Upload 13 files

README.md

@@ -1,3 +1,202 @@
----
-license: apache-2.0
----
+---
+base_model: MediaTek-Research/Breeze-7B-FC-v1_0
+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 0.12.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "E:\\text-generation-webui-1.14\\models\\MediaTek-Research_Breeze-7B-FC-v1_0",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32bf7b57ed089e8766f74965674c1174ee6f93d3c61dfebe3921a92ca6d73a7
+size 83945296

added_tokens.json

@@ -0,0 +1,10 @@
+{
+  "<EOD>": 61873,
+  "<PAD>": 61874,
+  "<|answer|>": 61880,
+  "<|im_end|>": 61876,
+  "<|im_start|>": 61875,
+  "<|tool_call_begin|>": 61877,
+  "<|tool_call_end|>": 61878,
+  "<|use_tool|>": 61879
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f5d9991a952c781ec93fa633874bfe6f1be3107d7bcd513069306e922d5bf3
+size 43122964

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcee61872be8ce4b146937b29f4c887e8389a189ad402764ed693c6c6611ac20
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2ed3da33bcb8817ec218d967507fb0ee215dfa8b8db7d2daec6625858ca6f3
+size 1192

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9298e56c094f0d30431b0e52ad53287f0cadc99ac8ca17cc2144b0eb4753f130
+size 911034

tokenizer_config.json

@@ -0,0 +1,110 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61873": {
+      "content": "<EOD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61874": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61875": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61876": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61877": {
+      "content": "<|tool_call_begin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61878": {
+      "content": "<|tool_call_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61879": {
+      "content": "<|use_tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61880": {
+      "content": "<|answer|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ '<s>' }}{% 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_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,1359 @@
+{
+  "best_metric": 0.08053209632635117,
+  "best_model_checkpoint": "saves/Breeze-7B-FC-v1_0-15-12-2024\\checkpoint-1700",
+  "epoch": 0.3381150088257962,
+  "eval_steps": 100,
+  "global_step": 1700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0019889118166223304,
+      "grad_norm": 0.6233828067779541,
+      "learning_rate": 0.0004,
+      "loss": 0.7108,
+      "step": 10
+    },
+    {
+      "epoch": 0.003977823633244661,
+      "grad_norm": 0.4662277102470398,
+      "learning_rate": 0.0004,
+      "loss": 0.729,
+      "step": 20
+    },
+    {
+      "epoch": 0.005966735449866992,
+      "grad_norm": 0.5307815670967102,
+      "learning_rate": 0.0004,
+      "loss": 0.6936,
+      "step": 30
+    },
+    {
+      "epoch": 0.007955647266489322,
+      "grad_norm": 0.5890870690345764,
+      "learning_rate": 0.0004,
+      "loss": 0.7229,
+      "step": 40
+    },
+    {
+      "epoch": 0.009944559083111653,
+      "grad_norm": 0.5515501499176025,
+      "learning_rate": 0.0004,
+      "loss": 0.6669,
+      "step": 50
+    },
+    {
+      "epoch": 0.011933470899733983,
+      "grad_norm": 0.5326377153396606,
+      "learning_rate": 0.0004,
+      "loss": 0.6564,
+      "step": 60
+    },
+    {
+      "epoch": 0.013922382716356313,
+      "grad_norm": 0.5636907815933228,
+      "learning_rate": 0.0004,
+      "loss": 0.6773,
+      "step": 70
+    },
+    {
+      "epoch": 0.015911294532978643,
+      "grad_norm": 0.49359801411628723,
+      "learning_rate": 0.0004,
+      "loss": 0.6516,
+      "step": 80
+    },
+    {
+      "epoch": 0.017900206349600975,
+      "grad_norm": 0.4739631116390228,
+      "learning_rate": 0.0004,
+      "loss": 0.6594,
+      "step": 90
+    },
+    {
+      "epoch": 0.019889118166223307,
+      "grad_norm": 0.5182624459266663,
+      "learning_rate": 0.0004,
+      "loss": 0.69,
+      "step": 100
+    },
+    {
+      "epoch": 0.019889118166223307,
+      "eval_loss": 0.08401616662740707,
+      "eval_runtime": 30.1147,
+      "eval_samples_per_second": 2.69,
+      "eval_steps_per_second": 1.361,
+      "step": 100
+    },
+    {
+      "epoch": 0.021878029982845635,
+      "grad_norm": 0.5577639937400818,
+      "learning_rate": 0.0004,
+      "loss": 0.6813,
