Hugging Face's logo

JammyMachina
/
elec-gmusic-familized-model-13-12__17-35-53

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files Community
2
m4lw4r3exe commited on
Commit
95b3c09
·
1 Parent(s): e31541e

Upload manual_upload with huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. manual_upload/README.md +104 -0
  2. manual_upload/checkpoint-32768/config.json +33 -0
  3. manual_upload/checkpoint-32768/optimizer.pt +3 -0
  4. manual_upload/checkpoint-32768/pytorch_model.bin +3 -0
  5. manual_upload/checkpoint-32768/rng_state.pth +3 -0
  6. manual_upload/checkpoint-32768/scaler.pt +3 -0
  7. manual_upload/checkpoint-32768/scheduler.pt +3 -0
  8. manual_upload/checkpoint-32768/trainer_state.json +464 -0
  9. manual_upload/checkpoint-32768/training_args.bin +3 -0
  10. manual_upload/checkpoint-36864/config.json +33 -0
  11. manual_upload/checkpoint-36864/optimizer.pt +3 -0
  12. manual_upload/checkpoint-36864/pytorch_model.bin +3 -0
  13. manual_upload/checkpoint-36864/rng_state.pth +3 -0
  14. manual_upload/checkpoint-36864/scaler.pt +3 -0
  15. manual_upload/checkpoint-36864/scheduler.pt +3 -0
  16. manual_upload/checkpoint-36864/trainer_state.json +520 -0
  17. manual_upload/checkpoint-36864/training_args.bin +3 -0
  18. manual_upload/checkpoint-40960/config.json +33 -0
  19. manual_upload/checkpoint-40960/optimizer.pt +3 -0
  20. manual_upload/checkpoint-40960/pytorch_model.bin +3 -0
  21. manual_upload/checkpoint-40960/rng_state.pth +3 -0
  22. manual_upload/checkpoint-40960/scaler.pt +3 -0
  23. manual_upload/checkpoint-40960/scheduler.pt +3 -0
  24. manual_upload/checkpoint-40960/trainer_state.json +576 -0
  25. manual_upload/checkpoint-40960/training_args.bin +3 -0
  26. manual_upload/checkpoint-45056/config.json +33 -0
  27. manual_upload/checkpoint-45056/optimizer.pt +3 -0
  28. manual_upload/checkpoint-45056/pytorch_model.bin +3 -0
  29. manual_upload/checkpoint-45056/rng_state.pth +3 -0
  30. manual_upload/checkpoint-45056/scaler.pt +3 -0
  31. manual_upload/checkpoint-45056/scheduler.pt +3 -0
  32. manual_upload/checkpoint-45056/trainer_state.json +632 -0
  33. manual_upload/checkpoint-45056/training_args.bin +3 -0
  34. manual_upload/checkpoint-49152/config.json +33 -0
  35. manual_upload/checkpoint-49152/optimizer.pt +3 -0
  36. manual_upload/checkpoint-49152/pytorch_model.bin +3 -0
  37. manual_upload/checkpoint-49152/rng_state.pth +3 -0
  38. manual_upload/checkpoint-49152/scaler.pt +3 -0
  39. manual_upload/checkpoint-49152/scheduler.pt +3 -0
  40. manual_upload/checkpoint-49152/trainer_state.json +688 -0
  41. manual_upload/checkpoint-49152/training_args.bin +3 -0
  42. manual_upload/config.json +1 -0
  43. manual_upload/manual_upload/.gitattributes +34 -0
  44. manual_upload/manual_upload/.gitignore +1 -0
  45. manual_upload/manual_upload/config.json +32 -0
  46. manual_upload/manual_upload/pytorch_model.bin +3 -0
  47. manual_upload/manual_upload/special_tokens_map.json +3 -0
  48. manual_upload/manual_upload/tokenizer.json +347 -0
  49. manual_upload/manual_upload/tokenizer_config.json +6 -0
  50. manual_upload/manual_upload/trainer_state.json +15 -0
manual_upload/README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: elec-gmusic-familized-model-13-12__17-35-53
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # elec-gmusic-familized-model-13-12__17-35-53
13
+
14
+ This model is a fine-tuned version of [JammyMachina/elec-gmusic-familized-model-13-12__17-35-53](https://huggingface.co/JammyMachina/elec-gmusic-familized-model-13-12__17-35-53) on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.4303
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 36
37
+ - eval_batch_size: 32
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 5
42
+ - mixed_precision_training: Native AMP
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:-----:|:---------------:|
48
+ | 0.2509 | 0.1 | 1024 | 0.4268 |
49
+ | 0.2521 | 0.2 | 2048 | 0.4284 |
50
+ | 0.2533 | 0.3 | 3072 | 0.4219 |
51
+ | 0.2517 | 0.4 | 4096 | 0.4245 |
52
+ | 0.2512 | 0.5 | 5120 | 0.4229 |
53
+ | 0.2506 | 0.6 | 6144 | 0.4191 |
54
+ | 0.2512 | 0.71 | 7168 | 0.4247 |
55
+ | 0.2483 | 0.81 | 8192 | 0.4239 |
56
+ | 0.2479 | 0.91 | 9216 | 0.4259 |
57
+ | 0.2498 | 1.01 | 10240 | 0.4262 |
58
+ | 0.2467 | 1.11 | 11264 | 0.4267 |
59
+ | 0.2466 | 1.21 | 12288 | 0.4263 |
60
+ | 0.2449 | 1.31 | 13312 | 0.4251 |
61
+ | 0.2452 | 1.41 | 14336 | 0.4274 |
62
+ | 0.2449 | 1.51 | 15360 | 0.4263 |
63
+ | 0.2444 | 1.61 | 16384 | 0.4240 |
64
+ | 0.2428 | 1.71 | 17408 | 0.4289 |
65
+ | 0.2425 | 1.81 | 18432 | 0.4229 |
66
+ | 0.2424 | 1.91 | 19456 | 0.4291 |
67
+ | 0.2422 | 2.01 | 20480 | 0.4247 |
68
+ | 0.2397 | 2.12 | 21504 | 0.4271 |
69
+ | 0.2397 | 2.22 | 22528 | 0.4226 |
70
+ | 0.2411 | 2.32 | 23552 | 0.4269 |
71
+ | 0.2408 | 2.42 | 24576 | 0.4288 |
72
+ | 0.2392 | 2.52 | 25600 | 0.4223 |
73
+ | 0.2391 | 2.62 | 26624 | 0.4297 |
74
+ | 0.2385 | 2.72 | 27648 | 0.4253 |
75
+ | 0.2371 | 2.82 | 28672 | 0.4297 |
76
