Upload 13 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/Phi-3.5-mini-instruct
+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 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_up_proj",
+    "o_proj",
+    "qkv_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:b569457c15f7808f323c48782603681f0a424013ae81034b8e6003a0822f57f6
+size 100697728

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fc245ec22feb8bc4e552d065abddff64f9b0f4d53f8a74046c4f91f96f5c16
+size 201534586

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b581b61d2a60bec07eab4b867f61fcdb86aeaca2bd1d2f5969b0cb7b0b2cfe8
+size 13926

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923acd5bcefa1959fa0ce9181b70f3c930874028ae3bab1e24f3c4fac57e9c68
+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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "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 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 512,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1783 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 76.92307692307692,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 5.159167766571045,
+      "learning_rate": 7.8125e-08,
+      "loss": 4.2745,
+      "step": 10
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 5.482397079467773,
+      "learning_rate": 1.5625e-07,
+      "loss": 4.2677,
+      "step": 20
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 5.341490268707275,
+      "learning_rate": 2.3437500000000003e-07,
+      "loss": 4.2277,
+      "step": 30
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 5.534327983856201,
+      "learning_rate": 3.125e-07,
+      "loss": 4.2715,
+      "step": 40
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 5.407191753387451,
+      "learning_rate": 3.90625e-07,
+      "loss": 4.2371,
+      "step": 50
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 5.150612831115723,
+      "learning_rate": 4.6875000000000006e-07,
+      "loss": 4.1953,
+      "step": 60
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 5.620100021362305,
+      "learning_rate": 5.468750000000001e-07,
+      "loss": 4.2908,
+      "step": 70
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 5.80696964263916,
+      "learning_rate": 6.25e-07,
+      "loss": 4.2603,
+      "step": 80
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 5.940330982208252,
+      "learning_rate": 7.03125e-07,
+      "loss": 4.2049,
+      "step": 90
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 5.8099141120910645,
+      "learning_rate": 7.8125e-07,
+      "loss": 4.1638,
+      "step": 100
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 5.388895511627197,
+      "learning_rate": 8.59375e-07,
+      "loss": 4.1409,
+      "step": 110
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 5.919471263885498,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 4.1658,
+      "step": 120
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 13097.25390625,
+      "learning_rate": 1.0156250000000001e-06,
+      "loss": 4.1936,
+      "step": 130
+    },
+    {
+      "epoch": 4.3076923076923075,
+      "grad_norm": 4.802829265594482,
+      "learning_rate": 1.0937500000000001e-06,
+      "loss": 4.021,
+      "step": 140
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 5.628367900848389,
+      "learning_rate": 1.1718750000000001e-06,
+      "loss": 4.019,
+      "step": 150
+    },
+    {
+      "epoch": 4.923076923076923,
+      "grad_norm": 5.601304531097412,
+      "learning_rate": 1.25e-06,
+      "loss": 3.9075,
+      "step": 160
+    },
+    {
+      "epoch": 5.230769230769231,
+      "grad_norm": 5.029603004455566,
+      "learning_rate": 1.328125e-06,
+      "loss": 3.8952,
+      "step": 170
+    },
+    {
+      "epoch": 5.538461538461538,
+      "grad_norm": 5.625918388366699,
+      "learning_rate": 1.40625e-06,
+      "loss": 3.7809,
+      "step": 180
+    },
+    {
+      "epoch": 5.846153846153846,
+      "grad_norm": 4.302311420440674,
+      "learning_rate": 1.484375e-06,
+      "loss": 3.5823,
+      "step": 190
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 4.250982284545898,
+      "learning_rate": 1.5625e-06,
+      "loss": 3.5112,
+      "step": 200
+    },
+    {
+      "epoch": 6.461538461538462,
+      "grad_norm": 3.137059211730957,
+      "learning_rate": 1.640625e-06,
+      "loss": 3.3867,
+      "step": 210
+    },
+    {
+      "epoch": 6.769230769230769,
+      "grad_norm": 3.2033724784851074,
+      "learning_rate": 1.71875e-06,
+      "loss": 3.2788,
+      "step": 220
+    },
+    {
+      "epoch": 7.076923076923077,
+      "grad_norm": 2.8167309761047363,
+      "learning_rate": 1.796875e-06,
+      "loss": 3.1566,
+      "step": 230
+    },
+    {
+      "epoch": 7.384615384615385,
+      "grad_norm": 2.167381525039673,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 2.9642,
+      "step": 240
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 2.2277944087982178,
+      "learning_rate": 1.953125e-06,
+      "loss": 2.8886,
+      "step": 250
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 60692.35546875,
+      "learning_rate": 2.0312500000000002e-06,
+      "loss": 2.7726,
+      "step": 260
+    },
+    {
+      "epoch": 8.307692307692308,
+      "grad_norm": 1.6853564977645874,
+      "learning_rate": 2.109375e-06,
+      "loss": 2.7062,
+      "step": 270
+    },
+    {
+      "epoch": 8.615384615384615,
+      "grad_norm": 1.5454535484313965,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 2.5508,
+      "step": 280
+    },
+    {
+      "epoch": 8.923076923076923,
