Upload folder using huggingface_hub

checkpoint-300/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-300/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": [
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "v_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-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55de7fd2afef8e16db3bd3d092c7c4e318f0de0c28186673cc21453985593d7
+size 59933632

checkpoint-300/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-300/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-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf616d022968f2c34c8f6869ce051c420c9340ccfff0fbebfa2795d870c4137
+size 120166091

checkpoint-300/rng_state.pth

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

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e505675c317883b766f2962f7aad0e9e7af355475f86ff6509ee84802ba836
+size 1465

checkpoint-300/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-300/tokenizer.json

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

checkpoint-300/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-300/trainer_state.json

@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.975824175824176,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 2.0722603797912598,
+      "learning_rate": 0.0,
+      "loss": 3.2131,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 1.6677350997924805,
+      "learning_rate": 4e-05,
+      "loss": 2.5554,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 1.6039100885391235,
+      "learning_rate": 8e-05,
+      "loss": 2.6951,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 1.6277270317077637,
+      "learning_rate": 0.00012,
+      "loss": 2.9003,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 2.0207111835479736,
+      "learning_rate": 0.00016,
+      "loss": 2.6989,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 2.6012003421783447,
+      "learning_rate": 0.0002,
+      "loss": 2.2728,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 2.338730812072754,
+      "learning_rate": 0.00019955654101995565,
+      "loss": 1.7083,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 2.3853142261505127,
+      "learning_rate": 0.00019911308203991133,
+      "loss": 1.5367,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 1.1683852672576904,
+      "learning_rate": 0.00019866962305986697,
+      "loss": 1.2907,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.9153192639350891,
+      "learning_rate": 0.00019822616407982261,
+      "loss": 1.16,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 1.4894245862960815,
+      "learning_rate": 0.00019778270509977829,
+      "loss": 1.5419,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.8791560530662537,
+      "learning_rate": 0.00019733924611973393,
+      "loss": 1.323,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.5337121486663818,
+      "learning_rate": 0.0001968957871396896,
+      "loss": 1.1458,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.5149000883102417,
+      "learning_rate": 0.00019645232815964525,
+      "loss": 1.0808,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.4778643846511841,
+      "learning_rate": 0.00019600886917960092,
+      "loss": 1.088,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.47255033254623413,
+      "learning_rate": 0.00019556541019955653,
+      "loss": 1.0745,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.43144354224205017,
+      "learning_rate": 0.0001951219512195122,
+      "loss": 1.2685,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.38666868209838867,
+      "learning_rate": 0.00019467849223946785,
+      "loss": 1.0754,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.38462671637535095,
+      "learning_rate": 0.00019423503325942352,
+      "loss": 0.9311,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.35871055722236633,
+      "learning_rate": 0.00019379157427937917,
+      "loss": 0.95,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.43639278411865234,
+      "learning_rate": 0.00019334811529933484,
+      "loss": 0.9915,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.3904358446598053,
+      "learning_rate": 0.00019290465631929045,
+      "loss": 1.0229,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.3931411802768707,
+      "learning_rate": 0.00019246119733924613,
+      "loss": 0.897,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.3906334340572357,
+      "learning_rate": 0.00019201773835920177,
+      "loss": 1.0983,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.3786067068576813,
+      "learning_rate": 0.00019157427937915744,
+      "loss": 1.0237,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.36092478036880493,
+      "learning_rate": 0.00019113082039911309,
+      "loss": 0.9729,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.27863427996635437,
+      "learning_rate": 0.00019068736141906876,
+      "loss": 0.9565,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.30928313732147217,
+      "learning_rate": 0.0001902439024390244,
+      "loss": 1.0746,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.3250511586666107,
+      "learning_rate": 0.00018980044345898005,
+      "loss": 0.9843,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.30846866965293884,
+      "learning_rate": 0.00018935698447893572,
+      "loss": 1.0582,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.3773055672645569,
+      "learning_rate": 0.00018891352549889136,
+      "loss": 0.9213,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.3716050386428833,
+      "learning_rate": 0.00018847006651884703,
+      "loss": 0.9804,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.3420291244983673,
+      "learning_rate": 0.00018802660753880268,
+      "loss": 1.0815,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.2763300836086273,
+      "learning_rate": 0.00018758314855875832,
+      "loss": 0.902,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.3937534689903259,
+      "learning_rate": 0.00018713968957871397,
+      "loss": 1.1645,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.27199873328208923,
