Upload 13 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-coder-6.7b-base
+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 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950a9784281d3b2a0e373b07a194fc3f896c2f7ebed825e056b0990aad53ffae
+size 639691872

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2d924006b69fdd9f9b25d9afbeb36ad855588d2f4686ebd05dea12ebcd7a868
+size 1279540474

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff97b555b966f7dd5dfe75daf6d6676cf8250d91c68840db59edb664b62dff1
+size 14768

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e660a5e628a2df519cbe55b4189cfe7af8cf8cfb18c40f12f0be867beda80d92
+size 14768

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a8308fbda56e1315bbdacd201cf73db6a30d5bb40bb6303e2fca7ec6f7a3fa
+size 14768

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec90720690d9bc72c277d37c452ce5a3a646d1879ecf2a784559bc30250d08df
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1609 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0775354794046383,
+  "eval_steps": 500,
+  "global_step": 2250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009230414214837892,
+      "grad_norm": 0.0994892492890358,
+      "learning_rate": 0.0002,
+      "loss": 1.5722,
+      "step": 10
+    },
+    {
+      "epoch": 0.018460828429675783,
+      "grad_norm": 0.062255557626485825,
+      "learning_rate": 0.0002,
+      "loss": 1.2813,
+      "step": 20
+    },
+    {
+      "epoch": 0.027691242644513673,
+      "grad_norm": 0.12040963768959045,
+      "learning_rate": 0.0002,
+      "loss": 1.3037,
+      "step": 30
+    },
+    {
+      "epoch": 0.036921656859351566,
+      "grad_norm": 0.04763123765587807,
+      "learning_rate": 0.0002,
+      "loss": 1.3666,
+      "step": 40
+    },
+    {
+      "epoch": 0.046152071074189456,
+      "grad_norm": 0.12753669917583466,
+      "learning_rate": 0.0002,
+      "loss": 1.1438,
+      "step": 50
+    },
+    {
+      "epoch": 0.055382485289027346,
+      "grad_norm": 0.10537329316139221,
+      "learning_rate": 0.0002,
+      "loss": 1.4241,
+      "step": 60
+    },
+    {
+      "epoch": 0.06461289950386524,
+      "grad_norm": 0.03980427607893944,
+      "learning_rate": 0.0002,
+      "loss": 1.2929,
+      "step": 70
+    },
+    {
+      "epoch": 0.07384331371870313,
+      "grad_norm": 0.12119753658771515,
+      "learning_rate": 0.0002,
+      "loss": 1.2938,
+      "step": 80
+    },
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 0.062459882348775864,
+      "learning_rate": 0.0002,
+      "loss": 1.3273,
+      "step": 90
+    },
+    {
+      "epoch": 0.09230414214837891,
+      "grad_norm": 0.15507832169532776,
+      "learning_rate": 0.0002,
+      "loss": 1.1885,
+      "step": 100
+    },
+    {
+      "epoch": 0.1015345563632168,
+      "grad_norm": 0.09834089875221252,
+      "learning_rate": 0.0002,
+      "loss": 1.3693,
+      "step": 110
+    },
+    {
+      "epoch": 0.11076497057805469,
+      "grad_norm": 0.05203542485833168,
+      "learning_rate": 0.0002,
+      "loss": 1.2587,
+      "step": 120
+    },
+    {
+      "epoch": 0.11999538479289258,
+      "grad_norm": 0.12015814334154129,
+      "learning_rate": 0.0002,
+      "loss": 1.2815,
+      "step": 130
+    },
+    {
+      "epoch": 0.12922579900773049,
+      "grad_norm": 0.06197419390082359,
+      "learning_rate": 0.0002,
+      "loss": 1.429,
+      "step": 140
+    },
+    {
+      "epoch": 0.13845621322256838,
+      "grad_norm": 0.17958974838256836,
+      "learning_rate": 0.0002,
+      "loss": 1.0941,
+      "step": 150
+    },
+    {
+      "epoch": 0.14768662743740626,
+      "grad_norm": 0.09950366616249084,
+      "learning_rate": 0.0002,
+      "loss": 1.4066,
+      "step": 160
+    },
+    {
+      "epoch": 0.15691704165224415,
+      "grad_norm": 0.050984274595975876,
+      "learning_rate": 0.0002,
+      "loss": 1.2131,
+      "step": 170
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 0.150551900267601,
+      "learning_rate": 0.0002,
+      "loss": 1.2422,
+      "step": 180
+    },
+    {
+      "epoch": 0.17537787008191993,
+      "grad_norm": 0.06124914437532425,
+      "learning_rate": 0.0002,
+      "loss": 1.3434,
+      "step": 190
+    },
+    {
+      "epoch": 0.18460828429675782,
+      "grad_norm": 0.17724090814590454,
+      "learning_rate": 0.0002,
+      "loss": 1.0898,
+      "step": 200
+    },
+    {
+      "epoch": 0.19383869851159571,
+      "grad_norm": 0.0937797948718071,
+      "learning_rate": 0.0002,
+      "loss": 1.432,
+      "step": 210
+    },
+    {
+      "epoch": 0.2030691127264336,
+      "grad_norm": 0.059550438076257706,
+      "learning_rate": 0.0002,
+      "loss": 1.1605,
+      "step": 220
+    },
+    {
+      "epoch": 0.2122995269412715,
