huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/slava-kpss
+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/e63e3a804916ed71bf2941ac4e190063.847x847x1.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">Слава КПСС (Slava KPSS)</div>
+    <a href="https://genius.com/artists/slava-kpss">
+    	<div style="text-align: center; font-size: 14px;">@slava-kpss</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 Слава КПСС (Slava KPSS).
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/slava-kpss).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/slava-kpss")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/foqrsz9e/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 Слава КПСС (Slava KPSS)'s lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1w16q2jl) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1w16q2jl/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/slava-kpss')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/slava-kpss")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/slava-kpss")
+```
+
+## 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": "4.10.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.7264798879623413, "eval_runtime": 80.0703, "eval_samples_per_second": 20.482, "eval_steps_per_second": 2.56, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337deda3e932cb8b9f9f45178fc4d42a4910182f8b2421baf2b41f81f8b5ed78
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b98963ca82fe7af24587df78468bdd55174ccee367ffeb555b4c0f8139cb2bc
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b79b39a5680447ab02ef00986c994924e2e55dbc55860448f00a8a0e01a1b45
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8613dacebf19a39d9111a86da44f69693a925419e314a219b17a1de0c3c2ef8f
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa1d50b5048030f9eea3f4e31d95b58aad9c69608bc50ec31c69b287312d0da
+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 +1,1140 @@
+{
+  "best_metric": 1.7264798879623413,
+  "best_model_checkpoint": "output/slava-kpss/checkpoint-933",
+  "epoch": 1.0,
+  "global_step": 933,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001371902778945302,
+      "loss": 2.663,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013716111433378645,
+      "loss": 2.4309,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013711251758398495,
+      "loss": 2.2912,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001370445014195492,
+      "loss": 2.3384,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013695708511920587,
+      "loss": 2.2697,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001368502934605203,
+      "loss": 2.2379,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00013672415671287354,
+      "loss": 2.1656,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00013657871062888258,
+      "loss": 2.1628,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00013641399643426666,
+      "loss": 2.1289,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.000136230060816162,
+      "loss": 2.09,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00013602695590988865,
+      "loss": 2.0049,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001358047392841732,
+      "loss": 2.2023,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013556347392483116,
+      "loss": 2.1472,
+      "step": 65
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013530322821691406,
+      "loss": 2.0605,
+      "step": 70
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013502407592532636,
+      "loss": 2.1713,
+      "step": 75
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013472609617391705,
+      "loss": 2.0815,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001344093734230526,
+      "loss": 1.998,
+      "step": 85
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013407399744567734,
+      "loss": 1.9623,
+      "step": 90
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013372006330186772,
+      "loss": 2.0139,
+      "step": 95
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013334767131188837,
+      "loss": 2.0258,
+      "step": 100
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013295692702775685,
+      "loss": 1.9965,
+      "step": 105
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013254794120332568,
+      "loss": 2.0578,
+      "step": 110
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013212082976288994,
+      "loss": 1.9713,
+      "step": 115
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00013167571376832926,
+      "loss": 2.0398,
+      "step": 120
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00013121271938479367,
+      "loss": 1.9906,
+      "step": 125
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00013073197784494285,
+      "loss": 1.9652,
+      "step": 130
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001302336254117493,
+      "loss": 1.9658,
+      "step": 135
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00012971780333987523,
+      "loss": 2.0634,
+      "step": 140
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012918465783563518,
+      "loss": 2.0384,
+      "step": 145
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012863434001555456,
+      "loss": 1.9783,
+      "step": 150
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00012806700586353683,
+      "loss": 2.0149,
+      "step": 155
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00012748281618665092,
+      "loss": 1.9433,
+      "step": 160
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012688193656955137,
+      "loss": 2.0019,
+      "step": 165
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001262645373275447,
+      "loss": 2.036,
+      "step": 170
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001256307934583145,
+      "loss": 1.9862,
+      "step": 175
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012498088459231957,
+      "loss": 1.9842,
+      "step": 180