+ | 0.2373 | 2.92 | 29696 | 0.4232 |
77
+ | 0.2368 | 3.02 | 30720 | 0.4296 |
78
+ | 0.2355 | 3.12 | 31744 | 0.4327 |
79
+ | 0.2354 | 3.22 | 32768 | 0.4305 |
80
+ | 0.2345 | 3.32 | 33792 | 0.4286 |
81
+ | 0.2355 | 3.42 | 34816 | 0.4350 |
82
+ | 0.2353 | 3.53 | 35840 | 0.4269 |
83
+ | 0.2351 | 3.63 | 36864 | 0.4301 |
84
+ | 0.2336 | 3.73 | 37888 | 0.4301 |
85
+ | 0.2344 | 3.83 | 38912 | 0.4319 |
86
+ | 0.2339 | 3.93 | 39936 | 0.4305 |
87
+ | 0.2326 | 4.03 | 40960 | 0.4298 |
88
+ | 0.2316 | 4.13 | 41984 | 0.4308 |
89
+ | 0.2311 | 4.23 | 43008 | 0.4330 |
90
+ | 0.2315 | 4.33 | 44032 | 0.4313 |
91
+ | 0.2305 | 4.43 | 45056 | 0.4319 |
92
+ | 0.2328 | 4.53 | 46080 | 0.4292 |
93
+ | 0.232 | 4.63 | 47104 | 0.4289 |
94
+ | 0.2309 | 4.73 | 48128 | 0.4303 |
95
+ | 0.23 | 4.83 | 49152 | 0.4317 |
96
+ | 0.2315 | 4.94 | 50176 | 0.4303 |
97
+
98
+
99
+ ### Framework versions
100
+
101
+ - Transformers 4.26.0.dev0
102
+ - Pytorch 1.13.1+cu116
103
+ - Datasets 2.7.1
104
+ - Tokenizers 0.13.2
manual_upload/checkpoint-32768/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "JammyMachina/elec-gmusic-familized-model-13-12__17-35-53",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 512,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 6,
18
+ "n_positions": 2048,
19
+ "pad_token_id": 1,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.26.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 301
33
+ }
manual_upload/checkpoint-32768/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458ee72534eb8b5ad8dccb794450b446bad2494326bb8beefb83ed28205a0db6
3
+ size 160988613
manual_upload/checkpoint-32768/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188a30cd4df09ff71af7227dcd5594d5c65b1afce81bdb7613c8f8b0eee22f06
3
+ size 105666297
manual_upload/checkpoint-32768/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5139f2582c3e753523ce47e10d63506fe8b53897ec575066a8f405daa71ebee5
3
+ size 17641
manual_upload/checkpoint-32768/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac2d928598cb5138c4a59645b28bcace0c1fd92792906a6e7ae72f6c4058c01
3
+ size 557
manual_upload/checkpoint-32768/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7e2068bb82ba682bdcc93651dcef0e77a4e1d68e53aa617acce19bdbe0f064
3
+ size 627
manual_upload/checkpoint-32768/trainer_state.json ADDED
@@ -0,0 +1,464 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.2229762958591524,
5
+ "global_step": 32768,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 4.899281990754402e-05,
13
+ "loss": 0.2509,
14
+ "step": 1024
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "eval_loss": 0.42676058411598206,
19
+ "eval_runtime": 32.3598,
20
+ "eval_samples_per_second": 106.212,
21
+ "eval_steps_per_second": 3.337,
22
+ "step": 1024
23
+ },
24
+ {
25
+ "epoch": 0.2,
26
+ "learning_rate": 4.798563981508803e-05,
27
+ "loss": 0.2521,
28
+ "step": 2048
29
+ },
30
+ {
31
+ "epoch": 0.2,
32
+ "eval_loss": 0.4283539652824402,
33
+ "eval_runtime": 32.4193,
34
+ "eval_samples_per_second": 106.017,
35
+ "eval_steps_per_second": 3.331,
36
+ "step": 2048
37
+ },
38
+ {
39
+ "epoch": 0.3,
40
+ "learning_rate": 4.697845972263204e-05,
41
+ "loss": 0.2533,
42
+ "step": 3072
43
+ },
44
+ {
45
+ "epoch": 0.3,
46
+ "eval_loss": 0.42187923192977905,
47
+ "eval_runtime": 32.3798,
48
+ "eval_samples_per_second": 106.146,
49
+ "eval_steps_per_second": 3.335,
50
+ "step": 3072
51
+ },
52
+ {
53
+ "epoch": 0.4,
54
+ "learning_rate": 4.597127963017606e-05,
55
+ "loss": 0.2517,
56
+ "step": 4096
57
+ },
58
+ {
59
+ "epoch": 0.4,
60
+ "eval_loss": 0.42451202869415283,
61
+ "eval_runtime": 32.3385,
62
+ "eval_samples_per_second": 106.282,
63
+ "eval_steps_per_second": 3.34,
64
+ "step": 4096
65
+ },
66
+ {
67
+ "epoch": 0.5,
68
+ "learning_rate": 4.496409953772008e-05,
69
+ "loss": 0.2512,
70
+ "step": 5120
71
+ },
72
+ {
73
+ "epoch": 0.5,
74
+ "eval_loss": 0.42285656929016113,
75
+ "eval_runtime": 32.3235,
76
+ "eval_samples_per_second": 106.331,
77
+ "eval_steps_per_second": 3.341,
78
+ "step": 5120
79
+ },
80
+ {
81
+ "epoch": 0.6,
82
+ "learning_rate": 4.3956919445264097e-05,
83
+ "loss": 0.2506,
84
+ "step": 6144
85
+ },
86
+ {
87
+ "epoch": 0.6,
88
+ "eval_loss": 0.4190705716609955,
89
+ "eval_runtime": 32.4437,
90
+ "eval_samples_per_second": 105.937,
91
+ "eval_steps_per_second": 3.329,
92
+ "step": 6144
93
+ },
94
+ {
95
+ "epoch": 0.71,
96
+ "learning_rate": 4.294973935280811e-05,
97
+ "loss": 0.2512,
98
+ "step": 7168
99
+ },
100
+ {
101
+ "epoch": 0.71,
102
+ "eval_loss": 0.4247213900089264,
103
+ "eval_runtime": 32.3289,
104
+ "eval_samples_per_second": 106.314,
105
+ "eval_steps_per_second": 3.341,
106
+ "step": 7168
107
+ },
108
+ {
109
+ "epoch": 0.81,
110
+ "learning_rate": 4.194255926035212e-05,
111
+ "loss": 0.2483,
112
+ "step": 8192
113
+ },
114
+ {
115
+ "epoch": 0.81,
116
+ "eval_loss": 0.4238651394844055,
117
+ "eval_runtime": 32.3862,
118
+ "eval_samples_per_second": 106.126,
119
+ "eval_steps_per_second": 3.335,
120
+ "step": 8192
121
+ },
122
+ {
123
+ "epoch": 0.91,