+      "learning_rate": 0.00018669623059866964,
+      "loss": 0.8738,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.2848569452762604,
+      "learning_rate": 0.00018625277161862528,
+      "loss": 1.0149,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.31365159153938293,
+      "learning_rate": 0.00018580931263858095,
+      "loss": 0.9087,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.24746054410934448,
+      "learning_rate": 0.0001853658536585366,
+      "loss": 0.9948,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.23962347209453583,
+      "learning_rate": 0.00018492239467849224,
+      "loss": 1.1008,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.28994685411453247,
+      "learning_rate": 0.0001844789356984479,
+      "loss": 0.915,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.30804207921028137,
+      "learning_rate": 0.00018403547671840356,
+      "loss": 0.8168,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.397780179977417,
+      "learning_rate": 0.0001835920177383592,
+      "loss": 1.0102,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.28575780987739563,
+      "learning_rate": 0.00018314855875831487,
+      "loss": 1.0709,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.2701430022716522,
+      "learning_rate": 0.00018270509977827052,
+      "loss": 0.9748,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.34878647327423096,
+      "learning_rate": 0.00018226164079822616,
+      "loss": 0.9461,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.29195308685302734,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.9907,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.32355818152427673,
+      "learning_rate": 0.00018137472283813748,
+      "loss": 1.0469,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.3442789614200592,
+      "learning_rate": 0.00018093126385809312,
+      "loss": 1.017,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.3519359827041626,
+      "learning_rate": 0.0001804878048780488,
+      "loss": 0.9013,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.26735949516296387,
+      "learning_rate": 0.00018004434589800444,
+      "loss": 1.0039,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.27275341749191284,
+      "learning_rate": 0.00017960088691796008,
+      "loss": 0.8377,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.3131617307662964,
+      "learning_rate": 0.00017915742793791575,
+      "loss": 1.079,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.3103640675544739,
+      "learning_rate": 0.0001787139689578714,
+      "loss": 1.1037,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.3662891089916229,
+      "learning_rate": 0.00017827050997782707,
+      "loss": 1.2238,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.31076231598854065,
+      "learning_rate": 0.00017782705099778271,
+      "loss": 1.0621,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.364701509475708,
+      "learning_rate": 0.00017738359201773839,
+      "loss": 0.8895,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.3279484212398529,
+      "learning_rate": 0.000176940133037694,
+      "loss": 0.8092,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.4195176959037781,
+      "learning_rate": 0.00017649667405764967,
+      "loss": 1.0942,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.35336142778396606,
+      "learning_rate": 0.00017605321507760532,
+      "loss": 0.9458,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.2668030560016632,
+      "learning_rate": 0.000175609756097561,
+      "loss": 0.7203,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.2878060042858124,
+      "learning_rate": 0.00017516629711751663,
+      "loss": 0.8954,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.28040236234664917,
+      "learning_rate": 0.0001747228381374723,
+      "loss": 0.847,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.38638436794281006,
+      "learning_rate": 0.00017427937915742792,
+      "loss": 0.9154,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.3532263934612274,
+      "learning_rate": 0.0001738359201773836,
+      "loss": 0.967,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.24510745704174042,
+      "learning_rate": 0.00017339246119733924,
+      "loss": 0.9775,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.2761436402797699,
+      "learning_rate": 0.0001729490022172949,
+      "loss": 0.9424,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.2630966901779175,
+      "learning_rate": 0.00017250554323725056,
+      "loss": 0.9213,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.2421293705701828,
+      "learning_rate": 0.00017206208425720623,
+      "loss": 0.903,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.3474556505680084,
+      "learning_rate": 0.00017161862527716187,
+      "loss": 1.0754,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.25004228949546814,
+      "learning_rate": 0.00017117516629711752,
+      "loss": 0.9385,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.3480256199836731,
+      "learning_rate": 0.0001707317073170732,
+      "loss": 0.8971,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.35953742265701294,
+      "learning_rate": 0.00017028824833702883,
+      "loss": 1.0076,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.2506542503833771,
+      "learning_rate": 0.0001698447893569845,
+      "loss": 0.771,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.29169702529907227,
+      "learning_rate": 0.00016940133037694015,
+      "loss": 0.7205,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.26952701807022095,
+      "learning_rate": 0.00016895787139689582,
+      "loss": 1.0331,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.3254987895488739,
+      "learning_rate": 0.00016851441241685144,
+      "loss": 0.9197,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.2873916029930115,
+      "learning_rate": 0.0001680709534368071,
+      "loss": 1.0837,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.3419133424758911,
