Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-chat-hf
+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 0.11.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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 sha256:664577383fae465b6299029c0f0847d3d740adf82802d1de24ec75da75106175
+size 16794200

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9bd9b987ee73b2af0ecbbc48251c6dcfe6de4ee3c02c0baaa3a9a572d7f823
+size 33630266

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310599335792fed3fbc00eff33df8547382562ea0cb5206faac1c420671c1302
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a1760d654783fa21ab023433f66d210cdfce9d79e1ba7107ab45b42aa3b2970
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1678 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0425531914893617,
+      "grad_norm": 0.49684813618659973,
+      "learning_rate": 0.00019999602855426865,
+      "loss": 1.1262,
+      "step": 10
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 0.43794313073158264,
+      "learning_rate": 0.00019998411453252217,
+      "loss": 0.8855,
+      "step": 20
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 0.7506595253944397,
+      "learning_rate": 0.0001999642588810784,
+      "loss": 0.652,
+      "step": 30
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.57978355884552,
+      "learning_rate": 0.00019993646317705016,
+      "loss": 0.4779,
+      "step": 40
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.583155632019043,
+      "learning_rate": 0.00019990072962822007,
+      "loss": 0.4035,
+      "step": 50
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 0.6853554844856262,
+      "learning_rate": 0.00019985706107286514,
+      "loss": 0.3479,
+      "step": 60
+    },
+    {
+      "epoch": 0.2978723404255319,
+      "grad_norm": 0.7098686099052429,
+      "learning_rate": 0.00019980546097953132,
+      "loss": 0.2903,
+      "step": 70
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.6163254380226135,
+      "learning_rate": 0.000199745933446758,
+      "loss": 0.2884,
+      "step": 80
+    },
+    {
+      "epoch": 0.3829787234042553,
+      "grad_norm": 1.0676591396331787,
+      "learning_rate": 0.0001996784832027525,
+      "loss": 0.2821,
+      "step": 90
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.9656098484992981,
+      "learning_rate": 0.00019960311560501454,
+      "loss": 0.2012,
+      "step": 100
+    },
+    {
+      "epoch": 0.46808510638297873,
+      "grad_norm": 0.7761662602424622,
+      "learning_rate": 0.00019951983663991056,
+      "loss": 0.2072,
+      "step": 110
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.7839683294296265,
+      "learning_rate": 0.00019942865292219838,
+      "loss": 0.1505,
+      "step": 120
+    },
+    {
+      "epoch": 0.5531914893617021,
+      "grad_norm": 0.6823858618736267,
+      "learning_rate": 0.0001993295716945017,
+      "loss": 0.1818,
+      "step": 130
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.579463005065918,
+      "learning_rate": 0.00019922260082673497,
+      "loss": 0.1059,
+      "step": 140
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 1.7094753980636597,
+      "learning_rate": 0.000199107748815478,
+      "loss": 0.1426,
+      "step": 150
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.9202602505683899,
+      "learning_rate": 0.00019898502478330152,
+      "loss": 0.0965,
+      "step": 160
+    },
+    {
+      "epoch": 0.723404255319149,
+      "grad_norm": 0.37124085426330566,
+      "learning_rate": 0.00019885443847804211,
+      "loss": 0.1027,
+      "step": 170
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.4608505666255951,
+      "learning_rate": 0.0001987160002720283,
+      "loss": 0.0691,
+      "step": 180
+    },
+    {
+      "epoch": 0.8085106382978723,
+      "grad_norm": 0.3972225487232208,
+      "learning_rate": 0.00019856972116125653,
+      "loss": 0.0891,
+      "step": 190
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.8271582126617432,
+      "learning_rate": 0.0001984156127645178,
+      "loss": 0.0726,
+      "step": 200
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 0.889887809753418,
+      "learning_rate": 0.0001982536873224748,
+      "loss": 0.1066,
+      "step": 210
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.7588837742805481,
+      "learning_rate": 0.00019808395769668963,
+      "loss": 0.0511,
+      "step": 220
+    },
+    {
+      "epoch": 0.9787234042553191,
+      "grad_norm": 0.3827434480190277,
+      "learning_rate": 0.00019790643736860227,
+      "loss": 0.0746,
+      "step": 230
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 1.043514609336853,
+      "learning_rate": 0.00019772114043845965,
+      "loss": 0.059,
+      "step": 240
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.5586545467376709,
+      "learning_rate": 0.0001975280816241959,
+      "loss": 0.0457,
+      "step": 250
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.6704376935958862,
+      "learning_rate": 0.00019732727626026305,
+      "loss": 0.0572,
+      "step": 260
+    },
+    {
+      "epoch": 1.148936170212766,
+      "grad_norm": 0.19444280862808228,
+      "learning_rate": 0.0001971187402964132,
+      "loss": 0.037,
+      "step": 270
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.3722103238105774,
