Training in progress, step 1880, checkpoint

.gitattributes

@@ -80,3 +80,4 @@ checkpoint-1720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1760/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1840/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1880/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1880/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-1.5B
+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 0.14.0

checkpoint-1880/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B",
+  "bias": "none",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1880/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3562cd06abdaec56814cb61f23304fdeaca253c81d9dc09b0dd14141ca2d13b3
+size 147770496

checkpoint-1880/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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-1880/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ca37116b2b3987e1158e022891c77d35e709e5ed2a43bf203f936ed0bb8af9
+size 295771370

checkpoint-1880/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
+size 14512

checkpoint-1880/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
+size 14512

checkpoint-1880/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cb4842d62225d5dacebe5277db9ccae38dc06be03a81fb1d270e3dad62f6a9
+size 988

checkpoint-1880/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f0a2dd6357e40688bacad42d4918658e194614b3b161afbacc551bb54c2d3a
+size 1064

checkpoint-1880/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1880/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-1880/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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
+    }
+  },
+  "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 messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|endoftext|>' + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1880/trainer_state.json

@@ -0,0 +1,1350 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2091042584434657,
+  "eval_steps": 500,
+  "global_step": 1880,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011747430249632892,
+      "grad_norm": 1.5699902772903442,
+      "learning_rate": 0.00027,
+      "loss": 3.0983,
+      "step": 10
+    },
+    {
+      "epoch": 0.023494860499265784,
+      "grad_norm": 1.6029695272445679,
+      "learning_rate": 0.00029991523567092526,
+      "loss": 2.062,
+      "step": 20
+    },
+    {
+      "epoch": 0.03524229074889868,
+      "grad_norm": 1.593436360359192,
+      "learning_rate": 0.00029962234616583063,
+      "loss": 1.2074,
+      "step": 30
+    },
+    {
+      "epoch": 0.04698972099853157,
+      "grad_norm": 0.5851414799690247,
+      "learning_rate": 0.00029912069357315393,
+      "loss": 0.888,
+      "step": 40
+    },
+    {
+      "epoch": 0.05873715124816446,
+      "grad_norm": 0.25992292165756226,
+      "learning_rate": 0.0002984109778320875,
+      "loss": 0.7685,
+      "step": 50
+    },
+    {
+      "epoch": 0.07048458149779736,
+      "grad_norm": 0.21082307398319244,
+      "learning_rate": 0.00029749418918542057,
+      "loss": 0.7096,
+      "step": 60
+    },
+    {
+      "epoch": 0.08223201174743025,
+      "grad_norm": 0.16843102872371674,
+      "learning_rate": 0.0002963716067978866,
+      "loss": 0.6901,
+      "step": 70
+    },
+    {
+      "epoch": 0.09397944199706314,
+      "grad_norm": 0.12076722830533981,
+      "learning_rate": 0.000295044796971387,
+      "loss": 0.6702,
+      "step": 80
+    },
+    {
+      "epoch": 0.10572687224669604,
+      "grad_norm": 0.21371866762638092,
+      "learning_rate": 0.000293515610959582,
+      "loss": 0.6353,
+      "step": 90
+    },
+    {
+      "epoch": 0.11747430249632893,
+      "grad_norm": 0.13458965718746185,
+      "learning_rate": 0.0002917861823848985,
+      "loss": 0.6479,
+      "step": 100
+    },
+    {
+      "epoch": 0.12922173274596183,
+      "grad_norm": 0.265765517950058,
+      "learning_rate": 0.0002898589242615568,
+      "loss": 0.6244,
+      "step": 110
+    },
+    {
+      "epoch": 0.14096916299559473,
+      "grad_norm": 0.1473032385110855,
+      "learning_rate": 0.0002877365256287728,
+      "loss": 0.6217,
+      "step": 120
+    },
+    {
+      "epoch": 0.1527165932452276,
+      "grad_norm": 0.1591167151927948,
+      "learning_rate": 0.00028542194779883047,
+      "loss": 0.6022,
+      "step": 130
+    },
+    {
+      "epoch": 0.1644640234948605,
+      "grad_norm": 0.13270772993564606,
+      "learning_rate": 0.00028291842022526133,
+      "loss": 0.6098,