+      "grad_norm": 0.10598563402891159,
+      "learning_rate": 0.0002,
+      "loss": 1.2004,
+      "step": 230
+    },
+    {
+      "epoch": 0.22152994115610938,
+      "grad_norm": 0.059932854026556015,
+      "learning_rate": 0.0002,
+      "loss": 1.2944,
+      "step": 240
+    },
+    {
+      "epoch": 0.23076035537094727,
+      "grad_norm": 0.16503147780895233,
+      "learning_rate": 0.0002,
+      "loss": 1.1301,
+      "step": 250
+    },
+    {
+      "epoch": 0.23999076958578516,
+      "grad_norm": 0.08444368839263916,
+      "learning_rate": 0.0002,
+      "loss": 1.4195,
+      "step": 260
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 0.05936718359589577,
+      "learning_rate": 0.0002,
+      "loss": 1.2805,
+      "step": 270
+    },
+    {
+      "epoch": 0.25845159801546097,
+      "grad_norm": 0.12579703330993652,
+      "learning_rate": 0.0002,
+      "loss": 1.2394,
+      "step": 280
+    },
+    {
+      "epoch": 0.26768201223029886,
+      "grad_norm": 0.06689989566802979,
+      "learning_rate": 0.0002,
+      "loss": 1.298,
+      "step": 290
+    },
+    {
+      "epoch": 0.27691242644513675,
+      "grad_norm": 0.17793583869934082,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 300
+    },
+    {
+      "epoch": 0.28614284065997464,
+      "grad_norm": 0.08275260776281357,
+      "learning_rate": 0.0002,
+      "loss": 1.3433,
+      "step": 310
+    },
+    {
+      "epoch": 0.29537325487481253,
+      "grad_norm": 0.05578906834125519,
+      "learning_rate": 0.0002,
+      "loss": 1.2197,
+      "step": 320
+    },
+    {
+      "epoch": 0.3046036690896504,
+      "grad_norm": 0.13691303133964539,
+      "learning_rate": 0.0002,
+      "loss": 1.2487,
+      "step": 330
+    },
+    {
+      "epoch": 0.3138340833044883,
+      "grad_norm": 0.055021870881319046,
+      "learning_rate": 0.0002,
+      "loss": 1.275,
+      "step": 340
+    },
+    {
+      "epoch": 0.3230644975193262,
+      "grad_norm": 0.1495254933834076,
+      "learning_rate": 0.0002,
+      "loss": 1.0445,
+      "step": 350
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.09207426011562347,
+      "learning_rate": 0.0002,
+      "loss": 1.3997,
+      "step": 360
+    },
+    {
+      "epoch": 0.341525325949002,
+      "grad_norm": 0.05421067774295807,
+      "learning_rate": 0.0002,
+      "loss": 1.1986,
+      "step": 370
+    },
+    {
+      "epoch": 0.35075574016383987,
+      "grad_norm": 0.12197154760360718,
+      "learning_rate": 0.0002,
+      "loss": 1.2589,
+      "step": 380
+    },
+    {
+      "epoch": 0.35998615437867776,
+      "grad_norm": 0.06101464852690697,
+      "learning_rate": 0.0002,
+      "loss": 1.3766,
+      "step": 390
+    },
+    {
+      "epoch": 0.36921656859351565,
+      "grad_norm": 0.19063565135002136,
+      "learning_rate": 0.0002,
+      "loss": 1.0677,
+      "step": 400
+    },
+    {
+      "epoch": 0.37844698280835354,
+      "grad_norm": 0.09075415134429932,
+      "learning_rate": 0.0002,
+      "loss": 1.4032,
+      "step": 410
+    },
+    {
+      "epoch": 0.38767739702319143,
+      "grad_norm": 0.053780850023031235,
+      "learning_rate": 0.0002,
+      "loss": 1.2328,
+      "step": 420
+    },
+    {
+      "epoch": 0.3969078112380293,
+      "grad_norm": 0.11555945128202438,
+      "learning_rate": 0.0002,
+      "loss": 1.2205,
+      "step": 430
+    },
+    {
+      "epoch": 0.4061382254528672,
+      "grad_norm": 0.0680965855717659,
+      "learning_rate": 0.0002,
+      "loss": 1.2906,
+      "step": 440
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.17800922691822052,
+      "learning_rate": 0.0002,
+      "loss": 1.0823,
+      "step": 450
+    },
+    {
+      "epoch": 0.424599053882543,
+      "grad_norm": 0.10128472000360489,
+      "learning_rate": 0.0002,
+      "loss": 1.3619,
+      "step": 460
+    },
+    {
+      "epoch": 0.4338294680973809,
+      "grad_norm": 0.049957141280174255,
+      "learning_rate": 0.0002,
+      "loss": 1.1817,
+      "step": 470
+    },
+    {
+      "epoch": 0.44305988231221877,
+      "grad_norm": 0.1359386295080185,
+      "learning_rate": 0.0002,
+      "loss": 1.2062,
+      "step": 480
+    },
+    {
+      "epoch": 0.45229029652705666,
+      "grad_norm": 0.0684947818517685,
+      "learning_rate": 0.0002,
+      "loss": 1.3084,
+      "step": 490
+    },
+    {
+      "epoch": 0.46152071074189455,
+      "grad_norm": 0.1941768378019333,
+      "learning_rate": 0.0002,
+      "loss": 1.0832,
+      "step": 500
+    },
+    {
+      "epoch": 0.47075112495673244,
+      "grad_norm": 0.09089575707912445,
+      "learning_rate": 0.0002,
+      "loss": 1.3617,
+      "step": 510
+    },
+    {
+      "epoch": 0.4799815391715703,
+      "grad_norm": 0.06254442036151886,
