Upload folder using huggingface_hub

.gitattributes

@@ -45,3 +45,4 @@ checkpoint-210/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-255/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-270/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-270/README.md

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

checkpoint-270/adapter_config.json

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

checkpoint-270/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f204a2299f6e5a1948f1c8c25437240da8bd98d399772ae3380b57e562c90208
+size 59933632

checkpoint-270/added_tokens.json

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

checkpoint-270/chat_template.jinja

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

checkpoint-270/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bac3369e3df001ba42fe14561ded22da69b12f8d7d8394900f1fa85269a6cf8
+size 120166091

checkpoint-270/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc4c4882f171836578d88678b73a58570743f8aa1254f14e32eb2bb03bddca3
+size 14645

checkpoint-270/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8829cbd30abfcf641fcffd45a34387a673076ba9b36887ecec9c4338dec7a4aa
+size 1465

checkpoint-270/special_tokens_map.json

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

checkpoint-270/tokenizer.json

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

checkpoint-270/tokenizer_config.json

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

checkpoint-270/trainer_state.json

@@ -0,0 +1,1924 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.778021978021978,
+  "eval_steps": 500,
+  "global_step": 270,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 1.3645844459533691,
+      "learning_rate": 0.0,
+      "loss": 2.5037,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 1.660995602607727,
+      "learning_rate": 4e-05,
+      "loss": 2.6031,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 1.6392755508422852,
+      "learning_rate": 8e-05,
+      "loss": 2.9118,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 1.710063099861145,
+      "learning_rate": 0.00012,
+      "loss": 2.7714,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 1.6210428476333618,
+      "learning_rate": 0.00016,
+      "loss": 2.1514,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 2.3645424842834473,
+      "learning_rate": 0.0002,
+      "loss": 2.5283,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 2.700213670730591,
+      "learning_rate": 0.00019955654101995565,
+      "loss": 1.7241,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 1.8606327772140503,
+      "learning_rate": 0.00019911308203991133,
+      "loss": 1.2173,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 0.842186450958252,
+      "learning_rate": 0.00019866962305986697,
+      "loss": 1.3338,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 1.0317293405532837,
+      "learning_rate": 0.00019822616407982261,
+      "loss": 1.5118,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 0.8248395919799805,
+      "learning_rate": 0.00019778270509977829,
+      "loss": 1.0751,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.5275245308876038,
+      "learning_rate": 0.00019733924611973393,
+      "loss": 1.0938,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.45801183581352234,
+      "learning_rate": 0.0001968957871396896,
+      "loss": 1.1561,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.5454519987106323,
+      "learning_rate": 0.00019645232815964525,
+      "loss": 1.2234,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.46795782446861267,
+      "learning_rate": 0.00019600886917960092,
+      "loss": 1.126,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.5097053050994873,
+      "learning_rate": 0.00019556541019955653,
+      "loss": 0.8651,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.39326727390289307,
+      "learning_rate": 0.0001951219512195122,
+      "loss": 1.102,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.4550538659095764,
+      "learning_rate": 0.00019467849223946785,
+      "loss": 1.2287,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.36811986565589905,
+      "learning_rate": 0.00019423503325942352,
+      "loss": 0.9848,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.36873698234558105,
+      "learning_rate": 0.00019379157427937917,
+      "loss": 1.0985,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.40543392300605774,
+      "learning_rate": 0.00019334811529933484,
+      "loss": 1.0776,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.3196291923522949,
+      "learning_rate": 0.00019290465631929045,
+      "loss": 1.1498,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.31376779079437256,
+      "learning_rate": 0.00019246119733924613,
+      "loss": 1.0388,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.2825721502304077,
+      "learning_rate": 0.00019201773835920177,
+      "loss": 1.0112,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.41585949063301086,
+      "learning_rate": 0.00019157427937915744,
+      "loss": 0.8182,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.30083444714546204,
+      "learning_rate": 0.00019113082039911309,
+      "loss": 0.8058,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.3621577322483063,
+      "learning_rate": 0.00019068736141906876,
+      "loss": 1.2748,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.2544698119163513,
+      "learning_rate": 0.0001902439024390244,
