
+    {
+      "epoch": 1.3824175824175824,
+      "grad_norm": 0.2835233807563782,
+      "learning_rate": 0.00010953436807095345,
+      "loss": 0.6362,
+      "step": 210
+    },
+    {
+      "epoch": 1.389010989010989,
+      "grad_norm": 0.26193857192993164,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.645,
+      "step": 211
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.2507191300392151,
+      "learning_rate": 0.00010864745011086475,
+      "loss": 0.648,
+      "step": 212
+    },
+    {
+      "epoch": 1.402197802197802,
+      "grad_norm": 0.268464595079422,
+      "learning_rate": 0.00010820399113082041,
+      "loss": 0.7722,
+      "step": 213
+    },
+    {
+      "epoch": 1.4087912087912087,
+      "grad_norm": 0.3000003695487976,
+      "learning_rate": 0.00010776053215077607,
+      "loss": 0.6898,
+      "step": 214
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 0.2898484468460083,
+      "learning_rate": 0.00010731707317073172,
+      "loss": 0.6315,
+      "step": 215
+    },
+    {
+      "epoch": 1.421978021978022,
+      "grad_norm": 0.313852459192276,
+      "learning_rate": 0.00010687361419068738,
+      "loss": 0.6447,
+      "step": 216
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.29412636160850525,
+      "learning_rate": 0.00010643015521064301,
+      "loss": 0.6423,
+      "step": 217
+    },
+    {
+      "epoch": 1.4351648351648352,
+      "grad_norm": 0.24455416202545166,
+      "learning_rate": 0.00010598669623059867,
+      "loss": 0.6511,
+      "step": 218
+    },
+    {
+      "epoch": 1.4417582417582417,
+      "grad_norm": 0.29522591829299927,
+      "learning_rate": 0.00010554323725055433,
+      "loss": 0.7184,
+      "step": 219
+    },
+    {
+      "epoch": 1.4483516483516483,
+      "grad_norm": 0.2859632968902588,
+      "learning_rate": 0.00010509977827050999,
+      "loss": 0.6522,
+      "step": 220
+    },
+    {
+      "epoch": 1.4549450549450549,
+      "grad_norm": 0.27325212955474854,
+      "learning_rate": 0.00010465631929046564,
+      "loss": 0.5928,
+      "step": 221
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.25304514169692993,
+      "learning_rate": 0.0001042128603104213,
+      "loss": 0.6103,
+      "step": 222
+    },
+    {
+      "epoch": 1.4681318681318682,
+      "grad_norm": 0.2548450827598572,
+      "learning_rate": 0.00010376940133037693,
+      "loss": 0.6031,
+      "step": 223
+    },
+    {
+      "epoch": 1.4747252747252748,
+      "grad_norm": 0.3130348026752472,
+      "learning_rate": 0.00010332594235033259,
+      "loss": 0.7278,
+      "step": 224
+    },
+    {
+      "epoch": 1.4813186813186814,
+      "grad_norm": 0.31668156385421753,
+      "learning_rate": 0.00010288248337028825,
+      "loss": 0.6885,
+      "step": 225
+    },
+    {
+      "epoch": 1.487912087912088,
+      "grad_norm": 0.3072829246520996,
+      "learning_rate": 0.0001024390243902439,
+      "loss": 0.7203,
+      "step": 226
+    },
+    {
+      "epoch": 1.4945054945054945,
+      "grad_norm": 0.26381248235702515,
+      "learning_rate": 0.00010199556541019956,
+      "loss": 0.6398,
+      "step": 227
+    },
+    {
+      "epoch": 1.501098901098901,
+      "grad_norm": 0.28612086176872253,
+      "learning_rate": 0.00010155210643015522,
+      "loss": 0.6526,
+      "step": 228
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 0.26881909370422363,
+      "learning_rate": 0.00010110864745011087,
+      "loss": 0.617,
+      "step": 229
+    },
+    {
+      "epoch": 1.5142857142857142,
+      "grad_norm": 0.2695836126804352,
+      "learning_rate": 0.00010066518847006652,
+      "loss": 0.6039,
+      "step": 230
+    },
+    {
+      "epoch": 1.5208791208791208,
+      "grad_norm": 0.2591269314289093,
+      "learning_rate": 0.00010022172949002218,
+      "loss": 0.6341,
+      "step": 231
+    },
+    {
+      "epoch": 1.5274725274725274,
+      "grad_norm": 0.28765055537223816,
+      "learning_rate": 9.977827050997783e-05,
+      "loss": 0.6063,
+      "step": 232
+    },
+    {
+      "epoch": 1.534065934065934,
+      "grad_norm": 0.28966453671455383,
+      "learning_rate": 9.933481152993348e-05,
+      "loss": 0.726,
+      "step": 233
+    },
+    {
+      "epoch": 1.5406593406593405,
+      "grad_norm": 0.2546531856060028,
+      "learning_rate": 9.889135254988914e-05,
+      "loss": 0.6841,
+      "step": 234
+    },
+    {
+      "epoch": 1.5472527472527473,
+      "grad_norm": 0.28424352407455444,
+      "learning_rate": 9.84478935698448e-05,
+      "loss": 0.6431,
+      "step": 235
+    },
+    {
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.2566540539264679,
+      "learning_rate": 9.800443458980046e-05,
+      "loss": 0.6409,
+      "step": 236
+    },
+    {
+      "epoch": 1.5604395604395604,
+      "grad_norm": 0.2491263747215271,
+      "learning_rate": 9.75609756097561e-05,
+      "loss": 0.5528,
+      "step": 237
+    },
+    {
+      "epoch": 1.567032967032967,
+      "grad_norm": 0.27940094470977783,
+      "learning_rate": 9.711751662971176e-05,
+      "loss": 0.6424,
+      "step": 238
+    },
+    {
+      "epoch": 1.5736263736263736,
+      "grad_norm": 0.27105605602264404,
+      "learning_rate": 9.667405764966742e-05,
+      "loss": 0.6374,
+      "step": 239
+    },
+    {
+      "epoch": 1.5802197802197804,
+      "grad_norm": 0.2752592861652374,
+      "learning_rate": 9.623059866962306e-05,
+      "loss": 0.5703,
+      "step": 240
+    },
+    {
