huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/kendrick-lamar
+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/d6d96651b423fa5a83c38ee2a4c6c939.1000x1000x1.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">Kendrick Lamar</div>
+    <a href="https://genius.com/artists/kendrick-lamar">
+    	<div style="text-align: center; font-size: 14px;">@kendrick-lamar</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 Kendrick Lamar.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/kendrick-lamar).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/kendrick-lamar")
+```
+
+[Explore the data](WANDB_PREPROCESS/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 Kendrick Lamar's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](WANDB_TRAIN) for full transparency and reproducibility.
+
+At the end of training, [the final model](WANDB_TRAIN/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/kendrick-lamar')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/kendrick-lamar")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/kendrick-lamar")
+```
+
+## 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 +1,42 @@
+{
+  "_name_or_path": "kendrick-lamar",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 3.553039312362671, "eval_runtime": 9.9332, "eval_samples_per_second": 40.37, "eval_steps_per_second": 5.134, "epoch": 3.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88fc23ca7d4d4e6ba8e123b49d156d1727bcfc4fa1e29aa441617c39cbb7f743
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9a75d06ce33952bf6ca8d64e0619aceac8ed838c873cd199b0ca47dfda1bef
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00f508adfd0c8522fb8f01e38f222108699a66adc07ba0dff84341e730981a0
+size 510396521

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e651a57091df8587e175f62b4d70295e46b37b34655319dc46699d0ad3ac85b
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f059015de4876d2096cc91d2af4c7461eb3e5f4a09f212da6550c2c160d8775
+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 +1,1018 @@
+{
+  "best_metric": 3.553039312362671,
+  "best_model_checkpoint": "output/kendrick-lamar/checkpoint-819",
+  "epoch": 3.0,
+  "global_step": 819,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001370864757190084,
+      "loss": 4.2722,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00013674627861254597,
+      "loss": 4.3361,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00013618053464655754,
+      "loss": 4.2033,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013539111628975924,
+      "loss": 4.0514,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001343806363162431,
+      "loss": 4.1327,
+      "step": 25
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013315243915785902,
+      "loss": 3.96,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00013171058983499535,
+      "loss": 3.9217,
+      "step": 35
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001300598605023948,
+      "loss": 3.7032,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012820571465453544,
+      "loss": 3.9717,
+      "step": 45
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012615428904285254,
+      "loss": 4.0279,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001239123733646515,
+      "loss": 3.8994,
+      "step": 55
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001214873877909356,
+      "loss": 4.0263,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011888735840752609,
+      "loss": 3.9161,
+      "step": 65
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011612089065075853,
+      "loss": 3.8483,
+      "step": 70
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011319714082567585,
+      "loss": 3.8609,
+      "step": 75
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00011012578580098631,
+      "loss": 3.9798,
+      "step": 80
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010691699098108779,
+      "loss": 3.7969,
+      "step": 85
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00010358137666116333,
+      "loss": 3.9596,
+      "step": 90
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00010012998287670373,
+      "loss": 4.1164,
+      "step": 95
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.657423286379646e-05,
+      "loss": 3.7924,
+      "step": 100
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.292589525111794e-05,
+      "loss": 4.0304,
+      "step": 105
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.91970451087642e-05,
+      "loss": 3.8561,
+      "step": 110
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.540002398283833e-05,
+      "loss": 3.8825,
+      "step": 115
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.154739904807008e-05,
+      "loss": 3.8513,
+      "step": 120
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.765192151366211e-05,
+      "loss": 3.752,
+      "step": 125
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.372648442002871e-05,
+      "loss": 3.6579,
+      "step": 130
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 6.978407996610966e-05,
+      "loss": 3.595,
+      "step": 135
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.583775650849414e-05,
+      "loss": 3.8015,
+      "step": 140
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.190057537467733e-05,
+      "loss": 3.756,
+      "step": 145
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.79855676333867e-05,
+      "loss": 3.8087,