+      "step": 110
+    },
+    {
+      "epoch": 0.023866941799467967,
+      "grad_norm": 0.5308650732040405,
+      "learning_rate": 0.0004,
+      "loss": 0.689,
+      "step": 120
+    },
+    {
+      "epoch": 0.025855853616090295,
+      "grad_norm": 0.705682635307312,
+      "learning_rate": 0.0004,
+      "loss": 0.6846,
+      "step": 130
+    },
+    {
+      "epoch": 0.027844765432712627,
+      "grad_norm": 0.5250112414360046,
+      "learning_rate": 0.0004,
+      "loss": 0.6699,
+      "step": 140
+    },
+    {
+      "epoch": 0.02983367724933496,
+      "grad_norm": 0.5885920524597168,
+      "learning_rate": 0.0004,
+      "loss": 0.6733,
+      "step": 150
+    },
+    {
+      "epoch": 0.03182258906595729,
+      "grad_norm": 0.5392662286758423,
+      "learning_rate": 0.0004,
+      "loss": 0.673,
+      "step": 160
+    },
+    {
+      "epoch": 0.03381150088257962,
+      "grad_norm": 0.576032280921936,
+      "learning_rate": 0.0004,
+      "loss": 0.6934,
+      "step": 170
+    },
+    {
+      "epoch": 0.03580041269920195,
+      "grad_norm": 0.5046477317810059,
+      "learning_rate": 0.0004,
+      "loss": 0.6535,
+      "step": 180
+    },
+    {
+      "epoch": 0.03778932451582428,
+      "grad_norm": 0.628962516784668,
+      "learning_rate": 0.0004,
+      "loss": 0.6758,
+      "step": 190
+    },
+    {
+      "epoch": 0.03977823633244661,
+      "grad_norm": 0.5312318801879883,
+      "learning_rate": 0.0004,
+      "loss": 0.6839,
+      "step": 200
+    },
+    {
+      "epoch": 0.03977823633244661,
+      "eval_loss": 0.08386518061161041,
+      "eval_runtime": 30.1222,
+      "eval_samples_per_second": 2.689,
+      "eval_steps_per_second": 1.361,
+      "step": 200
+    },
+    {
+      "epoch": 0.04176714814906894,
+      "grad_norm": 0.5689460635185242,
+      "learning_rate": 0.0004,
+      "loss": 0.6616,
+      "step": 210
+    },
+    {
+      "epoch": 0.04375605996569127,
+      "grad_norm": 0.5760230422019958,
+      "learning_rate": 0.0004,
+      "loss": 0.67,
+      "step": 220
+    },
+    {
+      "epoch": 0.045744971782313605,
+      "grad_norm": 0.6037033200263977,
+      "learning_rate": 0.0004,
+      "loss": 0.6608,
+      "step": 230
+    },
+    {
+      "epoch": 0.04773388359893593,
+      "grad_norm": 0.5196573138237,
+      "learning_rate": 0.0004,
+      "loss": 0.672,
+      "step": 240
+    },
+    {
+      "epoch": 0.04972279541555826,
+      "grad_norm": 0.5766464471817017,
+      "learning_rate": 0.0004,
+      "loss": 0.6651,
+      "step": 250
+    },
+    {
+      "epoch": 0.05171170723218059,
+      "grad_norm": 0.5686795711517334,
+      "learning_rate": 0.0004,
+      "loss": 0.6351,
+      "step": 260
+    },
+    {
+      "epoch": 0.053700619048802925,
+      "grad_norm": 0.5607637763023376,
+      "learning_rate": 0.0004,
+      "loss": 0.659,
+      "step": 270
+    },
+    {
+      "epoch": 0.05568953086542525,
+      "grad_norm": 0.545982837677002,
+      "learning_rate": 0.0004,
+      "loss": 0.6297,
+      "step": 280
+    },
+    {
+      "epoch": 0.05767844268204758,
+      "grad_norm": 0.6047331690788269,
+      "learning_rate": 0.0004,
+      "loss": 0.6541,
+      "step": 290
+    },
+    {
+      "epoch": 0.05966735449866992,
+      "grad_norm": 0.5864997506141663,
+      "learning_rate": 0.0004,
+      "loss": 0.6831,
+      "step": 300
+    },
+    {
+      "epoch": 0.05966735449866992,
+      "eval_loss": 0.0832422524690628,
+      "eval_runtime": 30.1361,
+      "eval_samples_per_second": 2.688,
+      "eval_steps_per_second": 1.36,
+      "step": 300
+    },
+    {
+      "epoch": 0.061656266315292245,
+      "grad_norm": 0.6031671166419983,
+      "learning_rate": 0.0004,
+      "loss": 0.6441,
+      "step": 310
+    },
+    {
+      "epoch": 0.06364517813191457,
+      "grad_norm": 0.5433733463287354,
+      "learning_rate": 0.0004,
+      "loss": 0.6836,
+      "step": 320
+    },
+    {
+      "epoch": 0.06563408994853691,
+      "grad_norm": 0.5863742232322693,
+      "learning_rate": 0.0004,
+      "loss": 0.6804,
+      "step": 330
+    },
+    {
+      "epoch": 0.06762300176515924,
+      "grad_norm": 0.7768782377243042,
+      "learning_rate": 0.0004,
+      "loss": 0.7014,
+      "step": 340
+    },
+    {
