AlekseyKorshuk commited on
Commit
7f2c5a8
1 Parent(s): ca209f5

huggingartists

Browse files
README.md CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
45
  dataset = load_dataset("huggingartists/queen")
46
  ```
47
 
48
- [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1odfy5f2/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
 
50
  ## Training procedure
51
 
52
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Queen's lyrics.
53
 
54
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/n5mutjgn) for full transparency and reproducibility.
55
 
56
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/n5mutjgn/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
 
45
  dataset = load_dataset("huggingartists/queen")
46
  ```
47
 
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1jdprwq2/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
 
50
  ## Training procedure
51
 
52
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Queen's lyrics.
53
 
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2lvkoamo) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2lvkoamo/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
config.json CHANGED
@@ -37,7 +37,7 @@
37
  }
38
  },
39
  "torch_dtype": "float32",
40
- "transformers_version": "4.20.0",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
 
37
  }
38
  },
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.20.1",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
evaluation.txt CHANGED
@@ -1 +1 @@
1
- {"eval_loss": 0.7435600757598877, "eval_runtime": 1.9524, "eval_samples_per_second": 44.56, "eval_steps_per_second": 5.634, "epoch": 2.0}
 
1
+ {"eval_loss": 0.6673863530158997, "eval_runtime": 2.2201, "eval_samples_per_second": 42.79, "eval_steps_per_second": 5.405, "epoch": 2.0}
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d59d4092b6fbaa70e9f950aa8fcb06e8531e931e125851c1d4493cca00a1d6d3
3
  size 497764120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5426a408b5d5b84e1ae5b6c6ef13577cc7459d4be7cb4670fbc861bdd8c9832b
3
  size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c66880bc32b68f34b3eb7af0a61b4e00e160a67a148722eca25b7babef5c4229
3
  size 995604017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b7bf14e6413ae5388a8e9590483437185ac7a86bbcfbf97feb2cba965b25a9
3
  size 995604017
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3308c600cab57fc29528fed25a3b6bbe8e7e16d4e20d2e4b9967b339a59a76b
3
  size 510396521
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a48e1744a8050fe41aa9965ca2432011f5f6dadcaaf7da0753f18e0b167b32
3
  size 510396521
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad122a9ca484f0a33b6603349e6dcbd96996d2bf9f426d0ada5eb32987c4387e
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2106753fad7f12850372556f05b325a609d5d1918d505246dc95a8ad23713d7d
3
  size 14503
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:243af1ebed26a3a8d0b96be16a026fc3571686ab7c16190d8dea7c3ff4208aee
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9400f744e6736bc4247e7cf5592a2fdcb5788998b7af1403eec6453074e2be8
3
  size 623
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.7435600757598877,
3
- "best_model_checkpoint": "output/queen/checkpoint-69",
4
- "epoch": 1.0,
5
- "global_step": 69,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -100,11 +100,103 @@
100
  "eval_samples_per_second": 48.039,
101
  "eval_steps_per_second": 6.074,
102
  "step": 69
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
  }
104
  ],
105
- "max_steps": 138,
106
  "num_train_epochs": 2,
107
- "total_flos": 70418202624000.0,
108
  "trial_name": null,
109
  "trial_params": null
110
  }
 
1
  {
2
+ "best_metric": 0.6673863530158997,
3
+ "best_model_checkpoint": "output/queen/checkpoint-136",
4
+ "epoch": 2.0,
5
+ "global_step": 136,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
100
  "eval_samples_per_second": 48.039,
101
  "eval_steps_per_second": 6.074,
102
  "step": 69
103
+ },
104
+ {
105
+ "epoch": 1.03,
106
+ "learning_rate": 2.926355061606355e-07,
107
+ "loss": 1.3103,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 1.1,
112
+ "learning_rate": 3.5561795752596966e-06,
113
+ "loss": 0.9826,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 1.18,
118
+ "learning_rate": 1.027510448894829e-05,
119
+ "loss": 0.9993,
120
+ "step": 80
121
+ },
122
+ {
123
+ "epoch": 1.25,
124
+ "learning_rate": 2.0092474810602806e-05,
125
+ "loss": 0.8551,
126
+ "step": 85
127
+ },
128
+ {
129
+ "epoch": 1.32,
130
+ "learning_rate": 3.2486753626613595e-05,
131
+ "loss": 1.0815,
132
+ "step": 90
133
+ },
134
+ {
135
+ "epoch": 1.4,
136
+ "learning_rate": 4.6799508616681124e-05,
137
+ "loss": 0.8781,
138
+ "step": 95
139
+ },
140
+ {
141
+ "epoch": 1.47,
142
+ "learning_rate": 6.227039054081734e-05,
143
+ "loss": 0.9205,
144
+ "step": 100
145
+ },
146
+ {
147
+ "epoch": 1.54,
148
+ "learning_rate": 7.807752594969924e-05,
149
+ "loss": 0.7833,
150
+ "step": 105
151
+ },
152
+ {
153
+ "epoch": 1.62,
154
+ "learning_rate": 9.338117830043863e-05,
155
+ "loss": 1.083,
156
+ "step": 110
157
+ },
158
+ {
159
+ "epoch": 1.69,
160
+ "learning_rate": 0.00010736835802938959,
161
+ "loss": 1.0006,
162
+ "step": 115
163
+ },
164
+ {
165
+ "epoch": 1.76,
166
+ "learning_rate": 0.00011929601172133724,
167
+ "loss": 1.0609,
168
+ "step": 120
169
+ },
170
+ {
171
+ "epoch": 1.84,
172
+ "learning_rate": 0.00012853049599834086,
173
+ "loss": 0.9702,
174
+ "step": 125
175
+ },
176
+ {
177
+ "epoch": 1.91,
178
+ "learning_rate": 0.00013458123912165544,
179
+ "loss": 1.0468,
180
+ "step": 130
181
+ },
182
+ {
183
+ "epoch": 1.99,
184
+ "learning_rate": 0.00013712680207144277,
185
+ "loss": 1.0231,
186
+ "step": 135
187
+ },
188
+ {
189
+ "epoch": 2.0,
190
+ "eval_loss": 0.6673863530158997,
191
+ "eval_runtime": 2.2427,
192
+ "eval_samples_per_second": 42.36,
193
+ "eval_steps_per_second": 5.351,
194
+ "step": 136
195
  }
196
  ],
197
+ "max_steps": 136,
198
  "num_train_epochs": 2,
199
+ "total_flos": 139660591104000.0,
200
  "trial_name": null,
201
  "trial_params": null
202
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3276c6263f8b9603729e374cfea7b7138a847c1c3c8a37df36295a1f7cfc5e34
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e996fa4db6846e691ba9e83e3330ddc142ed2dbd6e677589b0a43edc5c70fa
3
  size 3311