+      "learning_rate": 0.00019690249029643162,
+      "loss": 0.0716,
+      "step": 280
+    },
+    {
+      "epoch": 1.2340425531914894,
+      "grad_norm": 0.50620037317276,
+      "learning_rate": 0.0001966785434368211,
+      "loss": 0.0346,
+      "step": 290
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.49648305773735046,
+      "learning_rate": 0.00019644691750543767,
+      "loss": 0.0288,
+      "step": 300
+    },
+    {
+      "epoch": 1.3191489361702127,
+      "grad_norm": 0.3201454281806946,
+      "learning_rate": 0.00019620763090007762,
+      "loss": 0.0317,
+      "step": 310
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.2545865774154663,
+      "learning_rate": 0.00019596070262701626,
+      "loss": 0.0166,
+      "step": 320
+    },
+    {
+      "epoch": 1.4042553191489362,
+      "grad_norm": 0.23364359140396118,
+      "learning_rate": 0.00019570615229949842,
+      "loss": 0.0357,
+      "step": 330
+    },
+    {
+      "epoch": 1.4468085106382977,
+      "grad_norm": 0.4658994972705841,
+      "learning_rate": 0.00019544400013618023,
+      "loss": 0.0319,
+      "step": 340
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.11836043000221252,
+      "learning_rate": 0.00019517426695952358,
+      "loss": 0.0228,
+      "step": 350
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 0.7419282793998718,
+      "learning_rate": 0.00019489697419414182,
+      "loss": 0.0323,
+      "step": 360
+    },
+    {
+      "epoch": 1.574468085106383,
+      "grad_norm": 0.8870681524276733,
+      "learning_rate": 0.00019461214386509842,
+      "loss": 0.0493,
+      "step": 370
+    },
+    {
+      "epoch": 1.6170212765957448,
+      "grad_norm": 0.5847530961036682,
+      "learning_rate": 0.00019431979859615726,
+      "loss": 0.0487,
+      "step": 380
+    },
+    {
+      "epoch": 1.6595744680851063,
+      "grad_norm": 0.9245363473892212,
+      "learning_rate": 0.00019401996160798573,
+      "loss": 0.0634,
+      "step": 390
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.5757696032524109,
+      "learning_rate": 0.00019371265671631037,
+      "loss": 0.0439,
+      "step": 400
+    },
+    {
+      "epoch": 1.7446808510638299,
+      "grad_norm": 0.5014369487762451,
+      "learning_rate": 0.00019339790833002515,
+      "loss": 0.0316,
+      "step": 410
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 0.49838268756866455,
+      "learning_rate": 0.00019307574144925287,
+      "loss": 0.0535,
+      "step": 420
+    },
+    {
+      "epoch": 1.8297872340425532,
+      "grad_norm": 0.848798930644989,
+      "learning_rate": 0.00019274618166335912,
+      "loss": 0.0396,
+      "step": 430
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 0.41701218485832214,
+      "learning_rate": 0.00019240925514892,
+      "loss": 0.027,
+      "step": 440
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 1.0935739278793335,
+      "learning_rate": 0.00019206498866764288,
+      "loss": 0.0321,
+      "step": 450
+    },
+    {
+      "epoch": 1.9574468085106385,
+      "grad_norm": 0.7538416385650635,
+      "learning_rate": 0.00019171340956424074,
+      "loss": 0.0221,
+      "step": 460
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.4453732371330261,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0345,
+      "step": 470
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.2772938311100006,
+      "learning_rate": 0.00019098842577186314,
+      "loss": 0.0185,
+      "step": 480
+    },
+    {
+      "epoch": 2.0851063829787235,
+      "grad_norm": 0.12744171917438507,
+      "learning_rate": 0.00019061507866756347,
+      "loss": 0.0213,
+      "step": 490
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.29645049571990967,
+      "learning_rate": 0.00019023453410591635,
+      "loss": 0.0257,
+      "step": 500
+    },
+    {
+      "epoch": 2.1702127659574466,
+      "grad_norm": 0.22986823320388794,
+      "learning_rate": 0.00018984682231316333,
+      "loss": 0.0099,
+      "step": 510
+    },
+    {
+      "epoch": 2.2127659574468086,
+      "grad_norm": 0.19042347371578217,
+      "learning_rate": 0.00018945197408483123,
+      "loss": 0.0163,
+      "step": 520
+    },
+    {
+      "epoch": 2.25531914893617,
+      "grad_norm": 0.13396915793418884,
+      "learning_rate": 0.00018905002078328632,
+      "loss": 0.0225,
+      "step": 530
+    },
+    {
+      "epoch": 2.297872340425532,
+      "grad_norm": 0.08411907404661179,
+      "learning_rate": 0.000188640994335243,
+      "loss": 0.0158,
+      "step": 540
+    },
+    {
+      "epoch": 2.3404255319148937,
+      "grad_norm": 0.16173473000526428,
+      "learning_rate": 0.0001882249272292282,
+      "loss": 0.0164,
+      "step": 550
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 0.3895552158355713,
+      "learning_rate": 0.00018780185251300046,
+      "loss": 0.0255,
+      "step": 560
+    },
+    {
+      "epoch": 2.425531914893617,
+      "grad_norm": 0.42386066913604736,
+      "learning_rate": 0.00018737180379092537,
+      "loss": 0.0315,
+      "step": 570
+    },
+    {
+      "epoch": 2.4680851063829787,
+      "grad_norm": 0.10213664919137955,
+      "learning_rate": 0.0001869348152213061,
+      "loss": 0.0321,
+      "step": 580
+    },
+    {
+      "epoch": 2.5106382978723403,