+      "learning_rate": 0.0002,
+      "loss": 1.1961,
+      "step": 520
+    },
+    {
+      "epoch": 0.4892119533864082,
+      "grad_norm": 0.15948618948459625,
+      "learning_rate": 0.0002,
+      "loss": 1.2078,
+      "step": 530
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 0.06899358332157135,
+      "learning_rate": 0.0002,
+      "loss": 1.3514,
+      "step": 540
+    },
+    {
+      "epoch": 0.507672781816084,
+      "grad_norm": 0.16271327435970306,
+      "learning_rate": 0.0002,
+      "loss": 1.0975,
+      "step": 550
+    },
+    {
+      "epoch": 0.5169031960309219,
+      "grad_norm": 0.0963057279586792,
+      "learning_rate": 0.0002,
+      "loss": 1.3987,
+      "step": 560
+    },
+    {
+      "epoch": 0.5261336102457598,
+      "grad_norm": 0.05728481337428093,
+      "learning_rate": 0.0002,
+      "loss": 1.1942,
+      "step": 570
+    },
+    {
+      "epoch": 0.5353640244605977,
+      "grad_norm": 0.1385851353406906,
+      "learning_rate": 0.0002,
+      "loss": 1.1708,
+      "step": 580
+    },
+    {
+      "epoch": 0.5445944386754356,
+      "grad_norm": 0.06655001640319824,
+      "learning_rate": 0.0002,
+      "loss": 1.339,
+      "step": 590
+    },
+    {
+      "epoch": 0.5538248528902735,
+      "grad_norm": 0.1913049817085266,
+      "learning_rate": 0.0002,
+      "loss": 1.0967,
+      "step": 600
+    },
+    {
+      "epoch": 0.5630552671051113,
+      "grad_norm": 0.11070458590984344,
+      "learning_rate": 0.0002,
+      "loss": 1.4031,
+      "step": 610
+    },
+    {
+      "epoch": 0.5722856813199493,
+      "grad_norm": 0.05270432308316231,
+      "learning_rate": 0.0002,
+      "loss": 1.203,
+      "step": 620
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.12132929265499115,
+      "learning_rate": 0.0002,
+      "loss": 1.1632,
+      "step": 630
+    },
+    {
+      "epoch": 0.5907465097496251,
+      "grad_norm": 0.06843800842761993,
+      "learning_rate": 0.0002,
+      "loss": 1.3555,
+      "step": 640
+    },
+    {
+      "epoch": 0.5999769239644629,
+      "grad_norm": 0.1670321673154831,
+      "learning_rate": 0.0002,
+      "loss": 1.059,
+      "step": 650
+    },
+    {
+      "epoch": 0.6092073381793008,
+      "grad_norm": 0.10655465722084045,
+      "learning_rate": 0.0002,
+      "loss": 1.3544,
+      "step": 660
+    },
+    {
+      "epoch": 0.6184377523941387,
+      "grad_norm": 0.05795924738049507,
+      "learning_rate": 0.0002,
+      "loss": 1.25,
+      "step": 670
+    },
+    {
+      "epoch": 0.6276681666089766,
+      "grad_norm": 0.1298709660768509,
+      "learning_rate": 0.0002,
+      "loss": 1.222,
+      "step": 680
+    },
+    {
+      "epoch": 0.6368985808238145,
+      "grad_norm": 0.0654703825712204,
+      "learning_rate": 0.0002,
+      "loss": 1.3189,
+      "step": 690
+    },
+    {
+      "epoch": 0.6461289950386524,
+      "grad_norm": 0.18943524360656738,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 700
+    },
+    {
+      "epoch": 0.6553594092534902,
+      "grad_norm": 0.11117199063301086,
+      "learning_rate": 0.0002,
+      "loss": 1.3343,
+      "step": 710
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 0.05172109976410866,
+      "learning_rate": 0.0002,
+      "loss": 1.1328,
+      "step": 720
+    },
+    {
+      "epoch": 0.673820237683166,
+      "grad_norm": 0.13359065353870392,
+      "learning_rate": 0.0002,
+      "loss": 1.2447,
+      "step": 730
+    },
+    {
+      "epoch": 0.683050651898004,
+      "grad_norm": 0.059676457196474075,
+      "learning_rate": 0.0002,
+      "loss": 1.2718,
+      "step": 740
+    },
+    {
+      "epoch": 0.6922810661128418,
+      "grad_norm": 0.1960563063621521,
+      "learning_rate": 0.0002,
+      "loss": 1.0669,
+      "step": 750
+    },
+    {
+      "epoch": 0.7015114803276797,
+      "grad_norm": 0.11250808089971542,
+      "learning_rate": 0.0002,
+      "loss": 1.3465,
+      "step": 760
+    },
+    {
+      "epoch": 0.7107418945425176,
+      "grad_norm": 0.05576665699481964,
+      "learning_rate": 0.0002,
+      "loss": 1.1737,
+      "step": 770
+    },
+    {
+      "epoch": 0.7199723087573555,
+      "grad_norm": 0.16185137629508972,
+      "learning_rate": 0.0002,
+      "loss": 1.187,
+      "step": 780
+    },
+    {
+      "epoch": 0.7292027229721934,
+      "grad_norm": 0.06587795913219452,
+      "learning_rate": 0.0002,
+      "loss": 1.3014,
+      "step": 790
+    },
+    {
+      "epoch": 0.7384331371870313,
+      "grad_norm": 0.21672724187374115,
+      "learning_rate": 0.0002,
+      "loss": 1.1078,
+      "step": 800
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 0.09454522281885147,
+      "learning_rate": 0.0002,
+      "loss": 1.3883,
+      "step": 810
+    },
+    {
