Upload seed2/checkpoint-210

.gitattributes

@@ -108,3 +108,4 @@ seed2/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-165/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-195/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+seed2/checkpoint-210/tokenizer.json filter=lfs diff=lfs merge=lfs -text

seed2/checkpoint-210/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-210/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

seed2/checkpoint-210/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8d4fa2e90750cb5cb20183d34ed139ac7c3fddc30dfd54f8572d349052faf6
+size 80792096

seed2/checkpoint-210/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-210/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-210/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ccfaf8a875b7bad829015907611844f0b32de0faa20f16f650de75940dd9c0
+size 161816187

seed2/checkpoint-210/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b553bfda5728612f828419d30aa32edc9f6abc9f2bf4be372b4cc24477bc88b4
+size 14645

seed2/checkpoint-210/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acfe8dfa9c2258cb823940f74a2735e63222af1deea24112cf0ce5063a100663
+size 1465

seed2/checkpoint-210/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-210/tokenizer.json

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

seed2/checkpoint-210/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-210/trainer_state.json

@@ -0,0 +1,1504 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3824175824175824,
+  "eval_steps": 500,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 1.0638142824172974,
+      "learning_rate": 0.0,
+      "loss": 1.0777,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 0.9542151689529419,
+      "learning_rate": 9.56e-05,
+      "loss": 1.1025,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 1.0668847560882568,
+      "learning_rate": 0.0001912,
+      "loss": 1.0405,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 1.0646922588348389,
+      "learning_rate": 0.0002868,
+      "loss": 0.9056,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 0.6475369334220886,
+      "learning_rate": 0.0003824,
+      "loss": 0.8513,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 0.653504490852356,
+      "learning_rate": 0.000478,
+      "loss": 0.9432,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 0.5652804374694824,
+      "learning_rate": 0.00047694013303769406,
+      "loss": 0.8951,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 0.38114824891090393,
+      "learning_rate": 0.00047588026607538804,
+      "loss": 0.8546,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 0.3202402591705322,
+      "learning_rate": 0.0004748203991130821,
+      "loss": 0.9013,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.3632391095161438,
+      "learning_rate": 0.00047376053215077607,
+      "loss": 0.7981,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 0.38180795311927795,
+      "learning_rate": 0.00047270066518847006,
+      "loss": 0.8034,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.44034814834594727,
+      "learning_rate": 0.0004716407982261641,
+      "loss": 0.8194,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.5649089217185974,
+      "learning_rate": 0.00047058093126385814,
+      "loss": 0.7964,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.4905894994735718,
+      "learning_rate": 0.0004695210643015521,
+      "loss": 0.7767,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.5945530533790588,
+      "learning_rate": 0.00046846119733924617,
+      "loss": 0.7485,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.47223448753356934,
+      "learning_rate": 0.00046740133037694015,
+      "loss": 0.7412,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.4855833053588867,
+      "learning_rate": 0.00046634146341463414,
+      "loss": 0.7992,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.420284628868103,
+      "learning_rate": 0.0004652815964523282,
+      "loss": 0.7427,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.517633855342865,
+      "learning_rate": 0.0004642217294900222,
+      "loss": 0.7918,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.434706449508667,
+      "learning_rate": 0.0004631618625277162,
+      "loss": 0.7891,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.3698730766773224,
+      "learning_rate": 0.00046210199556541025,
+      "loss": 0.7076,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.3561922609806061,
+      "learning_rate": 0.00046104212860310423,
+      "loss": 0.7893,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.3815233111381531,
+      "learning_rate": 0.0004599822616407982,
+      "loss": 0.7999,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.38611900806427,