+      "epoch": 1.586813186813187,
+      "grad_norm": 0.2850567400455475,
+      "learning_rate": 9.578713968957872e-05,
+      "loss": 0.6445,
+      "step": 241
+    },
+    {
+      "epoch": 1.5934065934065935,
+      "grad_norm": 0.29228994250297546,
+      "learning_rate": 9.534368070953438e-05,
+      "loss": 0.6865,
+      "step": 242
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.2857453525066376,
+      "learning_rate": 9.490022172949002e-05,
+      "loss": 0.6547,
+      "step": 243
+    },
+    {
+      "epoch": 1.6065934065934067,
+      "grad_norm": 0.339375376701355,
+      "learning_rate": 9.445676274944568e-05,
+      "loss": 0.6671,
+      "step": 244
+    },
+    {
+      "epoch": 1.6131868131868132,
+      "grad_norm": 0.2887197732925415,
+      "learning_rate": 9.401330376940134e-05,
+      "loss": 0.6285,
+      "step": 245
+    },
+    {
+      "epoch": 1.6197802197802198,
+      "grad_norm": 0.27693381905555725,
+      "learning_rate": 9.356984478935698e-05,
+      "loss": 0.6421,
+      "step": 246
+    },
+    {
+      "epoch": 1.6263736263736264,
+      "grad_norm": 0.26970162987709045,
+      "learning_rate": 9.312638580931264e-05,
+      "loss": 0.6248,
+      "step": 247
+    },
+    {
+      "epoch": 1.632967032967033,
+      "grad_norm": 0.2887139320373535,
+      "learning_rate": 9.26829268292683e-05,
+      "loss": 0.5764,
+      "step": 248
+    },
+    {
+      "epoch": 1.6395604395604395,
+      "grad_norm": 0.2849027216434479,
+      "learning_rate": 9.223946784922394e-05,
+      "loss": 0.5988,
+      "step": 249
+    },
+    {
+      "epoch": 1.646153846153846,
+      "grad_norm": 0.3030661940574646,
+      "learning_rate": 9.17960088691796e-05,
+      "loss": 0.6623,
+      "step": 250
+    },
+    {
+      "epoch": 1.6527472527472526,
+      "grad_norm": 0.2827235758304596,
+      "learning_rate": 9.135254988913526e-05,
+      "loss": 0.7059,
+      "step": 251
+    },
+    {
+      "epoch": 1.6593406593406592,
+      "grad_norm": 0.2566092908382416,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.6596,
+      "step": 252
+    },
+    {
+      "epoch": 1.6659340659340658,
+      "grad_norm": 0.2589581310749054,
+      "learning_rate": 9.046563192904656e-05,
+      "loss": 0.7015,
+      "step": 253
+    },
+    {
+      "epoch": 1.6725274725274726,
+      "grad_norm": 0.269096314907074,
+      "learning_rate": 9.002217294900222e-05,
+      "loss": 0.6514,
+      "step": 254
+    },
+    {
+      "epoch": 1.6791208791208792,
+      "grad_norm": 0.2603346109390259,
+      "learning_rate": 8.957871396895788e-05,
+      "loss": 0.6413,
+      "step": 255
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.2775377035140991,
+      "learning_rate": 8.913525498891354e-05,
+      "loss": 0.6826,
+      "step": 256
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.2686198055744171,
+      "learning_rate": 8.869179600886919e-05,
+      "loss": 0.6647,
+      "step": 257
+    },
+    {
+      "epoch": 1.6989010989010989,
+      "grad_norm": 0.3018244802951813,
+      "learning_rate": 8.824833702882484e-05,
+      "loss": 0.691,
+      "step": 258
+    },
+    {
+      "epoch": 1.7054945054945057,
+      "grad_norm": 0.23714810609817505,
+      "learning_rate": 8.78048780487805e-05,
+      "loss": 0.6462,
+      "step": 259
+    },
+    {
+      "epoch": 1.7120879120879122,
+      "grad_norm": 0.24709635972976685,
+      "learning_rate": 8.736141906873615e-05,
+      "loss": 0.6921,
+      "step": 260
+    },
+    {
+      "epoch": 1.7186813186813188,
+      "grad_norm": 0.2733432650566101,
+      "learning_rate": 8.69179600886918e-05,
+      "loss": 0.6846,
+      "step": 261
+    },
+    {
+      "epoch": 1.7252747252747254,
+      "grad_norm": 0.2669680714607239,
+      "learning_rate": 8.647450110864746e-05,
+      "loss": 0.7075,
+      "step": 262
+    },
+    {
+      "epoch": 1.731868131868132,
+      "grad_norm": 0.2506164610385895,
+      "learning_rate": 8.603104212860311e-05,
+      "loss": 0.7026,
+      "step": 263
+    },
+    {
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.25369930267333984,
+      "learning_rate": 8.558758314855876e-05,
+      "loss": 0.6197,
+      "step": 264
+    },
+    {
+      "epoch": 1.745054945054945,
+      "grad_norm": 0.2686818540096283,
+      "learning_rate": 8.514412416851442e-05,
+      "loss": 0.66,
+      "step": 265
+    },
+    {
+      "epoch": 1.7516483516483516,
+      "grad_norm": 0.2570140063762665,
+      "learning_rate": 8.470066518847007e-05,
+      "loss": 0.6334,
+      "step": 266
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 0.3140219449996948,
+      "learning_rate": 8.425720620842572e-05,
+      "loss": 0.6692,
+      "step": 267
+    },
+    {
+      "epoch": 1.7648351648351648,
+      "grad_norm": 0.3045641779899597,
+      "learning_rate": 8.381374722838138e-05,
+      "loss": 0.685,
+      "step": 268
+    },
+    {
+      "epoch": 1.7714285714285714,
+      "grad_norm": 0.27470919489860535,
+      "learning_rate": 8.337028824833703e-05,
+      "loss": 0.6873,
+      "step": 269
+    },
+    {
+      "epoch": 1.778021978021978,
+      "grad_norm": 0.28925663232803345,
+      "learning_rate": 8.292682926829268e-05,
+      "loss": 0.6947,
+      "step": 270
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 0.3109953999519348,
+      "learning_rate": 8.248337028824834e-05,
+      "loss": 0.6541,
+      "step": 271
+    },
+    {
+      "epoch": 1.791208791208791,
