huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/taylor-swift
+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/3c1f124fcbbc2857a95e513fb34cc5a8.400x400x1.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">Taylor Swift</div>
+    <a href="https://genius.com/artists/taylor-swift">
+    	<div style="text-align: center; font-size: 14px;">@taylor-swift</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 Taylor Swift.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/taylor-swift).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/taylor-swift")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/orx9pgcj/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 Taylor Swift's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/13d0g1o4) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/13d0g1o4/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/taylor-swift')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/taylor-swift")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/taylor-swift")
+```
+
+## 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": "gpt2",
+  "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": "4.12.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 2.1195662021636963, "eval_runtime": 2.7951, "eval_samples_per_second": 76.561, "eval_steps_per_second": 9.66, "epoch": 5.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283ca8f9344b855954167e60f2db67ac2afc241037fe870abcdcea59b7262caf
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642b9dfcc4d3d148df04dbd5dd9fc2e06a625d5877f48239cd186fadbd82f0c0
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875d52e81b7c5b242a7496cd7be0fe29bfb0475bf80207c43583aeaede1cdaed
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8108166cfcb949d51c2438ab25802532e6d155d969ce33575bd2e1f5af1b15a0
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7733e18eff27c9a4da0b58764924ec541924a4be41ac9a645f4ee09be1782f09
+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 +1,1004 @@
+{
+  "best_metric": 2.1195662021636963,
+  "best_model_checkpoint": "output/taylor-swift/checkpoint-790",
+  "epoch": 5.0,
+  "global_step": 790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013686126352583852,
+      "loss": 3.3494,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00013584839936279803,
+      "loss": 3.1755,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013417141025243517,
+      "loss": 3.1276,
+      "step": 15
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00013184685763435497,
+      "loss": 3.1339,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012889769809041896,
+      "loss": 3.1666,
+      "step": 25
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012535305663245375,
+      "loss": 2.8811,
+      "step": 30
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00012124793907240209,
+      "loss": 2.9824,
+      "step": 35
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011662288631546257,
+      "loss": 2.9442,
+      "step": 40
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011152357399031441,
+      "loss": 2.961,
+      "step": 45
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000106000361370359,
+      "loss": 2.7762,
+      "step": 50
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00010010779404069628,
+      "loss": 2.8665,
+      "step": 55
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.390406522234693e-05,
+      "loss": 2.9223,
+      "step": 60
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.745044107352033e-05,
+      "loss": 2.8602,
+      "step": 65
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.081065564347997e-05,
+      "loss": 2.8085,
+      "step": 70
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.405028145425961e-05,
+      "loss": 2.7651,
+      "step": 75
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.723608192617619e-05,
+      "loss": 2.7224,
+      "step": 80
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 6.043535204238934e-05,
+      "loss": 2.6702,
+      "step": 85
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.371525376390658e-05,
+      "loss": 2.8382,
+      "step": 90
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.714215275827523e-05,
+      "loss": 2.5947,
+      "step": 95
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.078096299222862e-05,
+      "loss": 2.7596,
+      "step": 100
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.4694505660892814e-05,
+      "loss": 2.8001,
+      "step": 105
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.894288878457539e-05,
+      "loss": 2.7797,
+      "step": 110
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.358291360005225e-05,
+      "loss": 2.6613,
+      "step": 115
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.8667513608652705e-05,
+      "loss": 2.6169,
+      "step": 120
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.424523182093601e-05,
+      "loss": 2.5101,
+      "step": 125
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0359741360532426e-05,
+      "loss": 2.6278,
+      "step": 130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.049414161522035e-06,
+      "loss": 2.8319,
+      "step": 135
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.346942018765275e-06,
+      "loss": 2.7047,
+      "step": 140
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.2790137335786513e-06,
+      "loss": 2.7375,
+      "step": 145
