Upload folder using huggingface_hub

.gitattributes

@@ -47,3 +47,4 @@ 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-285/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-285/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-285/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",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "k_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-285/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa0fbd84469237428e422b2930347280ba1ed6150859418e7a3891a5ea05860
+size 59933632

checkpoint-285/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-285/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-285/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2bf36256b1bf16b26ffd4384f6fc82d9df383964766b976454613bfb73d9e1
+size 120166091

checkpoint-285/rng_state.pth

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

checkpoint-285/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90a9a9fbe67701c98f15e637590b7f0046852762f11a86ee7e805db955dd809
+size 1465

checkpoint-285/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-285/tokenizer.json

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

checkpoint-285/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-285/trainer_state.json

@@ -0,0 +1,2029 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.876923076923077,
+  "eval_steps": 500,
+  "global_step": 285,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006593406593406593,
+      "grad_norm": 1.5843391418457031,
+      "learning_rate": 0.0,
+      "loss": 2.8156,
+      "step": 1
+    },
+    {
+      "epoch": 0.013186813186813187,
+      "grad_norm": 1.8521391153335571,
+      "learning_rate": 4e-05,
+      "loss": 2.8825,
+      "step": 2
+    },
+    {
+      "epoch": 0.01978021978021978,
+      "grad_norm": 1.772310495376587,
+      "learning_rate": 8e-05,
+      "loss": 3.0455,
+      "step": 3
+    },
+    {
+      "epoch": 0.026373626373626374,
+      "grad_norm": 1.5936847925186157,
+      "learning_rate": 0.00012,
+      "loss": 2.3228,
+      "step": 4
+    },
+    {
+      "epoch": 0.03296703296703297,
+      "grad_norm": 1.7163457870483398,
+      "learning_rate": 0.00016,
+      "loss": 2.4105,
+      "step": 5
+    },
+    {
+      "epoch": 0.03956043956043956,
+      "grad_norm": 1.8210536241531372,
+      "learning_rate": 0.0002,
+      "loss": 1.9757,
+      "step": 6
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 2.4785475730895996,
+      "learning_rate": 0.00019955654101995565,
+      "loss": 1.9602,
+      "step": 7
+    },
+    {
+      "epoch": 0.05274725274725275,
+      "grad_norm": 1.8151148557662964,
+      "learning_rate": 0.00019911308203991133,
+      "loss": 1.5283,
+      "step": 8
+    },
+    {
+      "epoch": 0.05934065934065934,
+      "grad_norm": 0.8721301555633545,
+      "learning_rate": 0.00019866962305986697,
+      "loss": 1.1164,
+      "step": 9
+    },
+    {
+      "epoch": 0.06593406593406594,
+      "grad_norm": 0.8999813199043274,
+      "learning_rate": 0.00019822616407982261,
+      "loss": 1.3153,
+      "step": 10
+    },
+    {
+      "epoch": 0.07252747252747253,
+      "grad_norm": 0.8793871998786926,
+      "learning_rate": 0.00019778270509977829,
+      "loss": 1.5728,
+      "step": 11
+    },
+    {
+      "epoch": 0.07912087912087912,
+      "grad_norm": 0.7212244868278503,
+      "learning_rate": 0.00019733924611973393,
+      "loss": 1.4584,
+      "step": 12
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 0.5409421324729919,
+      "learning_rate": 0.0001968957871396896,
+      "loss": 1.2519,
+      "step": 13
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.44038522243499756,
+      "learning_rate": 0.00019645232815964525,
+      "loss": 1.4694,
+      "step": 14
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 0.35416823625564575,
+      "learning_rate": 0.00019600886917960092,
+      "loss": 0.9877,
+      "step": 15
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.4410957992076874,
+      "learning_rate": 0.00019556541019955653,
+      "loss": 1.2377,
+      "step": 16
+    },
+    {
+      "epoch": 0.11208791208791209,
+      "grad_norm": 0.39518073201179504,
+      "learning_rate": 0.0001951219512195122,
+      "loss": 1.1182,
+      "step": 17
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.4025755524635315,
+      "learning_rate": 0.00019467849223946785,
+      "loss": 1.1645,
+      "step": 18
+    },
+    {
+      "epoch": 0.12527472527472527,
+      "grad_norm": 0.3367070257663727,
+      "learning_rate": 0.00019423503325942352,
+      "loss": 0.8772,
+      "step": 19
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.3709753751754761,
+      "learning_rate": 0.00019379157427937917,
+      "loss": 1.2793,
+      "step": 20
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.40532636642456055,
+      "learning_rate": 0.00019334811529933484,
+      "loss": 0.9308,
+      "step": 21
+    },
+    {
+      "epoch": 0.14505494505494507,
+      "grad_norm": 0.3041611313819885,
+      "learning_rate": 0.00019290465631929045,
+      "loss": 1.1534,
+      "step": 22
+    },
+    {
+      "epoch": 0.15164835164835164,
+      "grad_norm": 0.38191983103752136,
+      "learning_rate": 0.00019246119733924613,
+      "loss": 0.9038,
+      "step": 23
+    },
+    {
+      "epoch": 0.15824175824175823,
+      "grad_norm": 0.377227246761322,
+      "learning_rate": 0.00019201773835920177,
+      "loss": 1.1424,
+      "step": 24
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 0.3673517107963562,
+      "learning_rate": 0.00019157427937915744,
+      "loss": 1.2671,
+      "step": 25
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 0.31700432300567627,
+      "learning_rate": 0.00019113082039911309,
+      "loss": 1.1441,
+      "step": 26
+    },
+    {
+      "epoch": 0.17802197802197803,
+      "grad_norm": 0.3470500409603119,
+      "learning_rate": 0.00019068736141906876,
+      "loss": 1.1671,
+      "step": 27
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.27670592069625854,
+      "learning_rate": 0.0001902439024390244,
+      "loss": 1.14,
+      "step": 28
+    },
+    {
+      "epoch": 0.1912087912087912,
+      "grad_norm": 0.3592919409275055,
+      "learning_rate": 0.00018980044345898005,
+      "loss": 1.3351,
+      "step": 29
+    },
+    {
+      "epoch": 0.1978021978021978,
+      "grad_norm": 0.38518282771110535,