+      "grad_norm": 0.27683985233306885,
+      "learning_rate": 0.0001864909215136705,
+      "loss": 0.0243,
+      "step": 590
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 0.7269228100776672,
+      "learning_rate": 0.00018604015792601396,
+      "loss": 0.0276,
+      "step": 600
+    },
+    {
+      "epoch": 2.595744680851064,
+      "grad_norm": 0.23035497963428497,
+      "learning_rate": 0.00018558256026199896,
+      "loss": 0.0208,
+      "step": 610
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "grad_norm": 0.334359347820282,
+      "learning_rate": 0.00018511816486811134,
+      "loss": 0.0228,
+      "step": 620
+    },
+    {
+      "epoch": 2.6808510638297873,
+      "grad_norm": 0.07350382953882217,
+      "learning_rate": 0.00018464700863077312,
+      "loss": 0.0295,
+      "step": 630
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 0.39336535334587097,
+      "learning_rate": 0.00018416912897341295,
+      "loss": 0.0289,
+      "step": 640
+    },
+    {
+      "epoch": 2.7659574468085104,
+      "grad_norm": 0.15300992131233215,
+      "learning_rate": 0.00018368456385349334,
+      "loss": 0.0183,
+      "step": 650
+    },
+    {
+      "epoch": 2.8085106382978724,
+      "grad_norm": 0.07117566466331482,
+      "learning_rate": 0.0001831933517594957,
+      "loss": 0.0345,
+      "step": 660
+    },
+    {
+      "epoch": 2.851063829787234,
+      "grad_norm": 0.1297655552625656,
+      "learning_rate": 0.0001826955317078636,
+      "loss": 0.0171,
+      "step": 670
+    },
+    {
+      "epoch": 2.8936170212765955,
+      "grad_norm": 0.361150324344635,
+      "learning_rate": 0.00018219114323990345,
+      "loss": 0.0174,
+      "step": 680
+    },
+    {
+      "epoch": 2.9361702127659575,
+      "grad_norm": 0.7295799851417542,
+      "learning_rate": 0.00018168022641864377,
+      "loss": 0.0226,
+      "step": 690
+    },
+    {
+      "epoch": 2.978723404255319,
+      "grad_norm": 0.06540104746818542,
+      "learning_rate": 0.00018116282182565311,
+      "loss": 0.0374,
+      "step": 700
+    },
+    {
+      "epoch": 3.021276595744681,
+      "grad_norm": 0.6617436408996582,
+      "learning_rate": 0.0001806389705578168,
+      "loss": 0.0136,
+      "step": 710
+    },
+    {
+      "epoch": 3.0638297872340425,
+      "grad_norm": 0.28398895263671875,
+      "learning_rate": 0.00018010871422407236,
+      "loss": 0.0185,
+      "step": 720
+    },
+    {
+      "epoch": 3.106382978723404,
+      "grad_norm": 0.07346879690885544,
+      "learning_rate": 0.00017957209494210493,
+      "loss": 0.0197,
+      "step": 730
+    },
+    {
+      "epoch": 3.148936170212766,
+      "grad_norm": 0.06647660583257675,
+      "learning_rate": 0.0001790291553350016,
+      "loss": 0.0093,
+      "step": 740
+    },
+    {
+      "epoch": 3.1914893617021276,
+      "grad_norm": 0.0874147042632103,
+      "learning_rate": 0.0001784799385278661,
+      "loss": 0.01,
+      "step": 750
+    },
+    {
+      "epoch": 3.2340425531914896,
+      "grad_norm": 0.45789024233818054,
+      "learning_rate": 0.00017792448814439333,
+      "loss": 0.0115,
+      "step": 760
+    },
+    {
+      "epoch": 3.276595744680851,
+      "grad_norm": 0.3800203204154968,
+      "learning_rate": 0.00017736284830340436,
+      "loss": 0.0209,
+      "step": 770
+    },
+    {
+      "epoch": 3.3191489361702127,
+      "grad_norm": 0.2505127191543579,
+      "learning_rate": 0.00017679506361534215,
+      "loss": 0.0167,
+      "step": 780
+    },
+    {
+      "epoch": 3.3617021276595747,
+      "grad_norm": 0.10206060856580734,
+      "learning_rate": 0.00017622117917872823,
+      "loss": 0.0172,
+      "step": 790
+    },
+    {
+      "epoch": 3.404255319148936,
+      "grad_norm": 0.45168524980545044,
+      "learning_rate": 0.00017564124057658056,
+      "loss": 0.0284,
+      "step": 800
+    },
+    {
+      "epoch": 3.4468085106382977,
+      "grad_norm": 0.44172531366348267,
+      "learning_rate": 0.00017505529387279277,
+      "loss": 0.0289,
+      "step": 810
+    },
+    {
+      "epoch": 3.4893617021276597,
+      "grad_norm": 0.20968879759311676,
+      "learning_rate": 0.00017446338560847568,
+      "loss": 0.0163,
+      "step": 820
+    },
+    {
+      "epoch": 3.5319148936170213,
+      "grad_norm": 0.2968202829360962,
+      "learning_rate": 0.00017386556279826021,
+      "loss": 0.0231,
+      "step": 830
+    },
+    {
+      "epoch": 3.574468085106383,
+      "grad_norm": 0.2778526246547699,
+      "learning_rate": 0.00017326187292656333,
+      "loss": 0.0157,
+      "step": 840
+    },
+    {
+      "epoch": 3.617021276595745,
+      "grad_norm": 0.08669642359018326,
+      "learning_rate": 0.00017265236394381633,
+      "loss": 0.0148,
+      "step": 850
+    },
+    {
+      "epoch": 3.6595744680851063,
+      "grad_norm": 0.06219767406582832,
+      "learning_rate": 0.00017203708426265614,
+      "loss": 0.0161,
+      "step": 860
+    },
+    {
+      "epoch": 3.702127659574468,
+      "grad_norm": 0.07938496023416519,
+      "learning_rate": 0.00017141608275408006,
+      "loss": 0.0145,
+      "step": 870
+    },
+    {
+      "epoch": 3.74468085106383,
+      "grad_norm": 0.4254000186920166,
+      "learning_rate": 0.00017078940874356392,
+      "loss": 0.0133,
+      "step": 880
+    },