+      "loss": 0.8783,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.3715449869632721,
+      "learning_rate": 0.00018980044345898005,
+      "loss": 1.1229,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.39372724294662476,
+      "learning_rate": 0.00018935698447893572,
+      "loss": 1.1051,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.3777405917644501,
+      "learning_rate": 0.00018891352549889136,
+      "loss": 1.2908,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.40752673149108887,
+      "learning_rate": 0.00018847006651884703,
+      "loss": 0.8454,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.3653320074081421,
+      "learning_rate": 0.00018802660753880268,
+      "loss": 1.0931,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.31746864318847656,
+      "learning_rate": 0.00018758314855875832,
+      "loss": 0.8643,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.3374824821949005,
+      "learning_rate": 0.00018713968957871397,
+      "loss": 0.8283,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.26290443539619446,
+      "learning_rate": 0.00018669623059866964,
+      "loss": 0.9068,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.24013353884220123,
+      "learning_rate": 0.00018625277161862528,
+      "loss": 0.9357,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.26812735199928284,
+      "learning_rate": 0.00018580931263858095,
+      "loss": 0.8113,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.2499343603849411,
+      "learning_rate": 0.0001853658536585366,
+      "loss": 0.843,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.28877875208854675,
+      "learning_rate": 0.00018492239467849224,
+      "loss": 0.9069,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.33010339736938477,
+      "learning_rate": 0.0001844789356984479,
+      "loss": 1.1674,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.31647464632987976,
+      "learning_rate": 0.00018403547671840356,
+      "loss": 1.0174,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.31002527475357056,
+      "learning_rate": 0.0001835920177383592,
+      "loss": 1.1348,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.3115866482257843,
+      "learning_rate": 0.00018314855875831487,
+      "loss": 0.8801,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.304898202419281,
+      "learning_rate": 0.00018270509977827052,
+      "loss": 0.7553,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.28940340876579285,
+      "learning_rate": 0.00018226164079822616,
+      "loss": 0.9455,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.3560061752796173,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.9425,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.3070710003376007,
+      "learning_rate": 0.00018137472283813748,
+      "loss": 0.9398,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.36494898796081543,
+      "learning_rate": 0.00018093126385809312,
+      "loss": 1.0877,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.28735437989234924,
+      "learning_rate": 0.0001804878048780488,
+      "loss": 0.9873,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.3916163146495819,
+      "learning_rate": 0.00018004434589800444,
+      "loss": 1.0092,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.33982348442077637,
+      "learning_rate": 0.00017960088691796008,
+      "loss": 0.9233,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.34739887714385986,
+      "learning_rate": 0.00017915742793791575,
+      "loss": 1.201,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.2715175151824951,
+      "learning_rate": 0.0001787139689578714,
+      "loss": 0.9341,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.27719396352767944,
+      "learning_rate": 0.00017827050997782707,
+      "loss": 1.1086,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.3649531900882721,
+      "learning_rate": 0.00017782705099778271,
+      "loss": 0.9422,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.27733761072158813,
+      "learning_rate": 0.00017738359201773839,
+      "loss": 1.0024,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.3377635180950165,
+      "learning_rate": 0.000176940133037694,
+      "loss": 1.0302,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.3234331011772156,
+      "learning_rate": 0.00017649667405764967,
+      "loss": 0.8961,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.4501403272151947,
+      "learning_rate": 0.00017605321507760532,
+      "loss": 1.0076,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.3447868824005127,
+      "learning_rate": 0.000175609756097561,
+      "loss": 0.9882,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.25949928164482117,
+      "learning_rate": 0.00017516629711751663,
+      "loss": 0.8351,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.30628013610839844,
+      "learning_rate": 0.0001747228381374723,
+      "loss": 1.0555,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.417680561542511,
+      "learning_rate": 0.00017427937915742792,
+      "loss": 1.261,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.32843342423439026,
+      "learning_rate": 0.0001738359201773836,
+      "loss": 1.1574,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.37481415271759033,
+      "learning_rate": 0.00017339246119733924,
+      "loss": 1.1188,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.27844470739364624,
+      "learning_rate": 0.0001729490022172949,