+      "epoch": 0.06961191358178156,
+      "grad_norm": 0.548475444316864,
+      "learning_rate": 0.0004,
+      "loss": 0.6545,
+      "step": 350
+    },
+    {
+      "epoch": 0.0716008253984039,
+      "grad_norm": 0.7511247992515564,
+      "learning_rate": 0.0004,
+      "loss": 0.6478,
+      "step": 360
+    },
+    {
+      "epoch": 0.07358973721502624,
+      "grad_norm": 0.6464333534240723,
+      "learning_rate": 0.0004,
+      "loss": 0.6762,
+      "step": 370
+    },
+    {
+      "epoch": 0.07557864903164856,
+      "grad_norm": 0.6280458569526672,
+      "learning_rate": 0.0004,
+      "loss": 0.6723,
+      "step": 380
+    },
+    {
+      "epoch": 0.07756756084827089,
+      "grad_norm": 0.6138644218444824,
+      "learning_rate": 0.0004,
+      "loss": 0.6834,
+      "step": 390
+    },
+    {
+      "epoch": 0.07955647266489323,
+      "grad_norm": 0.6612856984138489,
+      "learning_rate": 0.0004,
+      "loss": 0.662,
+      "step": 400
+    },
+    {
+      "epoch": 0.07955647266489323,
+      "eval_loss": 0.08379939943552017,
+      "eval_runtime": 30.1324,
+      "eval_samples_per_second": 2.688,
+      "eval_steps_per_second": 1.361,
+      "step": 400
+    },
+    {
+      "epoch": 0.08154538448151555,
+      "grad_norm": 0.5658541917800903,
+      "learning_rate": 0.0004,
+      "loss": 0.6507,
+      "step": 410
+    },
+    {
+      "epoch": 0.08353429629813788,
+      "grad_norm": 0.5861065983772278,
+      "learning_rate": 0.0004,
+      "loss": 0.6565,
+      "step": 420
+    },
+    {
+      "epoch": 0.08552320811476022,
+      "grad_norm": 0.6580057144165039,
+      "learning_rate": 0.0004,
+      "loss": 0.6961,
+      "step": 430
+    },
+    {
+      "epoch": 0.08751211993138254,
+      "grad_norm": 0.6456801295280457,
+      "learning_rate": 0.0004,
+      "loss": 0.6667,
+      "step": 440
+    },
+    {
+      "epoch": 0.08950103174800488,
+      "grad_norm": 0.6603415608406067,
+      "learning_rate": 0.0004,
+      "loss": 0.6589,
+      "step": 450
+    },
+    {
+      "epoch": 0.09148994356462721,
+      "grad_norm": 0.6744834184646606,
+      "learning_rate": 0.0004,
+      "loss": 0.6791,
+      "step": 460
+    },
+    {
+      "epoch": 0.09347885538124953,
+      "grad_norm": 0.6219160556793213,
+      "learning_rate": 0.0004,
+      "loss": 0.6748,
+      "step": 470
+    },
+    {
+      "epoch": 0.09546776719787187,
+      "grad_norm": 0.6373462677001953,
+      "learning_rate": 0.0004,
+      "loss": 0.654,
+      "step": 480
+    },
+    {
+      "epoch": 0.09745667901449419,
+      "grad_norm": 0.7271533608436584,
+      "learning_rate": 0.0004,
+      "loss": 0.651,
+      "step": 490
+    },
+    {
+      "epoch": 0.09944559083111652,
+      "grad_norm": 0.6483666300773621,
+      "learning_rate": 0.0004,
+      "loss": 0.6728,
+      "step": 500
+    },
+    {
+      "epoch": 0.09944559083111652,
+      "eval_loss": 0.08319716155529022,
+      "eval_runtime": 30.1252,
+      "eval_samples_per_second": 2.689,
+      "eval_steps_per_second": 1.361,
+      "step": 500
+    },
+    {
+      "epoch": 0.10143450264773886,
+      "grad_norm": 0.5817425847053528,
+      "learning_rate": 0.0004,
+      "loss": 0.6571,
+      "step": 510
+    },
+    {
+      "epoch": 0.10342341446436118,
+      "grad_norm": 0.6830428838729858,
+      "learning_rate": 0.0004,
+      "loss": 0.6618,
+      "step": 520
+    },
+    {
+      "epoch": 0.10541232628098351,
+      "grad_norm": 0.5775642395019531,
+      "learning_rate": 0.0004,
+      "loss": 0.6181,
+      "step": 530
+    },
+    {
+      "epoch": 0.10740123809760585,
+      "grad_norm": 0.6007582545280457,
+      "learning_rate": 0.0004,
+      "loss": 0.6839,
+      "step": 540
+    },
+    {
+      "epoch": 0.10939014991422817,
+      "grad_norm": 0.648262083530426,
+      "learning_rate": 0.0004,
+      "loss": 0.6643,
+      "step": 550
+    },
+    {
+      "epoch": 0.1113790617308505,
+      "grad_norm": 0.6632483601570129,
+      "learning_rate": 0.0004,
+      "loss": 0.652,
+      "step": 560
+    },
+    {
+      "epoch": 0.11336797354747284,
+      "grad_norm": 0.5972626805305481,
+      "learning_rate": 0.0004,
+      "loss": 0.6938,
+      "step": 570
+    },
+    {
+      "epoch": 0.11535688536409516,
+      "grad_norm": 0.6052406430244446,