124
+ "learning_rate": 4.093537916789614e-05,
125
+ "loss": 0.2479,
126
+ "step": 9216
127
+ },
128
+ {
129
+ "epoch": 0.91,
130
+ "eval_loss": 0.4259129762649536,
131
+ "eval_runtime": 32.4627,
132
+ "eval_samples_per_second": 105.875,
133
+ "eval_steps_per_second": 3.327,
134
+ "step": 9216
135
+ },
136
+ {
137
+ "epoch": 1.01,
138
+ "learning_rate": 3.9928199075440155e-05,
139
+ "loss": 0.2498,
140
+ "step": 10240
141
+ },
142
+ {
143
+ "epoch": 1.01,
144
+ "eval_loss": 0.4262418746948242,
145
+ "eval_runtime": 32.3999,
146
+ "eval_samples_per_second": 106.081,
147
+ "eval_steps_per_second": 3.333,
148
+ "step": 10240
149
+ },
150
+ {
151
+ "epoch": 1.11,
152
+ "learning_rate": 3.8921018982984166e-05,
153
+ "loss": 0.2467,
154
+ "step": 11264
155
+ },
156
+ {
157
+ "epoch": 1.11,
158
+ "eval_loss": 0.4267333149909973,
159
+ "eval_runtime": 32.3308,
160
+ "eval_samples_per_second": 106.307,
161
+ "eval_steps_per_second": 3.34,
162
+ "step": 11264
163
+ },
164
+ {
165
+ "epoch": 1.21,
166
+ "learning_rate": 3.791482246483722e-05,
167
+ "loss": 0.2466,
168
+ "step": 12288
169
+ },
170
+ {
171
+ "epoch": 1.21,
172
+ "eval_loss": 0.4263165295124054,
173
+ "eval_runtime": 32.4348,
174
+ "eval_samples_per_second": 105.967,
175
+ "eval_steps_per_second": 3.33,
176
+ "step": 12288
177
+ },
178
+ {
179
+ "epoch": 1.31,
180
+ "learning_rate": 3.690764237238124e-05,
181
+ "loss": 0.2449,
182
+ "step": 13312
183
+ },
184
+ {
185
+ "epoch": 1.31,
186
+ "eval_loss": 0.42505738139152527,
187
+ "eval_runtime": 32.3762,
188
+ "eval_samples_per_second": 106.158,
189
+ "eval_steps_per_second": 3.336,
190
+ "step": 13312
191
+ },
192
+ {
193
+ "epoch": 1.41,
194
+ "learning_rate": 3.590144585423429e-05,
195
+ "loss": 0.2452,
196
+ "step": 14336
197
+ },
198
+ {
199
+ "epoch": 1.41,
200
+ "eval_loss": 0.42740598320961,
201
+ "eval_runtime": 32.44,
202
+ "eval_samples_per_second": 105.949,
203
+ "eval_steps_per_second": 3.329,
204
+ "step": 14336
205
+ },
206
+ {
207
+ "epoch": 1.51,
208
+ "learning_rate": 3.489426576177831e-05,
209
+ "loss": 0.2449,
210
+ "step": 15360
211
+ },
212
+ {
213
+ "epoch": 1.51,
214
+ "eval_loss": 0.42628249526023865,
215
+ "eval_runtime": 32.3172,
216
+ "eval_samples_per_second": 106.352,
217
+ "eval_steps_per_second": 3.342,
218
+ "step": 15360
219
+ },
220
+ {
221
+ "epoch": 1.61,
222
+ "learning_rate": 3.388708566932232e-05,
223
+ "loss": 0.2444,
224
+ "step": 16384
225
+ },
226
+ {
227
+ "epoch": 1.61,
228
+ "eval_loss": 0.42398524284362793,
229
+ "eval_runtime": 32.2909,
230
+ "eval_samples_per_second": 106.439,
231
+ "eval_steps_per_second": 3.345,
232
+ "step": 16384
233
+ },
234
+ {
235
+ "epoch": 1.71,
236
+ "learning_rate": 3.287990557686633e-05,
237
+ "loss": 0.2428,
238
+ "step": 17408
239
+ },
240
+ {
241
+ "epoch": 1.71,
242
+ "eval_loss": 0.42891454696655273,
243
+ "eval_runtime": 32.3773,
244
+ "eval_samples_per_second": 106.155,
245
+ "eval_steps_per_second": 3.336,
246
+ "step": 17408
247
+ },
248
+ {
249
+ "epoch": 1.81,
250
+ "learning_rate": 3.1873709058719384e-05,
251
+ "loss": 0.2425,
252
+ "step": 18432
253
+ },
254
+ {
255
+ "epoch": 1.81,
256
+ "eval_loss": 0.4228712022304535,
257
+ "eval_runtime": 32.4341,
258
+ "eval_samples_per_second": 105.969,
259
+ "eval_steps_per_second": 3.33,
260
+ "step": 18432
261
+ },
262
+ {
263
+ "epoch": 1.91,
264
+ "learning_rate": 3.08665289662634e-05,
265
+ "loss": 0.2424,
266
+ "step": 19456
267
+ },
268
+ {
269
+ "epoch": 1.91,
270
+ "eval_loss": 0.4291061758995056,
271
+ "eval_runtime": 32.3192,
272
+ "eval_samples_per_second": 106.345,
273
+ "eval_steps_per_second": 3.342,
274
+ "step": 19456
275
+ },
276
+ {
277
+ "epoch": 2.01,
278
+ "learning_rate": 2.985934887380742e-05,
279
+ "loss": 0.2422,
280
+ "step": 20480
281
+ },
282
+ {
283
+ "epoch": 2.01,
284
+ "eval_loss": 0.4246675968170166,
285
+ "eval_runtime": 32.2862,
286
+ "eval_samples_per_second": 106.454,
287
+ "eval_steps_per_second": 3.345,
288
+ "step": 20480
289
+ },
290
+ {
291
+ "epoch": 2.12,
292
+ "learning_rate": 2.8853152355660473e-05,
293
+ "loss": 0.2397,
294
+ "step": 21504
295
+ },
296
+ {
297
+ "epoch": 2.12,
298
+ "eval_loss": 0.42707231640815735,
299
+ "eval_runtime": 32.3373,
300
+ "eval_samples_per_second": 106.286,
301
+ "eval_steps_per_second": 3.34,
302
+ "step": 21504
303
+ },
304
+ {
305
+ "epoch": 2.22,
306
+ "learning_rate": 2.7846955837513527e-05,
307
+ "loss": 0.2397,
308
+ "step": 22528
309
+ },
310
+ {
311
+ "epoch": 2.22,
312
+ "eval_loss": 0.42262786626815796,
313
+ "eval_runtime": 32.3328,
314
+ "eval_samples_per_second": 106.301,
315
+ "eval_steps_per_second": 3.34,
316
+ "step": 22528
317
+ },
318
+ {
319
+ "epoch": 2.32,
320
+ "learning_rate": 2.6839775745057538e-05,
321
+ "loss": 0.2411,
322
+ "step": 23552
323
+ },
324
+ {
325
+ "epoch": 2.32,
326
+ "eval_loss": 0.42685696482658386,
327
+ "eval_runtime": 32.3962,
328
+ "eval_samples_per_second": 106.093,
329
+ "eval_steps_per_second": 3.334,
330
+ "step": 23552
331
+ },
332
+ {
333