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 8.660515431675314e-07,
+      "loss": 2.9128,
+      "step": 150
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.2200943675939755e-07,
+      "loss": 2.6662,
+      "step": 155
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.5653560161590576,
+      "eval_runtime": 2.784,
+      "eval_samples_per_second": 76.868,
+      "eval_steps_per_second": 9.698,
+      "step": 158
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 5.4235350207093555e-08,
+      "loss": 2.594,
+      "step": 160
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 6.633985999863723e-07,
+      "loss": 2.722,
+      "step": 165
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.94348327322787e-06,
+      "loss": 2.6618,
+      "step": 170
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.881847639061565e-06,
+      "loss": 2.5415,
+      "step": 175
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.459348994545111e-06,
+      "loss": 2.5807,
+      "step": 180
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 9.650532712235251e-06,
+      "loss": 2.6543,
+      "step": 185
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3423883622425528e-05,
+      "loss": 2.5415,
+      "step": 190
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.7742137247474782e-05,
+      "loss": 2.435,
+      "step": 195
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.256264781457008e-05,
+      "loss": 2.629,
+      "step": 200
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.783780941254068e-05,
+      "loss": 2.4759,
+      "step": 205
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.3515526133505226e-05,
+      "loss": 2.5917,
+      "step": 210
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.953972655637492e-05,
+      "loss": 2.6353,
+      "step": 215
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.585091749132818e-05,
+      "loss": 2.6671,
+      "step": 220
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.238677151664272e-05,
+      "loss": 2.4302,
+      "step": 225
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.908274250554988e-05,
+      "loss": 2.65,
+      "step": 230
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 6.587270306435089e-05,
+      "loss": 2.6803,
+      "step": 235
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.268959758664963e-05,
+      "loss": 2.7479,
+      "step": 240
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 7.946610447433497e-05,
+      "loss": 2.5183,
+      "step": 245
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.613530098541655e-05,
+      "loss": 2.4577,
+      "step": 250
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.263132414287828e-05,
+      "loss": 2.6144,
+      "step": 255
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.889002117761157e-05,
+      "loss": 2.3613,
+      "step": 260
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0001048495830818497,
+      "loss": 2.3438,
+      "step": 265
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.000110451155016322,
+      "loss": 2.5456,
+      "step": 270
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00011563941754292792,
+      "loss": 2.4388,
+      "step": 275
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00012036313294285455,
+      "loss": 2.337,
+      "step": 280
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00012457565122486245,
+      "loss": 2.4888,
+      "step": 285
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00012823537082655537,
+      "loss": 2.5507,
+      "step": 290
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00013130614945888676,
+      "loss": 2.4084,
+      "step": 295
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0001337576610365259,
+      "loss": 2.5188,
+      "step": 300
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.0001355656951691469,
+      "loss": 2.4279,
+      "step": 305
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00013671239625595536,
+      "loss": 2.4089,
+      "step": 310
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0001371864398222265,
+      "loss": 2.3992,
+      "step": 315
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.427677631378174,
+      "eval_runtime": 2.7859,
+      "eval_samples_per_second": 76.814,
+      "eval_steps_per_second": 9.691,
+      "step": 316
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.00013698314435640815,
+      "loss": 2.4731,
+      "step": 320
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00013610451754331968,
+      "loss": 2.5107,
+      "step": 325
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00013455923643686105,
+      "loss": 2.2137,
+      "step": 330
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00013236256176804074,
+      "loss": 2.433,
+      "step": 335
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00012953618723459046,
+      "loss": 2.2366,
+      "step": 340
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.00012610802526053698,
+      "loss": 2.2305,
+      "step": 345
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.0001221119313415056,
+      "loss": 2.0334,
+      "step": 350
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00011758736969803705,
+      "loss": 2.2182,
+      "step": 355
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00011257902353882629,
+      "loss": 2.4565,
+      "step": 360
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00010713635378280492,