+    {
+      "epoch": 3.7872340425531914,
+      "grad_norm": 0.2674030065536499,
+      "learning_rate": 0.00017015711200714414,
+      "loss": 0.0162,
+      "step": 890
+    },
+    {
+      "epoch": 3.829787234042553,
+      "grad_norm": 0.08741254359483719,
+      "learning_rate": 0.00016951924276746425,
+      "loss": 0.0208,
+      "step": 900
+    },
+    {
+      "epoch": 3.872340425531915,
+      "grad_norm": 0.09643790125846863,
+      "learning_rate": 0.00016887585168978562,
+      "loss": 0.0109,
+      "step": 910
+    },
+    {
+      "epoch": 3.9148936170212765,
+      "grad_norm": 0.2952460050582886,
+      "learning_rate": 0.0001682269898779632,
+      "loss": 0.0154,
+      "step": 920
+    },
+    {
+      "epoch": 3.9574468085106385,
+      "grad_norm": 0.2182932198047638,
+      "learning_rate": 0.00016757270887038654,
+      "loss": 0.0156,
+      "step": 930
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.3799554109573364,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.014,
+      "step": 940
+    },
+    {
+      "epoch": 4.042553191489362,
+      "grad_norm": 0.3694469630718231,
+      "learning_rate": 0.00016624809756960444,
+      "loss": 0.0114,
+      "step": 950
+    },
+    {
+      "epoch": 4.085106382978723,
+      "grad_norm": 0.42959412932395935,
+      "learning_rate": 0.00016557787248883696,
+      "loss": 0.0127,
+      "step": 960
+    },
+    {
+      "epoch": 4.127659574468085,
+      "grad_norm": 0.25515562295913696,
+      "learning_rate": 0.00016490243862883413,
+      "loss": 0.0145,
+      "step": 970
+    },
+    {
+      "epoch": 4.170212765957447,
+      "grad_norm": 0.1240379586815834,
+      "learning_rate": 0.00016422184963857432,
+      "loss": 0.012,
+      "step": 980
+    },
+    {
+      "epoch": 4.212765957446808,
+      "grad_norm": 0.3189831078052521,
+      "learning_rate": 0.00016353615957650236,
+      "loss": 0.012,
+      "step": 990
+    },
+    {
+      "epoch": 4.25531914893617,
+      "grad_norm": 0.08477319031953812,
+      "learning_rate": 0.00016284542290623567,
+      "loss": 0.0103,
+      "step": 1000
+    },
+    {
+      "epoch": 4.297872340425532,
+      "grad_norm": 0.0562283881008625,
+      "learning_rate": 0.00016214969449223824,
+      "loss": 0.0159,
+      "step": 1010
+    },
+    {
+      "epoch": 4.340425531914893,
+      "grad_norm": 0.07840266078710556,
+      "learning_rate": 0.00016144902959546286,
+      "loss": 0.011,
+      "step": 1020
+    },
+    {
+      "epoch": 4.382978723404255,
+      "grad_norm": 0.33640316128730774,
+      "learning_rate": 0.00016074348386896177,
+      "loss": 0.0194,
+      "step": 1030
+    },
+    {
+      "epoch": 4.425531914893617,
+      "grad_norm": 0.06994381546974182,
+      "learning_rate": 0.00016003311335346636,
+      "loss": 0.0146,
+      "step": 1040
+    },
+    {
+      "epoch": 4.468085106382979,
+      "grad_norm": 0.4166668951511383,
+      "learning_rate": 0.00015931797447293552,
+      "loss": 0.0117,
+      "step": 1050
+    },
+    {
+      "epoch": 4.51063829787234,
+      "grad_norm": 0.10744202882051468,
+      "learning_rate": 0.00015859812403007443,
+      "loss": 0.0108,
+      "step": 1060
+    },
+    {
+      "epoch": 4.553191489361702,
+      "grad_norm": 0.06330662965774536,
+      "learning_rate": 0.0001578736192018224,
+      "loss": 0.0092,
+      "step": 1070
+    },
+    {
+      "epoch": 4.595744680851064,
+      "grad_norm": 0.6020157933235168,
+      "learning_rate": 0.00015714451753481168,
+      "loss": 0.0165,
+      "step": 1080
+    },
+    {
+      "epoch": 4.638297872340425,
+      "grad_norm": 0.07121607661247253,
+      "learning_rate": 0.0001564108769407962,
+      "loss": 0.0169,
+      "step": 1090
+    },
+    {
+      "epoch": 4.680851063829787,
+      "grad_norm": 0.3467644155025482,
+      "learning_rate": 0.00015567275569205218,
+      "loss": 0.0167,
+      "step": 1100
+    },
+    {
+      "epoch": 4.723404255319149,
+      "grad_norm": 0.2611311972141266,
+      "learning_rate": 0.00015493021241674918,
+      "loss": 0.0146,
+      "step": 1110
+    },
+    {
+      "epoch": 4.76595744680851,
+      "grad_norm": 0.35593244433403015,
+      "learning_rate": 0.0001541833060942937,
+      "loss": 0.0181,
+      "step": 1120
+    },
+    {
+      "epoch": 4.808510638297872,
+      "grad_norm": 0.05776326358318329,
+      "learning_rate": 0.00015343209605064422,
+      "loss": 0.0103,
+      "step": 1130
+    },
+    {
+      "epoch": 4.851063829787234,
+      "grad_norm": 0.07242272049188614,
+      "learning_rate": 0.00015267664195359917,
+      "loss": 0.009,
+      "step": 1140
+    },
+    {
+      "epoch": 4.8936170212765955,
+      "grad_norm": 0.07159385830163956,
+      "learning_rate": 0.00015191700380805752,
+      "loss": 0.0136,
+      "step": 1150
+    },
+    {
+      "epoch": 4.9361702127659575,
+      "grad_norm": 0.061515677720308304,
+      "learning_rate": 0.00015115324195125274,
+      "loss": 0.0118,
+      "step": 1160
+    },
+    {
+      "epoch": 4.9787234042553195,
+      "grad_norm": 0.4526319205760956,
+      "learning_rate": 0.00015038541704796003,
+      "loss": 0.0171,
+      "step": 1170
+    },
+    {
+      "epoch": 5.0212765957446805,
+      "grad_norm": 0.5487878322601318,
+      "learning_rate": 0.0001496135900856782,