+ "epoch": 2.42,
334
+ "learning_rate": 2.5832595652601556e-05,
335
+ "loss": 0.2408,
336
+ "step": 24576
337
+ },
338
+ {
339
+ "epoch": 2.42,
340
+ "eval_loss": 0.42877742648124695,
341
+ "eval_runtime": 32.3163,
342
+ "eval_samples_per_second": 106.355,
343
+ "eval_steps_per_second": 3.342,
344
+ "step": 24576
345
+ },
346
+ {
347
+ "epoch": 2.52,
348
+ "learning_rate": 2.482541556014557e-05,
349
+ "loss": 0.2392,
350
+ "step": 25600
351
+ },
352
+ {
353
+ "epoch": 2.52,
354
+ "eval_loss": 0.42227810621261597,
355
+ "eval_runtime": 32.369,
356
+ "eval_samples_per_second": 106.182,
357
+ "eval_steps_per_second": 3.337,
358
+ "step": 25600
359
+ },
360
+ {
361
+ "epoch": 2.62,
362
+ "learning_rate": 2.3819219041998624e-05,
363
+ "loss": 0.2391,
364
+ "step": 26624
365
+ },
366
+ {
367
+ "epoch": 2.62,
368
+ "eval_loss": 0.4296777546405792,
369
+ "eval_runtime": 32.4315,
370
+ "eval_samples_per_second": 105.977,
371
+ "eval_steps_per_second": 3.33,
372
+ "step": 26624
373
+ },
374
+ {
375
+ "epoch": 2.72,
376
+ "learning_rate": 2.2812038949542638e-05,
377
+ "loss": 0.2385,
378
+ "step": 27648
379
+ },
380
+ {
381
+ "epoch": 2.72,
382
+ "eval_loss": 0.4252742528915405,
383
+ "eval_runtime": 32.4362,
384
+ "eval_samples_per_second": 105.962,
385
+ "eval_steps_per_second": 3.33,
386
+ "step": 27648
387
+ },
388
+ {
389
+ "epoch": 2.82,
390
+ "learning_rate": 2.180584243139569e-05,
391
+ "loss": 0.2371,
392
+ "step": 28672
393
+ },
394
+ {
395
+ "epoch": 2.82,
396
+ "eval_loss": 0.42966845631599426,
397
+ "eval_runtime": 32.3834,
398
+ "eval_samples_per_second": 106.135,
399
+ "eval_steps_per_second": 3.335,
400
+ "step": 28672
401
+ },
402
+ {
403
+ "epoch": 2.92,
404
+ "learning_rate": 2.079866233893971e-05,
405
+ "loss": 0.2373,
406
+ "step": 29696
407
+ },
408
+ {
409
+ "epoch": 2.92,
410
+ "eval_loss": 0.4231690466403961,
411
+ "eval_runtime": 32.3708,
412
+ "eval_samples_per_second": 106.176,
413
+ "eval_steps_per_second": 3.336,
414
+ "step": 29696
415
+ },
416
+ {
417
+ "epoch": 3.02,
418
+ "learning_rate": 1.97934493951018e-05,
419
+ "loss": 0.2368,
420
+ "step": 30720
421
+ },
422
+ {
423
+ "epoch": 3.02,
424
+ "eval_loss": 0.42956846952438354,
425
+ "eval_runtime": 32.3442,
426
+ "eval_samples_per_second": 106.263,
427
+ "eval_steps_per_second": 3.339,
428
+ "step": 30720
429
+ },
430
+ {
431
+ "epoch": 3.12,
432
+ "learning_rate": 1.8786269302645816e-05,
433
+ "loss": 0.2355,
434
+ "step": 31744
435
+ },
436
+ {
437
+ "epoch": 3.12,
438
+ "eval_loss": 0.43274641036987305,
439
+ "eval_runtime": 32.3365,
440
+ "eval_samples_per_second": 106.289,
441
+ "eval_steps_per_second": 3.34,
442
+ "step": 31744
443
+ },
444
+ {
445
+ "epoch": 3.22,
446
+ "learning_rate": 1.777908921018983e-05,
447
+ "loss": 0.2354,
448
+ "step": 32768
449
+ },
450
+ {
451
+ "epoch": 3.22,
452
+ "eval_loss": 0.4304845929145813,
453
+ "eval_runtime": 32.2799,
454
+ "eval_samples_per_second": 106.475,
455
+ "eval_steps_per_second": 3.346,
456
+ "step": 32768
457
+ }
458
+ ],
459
+ "max_steps": 50835,
460
+ "num_train_epochs": 5,
461
+ "total_flos": 2.7417833655415603e+17,
462
+ "trial_name": null,
463
+ "trial_params": null
464
+ }
manual_upload/checkpoint-32768/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf489f059ab44f9bc26200d314d3fc5954dabfb501b51ecc19cdc4d4be8a527
3
+ size 3579
manual_upload/checkpoint-36864/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "JammyMachina/elec-gmusic-familized-model-13-12__17-35-53",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 512,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 6,
18
+ "n_positions": 2048,
19
+ "pad_token_id": 1,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.26.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 301
33
+ }
manual_upload/checkpoint-36864/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ecad87a8937c4d031e8a7c3c520eb1b72e462241910d2d3263324e1dabdf805
3
+ size 160988613
manual_upload/checkpoint-36864/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4e7b120db5f35f11faa3adbf92eb433f85fd1655d23f2fa34efb2f6ca0797f
3
+ size 105666297
manual_upload/checkpoint-36864/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6ad785729770a83edfc217714d13846c8593f7224b6b958900618c84c55687
3
+ size 17641
manual_upload/checkpoint-36864/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715831744278105fa1b716428f132c19d1f2e1ee6185f8f11745d5beb99422d6
3
+ size 557
manual_upload/checkpoint-36864/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66adcb2e982eff562b9d0b90f4e01c5bf86d5d64f89c61e617b491e5417a40f5
3
+ size 627
manual_upload/checkpoint-36864/trainer_state.json ADDED
@@ -0,0 +1,520 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.6258483328415463,
5
+ "global_step": 36864,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 4.899281990754402e-05,
13
+ "loss": 0.2509,
14
+ "step": 1024
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "eval_loss": 0.42676058411598206,
19
+ "eval_runtime": 32.3598,
20
+ "eval_samples_per_second": 106.212,