+      "epoch": 0.7568939656167071,
+      "grad_norm": 0.05657172575592995,
+      "learning_rate": 0.0002,
+      "loss": 1.2014,
+      "step": 820
+    },
+    {
+      "epoch": 0.7661243798315449,
+      "grad_norm": 0.12518398463726044,
+      "learning_rate": 0.0002,
+      "loss": 1.1624,
+      "step": 830
+    },
+    {
+      "epoch": 0.7753547940463829,
+      "grad_norm": 0.0718185231089592,
+      "learning_rate": 0.0002,
+      "loss": 1.2899,
+      "step": 840
+    },
+    {
+      "epoch": 0.7845852082612207,
+      "grad_norm": 0.1621280312538147,
+      "learning_rate": 0.0002,
+      "loss": 1.0833,
+      "step": 850
+    },
+    {
+      "epoch": 0.7938156224760586,
+      "grad_norm": 0.1027815043926239,
+      "learning_rate": 0.0002,
+      "loss": 1.352,
+      "step": 860
+    },
+    {
+      "epoch": 0.8030460366908965,
+      "grad_norm": 0.056900862604379654,
+      "learning_rate": 0.0002,
+      "loss": 1.2106,
+      "step": 870
+    },
+    {
+      "epoch": 0.8122764509057344,
+      "grad_norm": 0.138154998421669,
+      "learning_rate": 0.0002,
+      "loss": 1.1345,
+      "step": 880
+    },
+    {
+      "epoch": 0.8215068651205722,
+      "grad_norm": 0.06931914389133453,
+      "learning_rate": 0.0002,
+      "loss": 1.3355,
+      "step": 890
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.185394287109375,
+      "learning_rate": 0.0002,
+      "loss": 1.0777,
+      "step": 900
+    },
+    {
+      "epoch": 0.839967693550248,
+      "grad_norm": 0.09037897735834122,
+      "learning_rate": 0.0002,
+      "loss": 1.3078,
+      "step": 910
+    },
+    {
+      "epoch": 0.849198107765086,
+      "grad_norm": 0.05863342061638832,
+      "learning_rate": 0.0002,
+      "loss": 1.2147,
+      "step": 920
+    },
+    {
+      "epoch": 0.8584285219799238,
+      "grad_norm": 0.14246703684329987,
+      "learning_rate": 0.0002,
+      "loss": 1.1953,
+      "step": 930
+    },
+    {
+      "epoch": 0.8676589361947618,
+      "grad_norm": 0.07498980313539505,
+      "learning_rate": 0.0002,
+      "loss": 1.2837,
+      "step": 940
+    },
+    {
+      "epoch": 0.8768893504095996,
+      "grad_norm": 0.23275145888328552,
+      "learning_rate": 0.0002,
+      "loss": 1.0615,
+      "step": 950
+    },
+    {
+      "epoch": 0.8861197646244375,
+      "grad_norm": 0.09213528782129288,
+      "learning_rate": 0.0002,
+      "loss": 1.3883,
+      "step": 960
+    },
+    {
+      "epoch": 0.8953501788392754,
+      "grad_norm": 0.05749181658029556,
+      "learning_rate": 0.0002,
+      "loss": 1.2223,
+      "step": 970
+    },
+    {
+      "epoch": 0.9045805930541133,
+      "grad_norm": 0.12675738334655762,
+      "learning_rate": 0.0002,
+      "loss": 1.1542,
+      "step": 980
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.06891526281833649,
+      "learning_rate": 0.0002,
+      "loss": 1.2883,
+      "step": 990
+    },
+    {
+      "epoch": 0.9230414214837891,
+      "grad_norm": 0.1506439447402954,
+      "learning_rate": 0.0002,
+      "loss": 1.1152,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9322718356986269,
+      "grad_norm": 0.08551948517560959,
+      "learning_rate": 0.0002,
+      "loss": 1.3746,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9415022499134649,
+      "grad_norm": 0.05816769599914551,
+      "learning_rate": 0.0002,
+      "loss": 1.2117,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9507326641283027,
+      "grad_norm": 0.15679936110973358,
+      "learning_rate": 0.0002,
+      "loss": 1.2107,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9599630783431407,
+      "grad_norm": 0.06274525076150894,
+      "learning_rate": 0.0002,
+      "loss": 1.2783,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9691934925579785,
+      "grad_norm": 0.1663607805967331,
+      "learning_rate": 0.0002,
+      "loss": 1.0381,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9784239067728164,
+      "grad_norm": 0.10284286737442017,
+      "learning_rate": 0.0002,
+      "loss": 1.4281,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.06172878295183182,
+      "learning_rate": 0.0002,
+      "loss": 1.1913,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 0.11540690809488297,
+      "learning_rate": 0.0002,
+      "loss": 1.2357,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0064612899503864,
+      "grad_norm": 0.07405360043048859,
+      "learning_rate": 0.0002,
+      "loss": 1.3859,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0156917041652245,
+      "grad_norm": 0.07363928109407425,
+      "learning_rate": 0.0002,
+      "loss": 0.9267,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0249221183800623,
+      "grad_norm": 0.10718333721160889,
+      "learning_rate": 0.0002,
