Training in progress, epoch 0, checkpoint

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen2.5-14B
+library_name: peft
+---
+
+# 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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-14B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7ae9af0c6c8527180156233763b9db3a7b5f73bb73823c07441c81388b2d79
+size 550593184

last-checkpoint/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
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db34a05d1a751a55f94e2359fa9ac0267ac07a3b1359b5aede318adc2d503cd
+size 1101572914

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1efd845084d2851b43c81a6ea28600dc220bbe8a654013061a7aed566bc948
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b67aa60b01832f249be11fa58b489260336e8f6116596adfbff4b9d1382c04
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

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

last-checkpoint/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,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,2666 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9976720984369803,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002660458929165281,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.005320917858330562,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.007981376787495843,
+      "grad_norm": NaN,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.010641835716661123,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.013302294645826405,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.015962753574991686,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.018623212504156966,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.021283671433322247,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.02394413036248753,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.02660458929165281,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02926504822081809,
+      "grad_norm": NaN,
+      "learning_rate": 9.999954941610768e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.03192550714998337,
+      "grad_norm": NaN,
+      "learning_rate": 9.999819767255174e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.034585966079148656,
+      "grad_norm": NaN,
+      "learning_rate": 9.999594479369514e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.03724642500831393,
+      "grad_norm": NaN,
+      "learning_rate": 9.999279082014232e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.039906883937479216,
+      "grad_norm": NaN,
+      "learning_rate": 9.998873580873848e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.04256734286664449,
+      "grad_norm": NaN,
+      "learning_rate": 9.99837798325685e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.04522780179580978,
+      "grad_norm": NaN,
+      "learning_rate": 9.997792298095572e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.04788826072497506,
+      "grad_norm": NaN,
+      "learning_rate": 9.997116535946028e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.05054871965414034,
+      "grad_norm": NaN,
+      "learning_rate": 9.996350708987713e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.05320917858330562,
+      "grad_norm": NaN,
+      "learning_rate": 9.995494831023409e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0558696375124709,
+      "grad_norm": NaN,
+      "learning_rate": 9.994548917478899e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.05853009644163618,
+      "grad_norm": NaN,
+      "learning_rate": 9.993512985402724e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.06119055537080147,
+      "grad_norm": NaN,
+      "learning_rate": 9.992387053465857e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.06385101429996674,
+      "grad_norm": NaN,
+      "learning_rate": 9.991171141961369e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.06651147322913202,
+      "grad_norm": NaN,
+      "learning_rate": 9.989865272804063e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.06917193215829731,
+      "grad_norm": NaN,
+      "learning_rate": 9.988469469530086e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.07183239108746259,
+      "grad_norm": NaN,
+      "learning_rate": 9.986983757296498e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.07449285001662787,
+      "grad_norm": NaN,
+      "learning_rate": 9.985408162880813e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.07715330894579316,
+      "grad_norm": NaN,
+      "learning_rate": 9.983742714680538e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.07981376787495843,
+      "grad_norm": NaN,
+      "learning_rate": 9.981987442712633e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": NaN,
+      "learning_rate": 9.98014237861299e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.08513468573328899,
+      "grad_norm": NaN,
+      "learning_rate": 9.978207555635856e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.08779514466245428,
+      "grad_norm": NaN,
+      "learning_rate": 9.976183008653233e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.09045560359161955,
+      "grad_norm": NaN,
+      "learning_rate": 9.974068774154251e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.09311606252078483,
+      "grad_norm": NaN,
+      "learning_rate": 9.971864890244513e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.09577652144995012,
+      "grad_norm": NaN,
+      "learning_rate": 9.969571396645399e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0984369803791154,
+      "grad_norm": NaN,
+      "learning_rate": 9.967188334693363e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.10109743930828068,
+      "grad_norm": NaN,
+      "learning_rate": 9.964715747339178e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.10375789823744595,
+      "grad_norm": NaN,
+      "learning_rate": 9.962153679147161e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.10641835716661124,
+      "grad_norm": NaN,
+      "learning_rate": 9.959502176294383e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.10907881609577652,
+      "grad_norm": NaN,
+      "learning_rate": 9.956761286569824e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.1117392750249418,
+      "grad_norm": NaN,
+      "learning_rate": 9.953931059373511e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.11439973395410709,
+      "grad_norm": NaN,
+      "learning_rate": 9.951011545715636e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.11706019288327237,
+      "grad_norm": NaN,
+      "learning_rate": 9.948002798215632e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.11972065181243764,
+      "grad_norm": NaN,
+      "learning_rate": 9.944904871101228e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.12238111074160293,
+      "grad_norm": NaN,
+      "learning_rate": 9.941717820207461e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.1250415696707682,
+      "grad_norm": NaN,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.1277020285999335,
+      "grad_norm": NaN,
+      "learning_rate": 9.935076578452534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.13036248752909876,
+      "grad_norm": NaN,
+      "learning_rate": 9.931622507288834e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.13302294645826404,