21
+ "eval_steps_per_second": 3.337,
22
+ "step": 1024
23
+ },
24
+ {
25
+ "epoch": 0.2,
26
+ "learning_rate": 4.798563981508803e-05,
27
+ "loss": 0.2521,
28
+ "step": 2048
29
+ },
30
+ {
31
+ "epoch": 0.2,
32
+ "eval_loss": 0.4283539652824402,
33
+ "eval_runtime": 32.4193,
34
+ "eval_samples_per_second": 106.017,
35
+ "eval_steps_per_second": 3.331,
36
+ "step": 2048
37
+ },
38
+ {
39
+ "epoch": 0.3,
40
+ "learning_rate": 4.697845972263204e-05,
41
+ "loss": 0.2533,
42
+ "step": 3072
43
+ },
44
+ {
45
+ "epoch": 0.3,
46
+ "eval_loss": 0.42187923192977905,
47
+ "eval_runtime": 32.3798,
48
+ "eval_samples_per_second": 106.146,
49
+ "eval_steps_per_second": 3.335,
50
+ "step": 3072
51
+ },
52
+ {
53
+ "epoch": 0.4,
54
+ "learning_rate": 4.597127963017606e-05,
55
+ "loss": 0.2517,
56
+ "step": 4096
57
+ },
58
+ {
59
+ "epoch": 0.4,
60
+ "eval_loss": 0.42451202869415283,
61
+ "eval_runtime": 32.3385,
62
+ "eval_samples_per_second": 106.282,
63
+ "eval_steps_per_second": 3.34,
64
+ "step": 4096
65
+ },
66
+ {
67
+ "epoch": 0.5,
68
+ "learning_rate": 4.496409953772008e-05,
69
+ "loss": 0.2512,
70
+ "step": 5120
71
+ },
72
+ {
73
+ "epoch": 0.5,
74
+ "eval_loss": 0.42285656929016113,
75
+ "eval_runtime": 32.3235,
76
+ "eval_samples_per_second": 106.331,
77
+ "eval_steps_per_second": 3.341,
78
+ "step": 5120
79
+ },
80
+ {
81
+ "epoch": 0.6,
82
+ "learning_rate": 4.3956919445264097e-05,
83
+ "loss": 0.2506,
84
+ "step": 6144
85
+ },
86
+ {
87
+ "epoch": 0.6,
88
+ "eval_loss": 0.4190705716609955,
89
+ "eval_runtime": 32.4437,
90
+ "eval_samples_per_second": 105.937,
91
+ "eval_steps_per_second": 3.329,
92
+ "step": 6144
93
+ },
94
+ {
95
+ "epoch": 0.71,
96
+ "learning_rate": 4.294973935280811e-05,
97
+ "loss": 0.2512,
98
+ "step": 7168
99
+ },
100
+ {
101
+ "epoch": 0.71,
102
+ "eval_loss": 0.4247213900089264,
103
+ "eval_runtime": 32.3289,
104
+ "eval_samples_per_second": 106.314,
105
+ "eval_steps_per_second": 3.341,
106
+ "step": 7168
107
+ },
108
+ {
109
+ "epoch": 0.81,
110
+ "learning_rate": 4.194255926035212e-05,
111
+ "loss": 0.2483,
112
+ "step": 8192
113
+ },
114
+ {
115
+ "epoch": 0.81,
116
+ "eval_loss": 0.4238651394844055,
117
+ "eval_runtime": 32.3862,
118
+ "eval_samples_per_second": 106.126,
119
+ "eval_steps_per_second": 3.335,
120
+ "step": 8192
121
+ },
122
+ {
123
+ "epoch": 0.91,
124
+ "learning_rate": 4.093537916789614e-05,
125
+ "loss": 0.2479,
126
+ "step": 9216
127
+ },
128
+ {
129
+ "epoch": 0.91,
130
+ "eval_loss": 0.4259129762649536,
131
+ "eval_runtime": 32.4627,
132
+ "eval_samples_per_second": 105.875,
133
+ "eval_steps_per_second": 3.327,
134
+ "step": 9216
135
+ },
136
+ {
137
+ "epoch": 1.01,
138
+ "learning_rate": 3.9928199075440155e-05,
139
+ "loss": 0.2498,
140
+ "step": 10240
141
+ },
142
+ {
143
+ "epoch": 1.01,
144
+ "eval_loss": 0.4262418746948242,
145
+ "eval_runtime": 32.3999,
146
+ "eval_samples_per_second": 106.081,
147
+ "eval_steps_per_second": 3.333,
148
+ "step": 10240
149
+ },
150
+ {
151
+ "epoch": 1.11,
152
+ "learning_rate": 3.8921018982984166e-05,
153
+ "loss": 0.2467,
154
+ "step": 11264
155
+ },
156
+ {
157
+ "epoch": 1.11,
158
+ "eval_loss": 0.4267333149909973,
159
+ "eval_runtime": 32.3308,
160
+ "eval_samples_per_second": 106.307,
161
+ "eval_steps_per_second": 3.34,
162
+ "step": 11264
163
+ },
164
+ {
165
+ "epoch": 1.21,
166
+ "learning_rate": 3.791482246483722e-05,
167
+ "loss": 0.2466,
168
+ "step": 12288
169
+ },
170
+ {
171
+ "epoch": 1.21,
172
+ "eval_loss": 0.4263165295124054,
173
+ "eval_runtime": 32.4348,
174
+ "eval_samples_per_second": 105.967,
175
+ "eval_steps_per_second": 3.33,
176
+ "step": 12288
177
+ },
178
+ {
179
+ "epoch": 1.31,
180
+ "learning_rate": 3.690764237238124e-05,
181
+ "loss": 0.2449,
182
+ "step": 13312
183
+ },
184
+ {
185
+ "epoch": 1.31,
186
+ "eval_loss": 0.42505738139152527,
187
+ "eval_runtime": 32.3762,
188
+ "eval_samples_per_second": 106.158,
189
+ "eval_steps_per_second": 3.336,
190
+ "step": 13312
191
+ },
192
+ {
193
+ "epoch": 1.41,
194
+ "learning_rate": 3.590144585423429e-05,
195
+ "loss": 0.2452,
196
+ "step": 14336
197
+ },
198
+ {
199
+ "epoch": 1.41,
200
+ "eval_loss": 0.42740598320961,
201
+ "eval_runtime": 32.44,
202
+ "eval_samples_per_second": 105.949,
203
+ "eval_steps_per_second": 3.329,
204
+ "step": 14336
205
+ },
206
+ {
207
+ "epoch": 1.51,
208
+ "learning_rate": 3.489426576177831e-05,
209
+ "loss": 0.2449,
210
+ "step": 15360
211
+ },
212
+ {
213
+ "epoch": 1.51,
214
+ "eval_loss": 0.42628249526023865,
215
+ "eval_runtime": 32.3172,
216
+ "eval_samples_per_second": 106.352,
217
+ "eval_steps_per_second": 3.342,
218
+ "step": 15360
219
+ },
220
+ {
221
+ "epoch": 1.61,
222
+ "learning_rate": 3.388708566932232e-05,
223
+ "loss": 0.2444,
224
+ "step": 16384
225
+ },
226
+ {
227
+ "epoch": 1.61,
228
+ "eval_loss": 0.42398524284362793,
229
+ "eval_runtime": 32.2909,
230
+ "eval_samples_per_second": 106.439,
231
+ "eval_steps_per_second": 3.345,
232
+ "step": 16384
233
+ },
234
+ {