+      "loss": 1.242,
+      "step": 1110
+    },
+    {
+      "epoch": 1.0341525325949001,
+      "grad_norm": 0.06949968636035919,
+      "learning_rate": 0.0002,
+      "loss": 1.0087,
+      "step": 1120
+    },
+    {
+      "epoch": 1.043382946809738,
+      "grad_norm": 0.15124961733818054,
+      "learning_rate": 0.0002,
+      "loss": 1.0951,
+      "step": 1130
+    },
+    {
+      "epoch": 1.052613361024576,
+      "grad_norm": 0.08505109697580338,
+      "learning_rate": 0.0002,
+      "loss": 1.2338,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0618437752394139,
+      "grad_norm": 0.0844084769487381,
+      "learning_rate": 0.0002,
+      "loss": 0.9387,
+      "step": 1150
+    },
+    {
+      "epoch": 1.0710741894542517,
+      "grad_norm": 0.12017443031072617,
+      "learning_rate": 0.0002,
+      "loss": 1.2559,
+      "step": 1160
+    },
+    {
+      "epoch": 1.0803046036690898,
+      "grad_norm": 0.07678249478340149,
+      "learning_rate": 0.0002,
+      "loss": 1.0786,
+      "step": 1170
+    },
+    {
+      "epoch": 1.0895350178839276,
+      "grad_norm": 0.18587274849414825,
+      "learning_rate": 0.0002,
+      "loss": 1.0891,
+      "step": 1180
+    },
+    {
+      "epoch": 1.0987654320987654,
+      "grad_norm": 0.087877057492733,
+      "learning_rate": 0.0002,
+      "loss": 1.2243,
+      "step": 1190
+    },
+    {
+      "epoch": 1.1079958463136033,
+      "grad_norm": 0.08151056617498398,
+      "learning_rate": 0.0002,
+      "loss": 0.9319,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1172262605284413,
+      "grad_norm": 0.13637030124664307,
+      "learning_rate": 0.0002,
+      "loss": 1.342,
+      "step": 1210
+    },
+    {
+      "epoch": 1.1264566747432792,
+      "grad_norm": 0.07987112551927567,
+      "learning_rate": 0.0002,
+      "loss": 1.0845,
+      "step": 1220
+    },
+    {
+      "epoch": 1.135687088958117,
+      "grad_norm": 0.17300938069820404,
+      "learning_rate": 0.0002,
+      "loss": 1.1104,
+      "step": 1230
+    },
+    {
+      "epoch": 1.1449175031729548,
+      "grad_norm": 0.0821269229054451,
+      "learning_rate": 0.0002,
+      "loss": 1.2084,
+      "step": 1240
+    },
+    {
+      "epoch": 1.1541479173877929,
+      "grad_norm": 0.08363176882266998,
+      "learning_rate": 0.0002,
+      "loss": 0.9193,
+      "step": 1250
+    },
+    {
+      "epoch": 1.1633783316026307,
+      "grad_norm": 0.12400569021701813,
+      "learning_rate": 0.0002,
+      "loss": 1.3398,
+      "step": 1260
+    },
+    {
+      "epoch": 1.1726087458174685,
+      "grad_norm": 0.0741545781493187,
+      "learning_rate": 0.0002,
+      "loss": 1.07,
+      "step": 1270
+    },
+    {
+      "epoch": 1.1818391600323064,
+      "grad_norm": 0.18392737209796906,
+      "learning_rate": 0.0002,
+      "loss": 1.102,
+      "step": 1280
+    },
+    {
+      "epoch": 1.1910695742471444,
+      "grad_norm": 0.10395547747612,
+      "learning_rate": 0.0002,
+      "loss": 1.1766,
+      "step": 1290
+    },
+    {
+      "epoch": 1.2002999884619823,
+      "grad_norm": 0.08065596967935562,
+      "learning_rate": 0.0002,
+      "loss": 0.9593,
+      "step": 1300
+    },
+    {
+      "epoch": 1.20953040267682,
+      "grad_norm": 0.13076524436473846,
+      "learning_rate": 0.0002,
+      "loss": 1.2912,
+      "step": 1310
+    },
+    {
+      "epoch": 1.218760816891658,
+      "grad_norm": 0.08445240557193756,
+      "learning_rate": 0.0002,
+      "loss": 1.0545,
+      "step": 1320
+    },
+    {
+      "epoch": 1.227991231106496,
+      "grad_norm": 0.20568707585334778,
+      "learning_rate": 0.0002,
+      "loss": 1.0472,
+      "step": 1330
+    },
+    {
+      "epoch": 1.2372216453213338,
+      "grad_norm": 0.0978812500834465,
+      "learning_rate": 0.0002,
+      "loss": 1.1746,
+      "step": 1340
+    },
+    {
+      "epoch": 1.2464520595361717,
+      "grad_norm": 0.08013073354959488,
+      "learning_rate": 0.0002,
+      "loss": 0.9361,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2556824737510095,
+      "grad_norm": 0.15785863995552063,
+      "learning_rate": 0.0002,
+      "loss": 1.3058,
+      "step": 1360
+    },
+    {
+      "epoch": 1.2649128879658473,
+      "grad_norm": 0.08266527205705643,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 1370
+    },
+    {
+      "epoch": 1.2741433021806854,
+      "grad_norm": 0.18238036334514618,
+      "learning_rate": 0.0002,
+      "loss": 1.0587,
+      "step": 1380
+    },
+    {
+      "epoch": 1.2833737163955232,
+      "grad_norm": 0.09454452991485596,
+      "learning_rate": 0.0002,
+      "loss": 1.2299,
+      "step": 1390
+    },
+    {
+      "epoch": 1.292604130610361,
+      "grad_norm": 0.09221120178699493,
+      "learning_rate": 0.0002,