+      "loss": 0.0096,
+      "step": 1180
+    },
+    {
+      "epoch": 5.0638297872340425,
+      "grad_norm": 0.424087256193161,
+      "learning_rate": 0.0001488378223697851,
+      "loss": 0.0159,
+      "step": 1190
+    },
+    {
+      "epoch": 5.1063829787234045,
+      "grad_norm": 0.15037283301353455,
+      "learning_rate": 0.00014805817551866838,
+      "loss": 0.0102,
+      "step": 1200
+    },
+    {
+      "epoch": 5.148936170212766,
+      "grad_norm": 0.06197366863489151,
+      "learning_rate": 0.00014727471145883127,
+      "loss": 0.0102,
+      "step": 1210
+    },
+    {
+      "epoch": 5.191489361702128,
+      "grad_norm": 0.08480200916528702,
+      "learning_rate": 0.00014648749241997363,
+      "loss": 0.0133,
+      "step": 1220
+    },
+    {
+      "epoch": 5.23404255319149,
+      "grad_norm": 0.08053206652402878,
+      "learning_rate": 0.00014569658093004935,
+      "loss": 0.0097,
+      "step": 1230
+    },
+    {
+      "epoch": 5.276595744680851,
+      "grad_norm": 0.07565326988697052,
+      "learning_rate": 0.0001449020398102996,
+      "loss": 0.0112,
+      "step": 1240
+    },
+    {
+      "epoch": 5.319148936170213,
+      "grad_norm": 0.08997716754674911,
+      "learning_rate": 0.00014410393217026318,
+      "loss": 0.0136,
+      "step": 1250
+    },
+    {
+      "epoch": 5.361702127659575,
+      "grad_norm": 0.09614914655685425,
+      "learning_rate": 0.00014330232140276366,
+      "loss": 0.0093,
+      "step": 1260
+    },
+    {
+      "epoch": 5.404255319148936,
+      "grad_norm": 0.07535921782255173,
+      "learning_rate": 0.00014249727117887425,
+      "loss": 0.0131,
+      "step": 1270
+    },
+    {
+      "epoch": 5.446808510638298,
+      "grad_norm": 0.1804039031267166,
+      "learning_rate": 0.00014168884544286053,
+      "loss": 0.015,
+      "step": 1280
+    },
+    {
+      "epoch": 5.48936170212766,
+      "grad_norm": 0.20902135968208313,
+      "learning_rate": 0.0001408771084071012,
+      "loss": 0.0117,
+      "step": 1290
+    },
+    {
+      "epoch": 5.531914893617021,
+      "grad_norm": 0.0814347192645073,
+      "learning_rate": 0.00014006212454698797,
+      "loss": 0.0103,
+      "step": 1300
+    },
+    {
+      "epoch": 5.574468085106383,
+      "grad_norm": 0.2159033864736557,
+      "learning_rate": 0.00013924395859580432,
+      "loss": 0.0106,
+      "step": 1310
+    },
+    {
+      "epoch": 5.617021276595745,
+      "grad_norm": 0.8544533848762512,
+      "learning_rate": 0.00013842267553958371,
+      "loss": 0.0104,
+      "step": 1320
+    },
+    {
+      "epoch": 5.659574468085106,
+      "grad_norm": 0.05283027142286301,
+      "learning_rate": 0.00013759834061194794,
+      "loss": 0.0122,
+      "step": 1330
+    },
+    {
+      "epoch": 5.702127659574468,
+      "grad_norm": 0.26087766885757446,
+      "learning_rate": 0.00013677101928892554,
+      "loss": 0.0105,
+      "step": 1340
+    },
+    {
+      "epoch": 5.74468085106383,
+      "grad_norm": 0.16772738099098206,
+      "learning_rate": 0.00013594077728375128,
+      "loss": 0.0145,
+      "step": 1350
+    },
+    {
+      "epoch": 5.787234042553192,
+      "grad_norm": 0.5087531805038452,
+      "learning_rate": 0.00013510768054164653,
+      "loss": 0.0105,
+      "step": 1360
+    },
+    {
+      "epoch": 5.829787234042553,
+      "grad_norm": 0.11721577495336533,
+      "learning_rate": 0.00013427179523458127,
+      "loss": 0.0117,
+      "step": 1370
+    },
+    {
+      "epoch": 5.872340425531915,
+      "grad_norm": 0.051573414355516434,
+      "learning_rate": 0.0001334331877560182,
+      "loss": 0.0103,
+      "step": 1380
+    },
+    {
+      "epoch": 5.914893617021277,
+      "grad_norm": 0.12506790459156036,
+      "learning_rate": 0.00013259192471563912,
+      "loss": 0.0113,
+      "step": 1390
+    },
+    {
+      "epoch": 5.957446808510638,
+      "grad_norm": 0.0568876639008522,
+      "learning_rate": 0.00013174807293405428,
+      "loss": 0.0113,
+      "step": 1400
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.08331684023141861,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0088,
+      "step": 1410
+    },
+    {
+      "epoch": 6.042553191489362,
+      "grad_norm": 0.07224524766206741,
+      "learning_rate": 0.00013005287145248878,
+      "loss": 0.0081,
+      "step": 1420
+    },
+    {
+      "epoch": 6.085106382978723,
+      "grad_norm": 0.06308940798044205,
+      "learning_rate": 0.0001292016564005219,
+      "loss": 0.0087,
+      "step": 1430
+    },
+    {
+      "epoch": 6.127659574468085,
+      "grad_norm": 0.05843973904848099,
+      "learning_rate": 0.0001283481218926818,
+      "loss": 0.0088,
+      "step": 1440
+    },
+    {
+      "epoch": 6.170212765957447,
+      "grad_norm": 0.09169770032167435,
+      "learning_rate": 0.00012749233572428804,
+      "loss": 0.012,
+      "step": 1450
+    },
+    {
+      "epoch": 6.212765957446808,
+      "grad_norm": 0.19424813985824585,
+      "learning_rate": 0.00012663436586950714,
+      "loss": 0.0107,
+      "step": 1460
+    },
+    {
+      "epoch": 6.25531914893617,
+      "grad_norm": 0.14026446640491486,
+      "learning_rate": 0.00012577428047595344,
+      "loss": 0.0109,
+      "step": 1470
+    },
+    {
+      "epoch": 6.297872340425532,