+      "step": 140
+    },
+    {
+      "epoch": 0.1762114537444934,
+      "grad_norm": 0.1444919854402542,
+      "learning_rate": 0.0002802294359968954,
+      "loss": 0.5971,
+      "step": 150
+    },
+    {
+      "epoch": 0.18795888399412627,
+      "grad_norm": 0.1571902334690094,
+      "learning_rate": 0.0002773587469640702,
+      "loss": 0.5937,
+      "step": 160
+    },
+    {
+      "epoch": 0.19970631424375918,
+      "grad_norm": 0.11585285514593124,
+      "learning_rate": 0.0002743103585037989,
+      "loss": 0.6054,
+      "step": 170
+    },
+    {
+      "epoch": 0.21145374449339208,
+      "grad_norm": 0.10303252190351486,
+      "learning_rate": 0.0002710885239312008,
+      "loss": 0.5708,
+      "step": 180
+    },
+    {
+      "epoch": 0.22320117474302498,
+      "grad_norm": 0.09355439245700836,
+      "learning_rate": 0.00026769773856499167,
+      "loss": 0.5806,
+      "step": 190
+    },
+    {
+      "epoch": 0.23494860499265785,
+      "grad_norm": 0.09288550913333893,
+      "learning_rate": 0.0002641427334553158,
+      "loss": 0.5747,
+      "step": 200
+    },
+    {
+      "epoch": 0.24669603524229075,
+      "grad_norm": 0.10875760763883591,
+      "learning_rate": 0.00026042846878266795,
+      "loss": 0.5879,
+      "step": 210
+    },
+    {
+      "epoch": 0.25844346549192365,
+      "grad_norm": 0.09756477177143097,
+      "learning_rate": 0.0002565601269371192,
+      "loss": 0.5852,
+      "step": 220
+    },
+    {
+      "epoch": 0.2701908957415565,
+      "grad_norm": 0.10926368832588196,
+      "learning_rate": 0.0002525431052874997,
+      "loss": 0.5605,
+      "step": 230
+    },
+    {
+      "epoch": 0.28193832599118945,
+      "grad_norm": 0.09802033007144928,
+      "learning_rate": 0.00024838300865062966,
+      "loss": 0.5738,
+      "step": 240
+    },
+    {
+      "epoch": 0.2936857562408223,
+      "grad_norm": 0.10284294933080673,
+      "learning_rate": 0.00024408564147110443,
+      "loss": 0.5847,
+      "step": 250
+    },
+    {
+      "epoch": 0.3054331864904552,
+      "grad_norm": 0.09890703111886978,
+      "learning_rate": 0.00023965699972254602,
+      "loss": 0.5736,
+      "step": 260
+    },
+    {
+      "epoch": 0.31718061674008813,
+      "grad_norm": 0.09091509878635406,
+      "learning_rate": 0.00023510326254162027,
+      "loss": 0.5577,
+      "step": 270
+    },
+    {
+      "epoch": 0.328928046989721,
+      "grad_norm": 0.0930003970861435,
+      "learning_rate": 0.00023043078360649285,
+      "loss": 0.5651,
+      "step": 280
+    },
+    {
+      "epoch": 0.3406754772393539,
+      "grad_norm": 0.0988878533244133,
+      "learning_rate": 0.00022564608227175316,
+      "loss": 0.548,
+      "step": 290
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 0.11749754101037979,
+      "learning_rate": 0.0002207558344721757,
+      "loss": 0.5587,
+      "step": 300
+    },
+    {
+      "epoch": 0.3641703377386197,
+      "grad_norm": 0.10936658829450607,
+      "learning_rate": 0.00021576686340800985,
+      "loss": 0.5694,
+      "step": 310
+    },
+    {
+      "epoch": 0.37591776798825255,
+      "grad_norm": 0.15082670748233795,
+      "learning_rate": 0.00021068613002479553,
+      "loss": 0.5688,
+      "step": 320
+    },
+    {
+      "epoch": 0.3876651982378855,
+      "grad_norm": 0.10255635529756546,
+      "learning_rate": 0.00020552072330098716,
+      "loss": 0.56,
+      "step": 330
+    },
+    {
+      "epoch": 0.39941262848751835,
+      "grad_norm": 0.10504507273435593,
+      "learning_rate": 0.0002002778503569374,
+      "loss": 0.557,
+      "step": 340
+    },
+    {
+      "epoch": 0.4111600587371512,
+      "grad_norm": 0.1146383211016655,
+      "learning_rate": 0.00019496482639904194,
+      "loss": 0.5497,
+      "step": 350
+    },
+    {
+      "epoch": 0.42290748898678415,
+      "grad_norm": 0.09596443176269531,
+      "learning_rate": 0.00018958906451307489,
+      "loss": 0.556,
+      "step": 360
+    },
+    {
+      "epoch": 0.434654919236417,
+      "grad_norm": 0.10395421087741852,
+      "learning_rate": 0.0001841580653209565,
+      "loss": 0.5634,
+      "step": 370
+    },
+    {
+      "epoch": 0.44640234948604995,
+      "grad_norm": 0.08797866106033325,
+      "learning_rate": 0.00017867940651538483,
+      "loss": 0.5544,
+      "step": 380
+    },
+    {
+      "epoch": 0.4581497797356828,
+      "grad_norm": 0.1006847620010376,
+      "learning_rate": 0.0001731607322869329,
+      "loss": 0.5562,
+      "step": 390
+    },
+    {