+      "grad_norm": NaN,
+      "learning_rate": 9.928079551738543e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.13568340538742932,
+      "grad_norm": NaN,
+      "learning_rate": 9.924447775657605e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.13834386431659462,
+      "grad_norm": NaN,
+      "learning_rate": 9.920727244502818e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.1410043232457599,
+      "grad_norm": NaN,
+      "learning_rate": 9.916918025330635e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.14366478217492518,
+      "grad_norm": NaN,
+      "learning_rate": 9.913020186795967e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.14632524110409045,
+      "grad_norm": NaN,
+      "learning_rate": 9.909033799150946e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.14898570003325573,
+      "grad_norm": NaN,
+      "learning_rate": 9.904958934243654e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.151646158962421,
+      "grad_norm": NaN,
+      "learning_rate": 9.900795665516831e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.1543066178915863,
+      "grad_norm": NaN,
+      "learning_rate": 9.89654406800655e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.1569670768207516,
+      "grad_norm": NaN,
+      "learning_rate": 9.892204218340866e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.15962753574991687,
+      "grad_norm": NaN,
+      "learning_rate": 9.887776194738432e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.16228799467908214,
+      "grad_norm": NaN,
+      "learning_rate": 9.883260077007092e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": NaN,
+      "learning_rate": 9.878655946542443e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.1676089125374127,
+      "grad_norm": NaN,
+      "learning_rate": 9.873963886326365e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.17026937146657797,
+      "grad_norm": NaN,
+      "learning_rate": 9.869183980925532e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.17292983039574328,
+      "grad_norm": NaN,
+      "learning_rate": 9.864316316489873e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.17559028932490856,
+      "grad_norm": NaN,
+      "learning_rate": 9.85936098075104e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.17825074825407383,
+      "grad_norm": NaN,
+      "learning_rate": 9.85431806302081e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.1809112071832391,
+      "grad_norm": NaN,
+      "learning_rate": 9.849187654189487e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.18357166611240439,
+      "grad_norm": NaN,
+      "learning_rate": 9.843969846724247e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.18623212504156966,
+      "grad_norm": NaN,
+      "learning_rate": 9.838664734667495e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.18889258397073494,
+      "grad_norm": NaN,
+      "learning_rate": 9.83327241363515e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.19155304289990024,
+      "grad_norm": NaN,
+      "learning_rate": 9.827792980814933e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.19421350182906552,
+      "grad_norm": NaN,
+      "learning_rate": 9.822226534964614e-05,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.1968739607582308,
+      "grad_norm": NaN,
+      "learning_rate": 9.81657317641022e-05,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.19953441968739608,
+      "grad_norm": NaN,
+      "learning_rate": 9.810833007044247e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.20219487861656135,
+      "grad_norm": NaN,
+      "learning_rate": 9.805006130323809e-05,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.20485533754572663,
+      "grad_norm": NaN,
+      "learning_rate": 9.799092651268778e-05,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.2075157964748919,
+      "grad_norm": NaN,
+      "learning_rate": 9.79309267645989e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.2101762554040572,
+      "grad_norm": NaN,
+      "learning_rate": 9.787006314036824e-05,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.2128367143332225,
+      "grad_norm": NaN,
+      "learning_rate": 9.780833673696254e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.21549717326238776,
+      "grad_norm": NaN,
+      "learning_rate": 9.774574866689877e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.21815763219155304,
+      "grad_norm": NaN,
+      "learning_rate": 9.768230005822395e-05,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.22081809112071832,
+      "grad_norm": NaN,
+      "learning_rate": 9.76179920544949e-05,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.2234785500498836,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.22613900897904887,
+      "grad_norm": NaN,
+      "learning_rate": 9.74868025135266e-05,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.22879946790821418,
+      "grad_norm": NaN,
+      "learning_rate": 9.741992334076308e-05,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.23145992683737945,
+      "grad_norm": NaN,
+      "learning_rate": 9.735218950185428e-05,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.23412038576654473,
+      "grad_norm": NaN,
+      "learning_rate": 9.728360221759123e-05,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.23678084469571,
+      "grad_norm": NaN,
+      "learning_rate": 9.721416272414699e-05,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.23944130362487528,
+      "grad_norm": NaN,
+      "learning_rate": 9.714387227305422e-05,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.24210176255404056,
+      "grad_norm": NaN,
+      "learning_rate": 9.707273213118271e-05,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.24476222148320587,
+      "grad_norm": NaN,
+      "learning_rate": 9.700074358071659e-05,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": NaN,
+      "learning_rate": 9.692790791913106e-05,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.2500831393415364,
+      "grad_norm": NaN,
+      "learning_rate": 9.685422645916918e-05,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.2527435982707017,
+      "grad_norm": NaN,
+      "learning_rate": 9.67797005288181e-05,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.255404057199867,
+      "grad_norm": NaN,
+      "learning_rate": 9.670433147128521e-05,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": NaN,
+      "learning_rate": 9.66281206449738e-05,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.26072497505819753,
+      "grad_norm": NaN,
+      "learning_rate": 9.65510694234587e-05,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.2633854339873628,
+      "grad_norm": NaN,
+      "learning_rate": 9.64731791954615e-05,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.2660458929165281,
+      "grad_norm": NaN,
+      "learning_rate": 9.639445136482548e-05,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.26870635184569336,
+      "grad_norm": NaN,
+      "learning_rate": 9.631488735049033e-05,
+      "loss": 0.0,
+      "step": 101
+    },
+    {
+      "epoch": 0.27136681077485864,
+      "grad_norm": NaN,