+      "loss": 0.9915,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3018345448251991,
+      "grad_norm": 0.13429689407348633,
+      "learning_rate": 0.0002,
+      "loss": 1.3109,
+      "step": 1410
+    },
+    {
+      "epoch": 1.311064959040037,
+      "grad_norm": 0.08239381015300751,
+      "learning_rate": 0.0002,
+      "loss": 1.0279,
+      "step": 1420
+    },
+    {
+      "epoch": 1.3202953732548748,
+      "grad_norm": 0.20243394374847412,
+      "learning_rate": 0.0002,
+      "loss": 1.1165,
+      "step": 1430
+    },
+    {
+      "epoch": 1.3295257874697128,
+      "grad_norm": 0.10623496025800705,
+      "learning_rate": 0.0002,
+      "loss": 1.1892,
+      "step": 1440
+    },
+    {
+      "epoch": 1.3387562016845507,
+      "grad_norm": 0.08493519574403763,
+      "learning_rate": 0.0002,
+      "loss": 0.9719,
+      "step": 1450
+    },
+    {
+      "epoch": 1.3479866158993885,
+      "grad_norm": 0.16793687641620636,
+      "learning_rate": 0.0002,
+      "loss": 1.2933,
+      "step": 1460
+    },
+    {
+      "epoch": 1.3572170301142263,
+      "grad_norm": 0.0803951844573021,
+      "learning_rate": 0.0002,
+      "loss": 1.0914,
+      "step": 1470
+    },
+    {
+      "epoch": 1.3664474443290642,
+      "grad_norm": 0.18061946332454681,
+      "learning_rate": 0.0002,
+      "loss": 1.0951,
+      "step": 1480
+    },
+    {
+      "epoch": 1.3756778585439022,
+      "grad_norm": 0.09481924027204514,
+      "learning_rate": 0.0002,
+      "loss": 1.2137,
+      "step": 1490
+    },
+    {
+      "epoch": 1.38490827275874,
+      "grad_norm": 0.08988731354475021,
+      "learning_rate": 0.0002,
+      "loss": 1.0406,
+      "step": 1500
+    },
+    {
+      "epoch": 1.394138686973578,
+      "grad_norm": 0.16403962671756744,
+      "learning_rate": 0.0002,
+      "loss": 1.2664,
+      "step": 1510
+    },
+    {
+      "epoch": 1.403369101188416,
+      "grad_norm": 0.0818110927939415,
+      "learning_rate": 0.0002,
+      "loss": 1.0402,
+      "step": 1520
+    },
+    {
+      "epoch": 1.4125995154032538,
+      "grad_norm": 0.16447734832763672,
+      "learning_rate": 0.0002,
+      "loss": 1.1246,
+      "step": 1530
+    },
+    {
+      "epoch": 1.4218299296180916,
+      "grad_norm": 0.10654182732105255,
+      "learning_rate": 0.0002,
+      "loss": 1.1963,
+      "step": 1540
+    },
+    {
+      "epoch": 1.4310603438329295,
+      "grad_norm": 0.09120084345340729,
+      "learning_rate": 0.0002,
+      "loss": 1.0389,
+      "step": 1550
+    },
+    {
+      "epoch": 1.4402907580477673,
+      "grad_norm": 0.14979740977287292,
+      "learning_rate": 0.0002,
+      "loss": 1.2998,
+      "step": 1560
+    },
+    {
+      "epoch": 1.4495211722626054,
+      "grad_norm": 0.07872021943330765,
+      "learning_rate": 0.0002,
+      "loss": 1.0553,
+      "step": 1570
+    },
+    {
+      "epoch": 1.4587515864774432,
+      "grad_norm": 0.1971125304698944,
+      "learning_rate": 0.0002,
+      "loss": 1.0648,
+      "step": 1580
+    },
+    {
+      "epoch": 1.467982000692281,
+      "grad_norm": 0.10692698508501053,
+      "learning_rate": 0.0002,
+      "loss": 1.2246,
+      "step": 1590
+    },
+    {
+      "epoch": 1.477212414907119,
+      "grad_norm": 0.0899726077914238,
+      "learning_rate": 0.0002,
+      "loss": 0.8801,
+      "step": 1600
+    },
+    {
+      "epoch": 1.486442829121957,
+      "grad_norm": 0.14624738693237305,
+      "learning_rate": 0.0002,
+      "loss": 1.268,
+      "step": 1610
+    },
+    {
+      "epoch": 1.4956732433367947,
+      "grad_norm": 0.07690660655498505,
+      "learning_rate": 0.0002,
+      "loss": 1.0909,
+      "step": 1620
+    },
+    {
+      "epoch": 1.5049036575516326,
+      "grad_norm": 0.18284741044044495,
+      "learning_rate": 0.0002,
+      "loss": 1.0576,
+      "step": 1630
+    },
+    {
+      "epoch": 1.5141340717664704,
+      "grad_norm": 0.09398135542869568,
+      "learning_rate": 0.0002,
+      "loss": 1.2297,
+      "step": 1640
+    },
+    {
+      "epoch": 1.5233644859813085,
+      "grad_norm": 0.08855324983596802,
+      "learning_rate": 0.0002,
+      "loss": 0.97,
+      "step": 1650
+    },
+    {
+      "epoch": 1.5325949001961463,
+      "grad_norm": 0.15404872596263885,
+      "learning_rate": 0.0002,
+      "loss": 1.3044,
+      "step": 1660
+    },
+    {
+      "epoch": 1.5418253144109841,
+      "grad_norm": 0.08170903474092484,
+      "learning_rate": 0.0002,
+      "loss": 1.0842,
+      "step": 1670
+    },
+    {
+      "epoch": 1.5510557286258222,
+      "grad_norm": 0.18026649951934814,
+      "learning_rate": 0.0002,
+      "loss": 1.0973,
+      "step": 1680
+    },
+    {
+      "epoch": 1.56028614284066,
+      "grad_norm": 0.09690876305103302,
