Upload seed2/checkpoint-150

.gitattributes

@@ -104,3 +104,4 @@ seed2/checkpoint-90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 seed2/checkpoint-135/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+seed2/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text

seed2/checkpoint-150/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-150/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": [
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

seed2/checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f712dff0812d787f7ac64907c5d9fb7b905a8681d4fd4312b85bcd23955ad4b4
+size 80792096

seed2/checkpoint-150/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-150/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-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f03617bcb54a0873c4644974089f472caf324548a5979f063c86b51b45f6dca
+size 161816187

seed2/checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70e810f632cce673be23952df169e64960e5c47ffc534463461062440066524
+size 14645

seed2/checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276dbee112328fe959c71ab013ee8b824d6b627fc92972d23abaeef14e882344
+size 1465

seed2/checkpoint-150/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-150/tokenizer.json

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

seed2/checkpoint-150/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-150/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.989010989010989,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 1.195170283317566,
+      "learning_rate": 0.0,
+      "loss": 1.0821,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 1.0331945419311523,
+      "learning_rate": 9.56e-05,
+      "loss": 1.0763,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 1.1415084600448608,
+      "learning_rate": 0.0001912,
+      "loss": 1.0495,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 1.063579797744751,
+      "learning_rate": 0.0002868,
+      "loss": 0.956,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 0.6625626087188721,
+      "learning_rate": 0.0003824,
+      "loss": 0.8477,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 0.6782878637313843,
+      "learning_rate": 0.000478,
+      "loss": 1.0343,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 0.6161335110664368,
+      "learning_rate": 0.00047694013303769406,
+      "loss": 0.9727,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 0.41984498500823975,
+      "learning_rate": 0.00047588026607538804,
+      "loss": 0.8698,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 0.3116914927959442,
+      "learning_rate": 0.0004748203991130821,
+      "loss": 0.8446,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.29025012254714966,
+      "learning_rate": 0.00047376053215077607,
+      "loss": 0.7877,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 0.39959046244621277,
+      "learning_rate": 0.00047270066518847006,
+      "loss": 0.8688,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.5689778923988342,
+      "learning_rate": 0.0004716407982261641,
+      "loss": 0.8847,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.40798476338386536,
+      "learning_rate": 0.00047058093126385814,
+      "loss": 0.7254,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.6968982219696045,
+      "learning_rate": 0.0004695210643015521,
+      "loss": 0.8179,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.5194700360298157,
+      "learning_rate": 0.00046846119733924617,
+      "loss": 0.7156,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.43927809596061707,
+      "learning_rate": 0.00046740133037694015,
+      "loss": 0.8273,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.3979283571243286,
+      "learning_rate": 0.00046634146341463414,
+      "loss": 0.7288,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.4314859211444855,
+      "learning_rate": 0.0004652815964523282,
+      "loss": 0.7677,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.3548160791397095,
+      "learning_rate": 0.0004642217294900222,
+      "loss": 0.6472,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.38769328594207764,
+      "learning_rate": 0.0004631618625277162,
+      "loss": 0.6578,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.3017254173755646,
+      "learning_rate": 0.00046210199556541025,
+      "loss": 0.7163,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.33315712213516235,
+      "learning_rate": 0.00046104212860310423,
+      "loss": 0.6951,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.3334329426288605,
+      "learning_rate": 0.0004599822616407982,
+      "loss": 0.7464,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.301981121301651,
+      "learning_rate": 0.00045892239467849226,
+      "loss": 0.667,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.3768517076969147,
+      "learning_rate": 0.0004578625277161863,
+      "loss": 0.6719,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.3810518980026245,
+      "learning_rate": 0.0004568026607538803,
+      "loss": 0.7687,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.4689561128616333,
+      "learning_rate": 0.00045574279379157433,
+      "loss": 0.7114,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.3895481824874878,
+      "learning_rate": 0.00045468292682926826,
+      "loss": 0.7328,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.44972071051597595,
+      "learning_rate": 0.0004536230598669623,
+      "loss": 0.708,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.39502742886543274,
+      "learning_rate": 0.00045256319290465634,
+      "loss": 0.7672,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.5479147434234619,