+      "grad_norm": 1.2037118673324585,
+      "learning_rate": 2.265625e-06,
+      "loss": 2.4639,
+      "step": 290
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 1.0261240005493164,
+      "learning_rate": 2.3437500000000002e-06,
+      "loss": 2.4103,
+      "step": 300
+    },
+    {
+      "epoch": 9.538461538461538,
+      "grad_norm": 0.9358808994293213,
+      "learning_rate": 2.421875e-06,
+      "loss": 2.3032,
+      "step": 310
+    },
+    {
+      "epoch": 9.846153846153847,
+      "grad_norm": 0.7383924722671509,
+      "learning_rate": 2.5e-06,
+      "loss": 2.3002,
+      "step": 320
+    },
+    {
+      "epoch": 10.153846153846153,
+      "grad_norm": 0.685702383518219,
+      "learning_rate": 2.5781250000000004e-06,
+      "loss": 2.2148,
+      "step": 330
+    },
+    {
+      "epoch": 10.461538461538462,
+      "grad_norm": 0.6645168662071228,
+      "learning_rate": 2.65625e-06,
+      "loss": 2.1989,
+      "step": 340
+    },
+    {
+      "epoch": 10.76923076923077,
+      "grad_norm": 0.7011102437973022,
+      "learning_rate": 2.7343750000000004e-06,
+      "loss": 2.1496,
+      "step": 350
+    },
+    {
+      "epoch": 11.076923076923077,
+      "grad_norm": 0.5761039853096008,
+      "learning_rate": 2.8125e-06,
+      "loss": 2.1465,
+      "step": 360
+    },
+    {
+      "epoch": 11.384615384615385,
+      "grad_norm": 0.562958836555481,
+      "learning_rate": 2.8906250000000004e-06,
+      "loss": 2.0871,
+      "step": 370
+    },
+    {
+      "epoch": 11.692307692307692,
+      "grad_norm": 0.5713663101196289,
+      "learning_rate": 2.96875e-06,
+      "loss": 2.0732,
+      "step": 380
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 16827.7421875,
+      "learning_rate": 3.0468750000000004e-06,
+      "loss": 2.0684,
+      "step": 390
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 0.5909234285354614,
+      "learning_rate": 3.125e-06,
+      "loss": 2.0554,
+      "step": 400
+    },
+    {
+      "epoch": 12.615384615384615,
+      "grad_norm": 0.5658320784568787,
+      "learning_rate": 3.2031250000000004e-06,
+      "loss": 1.9929,
+      "step": 410
+    },
+    {
+      "epoch": 12.923076923076923,
+      "grad_norm": 0.5382928848266602,
+      "learning_rate": 3.28125e-06,
+      "loss": 1.9913,
+      "step": 420
+    },
+    {
+      "epoch": 13.23076923076923,
+      "grad_norm": 0.7106872200965881,
+      "learning_rate": 3.3593750000000003e-06,
+      "loss": 1.9562,
+      "step": 430
+    },
+    {
+      "epoch": 13.538461538461538,
+      "grad_norm": 0.5338084697723389,
+      "learning_rate": 3.4375e-06,
+      "loss": 1.9503,
+      "step": 440
+    },
+    {
+      "epoch": 13.846153846153847,
+      "grad_norm": 0.524355411529541,
+      "learning_rate": 3.5156250000000003e-06,
+      "loss": 1.9499,
+      "step": 450
+    },
+    {
+      "epoch": 14.153846153846153,
+      "grad_norm": 0.5286893248558044,
+      "learning_rate": 3.59375e-06,
+      "loss": 1.9225,
+      "step": 460
+    },
+    {
+      "epoch": 14.461538461538462,
+      "grad_norm": 0.5003280639648438,
+      "learning_rate": 3.6718750000000003e-06,
+      "loss": 1.8688,
+      "step": 470
+    },
+    {
+      "epoch": 14.76923076923077,
+      "grad_norm": 0.5744629502296448,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.8728,
+      "step": 480
+    },
+    {
+      "epoch": 15.076923076923077,
+      "grad_norm": 0.47028881311416626,
+      "learning_rate": 3.828125000000001e-06,
+      "loss": 1.818,
+      "step": 490
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 0.5076237320899963,
+      "learning_rate": 3.90625e-06,
+      "loss": 1.8375,
+      "step": 500
+    },
+    {
+      "epoch": 15.692307692307692,
+      "grad_norm": 0.5628578066825867,
+      "learning_rate": 3.984375e-06,
+      "loss": 1.823,
+      "step": 510
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 35255.69921875,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 1.8249,
+      "step": 520
+    },
+    {
+      "epoch": 16.307692307692307,
+      "grad_norm": 0.5536410212516785,
+      "learning_rate": 4.140625000000001e-06,
+      "loss": 1.7998,
+      "step": 530
+    },
+    {
+      "epoch": 16.615384615384617,
+      "grad_norm": 0.6619865298271179,
+      "learning_rate": 4.21875e-06,
+      "loss": 1.775,
+      "step": 540
+    },
+    {
+      "epoch": 16.923076923076923,
+      "grad_norm": 0.6591458320617676,
+      "learning_rate": 4.296875e-06,
+      "loss": 1.7605,
+      "step": 550
+    },
+    {
+      "epoch": 17.23076923076923,
+      "grad_norm": 0.8084316253662109,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.7278,
+      "step": 560
+    },
+    {
+      "epoch": 17.53846153846154,
+      "grad_norm": 0.6782126426696777,
+      "learning_rate": 4.453125000000001e-06,
+      "loss": 1.7261,
+      "step": 570
+    },
+    {
+      "epoch": 17.846153846153847,
+      "grad_norm": 0.6113712191581726,
+      "learning_rate": 4.53125e-06,
+      "loss": 1.7178,
+      "step": 580
+    },
+    {
+      "epoch": 18.153846153846153,
+      "grad_norm": 0.6165570020675659,
+      "learning_rate": 4.609375e-06,
+      "loss": 1.6865,
+      "step": 590
+    },
+    {
+      "epoch": 18.46153846153846,
+      "grad_norm": 0.7881684303283691,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 1.6793,
+      "step": 600
+    },
+    {
+      "epoch": 18.76923076923077,
+      "grad_norm": 0.672874927520752,
+      "learning_rate": 4.765625000000001e-06,
+      "loss": 1.6661,
+      "step": 610
+    },
+    {