+      "loss": 0.9118,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.3192802667617798,
+      "learning_rate": 0.00017250554323725056,
+      "loss": 0.9093,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.2857853174209595,
+      "learning_rate": 0.00017206208425720623,
+      "loss": 0.9354,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.2837400436401367,
+      "learning_rate": 0.00017161862527716187,
+      "loss": 0.895,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.45861223340034485,
+      "learning_rate": 0.00017117516629711752,
+      "loss": 1.0971,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.31916752457618713,
+      "learning_rate": 0.0001707317073170732,
+      "loss": 0.9987,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.32653743028640747,
+      "learning_rate": 0.00017028824833702883,
+      "loss": 0.9662,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.2894360423088074,
+      "learning_rate": 0.0001698447893569845,
+      "loss": 1.0653,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.3567565679550171,
+      "learning_rate": 0.00016940133037694015,
+      "loss": 0.9241,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.256074994802475,
+      "learning_rate": 0.00016895787139689582,
+      "loss": 0.7865,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.33665013313293457,
+      "learning_rate": 0.00016851441241685144,
+      "loss": 1.041,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.2950928807258606,
+      "learning_rate": 0.0001680709534368071,
+      "loss": 0.9518,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.264356791973114,
+      "learning_rate": 0.00016762749445676275,
+      "loss": 0.8075,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.3302100896835327,
+      "learning_rate": 0.00016718403547671842,
+      "loss": 0.8485,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.2833380401134491,
+      "learning_rate": 0.00016674057649667407,
+      "loss": 0.7926,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.3453841507434845,
+      "learning_rate": 0.00016629711751662974,
+      "loss": 0.971,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.2654123604297638,
+      "learning_rate": 0.00016585365853658536,
+      "loss": 1.1499,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.31106314063072205,
+      "learning_rate": 0.00016541019955654103,
+      "loss": 1.0009,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.367225706577301,
+      "learning_rate": 0.00016496674057649667,
+      "loss": 1.0477,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.3222266435623169,
+      "learning_rate": 0.00016452328159645234,
+      "loss": 0.9234,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.29851892590522766,
+      "learning_rate": 0.000164079822616408,
+      "loss": 0.935,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.22740495204925537,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.8715,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.34969761967658997,
+      "learning_rate": 0.0001631929046563193,
+      "loss": 0.9699,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.264044851064682,
+      "learning_rate": 0.00016274944567627495,
+      "loss": 0.8414,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3013779819011688,
+      "learning_rate": 0.0001623059866962306,
+      "loss": 1.0331,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.2941848933696747,
+      "learning_rate": 0.00016186252771618626,
+      "loss": 1.1354,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.2865702211856842,
+      "learning_rate": 0.0001614190687361419,
+      "loss": 0.9942,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.3316570520401001,
+      "learning_rate": 0.00016097560975609758,
+      "loss": 1.0279,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.36422255635261536,
+      "learning_rate": 0.00016053215077605322,
+      "loss": 1.0983,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.35495316982269287,
+      "learning_rate": 0.00016008869179600887,
+      "loss": 0.9114,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.3313552141189575,
+      "learning_rate": 0.00015964523281596454,
+      "loss": 0.7726,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.3033399283885956,
+      "learning_rate": 0.00015920177383592018,
+      "loss": 0.9066,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.2781226933002472,
+      "learning_rate": 0.00015875831485587586,
+      "loss": 0.7253,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.27466264367103577,
+      "learning_rate": 0.0001583148558758315,
+      "loss": 0.7809,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.2644181251525879,
+      "learning_rate": 0.00015787139689578714,
+      "loss": 0.8201,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.28048309683799744,
+      "learning_rate": 0.0001574279379157428,
+      "loss": 0.8246,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.33915644884109497,
+      "learning_rate": 0.00015698447893569846,
+      "loss": 1.0543,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.2994322180747986,
+      "learning_rate": 0.0001565410199556541,
+      "loss": 0.988,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.3395415246486664,
+      "learning_rate": 0.00015609756097560978,
+      "loss": 1.1211,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.34348204731941223,
+      "learning_rate": 0.00015565410199556542,