+      "learning_rate": 0.00045892239467849226,
+      "loss": 0.7928,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.29186370968818665,
+      "learning_rate": 0.0004578625277161863,
+      "loss": 0.724,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.3245350420475006,
+      "learning_rate": 0.0004568026607538803,
+      "loss": 0.7503,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.3803184926509857,
+      "learning_rate": 0.00045574279379157433,
+      "loss": 0.7455,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.3178353011608124,
+      "learning_rate": 0.00045468292682926826,
+      "loss": 0.7207,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.4353942573070526,
+      "learning_rate": 0.0004536230598669623,
+      "loss": 0.8268,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.3097940981388092,
+      "learning_rate": 0.00045256319290465634,
+      "loss": 0.6621,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.3318345546722412,
+      "learning_rate": 0.00045150332594235033,
+      "loss": 0.7092,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.31531524658203125,
+      "learning_rate": 0.00045044345898004437,
+      "loss": 0.7668,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.3566637933254242,
+      "learning_rate": 0.0004493835920177384,
+      "loss": 0.7545,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.36444291472435,
+      "learning_rate": 0.00044832372505543234,
+      "loss": 0.8064,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.3560720980167389,
+      "learning_rate": 0.0004472638580931264,
+      "loss": 0.7774,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.3715183734893799,
+      "learning_rate": 0.0004462039911308204,
+      "loss": 0.7131,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.2921788692474365,
+      "learning_rate": 0.0004451441241685144,
+      "loss": 0.8009,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.29083380103111267,
+      "learning_rate": 0.00044408425720620845,
+      "loss": 0.7223,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.3140243887901306,
+      "learning_rate": 0.0004430243902439025,
+      "loss": 0.7196,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.3676493465900421,
+      "learning_rate": 0.0004419645232815964,
+      "loss": 0.7143,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.3598462641239166,
+      "learning_rate": 0.00044090465631929047,
+      "loss": 0.7474,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.3195889890193939,
+      "learning_rate": 0.0004398447893569845,
+      "loss": 0.7229,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.30827897787094116,
+      "learning_rate": 0.0004387849223946785,
+      "loss": 0.7428,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.38703453540802,
+      "learning_rate": 0.00043772505543237253,
+      "loss": 0.7169,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.28942254185676575,
+      "learning_rate": 0.0004366651884700666,
+      "loss": 0.7456,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.35373979806900024,
+      "learning_rate": 0.0004356053215077605,
+      "loss": 0.7703,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.3619854748249054,
+      "learning_rate": 0.00043454545454545455,
+      "loss": 0.6991,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.3936954438686371,
+      "learning_rate": 0.0004334855875831486,
+      "loss": 0.7505,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.31419533491134644,
+      "learning_rate": 0.0004324257206208426,
+      "loss": 0.7218,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.31622064113616943,
+      "learning_rate": 0.0004313658536585366,
+      "loss": 0.7133,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.31881847977638245,
+      "learning_rate": 0.00043030598669623066,
+      "loss": 0.7015,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.29825660586357117,
+      "learning_rate": 0.0004292461197339246,
+      "loss": 0.7513,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.28996437788009644,
+      "learning_rate": 0.00042818625277161863,
+      "loss": 0.7417,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.317898690700531,
+      "learning_rate": 0.00042712638580931267,
+      "loss": 0.7547,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.35207676887512207,
+      "learning_rate": 0.00042606651884700666,
+      "loss": 0.8215,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.2996538579463959,
+      "learning_rate": 0.0004250066518847007,
+      "loss": 0.7897,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.35331282019615173,
+      "learning_rate": 0.00042394678492239474,
+      "loss": 0.7466,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.30339422821998596,