+      "learning_rate": 0.00018935698447893572,
+      "loss": 1.2833,
+      "step": 30
+    },
+    {
+      "epoch": 0.2043956043956044,
+      "grad_norm": 0.3708607852458954,
+      "learning_rate": 0.00018891352549889136,
+      "loss": 1.0154,
+      "step": 31
+    },
+    {
+      "epoch": 0.210989010989011,
+      "grad_norm": 0.3055068850517273,
+      "learning_rate": 0.00018847006651884703,
+      "loss": 0.9309,
+      "step": 32
+    },
+    {
+      "epoch": 0.2175824175824176,
+      "grad_norm": 0.2933763563632965,
+      "learning_rate": 0.00018802660753880268,
+      "loss": 0.9721,
+      "step": 33
+    },
+    {
+      "epoch": 0.22417582417582418,
+      "grad_norm": 0.34914690256118774,
+      "learning_rate": 0.00018758314855875832,
+      "loss": 1.1341,
+      "step": 34
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.31120434403419495,
+      "learning_rate": 0.00018713968957871397,
+      "loss": 1.1207,
+      "step": 35
+    },
+    {
+      "epoch": 0.23736263736263735,
+      "grad_norm": 0.30122801661491394,
+      "learning_rate": 0.00018669623059866964,
+      "loss": 1.3361,
+      "step": 36
+    },
+    {
+      "epoch": 0.24395604395604395,
+      "grad_norm": 0.3731483519077301,
+      "learning_rate": 0.00018625277161862528,
+      "loss": 1.0789,
+      "step": 37
+    },
+    {
+      "epoch": 0.25054945054945055,
+      "grad_norm": 0.30212077498435974,
+      "learning_rate": 0.00018580931263858095,
+      "loss": 1.3128,
+      "step": 38
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.3174402415752411,
+      "learning_rate": 0.0001853658536585366,
+      "loss": 1.0298,
+      "step": 39
+    },
+    {
+      "epoch": 0.26373626373626374,
+      "grad_norm": 0.27389031648635864,
+      "learning_rate": 0.00018492239467849224,
+      "loss": 0.7857,
+      "step": 40
+    },
+    {
+      "epoch": 0.2703296703296703,
+      "grad_norm": 0.358776718378067,
+      "learning_rate": 0.0001844789356984479,
+      "loss": 1.0977,
+      "step": 41
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.341391921043396,
+      "learning_rate": 0.00018403547671840356,
+      "loss": 1.1621,
+      "step": 42
+    },
+    {
+      "epoch": 0.2835164835164835,
+      "grad_norm": 0.385212242603302,
+      "learning_rate": 0.0001835920177383592,
+      "loss": 1.1445,
+      "step": 43
+    },
+    {
+      "epoch": 0.29010989010989013,
+      "grad_norm": 0.24659432470798492,
+      "learning_rate": 0.00018314855875831487,
+      "loss": 1.1188,
+      "step": 44
+    },
+    {
+      "epoch": 0.2967032967032967,
+      "grad_norm": 0.2595515847206116,
+      "learning_rate": 0.00018270509977827052,
+      "loss": 0.8302,
+      "step": 45
+    },
+    {
+      "epoch": 0.3032967032967033,
+      "grad_norm": 0.3767276108264923,
+      "learning_rate": 0.00018226164079822616,
+      "loss": 1.6553,
+      "step": 46
+    },
+    {
+      "epoch": 0.3098901098901099,
+      "grad_norm": 0.28310975432395935,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 1.1345,
+      "step": 47
+    },
+    {
+      "epoch": 0.31648351648351647,
+      "grad_norm": 0.35903477668762207,
+      "learning_rate": 0.00018137472283813748,
+      "loss": 0.7517,
+      "step": 48
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.342821329832077,
+      "learning_rate": 0.00018093126385809312,
+      "loss": 1.0464,
+      "step": 49
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 0.2808687090873718,
+      "learning_rate": 0.0001804878048780488,
+      "loss": 0.9247,
+      "step": 50
+    },
+    {
+      "epoch": 0.3362637362637363,
+      "grad_norm": 0.33112433552742004,
+      "learning_rate": 0.00018004434589800444,
+      "loss": 1.0519,
+      "step": 51
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.29903167486190796,
+      "learning_rate": 0.00017960088691796008,
+      "loss": 1.0643,
+      "step": 52
+    },
+    {
+      "epoch": 0.34945054945054943,
+      "grad_norm": 0.3124869465827942,
+      "learning_rate": 0.00017915742793791575,
+      "loss": 1.2023,
+      "step": 53
+    },
+    {
+      "epoch": 0.35604395604395606,
+      "grad_norm": 0.2661173939704895,
+      "learning_rate": 0.0001787139689578714,
+      "loss": 0.8074,
+      "step": 54
+    },
+    {
+      "epoch": 0.3626373626373626,
+      "grad_norm": 0.3182145953178406,
+      "learning_rate": 0.00017827050997782707,
+      "loss": 0.9457,
+      "step": 55
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.3288654088973999,
+      "learning_rate": 0.00017782705099778271,
+      "loss": 1.1957,
+      "step": 56
+    },
+    {
+      "epoch": 0.3758241758241758,
+      "grad_norm": 0.2978874742984772,
+      "learning_rate": 0.00017738359201773839,
+      "loss": 0.9535,
+      "step": 57
+    },
+    {
+      "epoch": 0.3824175824175824,
+      "grad_norm": 0.3069325387477875,
+      "learning_rate": 0.000176940133037694,
+      "loss": 1.0443,
+      "step": 58
+    },
+    {
+      "epoch": 0.389010989010989,
+      "grad_norm": 0.31956231594085693,
+      "learning_rate": 0.00017649667405764967,
+      "loss": 1.2383,
+      "step": 59
+    },
+    {
+      "epoch": 0.3956043956043956,
+      "grad_norm": 0.2928081154823303,
+      "learning_rate": 0.00017605321507760532,
+      "loss": 0.9903,
+      "step": 60
+    },
+    {
+      "epoch": 0.4021978021978022,
+      "grad_norm": 0.2808949947357178,
+      "learning_rate": 0.000175609756097561,
+      "loss": 1.0634,
+      "step": 61
+    },
+    {
+      "epoch": 0.4087912087912088,
+      "grad_norm": 0.3161472976207733,
+      "learning_rate": 0.00017516629711751663,
+      "loss": 0.9278,
+      "step": 62
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.3816571533679962,
+      "learning_rate": 0.0001747228381374723,
+      "loss": 0.9225,
+      "step": 63
+    },
+    {
+      "epoch": 0.421978021978022,
+      "grad_norm": 0.2767592966556549,
+      "learning_rate": 0.00017427937915742792,
+      "loss": 1.1057,
+      "step": 64
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.323319673538208,
+      "learning_rate": 0.0001738359201773836,
+      "loss": 0.9706,
+      "step": 65
+    },
+    {
+      "epoch": 0.4351648351648352,
+      "grad_norm": 0.35678160190582275,
+      "learning_rate": 0.00017339246119733924,
+      "loss": 1.2009,
+      "step": 66
+    },
+    {
+      "epoch": 0.44175824175824174,
+      "grad_norm": 0.311489462852478,