+      "epoch": 19.076923076923077,
+      "grad_norm": 0.730848491191864,
+      "learning_rate": 4.84375e-06,
+      "loss": 1.6431,
+      "step": 620
+    },
+    {
+      "epoch": 19.384615384615383,
+      "grad_norm": 0.6730669736862183,
+      "learning_rate": 4.921875e-06,
+      "loss": 1.6155,
+      "step": 630
+    },
+    {
+      "epoch": 19.692307692307693,
+      "grad_norm": 0.6560551524162292,
+      "learning_rate": 5e-06,
+      "loss": 1.6395,
+      "step": 640
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 4129.79052734375,
+      "learning_rate": 4.999811754597862e-06,
+      "loss": 1.5897,
+      "step": 650
+    },
+    {
+      "epoch": 20.307692307692307,
+      "grad_norm": 0.6594120860099792,
+      "learning_rate": 4.999247046740511e-06,
+      "loss": 1.5829,
+      "step": 660
+    },
+    {
+      "epoch": 20.615384615384617,
+      "grad_norm": 0.893703818321228,
+      "learning_rate": 4.998305961470874e-06,
+      "loss": 1.558,
+      "step": 670
+    },
+    {
+      "epoch": 20.923076923076923,
+      "grad_norm": 0.7144062519073486,
+      "learning_rate": 4.996988640512931e-06,
+      "loss": 1.5373,
+      "step": 680
+    },
+    {
+      "epoch": 21.23076923076923,
+      "grad_norm": 0.8453310132026672,
+      "learning_rate": 4.995295282250373e-06,
+      "loss": 1.4909,
+      "step": 690
+    },
+    {
+      "epoch": 21.53846153846154,
+      "grad_norm": 0.8293094635009766,
+      "learning_rate": 4.993226141696726e-06,
+      "loss": 1.4967,
+      "step": 700
+    },
+    {
+      "epoch": 21.846153846153847,
+      "grad_norm": 0.7181118726730347,
+      "learning_rate": 4.990781530456945e-06,
+      "loss": 1.4857,
+      "step": 710
+    },
+    {
+      "epoch": 22.153846153846153,
+      "grad_norm": 0.844008207321167,
+      "learning_rate": 4.987961816680493e-06,
+      "loss": 1.495,
+      "step": 720
+    },
+    {
+      "epoch": 22.46153846153846,
+      "grad_norm": 0.8761960864067078,
+      "learning_rate": 4.984767425005891e-06,
+      "loss": 1.4224,
+      "step": 730
+    },
+    {
+      "epoch": 22.76923076923077,
+      "grad_norm": 0.8939017057418823,
+      "learning_rate": 4.981198836496776e-06,
+      "loss": 1.4063,
+      "step": 740
+    },
+    {
+      "epoch": 23.076923076923077,
+      "grad_norm": 0.828834593296051,
+      "learning_rate": 4.97725658856945e-06,
+      "loss": 1.429,
+      "step": 750
+    },
+    {
+      "epoch": 23.384615384615383,
+      "grad_norm": 0.945023775100708,
+      "learning_rate": 4.972941274911953e-06,
+      "loss": 1.3588,
+      "step": 760
+    },
+    {
+      "epoch": 23.692307692307693,
+      "grad_norm": 1.122968316078186,
+      "learning_rate": 4.968253545394647e-06,
+      "loss": 1.3309,
+      "step": 770
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 93171.5546875,
+      "learning_rate": 4.9631941059723535e-06,
+      "loss": 1.335,
+      "step": 780
+    },
+    {
+      "epoch": 24.307692307692307,
+      "grad_norm": 1.0523442029953003,
+      "learning_rate": 4.957763718578042e-06,
+      "loss": 1.3347,
+      "step": 790
+    },
+    {
+      "epoch": 24.615384615384617,
+      "grad_norm": 1.179585576057434,
+      "learning_rate": 4.9519632010080765e-06,
+      "loss": 1.2618,
+      "step": 800
+    },
+    {
+      "epoch": 24.923076923076923,
+      "grad_norm": 0.854586124420166,
+      "learning_rate": 4.9457934267990695e-06,
+      "loss": 1.2321,
+      "step": 810
+    },
+    {
+      "epoch": 25.23076923076923,
+      "grad_norm": 1.0027631521224976,
+      "learning_rate": 4.939255325096322e-06,
+      "loss": 1.2041,
+      "step": 820
+    },
+    {
+      "epoch": 25.53846153846154,
+      "grad_norm": 1.045911192893982,
+      "learning_rate": 4.932349880513901e-06,
+      "loss": 1.1746,
+      "step": 830
+    },
+    {
+      "epoch": 25.846153846153847,
+      "grad_norm": 0.9622510075569153,
+      "learning_rate": 4.925078132986361e-06,
+      "loss": 1.1846,
+      "step": 840
+    },
+    {
+      "epoch": 26.153846153846153,
+      "grad_norm": 1.2767952680587769,
+      "learning_rate": 4.917441177612131e-06,
+      "loss": 1.1605,
+      "step": 850
+    },
+    {
+      "epoch": 26.46153846153846,
+      "grad_norm": 0.9456568360328674,
+      "learning_rate": 4.9094401644886e-06,
+      "loss": 1.1373,
+      "step": 860
+    },
+    {
+      "epoch": 26.76923076923077,
+      "grad_norm": 1.3368542194366455,
+      "learning_rate": 4.901076298538915e-06,
+      "loss": 1.0879,
+      "step": 870
+    },
+    {
+      "epoch": 27.076923076923077,
+      "grad_norm": 1.4178813695907593,
+      "learning_rate": 4.8923508393305224e-06,
+      "loss": 1.0359,
+      "step": 880
+    },
+    {
+      "epoch": 27.384615384615383,
+      "grad_norm": 1.4570515155792236,
+      "learning_rate": 4.883265100885484e-06,
+      "loss": 1.0313,
+      "step": 890
+    },
+    {
+      "epoch": 27.692307692307693,
+      "grad_norm": 1.415483832359314,
+      "learning_rate": 4.873820451482592e-06,
+      "loss": 1.034,
+      "step": 900
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 1146730.75,
+      "learning_rate": 4.864018313451304e-06,
+      "loss": 0.8984,
+      "step": 910
+    },
+    {
+      "epoch": 28.307692307692307,
+      "grad_norm": 1.3334933519363403,
+      "learning_rate": 4.8538601629575525e-06,
+      "loss": 0.9298,
+      "step": 920
+    },
+    {
+      "epoch": 28.615384615384617,
+      "grad_norm": 1.1457735300064087,
+      "learning_rate": 4.843347529781438e-06,
+      "loss": 0.94,
+      "step": 930
+    },
+    {
