huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/bruce-springsteen
+tags:
+- huggingartists
+- lyrics
+- lm-head
+- causal-lm
+widget:
+- text: "I am"
+---
+
+<div class="inline-flex flex-col" style="line-height: 1.5;">
+    <div class="flex">
+        <div
+			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/6dfe4b89b895b331f09c6b136a0705e5.807x807x1.jpg&#39;)">
+        </div>
+    </div>
+    <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
+    <div style="text-align: center; font-size: 16px; font-weight: 800">Bruce Springsteen</div>
+    <a href="https://genius.com/artists/bruce-springsteen">
+    	<div style="text-align: center; font-size: 14px;">@bruce-springsteen</div>
+    </a>
+</div>
+
+I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).
+
+Create your own bot based on your favorite artist with [the demo](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb)!
+
+## How does it work?
+
+To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).
+
+## Training data
+
+The model was trained on lyrics from Bruce Springsteen.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/bruce-springsteen).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/bruce-springsteen")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/28yd4w57/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
+
+## Training procedure
+
+The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Bruce Springsteen's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/6qq7wbab) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/6qq7wbab/artifacts) is logged and versioned.
+
+## How to use
+
+You can use this model directly with a pipeline for text generation:
+
+```python
+from transformers import pipeline
+generator = pipeline('text-generation',
+                     model='huggingartists/bruce-springsteen')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/bruce-springsteen")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/bruce-springsteen")
+```
+
+## Limitations and bias
+
+The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
+
+In addition, the data present in the user's tweets further affects the text generated by the model.
+
+## About
+
+*Built by Aleksey Korshuk*
+
+[![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
+
+[![Follow](https://img.shields.io/twitter/follow/alekseykorshuk?style=social)](https://twitter.com/intent/follow?screen_name=alekseykorshuk)
+
+[![Follow](https://img.shields.io/badge/dynamic/json?color=blue&label=Telegram%20Channel&query=%24.result&url=https%3A%2F%2Fapi.telegram.org%2Fbot1929545866%3AAAFGhV-KKnegEcLiyYJxsc4zV6C-bdPEBtQ%2FgetChatMemberCount%3Fchat_id%3D-1001253621662&style=social&logo=telegram)](https://t.me/joinchat/_CQ04KjcJ-4yZTky)
+
+For more details, visit the project repository.
+
+[![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 200,
+      "min_length": 100,
+      "temperature": 1.0,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 2.562410593032837, "eval_runtime": 8.7547, "eval_samples_per_second": 21.131, "eval_steps_per_second": 2.741, "epoch": 20.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d10dc81d9b50d874f93e8e68c4a2e4a00b0b2f3e187fe376625f32002ad0a67
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30ee3bcbb932cf5c052ba491db6f76b87cd13d2dc6bc7f12181c952ce31414c
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c4a675b660cc1ef7e9771491c8952638c54464549303776f270b68e4d6d468
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec33686a6d52a730b75fcda652fb2671b551225d74f8c0fab5e5e5f2e22ede81
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cd62b0c7892b777db0b867c23158b58538d7056ca9b90f535f64528ae00eb8
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -0,0 +1,1212 @@
+{
+  "best_metric": 2.562410593032837,
+  "best_model_checkpoint": "output/bruce-springsteen/checkpoint-952",
+  "epoch": 7.0,
+  "global_step": 952,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00013674294000958298,
+      "loss": 3.78,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013537785052914354,
+      "loss": 3.4816,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013312292187310875,
+      "loss": 3.3352,
+      "step": 15
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001300082017869573,
+      "loss": 3.354,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012607519505006897,
+      "loss": 3.4425,
+      "step": 25
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001213763104094255,
+      "loss": 3.4175,
+      "step": 30
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011597416221397217,
+      "loss": 3.1509,
+      "step": 35
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000109940736055617,
+      "loss": 3.3062,
+      "step": 40
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00010335642953500487,
+      "loss": 3.2804,
+      "step": 45
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.630898093421199e-05,
+      "loss": 2.9747,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.889230007218717e-05,
+      "loss": 3.4039,
+      "step": 55
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.120521692221673e-05,
+      "loss": 3.3281,
+      "step": 60
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.335016466654156e-05,
+      "loss": 3.1832,
+      "step": 65
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.543181473690228e-05,
+      "loss": 3.0942,
+      "step": 70
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.7555682029595066e-05,
+      "loss": 3.2014,
+      "step": 75