+      "grad_norm": 0.2664562463760376,
+      "learning_rate": 8.2039911308204e-05,
+      "loss": 0.6087,
+      "step": 272
+    },
+    {
+      "epoch": 1.7978021978021979,
+      "grad_norm": 0.2900189161300659,
+      "learning_rate": 8.159645232815965e-05,
+      "loss": 0.6596,
+      "step": 273
+    },
+    {
+      "epoch": 1.8043956043956044,
+      "grad_norm": 0.25098729133605957,
+      "learning_rate": 8.11529933481153e-05,
+      "loss": 0.6348,
+      "step": 274
+    },
+    {
+      "epoch": 1.810989010989011,
+      "grad_norm": 0.2515256106853485,
+      "learning_rate": 8.070953436807095e-05,
+      "loss": 0.5713,
+      "step": 275
+    },
+    {
+      "epoch": 1.8175824175824176,
+      "grad_norm": 0.29323166608810425,
+      "learning_rate": 8.026607538802661e-05,
+      "loss": 0.7117,
+      "step": 276
+    },
+    {
+      "epoch": 1.8241758241758241,
+      "grad_norm": 0.28458940982818604,
+      "learning_rate": 7.982261640798227e-05,
+      "loss": 0.7348,
+      "step": 277
+    },
+    {
+      "epoch": 1.830769230769231,
+      "grad_norm": 0.2711794972419739,
+      "learning_rate": 7.937915742793793e-05,
+      "loss": 0.6033,
+      "step": 278
+    },
+    {
+      "epoch": 1.8373626373626375,
+      "grad_norm": 0.2763634920120239,
+      "learning_rate": 7.893569844789357e-05,
+      "loss": 0.629,
+      "step": 279
+    },
+    {
+      "epoch": 1.843956043956044,
+      "grad_norm": 0.2724277377128601,
+      "learning_rate": 7.849223946784923e-05,
+      "loss": 0.6556,
+      "step": 280
+    },
+    {
+      "epoch": 1.8505494505494506,
+      "grad_norm": 0.2756093442440033,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 0.6108,
+      "step": 281
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.2640242874622345,
+      "learning_rate": 7.760532150776053e-05,
+      "loss": 0.6539,
+      "step": 282
+    },
+    {
+      "epoch": 1.8637362637362638,
+      "grad_norm": 0.29842934012413025,
+      "learning_rate": 7.716186252771619e-05,
+      "loss": 0.6506,
+      "step": 283
+    },
+    {
+      "epoch": 1.8703296703296703,
+      "grad_norm": 0.26119422912597656,
+      "learning_rate": 7.671840354767185e-05,
+      "loss": 0.6331,
+      "step": 284
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 0.28425905108451843,
+      "learning_rate": 7.627494456762749e-05,
+      "loss": 0.6646,
+      "step": 285
+    },
+    {
+      "epoch": 1.8835164835164835,
+      "grad_norm": 0.3047288954257965,
+      "learning_rate": 7.583148558758315e-05,
+      "loss": 0.5916,
+      "step": 286
+    },
+    {
+      "epoch": 1.89010989010989,
+      "grad_norm": 0.261098176240921,
+      "learning_rate": 7.538802660753881e-05,
+      "loss": 0.6364,
+      "step": 287
+    },
+    {
+      "epoch": 1.8967032967032966,
+      "grad_norm": 0.2626063823699951,
+      "learning_rate": 7.494456762749445e-05,
+      "loss": 0.6715,
+      "step": 288
+    },
+    {
+      "epoch": 1.9032967032967032,
+      "grad_norm": 0.2619648277759552,
+      "learning_rate": 7.450110864745011e-05,
+      "loss": 0.6214,
+      "step": 289
+    },
+    {
+      "epoch": 1.9098901098901098,
+      "grad_norm": 0.2693786323070526,
+      "learning_rate": 7.405764966740577e-05,
+      "loss": 0.6458,
+      "step": 290
+    },
+    {
+      "epoch": 1.9164835164835163,
+      "grad_norm": 0.2993558943271637,
+      "learning_rate": 7.361419068736141e-05,
+      "loss": 0.6265,
+      "step": 291
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.2900768220424652,
+      "learning_rate": 7.317073170731707e-05,
+      "loss": 0.6753,
+      "step": 292
+    },
+    {
+      "epoch": 1.9296703296703297,
+      "grad_norm": 0.33005234599113464,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.7007,
+      "step": 293
+    },
+    {
+      "epoch": 1.9362637362637363,
+      "grad_norm": 0.2958125174045563,
+      "learning_rate": 7.228381374722837e-05,
+      "loss": 0.6549,
+      "step": 294
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 0.26220574975013733,
+      "learning_rate": 7.184035476718403e-05,
+      "loss": 0.6255,
+      "step": 295
+    },
+    {
+      "epoch": 1.9494505494505494,
+      "grad_norm": 0.26721176505088806,
+      "learning_rate": 7.139689578713969e-05,
+      "loss": 0.6665,
+      "step": 296
+    },
+    {
+      "epoch": 1.9560439560439562,
+      "grad_norm": 0.28550317883491516,
+      "learning_rate": 7.095343680709535e-05,
+      "loss": 0.57,
+      "step": 297
+    },
+    {
+      "epoch": 1.9626373626373628,
+      "grad_norm": 0.2624494135379791,
+      "learning_rate": 7.0509977827051e-05,
+      "loss": 0.7116,
+      "step": 298
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 0.2984730303287506,
+      "learning_rate": 7.006651884700666e-05,
+      "loss": 0.5598,
+      "step": 299
+    },
+    {
+      "epoch": 1.975824175824176,
+      "grad_norm": 0.31408563256263733,
+      "learning_rate": 6.962305986696232e-05,
+      "loss": 0.7112,
+      "step": 300
+    },
+    {
+      "epoch": 1.9824175824175825,
+      "grad_norm": 0.28238028287887573,
+      "learning_rate": 6.917960088691796e-05,
+      "loss": 0.6848,
+      "step": 301
+    },
+    {
+      "epoch": 1.989010989010989,
+      "grad_norm": 0.2646782100200653,
+      "learning_rate": 6.873614190687362e-05,
+      "loss": 0.664,
+      "step": 302
+    },
+    {
+      "epoch": 1.9956043956043956,
+      "grad_norm": 0.262151300907135,