+      "learning_rate": 0.0001729490022172949,
+      "loss": 1.0323,
+      "step": 67
+    },
+    {
+      "epoch": 0.44835164835164837,
+      "grad_norm": 0.3634609580039978,
+      "learning_rate": 0.00017250554323725056,
+      "loss": 1.0794,
+      "step": 68
+    },
+    {
+      "epoch": 0.45494505494505494,
+      "grad_norm": 0.29051142930984497,
+      "learning_rate": 0.00017206208425720623,
+      "loss": 0.9095,
+      "step": 69
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.2702578604221344,
+      "learning_rate": 0.00017161862527716187,
+      "loss": 0.9749,
+      "step": 70
+    },
+    {
+      "epoch": 0.46813186813186813,
+      "grad_norm": 0.2855437695980072,
+      "learning_rate": 0.00017117516629711752,
+      "loss": 0.8197,
+      "step": 71
+    },
+    {
+      "epoch": 0.4747252747252747,
+      "grad_norm": 0.297456294298172,
+      "learning_rate": 0.0001707317073170732,
+      "loss": 0.9567,
+      "step": 72
+    },
+    {
+      "epoch": 0.48131868131868133,
+      "grad_norm": 0.24237467348575592,
+      "learning_rate": 0.00017028824833702883,
+      "loss": 0.8005,
+      "step": 73
+    },
+    {
+      "epoch": 0.4879120879120879,
+      "grad_norm": 0.328037291765213,
+      "learning_rate": 0.0001698447893569845,
+      "loss": 0.9423,
+      "step": 74
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 0.2795104384422302,
+      "learning_rate": 0.00016940133037694015,
+      "loss": 1.0958,
+      "step": 75
+    },
+    {
+      "epoch": 0.5010989010989011,
+      "grad_norm": 0.26989641785621643,
+      "learning_rate": 0.00016895787139689582,
+      "loss": 0.8853,
+      "step": 76
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.3442732095718384,
+      "learning_rate": 0.00016851441241685144,
+      "loss": 0.8165,
+      "step": 77
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.28731393814086914,
+      "learning_rate": 0.0001680709534368071,
+      "loss": 1.0472,
+      "step": 78
+    },
+    {
+      "epoch": 0.5208791208791209,
+      "grad_norm": 0.29334571957588196,
+      "learning_rate": 0.00016762749445676275,
+      "loss": 0.9369,
+      "step": 79
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 0.3078097403049469,
+      "learning_rate": 0.00016718403547671842,
+      "loss": 0.912,
+      "step": 80
+    },
+    {
+      "epoch": 0.5340659340659341,
+      "grad_norm": 0.33694934844970703,
+      "learning_rate": 0.00016674057649667407,
+      "loss": 1.1832,
+      "step": 81
+    },
+    {
+      "epoch": 0.5406593406593406,
+      "grad_norm": 0.27495941519737244,
+      "learning_rate": 0.00016629711751662974,
+      "loss": 0.9264,
+      "step": 82
+    },
+    {
+      "epoch": 0.5472527472527473,
+      "grad_norm": 0.3295109272003174,
+      "learning_rate": 0.00016585365853658536,
+      "loss": 1.1884,
+      "step": 83
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.30429670214653015,
+      "learning_rate": 0.00016541019955654103,
+      "loss": 1.2774,
+      "step": 84
+    },
+    {
+      "epoch": 0.5604395604395604,
+      "grad_norm": 0.28503450751304626,
+      "learning_rate": 0.00016496674057649667,
+      "loss": 0.8402,
+      "step": 85
+    },
+    {
+      "epoch": 0.567032967032967,
+      "grad_norm": 0.38091132044792175,
+      "learning_rate": 0.00016452328159645234,
+      "loss": 0.9921,
+      "step": 86
+    },
+    {
+      "epoch": 0.5736263736263736,
+      "grad_norm": 0.33023545145988464,
+      "learning_rate": 0.000164079822616408,
+      "loss": 1.168,
+      "step": 87
+    },
+    {
+      "epoch": 0.5802197802197803,
+      "grad_norm": 0.28644034266471863,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 1.048,
+      "step": 88
+    },
+    {
+      "epoch": 0.5868131868131868,
+      "grad_norm": 0.2850220501422882,
+      "learning_rate": 0.0001631929046563193,
+      "loss": 0.8613,
+      "step": 89
+    },
+    {
+      "epoch": 0.5934065934065934,
+      "grad_norm": 0.27724236249923706,
+      "learning_rate": 0.00016274944567627495,
+      "loss": 0.9522,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.28526735305786133,
+      "learning_rate": 0.0001623059866962306,
+      "loss": 1.0575,
+      "step": 91
+    },
+    {
+      "epoch": 0.6065934065934065,
+      "grad_norm": 0.3300544321537018,
+      "learning_rate": 0.00016186252771618626,
+      "loss": 1.1596,
+      "step": 92
+    },
+    {
+      "epoch": 0.6131868131868132,
+      "grad_norm": 0.3302018642425537,
+      "learning_rate": 0.0001614190687361419,
+      "loss": 1.1164,
+      "step": 93
+    },
+    {
+      "epoch": 0.6197802197802198,
+      "grad_norm": 0.34805142879486084,
+      "learning_rate": 0.00016097560975609758,
+      "loss": 1.1106,
+      "step": 94
+    },
+    {
+      "epoch": 0.6263736263736264,
+      "grad_norm": 0.36664891242980957,
+      "learning_rate": 0.00016053215077605322,
+      "loss": 0.9729,
+      "step": 95
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.29839083552360535,
+      "learning_rate": 0.00016008869179600887,
+      "loss": 0.86,
+      "step": 96
+    },
+    {
+      "epoch": 0.6395604395604395,
+      "grad_norm": 0.40213289856910706,
+      "learning_rate": 0.00015964523281596454,
+      "loss": 1.1324,
+      "step": 97
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.2544693648815155,
+      "learning_rate": 0.00015920177383592018,
+      "loss": 0.9688,
+      "step": 98
+    },
+    {
+      "epoch": 0.6527472527472528,
+      "grad_norm": 0.2986075282096863,
+      "learning_rate": 0.00015875831485587586,
+      "loss": 1.1061,
+      "step": 99
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 0.37222951650619507,
+      "learning_rate": 0.0001583148558758315,
+      "loss": 1.1107,
+      "step": 100
+    },
+    {
+      "epoch": 0.6659340659340659,
+      "grad_norm": 0.2792779505252838,
+      "learning_rate": 0.00015787139689578714,
+      "loss": 0.992,
+      "step": 101
+    },
+    {
+      "epoch": 0.6725274725274726,
+      "grad_norm": 0.2820577621459961,
+      "learning_rate": 0.0001574279379157428,
+      "loss": 0.8408,
+      "step": 102
+    },
+    {
+      "epoch": 0.6791208791208792,
+      "grad_norm": 0.31690841913223267,
+      "learning_rate": 0.00015698447893569846,
+      "loss": 1.2549,
+      "step": 103
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.2861771285533905,
+      "learning_rate": 0.0001565410199556541,