+      "learning_rate": 0.0002,
+      "loss": 1.2005,
+      "step": 1690
+    },
+    {
+      "epoch": 1.5695165570554979,
+      "grad_norm": 0.09389860183000565,
+      "learning_rate": 0.0002,
+      "loss": 0.97,
+      "step": 1700
+    },
+    {
+      "epoch": 1.578746971270336,
+      "grad_norm": 0.15237314999103546,
+      "learning_rate": 0.0002,
+      "loss": 1.2745,
+      "step": 1710
+    },
+    {
+      "epoch": 1.5879773854851735,
+      "grad_norm": 0.09236445277929306,
+      "learning_rate": 0.0002,
+      "loss": 1.0959,
+      "step": 1720
+    },
+    {
+      "epoch": 1.5972077997000116,
+      "grad_norm": 0.193682461977005,
+      "learning_rate": 0.0002,
+      "loss": 1.1163,
+      "step": 1730
+    },
+    {
+      "epoch": 1.6064382139148494,
+      "grad_norm": 0.1000017300248146,
+      "learning_rate": 0.0002,
+      "loss": 1.2142,
+      "step": 1740
+    },
+    {
+      "epoch": 1.6156686281296873,
+      "grad_norm": 0.0881427600979805,
+      "learning_rate": 0.0002,
+      "loss": 0.9718,
+      "step": 1750
+    },
+    {
+      "epoch": 1.6248990423445253,
+      "grad_norm": 0.16513171792030334,
+      "learning_rate": 0.0002,
+      "loss": 1.2881,
+      "step": 1760
+    },
+    {
+      "epoch": 1.6341294565593631,
+      "grad_norm": 0.0824236124753952,
+      "learning_rate": 0.0002,
+      "loss": 1.0153,
+      "step": 1770
+    },
+    {
+      "epoch": 1.643359870774201,
+      "grad_norm": 0.18334250152111053,
+      "learning_rate": 0.0002,
+      "loss": 1.0999,
+      "step": 1780
+    },
+    {
+      "epoch": 1.652590284989039,
+      "grad_norm": 0.09759881347417831,
+      "learning_rate": 0.0002,
+      "loss": 1.2143,
+      "step": 1790
+    },
+    {
+      "epoch": 1.6618206992038767,
+      "grad_norm": 0.09835653752088547,
+      "learning_rate": 0.0002,
+      "loss": 0.9948,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6710511134187147,
+      "grad_norm": 0.1422744244337082,
+      "learning_rate": 0.0002,
+      "loss": 1.2753,
+      "step": 1810
+    },
+    {
+      "epoch": 1.6802815276335525,
+      "grad_norm": 0.0781414732336998,
+      "learning_rate": 0.0002,
+      "loss": 1.0262,
+      "step": 1820
+    },
+    {
+      "epoch": 1.6895119418483904,
+      "grad_norm": 0.2046748399734497,
+      "learning_rate": 0.0002,
+      "loss": 1.0542,
+      "step": 1830
+    },
+    {
+      "epoch": 1.6987423560632284,
+      "grad_norm": 0.09908697754144669,
+      "learning_rate": 0.0002,
+      "loss": 1.1942,
+      "step": 1840
+    },
+    {
+      "epoch": 1.7079727702780663,
+      "grad_norm": 0.09801312536001205,
+      "learning_rate": 0.0002,
+      "loss": 0.9554,
+      "step": 1850
+    },
+    {
+      "epoch": 1.717203184492904,
+      "grad_norm": 0.1688520461320877,
+      "learning_rate": 0.0002,
+      "loss": 1.2497,
+      "step": 1860
+    },
+    {
+      "epoch": 1.7264335987077422,
+      "grad_norm": 0.08527534455060959,
+      "learning_rate": 0.0002,
+      "loss": 1.0928,
+      "step": 1870
+    },
+    {
+      "epoch": 1.7356640129225798,
+      "grad_norm": 0.19082818925380707,
+      "learning_rate": 0.0002,
+      "loss": 1.0729,
+      "step": 1880
+    },
+    {
+      "epoch": 1.7448944271374178,
+      "grad_norm": 0.10551278293132782,
+      "learning_rate": 0.0002,
+      "loss": 1.2043,
+      "step": 1890
+    },
+    {
+      "epoch": 1.7541248413522557,
+      "grad_norm": 0.0871649906039238,
+      "learning_rate": 0.0002,
+      "loss": 0.9317,
+      "step": 1900
+    },
+    {
+      "epoch": 1.7633552555670935,
+      "grad_norm": 0.13540509343147278,
+      "learning_rate": 0.0002,
+      "loss": 1.2648,
+      "step": 1910
+    },
+    {
+      "epoch": 1.7725856697819315,
+      "grad_norm": 0.0853731706738472,
+      "learning_rate": 0.0002,
+      "loss": 1.0521,
+      "step": 1920
+    },
+    {
+      "epoch": 1.7818160839967694,
+      "grad_norm": 0.20368990302085876,
+      "learning_rate": 0.0002,
+      "loss": 1.1177,
+      "step": 1930
+    },
+    {
+      "epoch": 1.7910464982116072,
+      "grad_norm": 0.09358594566583633,
+      "learning_rate": 0.0002,
+      "loss": 1.1872,
+      "step": 1940
+    },
+    {
+      "epoch": 1.8002769124264453,
+      "grad_norm": 0.08881039917469025,
+      "learning_rate": 0.0002,
+      "loss": 0.9926,
+      "step": 1950
+    },
+    {
+      "epoch": 1.8095073266412829,
+      "grad_norm": 0.14714112877845764,
+      "learning_rate": 0.0002,
+      "loss": 1.2216,
+      "step": 1960
+    },
+    {
+      "epoch": 1.818737740856121,
+      "grad_norm": 0.08117840439081192,
+      "learning_rate": 0.0002,
+      "loss": 1.0313,
+      "step": 1970
+    },
+    {
+      "epoch": 1.8279681550709588,