235
+ "epoch": 1.71,
236
+ "learning_rate": 3.287990557686633e-05,
237
+ "loss": 0.2428,
238
+ "step": 17408
239
+ },
240
+ {
241
+ "epoch": 1.71,
242
+ "eval_loss": 0.42891454696655273,
243
+ "eval_runtime": 32.3773,
244
+ "eval_samples_per_second": 106.155,
245
+ "eval_steps_per_second": 3.336,
246
+ "step": 17408
247
+ },
248
+ {
249
+ "epoch": 1.81,
250
+ "learning_rate": 3.1873709058719384e-05,
251
+ "loss": 0.2425,
252
+ "step": 18432
253
+ },
254
+ {
255
+ "epoch": 1.81,
256
+ "eval_loss": 0.4228712022304535,
257
+ "eval_runtime": 32.4341,
258
+ "eval_samples_per_second": 105.969,
259
+ "eval_steps_per_second": 3.33,
260
+ "step": 18432
261
+ },
262
+ {
263
+ "epoch": 1.91,
264
+ "learning_rate": 3.08665289662634e-05,
265
+ "loss": 0.2424,
266
+ "step": 19456
267
+ },
268
+ {
269
+ "epoch": 1.91,
270
+ "eval_loss": 0.4291061758995056,
271
+ "eval_runtime": 32.3192,
272
+ "eval_samples_per_second": 106.345,
273
+ "eval_steps_per_second": 3.342,
274
+ "step": 19456
275
+ },
276
+ {
277
+ "epoch": 2.01,
278
+ "learning_rate": 2.985934887380742e-05,
279
+ "loss": 0.2422,
280
+ "step": 20480
281
+ },
282
+ {
283
+ "epoch": 2.01,
284
+ "eval_loss": 0.4246675968170166,
285
+ "eval_runtime": 32.2862,
286
+ "eval_samples_per_second": 106.454,
287
+ "eval_steps_per_second": 3.345,
288
+ "step": 20480
289
+ },
290
+ {
291
+ "epoch": 2.12,
292
+ "learning_rate": 2.8853152355660473e-05,
293
+ "loss": 0.2397,
294
+ "step": 21504
295
+ },
296
+ {
297
+ "epoch": 2.12,
298
+ "eval_loss": 0.42707231640815735,
299
+ "eval_runtime": 32.3373,
300
+ "eval_samples_per_second": 106.286,
301
+ "eval_steps_per_second": 3.34,
302
+ "step": 21504
303
+ },
304
+ {
305
+ "epoch": 2.22,
306
+ "learning_rate": 2.7846955837513527e-05,
307
+ "loss": 0.2397,
308
+ "step": 22528
309
+ },
310
+ {
311
+ "epoch": 2.22,
312
+ "eval_loss": 0.42262786626815796,
313
+ "eval_runtime": 32.3328,
314
+ "eval_samples_per_second": 106.301,
315
+ "eval_steps_per_second": 3.34,
316
+ "step": 22528
317
+ },
318
+ {
319
+ "epoch": 2.32,
320
+ "learning_rate": 2.6839775745057538e-05,
321
+ "loss": 0.2411,
322
+ "step": 23552
323
+ },
324
+ {
325
+ "epoch": 2.32,
326
+ "eval_loss": 0.42685696482658386,
327
+ "eval_runtime": 32.3962,
328
+ "eval_samples_per_second": 106.093,
329
+ "eval_steps_per_second": 3.334,
330
+ "step": 23552
331
+ },
332
+ {
333
+ "epoch": 2.42,
334
+ "learning_rate": 2.5832595652601556e-05,
335
+ "loss": 0.2408,
336
+ "step": 24576
337
+ },
338
+ {
339
+ "epoch": 2.42,
340
+ "eval_loss": 0.42877742648124695,
341
+ "eval_runtime": 32.3163,
342
+ "eval_samples_per_second": 106.355,
343
+ "eval_steps_per_second": 3.342,
344
+ "step": 24576
345
+ },
346
+ {
347
+ "epoch": 2.52,
348
+ "learning_rate": 2.482541556014557e-05,
349
+ "loss": 0.2392,
350
+ "step": 25600
351
+ },
352
+ {
353
+ "epoch": 2.52,
354
+ "eval_loss": 0.42227810621261597,
355
+ "eval_runtime": 32.369,
356
+ "eval_samples_per_second": 106.182,
357
+ "eval_steps_per_second": 3.337,
358
+ "step": 25600
359
+ },
360
+ {
361
+ "epoch": 2.62,
362
+ "learning_rate": 2.3819219041998624e-05,
363
+ "loss": 0.2391,
364
+ "step": 26624
365
+ },
366
+ {
367
+ "epoch": 2.62,
368
+ "eval_loss": 0.4296777546405792,
369
+ "eval_runtime": 32.4315,
370
+ "eval_samples_per_second": 105.977,
371
+ "eval_steps_per_second": 3.33,
372
+ "step": 26624
373
+ },
374
+ {
375
+ "epoch": 2.72,
376
+ "learning_rate": 2.2812038949542638e-05,
377
+ "loss": 0.2385,
378
+ "step": 27648
379
+ },
380
+ {
381
+ "epoch": 2.72,
382
+ "eval_loss": 0.4252742528915405,
383
+ "eval_runtime": 32.4362,
384
+ "eval_samples_per_second": 105.962,
385
+ "eval_steps_per_second": 3.33,
386
+ "step": 27648
387
+ },
388
+ {
389
+ "epoch": 2.82,
390
+ "learning_rate": 2.180584243139569e-05,
391
+ "loss": 0.2371,
392
+ "step": 28672
393
+ },
394
+ {
395
+ "epoch": 2.82,
396
+ "eval_loss": 0.42966845631599426,
397
+ "eval_runtime": 32.3834,
398
+ "eval_samples_per_second": 106.135,
399
+ "eval_steps_per_second": 3.335,
400
+ "step": 28672
401
+ },
402
+ {
403
+ "epoch": 2.92,
404
+ "learning_rate": 2.079866233893971e-05,
405
+ "loss": 0.2373,
406
+ "step": 29696
407
+ },
408
+ {
409
+ "epoch": 2.92,
410
+ "eval_loss": 0.4231690466403961,
411
+ "eval_runtime": 32.3708,
412
+ "eval_samples_per_second": 106.176,
413
+ "eval_steps_per_second": 3.336,
414
+ "step": 29696
415
+ },
416
+ {
417
+ "epoch": 3.02,
418
+ "learning_rate": 1.97934493951018e-05,
419
+ "loss": 0.2368,
420
+ "step": 30720
421
+ },
422
+ {
423
+ "epoch": 3.02,
424
+ "eval_loss": 0.42956846952438354,
425
+ "eval_runtime": 32.3442,
426
+ "eval_samples_per_second": 106.263,
427
+ "eval_steps_per_second": 3.339,
428
+ "step": 30720
429
+ },
430
+ {
431
+ "epoch": 3.12,
432
+ "learning_rate": 1.8786269302645816e-05,
433
+ "loss": 0.2355,
434
+ "step": 31744
435
+ },
436
+ {
437
+ "epoch": 3.12,
438
+ "eval_loss": 0.43274641036987305,
439
+ "eval_runtime": 32.3365,
440
+ "eval_samples_per_second": 106.289,
441
+ "eval_steps_per_second": 3.34,
442
+ "step": 31744