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.982671888105512e-05,
+      "loss": 2.9804,
+      "step": 80
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2347916539754844e-05,
+      "loss": 2.9935,
+      "step": 85
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.5218932770313667e-05,
+      "loss": 3.0304,
+      "step": 90
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.8534763877493803e-05,
+      "loss": 3.0939,
+      "step": 95
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.2384478845846175e-05,
+      "loss": 3.2979,
+      "step": 100
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.6850032463056755e-05,
+      "loss": 3.1302,
+      "step": 105
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.200517324255647e-05,
+      "loss": 2.9578,
+      "step": 110
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.914460697724135e-06,
+      "loss": 3.1475,
+      "step": 115
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.6324050628611986e-06,
+      "loss": 3.0137,
+      "step": 120
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.202740924469675e-06,
+      "loss": 2.9044,
+      "step": 125
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.578444419609313e-07,
+      "loss": 3.0162,
+      "step": 130
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.8301923541685384e-08,
+      "loss": 3.0899,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.968862771987915,
+      "eval_runtime": 8.6913,
+      "eval_samples_per_second": 21.286,
+      "eval_steps_per_second": 2.761,
+      "step": 136
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.926355061606279e-07,
+      "loss": 3.099,
+      "step": 140
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4771895949302213e-06,
+      "loss": 2.9362,
+      "step": 145
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.55617957525975e-06,
+      "loss": 2.8939,
+      "step": 150
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.5019021485927275e-06,
+      "loss": 2.8441,
+      "step": 155
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.0275104488948473e-05,
+      "loss": 2.7526,
+      "step": 160
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4825507301122139e-05,
+      "loss": 3.0343,
+      "step": 165
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.009247481060283e-05,
+      "loss": 2.8204,
+      "step": 170
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.600582275734942e-05,
+      "loss": 2.8892,
+      "step": 175
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.2486753626613365e-05,
+      "loss": 3.0241,
+      "step": 180
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.9448906654517264e-05,
+      "loss": 2.9835,
+      "step": 185
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.679950861668151e-05,
+      "loss": 2.8951,
+      "step": 190
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.444061006522326e-05,
+      "loss": 2.9979,
+      "step": 195
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 6.227039054081748e-05,
+      "loss": 2.8296,
+      "step": 200
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.018451536739584e-05,
+      "loss": 2.9173,
+      "step": 205
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.807752594969911e-05,
+      "loss": 2.821,
+      "step": 210
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.58442450474616e-05,
+      "loss": 2.8064,
+      "step": 215
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.338117830043867e-05,
+      "loss": 2.8823,
+      "step": 220
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00010058789332844422,
+      "loss": 2.9615,
+      "step": 225
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00010736835802938978,
+      "loss": 2.8424,
+      "step": 230
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0001136322202420147,
+      "loss": 2.9272,
+      "step": 235
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011929601172133719,
+      "loss": 2.7972,
+      "step": 240
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00012428426038341373,
+      "loss": 2.6514,
+      "step": 245
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00012853049599834097,
+      "loss": 2.966,
+      "step": 250
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013197813593027427,
+      "loss": 3.0045,
+      "step": 255
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00013458123912165538,
+      "loss": 2.6775,
+      "step": 260
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00013630511827453364,
+      "loss": 2.6298,
+      "step": 265
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00013712680207144277,
+      "loss": 2.6688,
+      "step": 270
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.839606523513794,
+      "eval_runtime": 8.7347,
+      "eval_samples_per_second": 21.18,
+      "eval_steps_per_second": 2.748,
+      "step": 272
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.00013703534127657097,
+      "loss": 2.81,
+      "step": 275
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00013603195463831566,
+      "loss": 2.4255,
+      "step": 280
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00013413001264901686,
+      "loss": 2.5457,
+      "step": 285
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.00013135485937827823,
+      "loss": 2.3628,
+      "step": 290
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.0001277434747540102,
+      "loss": 2.6079,
+      "step": 295
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.0001233439817914244,