+      "learning_rate": 9.623448858646657e-05,
+      "loss": 0.0,
+      "step": 102
+    },
+    {
+      "epoch": 0.27402726970402397,
+      "grad_norm": NaN,
+      "learning_rate": 9.615325652180975e-05,
+      "loss": 0.0,
+      "step": 103
+    },
+    {
+      "epoch": 0.27668772863318924,
+      "grad_norm": NaN,
+      "learning_rate": 9.607119262059425e-05,
+      "loss": 0.0,
+      "step": 104
+    },
+    {
+      "epoch": 0.2793481875623545,
+      "grad_norm": NaN,
+      "learning_rate": 9.598829836188694e-05,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.2820086464915198,
+      "grad_norm": NaN,
+      "learning_rate": 9.590457523972056e-05,
+      "loss": 0.0,
+      "step": 106
+    },
+    {
+      "epoch": 0.2846691054206851,
+      "grad_norm": NaN,
+      "learning_rate": 9.582002476306668e-05,
+      "loss": 0.0,
+      "step": 107
+    },
+    {
+      "epoch": 0.28732956434985035,
+      "grad_norm": NaN,
+      "learning_rate": 9.573464845580864e-05,
+      "loss": 0.0,
+      "step": 108
+    },
+    {
+      "epoch": 0.28999002327901563,
+      "grad_norm": NaN,
+      "learning_rate": 9.564844785671398e-05,
+      "loss": 0.0,
+      "step": 109
+    },
+    {
+      "epoch": 0.2926504822081809,
+      "grad_norm": NaN,
+      "learning_rate": 9.55614245194068e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.2953109411373462,
+      "grad_norm": NaN,
+      "learning_rate": 9.547358001233959e-05,
+      "loss": 0.0,
+      "step": 111
+    },
+    {
+      "epoch": 0.29797140006651146,
+      "grad_norm": NaN,
+      "learning_rate": 9.538491591876522e-05,
+      "loss": 0.0,
+      "step": 112
+    },
+    {
+      "epoch": 0.30063185899567674,
+      "grad_norm": NaN,
+      "learning_rate": 9.529543383670814e-05,
+      "loss": 0.0,
+      "step": 113
+    },
+    {
+      "epoch": 0.303292317924842,
+      "grad_norm": NaN,
+      "learning_rate": 9.520513537893574e-05,
+      "loss": 0.0,
+      "step": 114
+    },
+    {
+      "epoch": 0.3059527768540073,
+      "grad_norm": NaN,
+      "learning_rate": 9.511402217292926e-05,
+      "loss": 0.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.3086132357831726,
+      "grad_norm": NaN,
+      "learning_rate": 9.502209586085444e-05,
+      "loss": 0.0,
+      "step": 116
+    },
+    {
+      "epoch": 0.3112736947123379,
+      "grad_norm": NaN,
+      "learning_rate": 9.492935809953185e-05,
+      "loss": 0.0,
+      "step": 117
+    },
+    {
+      "epoch": 0.3139341536415032,
+      "grad_norm": NaN,
+      "learning_rate": 9.483581056040719e-05,
+      "loss": 0.0,
+      "step": 118
+    },
+    {
+      "epoch": 0.31659461257066845,
+      "grad_norm": NaN,
+      "learning_rate": 9.474145492952102e-05,
+      "loss": 0.0,
+      "step": 119
+    },
+    {
+      "epoch": 0.31925507149983373,
+      "grad_norm": NaN,
+      "learning_rate": 9.464629290747842e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.321915530428999,
+      "grad_norm": NaN,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.0,
+      "step": 121
+    },
+    {
+      "epoch": 0.3245759893581643,
+      "grad_norm": NaN,
+      "learning_rate": 9.445355656498285e-05,
+      "loss": 0.0,
+      "step": 122
+    },
+    {
+      "epoch": 0.32723644828732956,
+      "grad_norm": NaN,
+      "learning_rate": 9.435598571828552e-05,
+      "loss": 0.0,
+      "step": 123
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": NaN,
+      "learning_rate": 9.425761542788048e-05,
+      "loss": 0.0,
+      "step": 124
+    },
+    {
+      "epoch": 0.3325573661456601,
+      "grad_norm": NaN,
+      "learning_rate": 9.415844746673047e-05,
+      "loss": 0.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.3352178250748254,
+      "grad_norm": NaN,
+      "learning_rate": 9.405848362217491e-05,
+      "loss": 0.0,
+      "step": 126
+    },
+    {
+      "epoch": 0.33787828400399067,
+      "grad_norm": NaN,
+      "learning_rate": 9.395772569589774e-05,
+      "loss": 0.0,
+      "step": 127
+    },
+    {
+      "epoch": 0.34053874293315595,
+      "grad_norm": NaN,
+      "learning_rate": 9.38561755038949e-05,
+      "loss": 0.0,
+      "step": 128
+    },
+    {
+      "epoch": 0.3431992018623212,
+      "grad_norm": NaN,
+      "learning_rate": 9.37538348764416e-05,
+      "loss": 0.0,
+      "step": 129
+    },
+    {
+      "epoch": 0.34585966079148656,
+      "grad_norm": NaN,
+      "learning_rate": 9.365070565805941e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.34852011972065183,
+      "grad_norm": NaN,
+      "learning_rate": 9.35467897074829e-05,
+      "loss": 0.0,
+      "step": 131
+    },
+    {
+      "epoch": 0.3511805786498171,
+      "grad_norm": NaN,
+      "learning_rate": 9.34420888976262e-05,
+      "loss": 0.0,
+      "step": 132
+    },
+    {
+      "epoch": 0.3538410375789824,
+      "grad_norm": NaN,
+      "learning_rate": 9.333660511554925e-05,
+      "loss": 0.0,
+      "step": 133
+    },
+    {
+      "epoch": 0.35650149650814766,
+      "grad_norm": NaN,
+      "learning_rate": 9.323034026242377e-05,
+      "loss": 0.0,
+      "step": 134
+    },
+    {
+      "epoch": 0.35916195543731294,
+      "grad_norm": NaN,
+      "learning_rate": 9.312329625349902e-05,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.3618224143664782,
+      "grad_norm": NaN,
+      "learning_rate": 9.301547501806726e-05,
+      "loss": 0.0,
+      "step": 136
+    },
+    {
+      "epoch": 0.3644828732956435,
+      "grad_norm": NaN,
+      "learning_rate": 9.290687849942893e-05,
+      "loss": 0.0,
+      "step": 137
+    },
+    {
+      "epoch": 0.36714333222480877,
+      "grad_norm": NaN,
+      "learning_rate": 9.279750865485772e-05,
+      "loss": 0.0,
+      "step": 138
+    },
+    {
+      "epoch": 0.36980379115397405,
+      "grad_norm": NaN,
+      "learning_rate": 9.268736745556527e-05,
+      "loss": 0.0,
+      "step": 139
+    },
+    {
+      "epoch": 0.3724642500831393,
+      "grad_norm": NaN,
+      "learning_rate": 9.257645688666556e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.3751247090123046,
+      "grad_norm": NaN,
+      "learning_rate": 9.246477894713925e-05,
+      "loss": 0.0,
+      "step": 141
+    },
+    {
+      "epoch": 0.3777851679414699,
+      "grad_norm": NaN,
+      "learning_rate": 9.235233564979755e-05,
+      "loss": 0.0,
+      "step": 142
+    },
+    {
+      "epoch": 0.3804456268706352,
+      "grad_norm": NaN,
+      "learning_rate": 9.223912902124601e-05,
+      "loss": 0.0,
+      "step": 143
+    },
+    {
+      "epoch": 0.3831060857998005,
+      "grad_norm": NaN,
+      "learning_rate": 9.212516110184794e-05,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 0.38576654472896577,
+      "grad_norm": NaN,
+      "learning_rate": 9.201043394568773e-05,
+      "loss": 0.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.38842700365813104,
+      "grad_norm": NaN,
+      "learning_rate": 9.189494962053368e-05,
+      "loss": 0.0,
+      "step": 146
+    },
+    {
+      "epoch": 0.3910874625872963,
+      "grad_norm": NaN,
+      "learning_rate": 9.17787102078009e-05,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 0.3937479215164616,
+      "grad_norm": NaN,