+      "epoch": 0.4698972099853157,
+      "grad_norm": 0.09849337488412857,
+      "learning_rate": 0.00016760974265836331,
+      "loss": 0.5477,
+      "step": 400
+    },
+    {
+      "epoch": 0.48164464023494863,
+      "grad_norm": 0.0988384336233139,
+      "learning_rate": 0.00016203418274104278,
+      "loss": 0.5459,
+      "step": 410
+    },
+    {
+      "epoch": 0.4933920704845815,
+      "grad_norm": 0.09625212848186493,
+      "learning_rate": 0.0001564418319284454,
+      "loss": 0.5516,
+      "step": 420
+    },
+    {
+      "epoch": 0.5051395007342144,
+      "grad_norm": 0.09705183655023575,
+      "learning_rate": 0.00015084049304182347,
+      "loss": 0.5375,
+      "step": 430
+    },
+    {
+      "epoch": 0.5168869309838473,
+      "grad_norm": 0.17180472612380981,
+      "learning_rate": 0.00014523798144319027,
+      "loss": 0.539,
+      "step": 440
+    },
+    {
+      "epoch": 0.5286343612334802,
+      "grad_norm": 0.09553302824497223,
+      "learning_rate": 0.00013964211413080522,
+      "loss": 0.5418,
+      "step": 450
+    },
+    {
+      "epoch": 0.540381791483113,
+      "grad_norm": 0.10648112744092941,
+      "learning_rate": 0.0001340606988323758,
+      "loss": 0.5414,
+      "step": 460
+    },
+    {
+      "epoch": 0.5521292217327459,
+      "grad_norm": 0.09907692670822144,
+      "learning_rate": 0.00012850152311119498,
+      "loss": 0.5353,
+      "step": 470
+    },
+    {
+      "epoch": 0.5638766519823789,
+      "grad_norm": 0.11162377148866653,
+      "learning_rate": 0.00012297234350041228,
+      "loss": 0.528,
+      "step": 480
+    },
+    {
+      "epoch": 0.5756240822320118,
+      "grad_norm": 0.10550152510404587,
+      "learning_rate": 0.00011748087468060128,
+      "loss": 0.533,
+      "step": 490
+    },
+    {
+      "epoch": 0.5873715124816447,
+      "grad_norm": 0.09718377143144608,
+      "learning_rate": 0.0001120347787157222,
+      "loss": 0.5409,
+      "step": 500
+    },
+    {
+      "epoch": 0.5991189427312775,
+      "grad_norm": 0.09185861796140671,
+      "learning_rate": 0.0001066416543624984,
+      "loss": 0.5354,
+      "step": 510
+    },
+    {
+      "epoch": 0.6108663729809104,
+      "grad_norm": 0.0927920788526535,
+      "learning_rate": 0.00010130902646812369,
+      "loss": 0.5454,
+      "step": 520
+    },
+    {
+      "epoch": 0.6226138032305433,
+      "grad_norm": 0.087093785405159,
+      "learning_rate": 9.604433547109344e-05,
+      "loss": 0.5295,
+      "step": 530
+    },
+    {
+      "epoch": 0.6343612334801763,
+      "grad_norm": 0.09994326531887054,
+      "learning_rate": 9.085492701980751e-05,
+      "loss": 0.5322,
+      "step": 540
+    },
+    {
+      "epoch": 0.6461086637298091,
+      "grad_norm": 0.09507084637880325,
+      "learning_rate": 8.574804172343134e-05,
+      "loss": 0.5224,
+      "step": 550
+    },
+    {
+      "epoch": 0.657856093979442,
+      "grad_norm": 0.08571015298366547,
+      "learning_rate": 8.07308050493148e-05,
+      "loss": 0.5378,
+      "step": 560
+    },
+    {
+      "epoch": 0.6696035242290749,
+      "grad_norm": 0.08876761794090271,
+      "learning_rate": 7.581021738106408e-05,
+      "loss": 0.5265,
+      "step": 570
+    },
+    {
+      "epoch": 0.6813509544787077,
+      "grad_norm": 0.09467241168022156,
+      "learning_rate": 7.099314425113907e-05,
+      "loss": 0.5392,
+      "step": 580
+    },
+    {
+      "epoch": 0.6930983847283406,
+      "grad_norm": 0.08804601430892944,
+      "learning_rate": 6.628630676160445e-05,
+      "loss": 0.5365,
+      "step": 590
+    },
+    {
+      "epoch": 0.7048458149779736,
+      "grad_norm": 0.08877623081207275,
+      "learning_rate": 6.169627220639871e-05,
+      "loss": 0.5354,
+      "step": 600
+    },
+    {
+      "epoch": 0.7165932452276065,
+      "grad_norm": 0.09122662246227264,
+      "learning_rate": 5.722944490820774e-05,
+      "loss": 0.5356,
+      "step": 610
+    },
+    {
+      "epoch": 0.7283406754772394,
+      "grad_norm": 0.08744510263204575,
+      "learning_rate": 5.289205728272586e-05,
+      "loss": 0.5424,
+      "step": 620
+    },
+    {
+      "epoch": 0.7400881057268722,
+      "grad_norm": 0.08927814662456512,
+      "learning_rate": 4.869016114277345e-05,
+      "loss": 0.5268,
+      "step": 630
+    },
+    {
+      "epoch": 0.7518355359765051,
+      "grad_norm": 0.09256933629512787,
+      "learning_rate": 4.462961925440341e-05,
+      "loss": 0.5414,
+      "step": 640
+    },
+    {
+      "epoch": 0.7635829662261381,