+      "learning_rate": 0.0004,
+      "loss": 0.6301,
+      "step": 580
+    },
+    {
+      "epoch": 0.1173457971807175,
+      "grad_norm": 0.5875466465950012,
+      "learning_rate": 0.0004,
+      "loss": 0.6614,
+      "step": 590
+    },
+    {
+      "epoch": 0.11933470899733983,
+      "grad_norm": 0.7067976593971252,
+      "learning_rate": 0.0004,
+      "loss": 0.647,
+      "step": 600
+    },
+    {
+      "epoch": 0.11933470899733983,
+      "eval_loss": 0.08319241553544998,
+      "eval_runtime": 30.1031,
+      "eval_samples_per_second": 2.691,
+      "eval_steps_per_second": 1.362,
+      "step": 600
+    },
+    {
+      "epoch": 0.12132362081396215,
+      "grad_norm": 0.66518634557724,
+      "learning_rate": 0.0004,
+      "loss": 0.693,
+      "step": 610
+    },
+    {
+      "epoch": 0.12331253263058449,
+      "grad_norm": 0.6959813833236694,
+      "learning_rate": 0.0004,
+      "loss": 0.6747,
+      "step": 620
+    },
+    {
+      "epoch": 0.1253014444472068,
+      "grad_norm": 0.935105562210083,
+      "learning_rate": 0.0004,
+      "loss": 0.6686,
+      "step": 630
+    },
+    {
+      "epoch": 0.12729035626382915,
+      "grad_norm": 0.713768720626831,
+      "learning_rate": 0.0004,
+      "loss": 0.6707,
+      "step": 640
+    },
+    {
+      "epoch": 0.12927926808045148,
+      "grad_norm": 0.7059699296951294,
+      "learning_rate": 0.0004,
+      "loss": 0.7255,
+      "step": 650
+    },
+    {
+      "epoch": 0.13126817989707382,
+      "grad_norm": 0.588306725025177,
+      "learning_rate": 0.0004,
+      "loss": 0.6689,
+      "step": 660
+    },
+    {
+      "epoch": 0.13325709171369615,
+      "grad_norm": 0.6097111105918884,
+      "learning_rate": 0.0004,
+      "loss": 0.6612,
+      "step": 670
+    },
+    {
+      "epoch": 0.1352460035303185,
+      "grad_norm": 0.642393946647644,
+      "learning_rate": 0.0004,
+      "loss": 0.6743,
+      "step": 680
+    },
+    {
+      "epoch": 0.1372349153469408,
+      "grad_norm": 0.7600162625312805,
+      "learning_rate": 0.0004,
+      "loss": 0.6768,
+      "step": 690
+    },
+    {
+      "epoch": 0.13922382716356313,
+      "grad_norm": 0.7193499207496643,
+      "learning_rate": 0.0004,
+      "loss": 0.6559,
+      "step": 700
+    },
+    {
+      "epoch": 0.13922382716356313,
+      "eval_loss": 0.08392166346311569,
+      "eval_runtime": 30.1253,
+      "eval_samples_per_second": 2.689,
+      "eval_steps_per_second": 1.361,
+      "step": 700
+    },
+    {
+      "epoch": 0.14121273898018546,
+      "grad_norm": 0.6542356014251709,
+      "learning_rate": 0.0004,
+      "loss": 0.6775,
+      "step": 710
+    },
+    {
+      "epoch": 0.1432016507968078,
+      "grad_norm": 0.629941999912262,
+      "learning_rate": 0.0004,
+      "loss": 0.6223,
+      "step": 720
+    },
+    {
+      "epoch": 0.14519056261343014,
+      "grad_norm": 0.6493385434150696,
+      "learning_rate": 0.0004,
+      "loss": 0.6894,
+      "step": 730
+    },
+    {
+      "epoch": 0.14717947443005247,
+      "grad_norm": 0.7201417684555054,
+      "learning_rate": 0.0004,
+      "loss": 0.6858,
+      "step": 740
+    },
+    {
+      "epoch": 0.14916838624667478,
+      "grad_norm": 0.6775253415107727,
+      "learning_rate": 0.0004,
+      "loss": 0.6628,
+      "step": 750
+    },
+    {
+      "epoch": 0.1511572980632971,
+      "grad_norm": 0.6149548292160034,
+      "learning_rate": 0.0004,
+      "loss": 0.6993,
+      "step": 760
+    },
+    {
+      "epoch": 0.15314620987991945,
+      "grad_norm": 0.6627587080001831,
+      "learning_rate": 0.0004,
+      "loss": 0.646,
+      "step": 770
+    },
+    {
+      "epoch": 0.15513512169654178,
+      "grad_norm": 0.6701797842979431,
+      "learning_rate": 0.0004,
+      "loss": 0.6927,
+      "step": 780
+    },
+    {
+      "epoch": 0.15712403351316412,
+      "grad_norm": 0.678193211555481,
+      "learning_rate": 0.0004,
+      "loss": 0.6454,
+      "step": 790
+    },
+    {
+      "epoch": 0.15911294532978645,
+      "grad_norm": 0.6337444186210632,
+      "learning_rate": 0.0004,
+      "loss": 0.6723,
+      "step": 800
+    },
+    {
+      "epoch": 0.15911294532978645,
+      "eval_loss": 0.08426591008901596,
+      "eval_runtime": 30.0445,