+      "loss": 0.9442,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.2971911132335663,
+      "learning_rate": 0.00015521064301552106,
+      "loss": 0.8242,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.33131423592567444,
+      "learning_rate": 0.0001547671840354767,
+      "loss": 0.7826,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.2895534336566925,
+      "learning_rate": 0.00015432372505543238,
+      "loss": 0.8066,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.3257606327533722,
+      "learning_rate": 0.00015388026607538802,
+      "loss": 0.8787,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.4537862241268158,
+      "learning_rate": 0.0001534368070953437,
+      "loss": 1.1323,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.3447017967700958,
+      "learning_rate": 0.00015299334811529934,
+      "loss": 0.8249,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.31839004158973694,
+      "learning_rate": 0.00015254988913525498,
+      "loss": 0.8348,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.32188424468040466,
+      "learning_rate": 0.00015210643015521066,
+      "loss": 0.8852,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.29803267121315,
+      "learning_rate": 0.0001516629711751663,
+      "loss": 0.8525,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.35410454869270325,
+      "learning_rate": 0.00015121951219512197,
+      "loss": 0.8925,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.331386923789978,
+      "learning_rate": 0.00015077605321507762,
+      "loss": 1.0724,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.3091491162776947,
+      "learning_rate": 0.0001503325942350333,
+      "loss": 0.83,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.33443400263786316,
+      "learning_rate": 0.0001498891352549889,
+      "loss": 1.1038,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.3229944109916687,
+      "learning_rate": 0.00014944567627494458,
+      "loss": 0.8973,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.3794395327568054,
+      "learning_rate": 0.00014900221729490022,
+      "loss": 1.2263,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.3192094564437866,
+      "learning_rate": 0.0001485587583148559,
+      "loss": 0.9628,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.2878473997116089,
+      "learning_rate": 0.00014811529933481154,
+      "loss": 0.8455,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.3617534637451172,
+      "learning_rate": 0.0001476718403547672,
+      "loss": 0.9286,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.369709312915802,
+      "learning_rate": 0.00014722838137472282,
+      "loss": 1.0686,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.32211580872535706,
+      "learning_rate": 0.0001467849223946785,
+      "loss": 0.9138,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.30251604318618774,
+      "learning_rate": 0.00014634146341463414,
+      "loss": 0.7867,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.31652215123176575,
+      "learning_rate": 0.0001458980044345898,
+      "loss": 0.7945,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.34764522314071655,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 1.0434,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.2947687804698944,
+      "learning_rate": 0.00014501108647450113,
+      "loss": 1.0344,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.3205331861972809,
+      "learning_rate": 0.00014456762749445675,
+      "loss": 0.878,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.3343464434146881,
+      "learning_rate": 0.00014412416851441242,
+      "loss": 0.8587,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.3218705952167511,
+      "learning_rate": 0.00014368070953436806,
+      "loss": 0.9212,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.3400528132915497,
+      "learning_rate": 0.00014323725055432373,
+      "loss": 0.9958,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.35043588280677795,
+      "learning_rate": 0.00014279379157427938,
+      "loss": 1.0509,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.26217612624168396,
+      "learning_rate": 0.00014235033259423505,
+      "loss": 0.7566,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.2991839647293091,
+      "learning_rate": 0.0001419068736141907,
+      "loss": 0.9788,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.30057451128959656,
+      "learning_rate": 0.00014146341463414634,
+      "loss": 0.9074,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.39408135414123535,
+      "learning_rate": 0.000141019955654102,
+      "loss": 0.876,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.23441436886787415,
+      "learning_rate": 0.00014057649667405765,
+      "loss": 0.5953,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.2987991273403168,
+      "learning_rate": 0.00014013303769401332,
+      "loss": 0.7754,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.388202965259552,
+      "learning_rate": 0.00013968957871396897,
+      "loss": 1.0875,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.33599621057510376,
+      "learning_rate": 0.00013924611973392464,
+      "loss": 1.14,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.32520949840545654,
+      "learning_rate": 0.00013880266075388026,
+      "loss": 0.7107,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.30610182881355286,
+      "learning_rate": 0.00013835920177383593,