+      "grad_norm": 0.08703339844942093,
+      "learning_rate": 4.071609715677899e-05,
+      "loss": 0.5376,
+      "step": 650
+    },
+    {
+      "epoch": 0.775330396475771,
+      "grad_norm": 0.08876251429319382,
+      "learning_rate": 3.695505525723465e-05,
+      "loss": 0.5307,
+      "step": 660
+    },
+    {
+      "epoch": 0.7870778267254038,
+      "grad_norm": 0.08702490478754044,
+      "learning_rate": 3.3351741212551595e-05,
+      "loss": 0.5307,
+      "step": 670
+    },
+    {
+      "epoch": 0.7988252569750367,
+      "grad_norm": 0.08601511269807816,
+      "learning_rate": 2.9911182607076516e-05,
+      "loss": 0.5372,
+      "step": 680
+    },
+    {
+      "epoch": 0.8105726872246696,
+      "grad_norm": 0.0857272818684578,
+      "learning_rate": 2.663817993790021e-05,
+      "loss": 0.528,
+      "step": 690
+    },
+    {
+      "epoch": 0.8223201174743024,
+      "grad_norm": 0.08725214004516602,
+      "learning_rate": 2.3537299916883512e-05,
+      "loss": 0.5378,
+      "step": 700
+    },
+    {
+      "epoch": 0.8340675477239354,
+      "grad_norm": 0.0845843032002449,
+      "learning_rate": 2.0612869098875988e-05,
+      "loss": 0.5389,
+      "step": 710
+    },
+    {
+      "epoch": 0.8458149779735683,
+      "grad_norm": 0.08480172604322433,
+      "learning_rate": 1.786896784501778e-05,
+      "loss": 0.5244,
+      "step": 720
+    },
+    {
+      "epoch": 0.8575624082232012,
+      "grad_norm": 0.09265288710594177,
+      "learning_rate": 1.5309424629547164e-05,
+      "loss": 0.5403,
+      "step": 730
+    },
+    {
+      "epoch": 0.869309838472834,
+      "grad_norm": 0.08523637801408768,
+      "learning_rate": 1.2937810698057921e-05,
+      "loss": 0.5332,
+      "step": 740
+    },
+    {
+      "epoch": 0.8810572687224669,
+      "grad_norm": 0.08431612700223923,
+      "learning_rate": 1.0757435084658694e-05,
+      "loss": 0.5198,
+      "step": 750
+    },
+    {
+      "epoch": 0.8928046989720999,
+      "grad_norm": 0.08998807519674301,
+      "learning_rate": 8.771339994987953e-06,
+      "loss": 0.5251,
+      "step": 760
+    },
+    {
+      "epoch": 0.9045521292217328,
+      "grad_norm": 0.08884080499410629,
+      "learning_rate": 6.98229656152543e-06,
+      "loss": 0.5449,
+      "step": 770
+    },
+    {
+      "epoch": 0.9162995594713657,
+      "grad_norm": 0.08583056926727295,
+      "learning_rate": 5.392800977123047e-06,
+      "loss": 0.5264,
+      "step": 780
+    },
+    {
+      "epoch": 0.9280469897209985,
+      "grad_norm": 0.08824951946735382,
+      "learning_rate": 4.005071012149952e-06,
+      "loss": 0.5306,
+      "step": 790
+    },
+    {
+      "epoch": 0.9397944199706314,
+      "grad_norm": 0.08726619184017181,
+      "learning_rate": 2.821042920111427e-06,
+      "loss": 0.5205,
+      "step": 800
+    },
+    {
+      "epoch": 0.9515418502202643,
+      "grad_norm": 0.08729498088359833,
+      "learning_rate": 1.8423687360584137e-06,
+      "loss": 0.5217,
+      "step": 810
+    },
+    {
+      "epoch": 0.9632892804698973,
+      "grad_norm": 0.08497074991464615,
+      "learning_rate": 1.070413971558115e-06,
+      "loss": 0.534,
+      "step": 820
+    },
+    {
+      "epoch": 0.9750367107195301,
+      "grad_norm": 0.08497001975774765,
+      "learning_rate": 5.062557094410058e-07,
+      "loss": 0.5241,
+      "step": 830
+    },
+    {
+      "epoch": 0.986784140969163,
+      "grad_norm": 0.08295251429080963,
+      "learning_rate": 1.5068110098296338e-07,
+      "loss": 0.5337,
+      "step": 840
+    },
+    {
+      "epoch": 0.9985315712187959,
+      "grad_norm": 0.10860061645507812,
+      "learning_rate": 0.00022638651575377874,
+      "loss": 0.5227,
+      "step": 850
+    },
+    {
+      "epoch": 1.0105726872246696,
+      "grad_norm": 0.11796294897794724,
+      "learning_rate": 0.00022478592280680777,
+      "loss": 0.588,
+      "step": 860
+    },
+    {
+      "epoch": 1.0223201174743024,
+      "grad_norm": 0.1594405323266983,
+      "learning_rate": 0.0002231739162937319,
+      "loss": 0.5307,
+      "step": 870
+    },
+    {
+      "epoch": 1.0340675477239354,
+      "grad_norm": 0.10787333548069,
+      "learning_rate": 0.0002215507422333499,
+      "loss": 0.5359,
+      "step": 880
+    },
+    {
+      "epoch": 1.0458149779735684,
+      "grad_norm": 0.10763130336999893,
+      "learning_rate": 0.0002199166483488127,
+      "loss": 0.5407,
+      "step": 890
+    },
+    {
+      "epoch": 1.0575624082232011,
+      "grad_norm": 0.13658902049064636,