+      "loss": 2.6005,
+      "step": 300
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.00011821500533633198,
+      "loss": 2.3133,
+      "step": 305
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00011242489086772457,
+      "loss": 2.691,
+      "step": 310
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.00010605079376937858,
+      "loss": 2.4907,
+      "step": 315
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 9.917765120627052e-05,
+      "loss": 2.614,
+      "step": 320
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 9.189705030592299e-05,
+      "loss": 2.5114,
+      "step": 325
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 8.430600772657927e-05,
+      "loss": 2.3745,
+      "step": 330
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.650567687490305e-05,
+      "loss": 2.6594,
+      "step": 335
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.860000000000001e-05,
+      "loss": 2.6282,
+      "step": 340
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 6.0694323125097e-05,
+      "loss": 2.4007,
+      "step": 345
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 5.289399227342078e-05,
+      "loss": 2.61,
+      "step": 350
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.530294969407699e-05,
+      "loss": 2.4243,
+      "step": 355
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.8022348793729525e-05,
+      "loss": 2.6903,
+      "step": 360
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 3.11492062306214e-05,
+      "loss": 2.4129,
+      "step": 365
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.4775109132275458e-05,
+      "loss": 2.5884,
+      "step": 370
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.8984994663667992e-05,
+      "loss": 2.5451,
+      "step": 375
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.3856018208575617e-05,
+      "loss": 2.3267,
+      "step": 380
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 9.45652524598977e-06,
+      "loss": 2.6289,
+      "step": 385
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.845140621721773e-06,
+      "loss": 2.6761,
+      "step": 390
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 3.069987350983113e-06,
+      "loss": 2.548,
+      "step": 395
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.1680453616843376e-06,
+      "loss": 2.2025,
+      "step": 400
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.646587234290122e-07,
+      "loss": 2.4811,
+      "step": 405
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.697875499725342,
+      "eval_runtime": 8.7457,
+      "eval_samples_per_second": 21.153,
+      "eval_steps_per_second": 2.744,
+      "step": 408
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 7.319792855724439e-08,
+      "loss": 2.3981,
+      "step": 410
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 8.948817254663383e-07,
+      "loss": 2.4304,
+      "step": 415
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 2.618760878344606e-06,
+      "loss": 2.3479,
+      "step": 420
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 5.22186406972573e-06,
+      "loss": 2.2508,
+      "step": 425
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 8.669504001659e-06,
+      "loss": 2.2017,
+      "step": 430
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 1.2915739616586271e-05,
+      "loss": 2.3098,
+      "step": 435
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.7903988278662747e-05,
+      "loss": 2.325,
+      "step": 440
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 2.3567779757985262e-05,
+      "loss": 2.331,
+      "step": 445
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 2.983164197061009e-05,
+      "loss": 2.2929,
+      "step": 450
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.6612106671555745e-05,
+      "loss": 2.2436,
+      "step": 455
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 4.381882169956124e-05,
+      "loss": 2.4438,
+      "step": 460
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 5.135575495253831e-05,
+      "loss": 2.1411,
+      "step": 465
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 5.9122474050300846e-05,
+      "loss": 2.2244,
+      "step": 470
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 6.701548463260412e-05,
+      "loss": 2.2979,
+      "step": 475
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 7.492960945918241e-05,
+      "loss": 2.188,
+      "step": 480
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 8.275938993477677e-05,
+      "loss": 2.0263,
+      "step": 485
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 9.04004913833184e-05,
+      "loss": 2.4795,
+      "step": 490
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 9.77510933454827e-05,
+      "loss": 2.287,
+      "step": 495
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.0001047132463733866,
+      "loss": 2.2963,
+      "step": 500
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.0001111941772426506,
+      "loss": 2.2048,
+      "step": 505
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.0001171075251893971,
+      "loss": 2.416,
+      "step": 510
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 0.00012237449269887778,
+      "loss": 2.3413,
+      "step": 515
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 0.0001269248955110515,
+      "loss": 2.3194,
+      "step": 520
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.00013069809785140726,
+      "loss": 2.3466,
+      "step": 525