+      "step": 150
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.410569096505683e-05,
+      "loss": 3.6749,
+      "step": 155
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5.0273786775201065e-05,
+      "loss": 3.9157,
+      "step": 160
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.6502537692623556e-05,
+      "loss": 3.6094,
+      "step": 165
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2804425593141775e-05,
+      "loss": 3.8656,
+      "step": 170
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.9191690287750474e-05,
+      "loss": 3.8787,
+      "step": 175
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.567628901195867e-05,
+      "loss": 3.7476,
+      "step": 180
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.226985685037943e-05,
+      "loss": 3.6491,
+      "step": 185
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.898366822755775e-05,
+      "loss": 3.7995,
+      "step": 190
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 3.8123,
+      "step": 195
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.2815093420347238e-05,
+      "loss": 3.9104,
+      "step": 200
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.9953123650527866e-05,
+      "loss": 3.8532,
+      "step": 205
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.725216267546246e-05,
+      "loss": 3.7647,
+      "step": 210
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.472114998939829e-05,
+      "loss": 3.6447,
+      "step": 215
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.2368462600946557e-05,
+      "loss": 3.8278,
+      "step": 220
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0201887307313513e-05,
+      "loss": 3.7164,
+      "step": 225
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.228594921980851e-06,
+      "loss": 3.7653,
+      "step": 230
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.455116541136077e-06,
+      "loss": 3.6369,
+      "step": 235
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.88732192740426e-06,
+      "loss": 3.8294,
+      "step": 240
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.53040008242582e-06,
+      "loss": 3.9352,
+      "step": 245
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.3888420725801435e-06,
+      "loss": 3.7973,
+      "step": 250
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.4664261646974657e-06,
+      "loss": 3.892,
+      "step": 255
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.662053209561833e-07,
+      "loss": 3.7137,
+      "step": 260
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.9049709435396624e-07,
+      "loss": 3.7595,
+      "step": 265
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.087595819657002e-08,
+      "loss": 3.7287,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.6416754722595215,
+      "eval_runtime": 10.1198,
+      "eval_samples_per_second": 39.625,
+      "eval_steps_per_second": 5.04,
+      "step": 273
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.816809499134402e-08,
+      "loss": 3.6986,
+      "step": 275
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.2244866199319123e-07,
+      "loss": 3.6869,
+      "step": 280
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 6.530415424531654e-07,
+      "loss": 3.6129,
+      "step": 285
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.3085215833929946e-06,
+      "loss": 3.6142,
+      "step": 290
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.1867193124992013e-06,
+      "loss": 3.6029,
+      "step": 295
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.2847281185250116e-06,
+      "loss": 3.5627,
+      "step": 300
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.598913871434634e-06,
+      "loss": 3.4652,
+      "step": 305
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.124926950450006e-06,
+      "loss": 3.632,
+      "step": 310
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.857716640189785e-06,
+      "loss": 3.6625,
+      "step": 315
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 9.791547847253513e-06,
+      "loss": 3.6645,
+      "step": 320
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.1920020081922749e-05,
+      "loss": 3.6207,
+      "step": 325
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4236088642155179e-05,
+      "loss": 3.738,
+      "step": 330
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.6732087929757627e-05,
+      "loss": 3.4442,
+      "step": 335
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.9399756821567315e-05,
+      "loss": 3.7553,
+      "step": 340
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.223026601166984e-05,
+      "loss": 3.5033,
+      "step": 345
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.5214247234157134e-05,
+      "loss": 3.6562,
+      "step": 350
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.8341824269706243e-05,
+      "loss": 3.7108,
+      "step": 355
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.1602645633354905e-05,
+      "loss": 3.6002,
+      "step": 360
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.4985918835285396e-05,
+      "loss": 3.6699,
+      "step": 365
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.848044610122224e-05,
+      "loss": 3.6041,
+      "step": 370
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.207466143421867e-05,
+      "loss": 3.5919,
+      "step": 375