+      "loss": 0.999,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.3671776056289673,
+      "learning_rate": 0.00013791574279379157,
+      "loss": 0.9704,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.3607579171657562,
+      "learning_rate": 0.00013747228381374724,
+      "loss": 0.8812,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.39117431640625,
+      "learning_rate": 0.0001370288248337029,
+      "loss": 0.8481,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.3547092378139496,
+      "learning_rate": 0.00013658536585365856,
+      "loss": 0.888,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.37551409006118774,
+      "learning_rate": 0.00013614190687361418,
+      "loss": 0.979,
+      "step": 150
+    },
+    {
+      "epoch": 0.9956043956043956,
+      "grad_norm": 0.3101620376110077,
+      "learning_rate": 0.00013569844789356985,
+      "loss": 0.985,
+      "step": 151
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.516344428062439,
+      "learning_rate": 0.0001352549889135255,
+      "loss": 1.0138,
+      "step": 152
+    },
+    {
+      "epoch": 1.0065934065934066,
+      "grad_norm": 0.29016128182411194,
+      "learning_rate": 0.00013481152993348116,
+      "loss": 0.842,
+      "step": 153
+    },
+    {
+      "epoch": 1.0131868131868131,
+      "grad_norm": 0.3120655417442322,
+      "learning_rate": 0.0001343680709534368,
+      "loss": 0.772,
+      "step": 154
+    },
+    {
+      "epoch": 1.0197802197802197,
+      "grad_norm": 0.46774476766586304,
+      "learning_rate": 0.00013392461197339248,
+      "loss": 1.1338,
+      "step": 155
+    },
+    {
+      "epoch": 1.0263736263736263,
+      "grad_norm": 0.32568323612213135,
+      "learning_rate": 0.00013348115299334812,
+      "loss": 0.9106,
+      "step": 156
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.27454429864883423,
+      "learning_rate": 0.00013303769401330377,
+      "loss": 0.8237,
+      "step": 157
+    },
+    {
+      "epoch": 1.0395604395604396,
+      "grad_norm": 0.3237532377243042,
+      "learning_rate": 0.00013259423503325944,
+      "loss": 0.8234,
+      "step": 158
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.3151777386665344,
+      "learning_rate": 0.00013215077605321509,
+      "loss": 0.8627,
+      "step": 159
+    },
+    {
+      "epoch": 1.0527472527472528,
+      "grad_norm": 0.3392980396747589,
+      "learning_rate": 0.00013170731707317076,
+      "loss": 1.1008,
+      "step": 160
+    },
+    {
+      "epoch": 1.0593406593406594,
+      "grad_norm": 0.3279169201850891,
+      "learning_rate": 0.0001312638580931264,
+      "loss": 0.8225,
+      "step": 161
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.2922564744949341,
+      "learning_rate": 0.00013082039911308205,
+      "loss": 0.8497,
+      "step": 162
+    },
+    {
+      "epoch": 1.0725274725274725,
+      "grad_norm": 0.36553239822387695,
+      "learning_rate": 0.0001303769401330377,
+      "loss": 0.9354,
+      "step": 163
+    },
+    {
+      "epoch": 1.079120879120879,
+      "grad_norm": 0.36235836148262024,
+      "learning_rate": 0.00012993348115299336,
+      "loss": 0.885,
+      "step": 164
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.33991509675979614,
+      "learning_rate": 0.000129490022172949,
+      "loss": 0.844,
+      "step": 165
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 0.3102955222129822,
+      "learning_rate": 0.00012904656319290468,
+      "loss": 0.7476,
+      "step": 166
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.3623199164867401,
+      "learning_rate": 0.00012860310421286032,
+      "loss": 1.2098,
+      "step": 167
+    },
+    {
+      "epoch": 1.1054945054945056,
+      "grad_norm": 0.32075178623199463,
+      "learning_rate": 0.00012815964523281597,
+      "loss": 0.73,
+      "step": 168
+    },
+    {
+      "epoch": 1.1120879120879121,
+      "grad_norm": 0.3391442596912384,
+      "learning_rate": 0.0001277161862527716,
+      "loss": 0.9461,
+      "step": 169
+    },
+    {
+      "epoch": 1.1186813186813187,
+      "grad_norm": 0.3235054016113281,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.8466,
+      "step": 170
+    },
+    {
+      "epoch": 1.1252747252747253,
+      "grad_norm": 0.6535243391990662,
+      "learning_rate": 0.00012682926829268293,
+      "loss": 0.8928,
+      "step": 171
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 0.32036539912223816,
+      "learning_rate": 0.0001263858093126386,
+      "loss": 0.844,
+      "step": 172
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 0.3938387930393219,
+      "learning_rate": 0.00012594235033259424,
+      "loss": 0.8433,
+      "step": 173
+    },
+    {
+      "epoch": 1.145054945054945,
+      "grad_norm": 0.4355946183204651,
+      "learning_rate": 0.00012549889135254989,
+      "loss": 1.1537,
+      "step": 174
+    },
+    {
+      "epoch": 1.1516483516483516,
+      "grad_norm": 0.3691166937351227,
+      "learning_rate": 0.00012505543237250553,
+      "loss": 0.8501,
+      "step": 175
+    },
+    {
+      "epoch": 1.1582417582417581,
+      "grad_norm": 0.31400832533836365,
+      "learning_rate": 0.0001246119733924612,
+      "loss": 0.7277,
+      "step": 176
+    },
+    {
+      "epoch": 1.164835164835165,
+      "grad_norm": 0.37562212347984314,
+      "learning_rate": 0.00012416851441241685,
+      "loss": 0.8707,
+      "step": 177
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 0.3351406157016754,