+      "epoch": 28.923076923076923,
+      "grad_norm": 1.3328795433044434,
+      "learning_rate": 4.832481997086848e-06,
+      "loss": 0.8961,
+      "step": 940
+    },
+    {
+      "epoch": 29.23076923076923,
+      "grad_norm": 1.455394983291626,
+      "learning_rate": 4.82126520118304e-06,
+      "loss": 0.9099,
+      "step": 950
+    },
+    {
+      "epoch": 29.53846153846154,
+      "grad_norm": 1.7109308242797852,
+      "learning_rate": 4.809698831278217e-06,
+      "loss": 0.8214,
+      "step": 960
+    },
+    {
+      "epoch": 29.846153846153847,
+      "grad_norm": 1.392449140548706,
+      "learning_rate": 4.797784629225145e-06,
+      "loss": 0.813,
+      "step": 970
+    },
+    {
+      "epoch": 30.153846153846153,
+      "grad_norm": 1.8153551816940308,
+      "learning_rate": 4.7855243892588275e-06,
+      "loss": 0.7938,
+      "step": 980
+    },
+    {
+      "epoch": 30.46153846153846,
+      "grad_norm": 1.7134582996368408,
+      "learning_rate": 4.772919957726306e-06,
+      "loss": 0.8109,
+      "step": 990
+    },
+    {
+      "epoch": 30.76923076923077,
+      "grad_norm": 1.7986242771148682,
+      "learning_rate": 4.759973232808609e-06,
+      "loss": 0.6657,
+      "step": 1000
+    },
+    {
+      "epoch": 31.076923076923077,
+      "grad_norm": 1.5258599519729614,
+      "learning_rate": 4.746686164234885e-06,
+      "loss": 0.7157,
+      "step": 1010
+    },
+    {
+      "epoch": 31.384615384615383,
+      "grad_norm": 1.645753264427185,
+      "learning_rate": 4.7330607529887885e-06,
+      "loss": 0.6876,
+      "step": 1020
+    },
+    {
+      "epoch": 31.692307692307693,
+      "grad_norm": 1.4284254312515259,
+      "learning_rate": 4.719099051007136e-06,
+      "loss": 0.6913,
+      "step": 1030
+    },
+    {
+      "epoch": 32.0,
+      "grad_norm": 322668.5625,
+      "learning_rate": 4.704803160870888e-06,
+      "loss": 0.6297,
+      "step": 1040
+    },
+    {
+      "epoch": 32.30769230769231,
+      "grad_norm": 1.519518256187439,
+      "learning_rate": 4.6901752354885166e-06,
+      "loss": 0.617,
+      "step": 1050
+    },
+    {
+      "epoch": 32.61538461538461,
+      "grad_norm": 1.3290555477142334,
+      "learning_rate": 4.675217477771779e-06,
+      "loss": 0.6476,
+      "step": 1060
+    },
+    {
+      "epoch": 32.92307692307692,
+      "grad_norm": 1.5469777584075928,
+      "learning_rate": 4.659932140303967e-06,
+      "loss": 0.5633,
+      "step": 1070
+    },
+    {
+      "epoch": 33.23076923076923,
+      "grad_norm": 1.5148197412490845,
+      "learning_rate": 4.644321525000681e-06,
+      "loss": 0.5595,
+      "step": 1080
+    },
+    {
+      "epoch": 33.53846153846154,
+      "grad_norm": 1.7467495203018188,
+      "learning_rate": 4.628387982763163e-06,
+      "loss": 0.5691,
+      "step": 1090
+    },
+    {
+      "epoch": 33.84615384615385,
+      "grad_norm": 1.9587457180023193,
+      "learning_rate": 4.612133913124268e-06,
+      "loss": 0.4897,
+      "step": 1100
+    },
+    {
+      "epoch": 34.15384615384615,
+      "grad_norm": 1.3276329040527344,
+      "learning_rate": 4.595561763887095e-06,
+      "loss": 0.5177,
+      "step": 1110
+    },
+    {
+      "epoch": 34.46153846153846,
+      "grad_norm": 1.5996724367141724,
+      "learning_rate": 4.578674030756364e-06,
+      "loss": 0.4505,
+      "step": 1120
+    },
+    {
+      "epoch": 34.76923076923077,
+      "grad_norm": 1.8829643726348877,
+      "learning_rate": 4.561473256962564e-06,
+      "loss": 0.5024,
+      "step": 1130
+    },
+    {
+      "epoch": 35.07692307692308,
+      "grad_norm": 2.2122015953063965,
+      "learning_rate": 4.54396203287896e-06,
+      "loss": 0.466,
+      "step": 1140
+    },
+    {
+      "epoch": 35.38461538461539,
+      "grad_norm": 1.784812092781067,
+      "learning_rate": 4.526142995631488e-06,
+      "loss": 0.4057,
+      "step": 1150
+    },
+    {
+      "epoch": 35.69230769230769,
+      "grad_norm": 1.3397154808044434,
+      "learning_rate": 4.508018828701613e-06,
+      "loss": 0.4513,
+      "step": 1160
+    },
+    {
+      "epoch": 36.0,
+      "grad_norm": 368474.65625,
+      "learning_rate": 4.489592261522209e-06,
+      "loss": 0.3743,
+      "step": 1170
+    },
+    {
+      "epoch": 36.30769230769231,
+      "grad_norm": 1.8128660917282104,
+      "learning_rate": 4.470866069066516e-06,
+      "loss": 0.3919,
+      "step": 1180
+    },
+    {
+      "epoch": 36.61538461538461,
+      "grad_norm": 1.7692885398864746,
+      "learning_rate": 4.451843071430236e-06,
+      "loss": 0.3589,
+      "step": 1190
+    },
+    {
+      "epoch": 36.92307692307692,
+      "grad_norm": 1.45668363571167,
+      "learning_rate": 4.432526133406843e-06,
+      "loss": 0.3578,
+      "step": 1200
+    },
+    {
+      "epoch": 37.23076923076923,
+      "grad_norm": 1.255777359008789,
+      "learning_rate": 4.412918164056148e-06,
+      "loss": 0.3436,
+      "step": 1210
+    },
+    {
+      "epoch": 37.53846153846154,
+      "grad_norm": 1.4039700031280518,
+      "learning_rate": 4.393022116266212e-06,
+      "loss": 0.3054,
+      "step": 1220
+    },
+    {
+      "epoch": 37.84615384615385,
+      "grad_norm": 2.489480495452881,
+      "learning_rate": 4.372840986308649e-06,
+      "loss": 0.3145,
+      "step": 1230
+    },
+    {
+      "epoch": 38.15384615384615,
+      "grad_norm": 2.235471725463867,
+      "learning_rate": 4.352377813387398e-06,
+      "loss": 0.3915,
+      "step": 1240
+    },
+    {
+      "epoch": 38.46153846153846,
+      "grad_norm": 1.5027036666870117,