443
+ },
444
+ {
445
+ "epoch": 3.22,
446
+ "learning_rate": 1.777908921018983e-05,
447
+ "loss": 0.2354,
448
+ "step": 32768
449
+ },
450
+ {
451
+ "epoch": 3.22,
452
+ "eval_loss": 0.4304845929145813,
453
+ "eval_runtime": 32.2799,
454
+ "eval_samples_per_second": 106.475,
455
+ "eval_steps_per_second": 3.346,
456
+ "step": 32768
457
+ },
458
+ {
459
+ "epoch": 3.32,
460
+ "learning_rate": 1.6771909117733845e-05,
461
+ "loss": 0.2345,
462
+ "step": 33792
463
+ },
464
+ {
465
+ "epoch": 3.32,
466
+ "eval_loss": 0.4286292791366577,
467
+ "eval_runtime": 32.4389,
468
+ "eval_samples_per_second": 105.953,
469
+ "eval_steps_per_second": 3.329,
470
+ "step": 33792
471
+ },
472
+ {
473
+ "epoch": 3.42,
474
+ "learning_rate": 1.5765712599586898e-05,
475
+ "loss": 0.2355,
476
+ "step": 34816
477
+ },
478
+ {
479
+ "epoch": 3.42,
480
+ "eval_loss": 0.4350430965423584,
481
+ "eval_runtime": 32.3371,
482
+ "eval_samples_per_second": 106.287,
483
+ "eval_steps_per_second": 3.34,
484
+ "step": 34816
485
+ },
486
+ {
487
+ "epoch": 3.53,
488
+ "learning_rate": 1.4758532507130915e-05,
489
+ "loss": 0.2353,
490
+ "step": 35840
491
+ },
492
+ {
493
+ "epoch": 3.53,
494
+ "eval_loss": 0.4268806278705597,
495
+ "eval_runtime": 32.3956,
496
+ "eval_samples_per_second": 106.095,
497
+ "eval_steps_per_second": 3.334,
498
+ "step": 35840
499
+ },
500
+ {
501
+ "epoch": 3.63,
502
+ "learning_rate": 1.375233598898397e-05,
503
+ "loss": 0.2351,
504
+ "step": 36864
505
+ },
506
+ {
507
+ "epoch": 3.63,
508
+ "eval_loss": 0.43005427718162537,
509
+ "eval_runtime": 32.3262,
510
+ "eval_samples_per_second": 106.323,
511
+ "eval_steps_per_second": 3.341,
512
+ "step": 36864
513
+ }
514
+ ],
515
+ "max_steps": 50835,
516
+ "num_train_epochs": 5,
517
+ "total_flos": 3.084517632593756e+17,
518
+ "trial_name": null,
519
+ "trial_params": null
520
+ }
manual_upload/checkpoint-36864/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf489f059ab44f9bc26200d314d3fc5954dabfb501b51ecc19cdc4d4be8a527
3
+ size 3579
manual_upload/checkpoint-40960/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "JammyMachina/elec-gmusic-familized-model-13-12__17-35-53",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 512,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 6,
18
+ "n_positions": 2048,
19
+ "pad_token_id": 1,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.26.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 301
33
+ }
manual_upload/checkpoint-40960/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194d9ac39fd6dd0aaf4f3a0f1d87e4e89c633f97b4d433de39e518540f86b6b0
3
+ size 160988613
manual_upload/checkpoint-40960/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8efb0bfe8122bfb4130dae55d638dc709a3ecb9c674f8fac344a75876a3f5bfc
3
+ size 105666297
manual_upload/checkpoint-40960/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e855b6afcb0da09e80c4b9468135e5f0c700df448590420b405f2eca6b418a8b
3
+ size 17641
manual_upload/checkpoint-40960/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c25c6f024cb9b63e362884769ba537bb0d48ae621b9dd00c56115f2a525a670
3
+ size 557
manual_upload/checkpoint-40960/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f56085a1a47b3b808c6a2c228c3ef37976e4c202f414e76879f0ccc3f1c700
3
+ size 627
manual_upload/checkpoint-40960/trainer_state.json ADDED
@@ -0,0 +1,576 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.02872036982394,
5
+ "global_step": 40960,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 4.899281990754402e-05,
13
+ "loss": 0.2509,
14
+ "step": 1024
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "eval_loss": 0.42676058411598206,
19
+ "eval_runtime": 32.3598,
20
+ "eval_samples_per_second": 106.212,
21
+ "eval_steps_per_second": 3.337,
22
+ "step": 1024
23
+ },
24
+ {
25
+ "epoch": 0.2,
26
+ "learning_rate": 4.798563981508803e-05,
27
+ "loss": 0.2521,
28
+ "step": 2048
29
+ },
30
+ {
31
+ "epoch": 0.2,
32
+ "eval_loss": 0.4283539652824402,
33
+ "eval_runtime": 32.4193,
34
+ "eval_samples_per_second": 106.017,
35
+ "eval_steps_per_second": 3.331,
36
+ "step": 2048
37
+ },
38
+ {
39
+ "epoch": 0.3,
40
+ "learning_rate": 4.697845972263204e-05,
41
+ "loss": 0.2533,
42
+ "step": 3072
43
+ },
44
+ {
45
+ "epoch": 0.3,
46
+ "eval_loss": 0.42187923192977905,
47
+ "eval_runtime": 32.3798,
48
+ "eval_samples_per_second": 106.146,
49
+ "eval_steps_per_second": 3.335,
50
+ "step": 3072
51
+ },
52
+ {
53
+ "epoch": 0.4,
54
+ "learning_rate": 4.597127963017606e-05,
55
+ "loss": 0.2517,
56
+ "step": 4096
57
+ },
58
+ {
59
+ "epoch": 0.4,
60
+ "eval_loss": 0.42451202869415283,
61
+ "eval_runtime": 32.3385,
62
+ "eval_samples_per_second": 106.282,
63
+ "eval_steps_per_second": 3.34,
64
+ "step": 4096
65
+ },
66
+ {
67
+ "epoch": 0.5,
68
+ "learning_rate": 4.496409953772008e-05,
69
+ "loss": 0.2512,
70
+ "step": 5120
71
+ },
72
+ {
73
+ "epoch": 0.5,
74
+ "eval_loss": 0.42285656929016113,
75
+ "eval_runtime": 32.3235,
76
+ "eval_samples_per_second": 106.331,
77
+ "eval_steps_per_second": 3.341,