+      "learning_rate": 0.00016762749445676275,
+      "loss": 0.8816,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.29397767782211304,
+      "learning_rate": 0.00016718403547671842,
+      "loss": 1.0683,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.2623101472854614,
+      "learning_rate": 0.00016674057649667407,
+      "loss": 0.8472,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.44186830520629883,
+      "learning_rate": 0.00016629711751662974,
+      "loss": 1.2116,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.4125562906265259,
+      "learning_rate": 0.00016585365853658536,
+      "loss": 1.0062,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.3349130153656006,
+      "learning_rate": 0.00016541019955654103,
+      "loss": 0.8995,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.34971699118614197,
+      "learning_rate": 0.00016496674057649667,
+      "loss": 0.8694,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.3700663447380066,
+      "learning_rate": 0.00016452328159645234,
+      "loss": 1.0927,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.28516340255737305,
+      "learning_rate": 0.000164079822616408,
+      "loss": 0.8334,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.27797970175743103,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.8108,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.3791492283344269,
+      "learning_rate": 0.0001631929046563193,
+      "loss": 0.8473,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.34083792567253113,
+      "learning_rate": 0.00016274944567627495,
+      "loss": 0.9353,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.28273823857307434,
+      "learning_rate": 0.0001623059866962306,
+      "loss": 0.8956,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.3167821764945984,
+      "learning_rate": 0.00016186252771618626,
+      "loss": 0.8953,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.26616188883781433,
+      "learning_rate": 0.0001614190687361419,
+      "loss": 0.8261,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.237916499376297,
+      "learning_rate": 0.00016097560975609758,
+      "loss": 0.8914,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.32362309098243713,
+      "learning_rate": 0.00016053215077605322,
+      "loss": 0.9295,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.2910405099391937,
+      "learning_rate": 0.00016008869179600887,
+      "loss": 1.047,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.279320627450943,
+      "learning_rate": 0.00015964523281596454,
+      "loss": 0.9465,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.36068761348724365,
+      "learning_rate": 0.00015920177383592018,
+      "loss": 1.0782,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.38116326928138733,
+      "learning_rate": 0.00015875831485587586,
+      "loss": 0.8893,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.28538259863853455,
+      "learning_rate": 0.0001583148558758315,
+      "loss": 0.8015,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.3541967272758484,
+      "learning_rate": 0.00015787139689578714,
+      "loss": 0.8434,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.34469982981681824,
+      "learning_rate": 0.0001574279379157428,
+      "loss": 0.8324,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.4213978946208954,
+      "learning_rate": 0.00015698447893569846,
+      "loss": 0.9444,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.3815469741821289,
+      "learning_rate": 0.0001565410199556541,
+      "loss": 0.8776,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.35397177934646606,
+      "learning_rate": 0.00015609756097560978,
+      "loss": 1.1552,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.2684699594974518,
+      "learning_rate": 0.00015565410199556542,
+      "loss": 0.7798,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.25741079449653625,
+      "learning_rate": 0.00015521064301552106,
+      "loss": 0.8422,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.32127293944358826,
+      "learning_rate": 0.0001547671840354767,
+      "loss": 0.8322,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.3340221643447876,
+      "learning_rate": 0.00015432372505543238,
+      "loss": 0.9798,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.34005194902420044,
+      "learning_rate": 0.00015388026607538802,
+      "loss": 0.8661,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.3739411532878876,
+      "learning_rate": 0.0001534368070953437,
+      "loss": 1.021,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.3668403625488281,
+      "learning_rate": 0.00015299334811529934,
+      "loss": 0.9958,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.3145362436771393,
+      "learning_rate": 0.00015254988913525498,
+      "loss": 1.0518,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.3513026535511017,
+      "learning_rate": 0.00015210643015521066,
+      "loss": 1.0291,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.34400007128715515,
+      "learning_rate": 0.0001516629711751663,
+      "loss": 0.9739,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.3597501516342163,
+      "learning_rate": 0.00015121951219512197,
+      "loss": 1.2324,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.2896723449230194,
+      "learning_rate": 0.00015077605321507762,
+      "loss": 0.8937,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.30057957768440247,
+      "learning_rate": 0.0001503325942350333,
+      "loss": 0.8983,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.3905964195728302,
+      "learning_rate": 0.0001498891352549889,
+      "loss": 0.7167,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.3202342092990875,
+      "learning_rate": 0.00014944567627494458,
+      "loss": 0.8969,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.2450852394104004,
+      "learning_rate": 0.00014900221729490022,
+      "loss": 0.9203,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.3147158622741699,
+      "learning_rate": 0.0001485587583148559,