+      "learning_rate": 0.00042288691796008867,
+      "loss": 0.7079,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.35229793190956116,
+      "learning_rate": 0.0004218270509977827,
+      "loss": 0.7322,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.3471188545227051,
+      "learning_rate": 0.00042076718403547675,
+      "loss": 0.6908,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.384351521730423,
+      "learning_rate": 0.00041970731707317074,
+      "loss": 0.6937,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.34261906147003174,
+      "learning_rate": 0.0004186474501108648,
+      "loss": 0.694,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.36659127473831177,
+      "learning_rate": 0.0004175875831485588,
+      "loss": 0.7186,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.3876580595970154,
+      "learning_rate": 0.00041652771618625275,
+      "loss": 0.7474,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.3435872495174408,
+      "learning_rate": 0.0004154678492239468,
+      "loss": 0.7313,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.2954373061656952,
+      "learning_rate": 0.00041440798226164083,
+      "loss": 0.6693,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.2931239604949951,
+      "learning_rate": 0.0004133481152993348,
+      "loss": 0.7175,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.37997666001319885,
+      "learning_rate": 0.00041228824833702886,
+      "loss": 0.704,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.3305527865886688,
+      "learning_rate": 0.00041122838137472285,
+      "loss": 0.7234,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.33284375071525574,
+      "learning_rate": 0.00041016851441241683,
+      "loss": 0.6931,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.32701659202575684,
+      "learning_rate": 0.00040910864745011087,
+      "loss": 0.7191,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.32257601618766785,
+      "learning_rate": 0.00040804878048780486,
+      "loss": 0.6495,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.34117209911346436,
+      "learning_rate": 0.0004069889135254989,
+      "loss": 0.7386,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.41902703046798706,
+      "learning_rate": 0.00040592904656319294,
+      "loss": 0.7807,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.3014705181121826,
+      "learning_rate": 0.0004048691796008869,
+      "loss": 0.6529,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.34272533655166626,
+      "learning_rate": 0.00040380931263858097,
+      "loss": 0.7318,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.3316797614097595,
+      "learning_rate": 0.00040274944567627495,
+      "loss": 0.6452,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.290902704000473,
+      "learning_rate": 0.00040168957871396894,
+      "loss": 0.742,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.34589096903800964,
+      "learning_rate": 0.000400629711751663,
+      "loss": 0.7207,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.35719630122184753,
+      "learning_rate": 0.000399569844789357,
+      "loss": 0.7156,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.36912935972213745,
+      "learning_rate": 0.000398509977827051,
+      "loss": 0.7168,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.3709248900413513,
+      "learning_rate": 0.00039745011086474505,
+      "loss": 0.7413,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.3554258942604065,
+      "learning_rate": 0.00039639024390243904,
+      "loss": 0.7422,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.2682874798774719,
+      "learning_rate": 0.000395330376940133,
+      "loss": 0.6487,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.275944322347641,
+      "learning_rate": 0.00039427050997782706,
+      "loss": 0.7031,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.3202199935913086,
+      "learning_rate": 0.0003932106430155211,
+      "loss": 0.6992,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.3686879575252533,
+      "learning_rate": 0.0003921507760532151,
+      "loss": 0.7499,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.303440660238266,
+      "learning_rate": 0.00039109090909090913,
+      "loss": 0.7126,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.3335700035095215,
+      "learning_rate": 0.0003900310421286031,
+      "loss": 0.782,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.33381161093711853,
+      "learning_rate": 0.0003889711751662971,
+      "loss": 0.6969,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.30890610814094543,
+      "learning_rate": 0.00038791130820399114,