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.5756668895166686e-05,
+      "loss": 3.7467,
+      "step": 380
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.9514281975331363e-05,
+      "loss": 3.5324,
+      "step": 385
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.333506393059682e-05,
+      "loss": 3.6562,
+      "step": 390
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.720636894392822e-05,
+      "loss": 3.6013,
+      "step": 395
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 6.11153839798114e-05,
+      "loss": 3.6502,
+      "step": 400
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 6.504917119214327e-05,
+      "loss": 3.469,
+      "step": 405
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 6.899471074521375e-05,
+      "loss": 3.5713,
+      "step": 410
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.293894390605244e-05,
+      "loss": 3.5885,
+      "step": 415
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.686881626551516e-05,
+      "loss": 3.6544,
+      "step": 420
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.077132094505965e-05,
+      "loss": 3.5478,
+      "step": 425
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.463354164620745e-05,
+      "loss": 3.5412,
+      "step": 430
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.844269540020853e-05,
+      "loss": 3.4616,
+      "step": 435
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.218617487641824e-05,
+      "loss": 3.6015,
+      "step": 440
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.585159010935713e-05,
+      "loss": 3.5197,
+      "step": 445
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.942680950634723e-05,
+      "loss": 3.4169,
+      "step": 450
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 3.6481,
+      "step": 455
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00010625966621266112,
+      "loss": 3.5313,
+      "step": 460
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00010949468850318882,
+      "loss": 3.5705,
+      "step": 465
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00011259435977013931,
+      "loss": 3.6504,
+      "step": 470
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00011554842088955072,
+      "loss": 3.5506,
+      "step": 475
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011834709467003562,
+      "loss": 3.6447,
+      "step": 480
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00012098111821279934,
+      "loss": 3.6195,
+      "step": 485
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0001234417735694802,
+      "loss": 3.6632,
+      "step": 490
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00012572091659634235,
+      "loss": 3.4833,
+      "step": 495
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0001278110039093217,
+      "loss": 3.5942,
+      "step": 500
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0001297051178507093,
+      "loss": 3.599,
+      "step": 505
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00013139698938484013,
+      "loss": 3.6315,
+      "step": 510
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00013288101884700735,
+      "loss": 3.6382,
+      "step": 515
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00013415229447692924,
+      "loss": 3.6227,
+      "step": 520
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00013520660867542716,
+      "loss": 3.4538,
+      "step": 525
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00013604047193050914,
+      "loss": 3.4112,
+      "step": 530
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00013665112436676765,
+      "loss": 3.6708,
+      "step": 535
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00013703654487986559,
+      "loss": 3.5041,
+      "step": 540
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013719545782587793,
+      "loss": 3.6424,
+      "step": 545
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.619663715362549,
+      "eval_runtime": 10.1067,
+      "eval_samples_per_second": 39.676,
+      "eval_steps_per_second": 5.046,
+      "step": 546
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.0001371273372433488,
+      "loss": 3.4712,
+      "step": 550
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.0001368324085940902,
+      "loss": 3.4434,
+      "step": 555
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00013631164801696085,
+      "loss": 3.3224,
+      "step": 560
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.00013556677909709434,
+      "loss": 3.3818,
+      "step": 565
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.000134600267161271,
+      "loss": 3.3693,
+      "step": 570
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00013341531111831246,
+      "loss": 3.5516,
+      "step": 575
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00013201583287150687,
+      "loss": 3.3951,
+      "step": 580
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00013040646433810595,
+      "loss": 3.4224,
+      "step": 585
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00012859253211885616,
+      "loss": 3.4472,
+      "step": 590
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.00012658003986830435,
+      "loss": 3.5578,
+      "step": 595
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.00012437564842422732,
+      "loss": 3.3637,
+      "step": 600