+      "grad_norm": 0.04988068342208862,
+      "learning_rate": 0.0001249121478592762,
+      "loss": 0.0099,
+      "step": 1480
+    },
+    {
+      "epoch": 6.340425531914893,
+      "grad_norm": 0.28419676423072815,
+      "learning_rate": 0.0001240480364977335,
+      "loss": 0.011,
+      "step": 1490
+    },
+    {
+      "epoch": 6.382978723404255,
+      "grad_norm": 0.21158523857593536,
+      "learning_rate": 0.00012318201502675285,
+      "loss": 0.0102,
+      "step": 1500
+    },
+    {
+      "epoch": 6.425531914893617,
+      "grad_norm": 0.08326342701911926,
+      "learning_rate": 0.00012231415223347972,
+      "loss": 0.0099,
+      "step": 1510
+    },
+    {
+      "epoch": 6.468085106382979,
+      "grad_norm": 0.058453477919101715,
+      "learning_rate": 0.0001214445170513139,
+      "loss": 0.0112,
+      "step": 1520
+    },
+    {
+      "epoch": 6.51063829787234,
+      "grad_norm": 0.06616617739200592,
+      "learning_rate": 0.00012057317855443395,
+      "loss": 0.0106,
+      "step": 1530
+    },
+    {
+      "epoch": 6.553191489361702,
+      "grad_norm": 0.05165652185678482,
+      "learning_rate": 0.00011970020595231101,
+      "loss": 0.009,
+      "step": 1540
+    },
+    {
+      "epoch": 6.595744680851064,
+      "grad_norm": 0.2629082500934601,
+      "learning_rate": 0.00011882566858421135,
+      "loss": 0.0088,
+      "step": 1550
+    },
+    {
+      "epoch": 6.638297872340425,
+      "grad_norm": 0.15236687660217285,
+      "learning_rate": 0.00011794963591368893,
+      "loss": 0.0121,
+      "step": 1560
+    },
+    {
+      "epoch": 6.680851063829787,
+      "grad_norm": 0.056746602058410645,
+      "learning_rate": 0.0001170721775230679,
+      "loss": 0.0092,
+      "step": 1570
+    },
+    {
+      "epoch": 6.723404255319149,
+      "grad_norm": 0.14222624897956848,
+      "learning_rate": 0.00011619336310791586,
+      "loss": 0.0107,
+      "step": 1580
+    },
+    {
+      "epoch": 6.76595744680851,
+      "grad_norm": 0.06217767670750618,
+      "learning_rate": 0.00011531326247150803,
+      "loss": 0.0092,
+      "step": 1590
+    },
+    {
+      "epoch": 6.808510638297872,
+      "grad_norm": 0.05023911967873573,
+      "learning_rate": 0.00011443194551928266,
+      "loss": 0.012,
+      "step": 1600
+    },
+    {
+      "epoch": 6.851063829787234,
+      "grad_norm": 0.07197170704603195,
+      "learning_rate": 0.00011354948225328877,
+      "loss": 0.009,
+      "step": 1610
+    },
+    {
+      "epoch": 6.8936170212765955,
+      "grad_norm": 0.07203277945518494,
+      "learning_rate": 0.0001126659427666257,
+      "loss": 0.0089,
+      "step": 1620
+    },
+    {
+      "epoch": 6.9361702127659575,
+      "grad_norm": 0.06472223252058029,
+      "learning_rate": 0.00011178139723787597,
+      "loss": 0.0106,
+      "step": 1630
+    },
+    {
+      "epoch": 6.9787234042553195,
+      "grad_norm": 0.2544592320919037,
+      "learning_rate": 0.00011089591592553082,
+      "loss": 0.0099,
+      "step": 1640
+    },
+    {
+      "epoch": 7.0212765957446805,
+      "grad_norm": 0.06306792795658112,
+      "learning_rate": 0.00011000956916240985,
+      "loss": 0.0094,
+      "step": 1650
+    },
+    {
+      "epoch": 7.0638297872340425,
+      "grad_norm": 0.04974300041794777,
+      "learning_rate": 0.00010912242735007441,
+      "loss": 0.009,
+      "step": 1660
+    },
+    {
+      "epoch": 7.1063829787234045,
+      "grad_norm": 0.06706953048706055,
+      "learning_rate": 0.00010823456095323579,
+      "loss": 0.0081,
+      "step": 1670
+    },
+    {
+      "epoch": 7.148936170212766,
+      "grad_norm": 0.2676733732223511,
+      "learning_rate": 0.00010734604049415822,
+      "loss": 0.0098,
+      "step": 1680
+    },
+    {
+      "epoch": 7.191489361702128,
+      "grad_norm": 0.04386402294039726,
+      "learning_rate": 0.0001064569365470574,
+      "loss": 0.0089,
+      "step": 1690
+    },
+    {
+      "epoch": 7.23404255319149,
+      "grad_norm": 0.0573345422744751,
+      "learning_rate": 0.00010556731973249485,
+      "loss": 0.0074,
+      "step": 1700
+    },
+    {
+      "epoch": 7.276595744680851,
+      "grad_norm": 0.0427543967962265,
+      "learning_rate": 0.00010467726071176853,
+      "loss": 0.0097,
+      "step": 1710
+    },
+    {
+      "epoch": 7.319148936170213,
+      "grad_norm": 0.056347280740737915,
+      "learning_rate": 0.00010378683018130047,
+      "loss": 0.0098,
+      "step": 1720
+    },
+    {
+      "epoch": 7.361702127659575,
+      "grad_norm": 0.06203380227088928,
+      "learning_rate": 0.0001028960988670212,
+      "loss": 0.0088,
+      "step": 1730
+    },
+    {
+      "epoch": 7.404255319148936,
+      "grad_norm": 0.22756724059581757,
+      "learning_rate": 0.00010200513751875227,
+      "loss": 0.0099,
+      "step": 1740
+    },
+    {
+      "epoch": 7.446808510638298,
+      "grad_norm": 0.0742747038602829,
+      "learning_rate": 0.00010111401690458654,
+      "loss": 0.0084,
+      "step": 1750
+    },
+    {
+      "epoch": 7.48936170212766,
+      "grad_norm": 0.07009650021791458,
+      "learning_rate": 0.00010022280780526725,
+      "loss": 0.0105,
+      "step": 1760
+    },
+    {
+      "epoch": 7.531914893617021,
+      "grad_norm": 0.19795449078083038,
+      "learning_rate": 9.93315810085658e-05,
+      "loss": 0.0108,