+      "eval_samples_per_second": 2.696,
+      "eval_steps_per_second": 1.365,
+      "step": 800
+    },
+    {
+      "epoch": 0.16110185714640876,
+      "grad_norm": 0.654451310634613,
+      "learning_rate": 0.0004,
+      "loss": 0.6799,
+      "step": 810
+    },
+    {
+      "epoch": 0.1630907689630311,
+      "grad_norm": 0.6989086866378784,
+      "learning_rate": 0.0004,
+      "loss": 0.6694,
+      "step": 820
+    },
+    {
+      "epoch": 0.16507968077965343,
+      "grad_norm": 0.6176579594612122,
+      "learning_rate": 0.0004,
+      "loss": 0.6225,
+      "step": 830
+    },
+    {
+      "epoch": 0.16706859259627577,
+      "grad_norm": 0.6462605595588684,
+      "learning_rate": 0.0004,
+      "loss": 0.6584,
+      "step": 840
+    },
+    {
+      "epoch": 0.1690575044128981,
+      "grad_norm": 0.7809733748435974,
+      "learning_rate": 0.0004,
+      "loss": 0.6601,
+      "step": 850
+    },
+    {
+      "epoch": 0.17104641622952044,
+      "grad_norm": 0.7143774032592773,
+      "learning_rate": 0.0004,
+      "loss": 0.6655,
+      "step": 860
+    },
+    {
+      "epoch": 0.17303532804614274,
+      "grad_norm": 0.7137865424156189,
+      "learning_rate": 0.0004,
+      "loss": 0.6849,
+      "step": 870
+    },
+    {
+      "epoch": 0.17502423986276508,
+      "grad_norm": 0.715568482875824,
+      "learning_rate": 0.0004,
+      "loss": 0.6408,
+      "step": 880
+    },
+    {
+      "epoch": 0.17701315167938741,
+      "grad_norm": 0.59111088514328,
+      "learning_rate": 0.0004,
+      "loss": 0.6772,
+      "step": 890
+    },
+    {
+      "epoch": 0.17900206349600975,
+      "grad_norm": 0.7616696357727051,
+      "learning_rate": 0.0004,
+      "loss": 0.6671,
+      "step": 900
+    },
+    {
+      "epoch": 0.17900206349600975,
+      "eval_loss": 0.084267757833004,
+      "eval_runtime": 30.1275,
+      "eval_samples_per_second": 2.689,
+      "eval_steps_per_second": 1.361,
+      "step": 900
+    },
+    {
+      "epoch": 0.18099097531263209,
+      "grad_norm": 0.6685693860054016,
+      "learning_rate": 0.0004,
+      "loss": 0.6792,
+      "step": 910
+    },
+    {
+      "epoch": 0.18297988712925442,
+      "grad_norm": 0.7320526838302612,
+      "learning_rate": 0.0004,
+      "loss": 0.6435,
+      "step": 920
+    },
+    {
+      "epoch": 0.18496879894587673,
+      "grad_norm": 0.6541480422019958,
+      "learning_rate": 0.0004,
+      "loss": 0.6649,
+      "step": 930
+    },
+    {
+      "epoch": 0.18695771076249906,
+      "grad_norm": 0.6433006525039673,
+      "learning_rate": 0.0004,
+      "loss": 0.6677,
+      "step": 940
+    },
+    {
+      "epoch": 0.1889466225791214,
+      "grad_norm": 0.6296941041946411,
+      "learning_rate": 0.0004,
+      "loss": 0.6334,
+      "step": 950
+    },
+    {
+      "epoch": 0.19093553439574373,
+      "grad_norm": 0.7856689691543579,
+      "learning_rate": 0.0004,
+      "loss": 0.7039,
+      "step": 960
+    },
+    {
+      "epoch": 0.19292444621236607,
+      "grad_norm": 0.6200475096702576,
+      "learning_rate": 0.0004,
+      "loss": 0.6602,
+      "step": 970
+    },
+    {
+      "epoch": 0.19491335802898838,
+      "grad_norm": 0.6970551609992981,
+      "learning_rate": 0.0004,
+      "loss": 0.6704,
+      "step": 980
+    },
+    {
+      "epoch": 0.1969022698456107,
+      "grad_norm": 0.6525449752807617,
+      "learning_rate": 0.0004,
+      "loss": 0.6721,
+      "step": 990
+    },
+    {
+      "epoch": 0.19889118166223305,
+      "grad_norm": 0.7507511377334595,
+      "learning_rate": 0.0004,
+      "loss": 0.6829,
+      "step": 1000
+    },
+    {
+      "epoch": 0.19889118166223305,
+      "eval_loss": 0.0835462287068367,
+      "eval_runtime": 30.0507,
+      "eval_samples_per_second": 2.695,
+      "eval_steps_per_second": 1.364,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20088009347885538,
+      "grad_norm": 0.7378696203231812,
+      "learning_rate": 0.0004,
+      "loss": 0.6567,
+      "step": 1010
+    },
+    {
+      "epoch": 0.20286900529547772,
+      "grad_norm": 0.6451396346092224,
+      "learning_rate": 0.0004,
+      "loss": 0.6502,
+      "step": 1020
+    },
+    {
+      "epoch": 0.20485791711210005,
+      "grad_norm": 0.6342566013336182,
+      "learning_rate": 0.0004,