+      "learning_rate": 9.166171780251365e-05,
+      "loss": 0.0,
+      "step": 148
+    },
+    {
+      "epoch": 0.3964083804456269,
+      "grad_norm": NaN,
+      "learning_rate": 9.154397451326766e-05,
+      "loss": 0.0,
+      "step": 149
+    },
+    {
+      "epoch": 0.39906883937479215,
+      "grad_norm": NaN,
+      "learning_rate": 9.142548246219212e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4017292983039574,
+      "grad_norm": NaN,
+      "learning_rate": 9.13062437849114e-05,
+      "loss": 0.0,
+      "step": 151
+    },
+    {
+      "epoch": 0.4043897572331227,
+      "grad_norm": NaN,
+      "learning_rate": 9.118626063050661e-05,
+      "loss": 0.0,
+      "step": 152
+    },
+    {
+      "epoch": 0.407050216162288,
+      "grad_norm": NaN,
+      "learning_rate": 9.106553516147682e-05,
+      "loss": 0.0,
+      "step": 153
+    },
+    {
+      "epoch": 0.40971067509145326,
+      "grad_norm": NaN,
+      "learning_rate": 9.09440695537001e-05,
+      "loss": 0.0,
+      "step": 154
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": NaN,
+      "learning_rate": 9.082186599639428e-05,
+      "loss": 0.0,
+      "step": 155
+    },
+    {
+      "epoch": 0.4150315929497838,
+      "grad_norm": NaN,
+      "learning_rate": 9.069892669207758e-05,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 0.41769205187894914,
+      "grad_norm": NaN,
+      "learning_rate": 9.057525385652878e-05,
+      "loss": 0.0,
+      "step": 157
+    },
+    {
+      "epoch": 0.4203525108081144,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 158
+    },
+    {
+      "epoch": 0.4230129697372797,
+      "grad_norm": NaN,
+      "learning_rate": 9.032571652091342e-05,
+      "loss": 0.0,
+      "step": 159
+    },
+    {
+      "epoch": 0.425673428666445,
+      "grad_norm": NaN,
+      "learning_rate": 9.019985651834703e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.42833388759561025,
+      "grad_norm": NaN,
+      "learning_rate": 9.007327197946781e-05,
+      "loss": 0.0,
+      "step": 161
+    },
+    {
+      "epoch": 0.43099434652477553,
+      "grad_norm": NaN,
+      "learning_rate": 8.994596518575392e-05,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 0.4336548054539408,
+      "grad_norm": NaN,
+      "learning_rate": 8.981793843170098e-05,
+      "loss": 0.0,
+      "step": 163
+    },
+    {
+      "epoch": 0.4363152643831061,
+      "grad_norm": NaN,
+      "learning_rate": 8.968919402478075e-05,
+      "loss": 0.0,
+      "step": 164
+    },
+    {
+      "epoch": 0.43897572331227136,
+      "grad_norm": NaN,
+      "learning_rate": 8.955973428539944e-05,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.44163618224143664,
+      "grad_norm": NaN,
+      "learning_rate": 8.942956154685596e-05,
+      "loss": 0.0,
+      "step": 166
+    },
+    {
+      "epoch": 0.4442966411706019,
+      "grad_norm": NaN,
+      "learning_rate": 8.929867815529993e-05,
+      "loss": 0.0,
+      "step": 167
+    },
+    {
+      "epoch": 0.4469571000997672,
+      "grad_norm": NaN,
+      "learning_rate": 8.916708646968923e-05,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 0.44961755902893247,
+      "grad_norm": NaN,
+      "learning_rate": 8.903478886174763e-05,
+      "loss": 0.0,
+      "step": 169
+    },
+    {
+      "epoch": 0.45227801795809774,
+      "grad_norm": NaN,
+      "learning_rate": 8.890178771592199e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.4549384768872631,
+      "grad_norm": NaN,
+      "learning_rate": 8.876808542933924e-05,
+      "loss": 0.0,
+      "step": 171
+    },
+    {
+      "epoch": 0.45759893581642835,
+      "grad_norm": NaN,
+      "learning_rate": 8.863368441176326e-05,
+      "loss": 0.0,
+      "step": 172
+    },
+    {
+      "epoch": 0.46025939474559363,
+      "grad_norm": NaN,
+      "learning_rate": 8.849858708555142e-05,
+      "loss": 0.0,
+      "step": 173
+    },
+    {
+      "epoch": 0.4629198536747589,
+      "grad_norm": NaN,
+      "learning_rate": 8.836279588561083e-05,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 0.4655803126039242,
+      "grad_norm": NaN,
+      "learning_rate": 8.822631325935463e-05,
+      "loss": 0.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.46824077153308946,
+      "grad_norm": NaN,
+      "learning_rate": 8.808914166665772e-05,
+      "loss": 0.0,
+      "step": 176
+    },
+    {
+      "epoch": 0.47090123046225474,
+      "grad_norm": NaN,
+      "learning_rate": 8.795128357981253e-05,
+      "loss": 0.0,
+      "step": 177
+    },
+    {
+      "epoch": 0.47356168939142,
+      "grad_norm": NaN,
+      "learning_rate": 8.781274148348437e-05,
+      "loss": 0.0,
+      "step": 178
+    },
+    {
+      "epoch": 0.4762221483205853,
+      "grad_norm": NaN,
+      "learning_rate": 8.767351787466673e-05,
+      "loss": 0.0,
+      "step": 179
+    },
+    {
+      "epoch": 0.47888260724975057,
+      "grad_norm": NaN,
+      "learning_rate": 8.753361526263621e-05,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.48154306617891585,
+      "grad_norm": NaN,
+      "learning_rate": 8.73930361689074e-05,
+      "loss": 0.0,
+      "step": 181
+    },
+    {
+      "epoch": 0.4842035251080811,
+      "grad_norm": NaN,
+      "learning_rate": 8.725178312718725e-05,
+      "loss": 0.0,
+      "step": 182
+    },
+    {
+      "epoch": 0.4868639840372464,
+      "grad_norm": NaN,
+      "learning_rate": 8.710985868332962e-05,
+      "loss": 0.0,
+      "step": 183
+    },
+    {
+      "epoch": 0.48952444296641173,
+      "grad_norm": NaN,
+      "learning_rate": 8.696726539528924e-05,
+      "loss": 0.0,
+      "step": 184
+    },
+    {
+      "epoch": 0.492184901895577,
+      "grad_norm": NaN,
+      "learning_rate": 8.682400583307562e-05,
+      "loss": 0.0,
+      "step": 185
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": NaN,
+      "learning_rate": 8.668008257870683e-05,
+      "loss": 0.0,
+      "step": 186
+    },
+    {
+      "epoch": 0.49750581975390756,
+      "grad_norm": NaN,
+      "learning_rate": 8.653549822616289e-05,
+      "loss": 0.0,
+      "step": 187
+    },
+    {
+      "epoch": 0.5001662786830728,
+      "grad_norm": NaN,
+      "learning_rate": 8.639025538133898e-05,
+      "loss": 0.0,
+      "step": 188
+    },
+    {
+      "epoch": 0.5028267376122381,
+      "grad_norm": NaN,
+      "learning_rate": 8.62443566619986e-05,
+      "loss": 0.0,
+      "step": 189
+    },
+    {
+      "epoch": 0.5054871965414034,
+      "grad_norm": NaN,
+      "learning_rate": 8.609780469772623e-05,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.5081476554705687,
+      "grad_norm": NaN,
+      "learning_rate": 8.595060212988006e-05,
+      "loss": 0.0,
+      "step": 191
+    },
+    {
+      "epoch": 0.510808114399734,
+      "grad_norm": NaN,
+      "learning_rate": 8.580275161154431e-05,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 0.5134685733288993,
+      "grad_norm": NaN,
+      "learning_rate": 8.56542558074815e-05,
+      "loss": 0.0,
+      "step": 193
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": NaN,
+      "learning_rate": 8.550511739408428e-05,
+      "loss": 0.0,
+      "step": 194
+    },
+    {