+      "learning_rate": 0.00021827188402981652,
+      "loss": 0.5255,
+      "step": 900
+    },
+    {
+      "epoch": 1.0693098384728341,
+      "grad_norm": 0.10522827506065369,
+      "learning_rate": 0.00021661670029454207,
+      "loss": 0.5276,
+      "step": 910
+    },
+    {
+      "epoch": 1.0810572687224669,
+      "grad_norm": 0.1422538459300995,
+      "learning_rate": 0.0002149513497513448,
+      "loss": 0.5245,
+      "step": 920
+    },
+    {
+      "epoch": 1.0928046989720999,
+      "grad_norm": 0.10326780378818512,
+      "learning_rate": 0.00021327608656020305,
+      "loss": 0.5294,
+      "step": 930
+    },
+    {
+      "epoch": 1.1045521292217328,
+      "grad_norm": 0.11100132018327713,
+      "learning_rate": 0.00021159116639392868,
+      "loss": 0.52,
+      "step": 940
+    },
+    {
+      "epoch": 1.1162995594713656,
+      "grad_norm": 0.09583411365747452,
+      "learning_rate": 0.00020989684639914738,
+      "loss": 0.5247,
+      "step": 950
+    },
+    {
+      "epoch": 1.1280469897209986,
+      "grad_norm": 0.10812857002019882,
+      "learning_rate": 0.00020819338515705378,
+      "loss": 0.5236,
+      "step": 960
+    },
+    {
+      "epoch": 1.1397944199706314,
+      "grad_norm": 0.12208293378353119,
+      "learning_rate": 0.00020648104264394784,
+      "loss": 0.5217,
+      "step": 970
+    },
+    {
+      "epoch": 1.1515418502202643,
+      "grad_norm": 0.11540035158395767,
+      "learning_rate": 0.00020476008019155794,
+      "loss": 0.5387,
+      "step": 980
+    },
+    {
+      "epoch": 1.1632892804698973,
+      "grad_norm": 0.10755149275064468,
+      "learning_rate": 0.00020303076044715738,
+      "loss": 0.5057,
+      "step": 990
+    },
+    {
+      "epoch": 1.17503671071953,
+      "grad_norm": 0.10145018994808197,
+      "learning_rate": 0.0002012933473334804,
+      "loss": 0.5202,
+      "step": 1000
+    },
+    {
+      "epoch": 1.186784140969163,
+      "grad_norm": 0.11095395684242249,
+      "learning_rate": 0.00019954810600844277,
+      "loss": 0.5314,
+      "step": 1010
+    },
+    {
+      "epoch": 1.1985315712187958,
+      "grad_norm": 0.097834512591362,
+      "learning_rate": 0.00019779530282467456,
+      "loss": 0.5178,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2102790014684288,
+      "grad_norm": 0.09915532171726227,
+      "learning_rate": 0.00019603520528887027,
+      "loss": 0.5205,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2220264317180616,
+      "grad_norm": 0.1107698306441307,
+      "learning_rate": 0.00019426808202096298,
+      "loss": 0.5268,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2337738619676946,
+      "grad_norm": 0.11669424921274185,
+      "learning_rate": 0.0001924942027131284,
+      "loss": 0.53,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2455212922173275,
+      "grad_norm": 0.11590099334716797,
+      "learning_rate": 0.00019071383808862534,
+      "loss": 0.5085,
+      "step": 1060
+    },
+    {
+      "epoch": 1.2572687224669603,
+      "grad_norm": 0.1027660220861435,
+      "learning_rate": 0.00018892725986047917,
+      "loss": 0.5193,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2690161527165933,
+      "grad_norm": 0.09436651319265366,
+      "learning_rate": 0.00018713474069001354,
+      "loss": 0.5002,
+      "step": 1080
+    },
+    {
+      "epoch": 1.280763582966226,
+      "grad_norm": 0.11379121989011765,
+      "learning_rate": 0.00018533655414523808,
+      "loss": 0.5212,
+      "step": 1090
+    },
+    {
+      "epoch": 1.292511013215859,
+      "grad_norm": 0.09809733927249908,
+      "learning_rate": 0.00018353297465909717,
+      "loss": 0.5124,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3042584434654918,
+      "grad_norm": 0.1027405858039856,
+      "learning_rate": 0.00018172427748758713,
+      "loss": 0.5177,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3160058737151248,
+      "grad_norm": 0.10089763253927231,
+      "learning_rate": 0.0001799107386677475,
+      "loss": 0.4969,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3277533039647578,
+      "grad_norm": 0.09994267672300339,
+      "learning_rate": 0.0001780926349755332,
+      "loss": 0.516,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3395007342143905,
+      "grad_norm": 0.10974204540252686,
+      "learning_rate": 0.00017627024388357416,
+      "loss": 0.5035,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3512481644640235,
+      "grad_norm": 0.09834876656532288,
+      "learning_rate": 0.00017444384351882817,