+      "step": 1770
+    },
+    {
+      "epoch": 7.574468085106383,
+      "grad_norm": 0.060066696256399155,
+      "learning_rate": 9.844040730365936e-05,
+      "loss": 0.009,
+      "step": 1780
+    },
+    {
+      "epoch": 7.617021276595745,
+      "grad_norm": 0.16794614493846893,
+      "learning_rate": 9.754935747550804e-05,
+      "loss": 0.0093,
+      "step": 1790
+    },
+    {
+      "epoch": 7.659574468085106,
+      "grad_norm": 0.04417448118329048,
+      "learning_rate": 9.665850229923258e-05,
+      "loss": 0.0083,
+      "step": 1800
+    },
+    {
+      "epoch": 7.702127659574468,
+      "grad_norm": 0.04747516289353371,
+      "learning_rate": 9.57679125344927e-05,
+      "loss": 0.0108,
+      "step": 1810
+    },
+    {
+      "epoch": 7.74468085106383,
+      "grad_norm": 0.3820296823978424,
+      "learning_rate": 9.487765891986682e-05,
+      "loss": 0.0106,
+      "step": 1820
+    },
+    {
+      "epoch": 7.787234042553192,
+      "grad_norm": 0.14944486320018768,
+      "learning_rate": 9.398781216723331e-05,
+      "loss": 0.0086,
+      "step": 1830
+    },
+    {
+      "epoch": 7.829787234042553,
+      "grad_norm": 0.05065152049064636,
+      "learning_rate": 9.309844295615389e-05,
+      "loss": 0.0079,
+      "step": 1840
+    },
+    {
+      "epoch": 7.872340425531915,
+      "grad_norm": 0.06406435370445251,
+      "learning_rate": 9.220962192825968e-05,
+      "loss": 0.0088,
+      "step": 1850
+    },
+    {
+      "epoch": 7.914893617021277,
+      "grad_norm": 0.06042446941137314,
+      "learning_rate": 9.132141968164026e-05,
+      "loss": 0.0088,
+      "step": 1860
+    },
+    {
+      "epoch": 7.957446808510638,
+      "grad_norm": 0.06469079107046127,
+      "learning_rate": 9.043390676523604e-05,
+      "loss": 0.0088,
+      "step": 1870
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.05605630949139595,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0085,
+      "step": 1880
+    },
+    {
+      "epoch": 8.042553191489361,
+      "grad_norm": 0.1482757031917572,
+      "learning_rate": 8.866123083947182e-05,
+      "loss": 0.0077,
+      "step": 1890
+    },
+    {
+      "epoch": 8.085106382978724,
+      "grad_norm": 0.12453223764896393,
+      "learning_rate": 8.777620863183657e-05,
+      "loss": 0.0086,
+      "step": 1900
+    },
+    {
+      "epoch": 8.127659574468085,
+      "grad_norm": 0.08895737677812576,
+      "learning_rate": 8.689215734668232e-05,
+      "loss": 0.0094,
+      "step": 1910
+    },
+    {
+      "epoch": 8.170212765957446,
+      "grad_norm": 0.057379741221666336,
+      "learning_rate": 8.600914720324316e-05,
+      "loss": 0.0098,
+      "step": 1920
+    },
+    {
+      "epoch": 8.212765957446809,
+      "grad_norm": 0.047437652945518494,
+      "learning_rate": 8.512724833805634e-05,
+      "loss": 0.0084,
+      "step": 1930
+    },
+    {
+      "epoch": 8.25531914893617,
+      "grad_norm": 0.057963624596595764,
+      "learning_rate": 8.424653079939156e-05,
+      "loss": 0.0101,
+      "step": 1940
+    },
+    {
+      "epoch": 8.297872340425531,
+      "grad_norm": 0.06452014297246933,
+      "learning_rate": 8.336706454168701e-05,
+      "loss": 0.0079,
+      "step": 1950
+    },
+    {
+      "epoch": 8.340425531914894,
+      "grad_norm": 0.0970030426979065,
+      "learning_rate": 8.248891941999297e-05,
+      "loss": 0.0075,
+      "step": 1960
+    },
+    {
+      "epoch": 8.382978723404255,
+      "grad_norm": 0.05405813828110695,
+      "learning_rate": 8.161216518442334e-05,
+      "loss": 0.0084,
+      "step": 1970
+    },
+    {
+      "epoch": 8.425531914893616,
+      "grad_norm": 0.12814395129680634,
+      "learning_rate": 8.073687147461547e-05,
+      "loss": 0.0085,
+      "step": 1980
+    },
+    {
+      "epoch": 8.46808510638298,
+      "grad_norm": 0.06040940061211586,
+      "learning_rate": 7.98631078141987e-05,
+      "loss": 0.009,
+      "step": 1990
+    },
+    {
+      "epoch": 8.51063829787234,
+      "grad_norm": 0.0705878734588623,
+      "learning_rate": 7.89909436052722e-05,
+      "loss": 0.0096,
+      "step": 2000
+    },
+    {
+      "epoch": 8.553191489361701,
+      "grad_norm": 0.07256048917770386,
+      "learning_rate": 7.812044812289249e-05,
+      "loss": 0.0081,
+      "step": 2010
+    },
+    {
+      "epoch": 8.595744680851064,
+      "grad_norm": 0.04781148582696915,
+      "learning_rate": 7.72516905095709e-05,
+      "loss": 0.0084,
+      "step": 2020
+    },
+    {
+      "epoch": 8.638297872340425,
+      "grad_norm": 0.049337003380060196,
+      "learning_rate": 7.638473976978177e-05,
+      "loss": 0.0075,
+      "step": 2030
+    },
+    {
+      "epoch": 8.680851063829786,
+      "grad_norm": 0.06392087787389755,
+      "learning_rate": 7.55196647644814e-05,
+      "loss": 0.009,
+      "step": 2040
+    },
+    {
+      "epoch": 8.72340425531915,
+      "grad_norm": 0.06608345359563828,
+      "learning_rate": 7.465653420563845e-05,
+      "loss": 0.0082,
+      "step": 2050
+    },
+    {
+      "epoch": 8.76595744680851,
+      "grad_norm": 0.05706971138715744,
+      "learning_rate": 7.379541665077643e-05,
+      "loss": 0.0095,
+      "step": 2060
+    },
+    {
+      "epoch": 8.808510638297872,
+      "grad_norm": 0.056169264018535614,