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00012198665376195207,
+      "loss": 3.4449,
+      "step": 605
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00011942096284653183,
+      "loss": 3.4946,
+      "step": 610
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00011668706746270184,
+      "loss": 3.4818,
+      "step": 615
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.00011379401610923057,
+      "loss": 3.4296,
+      "step": 620
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.00011075138405068863,
+      "loss": 3.4033,
+      "step": 625
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00010756924162575734,
+      "loss": 3.3291,
+      "step": 630
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.00010425812091696729,
+      "loss": 3.1571,
+      "step": 635
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.00010082898089218288,
+      "loss": 3.5678,
+      "step": 640
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 9.72931711332038e-05,
+      "loss": 3.3972,
+      "step": 645
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 9.36623942715347e-05,
+      "loss": 3.3953,
+      "step": 650
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.99486672556498e-05,
+      "loss": 3.446,
+      "step": 655
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 8.616428157794779e-05,
+      "loss": 3.3233,
+      "step": 660
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.232176259303673e-05,
+      "loss": 3.3524,
+      "step": 665
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.843382806199401e-05,
+      "loss": 3.3982,
+      "step": 670
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.451334605981051e-05,
+      "loss": 3.5036,
+      "step": 675
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.05732923853327e-05,
+      "loss": 3.3534,
+      "step": 680
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 6.662670761466734e-05,
+      "loss": 3.4981,
+      "step": 685
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 6.268665394018953e-05,
+      "loss": 3.3561,
+      "step": 690
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 5.876617193800604e-05,
+      "loss": 3.3629,
+      "step": 695
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5.4878237406963316e-05,
+      "loss": 3.478,
+      "step": 700
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 5.103571842205231e-05,
+      "loss": 3.2104,
+      "step": 705
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.7251332744350254e-05,
+      "loss": 3.5289,
+      "step": 710
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 4.3537605728465284e-05,
+      "loss": 3.2297,
+      "step": 715
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 3.990682886679629e-05,
+      "loss": 3.4077,
+      "step": 720
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 3.637101910781716e-05,
+      "loss": 3.4158,
+      "step": 725
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 3.294187908303268e-05,
+      "loss": 3.3786,
+      "step": 730
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 2.9630758374242683e-05,
+      "loss": 3.4328,
+      "step": 735
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.6448615949311343e-05,
+      "loss": 3.469,
+      "step": 740
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 2.340598389076947e-05,
+      "loss": 3.3519,
+      "step": 745
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.051293253729814e-05,
+      "loss": 3.2819,
+      "step": 750
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.7779037153468233e-05,
+      "loss": 3.2787,
+      "step": 755
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.521334623804796e-05,
+      "loss": 3.2639,
+      "step": 760
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.2824351575772677e-05,
+      "loss": 3.3124,
+      "step": 765
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.0619960131695668e-05,
+      "loss": 3.2562,
+      "step": 770
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.607467881143831e-06,
+      "loss": 3.1959,
+      "step": 775
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 6.793535661894062e-06,
+      "loss": 3.2322,
+      "step": 780
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.184167128493107e-06,
+      "loss": 3.5785,
+      "step": 785
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.784688881687565e-06,
+      "loss": 3.4374,
+      "step": 790
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.599732838729015e-06,
+      "loss": 3.4859,
+      "step": 795
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.6332209029056513e-06,
+      "loss": 3.396,
+      "step": 800
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.883519830391712e-07,
+      "loss": 3.3425,
+      "step": 805
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 3.6759140590977833e-07,
+      "loss": 3.241,
+      "step": 810
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 7.266275665120308e-08,
+      "loss": 3.3081,
+      "step": 815
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.553039312362671,
+      "eval_runtime": 10.0835,
+      "eval_samples_per_second": 39.768,
+      "eval_steps_per_second": 5.058,
+      "step": 819
+    }
+  ],
+  "max_steps": 819,
+  "num_train_epochs": 3,
+  "total_flos": 855992696832000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5403dc0eac98a0673a2985e0248bb53a70fadc52734e92f64f79f2e5d172b8bb
+size 3247