+      "loss": 0.7082,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.3305893540382385,
+      "learning_rate": 0.0003868514412416852,
+      "loss": 0.7532,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.29973316192626953,
+      "learning_rate": 0.00038579157427937917,
+      "loss": 0.6992,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.2805730402469635,
+      "learning_rate": 0.0003847317073170732,
+      "loss": 0.7513,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.29244521260261536,
+      "learning_rate": 0.0003836718403547672,
+      "loss": 0.7227,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.2936287224292755,
+      "learning_rate": 0.0003826119733924612,
+      "loss": 0.7598,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.30633246898651123,
+      "learning_rate": 0.0003815521064301552,
+      "loss": 0.6596,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.3642038404941559,
+      "learning_rate": 0.00038049223946784927,
+      "loss": 0.7832,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.3244490921497345,
+      "learning_rate": 0.00037943237250554325,
+      "loss": 0.6916,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.3080962896347046,
+      "learning_rate": 0.0003783725055432373,
+      "loss": 0.6874,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.340778648853302,
+      "learning_rate": 0.0003773126385809313,
+      "loss": 0.8066,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.3969302177429199,
+      "learning_rate": 0.00037625277161862527,
+      "loss": 0.726,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.30715158581733704,
+      "learning_rate": 0.0003751929046563193,
+      "loss": 0.7383,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.38129615783691406,
+      "learning_rate": 0.00037413303769401335,
+      "loss": 0.7091,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.33120641112327576,
+      "learning_rate": 0.00037307317073170733,
+      "loss": 0.7248,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.3293302059173584,
+      "learning_rate": 0.0003720133037694014,
+      "loss": 0.5786,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.32738253474235535,
+      "learning_rate": 0.00037095343680709536,
+      "loss": 0.7797,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.31135183572769165,
+      "learning_rate": 0.00036989356984478935,
+      "loss": 0.6484,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.40488898754119873,
+      "learning_rate": 0.0003688337028824834,
+      "loss": 0.7333,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.33448660373687744,
+      "learning_rate": 0.0003677738359201774,
+      "loss": 0.7262,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.38866227865219116,
+      "learning_rate": 0.0003667139689578714,
+      "loss": 0.6933,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.3379201591014862,
+      "learning_rate": 0.00036565410199556546,
+      "loss": 0.6609,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.33066609501838684,
+      "learning_rate": 0.0003645942350332594,
+      "loss": 0.725,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.2952742278575897,
+      "learning_rate": 0.00036353436807095343,
+      "loss": 0.6916,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.3941051661968231,
+      "learning_rate": 0.00036247450110864747,
+      "loss": 0.7429,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.3148791491985321,
+      "learning_rate": 0.00036141463414634146,
+      "loss": 0.7121,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.3531208336353302,
+      "learning_rate": 0.0003603547671840355,
+      "loss": 0.7297,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.3178044855594635,
+      "learning_rate": 0.00035929490022172954,
+      "loss": 0.7168,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.30421027541160583,
+      "learning_rate": 0.00035823503325942347,
+      "loss": 0.7223,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.3736768364906311,
+      "learning_rate": 0.0003571751662971175,
+      "loss": 0.6606,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.3562946617603302,
+      "learning_rate": 0.00035611529933481155,
+      "loss": 0.7329,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.3355368375778198,
+      "learning_rate": 0.00035505543237250554,
+      "loss": 0.6589,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.3533897399902344,
+      "learning_rate": 0.0003539955654101996,
+      "loss": 0.6781,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.31134122610092163,
+      "learning_rate": 0.0003529356984478936,
+      "loss": 0.6875,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.3257146179676056,
+      "learning_rate": 0.00035187583148558755,