+      "loss": 0.6477,
+      "step": 1030
+    },
+    {
+      "epoch": 0.20684682892872236,
+      "grad_norm": 0.7209526896476746,
+      "learning_rate": 0.0004,
+      "loss": 0.6661,
+      "step": 1040
+    },
+    {
+      "epoch": 0.2088357407453447,
+      "grad_norm": 0.6808329820632935,
+      "learning_rate": 0.0004,
+      "loss": 0.6515,
+      "step": 1050
+    },
+    {
+      "epoch": 0.21082465256196703,
+      "grad_norm": 0.6738231182098389,
+      "learning_rate": 0.0004,
+      "loss": 0.626,
+      "step": 1060
+    },
+    {
+      "epoch": 0.21281356437858936,
+      "grad_norm": 0.6646963357925415,
+      "learning_rate": 0.0004,
+      "loss": 0.6714,
+      "step": 1070
+    },
+    {
+      "epoch": 0.2148024761952117,
+      "grad_norm": 0.6372888088226318,
+      "learning_rate": 0.0004,
+      "loss": 0.6768,
+      "step": 1080
+    },
+    {
+      "epoch": 0.21679138801183404,
+      "grad_norm": 0.7138890624046326,
+      "learning_rate": 0.0004,
+      "loss": 0.6949,
+      "step": 1090
+    },
+    {
+      "epoch": 0.21878029982845634,
+      "grad_norm": 0.7249679565429688,
+      "learning_rate": 0.0004,
+      "loss": 0.6928,
+      "step": 1100
+    },
+    {
+      "epoch": 0.21878029982845634,
+      "eval_loss": 0.08422956615686417,
+      "eval_runtime": 30.1032,
+      "eval_samples_per_second": 2.691,
+      "eval_steps_per_second": 1.362,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22076921164507868,
+      "grad_norm": 0.6382346153259277,
+      "learning_rate": 0.0004,
+      "loss": 0.6619,
+      "step": 1110
+    },
+    {
+      "epoch": 0.222758123461701,
+      "grad_norm": 0.6400596499443054,
+      "learning_rate": 0.0004,
+      "loss": 0.7103,
+      "step": 1120
+    },
+    {
+      "epoch": 0.22474703527832335,
+      "grad_norm": 0.6994810700416565,
+      "learning_rate": 0.0004,
+      "loss": 0.6647,
+      "step": 1130
+    },
+    {
+      "epoch": 0.22673594709494568,
+      "grad_norm": 0.76835036277771,
+      "learning_rate": 0.0004,
+      "loss": 0.6923,
+      "step": 1140
+    },
+    {
+      "epoch": 0.22872485891156802,
+      "grad_norm": 0.6603644490242004,
+      "learning_rate": 0.0004,
+      "loss": 0.673,
+      "step": 1150
+    },
+    {
+      "epoch": 0.23071377072819033,
+      "grad_norm": 0.7264408469200134,
+      "learning_rate": 0.0004,
+      "loss": 0.6828,
+      "step": 1160
+    },
+    {
+      "epoch": 0.23270268254481266,
+      "grad_norm": 0.7072731852531433,
+      "learning_rate": 0.0004,
+      "loss": 0.6831,
+      "step": 1170
+    },
+    {
+      "epoch": 0.234691594361435,
+      "grad_norm": 0.6494096517562866,
+      "learning_rate": 0.0004,
+      "loss": 0.6659,
+      "step": 1180
+    },
+    {
+      "epoch": 0.23668050617805733,
+      "grad_norm": 0.6463006734848022,
+      "learning_rate": 0.0004,
+      "loss": 0.7155,
+      "step": 1190
+    },
+    {
+      "epoch": 0.23866941799467967,
+      "grad_norm": 0.6508920192718506,
+      "learning_rate": 0.0004,
+      "loss": 0.6563,
+      "step": 1200
+    },
+    {
+      "epoch": 0.23866941799467967,
+      "eval_loss": 0.08387701213359833,
+      "eval_runtime": 30.0299,
+      "eval_samples_per_second": 2.697,
+      "eval_steps_per_second": 1.365,
+      "step": 1200
+    },
+    {
+      "epoch": 0.240658329811302,
+      "grad_norm": 0.6701735258102417,
+      "learning_rate": 0.0004,
+      "loss": 0.6765,
+      "step": 1210
+    },
+    {
+      "epoch": 0.2426472416279243,
+      "grad_norm": 0.5798119902610779,
+      "learning_rate": 0.0004,
+      "loss": 0.6501,
+      "step": 1220
+    },
+    {
+      "epoch": 0.24463615344454664,
+      "grad_norm": 0.7210298776626587,
+      "learning_rate": 0.0004,
+      "loss": 0.6576,
+      "step": 1230
+    },
+    {
+      "epoch": 0.24662506526116898,
+      "grad_norm": 0.7448759078979492,
+      "learning_rate": 0.0004,
+      "loss": 0.6918,
+      "step": 1240
+    },
+    {
+      "epoch": 0.24861397707779131,
+      "grad_norm": 0.6556337475776672,
+      "learning_rate": 0.0004,
+      "loss": 0.6526,
+      "step": 1250
+    },
+    {
+      "epoch": 0.2506028888944136,
+      "grad_norm": 0.6584301590919495,
+      "learning_rate": 0.0004,
+      "loss": 0.6736,
+      "step": 1260