+      "learning_rate": 4.331635679181032e-06,
+      "loss": 0.2823,
+      "step": 1250
+    },
+    {
+      "epoch": 38.76923076923077,
+      "grad_norm": 1.8041187524795532,
+      "learning_rate": 4.3106177073786684e-06,
+      "loss": 0.2837,
+      "step": 1260
+    },
+    {
+      "epoch": 39.07692307692308,
+      "grad_norm": 1.359180212020874,
+      "learning_rate": 4.289327063209548e-06,
+      "loss": 0.277,
+      "step": 1270
+    },
+    {
+      "epoch": 39.38461538461539,
+      "grad_norm": 1.5031533241271973,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.2959,
+      "step": 1280
+    },
+    {
+      "epoch": 39.69230769230769,
+      "grad_norm": 1.5086129903793335,
+      "learning_rate": 4.245940623522433e-06,
+      "loss": 0.236,
+      "step": 1290
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 8115298.5,
+      "learning_rate": 4.223851361842668e-06,
+      "loss": 0.2243,
+      "step": 1300
+    },
+    {
+      "epoch": 40.30769230769231,
+      "grad_norm": 1.59078049659729,
+      "learning_rate": 4.201502494488633e-06,
+      "loss": 0.2423,
+      "step": 1310
+    },
+    {
+      "epoch": 40.61538461538461,
+      "grad_norm": 1.6530065536499023,
+      "learning_rate": 4.178897387117547e-06,
+      "loss": 0.2217,
+      "step": 1320
+    },
+    {
+      "epoch": 40.92307692307692,
+      "grad_norm": 1.6133264303207397,
+      "learning_rate": 4.15603944397543e-06,
+      "loss": 0.2185,
+      "step": 1330
+    },
+    {
+      "epoch": 41.23076923076923,
+      "grad_norm": 1.7328965663909912,
+      "learning_rate": 4.132932107384442e-06,
+      "loss": 0.2183,
+      "step": 1340
+    },
+    {
+      "epoch": 41.53846153846154,
+      "grad_norm": 1.5189462900161743,
+      "learning_rate": 4.109578857224478e-06,
+      "loss": 0.2167,
+      "step": 1350
+    },
+    {
+      "epoch": 41.84615384615385,
+      "grad_norm": 1.807603359222412,
+      "learning_rate": 4.085983210409114e-06,
+      "loss": 0.193,
+      "step": 1360
+    },
+    {
+      "epoch": 42.15384615384615,
+      "grad_norm": 1.4981666803359985,
+      "learning_rate": 4.062148720355967e-06,
+      "loss": 0.1724,
+      "step": 1370
+    },
+    {
+      "epoch": 42.46153846153846,
+      "grad_norm": 1.40492844581604,
+      "learning_rate": 4.038078976451567e-06,
+      "loss": 0.1658,
+      "step": 1380
+    },
+    {
+      "epoch": 42.76923076923077,
+      "grad_norm": 1.4978539943695068,
+      "learning_rate": 4.013777603510815e-06,
+      "loss": 0.1555,
+      "step": 1390
+    },
+    {
+      "epoch": 43.07692307692308,
+      "grad_norm": 1.2119354009628296,
+      "learning_rate": 3.989248261231084e-06,
+      "loss": 0.1833,
+      "step": 1400
+    },
+    {
+      "epoch": 43.38461538461539,
+      "grad_norm": 1.857128381729126,
+      "learning_rate": 3.964494643641097e-06,
+      "loss": 0.1622,
+      "step": 1410
+    },
+    {
+      "epoch": 43.69230769230769,
+      "grad_norm": 1.624523639678955,
+      "learning_rate": 3.939520478544614e-06,
+      "loss": 0.1499,
+      "step": 1420
+    },
+    {
+      "epoch": 44.0,
+      "grad_norm": 53768.84375,
+      "learning_rate": 3.914329526959033e-06,
+      "loss": 0.1712,
+      "step": 1430
+    },
+    {
+      "epoch": 44.30769230769231,
+      "grad_norm": 1.3771990537643433,
+      "learning_rate": 3.888925582549006e-06,
+      "loss": 0.1334,
+      "step": 1440
+    },
+    {
+      "epoch": 44.61538461538461,
+      "grad_norm": 2.549403190612793,
+      "learning_rate": 3.863312471055116e-06,
+      "loss": 0.1833,
+      "step": 1450
+    },
+    {
+      "epoch": 44.92307692307692,
+      "grad_norm": 1.4592410326004028,
+      "learning_rate": 3.8374940497177435e-06,
+      "loss": 0.1174,
+      "step": 1460
+    },
+    {
+      "epoch": 45.23076923076923,
+      "grad_norm": 1.5769482851028442,
+      "learning_rate": 3.8114742066961722e-06,
+      "loss": 0.1207,
+      "step": 1470
+    },
+    {
+      "epoch": 45.53846153846154,
+      "grad_norm": 1.1684468984603882,
+      "learning_rate": 3.785256860483054e-06,
+      "loss": 0.1275,
+      "step": 1480
+    },
+    {
+      "epoch": 45.84615384615385,
+      "grad_norm": 1.1915509700775146,
+      "learning_rate": 3.7588459593142944e-06,
+      "loss": 0.1253,
+      "step": 1490
+    },
+    {
+      "epoch": 46.15384615384615,
+      "grad_norm": 1.3312920331954956,
+      "learning_rate": 3.7322454805744605e-06,
+      "loss": 0.1159,
+      "step": 1500
+    },
+    {
+      "epoch": 46.46153846153846,
+      "grad_norm": 1.1740134954452515,
+      "learning_rate": 3.7054594301978075e-06,
+      "loss": 0.1312,
+      "step": 1510
+    },
+    {
+      "epoch": 46.76923076923077,
+      "grad_norm": 0.9904786348342896,
+      "learning_rate": 3.6784918420649952e-06,
+      "loss": 0.1171,
+      "step": 1520
+    },
+    {
+      "epoch": 47.07692307692308,
+      "grad_norm": 1.7853026390075684,
+      "learning_rate": 3.6513467773956002e-06,
+      "loss": 0.1229,
+      "step": 1530
+    },
+    {
+      "epoch": 47.38461538461539,
+      "grad_norm": 0.924367368221283,
+      "learning_rate": 3.624028324136517e-06,
+      "loss": 0.1087,
+      "step": 1540
+    },
+    {
+      "epoch": 47.69230769230769,
+      "grad_norm": 1.3565295934677124,
+      "learning_rate": 3.5965405963463197e-06,
+      "loss": 0.113,
+      "step": 1550
+    },
+    {
+      "epoch": 48.0,
+      "grad_norm": 27509738.0,
+      "learning_rate": 3.5688877335757055e-06,
+      "loss": 0.0949,
+      "step": 1560
+    },
+    {
+      "epoch": 48.30769230769231,