+      "loss": 0.7941,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.34787628054618835,
+      "learning_rate": 0.00014811529933481154,
+      "loss": 1.0058,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.3001445233821869,
+      "learning_rate": 0.0001476718403547672,
+      "loss": 0.8574,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.3221536874771118,
+      "learning_rate": 0.00014722838137472282,
+      "loss": 1.1149,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.32140639424324036,
+      "learning_rate": 0.0001467849223946785,
+      "loss": 1.1972,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.30501997470855713,
+      "learning_rate": 0.00014634146341463414,
+      "loss": 0.929,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.3393065333366394,
+      "learning_rate": 0.0001458980044345898,
+      "loss": 0.8179,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.3530517816543579,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 1.0044,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.29705455899238586,
+      "learning_rate": 0.00014501108647450113,
+      "loss": 0.9902,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.3452480733394623,
+      "learning_rate": 0.00014456762749445675,
+      "loss": 0.9743,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.2938392162322998,
+      "learning_rate": 0.00014412416851441242,
+      "loss": 0.8866,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.30601850152015686,
+      "learning_rate": 0.00014368070953436806,
+      "loss": 0.9861,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.28590455651283264,
+      "learning_rate": 0.00014323725055432373,
+      "loss": 0.8338,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.2874011695384979,
+      "learning_rate": 0.00014279379157427938,
+      "loss": 0.9952,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.3361506462097168,
+      "learning_rate": 0.00014235033259423505,
+      "loss": 1.0219,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.3574809730052948,
+      "learning_rate": 0.0001419068736141907,
+      "loss": 0.8814,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.4311088025569916,
+      "learning_rate": 0.00014146341463414634,
+      "loss": 0.9013,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.26233023405075073,
+      "learning_rate": 0.000141019955654102,
+      "loss": 0.8736,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.35940396785736084,
+      "learning_rate": 0.00014057649667405765,
+      "loss": 0.9749,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.27149611711502075,
+      "learning_rate": 0.00014013303769401332,
+      "loss": 0.922,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.4147508442401886,
+      "learning_rate": 0.00013968957871396897,
+      "loss": 1.0781,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.295341432094574,
+      "learning_rate": 0.00013924611973392464,
+      "loss": 0.9529,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.36334657669067383,
+      "learning_rate": 0.00013880266075388026,
+      "loss": 0.8085,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.24359752237796783,
+      "learning_rate": 0.00013835920177383593,
+      "loss": 0.7036,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.3110310733318329,
+      "learning_rate": 0.00013791574279379157,
+      "loss": 0.7797,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.3413989841938019,
+      "learning_rate": 0.00013747228381374724,
+      "loss": 1.0027,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.2888753116130829,
+      "learning_rate": 0.0001370288248337029,
+      "loss": 0.8844,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.32249295711517334,
+      "learning_rate": 0.00013658536585365856,
+      "loss": 0.8261,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.4273090660572052,
+      "learning_rate": 0.00013614190687361418,
+      "loss": 1.0066,
+      "step": 150
+    },
+    {
+      "epoch": 0.9956043956043956,
+      "grad_norm": 0.28998544812202454,
+      "learning_rate": 0.00013569844789356985,
+      "loss": 0.8485,
+      "step": 151
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4690309762954712,
+      "learning_rate": 0.0001352549889135255,
+      "loss": 0.6486,
+      "step": 152
+    },
+    {
+      "epoch": 1.0065934065934066,
+      "grad_norm": 0.3045438528060913,
+      "learning_rate": 0.00013481152993348116,
+      "loss": 0.8676,
+      "step": 153
+    },
+    {
+      "epoch": 1.0131868131868131,
+      "grad_norm": 0.3148064613342285,
+      "learning_rate": 0.0001343680709534368,
+      "loss": 0.9665,
+      "step": 154
+    },
+    {
+      "epoch": 1.0197802197802197,
+      "grad_norm": 0.32930025458335876,
+      "learning_rate": 0.00013392461197339248,
+      "loss": 0.8087,
+      "step": 155
+    },
+    {
+      "epoch": 1.0263736263736263,
+      "grad_norm": 0.2816562354564667,
+      "learning_rate": 0.00013348115299334812,
+      "loss": 0.7944,
+      "step": 156
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.3011133074760437,
+      "learning_rate": 0.00013303769401330377,
+      "loss": 0.7996,
+      "step": 157
+    },
+    {
+      "epoch": 1.0395604395604396,
+      "grad_norm": 0.3297262191772461,
+      "learning_rate": 0.00013259423503325944,
+      "loss": 0.8268,
+      "step": 158
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.3308207392692566,
+      "learning_rate": 0.00013215077605321509,
+      "loss": 0.7508,
+      "step": 159
+    },
+    {
+      "epoch": 1.0527472527472528,
+      "grad_norm": 0.3697322607040405,
+      "learning_rate": 0.00013170731707317076,
+      "loss": 0.7181,
+      "step": 160
+    },
+    {
+      "epoch": 1.0593406593406594,
+      "grad_norm": 0.3329128921031952,
+      "learning_rate": 0.0001312638580931264,
+      "loss": 0.7619,
+      "step": 161
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.36436977982521057,
+      "learning_rate": 0.00013082039911308205,
+      "loss": 0.7969,
+      "step": 162