+    },
+    {
+      "epoch": 0.252591800711036,
+      "grad_norm": 0.6725241541862488,
+      "learning_rate": 0.0004,
+      "loss": 0.6772,
+      "step": 1270
+    },
+    {
+      "epoch": 0.2545807125276583,
+      "grad_norm": 0.7188987731933594,
+      "learning_rate": 0.0004,
+      "loss": 0.6629,
+      "step": 1280
+    },
+    {
+      "epoch": 0.25656962434428066,
+      "grad_norm": 0.8247680068016052,
+      "learning_rate": 0.0004,
+      "loss": 0.6844,
+      "step": 1290
+    },
+    {
+      "epoch": 0.25855853616090296,
+      "grad_norm": 0.6960418224334717,
+      "learning_rate": 0.0004,
+      "loss": 0.6411,
+      "step": 1300
+    },
+    {
+      "epoch": 0.25855853616090296,
+      "eval_loss": 0.0839666873216629,
+      "eval_runtime": 30.0597,
+      "eval_samples_per_second": 2.695,
+      "eval_steps_per_second": 1.364,
+      "step": 1300
+    },
+    {
+      "epoch": 0.26054744797752527,
+      "grad_norm": 0.6796591877937317,
+      "learning_rate": 0.0004,
+      "loss": 0.6707,
+      "step": 1310
+    },
+    {
+      "epoch": 0.26253635979414763,
+      "grad_norm": 0.6542907357215881,
+      "learning_rate": 0.0004,
+      "loss": 0.6691,
+      "step": 1320
+    },
+    {
+      "epoch": 0.26452527161076994,
+      "grad_norm": 0.6826708912849426,
+      "learning_rate": 0.0004,
+      "loss": 0.6696,
+      "step": 1330
+    },
+    {
+      "epoch": 0.2665141834273923,
+      "grad_norm": 0.7088764905929565,
+      "learning_rate": 0.0004,
+      "loss": 0.6817,
+      "step": 1340
+    },
+    {
+      "epoch": 0.2685030952440146,
+      "grad_norm": 0.7242617607116699,
+      "learning_rate": 0.0004,
+      "loss": 0.6759,
+      "step": 1350
+    },
+    {
+      "epoch": 0.270492007060637,
+      "grad_norm": 0.7008711099624634,
+      "learning_rate": 0.0004,
+      "loss": 0.6592,
+      "step": 1360
+    },
+    {
+      "epoch": 0.2724809188772593,
+      "grad_norm": 0.6489241719245911,
+      "learning_rate": 0.0004,
+      "loss": 0.6637,
+      "step": 1370
+    },
+    {
+      "epoch": 0.2744698306938816,
+      "grad_norm": 0.7217922806739807,
+      "learning_rate": 0.0004,
+      "loss": 0.6539,
+      "step": 1380
+    },
+    {
+      "epoch": 0.27645874251050395,
+      "grad_norm": 0.8037365078926086,
+      "learning_rate": 0.0004,
+      "loss": 0.6994,
+      "step": 1390
+    },
+    {
+      "epoch": 0.27844765432712626,
+      "grad_norm": 0.659654974937439,
+      "learning_rate": 0.0004,
+      "loss": 0.6673,
+      "step": 1400
+    },
+    {
+      "epoch": 0.27844765432712626,
+      "eval_loss": 0.0840681791305542,
+      "eval_runtime": 30.0353,
+      "eval_samples_per_second": 2.697,
+      "eval_steps_per_second": 1.365,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2804365661437486,
+      "grad_norm": 0.7238272428512573,
+      "learning_rate": 0.0004,
+      "loss": 0.6974,
+      "step": 1410
+    },
+    {
+      "epoch": 0.28242547796037093,
+      "grad_norm": 0.6564947366714478,
+      "learning_rate": 0.0004,
+      "loss": 0.6687,
+      "step": 1420
+    },
+    {
+      "epoch": 0.28441438977699324,
+      "grad_norm": 0.7392669916152954,
+      "learning_rate": 0.0004,
+      "loss": 0.6546,
+      "step": 1430
+    },
+    {
+      "epoch": 0.2864033015936156,
+      "grad_norm": 0.7504440546035767,
+      "learning_rate": 0.0004,
+      "loss": 0.6737,
+      "step": 1440
+    },
+    {
+      "epoch": 0.2883922134102379,
+      "grad_norm": 0.7336270213127136,
+      "learning_rate": 0.0004,
+      "loss": 0.6803,
+      "step": 1450
+    },
+    {
+      "epoch": 0.29038112522686027,
+      "grad_norm": 1.862186312675476,
+      "learning_rate": 0.0004,
+      "loss": 0.658,
+      "step": 1460
+    },
+    {
+      "epoch": 0.2923700370434826,
+      "grad_norm": 0.7425276637077332,
+      "learning_rate": 0.0004,
+      "loss": 0.6383,
+      "step": 1470
+    },
+    {
+      "epoch": 0.29435894886010494,
+      "grad_norm": 0.6604830622673035,
+      "learning_rate": 0.0004,
+      "loss": 0.7077,
+      "step": 1480
+    },
+    {
+      "epoch": 0.29634786067672725,
+      "grad_norm": 0.7673712968826294,
+      "learning_rate": 0.0004,
+      "loss": 0.6722,
+      "step": 1490
+    },
+    {
+      "epoch": 0.29833677249334956,