+      "loss": 0.9154,
+      "step": 104
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.26935121417045593,
+      "learning_rate": 0.00015609756097560978,
+      "loss": 0.8391,
+      "step": 105
+    },
+    {
+      "epoch": 0.6989010989010989,
+      "grad_norm": 0.35693269968032837,
+      "learning_rate": 0.00015565410199556542,
+      "loss": 0.8458,
+      "step": 106
+    },
+    {
+      "epoch": 0.7054945054945055,
+      "grad_norm": 0.28164708614349365,
+      "learning_rate": 0.00015521064301552106,
+      "loss": 1.0945,
+      "step": 107
+    },
+    {
+      "epoch": 0.7120879120879121,
+      "grad_norm": 0.3093002438545227,
+      "learning_rate": 0.0001547671840354767,
+      "loss": 1.0787,
+      "step": 108
+    },
+    {
+      "epoch": 0.7186813186813187,
+      "grad_norm": 0.3896459639072418,
+      "learning_rate": 0.00015432372505543238,
+      "loss": 1.0757,
+      "step": 109
+    },
+    {
+      "epoch": 0.7252747252747253,
+      "grad_norm": 0.34897807240486145,
+      "learning_rate": 0.00015388026607538802,
+      "loss": 1.0409,
+      "step": 110
+    },
+    {
+      "epoch": 0.7318681318681318,
+      "grad_norm": 0.36673831939697266,
+      "learning_rate": 0.0001534368070953437,
+      "loss": 1.0385,
+      "step": 111
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.4313843548297882,
+      "learning_rate": 0.00015299334811529934,
+      "loss": 1.0996,
+      "step": 112
+    },
+    {
+      "epoch": 0.7450549450549451,
+      "grad_norm": 0.29618099331855774,
+      "learning_rate": 0.00015254988913525498,
+      "loss": 0.9261,
+      "step": 113
+    },
+    {
+      "epoch": 0.7516483516483516,
+      "grad_norm": 0.31989842653274536,
+      "learning_rate": 0.00015210643015521066,
+      "loss": 0.9106,
+      "step": 114
+    },
+    {
+      "epoch": 0.7582417582417582,
+      "grad_norm": 0.3386354446411133,
+      "learning_rate": 0.0001516629711751663,
+      "loss": 1.2015,
+      "step": 115
+    },
+    {
+      "epoch": 0.7648351648351648,
+      "grad_norm": 0.3514902591705322,
+      "learning_rate": 0.00015121951219512197,
+      "loss": 1.3507,
+      "step": 116
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.27930814027786255,
+      "learning_rate": 0.00015077605321507762,
+      "loss": 0.9667,
+      "step": 117
+    },
+    {
+      "epoch": 0.778021978021978,
+      "grad_norm": 0.3235801160335541,
+      "learning_rate": 0.0001503325942350333,
+      "loss": 1.1243,
+      "step": 118
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.2760171890258789,
+      "learning_rate": 0.0001498891352549889,
+      "loss": 1.063,
+      "step": 119
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 0.2974321246147156,
+      "learning_rate": 0.00014944567627494458,
+      "loss": 1.0874,
+      "step": 120
+    },
+    {
+      "epoch": 0.7978021978021979,
+      "grad_norm": 0.3042125403881073,
+      "learning_rate": 0.00014900221729490022,
+      "loss": 1.0485,
+      "step": 121
+    },
+    {
+      "epoch": 0.8043956043956044,
+      "grad_norm": 0.2973671555519104,
+      "learning_rate": 0.0001485587583148559,
+      "loss": 1.0581,
+      "step": 122
+    },
+    {
+      "epoch": 0.810989010989011,
+      "grad_norm": 0.4362548887729645,
+      "learning_rate": 0.00014811529933481154,
+      "loss": 1.0736,
+      "step": 123
+    },
+    {
+      "epoch": 0.8175824175824176,
+      "grad_norm": 0.31430351734161377,
+      "learning_rate": 0.0001476718403547672,
+      "loss": 0.9575,
+      "step": 124
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 0.31971320509910583,
+      "learning_rate": 0.00014722838137472282,
+      "loss": 1.06,
+      "step": 125
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.28114503622055054,
+      "learning_rate": 0.0001467849223946785,
+      "loss": 1.2639,
+      "step": 126
+    },
+    {
+      "epoch": 0.8373626373626374,
+      "grad_norm": 0.2903381586074829,
+      "learning_rate": 0.00014634146341463414,
+      "loss": 1.0742,
+      "step": 127
+    },
+    {
+      "epoch": 0.843956043956044,
+      "grad_norm": 0.3863905966281891,
+      "learning_rate": 0.0001458980044345898,
+      "loss": 0.9379,
+      "step": 128
+    },
+    {
+      "epoch": 0.8505494505494505,
+      "grad_norm": 0.30715394020080566,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.8741,
+      "step": 129
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.3623356223106384,
+      "learning_rate": 0.00014501108647450113,
+      "loss": 1.0023,
+      "step": 130
+    },
+    {
+      "epoch": 0.8637362637362638,
+      "grad_norm": 0.3077038824558258,
+      "learning_rate": 0.00014456762749445675,
+      "loss": 1.1705,
+      "step": 131
+    },
+    {
+      "epoch": 0.8703296703296703,
+      "grad_norm": 0.2857320308685303,
+      "learning_rate": 0.00014412416851441242,
+      "loss": 0.989,
+      "step": 132
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.4221183657646179,
+      "learning_rate": 0.00014368070953436806,
+      "loss": 1.1737,
+      "step": 133
+    },
+    {
+      "epoch": 0.8835164835164835,
+      "grad_norm": 0.26992401480674744,
+      "learning_rate": 0.00014323725055432373,
+      "loss": 1.1065,
+      "step": 134
+    },
+    {
+      "epoch": 0.8901098901098901,
+      "grad_norm": 0.2924363315105438,
+      "learning_rate": 0.00014279379157427938,
+      "loss": 1.1701,
+      "step": 135
+    },
+    {
+      "epoch": 0.8967032967032967,
+      "grad_norm": 0.29272526502609253,
+      "learning_rate": 0.00014235033259423505,
+      "loss": 1.0431,
+      "step": 136
+    },
+    {
+      "epoch": 0.9032967032967033,
+      "grad_norm": 0.35805362462997437,
+      "learning_rate": 0.0001419068736141907,
+      "loss": 1.0048,
+      "step": 137
+    },
+    {
+      "epoch": 0.9098901098901099,
+      "grad_norm": 0.3064621388912201,
+      "learning_rate": 0.00014146341463414634,
+      "loss": 1.0563,
+      "step": 138
+    },
+    {
+      "epoch": 0.9164835164835164,
+      "grad_norm": 0.2745743989944458,
+      "learning_rate": 0.000141019955654102,
+      "loss": 0.8093,
+      "step": 139
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.2574104368686676,
+      "learning_rate": 0.00014057649667405765,
+      "loss": 0.8897,
+      "step": 140
+    },
+    {
+      "epoch": 0.9296703296703297,
+      "grad_norm": 0.3551047742366791,