+      "loss": 0.693,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.355998694896698,
+      "learning_rate": 0.0003508159645232816,
+      "loss": 0.7246,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.30442821979522705,
+      "learning_rate": 0.00034975609756097563,
+      "loss": 0.7177,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.2803910970687866,
+      "learning_rate": 0.0003486962305986696,
+      "loss": 0.7422,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.3258972465991974,
+      "learning_rate": 0.00034763636363636366,
+      "loss": 0.7031,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.382231205701828,
+      "learning_rate": 0.0003465764966740577,
+      "loss": 0.7223,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.3049597144126892,
+      "learning_rate": 0.00034551662971175163,
+      "loss": 0.7557,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.34174099564552307,
+      "learning_rate": 0.00034445676274944567,
+      "loss": 0.729,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.348481684923172,
+      "learning_rate": 0.0003433968957871397,
+      "loss": 0.7002,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.28441721200942993,
+      "learning_rate": 0.0003423370288248337,
+      "loss": 0.7053,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.3341362178325653,
+      "learning_rate": 0.00034127716186252774,
+      "loss": 0.7317,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.3288741409778595,
+      "learning_rate": 0.0003402172949002218,
+      "loss": 0.7089,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.3161088526248932,
+      "learning_rate": 0.00033915742793791577,
+      "loss": 0.6842,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.3017628788948059,
+      "learning_rate": 0.00033809756097560975,
+      "loss": 0.6552,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.2661060690879822,
+      "learning_rate": 0.0003370376940133038,
+      "loss": 0.7478,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.31222012639045715,
+      "learning_rate": 0.0003359778270509978,
+      "loss": 0.7552,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.43476974964141846,
+      "learning_rate": 0.0003349179600886918,
+      "loss": 0.758,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.3367742598056793,
+      "learning_rate": 0.00033385809312638586,
+      "loss": 0.7794,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.3539772927761078,
+      "learning_rate": 0.00033279822616407985,
+      "loss": 0.7972,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.28672459721565247,
+      "learning_rate": 0.00033173835920177384,
+      "loss": 0.7016,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.28496575355529785,
+      "learning_rate": 0.0003306784922394679,
+      "loss": 0.7164,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.2734069228172302,
+      "learning_rate": 0.00032961862527716186,
+      "loss": 0.8092,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.26828694343566895,
+      "learning_rate": 0.0003285587583148559,
+      "loss": 0.7474,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.32626521587371826,
+      "learning_rate": 0.00032749889135254994,
+      "loss": 0.7146,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.3634294271469116,
+      "learning_rate": 0.00032643902439024393,
+      "loss": 0.7179,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.30671507120132446,
+      "learning_rate": 0.0003253791574279379,
+      "loss": 0.7103,
+      "step": 150
+    },
+    {
+      "epoch": 0.9956043956043956,
+      "grad_norm": 0.3247479498386383,
+      "learning_rate": 0.0003243192904656319,
+      "loss": 0.7221,
+      "step": 151
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.42680439352989197,
+      "learning_rate": 0.00032325942350332594,
+      "loss": 0.7161,
+      "step": 152
+    },
+    {
+      "epoch": 1.0065934065934066,
+      "grad_norm": 0.36276939511299133,
+      "learning_rate": 0.00032219955654102,
+      "loss": 0.7322,
+      "step": 153
+    },
+    {
+      "epoch": 1.0131868131868131,
+      "grad_norm": 0.3108954131603241,
+      "learning_rate": 0.00032113968957871397,
+      "loss": 0.673,
+      "step": 154
+    },
+    {
+      "epoch": 1.0197802197802197,
+      "grad_norm": 0.3481237292289734,
+      "learning_rate": 0.000320079822616408,
+      "loss": 0.6863,
+      "step": 155
+    },
+    {
+      "epoch": 1.0263736263736263,
+      "grad_norm": 0.4196075201034546,
+      "learning_rate": 0.000319019955654102,
+      "loss": 0.6962,
+      "step": 156
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.3725369870662689,
+      "learning_rate": 0.000317960088691796,
+      "loss": 0.6477,