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00012431499494187896,
+      "loss": 2.0212,
+      "step": 185
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000123633313248958,
+      "loss": 1.8205,
+      "step": 190
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012293603273167084,
+      "loss": 2.0015,
+      "step": 195
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012222335102951405,
+      "loss": 1.8653,
+      "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00012149547014734692,
+      "loss": 2.0522,
+      "step": 205
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00012075259639813464,
+      "loss": 1.8885,
+      "step": 210
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011999494034447026,
+      "loss": 1.8864,
+      "step": 215
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011922271673889206,
+      "loss": 1.9415,
+      "step": 220
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011843614446301341,
+      "loss": 1.9542,
+      "step": 225
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011763544646548234,
+      "loss": 1.8528,
+      "step": 230
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011682084969878809,
+      "loss": 1.8431,
+      "step": 235
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011599258505493302,
+      "loss": 1.9018,
+      "step": 240
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001151508872999878,
+      "loss": 1.8971,
+      "step": 245
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011429599500754859,
+      "loss": 1.9842,
+      "step": 250
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011342815049111488,
+      "loss": 1.8397,
+      "step": 255
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011254759973540735,
+      "loss": 1.854,
+      "step": 260
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001116545923266452,
+      "loss": 1.9264,
+      "step": 265
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00011074938138180258,
+      "loss": 1.833,
+      "step": 270
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00010983222347686431,
+      "loss": 1.8783,
+      "step": 275
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010890337857410102,
+      "loss": 1.8777,
+      "step": 280
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010796310994838476,
+      "loss": 1.8851,
+      "step": 285
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010701168411256533,
+      "loss": 1.8735,
+      "step": 290
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001060493707419291,
+      "loss": 1.9696,
+      "step": 295
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00010507644259776136,
+      "loss": 1.8878,
+      "step": 300
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00010409317545003389,
+      "loss": 1.8279,
+      "step": 305
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001030998479992398,
+      "loss": 1.9672,
+      "step": 310
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010209674179739785,
+      "loss": 1.889,
+      "step": 315
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010108414116824834,
+      "loss": 1.8617,
+      "step": 320
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00010006233312666341,
+      "loss": 1.9077,
+      "step": 325
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.90316072972947e-05,
+      "loss": 1.8912,
+      "step": 330
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.79922558324811e-05,
+      "loss": 1.7622,
+      "step": 335
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.694457332944009e-05,
+      "loss": 1.8778,
+      "step": 340
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.588885674676624e-05,
+      "loss": 1.8761,
+      "step": 345
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.482540532026027e-05,
+      "loss": 1.8225,
+      "step": 350
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.37545204781125e-05,
+      "loss": 1.7817,
+      "step": 355
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.26765057554653e-05,
+      "loss": 1.7633,
+      "step": 360
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.159166670837789e-05,
+      "loss": 1.8406,
+      "step": 365
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.05003108272186e-05,
+      "loss": 1.9374,
+      "step": 370
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.940274744950875e-05,
+      "loss": 1.8444,
+      "step": 375
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.829928767224302e-05,
+      "loss": 1.8098,
+      "step": 380
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.71902442637111e-05,
+      "loss": 1.822,
+      "step": 385
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.607593157484563e-05,
+      "loss": 1.87,
+      "step": 390
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.495666545012144e-05,
+      "loss": 1.8821,
+      "step": 395
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.383276313803162e-05,
+      "loss": 1.8619,
+      "step": 400
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.270454320116558e-05,
+      "loss": 1.896,
+      "step": 405
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.157232542591454e-05,
+      "loss": 1.776,
+      "step": 410
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.043643073183026e-05,
+      "loss": 1.8886,
+      "step": 415
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.92971810806626e-05,
+      "loss": 1.8725,
+      "step": 420
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.815489938510145e-05,
+      "loss": 1.8305,
+      "step": 425
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.700990941724947e-05,
+      "loss": 1.8383,
+      "step": 430
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.586253571685095e-05,
+      "loss": 1.872,
+      "step": 435
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.471310349930326e-05,