+      "loss": 0.5121,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3629955947136563,
+      "grad_norm": 0.09756341576576233,
+      "learning_rate": 0.0001726137126201342,
+      "loss": 0.5289,
+      "step": 1160
+    },
+    {
+      "epoch": 1.3747430249632893,
+      "grad_norm": 0.09796813875436783,
+      "learning_rate": 0.0001707801304956723,
+      "loss": 0.5054,
+      "step": 1170
+    },
+    {
+      "epoch": 1.3864904552129222,
+      "grad_norm": 0.09447074681520462,
+      "learning_rate": 0.00016894337698033663,
+      "loss": 0.5067,
+      "step": 1180
+    },
+    {
+      "epoch": 1.398237885462555,
+      "grad_norm": 0.10086411237716675,
+      "learning_rate": 0.00016710373239302772,
+      "loss": 0.5191,
+      "step": 1190
+    },
+    {
+      "epoch": 1.409985315712188,
+      "grad_norm": 0.10048293322324753,
+      "learning_rate": 0.00016526147749387155,
+      "loss": 0.5073,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4217327459618208,
+      "grad_norm": 0.09760654717683792,
+      "learning_rate": 0.00016341689344137088,
+      "loss": 0.5254,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4334801762114537,
+      "grad_norm": 0.09539603441953659,
+      "learning_rate": 0.00016157026174949538,
+      "loss": 0.5116,
+      "step": 1220
+    },
+    {
+      "epoch": 1.4452276064610867,
+      "grad_norm": 0.09473835676908493,
+      "learning_rate": 0.00015972186424471855,
+      "loss": 0.5011,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4569750367107195,
+      "grad_norm": 0.10754521191120148,
+      "learning_rate": 0.0001578719830230061,
+      "loss": 0.5116,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4687224669603525,
+      "grad_norm": 0.09202101826667786,
+      "learning_rate": 0.00015602090040676324,
+      "loss": 0.4964,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4804698972099852,
+      "grad_norm": 0.1060076653957367,
+      "learning_rate": 0.00015416889890174792,
+      "loss": 0.505,
+      "step": 1260
+    },
+    {
+      "epoch": 1.4922173274596182,
+      "grad_norm": 0.10437231510877609,
+      "learning_rate": 0.0001523162611539557,
+      "loss": 0.5065,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5039647577092512,
+      "grad_norm": 0.14216673374176025,
+      "learning_rate": 0.0001504632699064833,
+      "loss": 0.5221,
+      "step": 1280
+    },
+    {
+      "epoch": 1.515712187958884,
+      "grad_norm": 0.10676784813404083,
+      "learning_rate": 0.00014861020795637716,
+      "loss": 0.5057,
+      "step": 1290
+    },
+    {
+      "epoch": 1.5274596182085167,
+      "grad_norm": 0.09706170856952667,
+      "learning_rate": 0.00014675735811147444,
+      "loss": 0.5054,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5392070484581497,
+      "grad_norm": 0.09725037962198257,
+      "learning_rate": 0.00014490500314724117,
+      "loss": 0.5083,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5509544787077827,
+      "grad_norm": 0.09938537329435349,
+      "learning_rate": 0.0001430534257636167,
+      "loss": 0.5157,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5627019089574157,
+      "grad_norm": 0.10331527143716812,
+      "learning_rate": 0.00014120290854186863,
+      "loss": 0.5151,
+      "step": 1330
+    },
+    {
+      "epoch": 1.5744493392070484,
+      "grad_norm": 0.09629181027412415,
+      "learning_rate": 0.00013935373390146634,
+      "loss": 0.507,
+      "step": 1340
+    },
+    {
+      "epoch": 1.5861967694566812,
+      "grad_norm": 0.10021866858005524,
+      "learning_rate": 0.00013750618405697912,
+      "loss": 0.4973,
+      "step": 1350
+    },
+    {
+      "epoch": 1.5979441997063142,
+      "grad_norm": 0.10414128750562668,
+      "learning_rate": 0.0001356605409750058,
+      "loss": 0.5033,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6096916299559472,
+      "grad_norm": 0.11649428308010101,
+      "learning_rate": 0.0001340013252947644,
+      "loss": 0.5259,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6214390602055802,
+      "grad_norm": 0.09817013144493103,
+      "learning_rate": 0.00013216008080267535,
+      "loss": 0.5164,
+      "step": 1380
+    },
+    {
+      "epoch": 1.633186490455213,
+      "grad_norm": 0.10239794105291367,
+      "learning_rate": 0.0001303215589766901,
+      "loss": 0.5011,
+      "step": 1390
+    },
+    {
+      "epoch": 1.6449339207048457,
+      "grad_norm": 0.09663370996713638,
+      "learning_rate": 0.00012848604040558272,