+      "step": 157
+    },
+    {
+      "epoch": 1.0395604395604396,
+      "grad_norm": 0.3431801497936249,
+      "learning_rate": 0.00031690022172949,
+      "loss": 0.7138,
+      "step": 158
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.352556973695755,
+      "learning_rate": 0.00031584035476718407,
+      "loss": 0.696,
+      "step": 159
+    },
+    {
+      "epoch": 1.0527472527472528,
+      "grad_norm": 0.3816937208175659,
+      "learning_rate": 0.00031478048780487805,
+      "loss": 0.6795,
+      "step": 160
+    },
+    {
+      "epoch": 1.0593406593406594,
+      "grad_norm": 0.3353464901447296,
+      "learning_rate": 0.0003137206208425721,
+      "loss": 0.6945,
+      "step": 161
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.3413096070289612,
+      "learning_rate": 0.0003126607538802661,
+      "loss": 0.6986,
+      "step": 162
+    },
+    {
+      "epoch": 1.0725274725274725,
+      "grad_norm": 0.39247822761535645,
+      "learning_rate": 0.00031160088691796007,
+      "loss": 0.6975,
+      "step": 163
+    },
+    {
+      "epoch": 1.079120879120879,
+      "grad_norm": 0.37605905532836914,
+      "learning_rate": 0.0003105410199556541,
+      "loss": 0.6648,
+      "step": 164
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.3390028476715088,
+      "learning_rate": 0.00030948115299334815,
+      "loss": 0.6513,
+      "step": 165
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 0.3718453049659729,
+      "learning_rate": 0.00030842128603104213,
+      "loss": 0.6919,
+      "step": 166
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.2975955307483673,
+      "learning_rate": 0.0003073614190687362,
+      "loss": 0.6299,
+      "step": 167
+    },
+    {
+      "epoch": 1.1054945054945056,
+      "grad_norm": 0.34555625915527344,
+      "learning_rate": 0.00030630155210643016,
+      "loss": 0.7005,
+      "step": 168
+    },
+    {
+      "epoch": 1.1120879120879121,
+      "grad_norm": 0.32412344217300415,
+      "learning_rate": 0.00030524168514412415,
+      "loss": 0.6203,
+      "step": 169
+    },
+    {
+      "epoch": 1.1186813186813187,
+      "grad_norm": 0.3432216942310333,
+      "learning_rate": 0.0003041818181818182,
+      "loss": 0.606,
+      "step": 170
+    },
+    {
+      "epoch": 1.1252747252747253,
+      "grad_norm": 0.3454482853412628,
+      "learning_rate": 0.00030312195121951223,
+      "loss": 0.6129,
+      "step": 171
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 0.44866660237312317,
+      "learning_rate": 0.0003020620842572062,
+      "loss": 0.6854,
+      "step": 172
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 0.4065716564655304,
+      "learning_rate": 0.00030100221729490026,
+      "loss": 0.7183,
+      "step": 173
+    },
+    {
+      "epoch": 1.145054945054945,
+      "grad_norm": 0.35473760962486267,
+      "learning_rate": 0.00029994235033259424,
+      "loss": 0.5937,
+      "step": 174
+    },
+    {
+      "epoch": 1.1516483516483516,
+      "grad_norm": 0.4422287940979004,
+      "learning_rate": 0.00029888248337028823,
+      "loss": 0.6083,
+      "step": 175
+    },
+    {
+      "epoch": 1.1582417582417581,
+      "grad_norm": 0.3578943908214569,
+      "learning_rate": 0.00029782261640798227,
+      "loss": 0.6769,
+      "step": 176
+    },
+    {
+      "epoch": 1.164835164835165,
+      "grad_norm": 0.3340145945549011,
+      "learning_rate": 0.0002967627494456763,
+      "loss": 0.644,
+      "step": 177
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 0.33603644371032715,
+      "learning_rate": 0.0002957028824833703,
+      "loss": 0.645,
+      "step": 178
+    },
+    {
+      "epoch": 1.178021978021978,
+      "grad_norm": 0.3559483289718628,
+      "learning_rate": 0.00029464301552106434,
+      "loss": 0.6179,
+      "step": 179
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.38981226086616516,
+      "learning_rate": 0.0002935831485587583,
+      "loss": 0.6229,
+      "step": 180
+    },
+    {
+      "epoch": 1.1912087912087912,
+      "grad_norm": 0.48952823877334595,
+      "learning_rate": 0.0002925232815964523,
+      "loss": 0.7109,
+      "step": 181
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 0.36474210023880005,
+      "learning_rate": 0.00029146341463414635,
+      "loss": 0.6027,
+      "step": 182
+    },
+    {
+      "epoch": 1.2043956043956043,
+      "grad_norm": 0.34098976850509644,
+      "learning_rate": 0.0002904035476718404,
+      "loss": 0.7102,
+      "step": 183
+    },
+    {
+      "epoch": 1.210989010989011,
+      "grad_norm": 0.34124574065208435,
+      "learning_rate": 0.0002893436807095344,
+      "loss": 0.6423,
+      "step": 184
+    },
+    {
+      "epoch": 1.2175824175824177,