+      "grad_norm": 0.2248132824897766,
+      "learning_rate": 0.0002,
+      "loss": 1.1024,
+      "step": 1980
+    },
+    {
+      "epoch": 1.8371985692857966,
+      "grad_norm": 0.11052978783845901,
+      "learning_rate": 0.0002,
+      "loss": 1.18,
+      "step": 1990
+    },
+    {
+      "epoch": 1.8464289835006347,
+      "grad_norm": 0.08844051510095596,
+      "learning_rate": 0.0002,
+      "loss": 0.99,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8556593977154725,
+      "grad_norm": 0.17737261950969696,
+      "learning_rate": 0.0002,
+      "loss": 1.3163,
+      "step": 2010
+    },
+    {
+      "epoch": 1.8648898119303103,
+      "grad_norm": 0.09116645157337189,
+      "learning_rate": 0.0002,
+      "loss": 1.0379,
+      "step": 2020
+    },
+    {
+      "epoch": 1.8741202261451484,
+      "grad_norm": 0.16292434930801392,
+      "learning_rate": 0.0002,
+      "loss": 1.0473,
+      "step": 2030
+    },
+    {
+      "epoch": 1.883350640359986,
+      "grad_norm": 0.09686768054962158,
+      "learning_rate": 0.0002,
+      "loss": 1.1816,
+      "step": 2040
+    },
+    {
+      "epoch": 1.892581054574824,
+      "grad_norm": 0.09110133349895477,
+      "learning_rate": 0.0002,
+      "loss": 0.9796,
+      "step": 2050
+    },
+    {
+      "epoch": 1.901811468789662,
+      "grad_norm": 0.1265280693769455,
+      "learning_rate": 0.0002,
+      "loss": 1.3238,
+      "step": 2060
+    },
+    {
+      "epoch": 1.9110418830044997,
+      "grad_norm": 0.07903092354536057,
+      "learning_rate": 0.0002,
+      "loss": 1.0891,
+      "step": 2070
+    },
+    {
+      "epoch": 1.9202722972193378,
+      "grad_norm": 0.17232394218444824,
+      "learning_rate": 0.0002,
+      "loss": 1.134,
+      "step": 2080
+    },
+    {
+      "epoch": 1.9295027114341756,
+      "grad_norm": 0.10463748872280121,
+      "learning_rate": 0.0002,
+      "loss": 1.219,
+      "step": 2090
+    },
+    {
+      "epoch": 1.9387331256490135,
+      "grad_norm": 0.09100574254989624,
+      "learning_rate": 0.0002,
+      "loss": 0.9918,
+      "step": 2100
+    },
+    {
+      "epoch": 1.9479635398638515,
+      "grad_norm": 0.16899889707565308,
+      "learning_rate": 0.0002,
+      "loss": 1.2809,
+      "step": 2110
+    },
+    {
+      "epoch": 1.9571939540786891,
+      "grad_norm": 0.08439228683710098,
+      "learning_rate": 0.0002,
+      "loss": 1.0566,
+      "step": 2120
+    },
+    {
+      "epoch": 1.9664243682935272,
+      "grad_norm": 0.1993444412946701,
+      "learning_rate": 0.0002,
+      "loss": 1.0572,
+      "step": 2130
+    },
+    {
+      "epoch": 1.975654782508365,
+      "grad_norm": 0.1062462106347084,
+      "learning_rate": 0.0002,
+      "loss": 1.2122,
+      "step": 2140
+    },
+    {
+      "epoch": 1.9848851967232028,
+      "grad_norm": 0.08482355624437332,
+      "learning_rate": 0.0002,
+      "loss": 0.9347,
+      "step": 2150
+    },
+    {
+      "epoch": 1.994115610938041,
+      "grad_norm": 0.13126371800899506,
+      "learning_rate": 0.0002,
+      "loss": 1.2604,
+      "step": 2160
+    },
+    {
+      "epoch": 2.0036921656859352,
+      "grad_norm": 0.09182780981063843,
+      "learning_rate": 0.0002,
+      "loss": 1.1431,
+      "step": 2170
+    },
+    {
+      "epoch": 2.012922579900773,
+      "grad_norm": 0.1420363485813141,
+      "learning_rate": 0.0002,
+      "loss": 0.8912,
+      "step": 2180
+    },
+    {
+      "epoch": 2.022152994115611,
+      "grad_norm": 0.1376965492963791,
+      "learning_rate": 0.0002,
+      "loss": 1.1347,
+      "step": 2190
+    },
+    {
+      "epoch": 2.031383408330449,
+      "grad_norm": 0.07587343454360962,
+      "learning_rate": 0.0002,
+      "loss": 0.7146,
+      "step": 2200
+    },
+    {
+      "epoch": 2.0406138225452866,
+      "grad_norm": 0.20123699307441711,
+      "learning_rate": 0.0002,
+      "loss": 1.1783,
+      "step": 2210
+    },
+    {
+      "epoch": 2.0498442367601246,
+      "grad_norm": 0.10732077807188034,
+      "learning_rate": 0.0002,
+      "loss": 0.8584,
+      "step": 2220
+    },
+    {
+      "epoch": 2.0590746509749627,
+      "grad_norm": 0.19853752851486206,
+      "learning_rate": 0.0002,
+      "loss": 0.9121,
+      "step": 2230
+    },
+    {
+      "epoch": 2.0683050651898003,
+      "grad_norm": 0.13605843484401703,
+      "learning_rate": 0.0002,
+      "loss": 1.1323,
+      "step": 2240
+    },
+    {
+      "epoch": 2.0775354794046383,
+      "grad_norm": 0.07920292764902115,
+      "learning_rate": 0.0002,
+      "loss": 0.6811,
+      "step": 2250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.194849501524787e+17,
+  "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 sha256:4b3a33b28a63ef6c4eea67adc79f1ff24eadbb3100f3e0876901b03d61dc4d38
+size 7992