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.00013364382042474026,
+      "loss": 2.5401,
+      "step": 530
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.00013572281040506975,
+      "loss": 2.2886,
+      "step": 535
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.00013690736449383938,
+      "loss": 2.4436,
+      "step": 540
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.6544318199157715,
+      "eval_runtime": 8.682,
+      "eval_samples_per_second": 21.308,
+      "eval_steps_per_second": 2.764,
+      "step": 544
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 0.00013718169807645832,
+      "loss": 2.2455,
+      "step": 545
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 0.00013654215555803907,
+      "loss": 2.2189,
+      "step": 550
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00013499725907553032,
+      "loss": 2.0464,
+      "step": 555
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 0.00013256759493713885,
+      "loss": 2.0255,
+      "step": 560
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 0.00012928553930227594,
+      "loss": 1.9056,
+      "step": 565
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 0.0001251948267574435,
+      "loss": 2.1303,
+      "step": 570
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 0.00012034996753694334,
+      "loss": 2.1789,
+      "step": 575
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 0.00011481552115415383,
+      "loss": 2.1376,
+      "step": 580
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.00010866523612250621,
+      "loss": 2.1059,
+      "step": 585
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 0.00010198106722968643,
+      "loss": 2.3021,
+      "step": 590
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 9.485208346024522e-05,
+      "loss": 2.096,
+      "step": 595
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 8.73732811189448e-05,
+      "loss": 2.1222,
+      "step": 600
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 7.964431797040506e-05,
+      "loss": 2.1479,
+      "step": 605
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 7.176818526309773e-05,
+      "loss": 2.112,
+      "step": 610
+    },
+    {
+      "epoch": 4.52,
+      "learning_rate": 6.384983533345843e-05,
+      "loss": 1.9858,
+      "step": 615
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 5.599478307778335e-05,
+      "loss": 2.0653,
+      "step": 620
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 4.83076999278129e-05,
+      "loss": 2.3118,
+      "step": 625
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 4.089101906578792e-05,
+      "loss": 2.1364,
+      "step": 630
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 3.3843570464995244e-05,
+      "loss": 1.9424,
+      "step": 635
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 2.7259263944382997e-05,
+      "loss": 2.0466,
+      "step": 640
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 2.12258377860279e-05,
+      "loss": 2.2663,
+      "step": 645
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 1.5823689590574545e-05,
+      "loss": 2.1516,
+      "step": 650
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 1.112480494993106e-05,
+      "loss": 2.0252,
+      "step": 655
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 7.191798213042784e-06,
+      "loss": 2.1763,
+      "step": 660
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 4.077078126891299e-06,
+      "loss": 1.8925,
+      "step": 665
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 1.822149470856462e-06,
+      "loss": 2.0655,
+      "step": 670
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 4.570599904170397e-07,
+      "loss": 2.0477,
+      "step": 675
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 1.8207,
+      "step": 680
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.601478338241577,
+      "eval_runtime": 8.6457,
+      "eval_samples_per_second": 21.398,
+      "eval_steps_per_second": 2.776,
+      "step": 680
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 4.570599904170321e-07,
+      "loss": 1.6645,
+      "step": 685
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 1.8221494708564468e-06,
+      "loss": 1.9202,
+      "step": 690
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 4.0770781268912235e-06,
+      "loss": 1.761,
+      "step": 695
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 7.191798213042746e-06,
+      "loss": 1.877,
+      "step": 700
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 1.1124804949931014e-05,
+      "loss": 1.7914,
+      "step": 705
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 1.5823689590574568e-05,
+      "loss": 1.9094,
+      "step": 710
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 2.122583778602784e-05,
+      "loss": 1.8799,
+      "step": 715
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 2.7259263944382926e-05,
+      "loss": 1.625,
+      "step": 720
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 3.384357046499517e-05,
+      "loss": 1.673,
+      "step": 725
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 4.089101906578795e-05,
+      "loss": 1.7023,
+      "step": 730
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 4.8307699927812706e-05,
+      "loss": 1.9625,
+      "step": 735
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 5.599478307778327e-05,
+      "loss": 1.8095,
+      "step": 740
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 6.384983533345835e-05,
+      "loss": 2.0594,