+      "learning_rate": 6.829268292682928e-05,
+      "loss": 0.6369,
+      "step": 303
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4055860936641693,
+      "learning_rate": 6.784922394678492e-05,
+      "loss": 0.7321,
+      "step": 304
+    },
+    {
+      "epoch": 2.0065934065934066,
+      "grad_norm": 0.2767898738384247,
+      "learning_rate": 6.740576496674058e-05,
+      "loss": 0.6258,
+      "step": 305
+    },
+    {
+      "epoch": 2.013186813186813,
+      "grad_norm": 0.2767726182937622,
+      "learning_rate": 6.696230598669624e-05,
+      "loss": 0.5826,
+      "step": 306
+    },
+    {
+      "epoch": 2.0197802197802197,
+      "grad_norm": 0.333950936794281,
+      "learning_rate": 6.651884700665188e-05,
+      "loss": 0.6616,
+      "step": 307
+    },
+    {
+      "epoch": 2.0263736263736263,
+      "grad_norm": 0.30379459261894226,
+      "learning_rate": 6.607538802660754e-05,
+      "loss": 0.5949,
+      "step": 308
+    },
+    {
+      "epoch": 2.032967032967033,
+      "grad_norm": 0.3011108636856079,
+      "learning_rate": 6.56319290465632e-05,
+      "loss": 0.5842,
+      "step": 309
+    },
+    {
+      "epoch": 2.0395604395604394,
+      "grad_norm": 0.3045988380908966,
+      "learning_rate": 6.518847006651884e-05,
+      "loss": 0.6133,
+      "step": 310
+    },
+    {
+      "epoch": 2.046153846153846,
+      "grad_norm": 0.3474821150302887,
+      "learning_rate": 6.47450110864745e-05,
+      "loss": 0.7103,
+      "step": 311
+    },
+    {
+      "epoch": 2.0527472527472526,
+      "grad_norm": 0.33828631043434143,
+      "learning_rate": 6.430155210643016e-05,
+      "loss": 0.6312,
+      "step": 312
+    },
+    {
+      "epoch": 2.059340659340659,
+      "grad_norm": 0.3167876601219177,
+      "learning_rate": 6.38580931263858e-05,
+      "loss": 0.5796,
+      "step": 313
+    },
+    {
+      "epoch": 2.065934065934066,
+      "grad_norm": 0.33619222044944763,
+      "learning_rate": 6.341463414634146e-05,
+      "loss": 0.5836,
+      "step": 314
+    },
+    {
+      "epoch": 2.0725274725274727,
+      "grad_norm": 0.3406059741973877,
+      "learning_rate": 6.297117516629712e-05,
+      "loss": 0.6263,
+      "step": 315
+    },
+    {
+      "epoch": 2.0791208791208793,
+      "grad_norm": 0.2969309985637665,
+      "learning_rate": 6.252771618625277e-05,
+      "loss": 0.5175,
+      "step": 316
+    },
+    {
+      "epoch": 2.085714285714286,
+      "grad_norm": 0.2987888753414154,
+      "learning_rate": 6.208425720620842e-05,
+      "loss": 0.5892,
+      "step": 317
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": 0.34043604135513306,
+      "learning_rate": 6.164079822616408e-05,
+      "loss": 0.6071,
+      "step": 318
+    },
+    {
+      "epoch": 2.098901098901099,
+      "grad_norm": 0.3126677870750427,
+      "learning_rate": 6.119733924611974e-05,
+      "loss": 0.6094,
+      "step": 319
+    },
+    {
+      "epoch": 2.1054945054945056,
+      "grad_norm": 0.34577929973602295,
+      "learning_rate": 6.075388026607539e-05,
+      "loss": 0.6841,
+      "step": 320
+    },
+    {
+      "epoch": 2.112087912087912,
+      "grad_norm": 0.32912516593933105,
+      "learning_rate": 6.031042128603105e-05,
+      "loss": 0.6079,
+      "step": 321
+    },
+    {
+      "epoch": 2.1186813186813187,
+      "grad_norm": 0.4031827747821808,
+      "learning_rate": 5.98669623059867e-05,
+      "loss": 0.6365,
+      "step": 322
+    },
+    {
+      "epoch": 2.1252747252747253,
+      "grad_norm": 0.3113933801651001,
+      "learning_rate": 5.942350332594236e-05,
+      "loss": 0.6264,
+      "step": 323
+    },
+    {
+      "epoch": 2.131868131868132,
+      "grad_norm": 0.30763059854507446,
+      "learning_rate": 5.898004434589801e-05,
+      "loss": 0.6196,
+      "step": 324
+    },
+    {
+      "epoch": 2.1384615384615384,
+      "grad_norm": 0.3299765884876251,
+      "learning_rate": 5.853658536585366e-05,
+      "loss": 0.583,
+      "step": 325
+    },
+    {
+      "epoch": 2.145054945054945,
+      "grad_norm": 0.3048851191997528,
+      "learning_rate": 5.809312638580932e-05,
+      "loss": 0.632,
+      "step": 326
+    },
+    {
+      "epoch": 2.1516483516483516,
+      "grad_norm": 0.3228287398815155,
+      "learning_rate": 5.7649667405764975e-05,
+      "loss": 0.6074,
+      "step": 327
+    },
+    {
+      "epoch": 2.158241758241758,
+      "grad_norm": 0.36613574624061584,
+      "learning_rate": 5.720620842572062e-05,
+      "loss": 0.6738,
+      "step": 328
+    },
+    {
+      "epoch": 2.1648351648351647,
+      "grad_norm": 0.37679603695869446,
+      "learning_rate": 5.676274944567628e-05,
+      "loss": 0.6278,
+      "step": 329
+    },
+    {
+      "epoch": 2.1714285714285713,
+      "grad_norm": 0.349593847990036,
+      "learning_rate": 5.6319290465631935e-05,
+      "loss": 0.5695,
+      "step": 330
+    },
+    {
+      "epoch": 2.178021978021978,
+      "grad_norm": 0.35029375553131104,
+      "learning_rate": 5.587583148558758e-05,
+      "loss": 0.5633,
+      "step": 331
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 0.345669686794281,
+      "learning_rate": 5.543237250554324e-05,
+      "loss": 0.6263,
+      "step": 332
+    },
+    {
+      "epoch": 2.1912087912087914,
+      "grad_norm": 0.344555139541626,
+      "learning_rate": 5.4988913525498895e-05,
+      "loss": 0.5793,
+      "step": 333
+    },
+    {
+      "epoch": 2.197802197802198,