+      "learning_rate": 0.00012372505543237252,
+      "loss": 0.9269,
+      "step": 178
+    },
+    {
+      "epoch": 1.178021978021978,
+      "grad_norm": 0.34058475494384766,
+      "learning_rate": 0.00012328159645232816,
+      "loss": 0.7118,
+      "step": 179
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.43138498067855835,
+      "learning_rate": 0.0001228381374722838,
+      "loss": 0.8492,
+      "step": 180
+    },
+    {
+      "epoch": 1.1912087912087912,
+      "grad_norm": 0.3624028265476227,
+      "learning_rate": 0.00012239467849223948,
+      "loss": 0.8998,
+      "step": 181
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 0.31254106760025024,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.6725,
+      "step": 182
+    },
+    {
+      "epoch": 1.2043956043956043,
+      "grad_norm": 0.4228277802467346,
+      "learning_rate": 0.00012150776053215078,
+      "loss": 0.8379,
+      "step": 183
+    },
+    {
+      "epoch": 1.210989010989011,
+      "grad_norm": 0.4453306496143341,
+      "learning_rate": 0.00012106430155210644,
+      "loss": 0.9936,
+      "step": 184
+    },
+    {
+      "epoch": 1.2175824175824177,
+      "grad_norm": 0.35470545291900635,
+      "learning_rate": 0.0001206208425720621,
+      "loss": 0.6873,
+      "step": 185
+    },
+    {
+      "epoch": 1.2241758241758243,
+      "grad_norm": 0.4070935547351837,
+      "learning_rate": 0.00012017738359201774,
+      "loss": 0.9941,
+      "step": 186
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.3927744925022125,
+      "learning_rate": 0.0001197339246119734,
+      "loss": 0.7149,
+      "step": 187
+    },
+    {
+      "epoch": 1.2373626373626374,
+      "grad_norm": 0.3816845417022705,
+      "learning_rate": 0.00011929046563192906,
+      "loss": 0.7821,
+      "step": 188
+    },
+    {
+      "epoch": 1.243956043956044,
+      "grad_norm": 0.48257607221603394,
+      "learning_rate": 0.00011884700665188471,
+      "loss": 0.9079,
+      "step": 189
+    },
+    {
+      "epoch": 1.2505494505494505,
+      "grad_norm": 0.39814940094947815,
+      "learning_rate": 0.00011840354767184036,
+      "loss": 0.8417,
+      "step": 190
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.4431450664997101,
+      "learning_rate": 0.00011796008869179602,
+      "loss": 0.8851,
+      "step": 191
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 0.4541279077529907,
+      "learning_rate": 0.00011751662971175166,
+      "loss": 1.0822,
+      "step": 192
+    },
+    {
+      "epoch": 1.2703296703296703,
+      "grad_norm": 0.39300909638404846,
+      "learning_rate": 0.00011707317073170732,
+      "loss": 0.662,
+      "step": 193
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 0.4353281259536743,
+      "learning_rate": 0.00011662971175166298,
+      "loss": 0.9764,
+      "step": 194
+    },
+    {
+      "epoch": 1.2835164835164834,
+      "grad_norm": 0.45079368352890015,
+      "learning_rate": 0.00011618625277161863,
+      "loss": 0.8678,
+      "step": 195
+    },
+    {
+      "epoch": 1.2901098901098902,
+      "grad_norm": 0.47570279240608215,
+      "learning_rate": 0.00011574279379157429,
+      "loss": 0.9142,
+      "step": 196
+    },
+    {
+      "epoch": 1.2967032967032968,
+      "grad_norm": 0.43498265743255615,
+      "learning_rate": 0.00011529933481152995,
+      "loss": 0.9003,
+      "step": 197
+    },
+    {
+      "epoch": 1.3032967032967033,
+      "grad_norm": 0.4020139276981354,
+      "learning_rate": 0.00011485587583148558,
+      "loss": 0.8674,
+      "step": 198
+    },
+    {
+      "epoch": 1.30989010989011,
+      "grad_norm": 0.4982144236564636,
+      "learning_rate": 0.00011441241685144124,
+      "loss": 0.9978,
+      "step": 199
+    },
+    {
+      "epoch": 1.3164835164835165,
+      "grad_norm": 0.4197104573249817,
+      "learning_rate": 0.0001139689578713969,
+      "loss": 0.8158,
+      "step": 200
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 0.3533661365509033,
+      "learning_rate": 0.00011352549889135255,
+      "loss": 0.7254,
+      "step": 201
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 0.4614444077014923,
+      "learning_rate": 0.00011308203991130821,
+      "loss": 0.8771,
+      "step": 202
+    },
+    {
+      "epoch": 1.3362637362637364,
+      "grad_norm": 0.48093193769454956,
+      "learning_rate": 0.00011263858093126387,
+      "loss": 0.838,
+      "step": 203
+    },
+    {
+      "epoch": 1.342857142857143,
+      "grad_norm": 0.49853581190109253,
+      "learning_rate": 0.00011219512195121953,
+      "loss": 0.8146,
+      "step": 204
+    },
+    {
+      "epoch": 1.3494505494505495,
+      "grad_norm": 0.4436289072036743,
+      "learning_rate": 0.00011175166297117516,
+      "loss": 0.7759,
+      "step": 205
+    },
+    {
+      "epoch": 1.3560439560439561,
+      "grad_norm": 0.47563016414642334,
+      "learning_rate": 0.00011130820399113082,
+      "loss": 0.6754,
+      "step": 206
+    },
+    {
+      "epoch": 1.3626373626373627,
+      "grad_norm": 0.46922051906585693,
+      "learning_rate": 0.00011086474501108647,
+      "loss": 0.9646,
+      "step": 207
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.46633464097976685,
+      "learning_rate": 0.00011042128603104213,
+      "loss": 0.9401,
+      "step": 208
+    },
+    {
+      "epoch": 1.3758241758241758,
+      "grad_norm": 0.3811621367931366,
+      "learning_rate": 0.00010997782705099779,
+      "loss": 0.8297,
+      "step": 209
+    },