+      "grad_norm": 1.4091086387634277,
+      "learning_rate": 3.5410739002440938e-06,
+      "loss": 0.095,
+      "step": 1570
+    },
+    {
+      "epoch": 48.61538461538461,
+      "grad_norm": 1.1597000360488892,
+      "learning_rate": 3.5131032850124745e-06,
+      "loss": 0.0987,
+      "step": 1580
+    },
+    {
+      "epoch": 48.92307692307692,
+      "grad_norm": 1.2181200981140137,
+      "learning_rate": 3.484980100152621e-06,
+      "loss": 0.0894,
+      "step": 1590
+    },
+    {
+      "epoch": 49.23076923076923,
+      "grad_norm": 1.0059666633605957,
+      "learning_rate": 3.4567085809127247e-06,
+      "loss": 0.0962,
+      "step": 1600
+    },
+    {
+      "epoch": 49.53846153846154,
+      "grad_norm": 1.6103034019470215,
+      "learning_rate": 3.4282929848795944e-06,
+      "loss": 0.0842,
+      "step": 1610
+    },
+    {
+      "epoch": 49.84615384615385,
+      "grad_norm": 1.6124812364578247,
+      "learning_rate": 3.399737591337471e-06,
+      "loss": 0.0981,
+      "step": 1620
+    },
+    {
+      "epoch": 50.15384615384615,
+      "grad_norm": 1.14884614944458,
+      "learning_rate": 3.3710467006235865e-06,
+      "loss": 0.0996,
+      "step": 1630
+    },
+    {
+      "epoch": 50.46153846153846,
+      "grad_norm": 1.4607173204421997,
+      "learning_rate": 3.3422246334805504e-06,
+      "loss": 0.1034,
+      "step": 1640
+    },
+    {
+      "epoch": 50.76923076923077,
+      "grad_norm": 1.092631459236145,
+      "learning_rate": 3.313275730405658e-06,
+      "loss": 0.0801,
+      "step": 1650
+    },
+    {
+      "epoch": 51.07692307692308,
+      "grad_norm": 1.0797463655471802,
+      "learning_rate": 3.2842043509972294e-06,
+      "loss": 0.0795,
+      "step": 1660
+    },
+    {
+      "epoch": 51.38461538461539,
+      "grad_norm": 1.503728985786438,
+      "learning_rate": 3.2550148732980707e-06,
+      "loss": 0.0744,
+      "step": 1670
+    },
+    {
+      "epoch": 51.69230769230769,
+      "grad_norm": 1.0997803211212158,
+      "learning_rate": 3.225711693136156e-06,
+      "loss": 0.0741,
+      "step": 1680
+    },
+    {
+      "epoch": 52.0,
+      "grad_norm": 10298226.0,
+      "learning_rate": 3.196299223462633e-06,
+      "loss": 0.0699,
+      "step": 1690
+    },
+    {
+      "epoch": 52.30769230769231,
+      "grad_norm": 1.0617835521697998,
+      "learning_rate": 3.1667818936872463e-06,
+      "loss": 0.074,
+      "step": 1700
+    },
+    {
+      "epoch": 52.61538461538461,
+      "grad_norm": 0.8478608131408691,
+      "learning_rate": 3.137164149011287e-06,
+      "loss": 0.0577,
+      "step": 1710
+    },
+    {
+      "epoch": 52.92307692307692,
+      "grad_norm": 1.827232003211975,
+      "learning_rate": 3.10745044975816e-06,
+      "loss": 0.0871,
+      "step": 1720
+    },
+    {
+      "epoch": 53.23076923076923,
+      "grad_norm": 1.0407119989395142,
+      "learning_rate": 3.0776452707016784e-06,
+      "loss": 0.0682,
+      "step": 1730
+    },
+    {
+      "epoch": 53.53846153846154,
+      "grad_norm": 1.375914454460144,
+      "learning_rate": 3.0477531003921745e-06,
+      "loss": 0.0735,
+      "step": 1740
+    },
+    {
+      "epoch": 53.84615384615385,
+      "grad_norm": 1.3044782876968384,
+      "learning_rate": 3.0177784404805466e-06,
+      "loss": 0.0617,
+      "step": 1750
+    },
+    {
+      "epoch": 54.15384615384615,
+      "grad_norm": 0.6784080862998962,
+      "learning_rate": 2.9877258050403214e-06,
+      "loss": 0.0494,
+      "step": 1760
+    },
+    {
+      "epoch": 54.46153846153846,
+      "grad_norm": 1.0913127660751343,
+      "learning_rate": 2.957599719887853e-06,
+      "loss": 0.0685,
+      "step": 1770
+    },
+    {
+      "epoch": 54.76923076923077,
+      "grad_norm": 1.2988967895507812,
+      "learning_rate": 2.9274047219007533e-06,
+      "loss": 0.069,
+      "step": 1780
+    },
+    {
+      "epoch": 55.07692307692308,
+      "grad_norm": 1.0163013935089111,
+      "learning_rate": 2.8971453583346536e-06,
+      "loss": 0.0545,
+      "step": 1790
+    },
+    {
+      "epoch": 55.38461538461539,
+      "grad_norm": 0.7982223033905029,
+      "learning_rate": 2.8668261861384045e-06,
+      "loss": 0.0509,
+      "step": 1800
+    },
+    {
+      "epoch": 55.69230769230769,
+      "grad_norm": 1.5185413360595703,
+      "learning_rate": 2.8364517712678157e-06,
+      "loss": 0.0708,
+      "step": 1810
+    },
+    {
+      "epoch": 56.0,
+      "grad_norm": 54588.5390625,
+      "learning_rate": 2.806026687998041e-06,
+      "loss": 0.0531,
+      "step": 1820
+    },
+    {
+      "epoch": 56.30769230769231,
+      "grad_norm": 0.9050544500350952,
+      "learning_rate": 2.775555518234708e-06,
+      "loss": 0.0529,
+      "step": 1830
+    },
+    {
+      "epoch": 56.61538461538461,
+      "grad_norm": 1.0293651819229126,
+      "learning_rate": 2.7450428508239024e-06,
+      "loss": 0.0572,
+      "step": 1840
+    },
+    {
+      "epoch": 56.92307692307692,
+      "grad_norm": 1.1838538646697998,
+      "learning_rate": 2.7144932808611002e-06,
+      "loss": 0.0616,
+      "step": 1850
+    },
+    {
+      "epoch": 57.23076923076923,
+      "grad_norm": 1.2836631536483765,
+      "learning_rate": 2.683911408999169e-06,
+      "loss": 0.0536,
+      "step": 1860
+    },
+    {
+      "epoch": 57.53846153846154,
+      "grad_norm": 1.0823341608047485,
+      "learning_rate": 2.6533018407555216e-06,
+      "loss": 0.0476,
+      "step": 1870
+    },
+    {
+      "epoch": 57.84615384615385,
+      "grad_norm": 1.0420117378234863,
+      "learning_rate": 2.6226691858185454e-06,