+      "grad_norm": 0.34782081842422485,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.5609,
+      "step": 334
+    },
+    {
+      "epoch": 2.2043956043956046,
+      "grad_norm": 0.3399725556373596,
+      "learning_rate": 5.4101995565410204e-05,
+      "loss": 0.5927,
+      "step": 335
+    },
+    {
+      "epoch": 2.210989010989011,
+      "grad_norm": 0.3345470428466797,
+      "learning_rate": 5.365853658536586e-05,
+      "loss": 0.594,
+      "step": 336
+    },
+    {
+      "epoch": 2.2175824175824177,
+      "grad_norm": 0.35872822999954224,
+      "learning_rate": 5.3215077605321506e-05,
+      "loss": 0.6489,
+      "step": 337
+    },
+    {
+      "epoch": 2.2241758241758243,
+      "grad_norm": 0.3782046139240265,
+      "learning_rate": 5.2771618625277164e-05,
+      "loss": 0.664,
+      "step": 338
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 0.33910220861434937,
+      "learning_rate": 5.232815964523282e-05,
+      "loss": 0.6077,
+      "step": 339
+    },
+    {
+      "epoch": 2.2373626373626374,
+      "grad_norm": 0.32223838567733765,
+      "learning_rate": 5.1884700665188466e-05,
+      "loss": 0.5955,
+      "step": 340
+    },
+    {
+      "epoch": 2.243956043956044,
+      "grad_norm": 0.37492015957832336,
+      "learning_rate": 5.1441241685144124e-05,
+      "loss": 0.484,
+      "step": 341
+    },
+    {
+      "epoch": 2.2505494505494505,
+      "grad_norm": 0.3599349856376648,
+      "learning_rate": 5.099778270509978e-05,
+      "loss": 0.6382,
+      "step": 342
+    },
+    {
+      "epoch": 2.257142857142857,
+      "grad_norm": 0.3597133457660675,
+      "learning_rate": 5.0554323725055433e-05,
+      "loss": 0.5918,
+      "step": 343
+    },
+    {
+      "epoch": 2.2637362637362637,
+      "grad_norm": 0.3609064817428589,
+      "learning_rate": 5.011086474501109e-05,
+      "loss": 0.6358,
+      "step": 344
+    },
+    {
+      "epoch": 2.2703296703296703,
+      "grad_norm": 0.35410696268081665,
+      "learning_rate": 4.966740576496674e-05,
+      "loss": 0.6148,
+      "step": 345
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": 0.3661516606807709,
+      "learning_rate": 4.92239467849224e-05,
+      "loss": 0.6674,
+      "step": 346
+    },
+    {
+      "epoch": 2.2835164835164834,
+      "grad_norm": 0.4148848354816437,
+      "learning_rate": 4.878048780487805e-05,
+      "loss": 0.6196,
+      "step": 347
+    },
+    {
+      "epoch": 2.29010989010989,
+      "grad_norm": 0.3600256145000458,
+      "learning_rate": 4.833702882483371e-05,
+      "loss": 0.635,
+      "step": 348
+    },
+    {
+      "epoch": 2.2967032967032965,
+      "grad_norm": 0.36552894115448,
+      "learning_rate": 4.789356984478936e-05,
+      "loss": 0.6255,
+      "step": 349
+    },
+    {
+      "epoch": 2.303296703296703,
+      "grad_norm": 0.3612947165966034,
+      "learning_rate": 4.745011086474501e-05,
+      "loss": 0.6448,
+      "step": 350
+    },
+    {
+      "epoch": 2.3098901098901097,
+      "grad_norm": 0.37938806414604187,
+      "learning_rate": 4.700665188470067e-05,
+      "loss": 0.5957,
+      "step": 351
+    },
+    {
+      "epoch": 2.3164835164835162,
+      "grad_norm": 0.3745158314704895,
+      "learning_rate": 4.656319290465632e-05,
+      "loss": 0.5789,
+      "step": 352
+    },
+    {
+      "epoch": 2.3230769230769233,
+      "grad_norm": 0.38833531737327576,
+      "learning_rate": 4.611973392461197e-05,
+      "loss": 0.5743,
+      "step": 353
+    },
+    {
+      "epoch": 2.32967032967033,
+      "grad_norm": 0.3789951503276825,
+      "learning_rate": 4.567627494456763e-05,
+      "loss": 0.6078,
+      "step": 354
+    },
+    {
+      "epoch": 2.3362637362637364,
+      "grad_norm": 0.4078710675239563,
+      "learning_rate": 4.523281596452328e-05,
+      "loss": 0.5714,
+      "step": 355
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 0.3586929142475128,
+      "learning_rate": 4.478935698447894e-05,
+      "loss": 0.6029,
+      "step": 356
+    },
+    {
+      "epoch": 2.3494505494505495,
+      "grad_norm": 0.4597932994365692,
+      "learning_rate": 4.4345898004434597e-05,
+      "loss": 0.6498,
+      "step": 357
+    },
+    {
+      "epoch": 2.356043956043956,
+      "grad_norm": 0.40236249566078186,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 0.571,
+      "step": 358
+    },
+    {
+      "epoch": 2.3626373626373627,
+      "grad_norm": 0.4040866196155548,
+      "learning_rate": 4.34589800443459e-05,
+      "loss": 0.5343,
+      "step": 359
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 0.3976406157016754,
+      "learning_rate": 4.301552106430156e-05,
+      "loss": 0.6164,
+      "step": 360
+    },
+    {
+      "epoch": 2.375824175824176,
+      "grad_norm": 0.3879232108592987,
+      "learning_rate": 4.257206208425721e-05,
+      "loss": 0.6173,
+      "step": 361
+    },
+    {
+      "epoch": 2.3824175824175824,
+      "grad_norm": 0.41425254940986633,
+      "learning_rate": 4.212860310421286e-05,
+      "loss": 0.6112,
+      "step": 362
+    },
+    {
+      "epoch": 2.389010989010989,
+      "grad_norm": 0.3854585886001587,
+      "learning_rate": 4.168514412416852e-05,
+      "loss": 0.562,
+      "step": 363
+    },
+    {
+      "epoch": 2.3956043956043955,
+      "grad_norm": 0.3936591148376465,
+      "learning_rate": 4.124168514412417e-05,
+      "loss": 0.5748,
+      "step": 364
+    },
+    {
+      "epoch": 2.402197802197802,
+      "grad_norm": 0.40050625801086426,