+      "loss": 2.3876,
+      "step": 365
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.00010131311059799552,
+      "loss": 2.3244,
+      "step": 370
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 9.516680258103397e-05,
+      "loss": 2.1224,
+      "step": 375
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 8.875812881958139e-05,
+      "loss": 2.1287,
+      "step": 380
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.215037944640755e-05,
+      "loss": 2.3755,
+      "step": 385
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.540881060509307e-05,
+      "loss": 2.1973,
+      "step": 390
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.860000000000001e-05,
+      "loss": 2.3247,
+      "step": 395
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 6.179118939490698e-05,
+      "loss": 2.0219,
+      "step": 400
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 5.504962055359254e-05,
+      "loss": 2.2227,
+      "step": 405
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.844187118041858e-05,
+      "loss": 2.0213,
+      "step": 410
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 4.203319741896607e-05,
+      "loss": 2.4335,
+      "step": 415
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 3.5886889402004514e-05,
+      "loss": 2.1705,
+      "step": 420
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 3.006364621719512e-05,
+      "loss": 2.0096,
+      "step": 425
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.462097646117378e-05,
+      "loss": 2.233,
+      "step": 430
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.9612630301962937e-05,
+      "loss": 2.2407,
+      "step": 435
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.508806865849441e-05,
+      "loss": 2.1925,
+      "step": 440
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.1091974739463048e-05,
+      "loss": 2.0939,
+      "step": 445
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 7.66381276540956e-06,
+      "loss": 2.1105,
+      "step": 450
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.8374382319592885e-06,
+      "loss": 2.1558,
+      "step": 455
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.6407635631389823e-06,
+      "loss": 2.3444,
+      "step": 460
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.0954824566803356e-06,
+      "loss": 2.0945,
+      "step": 465
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 2.168556435918659e-07,
+      "loss": 1.9806,
+      "step": 470
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.2620296478271484,
+      "eval_runtime": 2.784,
+      "eval_samples_per_second": 76.867,
+      "eval_steps_per_second": 9.698,
+      "step": 474
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 1.3560177773502823e-08,
+      "loss": 1.9753,
+      "step": 475
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.87603744044624e-07,
+      "loss": 2.0561,
+      "step": 480
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.6343048308530896e-06,
+      "loss": 2.0054,
+      "step": 485
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 3.4423389634741234e-06,
+      "loss": 2.0684,
+      "step": 490
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 5.893850541113203e-06,
+      "loss": 1.8837,
+      "step": 495
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 8.964629173444626e-06,
+      "loss": 1.9202,
+      "step": 500
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 1.2624348775137553e-05,
+      "loss": 1.9576,
+      "step": 505
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 1.6836867057145347e-05,
+      "loss": 2.1642,
+      "step": 510
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 2.156058245707209e-05,
+      "loss": 2.2199,
+      "step": 515
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 2.6748844983678075e-05,
+      "loss": 2.24,
+      "step": 520
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 3.235041691815028e-05,
+      "loss": 2.2476,
+      "step": 525
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.830997882238844e-05,
+      "loss": 1.9431,
+      "step": 530
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 4.456867585712155e-05,
+      "loss": 1.9221,
+      "step": 535
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 5.1064699014583464e-05,
+      "loss": 1.8139,
+      "step": 540
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 5.773389552566511e-05,
+      "loss": 2.0033,
+      "step": 545
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 6.451040241335031e-05,
+      "loss": 2.0651,
+      "step": 550
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 7.132729693564907e-05,
+      "loss": 2.034,
+      "step": 555
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 7.811725749444997e-05,
+      "loss": 1.8939,
+      "step": 560
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 8.481322848335718e-05,
+      "loss": 2.2029,
+      "step": 565
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 9.134908250867189e-05,
+      "loss": 1.9256,
+      "step": 570
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 9.766027344362499e-05,
+      "loss": 1.9943,
+      "step": 575
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.00010368447386649474,
+      "loss": 1.9552,
+      "step": 580
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 0.00010936219058745934,
+      "loss": 1.9243,