+      "loss": 0.0527,
+      "step": 1880
+    },
+    {
+      "epoch": 58.15384615384615,
+      "grad_norm": 1.0533287525177002,
+      "learning_rate": 2.5920180573533975e-06,
+      "loss": 0.0623,
+      "step": 1890
+    },
+    {
+      "epoch": 58.46153846153846,
+      "grad_norm": 0.9571561217308044,
+      "learning_rate": 2.561353071307281e-06,
+      "loss": 0.0498,
+      "step": 1900
+    },
+    {
+      "epoch": 58.76923076923077,
+      "grad_norm": 1.224555253982544,
+      "learning_rate": 2.5306788457143e-06,
+      "loss": 0.0447,
+      "step": 1910
+    },
+    {
+      "epoch": 59.07692307692308,
+      "grad_norm": 1.900484561920166,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0578,
+      "step": 1920
+    },
+    {
+      "epoch": 59.38461538461539,
+      "grad_norm": 0.9753430485725403,
+      "learning_rate": 2.4693211542857005e-06,
+      "loss": 0.052,
+      "step": 1930
+    },
+    {
+      "epoch": 59.69230769230769,
+      "grad_norm": 1.0865504741668701,
+      "learning_rate": 2.43864692869272e-06,
+      "loss": 0.0447,
+      "step": 1940
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 39835.109375,
+      "learning_rate": 2.407981942646603e-06,
+      "loss": 0.0477,
+      "step": 1950
+    },
+    {
+      "epoch": 60.30769230769231,
+      "grad_norm": 1.1388822793960571,
+      "learning_rate": 2.377330814181455e-06,
+      "loss": 0.0516,
+      "step": 1960
+    },
+    {
+      "epoch": 60.61538461538461,
+      "grad_norm": 1.2782968282699585,
+      "learning_rate": 2.346698159244479e-06,
+      "loss": 0.0501,
+      "step": 1970
+    },
+    {
+      "epoch": 60.92307692307692,
+      "grad_norm": 1.6132394075393677,
+      "learning_rate": 2.3160885910008317e-06,
+      "loss": 0.0408,
+      "step": 1980
+    },
+    {
+      "epoch": 61.23076923076923,
+      "grad_norm": 0.8268479108810425,
+      "learning_rate": 2.2855067191389006e-06,
+      "loss": 0.0407,
+      "step": 1990
+    },
+    {
+      "epoch": 61.53846153846154,
+      "grad_norm": 0.9518911838531494,
+      "learning_rate": 2.2549571491760985e-06,
+      "loss": 0.0455,
+      "step": 2000
+    },
+    {
+      "epoch": 61.84615384615385,
+      "grad_norm": 1.2631924152374268,
+      "learning_rate": 2.2244444817652923e-06,
+      "loss": 0.0462,
+      "step": 2010
+    },
+    {
+      "epoch": 62.15384615384615,
+      "grad_norm": 1.0491702556610107,
+      "learning_rate": 2.19397331200196e-06,
+      "loss": 0.0384,
+      "step": 2020
+    },
+    {
+      "epoch": 62.46153846153846,
+      "grad_norm": 1.37276291847229,
+      "learning_rate": 2.1635482287321848e-06,
+      "loss": 0.0384,
+      "step": 2030
+    },
+    {
+      "epoch": 62.76923076923077,
+      "grad_norm": 0.911716103553772,
+      "learning_rate": 2.133173813861596e-06,
+      "loss": 0.0489,
+      "step": 2040
+    },
+    {
+      "epoch": 63.07692307692308,
+      "grad_norm": 0.8453769683837891,
+      "learning_rate": 2.102854641665347e-06,
+      "loss": 0.0519,
+      "step": 2050
+    },
+    {
+      "epoch": 63.38461538461539,
+      "grad_norm": 1.1368571519851685,
+      "learning_rate": 2.072595278099247e-06,
+      "loss": 0.0383,
+      "step": 2060
+    },
+    {
+      "epoch": 63.69230769230769,
+      "grad_norm": 1.6040756702423096,
+      "learning_rate": 2.042400280112148e-06,
+      "loss": 0.0421,
+      "step": 2070
+    },
+    {
+      "epoch": 64.0,
+      "grad_norm": 664656.875,
+      "learning_rate": 2.01227419495968e-06,
+      "loss": 0.0473,
+      "step": 2080
+    },
+    {
+      "epoch": 64.3076923076923,
+      "grad_norm": 0.9847516417503357,
+      "learning_rate": 1.982221559519454e-06,
+      "loss": 0.042,
+      "step": 2090
+    },
+    {
+      "epoch": 64.61538461538461,
+      "grad_norm": 0.77010577917099,
+      "learning_rate": 1.952246899607826e-06,
+      "loss": 0.042,
+      "step": 2100
+    },
+    {
+      "epoch": 64.92307692307692,
+      "grad_norm": 1.2908334732055664,
+      "learning_rate": 1.9223547292983225e-06,
+      "loss": 0.0416,
+      "step": 2110
+    },
+    {
+      "epoch": 65.23076923076923,
+      "grad_norm": 0.7256491184234619,
+      "learning_rate": 1.8925495502418407e-06,
+      "loss": 0.0353,
+      "step": 2120
+    },
+    {
+      "epoch": 65.53846153846153,
+      "grad_norm": 1.212572455406189,
+      "learning_rate": 1.862835850988714e-06,
+      "loss": 0.0427,
+      "step": 2130
+    },
+    {
+      "epoch": 65.84615384615384,
+      "grad_norm": 1.154390811920166,
+      "learning_rate": 1.8332181063127543e-06,
+      "loss": 0.0396,
+      "step": 2140
+    },
+    {
+      "epoch": 66.15384615384616,
+      "grad_norm": 0.8889743685722351,
+      "learning_rate": 1.8037007765373677e-06,
+      "loss": 0.0381,
+      "step": 2150
+    },
+    {
+      "epoch": 66.46153846153847,
+      "grad_norm": 1.1566401720046997,
+      "learning_rate": 1.7742883068638447e-06,
+      "loss": 0.041,
+      "step": 2160
+    },
+    {
+      "epoch": 66.76923076923077,
+      "grad_norm": 0.9389579892158508,
+      "learning_rate": 1.74498512670193e-06,
+      "loss": 0.0385,
+      "step": 2170
+    },
+    {
+      "epoch": 67.07692307692308,
+      "grad_norm": 0.709125816822052,
+      "learning_rate": 1.7157956490027716e-06,
+      "loss": 0.0432,
+      "step": 2180
+    },
+    {
+      "epoch": 67.38461538461539,
+      "grad_norm": 1.1108027696609497,
+      "learning_rate": 1.686724269594343e-06,
+      "loss": 0.0395,
+      "step": 2190
+    },
+    {
+      "epoch": 67.6923076923077,