+      "learning_rate": 0.00045150332594235033,
+      "loss": 0.7583,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.33382317423820496,
+      "learning_rate": 0.00045044345898004437,
+      "loss": 0.7369,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.49583446979522705,
+      "learning_rate": 0.0004493835920177384,
+      "loss": 0.8174,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.3855836093425751,
+      "learning_rate": 0.00044832372505543234,
+      "loss": 0.7935,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.45332643389701843,
+      "learning_rate": 0.0004472638580931264,
+      "loss": 0.7593,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.3067397475242615,
+      "learning_rate": 0.0004462039911308204,
+      "loss": 0.6878,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.3372962474822998,
+      "learning_rate": 0.0004451441241685144,
+      "loss": 0.7705,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.40445494651794434,
+      "learning_rate": 0.00044408425720620845,
+      "loss": 0.7849,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.3279916048049927,
+      "learning_rate": 0.0004430243902439025,
+      "loss": 0.715,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.31464719772338867,
+      "learning_rate": 0.0004419645232815964,
+      "loss": 0.7322,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.27914178371429443,
+      "learning_rate": 0.00044090465631929047,
+      "loss": 0.6922,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.27055102586746216,
+      "learning_rate": 0.0004398447893569845,
+      "loss": 0.7071,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.30358147621154785,
+      "learning_rate": 0.0004387849223946785,
+      "loss": 0.7257,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.3098717927932739,
+      "learning_rate": 0.00043772505543237253,
+      "loss": 0.6871,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.32566770911216736,
+      "learning_rate": 0.0004366651884700666,
+      "loss": 0.7264,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.3617362082004547,
+      "learning_rate": 0.0004356053215077605,
+      "loss": 0.6902,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.43403375148773193,
+      "learning_rate": 0.00043454545454545455,
+      "loss": 0.7037,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.33475279808044434,
+      "learning_rate": 0.0004334855875831486,
+      "loss": 0.7261,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.34020453691482544,
+      "learning_rate": 0.0004324257206208426,
+      "loss": 0.6361,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.29145631194114685,
+      "learning_rate": 0.0004313658536585366,
+      "loss": 0.6797,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.35258740186691284,
+      "learning_rate": 0.00043030598669623066,
+      "loss": 0.6811,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.31551578640937805,
+      "learning_rate": 0.0004292461197339246,
+      "loss": 0.6662,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.40033137798309326,
+      "learning_rate": 0.00042818625277161863,
+      "loss": 0.7066,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.34928882122039795,
+      "learning_rate": 0.00042712638580931267,
+      "loss": 0.6704,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.3890458345413208,
+      "learning_rate": 0.00042606651884700666,
+      "loss": 0.7074,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.34585464000701904,
+      "learning_rate": 0.0004250066518847007,
+      "loss": 0.7147,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.2896708548069,
+      "learning_rate": 0.00042394678492239474,
+      "loss": 0.7679,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.3353179395198822,
+      "learning_rate": 0.00042288691796008867,
+      "loss": 0.6415,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.32367175817489624,
+      "learning_rate": 0.0004218270509977827,
+      "loss": 0.7697,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.32652848958969116,
+      "learning_rate": 0.00042076718403547675,
+      "loss": 0.6835,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.2857896089553833,
+      "learning_rate": 0.00041970731707317074,
+      "loss": 0.7343,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.35556867718696594,
+      "learning_rate": 0.0004186474501108648,
+      "loss": 0.6726,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.3160596191883087,
+      "learning_rate": 0.0004175875831485588,
+      "loss": 0.7143,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.3572760224342346,
+      "learning_rate": 0.00041652771618625275,
+      "loss": 0.7587,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.2954725921154022,
+      "learning_rate": 0.0004154678492239468,
+      "loss": 0.6812,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.3745565116405487,
+      "learning_rate": 0.00041440798226164083,
+      "loss": 0.7258,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.3284990191459656,
+      "learning_rate": 0.0004133481152993348,
+      "loss": 0.7153,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.30010706186294556,
+      "learning_rate": 0.00041228824833702886,
+      "loss": 0.6984,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.2915664613246918,
+      "learning_rate": 0.00041122838137472285,
+      "loss": 0.7052,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.29902124404907227,
+      "learning_rate": 0.00041016851441241683,
+      "loss": 0.6934,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.3071542978286743,
+      "learning_rate": 0.00040910864745011087,