+      "learning_rate": 0.00014013303769401332,
+      "loss": 0.9551,
+      "step": 141
+    },
+    {
+      "epoch": 0.9362637362637363,
+      "grad_norm": 0.31768593192100525,
+      "learning_rate": 0.00013968957871396897,
+      "loss": 1.0787,
+      "step": 142
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.3659076392650604,
+      "learning_rate": 0.00013924611973392464,
+      "loss": 1.0164,
+      "step": 143
+    },
+    {
+      "epoch": 0.9494505494505494,
+      "grad_norm": 0.33559244871139526,
+      "learning_rate": 0.00013880266075388026,
+      "loss": 1.0276,
+      "step": 144
+    },
+    {
+      "epoch": 0.9560439560439561,
+      "grad_norm": 0.3228370249271393,
+      "learning_rate": 0.00013835920177383593,
+      "loss": 1.2313,
+      "step": 145
+    },
+    {
+      "epoch": 0.9626373626373627,
+      "grad_norm": 0.2789573073387146,
+      "learning_rate": 0.00013791574279379157,
+      "loss": 0.8152,
+      "step": 146
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.324306845664978,
+      "learning_rate": 0.00013747228381374724,
+      "loss": 0.9888,
+      "step": 147
+    },
+    {
+      "epoch": 0.9758241758241758,
+      "grad_norm": 0.307303249835968,
+      "learning_rate": 0.0001370288248337029,
+      "loss": 0.9933,
+      "step": 148
+    },
+    {
+      "epoch": 0.9824175824175824,
+      "grad_norm": 0.29327502846717834,
+      "learning_rate": 0.00013658536585365856,
+      "loss": 0.9589,
+      "step": 149
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 0.33833250403404236,
+      "learning_rate": 0.00013614190687361418,
+      "loss": 0.9858,
+      "step": 150
+    },
+    {
+      "epoch": 0.9956043956043956,
+      "grad_norm": 0.2873021364212036,
+      "learning_rate": 0.00013569844789356985,
+      "loss": 0.9503,
+      "step": 151
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.38166123628616333,
+      "learning_rate": 0.0001352549889135255,
+      "loss": 0.9859,
+      "step": 152
+    },
+    {
+      "epoch": 1.0065934065934066,
+      "grad_norm": 0.3040919005870819,
+      "learning_rate": 0.00013481152993348116,
+      "loss": 0.9403,
+      "step": 153
+    },
+    {
+      "epoch": 1.0131868131868131,
+      "grad_norm": 0.3346724212169647,
+      "learning_rate": 0.0001343680709534368,
+      "loss": 1.3198,
+      "step": 154
+    },
+    {
+      "epoch": 1.0197802197802197,
+      "grad_norm": 0.2888737916946411,
+      "learning_rate": 0.00013392461197339248,
+      "loss": 0.9449,
+      "step": 155
+    },
+    {
+      "epoch": 1.0263736263736263,
+      "grad_norm": 0.24763283133506775,
+      "learning_rate": 0.00013348115299334812,
+      "loss": 0.845,
+      "step": 156
+    },
+    {
+      "epoch": 1.032967032967033,
+      "grad_norm": 0.35276684165000916,
+      "learning_rate": 0.00013303769401330377,
+      "loss": 0.8571,
+      "step": 157
+    },
+    {
+      "epoch": 1.0395604395604396,
+      "grad_norm": 0.3068442642688751,
+      "learning_rate": 0.00013259423503325944,
+      "loss": 0.9584,
+      "step": 158
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.2783297896385193,
+      "learning_rate": 0.00013215077605321509,
+      "loss": 0.8542,
+      "step": 159
+    },
+    {
+      "epoch": 1.0527472527472528,
+      "grad_norm": 0.30835285782814026,
+      "learning_rate": 0.00013170731707317076,
+      "loss": 0.8036,
+      "step": 160
+    },
+    {
+      "epoch": 1.0593406593406594,
+      "grad_norm": 0.32938769459724426,
+      "learning_rate": 0.0001312638580931264,
+      "loss": 0.701,
+      "step": 161
+    },
+    {
+      "epoch": 1.065934065934066,
+      "grad_norm": 0.42673012614250183,
+      "learning_rate": 0.00013082039911308205,
+      "loss": 1.1817,
+      "step": 162
+    },
+    {
+      "epoch": 1.0725274725274725,
+      "grad_norm": 0.37019211053848267,
+      "learning_rate": 0.0001303769401330377,
+      "loss": 0.9628,
+      "step": 163
+    },
+    {
+      "epoch": 1.079120879120879,
+      "grad_norm": 0.3247932493686676,
+      "learning_rate": 0.00012993348115299336,
+      "loss": 1.1035,
+      "step": 164
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "grad_norm": 0.31072118878364563,
+      "learning_rate": 0.000129490022172949,
+      "loss": 1.0836,
+      "step": 165
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 0.3443380892276764,
+      "learning_rate": 0.00012904656319290468,
+      "loss": 1.0268,
+      "step": 166
+    },
+    {
+      "epoch": 1.098901098901099,
+      "grad_norm": 0.39338764548301697,
+      "learning_rate": 0.00012860310421286032,
+      "loss": 1.2012,
+      "step": 167
+    },
+    {
+      "epoch": 1.1054945054945056,
+      "grad_norm": 0.3188355267047882,
+      "learning_rate": 0.00012815964523281597,
+      "loss": 1.073,
+      "step": 168
+    },
+    {
+      "epoch": 1.1120879120879121,
+      "grad_norm": 0.390495628118515,
+      "learning_rate": 0.0001277161862527716,
+      "loss": 1.0057,
+      "step": 169
+    },
+    {
+      "epoch": 1.1186813186813187,
+      "grad_norm": 0.38059771060943604,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.8281,
+      "step": 170
+    },
+    {
+      "epoch": 1.1252747252747253,
+      "grad_norm": 0.3839198648929596,
+      "learning_rate": 0.00012682926829268293,
+      "loss": 0.9558,
+      "step": 171
+    },
+    {
+      "epoch": 1.1318681318681318,
+      "grad_norm": 0.3393332064151764,
+      "learning_rate": 0.0001263858093126386,
+      "loss": 0.9078,
+      "step": 172
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 0.34839192032814026,
+      "learning_rate": 0.00012594235033259424,
+      "loss": 0.876,
+      "step": 173
+    },
+    {
+      "epoch": 1.145054945054945,
+      "grad_norm": 0.36449167132377625,
+      "learning_rate": 0.00012549889135254989,
+      "loss": 0.8704,
+      "step": 174
+    },
+    {
+      "epoch": 1.1516483516483516,
+      "grad_norm": 0.40781110525131226,
+      "learning_rate": 0.00012505543237250553,
+      "loss": 1.0215,
+      "step": 175
+    },
+    {
+      "epoch": 1.1582417582417581,
+      "grad_norm": 0.3179631233215332,
+      "learning_rate": 0.0001246119733924612,
+      "loss": 0.7361,
+      "step": 176
+    },
+    {
+      "epoch": 1.164835164835165,
+      "grad_norm": 0.44013991951942444,
+      "learning_rate": 0.00012416851441241685,
+      "loss": 0.9469,
+      "step": 177
+    },
+    {