+      "epoch": 0.5187894911872298,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 0.5214499501163951,
+      "grad_norm": NaN,
+      "learning_rate": 8.520492350271896e-05,
+      "loss": 0.0,
+      "step": 196
+    },
+    {
+      "epoch": 0.5241104090455604,
+      "grad_norm": NaN,
+      "learning_rate": 8.505387343525209e-05,
+      "loss": 0.0,
+      "step": 197
+    },
+    {
+      "epoch": 0.5267708679747256,
+      "grad_norm": NaN,
+      "learning_rate": 8.490219157935589e-05,
+      "loss": 0.0,
+      "step": 198
+    },
+    {
+      "epoch": 0.5294313269038909,
+      "grad_norm": NaN,
+      "learning_rate": 8.47498806688464e-05,
+      "loss": 0.0,
+      "step": 199
+    },
+    {
+      "epoch": 0.5320917858330562,
+      "grad_norm": NaN,
+      "learning_rate": 8.459694344887732e-05,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5347522447622215,
+      "grad_norm": NaN,
+      "learning_rate": 8.444338267589057e-05,
+      "loss": 0.0,
+      "step": 201
+    },
+    {
+      "epoch": 0.5374127036913867,
+      "grad_norm": NaN,
+      "learning_rate": 8.428920111756658e-05,
+      "loss": 0.0,
+      "step": 202
+    },
+    {
+      "epoch": 0.540073162620552,
+      "grad_norm": NaN,
+      "learning_rate": 8.413440155277443e-05,
+      "loss": 0.0,
+      "step": 203
+    },
+    {
+      "epoch": 0.5427336215497173,
+      "grad_norm": NaN,
+      "learning_rate": 8.397898677152173e-05,
+      "loss": 0.0,
+      "step": 204
+    },
+    {
+      "epoch": 0.5453940804788826,
+      "grad_norm": NaN,
+      "learning_rate": 8.382295957490436e-05,
+      "loss": 0.0,
+      "step": 205
+    },
+    {
+      "epoch": 0.5480545394080479,
+      "grad_norm": NaN,
+      "learning_rate": 8.366632277505597e-05,
+      "loss": 0.0,
+      "step": 206
+    },
+    {
+      "epoch": 0.5507149983372132,
+      "grad_norm": NaN,
+      "learning_rate": 8.350907919509734e-05,
+      "loss": 0.0,
+      "step": 207
+    },
+    {
+      "epoch": 0.5533754572663785,
+      "grad_norm": NaN,
+      "learning_rate": 8.335123166908544e-05,
+      "loss": 0.0,
+      "step": 208
+    },
+    {
+      "epoch": 0.5560359161955437,
+      "grad_norm": NaN,
+      "learning_rate": 8.319278304196237e-05,
+      "loss": 0.0,
+      "step": 209
+    },
+    {
+      "epoch": 0.558696375124709,
+      "grad_norm": NaN,
+      "learning_rate": 8.303373616950408e-05,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.5613568340538743,
+      "grad_norm": NaN,
+      "learning_rate": 8.287409391826895e-05,
+      "loss": 0.0,
+      "step": 211
+    },
+    {
+      "epoch": 0.5640172929830396,
+      "grad_norm": NaN,
+      "learning_rate": 8.271385916554605e-05,
+      "loss": 0.0,
+      "step": 212
+    },
+    {
+      "epoch": 0.5666777519122048,
+      "grad_norm": NaN,
+      "learning_rate": 8.255303479930333e-05,
+      "loss": 0.0,
+      "step": 213
+    },
+    {
+      "epoch": 0.5693382108413702,
+      "grad_norm": NaN,
+      "learning_rate": 8.239162371813551e-05,
+      "loss": 0.0,
+      "step": 214
+    },
+    {
+      "epoch": 0.5719986697705354,
+      "grad_norm": NaN,
+      "learning_rate": 8.222962883121196e-05,
+      "loss": 0.0,
+      "step": 215
+    },
+    {
+      "epoch": 0.5746591286997007,
+      "grad_norm": NaN,
+      "learning_rate": 8.206705305822413e-05,
+      "loss": 0.0,
+      "step": 216
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": NaN,
+      "learning_rate": 8.190389932933301e-05,
+      "loss": 0.0,
+      "step": 217
+    },
+    {
+      "epoch": 0.5799800465580313,
+      "grad_norm": NaN,
+      "learning_rate": 8.174017058511629e-05,
+      "loss": 0.0,
+      "step": 218
+    },
+    {
+      "epoch": 0.5826405054871966,
+      "grad_norm": NaN,
+      "learning_rate": 8.157586977651534e-05,
+      "loss": 0.0,
+      "step": 219
+    },
+    {
+      "epoch": 0.5853009644163618,
+      "grad_norm": NaN,
+      "learning_rate": 8.141099986478212e-05,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.5879614233455271,
+      "grad_norm": NaN,
+      "learning_rate": 8.124556382142565e-05,
+      "loss": 0.0,
+      "step": 221
+    },
+    {
+      "epoch": 0.5906218822746924,
+      "grad_norm": NaN,
+      "learning_rate": 8.107956462815861e-05,
+      "loss": 0.0,
+      "step": 222
+    },
+    {
+      "epoch": 0.5932823412038577,
+      "grad_norm": NaN,
+      "learning_rate": 8.091300527684349e-05,
+      "loss": 0.0,
+      "step": 223
+    },
+    {
+      "epoch": 0.5959428001330229,
+      "grad_norm": NaN,
+      "learning_rate": 8.074588876943873e-05,
+      "loss": 0.0,
+      "step": 224
+    },
+    {
+      "epoch": 0.5986032590621883,
+      "grad_norm": NaN,
+      "learning_rate": 8.057821811794458e-05,
+      "loss": 0.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.6012637179913535,
+      "grad_norm": NaN,
+      "learning_rate": 8.040999634434883e-05,
+      "loss": 0.0,
+      "step": 226
+    },
+    {
+      "epoch": 0.6039241769205188,
+      "grad_norm": NaN,
+      "learning_rate": 8.024122648057234e-05,
+      "loss": 0.0,
+      "step": 227
+    },
+    {
+      "epoch": 0.606584635849684,
+      "grad_norm": NaN,
+      "learning_rate": 8.007191156841441e-05,
+      "loss": 0.0,
+      "step": 228
+    },
+    {
+      "epoch": 0.6092450947788494,
+      "grad_norm": NaN,
+      "learning_rate": 7.990205465949791e-05,
+      "loss": 0.0,
+      "step": 229
+    },
+    {
+      "epoch": 0.6119055537080146,
+      "grad_norm": NaN,
+      "learning_rate": 7.973165881521434e-05,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.6145660126371799,
+      "grad_norm": NaN,
+      "learning_rate": 7.956072710666859e-05,
+      "loss": 0.0,
+      "step": 231
+    },
+    {
+      "epoch": 0.6172264715663452,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 232
+    },
+    {
+      "epoch": 0.6198869304955105,
+      "grad_norm": NaN,
+      "learning_rate": 7.921726842944508e-05,
+      "loss": 0.0,
+      "step": 233
+    },
+    {
+      "epoch": 0.6225473894246758,
+      "grad_norm": NaN,
+      "learning_rate": 7.90447476510452e-05,
+      "loss": 0.0,
+      "step": 234
+    },
+    {
+      "epoch": 0.625207848353841,
+      "grad_norm": NaN,
+      "learning_rate": 7.88717033888274e-05,
+      "loss": 0.0,
+      "step": 235
+    },
+    {
+      "epoch": 0.6278683072830064,
+      "grad_norm": NaN,
+      "learning_rate": 7.869813876162998e-05,
+      "loss": 0.0,
+      "step": 236
+    },
+    {
+      "epoch": 0.6305287662121716,
+      "grad_norm": NaN,
+      "learning_rate": 7.852405689766993e-05,
+      "loss": 0.0,
+      "step": 237
+    },
+    {
+      "epoch": 0.6331892251413369,
+      "grad_norm": NaN,
+      "learning_rate": 7.834946093448659e-05,
+      "loss": 0.0,
+      "step": 238
+    },
+    {
+      "epoch": 0.6358496840705021,
+      "grad_norm": NaN,
+      "learning_rate": 7.817435401888513e-05,
+      "loss": 0.0,
+      "step": 239
+    },
+    {
+      "epoch": 0.6385101429996675,
+      "grad_norm": NaN,
+      "learning_rate": 7.799873930687978e-05,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.6411706019288327,
+      "grad_norm": NaN,
+      "learning_rate": 7.782261996363693e-05,