+    },
+    {
+      "epoch": 1.0725274725274725,
+      "grad_norm": 0.33429184556007385,
+      "learning_rate": 0.0001303769401330377,
+      "loss": 1.0637,
+      "step": 163
+    },
+    {
+      "epoch": 1.079120879120879,
+      "grad_norm": 0.4259260892868042,
+      "learning_rate": 0.00012993348115299336,
+      "loss": 0.968,
+      "step": 164
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.3352951109409332,
+      "learning_rate": 0.000129490022172949,
+      "loss": 0.8191,
+      "step": 165
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 0.4135381579399109,
+      "learning_rate": 0.00012904656319290468,
+      "loss": 0.9858,
+      "step": 166
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.3486995995044708,
+      "learning_rate": 0.00012860310421286032,
+      "loss": 0.8626,
+      "step": 167
+    },
+    {
+      "epoch": 1.1054945054945056,
+      "grad_norm": 0.37806546688079834,
+      "learning_rate": 0.00012815964523281597,
+      "loss": 0.9596,
+      "step": 168
+    },
+    {
+      "epoch": 1.1120879120879121,
+      "grad_norm": 0.3310850262641907,
+      "learning_rate": 0.0001277161862527716,
+      "loss": 0.9345,
+      "step": 169
+    },
+    {
+      "epoch": 1.1186813186813187,
+      "grad_norm": 0.3593229651451111,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.9171,
+      "step": 170
+    },
+    {
+      "epoch": 1.1252747252747253,
+      "grad_norm": 0.38787880539894104,
+      "learning_rate": 0.00012682926829268293,
+      "loss": 0.8608,
+      "step": 171
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 0.35755735635757446,
+      "learning_rate": 0.0001263858093126386,
+      "loss": 0.7518,
+      "step": 172
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 0.45123910903930664,
+      "learning_rate": 0.00012594235033259424,
+      "loss": 0.8825,
+      "step": 173
+    },
+    {
+      "epoch": 1.145054945054945,
+      "grad_norm": 0.3731641471385956,
+      "learning_rate": 0.00012549889135254989,
+      "loss": 0.9151,
+      "step": 174
+    },
+    {
+      "epoch": 1.1516483516483516,
+      "grad_norm": 0.4211123287677765,
+      "learning_rate": 0.00012505543237250553,
+      "loss": 0.9073,
+      "step": 175
+    },
+    {
+      "epoch": 1.1582417582417581,
+      "grad_norm": 0.3269520103931427,
+      "learning_rate": 0.0001246119733924612,
+      "loss": 0.7488,
+      "step": 176
+    },
+    {
+      "epoch": 1.164835164835165,
+      "grad_norm": 0.36462828516960144,
+      "learning_rate": 0.00012416851441241685,
+      "loss": 0.8809,
+      "step": 177
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 0.36362966895103455,
+      "learning_rate": 0.00012372505543237252,
+      "loss": 0.8035,
+      "step": 178
+    },
+    {
+      "epoch": 1.178021978021978,
+      "grad_norm": 0.3671634793281555,
+      "learning_rate": 0.00012328159645232816,
+      "loss": 0.9194,
+      "step": 179
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.3457624018192291,
+      "learning_rate": 0.0001228381374722838,
+      "loss": 0.7065,
+      "step": 180
+    },
+    {
+      "epoch": 1.1912087912087912,
+      "grad_norm": 0.4401772618293762,
+      "learning_rate": 0.00012239467849223948,
+      "loss": 0.9267,
+      "step": 181
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 0.4606243371963501,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 0.836,
+      "step": 182
+    },
+    {
+      "epoch": 1.2043956043956043,
+      "grad_norm": 0.3353036940097809,
+      "learning_rate": 0.00012150776053215078,
+      "loss": 0.6218,
+      "step": 183
+    },
+    {
+      "epoch": 1.210989010989011,
+      "grad_norm": 0.4171563684940338,
+      "learning_rate": 0.00012106430155210644,
+      "loss": 0.7914,
+      "step": 184
+    },
+    {
+      "epoch": 1.2175824175824177,
+      "grad_norm": 0.3640008270740509,
+      "learning_rate": 0.0001206208425720621,
+      "loss": 0.8632,
+      "step": 185
+    },
+    {
+      "epoch": 1.2241758241758243,
+      "grad_norm": 0.43573465943336487,
+      "learning_rate": 0.00012017738359201774,
+      "loss": 0.8191,
+      "step": 186
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.3201373219490051,
+      "learning_rate": 0.0001197339246119734,
+      "loss": 0.7808,
+      "step": 187
+    },
+    {
+      "epoch": 1.2373626373626374,
+      "grad_norm": 0.403213769197464,
+      "learning_rate": 0.00011929046563192906,
+      "loss": 0.9004,
+      "step": 188
+    },
+    {
+      "epoch": 1.243956043956044,
+      "grad_norm": 0.4063056707382202,
+      "learning_rate": 0.00011884700665188471,
+      "loss": 0.9791,
+      "step": 189
+    },
+    {
+      "epoch": 1.2505494505494505,
+      "grad_norm": 0.4900030195713043,
+      "learning_rate": 0.00011840354767184036,
+      "loss": 0.8013,
+      "step": 190
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.49652716517448425,
+      "learning_rate": 0.00011796008869179602,
+      "loss": 0.9993,
+      "step": 191
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 0.4425002634525299,
+      "learning_rate": 0.00011751662971175166,
+      "loss": 0.8854,
+      "step": 192
+    },
+    {
+      "epoch": 1.2703296703296703,
+      "grad_norm": 0.46226751804351807,
+      "learning_rate": 0.00011707317073170732,
+      "loss": 0.9893,
+      "step": 193
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 0.3779703378677368,
+      "learning_rate": 0.00011662971175166298,
+      "loss": 0.7875,
+      "step": 194
+    },
+    {
+      "epoch": 1.2835164835164834,
+      "grad_norm": 0.4313388168811798,
+      "learning_rate": 0.00011618625277161863,
+      "loss": 0.7672,
+      "step": 195
+    },
+    {
+      "epoch": 1.2901098901098902,
+      "grad_norm": 0.36810222268104553,
+      "learning_rate": 0.00011574279379157429,
+      "loss": 0.6342,
+      "step": 196
+    },
+    {
+      "epoch": 1.2967032967032968,
+      "grad_norm": 0.37219274044036865,
+      "learning_rate": 0.00011529933481152995,
+      "loss": 0.8084,
+      "step": 197
+    },
+    {