+    {
+      "epoch": 1.3824175824175824,
+      "grad_norm": 0.5075516104698181,
+      "learning_rate": 0.00010953436807095345,
+      "loss": 0.8602,
+      "step": 210
+    },
+    {
+      "epoch": 1.389010989010989,
+      "grad_norm": 0.4817669093608856,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.84,
+      "step": 211
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.45805370807647705,
+      "learning_rate": 0.00010864745011086475,
+      "loss": 0.8593,
+      "step": 212
+    },
+    {
+      "epoch": 1.402197802197802,
+      "grad_norm": 0.5276244282722473,
+      "learning_rate": 0.00010820399113082041,
+      "loss": 0.9328,
+      "step": 213
+    },
+    {
+      "epoch": 1.4087912087912087,
+      "grad_norm": 0.3852386176586151,
+      "learning_rate": 0.00010776053215077607,
+      "loss": 0.777,
+      "step": 214
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 0.5280368328094482,
+      "learning_rate": 0.00010731707317073172,
+      "loss": 0.9103,
+      "step": 215
+    },
+    {
+      "epoch": 1.421978021978022,
+      "grad_norm": 0.4720604419708252,
+      "learning_rate": 0.00010687361419068738,
+      "loss": 0.899,
+      "step": 216
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.4391266405582428,
+      "learning_rate": 0.00010643015521064301,
+      "loss": 0.8566,
+      "step": 217
+    },
+    {
+      "epoch": 1.4351648351648352,
+      "grad_norm": 0.4955165684223175,
+      "learning_rate": 0.00010598669623059867,
+      "loss": 0.8369,
+      "step": 218
+    },
+    {
+      "epoch": 1.4417582417582417,
+      "grad_norm": 0.4326469600200653,
+      "learning_rate": 0.00010554323725055433,
+      "loss": 0.6505,
+      "step": 219
+    },
+    {
+      "epoch": 1.4483516483516483,
+      "grad_norm": 0.44879817962646484,
+      "learning_rate": 0.00010509977827050999,
+      "loss": 0.7841,
+      "step": 220
+    },
+    {
+      "epoch": 1.4549450549450549,
+      "grad_norm": 0.5331604480743408,
+      "learning_rate": 0.00010465631929046564,
+      "loss": 0.8574,
+      "step": 221
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.4915289878845215,
+      "learning_rate": 0.0001042128603104213,
+      "loss": 0.791,
+      "step": 222
+    },
+    {
+      "epoch": 1.4681318681318682,
+      "grad_norm": 0.4709063768386841,
+      "learning_rate": 0.00010376940133037693,
+      "loss": 0.6844,
+      "step": 223
+    },
+    {
+      "epoch": 1.4747252747252748,
+      "grad_norm": 0.45887377858161926,
+      "learning_rate": 0.00010332594235033259,
+      "loss": 0.9128,
+      "step": 224
+    },
+    {
+      "epoch": 1.4813186813186814,
+      "grad_norm": 0.4885948896408081,
+      "learning_rate": 0.00010288248337028825,
+      "loss": 0.7761,
+      "step": 225
+    },
+    {
+      "epoch": 1.487912087912088,
+      "grad_norm": 0.39953744411468506,
+      "learning_rate": 0.0001024390243902439,
+      "loss": 0.8216,
+      "step": 226
+    },
+    {
+      "epoch": 1.4945054945054945,
+      "grad_norm": 0.5171068906784058,
+      "learning_rate": 0.00010199556541019956,
+      "loss": 0.9192,
+      "step": 227
+    },
+    {
+      "epoch": 1.501098901098901,
+      "grad_norm": 0.48356959223747253,
+      "learning_rate": 0.00010155210643015522,
+      "loss": 0.8489,
+      "step": 228
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 0.4443300664424896,
+      "learning_rate": 0.00010110864745011087,
+      "loss": 0.8595,
+      "step": 229
+    },
+    {
+      "epoch": 1.5142857142857142,
+      "grad_norm": 0.48143601417541504,
+      "learning_rate": 0.00010066518847006652,
+      "loss": 0.8419,
+      "step": 230
+    },
+    {
+      "epoch": 1.5208791208791208,
+      "grad_norm": 0.5052889585494995,
+      "learning_rate": 0.00010022172949002218,
+      "loss": 0.8372,
+      "step": 231
+    },
+    {
+      "epoch": 1.5274725274725274,
+      "grad_norm": 0.4910125136375427,
+      "learning_rate": 9.977827050997783e-05,
+      "loss": 0.8396,
+      "step": 232
+    },
+    {
+      "epoch": 1.534065934065934,
+      "grad_norm": 0.48845505714416504,
+      "learning_rate": 9.933481152993348e-05,
+      "loss": 0.6537,
+      "step": 233
+    },
+    {
+      "epoch": 1.5406593406593405,
+      "grad_norm": 0.509827196598053,
+      "learning_rate": 9.889135254988914e-05,
+      "loss": 1.0303,
+      "step": 234
+    },
+    {
+      "epoch": 1.5472527472527473,
+      "grad_norm": 0.5705282688140869,
+      "learning_rate": 9.84478935698448e-05,
+      "loss": 0.9851,
+      "step": 235
+    },
+    {
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.44724127650260925,
+      "learning_rate": 9.800443458980046e-05,
+      "loss": 0.7188,
+      "step": 236
+    },
+    {
+      "epoch": 1.5604395604395604,
+      "grad_norm": 0.5184109807014465,
+      "learning_rate": 9.75609756097561e-05,
+      "loss": 1.0064,
+      "step": 237
+    },
+    {
+      "epoch": 1.567032967032967,
+      "grad_norm": 0.5052575469017029,
+      "learning_rate": 9.711751662971176e-05,
+      "loss": 0.8127,
+      "step": 238
+    },
+    {
+      "epoch": 1.5736263736263736,
+      "grad_norm": 0.4074278473854065,
+      "learning_rate": 9.667405764966742e-05,
+      "loss": 0.7519,
+      "step": 239
+    },
+    {
+      "epoch": 1.5802197802197804,
+      "grad_norm": 0.5534332990646362,
+      "learning_rate": 9.623059866962306e-05,
+      "loss": 0.8368,
+      "step": 240
+    },
+    {
+      "epoch": 1.586813186813187,