+      "grad_norm": 1.087064266204834,
+      "learning_rate": 1.6577753665194502e-06,
+      "loss": 0.0402,
+      "step": 2200
+    },
+    {
+      "epoch": 68.0,
+      "grad_norm": 3785425.75,
+      "learning_rate": 1.628953299376414e-06,
+      "loss": 0.0351,
+      "step": 2210
+    },
+    {
+      "epoch": 68.3076923076923,
+      "grad_norm": 0.9498631954193115,
+      "learning_rate": 1.6002624086625296e-06,
+      "loss": 0.0402,
+      "step": 2220
+    },
+    {
+      "epoch": 68.61538461538461,
+      "grad_norm": 0.6672590374946594,
+      "learning_rate": 1.5717070151204064e-06,
+      "loss": 0.0333,
+      "step": 2230
+    },
+    {
+      "epoch": 68.92307692307692,
+      "grad_norm": 0.671436607837677,
+      "learning_rate": 1.5432914190872757e-06,
+      "loss": 0.0387,
+      "step": 2240
+    },
+    {
+      "epoch": 69.23076923076923,
+      "grad_norm": 0.7344552874565125,
+      "learning_rate": 1.5150198998473802e-06,
+      "loss": 0.0345,
+      "step": 2250
+    },
+    {
+      "epoch": 69.53846153846153,
+      "grad_norm": 0.5938952565193176,
+      "learning_rate": 1.4868967149875257e-06,
+      "loss": 0.0343,
+      "step": 2260
+    },
+    {
+      "epoch": 69.84615384615384,
+      "grad_norm": 0.862509548664093,
+      "learning_rate": 1.4589260997559077e-06,
+      "loss": 0.0359,
+      "step": 2270
+    },
+    {
+      "epoch": 70.15384615384616,
+      "grad_norm": 0.8928817510604858,
+      "learning_rate": 1.4311122664242955e-06,
+      "loss": 0.0406,
+      "step": 2280
+    },
+    {
+      "epoch": 70.46153846153847,
+      "grad_norm": 0.81640625,
+      "learning_rate": 1.4034594036536816e-06,
+      "loss": 0.0332,
+      "step": 2290
+    },
+    {
+      "epoch": 70.76923076923077,
+      "grad_norm": 0.5396949648857117,
+      "learning_rate": 1.3759716758634833e-06,
+      "loss": 0.0389,
+      "step": 2300
+    },
+    {
+      "epoch": 71.07692307692308,
+      "grad_norm": 0.918347954750061,
+      "learning_rate": 1.3486532226044e-06,
+      "loss": 0.0329,
+      "step": 2310
+    },
+    {
+      "epoch": 71.38461538461539,
+      "grad_norm": 0.8731901049613953,
+      "learning_rate": 1.3215081579350058e-06,
+      "loss": 0.0355,
+      "step": 2320
+    },
+    {
+      "epoch": 71.6923076923077,
+      "grad_norm": 0.9578891396522522,
+      "learning_rate": 1.294540569802193e-06,
+      "loss": 0.037,
+      "step": 2330
+    },
+    {
+      "epoch": 72.0,
+      "grad_norm": 3753634.75,
+      "learning_rate": 1.2677545194255403e-06,
+      "loss": 0.0372,
+      "step": 2340
+    },
+    {
+      "epoch": 72.3076923076923,
+      "grad_norm": 0.9850757122039795,
+      "learning_rate": 1.2411540406857064e-06,
+      "loss": 0.0388,
+      "step": 2350
+    },
+    {
+      "epoch": 72.61538461538461,
+      "grad_norm": 1.0889559984207153,
+      "learning_rate": 1.214743139516946e-06,
+      "loss": 0.0329,
+      "step": 2360
+    },
+    {
+      "epoch": 72.92307692307692,
+      "grad_norm": 1.2561447620391846,
+      "learning_rate": 1.1885257933038282e-06,
+      "loss": 0.0334,
+      "step": 2370
+    },
+    {
+      "epoch": 73.23076923076923,
+      "grad_norm": 1.08214271068573,
+      "learning_rate": 1.1625059502822575e-06,
+      "loss": 0.0438,
+      "step": 2380
+    },
+    {
+      "epoch": 73.53846153846153,
+      "grad_norm": 0.6585337519645691,
+      "learning_rate": 1.1366875289448844e-06,
+      "loss": 0.0283,
+      "step": 2390
+    },
+    {
+      "epoch": 73.84615384615384,
+      "grad_norm": 1.001531720161438,
+      "learning_rate": 1.1110744174509952e-06,
+      "loss": 0.0405,
+      "step": 2400
+    },
+    {
+      "epoch": 74.15384615384616,
+      "grad_norm": 0.774890124797821,
+      "learning_rate": 1.0856704730409667e-06,
+      "loss": 0.035,
+      "step": 2410
+    },
+    {
+      "epoch": 74.46153846153847,
+      "grad_norm": 0.8112567663192749,
+      "learning_rate": 1.0604795214553867e-06,
+      "loss": 0.0371,
+      "step": 2420
+    },
+    {
+      "epoch": 74.76923076923077,
+      "grad_norm": 0.7539799809455872,
+      "learning_rate": 1.035505356358903e-06,
+      "loss": 0.0363,
+      "step": 2430
+    },
+    {
+      "epoch": 75.07692307692308,
+      "grad_norm": 1.047004222869873,
+      "learning_rate": 1.0107517387689168e-06,
+      "loss": 0.0305,
+      "step": 2440
+    },
+    {
+      "epoch": 75.38461538461539,
+      "grad_norm": 0.5877715945243835,
+      "learning_rate": 9.862223964891864e-07,
+      "loss": 0.032,
+      "step": 2450
+    },
+    {
+      "epoch": 75.6923076923077,
+      "grad_norm": 0.7707840204238892,
+      "learning_rate": 9.61921023548433e-07,
+      "loss": 0.0345,
+      "step": 2460
+    },
+    {
+      "epoch": 76.0,
+      "grad_norm": 8456043.0,
+      "learning_rate": 9.378512796440345e-07,
+      "loss": 0.0362,
+      "step": 2470
+    },
+    {
+      "epoch": 76.3076923076923,
+      "grad_norm": 1.2004197835922241,
+      "learning_rate": 9.140167895908867e-07,
+      "loss": 0.0318,
+      "step": 2480
+    },
+    {
+      "epoch": 76.61538461538461,
+      "grad_norm": 0.7192149758338928,
+      "learning_rate": 8.904211427755219e-07,
+      "loss": 0.0339,
+      "step": 2490
+    },
+    {
+      "epoch": 76.92307692307692,
+      "grad_norm": 0.8858992457389832,
+      "learning_rate": 8.670678926155588e-07,
+      "loss": 0.0365,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.4736165944792064e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1993c1dd567888612b9f98e8fe3b9f847f44fa985220b5be4280c19d42df745
+size 5432