+      "learning_rate": 4.0798226164079826e-05,
+      "loss": 0.5899,
+      "step": 365
+    },
+    {
+      "epoch": 2.4087912087912087,
+      "grad_norm": 0.38004061579704285,
+      "learning_rate": 4.035476718403548e-05,
+      "loss": 0.6193,
+      "step": 366
+    },
+    {
+      "epoch": 2.4153846153846152,
+      "grad_norm": 0.4139723479747772,
+      "learning_rate": 3.9911308203991135e-05,
+      "loss": 0.5956,
+      "step": 367
+    },
+    {
+      "epoch": 2.421978021978022,
+      "grad_norm": 0.39874425530433655,
+      "learning_rate": 3.9467849223946786e-05,
+      "loss": 0.6088,
+      "step": 368
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.385820209980011,
+      "learning_rate": 3.9024390243902444e-05,
+      "loss": 0.5133,
+      "step": 369
+    },
+    {
+      "epoch": 2.4351648351648354,
+      "grad_norm": 0.3776566982269287,
+      "learning_rate": 3.8580931263858095e-05,
+      "loss": 0.617,
+      "step": 370
+    },
+    {
+      "epoch": 2.441758241758242,
+      "grad_norm": 0.434494286775589,
+      "learning_rate": 3.8137472283813746e-05,
+      "loss": 0.6057,
+      "step": 371
+    },
+    {
+      "epoch": 2.4483516483516485,
+      "grad_norm": 0.4495853781700134,
+      "learning_rate": 3.7694013303769404e-05,
+      "loss": 0.556,
+      "step": 372
+    },
+    {
+      "epoch": 2.454945054945055,
+      "grad_norm": 0.3991885781288147,
+      "learning_rate": 3.7250554323725055e-05,
+      "loss": 0.6397,
+      "step": 373
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.3977200388908386,
+      "learning_rate": 3.6807095343680706e-05,
+      "loss": 0.5569,
+      "step": 374
+    },
+    {
+      "epoch": 2.4681318681318682,
+      "grad_norm": 0.41530755162239075,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.6035,
+      "step": 375
+    },
+    {
+      "epoch": 2.474725274725275,
+      "grad_norm": 0.4019760489463806,
+      "learning_rate": 3.5920177383592015e-05,
+      "loss": 0.5786,
+      "step": 376
+    },
+    {
+      "epoch": 2.4813186813186814,
+      "grad_norm": 0.4121412932872772,
+      "learning_rate": 3.547671840354767e-05,
+      "loss": 0.5886,
+      "step": 377
+    },
+    {
+      "epoch": 2.487912087912088,
+      "grad_norm": 0.4172489047050476,
+      "learning_rate": 3.503325942350333e-05,
+      "loss": 0.6401,
+      "step": 378
+    },
+    {
+      "epoch": 2.4945054945054945,
+      "grad_norm": 0.39942315220832825,
+      "learning_rate": 3.458980044345898e-05,
+      "loss": 0.5479,
+      "step": 379
+    },
+    {
+      "epoch": 2.501098901098901,
+      "grad_norm": 0.39400216937065125,
+      "learning_rate": 3.414634146341464e-05,
+      "loss": 0.5784,
+      "step": 380
+    },
+    {
+      "epoch": 2.5076923076923077,
+      "grad_norm": 0.397125780582428,
+      "learning_rate": 3.370288248337029e-05,
+      "loss": 0.6448,
+      "step": 381
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.3930623233318329,
+      "learning_rate": 3.325942350332594e-05,
+      "loss": 0.5781,
+      "step": 382
+    },
+    {
+      "epoch": 2.520879120879121,
+      "grad_norm": 0.4061959385871887,
+      "learning_rate": 3.28159645232816e-05,
+      "loss": 0.5337,
+      "step": 383
+    },
+    {
+      "epoch": 2.5274725274725274,
+      "grad_norm": 0.40153974294662476,
+      "learning_rate": 3.237250554323725e-05,
+      "loss": 0.5689,
+      "step": 384
+    },
+    {
+      "epoch": 2.534065934065934,
+      "grad_norm": 0.4028501510620117,
+      "learning_rate": 3.19290465631929e-05,
+      "loss": 0.6775,
+      "step": 385
+    },
+    {
+      "epoch": 2.5406593406593405,
+      "grad_norm": 0.39602965116500854,
+      "learning_rate": 3.148558758314856e-05,
+      "loss": 0.589,
+      "step": 386
+    },
+    {
+      "epoch": 2.547252747252747,
+      "grad_norm": 0.41992124915122986,
+      "learning_rate": 3.104212860310421e-05,
+      "loss": 0.6312,
+      "step": 387
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 0.38882148265838623,
+      "learning_rate": 3.059866962305987e-05,
+      "loss": 0.6133,
+      "step": 388
+    },
+    {
+      "epoch": 2.5604395604395602,
+      "grad_norm": 0.44356104731559753,
+      "learning_rate": 3.0155210643015524e-05,
+      "loss": 0.6421,
+      "step": 389
+    },
+    {
+      "epoch": 2.567032967032967,
+      "grad_norm": 0.4221073389053345,
+      "learning_rate": 2.971175166297118e-05,
+      "loss": 0.5587,
+      "step": 390
+    },
+    {
+      "epoch": 2.5736263736263734,
+      "grad_norm": 0.3849692940711975,
+      "learning_rate": 2.926829268292683e-05,
+      "loss": 0.5348,
+      "step": 391
+    },
+    {
+      "epoch": 2.5802197802197804,
+      "grad_norm": 0.4010922610759735,
+      "learning_rate": 2.8824833702882487e-05,
+      "loss": 0.6871,
+      "step": 392
+    },
+    {
+      "epoch": 2.586813186813187,
+      "grad_norm": 0.43920648097991943,
+      "learning_rate": 2.838137472283814e-05,
+      "loss": 0.653,
+      "step": 393
+    },
+    {
+      "epoch": 2.5934065934065935,
+      "grad_norm": 0.37430340051651,
+      "learning_rate": 2.793791574279379e-05,
+      "loss": 0.6403,
+      "step": 394
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.45172011852264404,
+      "learning_rate": 2.7494456762749448e-05,
+      "loss": 0.6848,
+      "step": 395
+    },
+    {
+      "epoch": 2.6065934065934067,
+      "grad_norm": 0.4015762507915497,
+      "learning_rate": 2.7050997782705102e-05,