+      "loss": 0.0,
+      "step": 241
+    },
+    {
+      "epoch": 0.643831060857998,
+      "grad_norm": NaN,
+      "learning_rate": 7.764599916341817e-05,
+      "loss": 0.0,
+      "step": 242
+    },
+    {
+      "epoch": 0.6464915197871632,
+      "grad_norm": NaN,
+      "learning_rate": 7.746888008952301e-05,
+      "loss": 0.0,
+      "step": 243
+    },
+    {
+      "epoch": 0.6491519787163286,
+      "grad_norm": NaN,
+      "learning_rate": 7.729126593423151e-05,
+      "loss": 0.0,
+      "step": 244
+    },
+    {
+      "epoch": 0.6518124376454939,
+      "grad_norm": NaN,
+      "learning_rate": 7.711315989874677e-05,
+      "loss": 0.0,
+      "step": 245
+    },
+    {
+      "epoch": 0.6544728965746591,
+      "grad_norm": NaN,
+      "learning_rate": 7.69345651931372e-05,
+      "loss": 0.0,
+      "step": 246
+    },
+    {
+      "epoch": 0.6571333555038245,
+      "grad_norm": NaN,
+      "learning_rate": 7.675548503627871e-05,
+      "loss": 0.0,
+      "step": 247
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": NaN,
+      "learning_rate": 7.65759226557967e-05,
+      "loss": 0.0,
+      "step": 248
+    },
+    {
+      "epoch": 0.662454273362155,
+      "grad_norm": NaN,
+      "learning_rate": 7.639588128800778e-05,
+      "loss": 0.0,
+      "step": 249
+    },
+    {
+      "epoch": 0.6651147322913202,
+      "grad_norm": NaN,
+      "learning_rate": 7.621536417786159e-05,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.6677751912204856,
+      "grad_norm": NaN,
+      "learning_rate": 7.60343745788822e-05,
+      "loss": 0.0,
+      "step": 251
+    },
+    {
+      "epoch": 0.6704356501496508,
+      "grad_norm": NaN,
+      "learning_rate": 7.585291575310952e-05,
+      "loss": 0.0,
+      "step": 252
+    },
+    {
+      "epoch": 0.6730961090788161,
+      "grad_norm": NaN,
+      "learning_rate": 7.567099097104054e-05,
+      "loss": 0.0,
+      "step": 253
+    },
+    {
+      "epoch": 0.6757565680079813,
+      "grad_norm": NaN,
+      "learning_rate": 7.548860351157027e-05,
+      "loss": 0.0,
+      "step": 254
+    },
+    {
+      "epoch": 0.6784170269371467,
+      "grad_norm": NaN,
+      "learning_rate": 7.530575666193283e-05,
+      "loss": 0.0,
+      "step": 255
+    },
+    {
+      "epoch": 0.6810774858663119,
+      "grad_norm": NaN,
+      "learning_rate": 7.512245371764197e-05,
+      "loss": 0.0,
+      "step": 256
+    },
+    {
+      "epoch": 0.6837379447954772,
+      "grad_norm": NaN,
+      "learning_rate": 7.493869798243187e-05,
+      "loss": 0.0,
+      "step": 257
+    },
+    {
+      "epoch": 0.6863984037246424,
+      "grad_norm": NaN,
+      "learning_rate": 7.475449276819753e-05,
+      "loss": 0.0,
+      "step": 258
+    },
+    {
+      "epoch": 0.6890588626538078,
+      "grad_norm": NaN,
+      "learning_rate": 7.456984139493502e-05,
+      "loss": 0.0,
+      "step": 259
+    },
+    {
+      "epoch": 0.6917193215829731,
+      "grad_norm": NaN,
+      "learning_rate": 7.438474719068173e-05,
+      "loss": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.6943797805121383,
+      "grad_norm": NaN,
+      "learning_rate": 7.419921349145634e-05,
+      "loss": 0.0,
+      "step": 261
+    },
+    {
+      "epoch": 0.6970402394413037,
+      "grad_norm": NaN,
+      "learning_rate": 7.401324364119871e-05,
+      "loss": 0.0,
+      "step": 262
+    },
+    {
+      "epoch": 0.6997006983704689,
+      "grad_norm": NaN,
+      "learning_rate": 7.382684099170959e-05,
+      "loss": 0.0,
+      "step": 263
+    },
+    {
+      "epoch": 0.7023611572996342,
+      "grad_norm": NaN,
+      "learning_rate": 7.364000890259025e-05,
+      "loss": 0.0,
+      "step": 264
+    },
+    {
+      "epoch": 0.7050216162287994,
+      "grad_norm": NaN,
+      "learning_rate": 7.345275074118185e-05,
+      "loss": 0.0,
+      "step": 265
+    },
+    {
+      "epoch": 0.7076820751579648,
+      "grad_norm": NaN,
+      "learning_rate": 7.326506988250488e-05,
+      "loss": 0.0,
+      "step": 266
+    },
+    {
+      "epoch": 0.71034253408713,
+      "grad_norm": NaN,
+      "learning_rate": 7.307696970919818e-05,
+      "loss": 0.0,
+      "step": 267
+    },
+    {
+      "epoch": 0.7130029930162953,
+      "grad_norm": NaN,
+      "learning_rate": 7.288845361145811e-05,
+      "loss": 0.0,
+      "step": 268
+    },
+    {
+      "epoch": 0.7156634519454605,
+      "grad_norm": NaN,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.0,
+      "step": 269
+    },
+    {
+      "epoch": 0.7183239108746259,
+      "grad_norm": NaN,
+      "learning_rate": 7.251018724088367e-05,
+      "loss": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.7209843698037911,
+      "grad_norm": NaN,
+      "learning_rate": 7.232044378567864e-05,
+      "loss": 0.0,
+      "step": 271
+    },
+    {
+      "epoch": 0.7236448287329564,
+      "grad_norm": NaN,
+      "learning_rate": 7.213029804117604e-05,
+      "loss": 0.0,
+      "step": 272
+    },
+    {
+      "epoch": 0.7263052876621218,
+      "grad_norm": NaN,
+      "learning_rate": 7.193975343444023e-05,
+      "loss": 0.0,
+      "step": 273
+    },
+    {
+      "epoch": 0.728965746591287,
+      "grad_norm": NaN,
+      "learning_rate": 7.174881339972448e-05,
+      "loss": 0.0,
+      "step": 274
+    },
+    {
+      "epoch": 0.7316262055204523,
+      "grad_norm": NaN,
+      "learning_rate": 7.155748137840892e-05,
+      "loss": 0.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.7342866644496175,
+      "grad_norm": NaN,
+      "learning_rate": 7.136576081893863e-05,
+      "loss": 0.0,
+      "step": 276
+    },
+    {
+      "epoch": 0.7369471233787829,
+      "grad_norm": NaN,
+      "learning_rate": 7.117365517676145e-05,
+      "loss": 0.0,
+      "step": 277
+    },
+    {
+      "epoch": 0.7396075823079481,
+      "grad_norm": NaN,
+      "learning_rate": 7.09811679142657e-05,
+      "loss": 0.0,
+      "step": 278
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": NaN,
+      "learning_rate": 7.078830250071777e-05,
+      "loss": 0.0,
+      "step": 279
+    },
+    {
+      "epoch": 0.7449285001662787,
+      "grad_norm": NaN,
+      "learning_rate": 7.059506241219965e-05,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.747588959095444,
+      "grad_norm": NaN,
+      "learning_rate": 7.040145113154612e-05,
+      "loss": 0.0,
+      "step": 281
+    },
+    {
+      "epoch": 0.7502494180246092,
+      "grad_norm": NaN,
+      "learning_rate": 7.020747214828221e-05,
+      "loss": 0.0,
+      "step": 282
+    },
+    {
+      "epoch": 0.7529098769537745,
+      "grad_norm": NaN,
+      "learning_rate": 7.001312895856011e-05,
+      "loss": 0.0,
+      "step": 283
+    },
+    {
+      "epoch": 0.7555703358829398,
+      "grad_norm": NaN,
+      "learning_rate": 6.981842506509625e-05,
+      "loss": 0.0,
+      "step": 284
+    },
+    {
+      "epoch": 0.7582307948121051,
+      "grad_norm": NaN,
+      "learning_rate": 6.962336397710819e-05,
+      "loss": 0.0,
+      "step": 285
+    },
+    {
+      "epoch": 0.7608912537412704,
+      "grad_norm": NaN,
+      "learning_rate": 6.942794921025126e-05,
+      "loss": 0.0,
+      "step": 286
+    },
+    {