+      "step": 745
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 7.176818526309777e-05,
+      "loss": 1.9059,
+      "step": 750
+    },
+    {
+      "epoch": 5.55,
+      "learning_rate": 7.964431797040486e-05,
+      "loss": 1.8821,
+      "step": 755
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 8.737328111894472e-05,
+      "loss": 2.187,
+      "step": 760
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 9.485208346024515e-05,
+      "loss": 2.0599,
+      "step": 765
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 0.00010198106722968646,
+      "loss": 1.9395,
+      "step": 770
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 0.00010866523612250605,
+      "loss": 1.8671,
+      "step": 775
+    },
+    {
+      "epoch": 5.74,
+      "learning_rate": 0.00011481552115415377,
+      "loss": 2.1133,
+      "step": 780
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 0.0001203499675369433,
+      "loss": 1.9346,
+      "step": 785
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 0.00012519482675744353,
+      "loss": 2.0467,
+      "step": 790
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 0.00012928553930227583,
+      "loss": 1.8789,
+      "step": 795
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 0.00013256759493713883,
+      "loss": 1.8932,
+      "step": 800
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 0.0001349972590755303,
+      "loss": 1.8909,
+      "step": 805
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 0.00013654215555803907,
+      "loss": 2.1403,
+      "step": 810
+    },
+    {
+      "epoch": 5.99,
+      "learning_rate": 0.00013718169807645832,
+      "loss": 1.8803,
+      "step": 815
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.6078295707702637,
+      "eval_runtime": 8.6964,
+      "eval_samples_per_second": 21.273,
+      "eval_steps_per_second": 2.76,
+      "step": 816
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.00013690736449383938,
+      "loss": 1.7367,
+      "step": 820
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00013572281040506978,
+      "loss": 1.8923,
+      "step": 825
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 0.0001336438204247403,
+      "loss": 1.7941,
+      "step": 830
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 0.00013069809785140734,
+      "loss": 1.733,
+      "step": 835
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 0.00012692489551105156,
+      "loss": 1.6456,
+      "step": 840
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 0.00012237449269887794,
+      "loss": 1.7817,
+      "step": 845
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 0.00011710752518939715,
+      "loss": 1.8526,
+      "step": 850
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.00011119417724265067,
+      "loss": 1.6085,
+      "step": 855
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 0.00010471324637338676,
+      "loss": 1.7472,
+      "step": 860
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 9.775109334548278e-05,
+      "loss": 1.7182,
+      "step": 865
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 9.040049138331835e-05,
+      "loss": 1.7503,
+      "step": 870
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 8.275938993477671e-05,
+      "loss": 1.7068,
+      "step": 875
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 7.492960945918261e-05,
+      "loss": 1.6923,
+      "step": 880
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 6.701548463260408e-05,
+      "loss": 1.6817,
+      "step": 885
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 5.912247405030094e-05,
+      "loss": 1.6556,
+      "step": 890
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 5.135575495253826e-05,
+      "loss": 1.7865,
+      "step": 895
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 4.3818821699561535e-05,
+      "loss": 1.9308,
+      "step": 900
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 3.661210667155582e-05,
+      "loss": 1.7407,
+      "step": 905
+    },
+    {
+      "epoch": 6.69,
+      "learning_rate": 2.9831641970610168e-05,
+      "loss": 1.5858,
+      "step": 910
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 2.3567779757985323e-05,
+      "loss": 1.6857,
+      "step": 915
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 1.7903988278662893e-05,
+      "loss": 1.6211,
+      "step": 920
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 1.2915739616586247e-05,
+      "loss": 1.6546,
+      "step": 925
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 8.669504001659107e-06,
+      "loss": 1.9644,
+      "step": 930
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 5.221864069725715e-06,
+      "loss": 1.6495,
+      "step": 935
+    },
+    {
+      "epoch": 6.91,
+      "learning_rate": 2.618760878344629e-06,
+      "loss": 1.7503,
+      "step": 940
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 8.948817254663764e-07,
+      "loss": 1.9784,
+      "step": 945
+    },
+    {
+      "epoch": 6.99,
+      "learning_rate": 7.3197928557252e-08,
+      "loss": 1.7477,
+      "step": 950
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.562410593032837,
+      "eval_runtime": 8.7008,
+      "eval_samples_per_second": 21.262,
+      "eval_steps_per_second": 2.758,
+      "step": 952
+    }
+  ],
+  "max_steps": 2720,
+  "num_train_epochs": 20,
+  "total_flos": 991341969408000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c870882292272d33b62b9ef881bad4f77a261fd8fb28315858dfc9592f2134
+size 2671