+      "epoch": 1.3032967032967033,
+      "grad_norm": 0.4840892553329468,
+      "learning_rate": 0.00011485587583148558,
+      "loss": 0.804,
+      "step": 198
+    },
+    {
+      "epoch": 1.30989010989011,
+      "grad_norm": 0.4374985694885254,
+      "learning_rate": 0.00011441241685144124,
+      "loss": 0.8546,
+      "step": 199
+    },
+    {
+      "epoch": 1.3164835164835165,
+      "grad_norm": 0.3962724208831787,
+      "learning_rate": 0.0001139689578713969,
+      "loss": 0.7414,
+      "step": 200
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 0.37382033467292786,
+      "learning_rate": 0.00011352549889135255,
+      "loss": 0.8653,
+      "step": 201
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 0.44277113676071167,
+      "learning_rate": 0.00011308203991130821,
+      "loss": 0.8241,
+      "step": 202
+    },
+    {
+      "epoch": 1.3362637362637364,
+      "grad_norm": 0.46842196583747864,
+      "learning_rate": 0.00011263858093126387,
+      "loss": 0.7964,
+      "step": 203
+    },
+    {
+      "epoch": 1.342857142857143,
+      "grad_norm": 0.4144313931465149,
+      "learning_rate": 0.00011219512195121953,
+      "loss": 0.7453,
+      "step": 204
+    },
+    {
+      "epoch": 1.3494505494505495,
+      "grad_norm": 0.4482251703739166,
+      "learning_rate": 0.00011175166297117516,
+      "loss": 0.9691,
+      "step": 205
+    },
+    {
+      "epoch": 1.3560439560439561,
+      "grad_norm": 0.41152456402778625,
+      "learning_rate": 0.00011130820399113082,
+      "loss": 0.7846,
+      "step": 206
+    },
+    {
+      "epoch": 1.3626373626373627,
+      "grad_norm": 0.4497469961643219,
+      "learning_rate": 0.00011086474501108647,
+      "loss": 1.001,
+      "step": 207
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.45057448744773865,
+      "learning_rate": 0.00011042128603104213,
+      "loss": 0.8659,
+      "step": 208
+    },
+    {
+      "epoch": 1.3758241758241758,
+      "grad_norm": 0.4924719035625458,
+      "learning_rate": 0.00010997782705099779,
+      "loss": 0.9199,
+      "step": 209
+    },
+    {
+      "epoch": 1.3824175824175824,
+      "grad_norm": 0.4531312584877014,
+      "learning_rate": 0.00010953436807095345,
+      "loss": 0.9154,
+      "step": 210
+    },
+    {
+      "epoch": 1.389010989010989,
+      "grad_norm": 0.43056848645210266,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.8943,
+      "step": 211
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.4362466037273407,
+      "learning_rate": 0.00010864745011086475,
+      "loss": 0.6209,
+      "step": 212
+    },
+    {
+      "epoch": 1.402197802197802,
+      "grad_norm": 0.5599644780158997,
+      "learning_rate": 0.00010820399113082041,
+      "loss": 0.8043,
+      "step": 213
+    },
+    {
+      "epoch": 1.4087912087912087,
+      "grad_norm": 0.38885924220085144,
+      "learning_rate": 0.00010776053215077607,
+      "loss": 0.8007,
+      "step": 214
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 0.4377254843711853,
+      "learning_rate": 0.00010731707317073172,
+      "loss": 0.8852,
+      "step": 215
+    },
+    {
+      "epoch": 1.421978021978022,
+      "grad_norm": 0.3999001383781433,
+      "learning_rate": 0.00010687361419068738,
+      "loss": 0.9147,
+      "step": 216
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.46440982818603516,
+      "learning_rate": 0.00010643015521064301,
+      "loss": 0.8844,
+      "step": 217
+    },
+    {
+      "epoch": 1.4351648351648352,
+      "grad_norm": 0.46195998787879944,
+      "learning_rate": 0.00010598669623059867,
+      "loss": 0.7938,
+      "step": 218
+    },
+    {
+      "epoch": 1.4417582417582417,
+      "grad_norm": 0.38602715730667114,
+      "learning_rate": 0.00010554323725055433,
+      "loss": 0.6682,
+      "step": 219
+    },
+    {
+      "epoch": 1.4483516483516483,
+      "grad_norm": 0.4990112781524658,
+      "learning_rate": 0.00010509977827050999,
+      "loss": 1.0977,
+      "step": 220
+    },
+    {
+      "epoch": 1.4549450549450549,
+      "grad_norm": 0.3537238836288452,
+      "learning_rate": 0.00010465631929046564,
+      "loss": 0.7534,
+      "step": 221
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.5449821949005127,
+      "learning_rate": 0.0001042128603104213,
+      "loss": 1.017,
+      "step": 222
+    },
+    {
+      "epoch": 1.4681318681318682,
+      "grad_norm": 0.44483187794685364,
+      "learning_rate": 0.00010376940133037693,
+      "loss": 0.8461,
+      "step": 223
+    },
+    {
+      "epoch": 1.4747252747252748,
+      "grad_norm": 0.459046334028244,
+      "learning_rate": 0.00010332594235033259,
+      "loss": 0.8609,
+      "step": 224
+    },
+    {
+      "epoch": 1.4813186813186814,
+      "grad_norm": 0.4648573100566864,
+      "learning_rate": 0.00010288248337028825,
+      "loss": 0.7077,
+      "step": 225
+    },
+    {
+      "epoch": 1.487912087912088,
+      "grad_norm": 0.46832260489463806,
+      "learning_rate": 0.0001024390243902439,
+      "loss": 0.995,
+      "step": 226
+    },
+    {
+      "epoch": 1.4945054945054945,
+      "grad_norm": 0.5647684335708618,
+      "learning_rate": 0.00010199556541019956,
+      "loss": 0.9797,
+      "step": 227
+    },
+    {
+      "epoch": 1.501098901098901,
+      "grad_norm": 0.3861806094646454,
+      "learning_rate": 0.00010155210643015522,
+      "loss": 0.8115,
+      "step": 228
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 0.4496518671512604,
+      "learning_rate": 0.00010110864745011087,
+      "loss": 0.8522,
+      "step": 229
+    },
+    {
+      "epoch": 1.5142857142857142,
+      "grad_norm": 0.428604394197464,
+      "learning_rate": 0.00010066518847006652,
+      "loss": 0.8554,
+      "step": 230
+    },
+    {
+      "epoch": 1.5208791208791208,
+      "grad_norm": 0.46109339594841003,
+      "learning_rate": 0.00010022172949002218,
+      "loss": 0.9584,
+      "step": 231
+    },
+    {
+      "epoch": 1.5274725274725274,
+      "grad_norm": 0.5141985416412354,
+      "learning_rate": 9.977827050997783e-05,
+      "loss": 0.9228,