+      "learning_rate": 7.293638049752812e-05,
+      "loss": 0.0085,
+      "step": 2070
+    },
+    {
+      "epoch": 8.851063829787234,
+      "grad_norm": 0.4233561158180237,
+      "learning_rate": 7.207949397820278e-05,
+      "loss": 0.0083,
+      "step": 2080
+    },
+    {
+      "epoch": 8.893617021276595,
+      "grad_norm": 0.04603901505470276,
+      "learning_rate": 7.122482515436661e-05,
+      "loss": 0.0089,
+      "step": 2090
+    },
+    {
+      "epoch": 8.936170212765958,
+      "grad_norm": 0.05150962248444557,
+      "learning_rate": 7.037244191143661e-05,
+      "loss": 0.0083,
+      "step": 2100
+    },
+    {
+      "epoch": 8.97872340425532,
+      "grad_norm": 0.06366905570030212,
+      "learning_rate": 6.952241195328868e-05,
+      "loss": 0.008,
+      "step": 2110
+    },
+    {
+      "epoch": 9.02127659574468,
+      "grad_norm": 0.05785864219069481,
+      "learning_rate": 6.867480279687974e-05,
+      "loss": 0.0079,
+      "step": 2120
+    },
+    {
+      "epoch": 9.063829787234043,
+      "grad_norm": 0.05374649167060852,
+      "learning_rate": 6.782968176688514e-05,
+      "loss": 0.0079,
+      "step": 2130
+    },
+    {
+      "epoch": 9.106382978723405,
+      "grad_norm": 0.055857494473457336,
+      "learning_rate": 6.6987115990351e-05,
+      "loss": 0.0082,
+      "step": 2140
+    },
+    {
+      "epoch": 9.148936170212766,
+      "grad_norm": 0.05628526955842972,
+      "learning_rate": 6.614717239136246e-05,
+      "loss": 0.0085,
+      "step": 2150
+    },
+    {
+      "epoch": 9.191489361702128,
+      "grad_norm": 0.24210433661937714,
+      "learning_rate": 6.530991768572794e-05,
+      "loss": 0.0077,
+      "step": 2160
+    },
+    {
+      "epoch": 9.23404255319149,
+      "grad_norm": 0.05308128893375397,
+      "learning_rate": 6.447541837568e-05,
+      "loss": 0.0084,
+      "step": 2170
+    },
+    {
+      "epoch": 9.27659574468085,
+      "grad_norm": 0.056445565074682236,
+      "learning_rate": 6.364374074459307e-05,
+      "loss": 0.008,
+      "step": 2180
+    },
+    {
+      "epoch": 9.319148936170214,
+      "grad_norm": 0.0540035143494606,
+      "learning_rate": 6.281495085171869e-05,
+      "loss": 0.0075,
+      "step": 2190
+    },
+    {
+      "epoch": 9.361702127659575,
+      "grad_norm": 0.16720785200595856,
+      "learning_rate": 6.198911452693853e-05,
+      "loss": 0.0102,
+      "step": 2200
+    },
+    {
+      "epoch": 9.404255319148936,
+      "grad_norm": 0.09645309299230576,
+      "learning_rate": 6.116629736553552e-05,
+      "loss": 0.0075,
+      "step": 2210
+    },
+    {
+      "epoch": 9.446808510638299,
+      "grad_norm": 0.05031803250312805,
+      "learning_rate": 6.0346564722983736e-05,
+      "loss": 0.0086,
+      "step": 2220
+    },
+    {
+      "epoch": 9.48936170212766,
+      "grad_norm": 0.07071155309677124,
+      "learning_rate": 5.952998170975724e-05,
+      "loss": 0.0076,
+      "step": 2230
+    },
+    {
+      "epoch": 9.53191489361702,
+      "grad_norm": 0.06481063365936279,
+      "learning_rate": 5.871661318615848e-05,
+      "loss": 0.0076,
+      "step": 2240
+    },
+    {
+      "epoch": 9.574468085106384,
+      "grad_norm": 0.06360594928264618,
+      "learning_rate": 5.790652375716652e-05,
+      "loss": 0.0085,
+      "step": 2250
+    },
+    {
+      "epoch": 9.617021276595745,
+      "grad_norm": 0.06016814708709717,
+      "learning_rate": 5.709977776730537e-05,
+      "loss": 0.0078,
+      "step": 2260
+    },
+    {
+      "epoch": 9.659574468085106,
+      "grad_norm": 0.0806780532002449,
+      "learning_rate": 5.62964392955335e-05,
+      "loss": 0.0086,
+      "step": 2270
+    },
+    {
+      "epoch": 9.702127659574469,
+      "grad_norm": 0.10996109992265701,
+      "learning_rate": 5.549657215015367e-05,
+      "loss": 0.0079,
+      "step": 2280
+    },
+    {
+      "epoch": 9.74468085106383,
+      "grad_norm": 0.07162634283304214,
+      "learning_rate": 5.470023986374516e-05,
+      "loss": 0.008,
+      "step": 2290
+    },
+    {
+      "epoch": 9.787234042553191,
+      "grad_norm": 0.05707460269331932,
+      "learning_rate": 5.39075056881172e-05,
+      "loss": 0.0073,
+      "step": 2300
+    },
+    {
+      "epoch": 9.829787234042554,
+      "grad_norm": 0.05895783007144928,
+      "learning_rate": 5.31184325892849e-05,
+      "loss": 0.0092,
+      "step": 2310
+    },
+    {
+      "epoch": 9.872340425531915,
+      "grad_norm": 0.058236416429281235,
+      "learning_rate": 5.233308324246805e-05,
+      "loss": 0.0072,
+      "step": 2320
+    },
+    {
+      "epoch": 9.914893617021276,
+      "grad_norm": 0.12872685492038727,
+      "learning_rate": 5.155152002711285e-05,
+      "loss": 0.008,
+      "step": 2330
+    },
+    {
+      "epoch": 9.957446808510639,
+      "grad_norm": 0.08264678716659546,
+      "learning_rate": 5.077380502193725e-05,
+      "loss": 0.0083,
+      "step": 2340
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.05181215703487396,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0088,
+      "step": 2350
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3525,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.43024810450944e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:782c30e0be63e1544c7d8b053fa9eba5fc9c850a504ec4b0c365364b1364bfc2
+size 5432