+      "epoch": 1.1714285714285715,
+      "grad_norm": 0.3477267920970917,
+      "learning_rate": 0.00012372505543237252,
+      "loss": 0.995,
+      "step": 178
+    },
+    {
+      "epoch": 1.178021978021978,
+      "grad_norm": 0.3559893071651459,
+      "learning_rate": 0.00012328159645232816,
+      "loss": 0.9047,
+      "step": 179
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.47691860795021057,
+      "learning_rate": 0.0001228381374722838,
+      "loss": 1.0441,
+      "step": 180
+    },
+    {
+      "epoch": 1.1912087912087912,
+      "grad_norm": 0.31850194931030273,
+      "learning_rate": 0.00012239467849223948,
+      "loss": 0.8703,
+      "step": 181
+    },
+    {
+      "epoch": 1.1978021978021978,
+      "grad_norm": 0.45557940006256104,
+      "learning_rate": 0.00012195121951219512,
+      "loss": 1.1753,
+      "step": 182
+    },
+    {
+      "epoch": 1.2043956043956043,
+      "grad_norm": 0.3637930750846863,
+      "learning_rate": 0.00012150776053215078,
+      "loss": 1.151,
+      "step": 183
+    },
+    {
+      "epoch": 1.210989010989011,
+      "grad_norm": 0.43823617696762085,
+      "learning_rate": 0.00012106430155210644,
+      "loss": 0.8979,
+      "step": 184
+    },
+    {
+      "epoch": 1.2175824175824177,
+      "grad_norm": 0.3514891266822815,
+      "learning_rate": 0.0001206208425720621,
+      "loss": 0.9443,
+      "step": 185
+    },
+    {
+      "epoch": 1.2241758241758243,
+      "grad_norm": 0.3895740211009979,
+      "learning_rate": 0.00012017738359201774,
+      "loss": 0.972,
+      "step": 186
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.3714885115623474,
+      "learning_rate": 0.0001197339246119734,
+      "loss": 0.8454,
+      "step": 187
+    },
+    {
+      "epoch": 1.2373626373626374,
+      "grad_norm": 0.47325366735458374,
+      "learning_rate": 0.00011929046563192906,
+      "loss": 0.8913,
+      "step": 188
+    },
+    {
+      "epoch": 1.243956043956044,
+      "grad_norm": 0.37345072627067566,
+      "learning_rate": 0.00011884700665188471,
+      "loss": 1.1981,
+      "step": 189
+    },
+    {
+      "epoch": 1.2505494505494505,
+      "grad_norm": 0.4246751666069031,
+      "learning_rate": 0.00011840354767184036,
+      "loss": 0.8321,
+      "step": 190
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.49544385075569153,
+      "learning_rate": 0.00011796008869179602,
+      "loss": 1.0758,
+      "step": 191
+    },
+    {
+      "epoch": 1.2637362637362637,
+      "grad_norm": 0.5096224546432495,
+      "learning_rate": 0.00011751662971175166,
+      "loss": 0.81,
+      "step": 192
+    },
+    {
+      "epoch": 1.2703296703296703,
+      "grad_norm": 0.4344899654388428,
+      "learning_rate": 0.00011707317073170732,
+      "loss": 1.0509,
+      "step": 193
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 0.43887391686439514,
+      "learning_rate": 0.00011662971175166298,
+      "loss": 0.9858,
+      "step": 194
+    },
+    {
+      "epoch": 1.2835164835164834,
+      "grad_norm": 0.47227200865745544,
+      "learning_rate": 0.00011618625277161863,
+      "loss": 0.9425,
+      "step": 195
+    },
+    {
+      "epoch": 1.2901098901098902,
+      "grad_norm": 0.44675981998443604,
+      "learning_rate": 0.00011574279379157429,
+      "loss": 1.0873,
+      "step": 196
+    },
+    {
+      "epoch": 1.2967032967032968,
+      "grad_norm": 0.3999116122722626,
+      "learning_rate": 0.00011529933481152995,
+      "loss": 0.9234,
+      "step": 197
+    },
+    {
+      "epoch": 1.3032967032967033,
+      "grad_norm": 0.4873921871185303,
+      "learning_rate": 0.00011485587583148558,
+      "loss": 1.3982,
+      "step": 198
+    },
+    {
+      "epoch": 1.30989010989011,
+      "grad_norm": 0.5263328552246094,
+      "learning_rate": 0.00011441241685144124,
+      "loss": 1.1196,
+      "step": 199
+    },
+    {
+      "epoch": 1.3164835164835165,
+      "grad_norm": 0.41891786456108093,
+      "learning_rate": 0.0001139689578713969,
+      "loss": 0.9244,
+      "step": 200
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 0.3824903666973114,
+      "learning_rate": 0.00011352549889135255,
+      "loss": 0.8249,
+      "step": 201
+    },
+    {
+      "epoch": 1.3296703296703296,
+      "grad_norm": 0.3771800100803375,
+      "learning_rate": 0.00011308203991130821,
+      "loss": 0.7892,
+      "step": 202
+    },
+    {
+      "epoch": 1.3362637362637364,
+      "grad_norm": 0.45261913537979126,
+      "learning_rate": 0.00011263858093126387,
+      "loss": 1.0867,
+      "step": 203
+    },
+    {
+      "epoch": 1.342857142857143,
+      "grad_norm": 0.421709805727005,
+      "learning_rate": 0.00011219512195121953,
+      "loss": 0.8096,
+      "step": 204
+    },
+    {
+      "epoch": 1.3494505494505495,
+      "grad_norm": 0.5280342698097229,
+      "learning_rate": 0.00011175166297117516,
+      "loss": 0.7606,
+      "step": 205
+    },
+    {
+      "epoch": 1.3560439560439561,
+      "grad_norm": 0.38911956548690796,
+      "learning_rate": 0.00011130820399113082,
+      "loss": 0.7891,
+      "step": 206
+    },
+    {
+      "epoch": 1.3626373626373627,
+      "grad_norm": 0.47260016202926636,
+      "learning_rate": 0.00011086474501108647,
+      "loss": 0.9646,
+      "step": 207
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.479998916387558,
+      "learning_rate": 0.00011042128603104213,
+      "loss": 0.7267,
+      "step": 208
+    },
+    {
+      "epoch": 1.3758241758241758,
+      "grad_norm": 0.476073682308197,
+      "learning_rate": 0.00010997782705099779,
+      "loss": 1.0749,
+      "step": 209
+    },
+    {
+      "epoch": 1.3824175824175824,
+      "grad_norm": 0.45205914974212646,
+      "learning_rate": 0.00010953436807095345,
+      "loss": 0.9639,
+      "step": 210
+    },
+    {
+      "epoch": 1.389010989010989,
+      "grad_norm": 0.44608914852142334,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.9021,
+      "step": 211
+    },
+    {
+      "epoch": 1.3956043956043955,
+      "grad_norm": 0.46160390973091125,
+      "learning_rate": 0.00010864745011086475,
+      "loss": 0.9141,
+      "step": 212
+    },
+    {
+      "epoch": 1.402197802197802,
+      "grad_norm": 0.4132397174835205,
+      "learning_rate": 0.00010820399113082041,
+      "loss": 0.9648,
+      "step": 213
+    },
+    {
+      "epoch": 1.4087912087912087,
+      "grad_norm": 0.4495893716812134,