+      "step": 232
+    },
+    {
+      "epoch": 1.534065934065934,
+      "grad_norm": 0.49423670768737793,
+      "learning_rate": 9.933481152993348e-05,
+      "loss": 0.797,
+      "step": 233
+    },
+    {
+      "epoch": 1.5406593406593405,
+      "grad_norm": 0.47565293312072754,
+      "learning_rate": 9.889135254988914e-05,
+      "loss": 0.886,
+      "step": 234
+    },
+    {
+      "epoch": 1.5472527472527473,
+      "grad_norm": 0.4218743145465851,
+      "learning_rate": 9.84478935698448e-05,
+      "loss": 0.8496,
+      "step": 235
+    },
+    {
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.45972034335136414,
+      "learning_rate": 9.800443458980046e-05,
+      "loss": 0.7161,
+      "step": 236
+    },
+    {
+      "epoch": 1.5604395604395604,
+      "grad_norm": 0.5325828194618225,
+      "learning_rate": 9.75609756097561e-05,
+      "loss": 0.8005,
+      "step": 237
+    },
+    {
+      "epoch": 1.567032967032967,
+      "grad_norm": 0.4783444404602051,
+      "learning_rate": 9.711751662971176e-05,
+      "loss": 0.8983,
+      "step": 238
+    },
+    {
+      "epoch": 1.5736263736263736,
+      "grad_norm": 0.48973003029823303,
+      "learning_rate": 9.667405764966742e-05,
+      "loss": 0.8455,
+      "step": 239
+    },
+    {
+      "epoch": 1.5802197802197804,
+      "grad_norm": 0.4571506977081299,
+      "learning_rate": 9.623059866962306e-05,
+      "loss": 0.8023,
+      "step": 240
+    },
+    {
+      "epoch": 1.586813186813187,
+      "grad_norm": 0.40492597222328186,
+      "learning_rate": 9.578713968957872e-05,
+      "loss": 0.7615,
+      "step": 241
+    },
+    {
+      "epoch": 1.5934065934065935,
+      "grad_norm": 0.44703274965286255,
+      "learning_rate": 9.534368070953438e-05,
+      "loss": 0.8295,
+      "step": 242
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.46830523014068604,
+      "learning_rate": 9.490022172949002e-05,
+      "loss": 0.7677,
+      "step": 243
+    },
+    {
+      "epoch": 1.6065934065934067,
+      "grad_norm": 0.5389837622642517,
+      "learning_rate": 9.445676274944568e-05,
+      "loss": 0.929,
+      "step": 244
+    },
+    {
+      "epoch": 1.6131868131868132,
+      "grad_norm": 0.4897559583187103,
+      "learning_rate": 9.401330376940134e-05,
+      "loss": 0.7929,
+      "step": 245
+    },
+    {
+      "epoch": 1.6197802197802198,
+      "grad_norm": 0.48635751008987427,
+      "learning_rate": 9.356984478935698e-05,
+      "loss": 0.8176,
+      "step": 246
+    },
+    {
+      "epoch": 1.6263736263736264,
+      "grad_norm": 0.5070086717605591,
+      "learning_rate": 9.312638580931264e-05,
+      "loss": 0.8988,
+      "step": 247
+    },
+    {
+      "epoch": 1.632967032967033,
+      "grad_norm": 0.5040110945701599,
+      "learning_rate": 9.26829268292683e-05,
+      "loss": 0.9827,
+      "step": 248
+    },
+    {
+      "epoch": 1.6395604395604395,
+      "grad_norm": 0.4893195331096649,
+      "learning_rate": 9.223946784922394e-05,
+      "loss": 0.9108,
+      "step": 249
+    },
+    {
+      "epoch": 1.646153846153846,
+      "grad_norm": 0.5183725953102112,
+      "learning_rate": 9.17960088691796e-05,
+      "loss": 1.0375,
+      "step": 250
+    },
+    {
+      "epoch": 1.6527472527472526,
+      "grad_norm": 0.5050914287567139,
+      "learning_rate": 9.135254988913526e-05,
+      "loss": 0.8868,
+      "step": 251
+    },
+    {
+      "epoch": 1.6593406593406592,
+      "grad_norm": 0.6539065837860107,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.919,
+      "step": 252
+    },
+    {
+      "epoch": 1.6659340659340658,
+      "grad_norm": 0.5070188045501709,
+      "learning_rate": 9.046563192904656e-05,
+      "loss": 0.8922,
+      "step": 253
+    },
+    {
+      "epoch": 1.6725274725274726,
+      "grad_norm": 0.5404043197631836,
+      "learning_rate": 9.002217294900222e-05,
+      "loss": 0.9583,
+      "step": 254
+    },
+    {
+      "epoch": 1.6791208791208792,
+      "grad_norm": 0.5274918079376221,
+      "learning_rate": 8.957871396895788e-05,
+      "loss": 0.9918,
+      "step": 255
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.5713817477226257,
+      "learning_rate": 8.913525498891354e-05,
+      "loss": 0.7026,
+      "step": 256
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.4875091314315796,
+      "learning_rate": 8.869179600886919e-05,
+      "loss": 0.7633,
+      "step": 257
+    },
+    {
+      "epoch": 1.6989010989010989,
+      "grad_norm": 0.4186699688434601,
+      "learning_rate": 8.824833702882484e-05,
+      "loss": 0.8017,
+      "step": 258
+    },
+    {
+      "epoch": 1.7054945054945057,
+      "grad_norm": 0.4443645477294922,
+      "learning_rate": 8.78048780487805e-05,
+      "loss": 0.6736,
+      "step": 259
+    },
+    {
+      "epoch": 1.7120879120879122,
+      "grad_norm": 0.4955357611179352,
+      "learning_rate": 8.736141906873615e-05,
+      "loss": 0.7624,
+      "step": 260
+    },
+    {
+      "epoch": 1.7186813186813188,
+      "grad_norm": 0.4375542104244232,
+      "learning_rate": 8.69179600886918e-05,
+      "loss": 0.7421,
+      "step": 261
+    },
+    {
+      "epoch": 1.7252747252747254,
+      "grad_norm": 0.47112950682640076,
+      "learning_rate": 8.647450110864746e-05,
+      "loss": 0.8486,
+      "step": 262
+    },
+    {
+      "epoch": 1.731868131868132,
+      "grad_norm": 0.6528114676475525,
+      "learning_rate": 8.603104212860311e-05,
+      "loss": 0.7325,
+      "step": 263
+    },
+    {
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.46200332045555115,
+      "learning_rate": 8.558758314855876e-05,
+      "loss": 0.8528,
+      "step": 264
+    },
+    {
+      "epoch": 1.745054945054945,
+      "grad_norm": 0.574214518070221,
+      "learning_rate": 8.514412416851442e-05,
+      "loss": 0.7978,
+      "step": 265
+    },
+    {
+      "epoch": 1.7516483516483516,
+      "grad_norm": 0.4962877333164215,
+      "learning_rate": 8.470066518847007e-05,
+      "loss": 0.8764,
+      "step": 266
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 0.4789123237133026,