+      "loss": 0.5586,
+      "step": 396
+    },
+    {
+      "epoch": 2.6131868131868132,
+      "grad_norm": 0.38632863759994507,
+      "learning_rate": 2.6607538802660753e-05,
+      "loss": 0.565,
+      "step": 397
+    },
+    {
+      "epoch": 2.61978021978022,
+      "grad_norm": 0.4415051341056824,
+      "learning_rate": 2.616407982261641e-05,
+      "loss": 0.6212,
+      "step": 398
+    },
+    {
+      "epoch": 2.6263736263736264,
+      "grad_norm": 0.4472382962703705,
+      "learning_rate": 2.5720620842572062e-05,
+      "loss": 0.6569,
+      "step": 399
+    },
+    {
+      "epoch": 2.632967032967033,
+      "grad_norm": 0.47554266452789307,
+      "learning_rate": 2.5277161862527717e-05,
+      "loss": 0.6135,
+      "step": 400
+    },
+    {
+      "epoch": 2.6395604395604395,
+      "grad_norm": 0.4063940644264221,
+      "learning_rate": 2.483370288248337e-05,
+      "loss": 0.6134,
+      "step": 401
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": 0.4553447663784027,
+      "learning_rate": 2.4390243902439026e-05,
+      "loss": 0.6883,
+      "step": 402
+    },
+    {
+      "epoch": 2.6527472527472526,
+      "grad_norm": 0.43455392122268677,
+      "learning_rate": 2.394678492239468e-05,
+      "loss": 0.5849,
+      "step": 403
+    },
+    {
+      "epoch": 2.659340659340659,
+      "grad_norm": 0.4113107919692993,
+      "learning_rate": 2.3503325942350335e-05,
+      "loss": 0.6229,
+      "step": 404
+    },
+    {
+      "epoch": 2.665934065934066,
+      "grad_norm": 0.46329283714294434,
+      "learning_rate": 2.3059866962305986e-05,
+      "loss": 0.6359,
+      "step": 405
+    },
+    {
+      "epoch": 2.672527472527473,
+      "grad_norm": 0.4273914396762848,
+      "learning_rate": 2.261640798226164e-05,
+      "loss": 0.5758,
+      "step": 406
+    },
+    {
+      "epoch": 2.6791208791208794,
+      "grad_norm": 0.43240711092948914,
+      "learning_rate": 2.2172949002217298e-05,
+      "loss": 0.5574,
+      "step": 407
+    },
+    {
+      "epoch": 2.685714285714286,
+      "grad_norm": 0.4142119288444519,
+      "learning_rate": 2.172949002217295e-05,
+      "loss": 0.5856,
+      "step": 408
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 0.4401680827140808,
+      "learning_rate": 2.1286031042128604e-05,
+      "loss": 0.7033,
+      "step": 409
+    },
+    {
+      "epoch": 2.698901098901099,
+      "grad_norm": 0.4058586359024048,
+      "learning_rate": 2.084257206208426e-05,
+      "loss": 0.6391,
+      "step": 410
+    },
+    {
+      "epoch": 2.7054945054945057,
+      "grad_norm": 0.4072122573852539,
+      "learning_rate": 2.0399113082039913e-05,
+      "loss": 0.5385,
+      "step": 411
+    },
+    {
+      "epoch": 2.7120879120879122,
+      "grad_norm": 0.4295085668563843,
+      "learning_rate": 1.9955654101995567e-05,
+      "loss": 0.5743,
+      "step": 412
+    },
+    {
+      "epoch": 2.718681318681319,
+      "grad_norm": 0.43043872714042664,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 0.6177,
+      "step": 413
+    },
+    {
+      "epoch": 2.7252747252747254,
+      "grad_norm": 0.43385621905326843,
+      "learning_rate": 1.9068736141906873e-05,
+      "loss": 0.6556,
+      "step": 414
+    },
+    {
+      "epoch": 2.731868131868132,
+      "grad_norm": 0.41579902172088623,
+      "learning_rate": 1.8625277161862528e-05,
+      "loss": 0.6667,
+      "step": 415
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "grad_norm": 0.43041008710861206,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.6309,
+      "step": 416
+    },
+    {
+      "epoch": 2.745054945054945,
+      "grad_norm": 0.4350832402706146,
+      "learning_rate": 1.7738359201773837e-05,
+      "loss": 0.5466,
+      "step": 417
+    },
+    {
+      "epoch": 2.7516483516483516,
+      "grad_norm": 0.4616117477416992,
+      "learning_rate": 1.729490022172949e-05,
+      "loss": 0.5392,
+      "step": 418
+    },
+    {
+      "epoch": 2.758241758241758,
+      "grad_norm": 0.4365164637565613,
+      "learning_rate": 1.6851441241685146e-05,
+      "loss": 0.5495,
+      "step": 419
+    },
+    {
+      "epoch": 2.764835164835165,
+      "grad_norm": 0.4348524808883667,
+      "learning_rate": 1.64079822616408e-05,
+      "loss": 0.5992,
+      "step": 420
+    },
+    {
+      "epoch": 2.7714285714285714,
+      "grad_norm": 0.4587492346763611,
+      "learning_rate": 1.596452328159645e-05,
+      "loss": 0.6176,
+      "step": 421
+    },
+    {
+      "epoch": 2.778021978021978,
+      "grad_norm": 0.43321162462234497,
+      "learning_rate": 1.5521064301552106e-05,
+      "loss": 0.549,
+      "step": 422
+    },
+    {
+      "epoch": 2.7846153846153845,
+      "grad_norm": 0.3984859585762024,
+      "learning_rate": 1.5077605321507762e-05,
+      "loss": 0.6063,
+      "step": 423
+    },
+    {
+      "epoch": 2.791208791208791,
+      "grad_norm": 0.453141987323761,
+      "learning_rate": 1.4634146341463415e-05,
+      "loss": 0.5873,
+      "step": 424
+    },
+    {
+      "epoch": 2.7978021978021976,
+      "grad_norm": 0.433131605386734,
+      "learning_rate": 1.419068736141907e-05,
+      "loss": 0.5662,
+      "step": 425
+    },
+    {
+      "epoch": 2.804395604395604,
+      "grad_norm": 0.42879295349121094,
+      "learning_rate": 1.3747228381374724e-05,
+      "loss": 0.546,
+      "step": 426
+    },
+    {
+      "epoch": 2.8109890109890108,
+      "grad_norm": 0.450687050819397,