+      "grad_norm": 0.7889634370803833,
+      "learning_rate": 0.0004,
+      "loss": 0.6909,
+      "step": 1500
+    },
+    {
+      "epoch": 0.29833677249334956,
+      "eval_loss": 0.08427305519580841,
+      "eval_runtime": 30.0826,
+      "eval_samples_per_second": 2.693,
+      "eval_steps_per_second": 1.363,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3003256843099719,
+      "grad_norm": 0.8077505826950073,
+      "learning_rate": 0.0004,
+      "loss": 0.6976,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3023145961265942,
+      "grad_norm": 0.6837480068206787,
+      "learning_rate": 0.0004,
+      "loss": 0.675,
+      "step": 1520
+    },
+    {
+      "epoch": 0.3043035079432166,
+      "grad_norm": 0.6629063487052917,
+      "learning_rate": 0.0004,
+      "loss": 0.6396,
+      "step": 1530
+    },
+    {
+      "epoch": 0.3062924197598389,
+      "grad_norm": 0.7187213897705078,
+      "learning_rate": 0.0004,
+      "loss": 0.6898,
+      "step": 1540
+    },
+    {
+      "epoch": 0.3082813315764612,
+      "grad_norm": 0.7269571423530579,
+      "learning_rate": 0.0004,
+      "loss": 0.7106,
+      "step": 1550
+    },
+    {
+      "epoch": 0.31027024339308357,
+      "grad_norm": 0.6767787337303162,
+      "learning_rate": 0.0004,
+      "loss": 0.6836,
+      "step": 1560
+    },
+    {
+      "epoch": 0.3122591552097059,
+      "grad_norm": 0.7046016454696655,
+      "learning_rate": 0.0004,
+      "loss": 0.7129,
+      "step": 1570
+    },
+    {
+      "epoch": 0.31424806702632824,
+      "grad_norm": 0.6218843460083008,
+      "learning_rate": 0.0004,
+      "loss": 0.7129,
+      "step": 1580
+    },
+    {
+      "epoch": 0.31623697884295054,
+      "grad_norm": 0.7410914897918701,
+      "learning_rate": 0.0004,
+      "loss": 0.6616,
+      "step": 1590
+    },
+    {
+      "epoch": 0.3182258906595729,
+      "grad_norm": 0.5945529937744141,
+      "learning_rate": 0.0004,
+      "loss": 0.6878,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3182258906595729,
+      "eval_loss": 0.08433911204338074,
+      "eval_runtime": 30.0269,
+      "eval_samples_per_second": 2.698,
+      "eval_steps_per_second": 1.365,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3202148024761952,
+      "grad_norm": 0.6479379534721375,
+      "learning_rate": 4e-05,
+      "loss": 0.6708,
+      "step": 1610
+    },
+    {
+      "epoch": 0.3222037142928175,
+      "grad_norm": 0.6011672616004944,
+      "learning_rate": 4e-05,
+      "loss": 0.6511,
+      "step": 1620
+    },
+    {
+      "epoch": 0.3241926261094399,
+      "grad_norm": 0.6457736492156982,
+      "learning_rate": 4e-05,
+      "loss": 0.6601,
+      "step": 1630
+    },
+    {
+      "epoch": 0.3261815379260622,
+      "grad_norm": 0.6549608707427979,
+      "learning_rate": 4e-05,
+      "loss": 0.6643,
+      "step": 1640
+    },
+    {
+      "epoch": 0.32817044974268456,
+      "grad_norm": 0.6869723200798035,
+      "learning_rate": 4e-05,
+      "loss": 0.6766,
+      "step": 1650
+    },
+    {
+      "epoch": 0.33015936155930686,
+      "grad_norm": 0.6526493430137634,
+      "learning_rate": 4e-05,
+      "loss": 0.6625,
+      "step": 1660
+    },
+    {
+      "epoch": 0.33214827337592917,
+      "grad_norm": 0.6106629967689514,
+      "learning_rate": 4e-05,
+      "loss": 0.6412,
+      "step": 1670
+    },
+    {
+      "epoch": 0.33413718519255153,
+      "grad_norm": 0.6620826125144958,
+      "learning_rate": 4e-05,
+      "loss": 0.6314,
+      "step": 1680
+    },
+    {
+      "epoch": 0.33612609700917384,
+      "grad_norm": 0.6487278938293457,
+      "learning_rate": 4e-05,
+      "loss": 0.643,
+      "step": 1690
+    },
+    {
+      "epoch": 0.3381150088257962,
+      "grad_norm": 0.7703284621238708,
+      "learning_rate": 4e-05,
+      "loss": 0.6298,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3381150088257962,
+      "eval_loss": 0.08053209632635117,
+      "eval_runtime": 30.0784,
+      "eval_samples_per_second": 2.693,
+      "eval_steps_per_second": 1.363,
+      "step": 1700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.460398769660756e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a8bdead2dfcd61275615e9f65facc545f9e35cb810202e1131816f9357b94d
+size 5432