+      "learning_rate": 0.00010776053215077607,
+      "loss": 0.9116,
+      "step": 214
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 0.4337720572948456,
+      "learning_rate": 0.00010731707317073172,
+      "loss": 0.694,
+      "step": 215
+    },
+    {
+      "epoch": 1.421978021978022,
+      "grad_norm": 0.5669428110122681,
+      "learning_rate": 0.00010687361419068738,
+      "loss": 0.8486,
+      "step": 216
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.41822999715805054,
+      "learning_rate": 0.00010643015521064301,
+      "loss": 0.8772,
+      "step": 217
+    },
+    {
+      "epoch": 1.4351648351648352,
+      "grad_norm": 0.49358034133911133,
+      "learning_rate": 0.00010598669623059867,
+      "loss": 1.2407,
+      "step": 218
+    },
+    {
+      "epoch": 1.4417582417582417,
+      "grad_norm": 0.5223171710968018,
+      "learning_rate": 0.00010554323725055433,
+      "loss": 0.8801,
+      "step": 219
+    },
+    {
+      "epoch": 1.4483516483516483,
+      "grad_norm": 0.4524052143096924,
+      "learning_rate": 0.00010509977827050999,
+      "loss": 0.7871,
+      "step": 220
+    },
+    {
+      "epoch": 1.4549450549450549,
+      "grad_norm": 0.4000990092754364,
+      "learning_rate": 0.00010465631929046564,
+      "loss": 0.8886,
+      "step": 221
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 0.5052671432495117,
+      "learning_rate": 0.0001042128603104213,
+      "loss": 0.8672,
+      "step": 222
+    },
+    {
+      "epoch": 1.4681318681318682,
+      "grad_norm": 0.4210032820701599,
+      "learning_rate": 0.00010376940133037693,
+      "loss": 0.8045,
+      "step": 223
+    },
+    {
+      "epoch": 1.4747252747252748,
+      "grad_norm": 0.4130396246910095,
+      "learning_rate": 0.00010332594235033259,
+      "loss": 0.7502,
+      "step": 224
+    },
+    {
+      "epoch": 1.4813186813186814,
+      "grad_norm": 0.4363018274307251,
+      "learning_rate": 0.00010288248337028825,
+      "loss": 0.7552,
+      "step": 225
+    },
+    {
+      "epoch": 1.487912087912088,
+      "grad_norm": 0.568086564540863,
+      "learning_rate": 0.0001024390243902439,
+      "loss": 1.1268,
+      "step": 226
+    },
+    {
+      "epoch": 1.4945054945054945,
+      "grad_norm": 0.43064337968826294,
+      "learning_rate": 0.00010199556541019956,
+      "loss": 0.855,
+      "step": 227
+    },
+    {
+      "epoch": 1.501098901098901,
+      "grad_norm": 0.46825194358825684,
+      "learning_rate": 0.00010155210643015522,
+      "loss": 0.9004,
+      "step": 228
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 0.42373931407928467,
+      "learning_rate": 0.00010110864745011087,
+      "loss": 0.9398,
+      "step": 229
+    },
+    {
+      "epoch": 1.5142857142857142,
+      "grad_norm": 0.5816337466239929,
+      "learning_rate": 0.00010066518847006652,
+      "loss": 0.9807,
+      "step": 230
+    },
+    {
+      "epoch": 1.5208791208791208,
+      "grad_norm": 0.5260667204856873,
+      "learning_rate": 0.00010022172949002218,
+      "loss": 0.9639,
+      "step": 231
+    },
+    {
+      "epoch": 1.5274725274725274,
+      "grad_norm": 0.3763827085494995,
+      "learning_rate": 9.977827050997783e-05,
+      "loss": 0.7729,
+      "step": 232
+    },
+    {
+      "epoch": 1.534065934065934,
+      "grad_norm": 0.4962773323059082,
+      "learning_rate": 9.933481152993348e-05,
+      "loss": 1.0272,
+      "step": 233
+    },
+    {
+      "epoch": 1.5406593406593405,
+      "grad_norm": 0.5261977314949036,
+      "learning_rate": 9.889135254988914e-05,
+      "loss": 1.0381,
+      "step": 234
+    },
+    {
+      "epoch": 1.5472527472527473,
+      "grad_norm": 0.5453608632087708,
+      "learning_rate": 9.84478935698448e-05,
+      "loss": 1.0068,
+      "step": 235
+    },
+    {
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.5260674953460693,
+      "learning_rate": 9.800443458980046e-05,
+      "loss": 1.24,
+      "step": 236
+    },
+    {
+      "epoch": 1.5604395604395604,
+      "grad_norm": 0.4607008397579193,
+      "learning_rate": 9.75609756097561e-05,
+      "loss": 1.136,
+      "step": 237
+    },
+    {
+      "epoch": 1.567032967032967,
+      "grad_norm": 0.48102492094039917,
+      "learning_rate": 9.711751662971176e-05,
+      "loss": 0.9013,
+      "step": 238
+    },
+    {
+      "epoch": 1.5736263736263736,
+      "grad_norm": 0.55854731798172,
+      "learning_rate": 9.667405764966742e-05,
+      "loss": 0.9384,
+      "step": 239
+    },
+    {
+      "epoch": 1.5802197802197804,
+      "grad_norm": 0.4186471402645111,
+      "learning_rate": 9.623059866962306e-05,
+      "loss": 0.804,
+      "step": 240
+    },
+    {
+      "epoch": 1.586813186813187,
+      "grad_norm": 0.40134361386299133,
+      "learning_rate": 9.578713968957872e-05,
+      "loss": 0.7636,
+      "step": 241
+    },
+    {
+      "epoch": 1.5934065934065935,
+      "grad_norm": 0.5034297704696655,
+      "learning_rate": 9.534368070953438e-05,
+      "loss": 0.8872,
+      "step": 242
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.580937922000885,
+      "learning_rate": 9.490022172949002e-05,
+      "loss": 0.8523,
+      "step": 243
+    },
+    {
+      "epoch": 1.6065934065934067,
+      "grad_norm": 0.5723124146461487,
+      "learning_rate": 9.445676274944568e-05,
+      "loss": 1.0189,
+      "step": 244
+    },
+    {
+      "epoch": 1.6131868131868132,
+      "grad_norm": 0.4987668991088867,
+      "learning_rate": 9.401330376940134e-05,
+      "loss": 1.1715,
+      "step": 245
+    },
+    {
+      "epoch": 1.6197802197802198,
+      "grad_norm": 0.4497898817062378,
+      "learning_rate": 9.356984478935698e-05,
+      "loss": 0.7361,
+      "step": 246
+    },
+    {
+      "epoch": 1.6263736263736264,
+      "grad_norm": 0.4929165244102478,
+      "learning_rate": 9.312638580931264e-05,
+      "loss": 1.0925,
+      "step": 247
+    },
+    {
+      "epoch": 1.632967032967033,
+      "grad_norm": 0.5543283820152283,
+      "learning_rate": 9.26829268292683e-05,
+      "loss": 0.8029,
+      "step": 248
+    },
+    {
+      "epoch": 1.6395604395604395,
+      "grad_norm": 0.4303639233112335,
+      "learning_rate": 9.223946784922394e-05,
+      "loss": 0.7868,
+      "step": 249
+    },
+    {
+      "epoch": 1.646153846153846,
+      "grad_norm": 0.5302845239639282,
+      "learning_rate": 9.17960088691796e-05,
+      "loss": 0.8876,
+      "step": 250