+      "learning_rate": 1.3303769401330377e-05,
+      "loss": 0.6313,
+      "step": 427
+    },
+    {
+      "epoch": 2.8175824175824173,
+      "grad_norm": 0.45722416043281555,
+      "learning_rate": 1.2860310421286031e-05,
+      "loss": 0.6103,
+      "step": 428
+    },
+    {
+      "epoch": 2.824175824175824,
+      "grad_norm": 0.44927874207496643,
+      "learning_rate": 1.2416851441241686e-05,
+      "loss": 0.6485,
+      "step": 429
+    },
+    {
+      "epoch": 2.830769230769231,
+      "grad_norm": 0.4113784432411194,
+      "learning_rate": 1.197339246119734e-05,
+      "loss": 0.648,
+      "step": 430
+    },
+    {
+      "epoch": 2.8373626373626375,
+      "grad_norm": 0.45794856548309326,
+      "learning_rate": 1.1529933481152993e-05,
+      "loss": 0.5846,
+      "step": 431
+    },
+    {
+      "epoch": 2.843956043956044,
+      "grad_norm": 0.45426440238952637,
+      "learning_rate": 1.1086474501108649e-05,
+      "loss": 0.6296,
+      "step": 432
+    },
+    {
+      "epoch": 2.8505494505494506,
+      "grad_norm": 0.4488619863986969,
+      "learning_rate": 1.0643015521064302e-05,
+      "loss": 0.63,
+      "step": 433
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.4205934703350067,
+      "learning_rate": 1.0199556541019956e-05,
+      "loss": 0.5721,
+      "step": 434
+    },
+    {
+      "epoch": 2.8637362637362638,
+      "grad_norm": 0.4080902338027954,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 0.5893,
+      "step": 435
+    },
+    {
+      "epoch": 2.8703296703296703,
+      "grad_norm": 0.4314049780368805,
+      "learning_rate": 9.312638580931264e-06,
+      "loss": 0.5525,
+      "step": 436
+    },
+    {
+      "epoch": 2.876923076923077,
+      "grad_norm": 0.40637901425361633,
+      "learning_rate": 8.869179600886918e-06,
+      "loss": 0.5777,
+      "step": 437
+    },
+    {
+      "epoch": 2.8835164835164835,
+      "grad_norm": 0.45440784096717834,
+      "learning_rate": 8.425720620842573e-06,
+      "loss": 0.6525,
+      "step": 438
+    },
+    {
+      "epoch": 2.89010989010989,
+      "grad_norm": 0.4568384289741516,
+      "learning_rate": 7.982261640798226e-06,
+      "loss": 0.6799,
+      "step": 439
+    },
+    {
+      "epoch": 2.8967032967032966,
+      "grad_norm": 0.43314939737319946,
+      "learning_rate": 7.538802660753881e-06,
+      "loss": 0.6163,
+      "step": 440
+    },
+    {
+      "epoch": 2.903296703296703,
+      "grad_norm": 0.420584499835968,
+      "learning_rate": 7.095343680709535e-06,
+      "loss": 0.6304,
+      "step": 441
+    },
+    {
+      "epoch": 2.9098901098901098,
+      "grad_norm": 0.444281667470932,
+      "learning_rate": 6.651884700665188e-06,
+      "loss": 0.6378,
+      "step": 442
+    },
+    {
+      "epoch": 2.9164835164835163,
+      "grad_norm": 0.41703835129737854,
+      "learning_rate": 6.208425720620843e-06,
+      "loss": 0.634,
+      "step": 443
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.3929488956928253,
+      "learning_rate": 5.7649667405764965e-06,
+      "loss": 0.5391,
+      "step": 444
+    },
+    {
+      "epoch": 2.92967032967033,
+      "grad_norm": 0.45001310110092163,
+      "learning_rate": 5.321507760532151e-06,
+      "loss": 0.5966,
+      "step": 445
+    },
+    {
+      "epoch": 2.9362637362637365,
+      "grad_norm": 0.4296533763408661,
+      "learning_rate": 4.8780487804878055e-06,
+      "loss": 0.6037,
+      "step": 446
+    },
+    {
+      "epoch": 2.942857142857143,
+      "grad_norm": 0.4438004195690155,
+      "learning_rate": 4.434589800443459e-06,
+      "loss": 0.6359,
+      "step": 447
+    },
+    {
+      "epoch": 2.9494505494505496,
+      "grad_norm": 0.4249172508716583,
+      "learning_rate": 3.991130820399113e-06,
+      "loss": 0.6074,
+      "step": 448
+    },
+    {
+      "epoch": 2.956043956043956,
+      "grad_norm": 0.4326271116733551,
+      "learning_rate": 3.5476718403547673e-06,
+      "loss": 0.6269,
+      "step": 449
+    },
+    {
+      "epoch": 2.9626373626373628,
+      "grad_norm": 0.44677722454071045,
+      "learning_rate": 3.1042128603104214e-06,
+      "loss": 0.621,
+      "step": 450
+    },
+    {
+      "epoch": 2.9692307692307693,
+      "grad_norm": 0.44106268882751465,
+      "learning_rate": 2.6607538802660755e-06,
+      "loss": 0.6188,
+      "step": 451
+    },
+    {
+      "epoch": 2.975824175824176,
+      "grad_norm": 0.44327107071876526,
+      "learning_rate": 2.2172949002217296e-06,
+      "loss": 0.5864,
+      "step": 452
+    },
+    {
+      "epoch": 2.9824175824175825,
+      "grad_norm": 0.44434189796447754,
+      "learning_rate": 1.7738359201773837e-06,
+      "loss": 0.608,
+      "step": 453
+    },
+    {
+      "epoch": 2.989010989010989,
+      "grad_norm": 0.4226035177707672,
+      "learning_rate": 1.3303769401330377e-06,
+      "loss": 0.6373,
+      "step": 454
+    },
+    {
+      "epoch": 2.9956043956043956,
+      "grad_norm": 0.4222874939441681,
+      "learning_rate": 8.869179600886918e-07,
+      "loss": 0.5743,
+      "step": 455
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6289628744125366,
+      "learning_rate": 4.434589800443459e-07,
+      "loss": 0.6039,
+      "step": 456
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0983065314835456e+17,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

seed2/checkpoint-456/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b83d56b10c82f48270b2a62ff197500d0fa85662617e7ab982dfd0ef48c177
+size 6289