+      "loss": 1.8617,
+      "step": 440
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.356193856347655e-05,
+      "loss": 1.8118,
+      "step": 445
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.24093671993686e-05,
+      "loss": 1.8363,
+      "step": 450
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.125571609561963e-05,
+      "loss": 1.7498,
+      "step": 455
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.010131224691501e-05,
+      "loss": 1.8902,
+      "step": 460
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.894648286130055e-05,
+      "loss": 1.9075,
+      "step": 465
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.779155526743765e-05,
+      "loss": 1.8081,
+      "step": 470
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.66368568218242e-05,
+      "loss": 1.8239,
+      "step": 475
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.548271481600758e-05,
+      "loss": 1.8584,
+      "step": 480
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.432945638381598e-05,
+      "loss": 1.9037,
+      "step": 485
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.317740840863456e-05,
+      "loss": 1.7551,
+      "step": 490
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.202689743075261e-05,
+      "loss": 1.8329,
+      "step": 495
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 6.0878249554807756e-05,
+      "loss": 1.7776,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.9731790357353845e-05,
+      "loss": 1.8987,
+      "step": 505
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.8587844794578496e-05,
+      "loss": 1.6097,
+      "step": 510
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.744673711019635e-05,
+      "loss": 1.8081,
+      "step": 515
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.630879074354446e-05,
+      "loss": 1.8023,
+      "step": 520
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.517432823790546e-05,
+      "loss": 1.709,
+      "step": 525
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.404367114908498e-05,
+      "loss": 1.7632,
+      "step": 530
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.291713995426862e-05,
+      "loss": 1.796,
+      "step": 535
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.179505396118502e-05,
+      "loss": 1.7405,
+      "step": 540
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.067773121760007e-05,
+      "loss": 1.8264,
+      "step": 545
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.9565488421168504e-05,
+      "loss": 1.8083,
+      "step": 550
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.8458640829668e-05,
+      "loss": 1.7488,
+      "step": 555
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.735750217164156e-05,
+      "loss": 1.8385,
+      "step": 560
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.6262384557473104e-05,
+      "loss": 1.8445,
+      "step": 565
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.517359839092207e-05,
+      "loss": 1.7808,
+      "step": 570
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.409145228114133e-05,
+      "loss": 1.7932,
+      "step": 575
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.3016252955204197e-05,
+      "loss": 1.7931,
+      "step": 580
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.1948305171164515e-05,
+      "loss": 1.7508,
+      "step": 585
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.08879116316751e-05,
+      "loss": 1.7877,
+      "step": 590
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.98353728981888e-05,
+      "loss": 1.8233,
+      "step": 595
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.879098730576618e-05,
+      "loss": 1.8181,
+      "step": 600
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.7755050878514536e-05,
+      "loss": 1.6906,
+      "step": 605
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.672785724568185e-05,
+      "loss": 1.7465,
+      "step": 610
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.570969755842952e-05,
+      "loss": 1.7276,
+      "step": 615
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.4700860407307565e-05,
+      "loss": 1.7561,
+      "step": 620
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.3701631740455454e-05,
+      "loss": 1.8063,
+      "step": 625
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.271229478255218e-05,
+      "loss": 1.6319,
+      "step": 630
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.173312995453793e-05,
+      "loss": 1.7234,
+      "step": 635
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.07644147941308e-05,
+      "loss": 1.811,
+      "step": 640
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.9806423877160492e-05,
+      "loss": 1.8344,
+      "step": 645
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.8859428739741754e-05,
+      "loss": 1.7602,
+      "step": 650
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.7923697801309092e-05,
+      "loss": 1.8365,
+      "step": 655
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.699949628853528e-05,
+      "loss": 1.7506,
+      "step": 660
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.60870861601545e-05,
+      "loss": 1.7098,
+      "step": 665
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.518672603271192e-05,
+      "loss": 1.8215,
+      "step": 670
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.429867110726057e-05,
+      "loss": 1.8035,
+      "step": 675
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.3423173097026407e-05,
+      "loss": 1.7455,
+      "step": 680
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.25604801560617e-05,
+      "loss": 1.8008,
+      "step": 685
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.1710836808907555e-05,
+      "loss": 1.7584,
+      "step": 690
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.0874483881285084e-05,