+    },
+    {
+      "epoch": 1.6527472527472526,
+      "grad_norm": 0.4498642385005951,
+      "learning_rate": 9.135254988913526e-05,
+      "loss": 0.764,
+      "step": 251
+    },
+    {
+      "epoch": 1.6593406593406592,
+      "grad_norm": 0.5256994962692261,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.824,
+      "step": 252
+    },
+    {
+      "epoch": 1.6659340659340658,
+      "grad_norm": 0.5303184986114502,
+      "learning_rate": 9.046563192904656e-05,
+      "loss": 0.9397,
+      "step": 253
+    },
+    {
+      "epoch": 1.6725274725274726,
+      "grad_norm": 0.4846528172492981,
+      "learning_rate": 9.002217294900222e-05,
+      "loss": 0.9016,
+      "step": 254
+    },
+    {
+      "epoch": 1.6791208791208792,
+      "grad_norm": 0.5512136816978455,
+      "learning_rate": 8.957871396895788e-05,
+      "loss": 0.8242,
+      "step": 255
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.4381351172924042,
+      "learning_rate": 8.913525498891354e-05,
+      "loss": 0.8273,
+      "step": 256
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.4924697279930115,
+      "learning_rate": 8.869179600886919e-05,
+      "loss": 0.8862,
+      "step": 257
+    },
+    {
+      "epoch": 1.6989010989010989,
+      "grad_norm": 0.5716632604598999,
+      "learning_rate": 8.824833702882484e-05,
+      "loss": 0.9845,
+      "step": 258
+    },
+    {
+      "epoch": 1.7054945054945057,
+      "grad_norm": 0.5491411685943604,
+      "learning_rate": 8.78048780487805e-05,
+      "loss": 1.1376,
+      "step": 259
+    },
+    {
+      "epoch": 1.7120879120879122,
+      "grad_norm": 0.4519512951374054,
+      "learning_rate": 8.736141906873615e-05,
+      "loss": 0.894,
+      "step": 260
+    },
+    {
+      "epoch": 1.7186813186813188,
+      "grad_norm": 0.5698287487030029,
+      "learning_rate": 8.69179600886918e-05,
+      "loss": 0.9092,
+      "step": 261
+    },
+    {
+      "epoch": 1.7252747252747254,
+      "grad_norm": 0.5243552327156067,
+      "learning_rate": 8.647450110864746e-05,
+      "loss": 1.1471,
+      "step": 262
+    },
+    {
+      "epoch": 1.731868131868132,
+      "grad_norm": 0.5263996720314026,
+      "learning_rate": 8.603104212860311e-05,
+      "loss": 0.87,
+      "step": 263
+    },
+    {
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.6195815205574036,
+      "learning_rate": 8.558758314855876e-05,
+      "loss": 1.1107,
+      "step": 264
+    },
+    {
+      "epoch": 1.745054945054945,
+      "grad_norm": 0.48275279998779297,
+      "learning_rate": 8.514412416851442e-05,
+      "loss": 0.8535,
+      "step": 265
+    },
+    {
+      "epoch": 1.7516483516483516,
+      "grad_norm": 0.5186773538589478,
+      "learning_rate": 8.470066518847007e-05,
+      "loss": 1.042,
+      "step": 266
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 0.5344981551170349,
+      "learning_rate": 8.425720620842572e-05,
+      "loss": 0.7889,
+      "step": 267
+    },
+    {
+      "epoch": 1.7648351648351648,
+      "grad_norm": 0.5524676442146301,
+      "learning_rate": 8.381374722838138e-05,
+      "loss": 0.9962,
+      "step": 268
+    },
+    {
+      "epoch": 1.7714285714285714,
+      "grad_norm": 0.3948223888874054,
+      "learning_rate": 8.337028824833703e-05,
+      "loss": 0.7196,
+      "step": 269
+    },
+    {
+      "epoch": 1.778021978021978,
+      "grad_norm": 0.4786475896835327,
+      "learning_rate": 8.292682926829268e-05,
+      "loss": 1.116,
+      "step": 270
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 0.5435975193977356,
+      "learning_rate": 8.248337028824834e-05,
+      "loss": 1.0744,
+      "step": 271
+    },
+    {
+      "epoch": 1.791208791208791,
+      "grad_norm": 0.5018028020858765,
+      "learning_rate": 8.2039911308204e-05,
+      "loss": 0.9117,
+      "step": 272
+    },
+    {
+      "epoch": 1.7978021978021979,
+      "grad_norm": 0.48708081245422363,
+      "learning_rate": 8.159645232815965e-05,
+      "loss": 0.9195,
+      "step": 273
+    },
+    {
+      "epoch": 1.8043956043956044,
+      "grad_norm": 0.4467397630214691,
+      "learning_rate": 8.11529933481153e-05,
+      "loss": 0.7994,
+      "step": 274
+    },
+    {
+      "epoch": 1.810989010989011,
+      "grad_norm": 0.591704785823822,
+      "learning_rate": 8.070953436807095e-05,
+      "loss": 0.8821,
+      "step": 275
+    },
+    {
+      "epoch": 1.8175824175824176,
+      "grad_norm": 0.576015055179596,
+      "learning_rate": 8.026607538802661e-05,
+      "loss": 1.1339,
+      "step": 276
+    },
+    {
+      "epoch": 1.8241758241758241,
+      "grad_norm": 0.4751889705657959,
+      "learning_rate": 7.982261640798227e-05,
+      "loss": 0.7876,
+      "step": 277
+    },
+    {
+      "epoch": 1.830769230769231,
+      "grad_norm": 0.42400187253952026,
+      "learning_rate": 7.937915742793793e-05,
+      "loss": 0.7932,
+      "step": 278
+    },
+    {
+      "epoch": 1.8373626373626375,
+      "grad_norm": 0.5698517560958862,
+      "learning_rate": 7.893569844789357e-05,
+      "loss": 0.9826,
+      "step": 279
+    },
+    {
+      "epoch": 1.843956043956044,
+      "grad_norm": 0.551084578037262,
+      "learning_rate": 7.849223946784923e-05,
+      "loss": 0.8561,
+      "step": 280
+    },
+    {
+      "epoch": 1.8505494505494506,
+      "grad_norm": 0.5639991164207458,
+      "learning_rate": 7.804878048780489e-05,
+      "loss": 0.9351,
+      "step": 281
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.4367116093635559,
+      "learning_rate": 7.760532150776053e-05,
+      "loss": 0.8926,
+      "step": 282
+    },
+    {
+      "epoch": 1.8637362637362638,
+      "grad_norm": 0.4931100904941559,
+      "learning_rate": 7.716186252771619e-05,
+      "loss": 0.7449,
+      "step": 283
+    },
+    {
+      "epoch": 1.8703296703296703,
+      "grad_norm": 0.5315260887145996,
+      "learning_rate": 7.671840354767185e-05,
+      "loss": 1.158,
+      "step": 284
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 0.505445659160614,
+      "learning_rate": 7.627494456762749e-05,
+      "loss": 0.7556,
+      "step": 285
+    }
+  ],
+  "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": 5.02873050980352e+16,
+  "train_batch_size": 22,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-285/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a9e8a06bc9bb75559c6cd959d31d2788f88ac12a188c89eb90e420dceb4a87
+size 6417