huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/ghostemane
+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/c4407bb331c50916c1dfdc7f875f73a9.1000x1000x1.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">Ghostemane</div>
+    <a href="https://genius.com/artists/ghostemane">
+    	<div style="text-align: center; font-size: 14px;">@ghostemane</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 Ghostemane.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/ghostemane).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/ghostemane")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3rh17qau/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 Ghostemane's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/20jv1co7) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/20jv1co7/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/ghostemane')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/ghostemane")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/ghostemane")
+```
+
+## 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
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015b172a5a2d0391b8d62a84b9a4cb18f07b868c2a8304cb4dff1d2b0af71fbe
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c692883273acdd96b257e437b087ebe5a5afe7cf2e6e69e435b6a9d84c086d0
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5baeffc16fd04ca7a62effee68fbbb7f740145625c1eadd128caf4c2c37c9004
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c04fd1b5d311f1a14c4b405a718d717e325f1f3281b96d63575dfb04e76e69f
+size 14631

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ee231ce795a3df47a140b5d9cf5d222517e0f91ca7ba49c5b1339eb413a905
+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 +1,688 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013451892828543385,
+      "loss": 3.9488,
+      "step": 5
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012668528006706028,
+      "loss": 3.8298,
+      "step": 10
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011431137524750748,
+      "loss": 3.7557,
+      "step": 15
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.836442450346448e-05,
+      "loss": 3.5311,
+      "step": 20
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.009092691870492e-05,
+      "loss": 3.3526,
+      "step": 25
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 6.0919236939313083e-05,
+      "loss": 3.5934,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2347916539754844e-05,
+      "loss": 3.3983,
+      "step": 35
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 3.6609,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2652524389394753e-05,
+      "loss": 3.4898,
+      "step": 45
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.849603540845984e-06,
+      "loss": 3.5749,
+      "step": 50
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0792048977778093e-07,
+      "loss": 3.4588,
+      "step": 55
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.7199452243268996e-06,
+      "loss": 3.2536,
+      "step": 60
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.559673257059505e-06,
+      "loss": 3.2439,
+      "step": 65
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.009247481060283e-05,
+      "loss": 3.2968,
+      "step": 70
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.541688434458052e-05,
+      "loss": 3.4346,
+      "step": 75
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.333506393059682e-05,
+      "loss": 3.3563,
+      "step": 80
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.244643268047132e-05,
+      "loss": 3.2696,
+      "step": 85
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.125714365012444e-05,
+      "loss": 3.4046,
+      "step": 90
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00010829685091793463,
+      "loss": 3.4708,
+      "step": 95
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00012223363969730684,
+      "loss": 3.2387,
+      "step": 100
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013197813593027427,
+      "loss": 3.3163,
+      "step": 105
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00013676865759867644,
+      "loss": 3.2581,
+      "step": 110
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.000136230751870351,
+      "loss": 3.1941,
+      "step": 115
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00013040646433810595,
+      "loss": 3.0392,
+      "step": 120
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00011975105251098516,
+      "loss": 3.0188,
+      "step": 125
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.00010509740044895205,
+      "loss": 3.1013,
+      "step": 130
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 8.759091608374473e-05,
+      "loss": 3.0585,
+      "step": 135
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.860000000000001e-05,
+      "loss": 3.1302,
+      "step": 140
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.9609083916255386e-05,
+      "loss": 3.2358,
+      "step": 145
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 3.210259955104798e-05,
+      "loss": 3.119,
+      "step": 150
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.744894748901483e-05,
+      "loss": 2.9946,
+      "step": 155
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 6.793535661894062e-06,
+      "loss": 3.0184,
+      "step": 160
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 9.692481296490106e-07,
+      "loss": 2.9798,
+      "step": 165
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.313424013235498e-07,
+      "loss": 3.1282,
+      "step": 170
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 5.22186406972573e-06,
+      "loss": 3.0772,
+      "step": 175
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 1.496636030269314e-05,
+      "loss": 2.8216,
+      "step": 180
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 2.890314908206528e-05,
+      "loss": 2.7665,
+      "step": 185
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 4.594285634987545e-05,
+      "loss": 3.0073,
+      "step": 190
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 6.475356731952864e-05,
+      "loss": 3.0372,
+      "step": 195
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 8.386493606940314e-05,
+      "loss": 2.807,
+      "step": 200
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 0.0001017831156554194,
+      "loss": 3.1058,
+      "step": 205
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.0001171075251893971,
+      "loss": 2.961,
+      "step": 210
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 0.0001286403267429405,
+      "loss": 3.1032,
+      "step": 215
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.0001354800547756731,
+      "loss": 2.7667,
+      "step": 220
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 0.00013709207951022223,
+      "loss": 3.0024,
+      "step": 225
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.00013335039645915404,
+      "loss": 2.8538,
+      "step": 230
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 0.00012454747561060531,
+      "loss": 2.8202,
+      "step": 235
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.00011137140040750914,
+      "loss": 2.6845,
+      "step": 240
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 9.485208346024522e-05,
+      "loss": 2.6865,
+      "step": 245
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 7.62807630606869e-05,
+      "loss": 2.8686,
+      "step": 250
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 5.710907308129509e-05,