+      "loss": 0.708,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.27577969431877136,
+      "learning_rate": 0.00040804878048780486,
+      "loss": 0.7428,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.2982359826564789,
+      "learning_rate": 0.0004069889135254989,
+      "loss": 0.7779,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.30666181445121765,
+      "learning_rate": 0.00040592904656319294,
+      "loss": 0.7067,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.2994212508201599,
+      "learning_rate": 0.0004048691796008869,
+      "loss": 0.6904,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.2912769317626953,
+      "learning_rate": 0.00040380931263858097,
+      "loss": 0.7374,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.26267528533935547,
+      "learning_rate": 0.00040274944567627495,
+      "loss": 0.7415,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.3228910565376282,
+      "learning_rate": 0.00040168957871396894,
+      "loss": 0.6345,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.3353758752346039,
+      "learning_rate": 0.000400629711751663,
+      "loss": 0.6988,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.34910428524017334,
+      "learning_rate": 0.000399569844789357,
+      "loss": 0.6955,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.35183653235435486,
+      "learning_rate": 0.000398509977827051,
+      "loss": 0.668,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.2986193001270294,
+      "learning_rate": 0.00039745011086474505,
+      "loss": 0.7467,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.3669707775115967,
+      "learning_rate": 0.00039639024390243904,
+      "loss": 0.7143,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.3397374749183655,
+      "learning_rate": 0.000395330376940133,
+      "loss": 0.6948,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.36349624395370483,
+      "learning_rate": 0.00039427050997782706,
+      "loss": 0.6381,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.3161599934101105,
+      "learning_rate": 0.0003932106430155211,
+      "loss": 0.7035,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.34338268637657166,
+      "learning_rate": 0.0003921507760532151,
+      "loss": 0.6079,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.3725844621658325,
+      "learning_rate": 0.00039109090909090913,
+      "loss": 0.6842,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.3499543368816376,
+      "learning_rate": 0.0003900310421286031,
+      "loss": 0.6663,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.27967825531959534,
+      "learning_rate": 0.0003889711751662971,
+      "loss": 0.7043,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.42830947041511536,
+      "learning_rate": 0.00038791130820399114,
+      "loss": 0.6066,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.2985455095767975,
+      "learning_rate": 0.0003868514412416852,
+      "loss": 0.7876,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.31391894817352295,
+      "learning_rate": 0.00038579157427937917,
+      "loss": 0.7133,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.3369094133377075,
+      "learning_rate": 0.0003847317073170732,
+      "loss": 0.6965,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.35192903876304626,
+      "learning_rate": 0.0003836718403547672,
+      "loss": 0.738,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.30551454424858093,
+      "learning_rate": 0.0003826119733924612,
+      "loss": 0.6792,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.2987115681171417,
+      "learning_rate": 0.0003815521064301552,
+      "loss": 0.684,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.2904681861400604,
+      "learning_rate": 0.00038049223946784927,
+      "loss": 0.7354,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.3646203279495239,
+      "learning_rate": 0.00037943237250554325,
+      "loss": 0.7511,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.27354785799980164,
+      "learning_rate": 0.0003783725055432373,
+      "loss": 0.6868,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.3103290796279907,
+      "learning_rate": 0.0003773126385809313,
+      "loss": 0.6935,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.33116936683654785,
+      "learning_rate": 0.00037625277161862527,
+      "loss": 0.7088,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.31001362204551697,
+      "learning_rate": 0.0003751929046563193,
+      "loss": 0.7556,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.34533751010894775,
+      "learning_rate": 0.00037413303769401335,
+      "loss": 0.6535,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.3335258364677429,
+      "learning_rate": 0.00037307317073170733,
+      "loss": 0.7302,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.2870931923389435,
+      "learning_rate": 0.0003720133037694014,
+      "loss": 0.6758,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.3254625201225281,
+      "learning_rate": 0.00037095343680709536,
+      "loss": 0.7593,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.30663806200027466,
+      "learning_rate": 0.00036989356984478935,
+      "loss": 0.7143,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.2793548107147217,
+      "learning_rate": 0.0003688337028824834,
+      "loss": 0.7234,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.31374335289001465,
+      "learning_rate": 0.0003677738359201774,
+      "loss": 0.7025,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.3022034764289856,
+      "learning_rate": 0.0003667139689578714,
+      "loss": 0.6732,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.3161036968231201,