+      "loss": 0.5096,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6566813509544787,
+      "grad_norm": 0.10224564373493195,
+      "learning_rate": 0.0001266538052197809,
+      "loss": 0.5055,
+      "step": 1410
+    },
+    {
+      "epoch": 1.6684287812041116,
+      "grad_norm": 0.09594379365444183,
+      "learning_rate": 0.00012482513304861364,
+      "loss": 0.5051,
+      "step": 1420
+    },
+    {
+      "epoch": 1.6801762114537446,
+      "grad_norm": 0.10660111159086227,
+      "learning_rate": 0.00012300030297763518,
+      "loss": 0.5076,
+      "step": 1430
+    },
+    {
+      "epoch": 1.6919236417033774,
+      "grad_norm": 0.10405760258436203,
+      "learning_rate": 0.0001211795935060317,
+      "loss": 0.5089,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7036710719530102,
+      "grad_norm": 0.10634606331586838,
+      "learning_rate": 0.00011936328250411801,
+      "loss": 0.504,
+      "step": 1450
+    },
+    {
+      "epoch": 1.7154185022026431,
+      "grad_norm": 0.1119045689702034,
+      "learning_rate": 0.00011755164717092988,
+      "loss": 0.5105,
+      "step": 1460
+    },
+    {
+      "epoch": 1.7271659324522761,
+      "grad_norm": 0.10727712512016296,
+      "learning_rate": 0.00011574496399191876,
+      "loss": 0.5185,
+      "step": 1470
+    },
+    {
+      "epoch": 1.738913362701909,
+      "grad_norm": 0.09993914514780045,
+      "learning_rate": 0.00011394350869675567,
+      "loss": 0.5004,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7506607929515419,
+      "grad_norm": 0.10068885236978531,
+      "learning_rate": 0.00011214755621725042,
+      "loss": 0.5091,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7624082232011746,
+      "grad_norm": 0.09819114953279495,
+      "learning_rate": 0.00011035738064539201,
+      "loss": 0.496,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7741556534508076,
+      "grad_norm": 0.09929963946342468,
+      "learning_rate": 0.00010857325519151842,
+      "loss": 0.5033,
+      "step": 1510
+    },
+    {
+      "epoch": 1.7859030837004406,
+      "grad_norm": 0.09696891903877258,
+      "learning_rate": 0.00010679545214261935,
+      "loss": 0.5133,
+      "step": 1520
+    },
+    {
+      "epoch": 1.7976505139500736,
+      "grad_norm": 0.1030985563993454,
+      "learning_rate": 0.0001050242428207814,
+      "loss": 0.5142,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8093979441997063,
+      "grad_norm": 0.10666483640670776,
+      "learning_rate": 0.0001032598975417796,
+      "loss": 0.5205,
+      "step": 1540
+    },
+    {
+      "epoch": 1.821145374449339,
+      "grad_norm": 0.1053660586476326,
+      "learning_rate": 0.00010150268557382262,
+      "loss": 0.498,
+      "step": 1550
+    },
+    {
+      "epoch": 1.832892804698972,
+      "grad_norm": 0.1028640866279602,
+      "learning_rate": 9.975287509645826e-05,
+      "loss": 0.5096,
+      "step": 1560
+    },
+    {
+      "epoch": 1.844640234948605,
+      "grad_norm": 0.10187330096960068,
+      "learning_rate": 9.801073315964465e-05,
+      "loss": 0.4961,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8563876651982378,
+      "grad_norm": 0.0993318185210228,
+      "learning_rate": 9.627652564299405e-05,
+      "loss": 0.5028,
+      "step": 1580
+    },
+    {
+      "epoch": 1.8681350954478708,
+      "grad_norm": 0.11013616621494293,
+      "learning_rate": 9.455051721519528e-05,
+      "loss": 0.5011,
+      "step": 1590
+    },
+    {
+      "epoch": 1.8798825256975036,
+      "grad_norm": 0.10433095693588257,
+      "learning_rate": 9.283297129362094e-05,
+      "loss": 0.4977,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8916299559471366,
+      "grad_norm": 0.10458213835954666,
+      "learning_rate": 9.112415000412531e-05,
+      "loss": 0.5107,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9033773861967695,
+      "grad_norm": 0.10259649157524109,
+      "learning_rate": 8.942431414104001e-05,
+      "loss": 0.4994,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9151248164464023,
+      "grad_norm": 0.09932565689086914,
+      "learning_rate": 8.773372312737238e-05,
+      "loss": 0.499,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9268722466960353,
+      "grad_norm": 0.10920233279466629,
+      "learning_rate": 8.605263497521283e-05,
+      "loss": 0.5061,
+      "step": 1640
+    },
+    {
+      "epoch": 1.938619676945668,
+      "grad_norm": 0.0942125990986824,
+      "learning_rate": 8.438130624635852e-05,
+      "loss": 0.4941,