+      "loss": 2.9936,
+      "step": 255
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 3.883557549653544e-05,
+      "loss": 2.5979,
+      "step": 260
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 2.2888624752492583e-05,
+      "loss": 2.7179,
+      "step": 265
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 1.0514719932939762e-05,
+      "loss": 2.9387,
+      "step": 270
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 2.681071714566175e-06,
+      "loss": 2.6822,
+      "step": 275
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 2.7684,
+      "step": 280
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 2.6810717145661523e-06,
+      "loss": 2.6722,
+      "step": 285
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 1.0514719932939649e-05,
+      "loss": 2.597,
+      "step": 290
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 2.2888624752492607e-05,
+      "loss": 2.7343,
+      "step": 295
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 3.8835575496535365e-05,
+      "loss": 2.567,
+      "step": 300
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 5.7109073081294886e-05,
+      "loss": 2.6375,
+      "step": 305
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 7.628076306068694e-05,
+      "loss": 2.734,
+      "step": 310
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 9.485208346024515e-05,
+      "loss": 2.6448,
+      "step": 315
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00011137140040750908,
+      "loss": 2.6255,
+      "step": 320
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 0.0001245474756106052,
+      "loss": 2.6455,
+      "step": 325
+    },
+    {
+      "epoch": 5.89,
+      "learning_rate": 0.00013335039645915407,
+      "loss": 2.5969,
+      "step": 330
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 0.00013709207951022223,
+      "loss": 2.6923,
+      "step": 335
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00013548005477567314,
+      "loss": 2.3761,
+      "step": 340
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 0.00012864032674294047,
+      "loss": 2.4563,
+      "step": 345
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 0.00011710752518939715,
+      "loss": 2.4791,
+      "step": 350
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 0.00010178311565541947,
+      "loss": 2.446,
+      "step": 355
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 8.386493606940322e-05,
+      "loss": 2.5515,
+      "step": 360
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 6.475356731952872e-05,
+      "loss": 2.5469,
+      "step": 365
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 4.594285634987565e-05,
+      "loss": 2.6391,
+      "step": 370
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 2.890314908206545e-05,
+      "loss": 2.36,
+      "step": 375
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 1.496636030269327e-05,
+      "loss": 2.4806,
+      "step": 380
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 5.221864069725715e-06,
+      "loss": 2.6083,
+      "step": 385
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 4.3134240132355735e-07,
+      "loss": 2.6457,
+      "step": 390
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 9.692481296490106e-07,
+      "loss": 2.4165,
+      "step": 395
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 6.793535661894024e-06,
+      "loss": 2.301,
+      "step": 400
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 1.744894748901478e-05,
+      "loss": 2.4478,
+      "step": 405
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 3.2102599551047805e-05,
+      "loss": 2.3692,
+      "step": 410
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 4.960908391625518e-05,
+      "loss": 2.3269,
+      "step": 415
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 6.859999999999982e-05,
+      "loss": 2.1706,
+      "step": 420
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 8.759091608374469e-05,
+      "loss": 2.3618,
+      "step": 425
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 0.00010509740044895209,
+      "loss": 2.284,
+      "step": 430
+    },
+    {
+      "epoch": 7.77,
+      "learning_rate": 0.00011975105251098514,
+      "loss": 2.3587,
+      "step": 435
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 0.00013040646433810593,
+      "loss": 2.4467,
+      "step": 440
+    },
+    {
+      "epoch": 7.95,
+      "learning_rate": 0.000136230751870351,
+      "loss": 2.5326,
+      "step": 445
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 0.00013676865759867642,
+      "loss": 2.3045,
+      "step": 450
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 0.00013197813593027432,
+      "loss": 2.1819,
+      "step": 455
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 0.00012223363969730697,
+      "loss": 2.2893,
+      "step": 460
+    },
+    {
+      "epoch": 8.3,
+      "learning_rate": 0.00010829685091793466,
+      "loss": 2.3117,
+      "step": 465
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 9.12571436501247e-05,
+      "loss": 2.272,
+      "step": 470
+    },
+    {
+      "epoch": 8.48,
+      "learning_rate": 7.24464326804714e-05,
+      "loss": 2.3461,
+      "step": 475
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 5.33350639305969e-05,
+      "loss": 2.1348,
+      "step": 480
+    },
+    {
+      "epoch": 8.66,
+      "learning_rate": 3.541688434458043e-05,
+      "loss": 2.2985,
+      "step": 485
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 2.0092474810602934e-05,
+      "loss": 2.077,
+      "step": 490
+    },
+    {
+      "epoch": 8.84,
+      "learning_rate": 8.559673257059573e-06,
+      "loss": 2.2565,
+      "step": 495
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 1.719945224326892e-06,
+      "loss": 2.1992,
+      "step": 500
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 1.0792048977777332e-07,
+      "loss": 2.1455,
+      "step": 505
+    },
+    {
+      "epoch": 9.11,
+      "learning_rate": 3.849603540845977e-06,
+      "loss": 2.1314,
+      "step": 510
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 1.2652524389394722e-05,
+      "loss": 1.9046,
+      "step": 515
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 2.582859959249101e-05,
+      "loss": 2.0235,
+      "step": 520
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 4.234791653975475e-05,
+      "loss": 2.0746,
+      "step": 525
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 6.091923693931295e-05,
+      "loss": 2.0545,
+      "step": 530
+    },
+    {
+      "epoch": 9.55,
+      "learning_rate": 8.0090926918705e-05,
+      "loss": 2.0609,
+      "step": 535
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 9.83644245034643e-05,
+      "loss": 2.1458,
+      "step": 540
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 0.00011431137524750748,
+      "loss": 1.9214,
+      "step": 545
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 0.00012668528006706028,
+      "loss": 2.2293,
+      "step": 550
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 0.00013451892828543387,
+      "loss": 2.2592,
+      "step": 555
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0001372,
+      "loss": 2.1707,
+      "step": 560
+    }
+  ],
+  "max_steps": 560,
+  "num_train_epochs": 10,
+  "total_flos": 578761850880000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ce1bb2152f72c585a5945881263d149e91a628595bf2a816d138504612b188
+size 2671