+      "step": 585
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.00011463735218542983,
+      "loss": 1.8552,
+      "step": 590
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.00011945786275252523,
+      "loss": 2.067,
+      "step": 595
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.00012377611637757444,
+      "loss": 2.0837,
+      "step": 600
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.0001275494672877647,
+      "loss": 2.0373,
+      "step": 605
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.0001307406510054549,
+      "loss": 1.8866,
+      "step": 610
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.0001333181523609384,
+      "loss": 2.045,
+      "step": 615
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 0.00013525651672677215,
+      "loss": 2.0499,
+      "step": 620
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 0.00013653660140001365,
+      "loss": 1.9574,
+      "step": 625
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 0.0001371457646497929,
+      "loss": 2.1066,
+      "step": 630
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.209007978439331,
+      "eval_runtime": 2.7857,
+      "eval_samples_per_second": 76.822,
+      "eval_steps_per_second": 9.692,
+      "step": 632
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 0.0001370779905632406,
+      "loss": 1.8936,
+      "step": 635
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 0.00013633394845683248,
+      "loss": 1.9616,
+      "step": 640
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00013492098626642133,
+      "loss": 1.7865,
+      "step": 645
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.00013285305798123475,
+      "loss": 1.8786,
+      "step": 650
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 0.00013015058583847798,
+      "loss": 1.9233,
+      "step": 655
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 0.00012684025863946756,
+      "loss": 1.8903,
+      "step": 660
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.000122954768179064,
+      "loss": 1.895,
+      "step": 665
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 0.00011853248639134728,
+      "loss": 1.8842,
+      "step": 670
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 0.00011361708639994783,
+      "loss": 1.7602,
+      "step": 675
+    },
+    {
+      "epoch": 4.3,
+      "learning_rate": 0.00010825711121542465,
+      "loss": 1.7436,
+      "step": 680
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 0.00010250549433910721,
+      "loss": 1.8129,
+      "step": 685
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 9.64190370077714e-05,
+      "loss": 1.7891,
+      "step": 690
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 9.005784724172477e-05,
+      "loss": 1.8476,
+      "step": 695
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 8.348474623609351e-05,
+      "loss": 2.0649,
+      "step": 700
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 7.676464795761073e-05,
+      "loss": 1.9673,
+      "step": 705
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 6.996391807382385e-05,
+      "loss": 2.0106,
+      "step": 710
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 6.314971854574042e-05,
+      "loss": 1.8144,
+      "step": 715
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 5.638934435652005e-05,
+      "loss": 1.8997,
+      "step": 720
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 4.974955892647975e-05,
+      "loss": 1.6943,
+      "step": 725
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 4.329593477765313e-05,
+      "loss": 1.784,
+      "step": 730
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 3.709220595930377e-05,
+      "loss": 1.7719,
+      "step": 735
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 3.119963862964102e-05,
+      "loss": 1.6203,
+      "step": 740
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 2.5676426009685593e-05,
+      "loss": 1.7432,
+      "step": 745
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.0577113684537407e-05,
+      "loss": 1.6835,
+      "step": 750
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 1.5952060927597964e-05,
+      "loss": 1.8013,
+      "step": 755
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 1.1846943367546308e-05,
+      "loss": 1.6429,
+      "step": 760
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 8.302301909581063e-06,
+      "loss": 1.8303,
+      "step": 765
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 5.353142365645029e-06,
+      "loss": 1.6484,
+      "step": 770
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 3.0285897475648074e-06,
+      "loss": 1.7701,
+      "step": 775
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 1.3516006372019799e-06,
+      "loss": 1.7971,
+      "step": 780
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 3.3873647416147947e-07,
+      "loss": 1.8325,
+      "step": 785
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 1.7255,
+      "step": 790
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.1195662021636963,
+      "eval_runtime": 2.7825,
+      "eval_samples_per_second": 76.91,
+      "eval_steps_per_second": 9.704,
+      "step": 790
+    }
+  ],
+  "max_steps": 790,
+  "num_train_epochs": 5,
+  "total_flos": 825029591040000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfb6e247e098310914adb6ffa99cbac18054688ed991eef0c2acb3531d8319c
+size 2863