+      "learning_rate": 8.425720620842572e-05,
+      "loss": 0.8737,
+      "step": 267
+    },
+    {
+      "epoch": 1.7648351648351648,
+      "grad_norm": 0.5246762037277222,
+      "learning_rate": 8.381374722838138e-05,
+      "loss": 0.8024,
+      "step": 268
+    },
+    {
+      "epoch": 1.7714285714285714,
+      "grad_norm": 0.41688671708106995,
+      "learning_rate": 8.337028824833703e-05,
+      "loss": 0.5601,
+      "step": 269
+    },
+    {
+      "epoch": 1.778021978021978,
+      "grad_norm": 0.4610651433467865,
+      "learning_rate": 8.292682926829268e-05,
+      "loss": 0.6669,
+      "step": 270
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 0.5566967129707336,
+      "learning_rate": 8.248337028824834e-05,
+      "loss": 0.8098,
+      "step": 271
+    },
+    {
+      "epoch": 1.791208791208791,
+      "grad_norm": 0.48066723346710205,
+      "learning_rate": 8.2039911308204e-05,
+      "loss": 0.8288,
+      "step": 272
+    },
+    {
+      "epoch": 1.7978021978021979,
+      "grad_norm": 0.564047634601593,
+      "learning_rate": 8.159645232815965e-05,
+      "loss": 0.9512,
+      "step": 273
+    },
+    {
+      "epoch": 1.8043956043956044,
+      "grad_norm": 0.4820556938648224,
+      "learning_rate": 8.11529933481153e-05,
+      "loss": 0.499,
+      "step": 274
+    },
+    {
+      "epoch": 1.810989010989011,
+      "grad_norm": 0.5948233604431152,
+      "learning_rate": 8.070953436807095e-05,
+      "loss": 0.8845,
+      "step": 275
+    },
+    {
+      "epoch": 1.8175824175824176,
+      "grad_norm": 0.510066032409668,
+      "learning_rate": 8.026607538802661e-05,
+      "loss": 0.8913,
+      "step": 276
+    },
+    {
+      "epoch": 1.8241758241758241,
+      "grad_norm": 0.5342652797698975,
+      "learning_rate": 7.982261640798227e-05,
+      "loss": 0.8842,
+      "step": 277
+    },
+    {
+      "epoch": 1.830769230769231,
+      "grad_norm": 0.5228323340415955,
+      "learning_rate": 7.937915742793793e-05,
+      "loss": 0.8055,
+      "step": 278
+    },
+    {
+      "epoch": 1.8373626373626375,
+      "grad_norm": 0.501943826675415,
+      "learning_rate": 7.893569844789357e-05,
+      "loss": 0.8469,
+      "step": 279
+    },
+    {
+      "epoch": 1.843956043956044,
+      "grad_norm": 0.5378738641738892,
+      "learning_rate": 7.849223946784923e-05,
+      "loss": 0.9278,
+      "step": 280
+    },
+    {
+      "epoch": 1.8505494505494506,
+      "grad_norm": 0.632314920425415,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 1.0605,
+      "step": 281
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.40868574380874634,
+      "learning_rate": 7.760532150776053e-05,
+      "loss": 0.8974,
+      "step": 282
+    },
+    {
+      "epoch": 1.8637362637362638,
+      "grad_norm": 0.5296427607536316,
+      "learning_rate": 7.716186252771619e-05,
+      "loss": 0.8518,
+      "step": 283
+    },
+    {
+      "epoch": 1.8703296703296703,
+      "grad_norm": 0.48775559663772583,
+      "learning_rate": 7.671840354767185e-05,
+      "loss": 0.6894,
+      "step": 284
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 0.5466031432151794,
+      "learning_rate": 7.627494456762749e-05,
+      "loss": 0.847,
+      "step": 285
+    },
+    {
+      "epoch": 1.8835164835164835,
+      "grad_norm": 0.6754628419876099,
+      "learning_rate": 7.583148558758315e-05,
+      "loss": 0.9727,
+      "step": 286
+    },
+    {
+      "epoch": 1.89010989010989,
+      "grad_norm": 0.5291099548339844,
+      "learning_rate": 7.538802660753881e-05,
+      "loss": 0.9499,
+      "step": 287
+    },
+    {
+      "epoch": 1.8967032967032966,
+      "grad_norm": 0.49350351095199585,
+      "learning_rate": 7.494456762749445e-05,
+      "loss": 0.6847,
+      "step": 288
+    },
+    {
+      "epoch": 1.9032967032967032,
+      "grad_norm": 0.4854298233985901,
+      "learning_rate": 7.450110864745011e-05,
+      "loss": 0.8089,
+      "step": 289
+    },
+    {
+      "epoch": 1.9098901098901098,
+      "grad_norm": 0.5256028771400452,
+      "learning_rate": 7.405764966740577e-05,
+      "loss": 0.789,
+      "step": 290
+    },
+    {
+      "epoch": 1.9164835164835163,
+      "grad_norm": 0.5372645854949951,
+      "learning_rate": 7.361419068736141e-05,
+      "loss": 0.9326,
+      "step": 291
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.4498584270477295,
+      "learning_rate": 7.317073170731707e-05,
+      "loss": 0.7562,
+      "step": 292
+    },
+    {
+      "epoch": 1.9296703296703297,
+      "grad_norm": 0.5483140349388123,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.6764,
+      "step": 293
+    },
+    {
+      "epoch": 1.9362637362637363,
+      "grad_norm": 0.6889297366142273,
+      "learning_rate": 7.228381374722837e-05,
+      "loss": 0.9722,
+      "step": 294
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 0.4986286163330078,
+      "learning_rate": 7.184035476718403e-05,
+      "loss": 0.9781,
+      "step": 295
+    },
+    {
+      "epoch": 1.9494505494505494,
+      "grad_norm": 0.6074146032333374,
+      "learning_rate": 7.139689578713969e-05,
+      "loss": 0.7487,
+      "step": 296
+    },
+    {
+      "epoch": 1.9560439560439562,
+      "grad_norm": 0.5098879337310791,
+      "learning_rate": 7.095343680709535e-05,
+      "loss": 0.97,
+      "step": 297
+    },
+    {
+      "epoch": 1.9626373626373628,
+      "grad_norm": 0.5738970041275024,
+      "learning_rate": 7.0509977827051e-05,
+      "loss": 0.7691,
+      "step": 298
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 0.4587015211582184,
+      "learning_rate": 7.006651884700666e-05,
+      "loss": 0.7854,
+      "step": 299
+    },
+    {
+      "epoch": 1.975824175824176,
+      "grad_norm": 0.5862131118774414,
+      "learning_rate": 6.962305986696232e-05,
+      "loss": 0.8636,
+      "step": 300
+    }
+  ],
+  "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": 4.93298661433344e+16,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5771e71948dbda34583aadd9b95aaa5dcfa1508ab9cc504a7b946d80e194ff1
+size 6417