+      "learning_rate": 0.00036565410199556546,
+      "loss": 0.7136,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.30554062128067017,
+      "learning_rate": 0.0003645942350332594,
+      "loss": 0.6756,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.29600027203559875,
+      "learning_rate": 0.00036353436807095343,
+      "loss": 0.7567,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.29495969414711,
+      "learning_rate": 0.00036247450110864747,
+      "loss": 0.6993,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.36187559366226196,
+      "learning_rate": 0.00036141463414634146,
+      "loss": 0.7093,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.2875276505947113,
+      "learning_rate": 0.0003603547671840355,
+      "loss": 0.6432,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.3426610827445984,
+      "learning_rate": 0.00035929490022172954,
+      "loss": 0.6835,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.3620908558368683,
+      "learning_rate": 0.00035823503325942347,
+      "loss": 0.756,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.2915194630622864,
+      "learning_rate": 0.0003571751662971175,
+      "loss": 0.6883,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.32311534881591797,
+      "learning_rate": 0.00035611529933481155,
+      "loss": 0.727,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.3259125053882599,
+      "learning_rate": 0.00035505543237250554,
+      "loss": 0.6523,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.33542436361312866,
+      "learning_rate": 0.0003539955654101996,
+      "loss": 0.6245,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.4077654480934143,
+      "learning_rate": 0.0003529356984478936,
+      "loss": 0.7295,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.35173124074935913,
+      "learning_rate": 0.00035187583148558755,
+      "loss": 0.7189,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.3285554349422455,
+      "learning_rate": 0.0003508159645232816,
+      "loss": 0.7179,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.3704049289226532,
+      "learning_rate": 0.00034975609756097563,
+      "loss": 0.7213,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.30321356654167175,
+      "learning_rate": 0.0003486962305986696,
+      "loss": 0.701,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.25718748569488525,
+      "learning_rate": 0.00034763636363636366,
+      "loss": 0.7196,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.38271740078926086,
+      "learning_rate": 0.0003465764966740577,
+      "loss": 0.7567,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.3291567862033844,
+      "learning_rate": 0.00034551662971175163,
+      "loss": 0.7078,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.3053141236305237,
+      "learning_rate": 0.00034445676274944567,
+      "loss": 0.6136,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.300508052110672,
+      "learning_rate": 0.0003433968957871397,
+      "loss": 0.7905,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.3538469970226288,
+      "learning_rate": 0.0003423370288248337,
+      "loss": 0.6981,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.285239040851593,
+      "learning_rate": 0.00034127716186252774,
+      "loss": 0.7405,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.39319372177124023,
+      "learning_rate": 0.0003402172949002218,
+      "loss": 0.7222,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.381517231464386,
+      "learning_rate": 0.00033915742793791577,
+      "loss": 0.712,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.3278730511665344,
+      "learning_rate": 0.00033809756097560975,
+      "loss": 0.6998,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.3165235221385956,
+      "learning_rate": 0.0003370376940133038,
+      "loss": 0.7314,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.34131768345832825,
+      "learning_rate": 0.0003359778270509978,
+      "loss": 0.696,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.3008774518966675,
+      "learning_rate": 0.0003349179600886918,
+      "loss": 0.6536,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.3007766306400299,
+      "learning_rate": 0.00033385809312638586,
+      "loss": 0.6952,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.3253723680973053,
+      "learning_rate": 0.00033279822616407985,
+      "loss": 0.7443,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.31287214159965515,
+      "learning_rate": 0.00033173835920177384,
+      "loss": 0.7231,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.31145626306533813,
+      "learning_rate": 0.0003306784922394679,
+      "loss": 0.6726,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.3471812307834625,
+      "learning_rate": 0.00032961862527716186,
+      "loss": 0.685,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.33790674805641174,
+      "learning_rate": 0.0003285587583148559,
+      "loss": 0.6287,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.29381513595581055,
+      "learning_rate": 0.00032749889135254994,
+      "loss": 0.7269,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.33163395524024963,
+      "learning_rate": 0.00032643902439024393,
+      "loss": 0.6688,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.28233274817466736,
+      "learning_rate": 0.0003253791574279379,
+      "loss": 0.7459,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.87743908857815e+16,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

seed2/checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d9d73f388b6f9c3d812566505957c8cd4adf53feae463e3f717713facbdd6d
+size 6289