+      "grad_norm": 0.6015632152557373,
+      "learning_rate": 9.578713968957872e-05,
+      "loss": 0.834,
+      "step": 241
+    },
+    {
+      "epoch": 1.5934065934065935,
+      "grad_norm": 0.510938823223114,
+      "learning_rate": 9.534368070953438e-05,
+      "loss": 0.7493,
+      "step": 242
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.49720829725265503,
+      "learning_rate": 9.490022172949002e-05,
+      "loss": 0.9086,
+      "step": 243
+    },
+    {
+      "epoch": 1.6065934065934067,
+      "grad_norm": 0.5068328976631165,
+      "learning_rate": 9.445676274944568e-05,
+      "loss": 0.8976,
+      "step": 244
+    },
+    {
+      "epoch": 1.6131868131868132,
+      "grad_norm": 0.5591776371002197,
+      "learning_rate": 9.401330376940134e-05,
+      "loss": 0.9067,
+      "step": 245
+    },
+    {
+      "epoch": 1.6197802197802198,
+      "grad_norm": 0.5390080809593201,
+      "learning_rate": 9.356984478935698e-05,
+      "loss": 0.8687,
+      "step": 246
+    },
+    {
+      "epoch": 1.6263736263736264,
+      "grad_norm": 0.511387050151825,
+      "learning_rate": 9.312638580931264e-05,
+      "loss": 0.7652,
+      "step": 247
+    },
+    {
+      "epoch": 1.632967032967033,
+      "grad_norm": 0.40768322348594666,
+      "learning_rate": 9.26829268292683e-05,
+      "loss": 0.8205,
+      "step": 248
+    },
+    {
+      "epoch": 1.6395604395604395,
+      "grad_norm": 0.5464216470718384,
+      "learning_rate": 9.223946784922394e-05,
+      "loss": 0.94,
+      "step": 249
+    },
+    {
+      "epoch": 1.646153846153846,
+      "grad_norm": 0.47660166025161743,
+      "learning_rate": 9.17960088691796e-05,
+      "loss": 0.7779,
+      "step": 250
+    },
+    {
+      "epoch": 1.6527472527472526,
+      "grad_norm": 0.5641666054725647,
+      "learning_rate": 9.135254988913526e-05,
+      "loss": 0.9036,
+      "step": 251
+    },
+    {
+      "epoch": 1.6593406593406592,
+      "grad_norm": 0.48709836602211,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.87,
+      "step": 252
+    },
+    {
+      "epoch": 1.6659340659340658,
+      "grad_norm": 0.39728599786758423,
+      "learning_rate": 9.046563192904656e-05,
+      "loss": 0.7952,
+      "step": 253
+    },
+    {
+      "epoch": 1.6725274725274726,
+      "grad_norm": 0.4963222146034241,
+      "learning_rate": 9.002217294900222e-05,
+      "loss": 0.7242,
+      "step": 254
+    },
+    {
+      "epoch": 1.6791208791208792,
+      "grad_norm": 0.6376790404319763,
+      "learning_rate": 8.957871396895788e-05,
+      "loss": 0.9597,
+      "step": 255
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.572260856628418,
+      "learning_rate": 8.913525498891354e-05,
+      "loss": 0.8838,
+      "step": 256
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.5015119910240173,
+      "learning_rate": 8.869179600886919e-05,
+      "loss": 0.8451,
+      "step": 257
+    },
+    {
+      "epoch": 1.6989010989010989,
+      "grad_norm": 0.488455206155777,
+      "learning_rate": 8.824833702882484e-05,
+      "loss": 0.8349,
+      "step": 258
+    },
+    {
+      "epoch": 1.7054945054945057,
+      "grad_norm": 0.5792441964149475,
+      "learning_rate": 8.78048780487805e-05,
+      "loss": 0.8859,
+      "step": 259
+    },
+    {
+      "epoch": 1.7120879120879122,
+      "grad_norm": 0.4997487962245941,
+      "learning_rate": 8.736141906873615e-05,
+      "loss": 1.0839,
+      "step": 260
+    },
+    {
+      "epoch": 1.7186813186813188,
+      "grad_norm": 0.4827248454093933,
+      "learning_rate": 8.69179600886918e-05,
+      "loss": 0.8513,
+      "step": 261
+    },
+    {
+      "epoch": 1.7252747252747254,
+      "grad_norm": 0.45640331506729126,
+      "learning_rate": 8.647450110864746e-05,
+      "loss": 0.7986,
+      "step": 262
+    },
+    {
+      "epoch": 1.731868131868132,
+      "grad_norm": 0.5226643681526184,
+      "learning_rate": 8.603104212860311e-05,
+      "loss": 0.8307,
+      "step": 263
+    },
+    {
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.592502236366272,
+      "learning_rate": 8.558758314855876e-05,
+      "loss": 0.9358,
+      "step": 264
+    },
+    {
+      "epoch": 1.745054945054945,
+      "grad_norm": 0.5692462921142578,
+      "learning_rate": 8.514412416851442e-05,
+      "loss": 1.0558,
+      "step": 265
+    },
+    {
+      "epoch": 1.7516483516483516,
+      "grad_norm": 0.4775419533252716,
+      "learning_rate": 8.470066518847007e-05,
+      "loss": 0.912,
+      "step": 266
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 0.4994668960571289,
+      "learning_rate": 8.425720620842572e-05,
+      "loss": 0.842,
+      "step": 267
+    },
+    {
+      "epoch": 1.7648351648351648,
+      "grad_norm": 0.5042735934257507,
+      "learning_rate": 8.381374722838138e-05,
+      "loss": 0.7423,
+      "step": 268
+    },
+    {
+      "epoch": 1.7714285714285714,
+      "grad_norm": 0.6815941333770752,
+      "learning_rate": 8.337028824833703e-05,
+      "loss": 0.857,
+      "step": 269
+    },
+    {
+      "epoch": 1.778021978021978,
+      "grad_norm": 0.47586917877197266,
+      "learning_rate": 8.292682926829268e-05,
+      "loss": 0.8728,
+      "step": 270
+    }
+  ],
+  "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": 4.46994101525545e+16,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-270/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ffad603db8321b6781b19623ddaba0aa061d708e42497fae8844413e43bb9d
+size 6417