+      "grad_norm": 0.3932075500488281,
+      "learning_rate": 0.0002882838137472284,
+      "loss": 0.6671,
+      "step": 185
+    },
+    {
+      "epoch": 1.2241758241758243,
+      "grad_norm": 0.33542463183403015,
+      "learning_rate": 0.0002872239467849224,
+      "loss": 0.6803,
+      "step": 186
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.3534783124923706,
+      "learning_rate": 0.0002861640798226164,
+      "loss": 0.6576,
+      "step": 187
+    },
+    {
+      "epoch": 1.2373626373626374,
+      "grad_norm": 0.40464842319488525,
+      "learning_rate": 0.00028510421286031043,
+      "loss": 0.6706,
+      "step": 188
+    },
+    {
+      "epoch": 1.243956043956044,
+      "grad_norm": 0.40317490696907043,
+      "learning_rate": 0.0002840443458980045,
+      "loss": 0.7072,
+      "step": 189
+    },
+    {
+      "epoch": 1.2505494505494505,
+      "grad_norm": 0.4195561707019806,
+      "learning_rate": 0.00028298447893569846,
+      "loss": 0.6661,
+      "step": 190
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.38662609457969666,
+      "learning_rate": 0.0002819246119733925,
+      "loss": 0.6754,
+      "step": 191
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 0.3110015094280243,
+      "learning_rate": 0.00028086474501108643,
+      "loss": 0.6553,
+      "step": 192
+    },
+    {
+      "epoch": 1.2703296703296703,
+      "grad_norm": 0.3761013150215149,
+      "learning_rate": 0.0002798048780487805,
+      "loss": 0.7035,
+      "step": 193
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 0.38549262285232544,
+      "learning_rate": 0.0002787450110864745,
+      "loss": 0.7035,
+      "step": 194
+    },
+    {
+      "epoch": 1.2835164835164834,
+      "grad_norm": 0.33969804644584656,
+      "learning_rate": 0.0002776851441241685,
+      "loss": 0.5982,
+      "step": 195
+    },
+    {
+      "epoch": 1.2901098901098902,
+      "grad_norm": 0.38856765627861023,
+      "learning_rate": 0.00027662527716186254,
+      "loss": 0.6633,
+      "step": 196
+    },
+    {
+      "epoch": 1.2967032967032968,
+      "grad_norm": 0.40017169713974,
+      "learning_rate": 0.0002755654101995566,
+      "loss": 0.5817,
+      "step": 197
+    },
+    {
+      "epoch": 1.3032967032967033,
+      "grad_norm": 0.4068447947502136,
+      "learning_rate": 0.0002745055432372505,
+      "loss": 0.7324,
+      "step": 198
+    },
+    {
+      "epoch": 1.30989010989011,
+      "grad_norm": 0.40120214223861694,
+      "learning_rate": 0.00027344567627494455,
+      "loss": 0.6351,
+      "step": 199
+    },
+    {
+      "epoch": 1.3164835164835165,
+      "grad_norm": 0.3413095772266388,
+      "learning_rate": 0.0002723858093126386,
+      "loss": 0.6304,
+      "step": 200
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 0.4990409016609192,
+      "learning_rate": 0.0002713259423503326,
+      "loss": 0.7766,
+      "step": 201
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 0.42951729893684387,
+      "learning_rate": 0.0002702660753880266,
+      "loss": 0.6906,
+      "step": 202
+    },
+    {
+      "epoch": 1.3362637362637364,
+      "grad_norm": 0.3540504276752472,
+      "learning_rate": 0.00026920620842572066,
+      "loss": 0.6968,
+      "step": 203
+    },
+    {
+      "epoch": 1.342857142857143,
+      "grad_norm": 0.48668473958969116,
+      "learning_rate": 0.00026814634146341465,
+      "loss": 0.6692,
+      "step": 204
+    },
+    {
+      "epoch": 1.3494505494505495,
+      "grad_norm": 0.37050965428352356,
+      "learning_rate": 0.00026708647450110864,
+      "loss": 0.6669,
+      "step": 205
+    },
+    {
+      "epoch": 1.3560439560439561,
+      "grad_norm": 0.39586934447288513,
+      "learning_rate": 0.0002660266075388027,
+      "loss": 0.6758,
+      "step": 206
+    },
+    {
+      "epoch": 1.3626373626373627,
+      "grad_norm": 0.40397927165031433,
+      "learning_rate": 0.00026496674057649666,
+      "loss": 0.6899,
+      "step": 207
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.37612348794937134,
+      "learning_rate": 0.0002639068736141907,
+      "loss": 0.6707,
+      "step": 208
+    },
+    {
+      "epoch": 1.3758241758241758,
+      "grad_norm": 0.3504735231399536,
+      "learning_rate": 0.00026284700665188474,
+      "loss": 0.6767,
+      "step": 209
+    },
+    {
+      "epoch": 1.3824175824175824,
+      "grad_norm": 0.35173776745796204,
+      "learning_rate": 0.00026178713968957873,
+      "loss": 0.5735,
+      "step": 210
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.572415523098624e+16,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

seed2/checkpoint-210/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221d20e98f92f73763cd808ab93d1bc7e458ae3eb6047a59a874501c3a1b74cc
+size 6289