+      "step": 1650
+    },
+    {
+      "epoch": 1.950367107195301,
+      "grad_norm": 0.12091836333274841,
+      "learning_rate": 8.271999201315755e-05,
+      "loss": 0.499,
+      "step": 1660
+    },
+    {
+      "epoch": 1.962114537444934,
+      "grad_norm": 0.10680700093507767,
+      "learning_rate": 8.106894581958054e-05,
+      "loss": 0.4949,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9738619676945668,
+      "grad_norm": 0.10140874981880188,
+      "learning_rate": 7.942841964252586e-05,
+      "loss": 0.5032,
+      "step": 1680
+    },
+    {
+      "epoch": 1.9856093979441996,
+      "grad_norm": 0.10470426827669144,
+      "learning_rate": 7.779866385336391e-05,
+      "loss": 0.5072,
+      "step": 1690
+    },
+    {
+      "epoch": 1.9973568281938325,
+      "grad_norm": 0.10490316152572632,
+      "learning_rate": 7.617992717972585e-05,
+      "loss": 0.5024,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0093979441997063,
+      "grad_norm": 0.10185109823942184,
+      "learning_rate": 7.457245666754417e-05,
+      "loss": 0.541,
+      "step": 1710
+    },
+    {
+      "epoch": 2.0211453744493393,
+      "grad_norm": 0.10151582956314087,
+      "learning_rate": 7.297649764334912e-05,
+      "loss": 0.4831,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0328928046989723,
+      "grad_norm": 0.10989069938659668,
+      "learning_rate": 7.139229367682778e-05,
+      "loss": 0.486,
+      "step": 1730
+    },
+    {
+      "epoch": 2.044640234948605,
+      "grad_norm": 0.11440616101026535,
+      "learning_rate": 6.982008654365156e-05,
+      "loss": 0.4842,
+      "step": 1740
+    },
+    {
+      "epoch": 2.056387665198238,
+      "grad_norm": 0.1018548235297203,
+      "learning_rate": 6.82601161885771e-05,
+      "loss": 0.4911,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0681350954478708,
+      "grad_norm": 0.1053592786192894,
+      "learning_rate": 6.671262068882665e-05,
+      "loss": 0.4924,
+      "step": 1760
+    },
+    {
+      "epoch": 2.0798825256975038,
+      "grad_norm": 0.10619944334030151,
+      "learning_rate": 6.517783621775382e-05,
+      "loss": 0.4736,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0916299559471367,
+      "grad_norm": 0.11708024144172668,
+      "learning_rate": 6.36559970087992e-05,
+      "loss": 0.4824,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1033773861967693,
+      "grad_norm": 0.12601934373378754,
+      "learning_rate": 6.214733531974292e-05,
+      "loss": 0.4834,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1151248164464023,
+      "grad_norm": 0.10728344321250916,
+      "learning_rate": 6.065208139725811e-05,
+      "loss": 0.4889,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1268722466960353,
+      "grad_norm": 0.10394187271595001,
+      "learning_rate": 5.917046344177123e-05,
+      "loss": 0.4893,
+      "step": 1810
+    },
+    {
+      "epoch": 2.1386196769456682,
+      "grad_norm": 0.11126961559057236,
+      "learning_rate": 5.770270757263536e-05,
+      "loss": 0.4876,
+      "step": 1820
+    },
+    {
+      "epoch": 2.150367107195301,
+      "grad_norm": 0.10413071513175964,
+      "learning_rate": 5.624903779362031e-05,
+      "loss": 0.4764,
+      "step": 1830
+    },
+    {
+      "epoch": 2.1621145374449338,
+      "grad_norm": 0.10565336793661118,
+      "learning_rate": 5.480967595872602e-05,
+      "loss": 0.4781,
+      "step": 1840
+    },
+    {
+      "epoch": 2.1738619676945667,
+      "grad_norm": 0.10836539417505264,
+      "learning_rate": 5.338484173832413e-05,
+      "loss": 0.4854,
+      "step": 1850
+    },
+    {
+      "epoch": 2.1856093979441997,
+      "grad_norm": 0.11080804467201233,
+      "learning_rate": 5.197475258563249e-05,
+      "loss": 0.4815,
+      "step": 1860
+    },
+    {
+      "epoch": 2.1973568281938327,
+      "grad_norm": 0.11599951237440109,
+      "learning_rate": 5.057962370352815e-05,
+      "loss": 0.4878,
+      "step": 1870
+    },
+    {
+      "epoch": 2.2091042584434657,
+      "grad_norm": 0.10745177417993546,
+      "learning_rate": 4.91996680117041e-05,
+      "loss": 0.4737,
+      "step": 1880
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2553,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 40,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.984916128047563e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1880/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2db69a706d840c833279feb43cd380caf2ea3109923fe2a30592c8b14b96f0e
+size 5752