+      "loss": 1.7836,
+      "step": 695
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.0051658431834844e-05,
+      "loss": 1.7353,
+      "step": 700
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.924259368492425e-05,
+      "loss": 1.7518,
+      "step": 705
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.844751896454173e-05,
+      "loss": 1.7968,
+      "step": 710
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.766665962929623e-05,
+      "loss": 1.751,
+      "step": 715
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.6900237008540944e-05,
+      "loss": 1.7056,
+      "step": 720
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6148468339638933e-05,
+      "loss": 1.7457,
+      "step": 725
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.5411566706388707e-05,
+      "loss": 1.7712,
+      "step": 730
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4689740978626948e-05,
+      "loss": 1.7609,
+      "step": 735
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3983195753025887e-05,
+      "loss": 1.7358,
+      "step": 740
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3292131295101604e-05,
+      "loss": 1.8011,
+      "step": 745
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2616743482450217e-05,
+      "loss": 1.7338,
+      "step": 750
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.1957223749227626e-05,
+      "loss": 1.7185,
+      "step": 755
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.1313759031888791e-05,
+      "loss": 1.7987,
+      "step": 760
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0686531716201893e-05,
+      "loss": 1.7855,
+      "step": 765
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.0075719585552289e-05,
+      "loss": 1.755,
+      "step": 770
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.481495770550924e-06,
+      "loss": 1.7749,
+      "step": 775
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.90402869996171e-06,
+      "loss": 1.7306,
+      "step": 780
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.343482052961487e-06,
+      "loss": 1.7385,
+      "step": 785
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.800014712746244e-06,
+      "loss": 1.8382,
+      "step": 790
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.273780721496786e-06,
+      "loss": 1.7857,
+      "step": 795
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.7649292367164704e-06,
+      "loss": 1.7224,
+      "step": 800
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.2736044889534784e-06,
+      "loss": 1.7514,
+      "step": 805
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.799945740919712e-06,
+      "loss": 1.7887,
+      "step": 810
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.344087248017646e-06,
+      "loss": 1.7605,
+      "step": 815
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.906158220286551e-06,
+      "loss": 1.7712,
+      "step": 820
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.486282785778806e-06,
+      "loss": 1.7334,
+      "step": 825
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.084579955376559e-06,
+      "loss": 1.749,
+      "step": 830
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.7011635890589766e-06,
+      "loss": 1.7343,
+      "step": 835
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.3361423636293224e-06,
+      "loss": 1.7663,
+      "step": 840
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.989619741911281e-06,
+      "loss": 1.759,
+      "step": 845
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.6616939434230985e-06,
+      "loss": 1.7025,
+      "step": 850
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.352457916537921e-06,
+      "loss": 1.7564,
+      "step": 855
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.0619993121382247e-06,
+      "loss": 1.8452,
+      "step": 860
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.7904004587717305e-06,
+      "loss": 1.7741,
+      "step": 865
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5377383393159132e-06,
+      "loss": 1.7832,
+      "step": 870
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3040845691577635e-06,
+      "loss": 1.8237,
+      "step": 875
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0895053758948607e-06,
+      "loss": 1.7458,
+      "step": 880
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 8.940615805635918e-07,
+      "loss": 1.7009,
+      "step": 885
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.178085803998752e-07,
+      "loss": 1.725,
+      "step": 890
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.607963331371593e-07,
+      "loss": 1.7469,
+      "step": 895
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.2306934284621745e-07,
+      "loss": 1.6719,
+      "step": 900
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.04666647320803e-07,
+      "loss": 1.8424,
+      "step": 905
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.0562180701263117e-07,
+      "loss": 1.7483,
+      "step": 910
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2596289551889364e-07,
+      "loss": 1.7528,
+      "step": 915
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.571249162498684e-08,
+      "loss": 1.8179,
+      "step": 920
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.4887672904708548e-08,
+      "loss": 1.7763,
+      "step": 925
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.5000108797349717e-09,
+      "loss": 1.7489,
+      "step": 930
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.7264798879623413,
+      "eval_runtime": 80.022,
+      "eval_samples_per_second": 20.494,
+      "eval_steps_per_second": 2.562,
+      "step": 933
+    }
+  ],
+  "max_steps": 933,
+  "num_train_epochs": 1,
+  "total_flos": 974357987328000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67df3bd264a71efcb0d01d8192714279a8fc3600ce7fa98693fe3fda12d80b92
+size 2671