+      "epoch": 0.7635517126704356,
+      "grad_norm": NaN,
+      "learning_rate": 6.923218428655534e-05,
+      "loss": 0.0,
+      "step": 287
+    },
+    {
+      "epoch": 0.766212171599601,
+      "grad_norm": NaN,
+      "learning_rate": 6.903607273436128e-05,
+      "loss": 0.0,
+      "step": 288
+    },
+    {
+      "epoch": 0.7688726305287662,
+      "grad_norm": NaN,
+      "learning_rate": 6.883961808825732e-05,
+      "loss": 0.0,
+      "step": 289
+    },
+    {
+      "epoch": 0.7715330894579315,
+      "grad_norm": NaN,
+      "learning_rate": 6.864282388901544e-05,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": NaN,
+      "learning_rate": 6.844569368352748e-05,
+      "loss": 0.0,
+      "step": 291
+    },
+    {
+      "epoch": 0.7768540073162621,
+      "grad_norm": NaN,
+      "learning_rate": 6.824823102474128e-05,
+      "loss": 0.0,
+      "step": 292
+    },
+    {
+      "epoch": 0.7795144662454273,
+      "grad_norm": NaN,
+      "learning_rate": 6.805043947159651e-05,
+      "loss": 0.0,
+      "step": 293
+    },
+    {
+      "epoch": 0.7821749251745926,
+      "grad_norm": NaN,
+      "learning_rate": 6.785232258896077e-05,
+      "loss": 0.0,
+      "step": 294
+    },
+    {
+      "epoch": 0.7848353841037579,
+      "grad_norm": NaN,
+      "learning_rate": 6.765388394756504e-05,
+      "loss": 0.0,
+      "step": 295
+    },
+    {
+      "epoch": 0.7874958430329232,
+      "grad_norm": NaN,
+      "learning_rate": 6.745512712393957e-05,
+      "loss": 0.0,
+      "step": 296
+    },
+    {
+      "epoch": 0.7901563019620884,
+      "grad_norm": NaN,
+      "learning_rate": 6.725605570034929e-05,
+      "loss": 0.0,
+      "step": 297
+    },
+    {
+      "epoch": 0.7928167608912537,
+      "grad_norm": NaN,
+      "learning_rate": 6.705667326472925e-05,
+      "loss": 0.0,
+      "step": 298
+    },
+    {
+      "epoch": 0.795477219820419,
+      "grad_norm": NaN,
+      "learning_rate": 6.685698341062002e-05,
+      "loss": 0.0,
+      "step": 299
+    },
+    {
+      "epoch": 0.7981376787495843,
+      "grad_norm": NaN,
+      "learning_rate": 6.665698973710288e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.8007981376787496,
+      "grad_norm": NaN,
+      "learning_rate": 6.645669584873494e-05,
+      "loss": 0.0,
+      "step": 301
+    },
+    {
+      "epoch": 0.8034585966079149,
+      "grad_norm": NaN,
+      "learning_rate": 6.625610535548418e-05,
+      "loss": 0.0,
+      "step": 302
+    },
+    {
+      "epoch": 0.8061190555370802,
+      "grad_norm": NaN,
+      "learning_rate": 6.605522187266441e-05,
+      "loss": 0.0,
+      "step": 303
+    },
+    {
+      "epoch": 0.8087795144662454,
+      "grad_norm": NaN,
+      "learning_rate": 6.585404902087011e-05,
+      "loss": 0.0,
+      "step": 304
+    },
+    {
+      "epoch": 0.8114399733954107,
+      "grad_norm": NaN,
+      "learning_rate": 6.565259042591113e-05,
+      "loss": 0.0,
+      "step": 305
+    },
+    {
+      "epoch": 0.814100432324576,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 306
+    },
+    {
+      "epoch": 0.8167608912537413,
+      "grad_norm": NaN,
+      "learning_rate": 6.524883053542339e-05,
+      "loss": 0.0,
+      "step": 307
+    },
+    {
+      "epoch": 0.8194213501829065,
+      "grad_norm": NaN,
+      "learning_rate": 6.504653651700278e-05,
+      "loss": 0.0,
+      "step": 308
+    },
+    {
+      "epoch": 0.8220818091120718,
+      "grad_norm": NaN,
+      "learning_rate": 6.484397130950254e-05,
+      "loss": 0.0,
+      "step": 309
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": NaN,
+      "learning_rate": 6.464113856382752e-05,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.8274027269704024,
+      "grad_norm": NaN,
+      "learning_rate": 6.44380419357044e-05,
+      "loss": 0.0,
+      "step": 311
+    },
+    {
+      "epoch": 0.8300631858995676,
+      "grad_norm": NaN,
+      "learning_rate": 6.423468508561599e-05,
+      "loss": 0.0,
+      "step": 312
+    },
+    {
+      "epoch": 0.832723644828733,
+      "grad_norm": NaN,
+      "learning_rate": 6.403107167873509e-05,
+      "loss": 0.0,
+      "step": 313
+    },
+    {
+      "epoch": 0.8353841037578983,
+      "grad_norm": NaN,
+      "learning_rate": 6.382720538485856e-05,
+      "loss": 0.0,
+      "step": 314
+    },
+    {
+      "epoch": 0.8380445626870635,
+      "grad_norm": NaN,
+      "learning_rate": 6.362308987834115e-05,
+      "loss": 0.0,
+      "step": 315
+    },
+    {
+      "epoch": 0.8407050216162288,
+      "grad_norm": NaN,
+      "learning_rate": 6.341872883802923e-05,
+      "loss": 0.0,
+      "step": 316
+    },
+    {
+      "epoch": 0.8433654805453941,
+      "grad_norm": NaN,
+      "learning_rate": 6.321412594719451e-05,
+      "loss": 0.0,
+      "step": 317
+    },
+    {
+      "epoch": 0.8460259394745594,
+      "grad_norm": NaN,
+      "learning_rate": 6.300928489346766e-05,
+      "loss": 0.0,
+      "step": 318
+    },
+    {
+      "epoch": 0.8486863984037246,
+      "grad_norm": NaN,
+      "learning_rate": 6.280420936877188e-05,
+      "loss": 0.0,
+      "step": 319
+    },
+    {
+      "epoch": 0.85134685733289,
+      "grad_norm": NaN,
+      "learning_rate": 6.259890306925627e-05,
+      "loss": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.8540073162620552,
+      "grad_norm": NaN,
+      "learning_rate": 6.239336969522932e-05,
+      "loss": 0.0,
+      "step": 321
+    },
+    {
+      "epoch": 0.8566677751912205,
+      "grad_norm": NaN,
+      "learning_rate": 6.218761295109208e-05,
+      "loss": 0.0,
+      "step": 322
+    },
+    {
+      "epoch": 0.8593282341203857,
+      "grad_norm": NaN,
+      "learning_rate": 6.19816365452716e-05,
+      "loss": 0.0,
+      "step": 323
+    },
+    {
+      "epoch": 0.8619886930495511,
+      "grad_norm": NaN,
+      "learning_rate": 6.177544419015388e-05,
+      "loss": 0.0,
+      "step": 324
+    },
+    {
+      "epoch": 0.8646491519787163,
+      "grad_norm": NaN,
+      "learning_rate": 6.156903960201709e-05,
+      "loss": 0.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.8673096109078816,
+      "grad_norm": NaN,
+      "learning_rate": 6.136242650096451e-05,
+      "loss": 0.0,
+      "step": 326
+    },
+    {
+      "epoch": 0.8699700698370469,
+      "grad_norm": NaN,
+      "learning_rate": 6.115560861085756e-05,
+      "loss": 0.0,
+      "step": 327
+    },
+    {
+      "epoch": 0.8726305287662122,
+      "grad_norm": NaN,
+      "learning_rate": 6.0948589659248654e-05,
+      "loss": 0.0,
+      "step": 328
+    },
+    {
+      "epoch": 0.8752909876953775,
+      "grad_norm": NaN,
+      "learning_rate": 6.0741373377314005e-05,
+      "loss": 0.0,
+      "step": 329
+    },
+    {
+      "epoch": 0.8779514466245427,
+      "grad_norm": NaN,
+      "learning_rate": 6.0533963499786314e-05,
+      "loss": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.880611905553708,
+      "grad_norm": NaN,
+      "learning_rate": 6.032636376488763e-05,
+      "loss": 0.0,
+      "step": 331
+    },
+    {
+      "epoch": 0.8832723644828733,
+      "grad_norm": NaN,
+      "learning_rate": 6.0118577914261784e-05,
+      "loss": 0.0,
+      "step": 332
+    },
+    {
+      "epoch": 0.8859328234120386,
+      "grad_norm": NaN,
+      "learning_rate": 5.99106096929071e-05,
+      "loss": 0.0,
+      "step": 333
+    },
+    {
+      "epoch": 0.8885932823412038,
+      "grad_norm": NaN,
+      "learning_rate": 5.970246284910876e-05,
+      "loss": 0.0,
+      "step": 334
+    },
+    {
+      "epoch": 0.8912537412703692,
+      "grad_norm": NaN,
+      "learning_rate": 5.949414113437142e-05,
+      "loss": 0.0,
+      "step": 335
+    },
+    {
+      "epoch": 0.8939142001995344,
+      "grad_norm": NaN,
+      "learning_rate": 5.9285648303351404e-05,
+      "loss": 0.0,
+      "step": 336
+    },
+    {
+      "epoch": 0.8965746591286997,
+      "grad_norm": NaN,
+      "learning_rate": 5.907698811378919e-05,
+      "loss": 0.0,
+      "step": 337
+    },
+    {
+      "epoch": 0.8992351180578649,
+      "grad_norm": NaN,
+      "learning_rate": 5.8868164326441546e-05,
+      "loss": 0.0,
+      "step": 338
+    },
+    {
+      "epoch": 0.9018955769870303,
+      "grad_norm": NaN,
+      "learning_rate": 5.8659180705013936e-05,
+      "loss": 0.0,
+      "step": 339
+    },
+    {
+      "epoch": 0.9045560359161955,
+      "grad_norm": NaN,
+      "learning_rate": 5.8450041016092464e-05,
+      "loss": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": NaN,
+      "learning_rate": 5.8240749029076134e-05,
+      "loss": 0.0,
+      "step": 341
+    },
+    {
+      "epoch": 0.9098769537745262,
+      "grad_norm": NaN,
+      "learning_rate": 5.803130851610886e-05,
+      "loss": 0.0,
+      "step": 342
+    },
+    {
+      "epoch": 0.9125374127036914,
+      "grad_norm": NaN,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.0,
+      "step": 343
+    },
+    {
+      "epoch": 0.9151978716328567,
+      "grad_norm": NaN,
+      "learning_rate": 5.761199701421391e-05,
+      "loss": 0.0,
+      "step": 344
+    },
+    {
+      "epoch": 0.9178583305620219,
+      "grad_norm": NaN,
+      "learning_rate": 5.7402133582686576e-05,
+      "loss": 0.0,
+      "step": 345
+    },
+    {
+      "epoch": 0.9205187894911873,
+      "grad_norm": NaN,
+      "learning_rate": 5.719213673987277e-05,
+      "loss": 0.0,
+      "step": 346
+    },
+    {
+      "epoch": 0.9231792484203525,
+      "grad_norm": NaN,
+      "learning_rate": 5.698201027062034e-05,
+      "loss": 0.0,
+      "step": 347
+    },
+    {
+      "epoch": 0.9258397073495178,
+      "grad_norm": NaN,
+      "learning_rate": 5.6771757962113323e-05,
+      "loss": 0.0,
+      "step": 348
+    },
+    {
+      "epoch": 0.928500166278683,
+      "grad_norm": NaN,
+      "learning_rate": 5.656138360380391e-05,
+      "loss": 0.0,
+      "step": 349
+    },
+    {
+      "epoch": 0.9311606252078484,
+      "grad_norm": NaN,
+      "learning_rate": 5.6350890987343944e-05,
+      "loss": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.9338210841370136,
+      "grad_norm": NaN,
+      "learning_rate": 5.614028390651675e-05,
+      "loss": 0.0,
+      "step": 351
+    },
+    {
+      "epoch": 0.9364815430661789,
+      "grad_norm": NaN,
+      "learning_rate": 5.5929566157168665e-05,
+      "loss": 0.0,
+      "step": 352
+    },
+    {
+      "epoch": 0.9391420019953441,
+      "grad_norm": NaN,
+      "learning_rate": 5.571874153714063e-05,
+      "loss": 0.0,
+      "step": 353
+    },
+    {
+      "epoch": 0.9418024609245095,
+      "grad_norm": NaN,
+      "learning_rate": 5.550781384619973e-05,
+      "loss": 0.0,
+      "step": 354
+    },
+    {
+      "epoch": 0.9444629198536748,
+      "grad_norm": NaN,
+      "learning_rate": 5.5296786885970805e-05,
+      "loss": 0.0,
+      "step": 355
+    },
+    {
+      "epoch": 0.94712337878284,
+      "grad_norm": NaN,
+      "learning_rate": 5.50856644598678e-05,
+      "loss": 0.0,
+      "step": 356
+    },
+    {
+      "epoch": 0.9497838377120054,
+      "grad_norm": NaN,
+      "learning_rate": 5.487445037302531e-05,
+      "loss": 0.0,
+      "step": 357
+    },
+    {
+      "epoch": 0.9524442966411706,
+      "grad_norm": NaN,
+      "learning_rate": 5.466314843222993e-05,
+      "loss": 0.0,
+      "step": 358
+    },
+    {
+      "epoch": 0.9551047555703359,
+      "grad_norm": NaN,
+      "learning_rate": 5.4451762445851705e-05,
+      "loss": 0.0,
+      "step": 359
+    },
+    {
+      "epoch": 0.9577652144995011,
+      "grad_norm": NaN,
+      "learning_rate": 5.4240296223775465e-05,
+      "loss": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.9604256734286665,
+      "grad_norm": NaN,
+      "learning_rate": 5.4028753577332146e-05,
+      "loss": 0.0,
+      "step": 361
+    },
+    {
+      "epoch": 0.9630861323578317,
+      "grad_norm": NaN,
+      "learning_rate": 5.3817138319230076e-05,
+      "loss": 0.0,
+      "step": 362
+    },
+    {
+      "epoch": 0.965746591286997,
+      "grad_norm": NaN,
+      "learning_rate": 5.360545426348638e-05,
+      "loss": 0.0,
+      "step": 363
+    },
+    {
+      "epoch": 0.9684070502161622,
+      "grad_norm": NaN,
+      "learning_rate": 5.3393705225358046e-05,
+      "loss": 0.0,
+      "step": 364
+    },
+    {
+      "epoch": 0.9710675091453276,
+      "grad_norm": NaN,
+      "learning_rate": 5.318189502127332e-05,
+      "loss": 0.0,
+      "step": 365
+    },
+    {
+      "epoch": 0.9737279680744928,
+      "grad_norm": NaN,
+      "learning_rate": 5.297002746876284e-05,
+      "loss": 0.0,
+      "step": 366
+    },
+    {
+      "epoch": 0.9763884270036581,
+      "grad_norm": NaN,
+      "learning_rate": 5.275810638639088e-05,
+      "loss": 0.0,
+      "step": 367
+    },
+    {
+      "epoch": 0.9790488859328235,
+      "grad_norm": NaN,
+      "learning_rate": 5.254613559368649e-05,
+      "loss": 0.0,
+      "step": 368
+    },
+    {
+      "epoch": 0.9817093448619887,
+      "grad_norm": NaN,
+      "learning_rate": 5.2334118911074635e-05,
+      "loss": 0.0,
+      "step": 369
+    },
+    {
+      "epoch": 0.984369803791154,
+      "grad_norm": NaN,
+      "learning_rate": 5.212206015980742e-05,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.9870302627203192,
+      "grad_norm": NaN,
+      "learning_rate": 5.190996316189515e-05,
+      "loss": 0.0,
+      "step": 371
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": NaN,
+      "learning_rate": 5.1697831740037436e-05,
+      "loss": 0.0,
+      "step": 372
+    },
+    {
+      "epoch": 0.9923511805786498,
+      "grad_norm": NaN,
+      "learning_rate": 5.1485669717554396e-05,
+      "loss": 0.0,
+      "step": 373
+    },
+    {
+      "epoch": 0.9950116395078151,
+      "grad_norm": NaN,
+      "learning_rate": 5.1273480918317554e-05,
+      "loss": 0.0,
+      "step": 374
+    },
+    {
+      "epoch": 0.9976720984369803,
+      "grad_norm": NaN,
+      "learning_rate": 5.1061269166681183e-05,
+      "loss": 0.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.9976720984369803,
+      "eval_loss": NaN,
+      "eval_runtime": 83.394,
+      "eval_samples_per_second": 7.59,
+      "eval_steps_per_second": 1.907,
+      "step": 375
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0424041374146888e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ecbdc15e17086e0f7655dadf207a26f3bbb453c3057c18580ec6769ae316c6c
+size 6776