78
+ "step": 5120
79
+ },
80
+ {
81
+ "epoch": 0.6,
82
+ "learning_rate": 4.3956919445264097e-05,
83
+ "loss": 0.2506,
84
+ "step": 6144
85
+ },
86
+ {
87
+ "epoch": 0.6,
88
+ "eval_loss": 0.4190705716609955,
89
+ "eval_runtime": 32.4437,
90
+ "eval_samples_per_second": 105.937,
91
+ "eval_steps_per_second": 3.329,
92
+ "step": 6144
93
+ },
94
+ {
95
+ "epoch": 0.71,
96
+ "learning_rate": 4.294973935280811e-05,
97
+ "loss": 0.2512,
98
+ "step": 7168
99
+ },
100
+ {
101
+ "epoch": 0.71,
102
+ "eval_loss": 0.4247213900089264,
103
+ "eval_runtime": 32.3289,
104
+ "eval_samples_per_second": 106.314,
105
+ "eval_steps_per_second": 3.341,
106
+ "step": 7168
107
+ },
108
+ {
109
+ "epoch": 0.81,
110
+ "learning_rate": 4.194255926035212e-05,
111
+ "loss": 0.2483,
112
+ "step": 8192
113
+ },
114
+ {
115
+ "epoch": 0.81,
116
+ "eval_loss": 0.4238651394844055,
117
+ "eval_runtime": 32.3862,
118
+ "eval_samples_per_second": 106.126,
119
+ "eval_steps_per_second": 3.335,
120
+ "step": 8192
121
+ },
122
+ {
123
+ "epoch": 0.91,
124
+ "learning_rate": 4.093537916789614e-05,
125
+ "loss": 0.2479,
126
+ "step": 9216
127
+ },
128
+ {
129
+ "epoch": 0.91,
130
+ "eval_loss": 0.4259129762649536,
131
+ "eval_runtime": 32.4627,
132
+ "eval_samples_per_second": 105.875,
133
+ "eval_steps_per_second": 3.327,
134
+ "step": 9216
135
+ },
136
+ {
137
+ "epoch": 1.01,
138
+ "learning_rate": 3.9928199075440155e-05,
139
+ "loss": 0.2498,
140
+ "step": 10240
141
+ },
142
+ {
143
+ "epoch": 1.01,
144
+ "eval_loss": 0.4262418746948242,
145
+ "eval_runtime": 32.3999,
146
+ "eval_samples_per_second": 106.081,
147
+ "eval_steps_per_second": 3.333,
148
+ "step": 10240
149
+ },
150
+ {
151
+ "epoch": 1.11,
152
+ "learning_rate": 3.8921018982984166e-05,
153
+ "loss": 0.2467,
154
+ "step": 11264
155
+ },
156
+ {
157
+ "epoch": 1.11,
158
+ "eval_loss": 0.4267333149909973,
159
+ "eval_runtime": 32.3308,
160
+ "eval_samples_per_second": 106.307,
161
+ "eval_steps_per_second": 3.34,
162
+ "step": 11264
163
+ },
164
+ {
165
+ "epoch": 1.21,
166
+ "learning_rate": 3.791482246483722e-05,
167
+ "loss": 0.2466,
168
+ "step": 12288
169
+ },
170
+ {
171
+ "epoch": 1.21,
172
+ "eval_loss": 0.4263165295124054,
173
+ "eval_runtime": 32.4348,
174
+ "eval_samples_per_second": 105.967,
175
+ "eval_steps_per_second": 3.33,
176
+ "step": 12288
177
+ },
178
+ {
179
+ "epoch": 1.31,
180
+ "learning_rate": 3.690764237238124e-05,
181
+ "loss": 0.2449,
182
+ "step": 13312
183
+ },
184
+ {
185
+ "epoch": 1.31,
186
+ "eval_loss": 0.42505738139152527,
187
+ "eval_runtime": 32.3762,
188
+ "eval_samples_per_second": 106.158,
189
+ "eval_steps_per_second": 3.336,
190
+ "step": 13312
191
+ },
192
+ {
193
+ "epoch": 1.41,
194
+ "learning_rate": 3.590144585423429e-05,
195
+ "loss": 0.2452,
196
+ "step": 14336
197
+ },
198
+ {
199
+ "epoch": 1.41,
200
+ "eval_loss": 0.42740598320961,
201
+ "eval_runtime": 32.44,
202
+ "eval_samples_per_second": 105.949,
203
+ "eval_steps_per_second": 3.329,
204
+ "step": 14336
205
+ },
206
+ {
207
+ "epoch": 1.51,
208
+ "learning_rate": 3.489426576177831e-05,
209
+ "loss": 0.2449,
210
+ "step": 15360
211
+ },
212
+ {
213
+ "epoch": 1.51,
214
+ "eval_loss": 0.42628249526023865,
215
+ "eval_runtime": 32.3172,
216
+ "eval_samples_per_second": 106.352,
217
+ "eval_steps_per_second": 3.342,
218
+ "step": 15360
219
+ },
220
+ {
221
+ "epoch": 1.61,
222
+ "learning_rate": 3.388708566932232e-05,
223
+ "loss": 0.2444,
224
+ "step": 16384
225
+ },
226
+ {
227
+ "epoch": 1.61,
228
+ "eval_loss": 0.42398524284362793,
229
+ "eval_runtime": 32.2909,
230
+ "eval_samples_per_second": 106.439,
231
+ "eval_steps_per_second": 3.345,
232
+ "step": 16384
233
+ },
234
+ {
235
+ "epoch": 1.71,
236
+ "learning_rate": 3.287990557686633e-05,
237
+ "loss": 0.2428,
238
+ "step": 17408
239
+ },
240
+ {
241
+ "epoch": 1.71,
242
+ "eval_loss": 0.42891454696655273,
243
+ "eval_runtime": 32.3773,
244
+ "eval_samples_per_second": 106.155,
245
+ "eval_steps_per_second": 3.336,
246
+ "step": 17408
247
+ },
248
+ {
249
+ "epoch": 1.81,
250
+ "learning_rate": 3.1873709058719384e-05,
251
+ "loss": 0.2425,
252
+ "step": 18432
253
+ },
254
+ {
255
+ "epoch": 1.81,
256
+ "eval_loss": 0.4228712022304535,
257
+ "eval_runtime": 32.4341,
258
+ "eval_samples_per_second": 105.969,
259
+ "eval_steps_per_second": 3.33,
260
+ "step": 18432
261
+ },
262
+ {
263
+ "epoch": 1.91,
264
+ "learning_rate": 3.08665289662634e-05,
265
+ "loss": 0.2424,
266
+ "step": 19456
267
+ },
268
+ {
269
+ "epoch": 1.91,
270
+ "eval_loss": 0.4291061758995056,
271
+ "eval_runtime": 32.3192,
272
+ "eval_samples_per_second": 106.345,
273
+ "eval_steps_per_second": 3.342,
274
+ "step": 19456
275
+ },
276
+ {
277
+ "epoch": 2.01,
278
+ "learning_rate": 2.985934887380742e-05,
279
+ "loss": 0.2422,
280
+ "step": 20480
281
+ },
282
+ {
283
+ "epoch": 2.01,
284
+ "eval_loss": 0.4246675968170166,
285
+ "eval_runtime": 32.2862,
286
+ "eval_samples_per_second": 106.454,
287
+ "eval_steps_per_second": 3.345,
288
+ "step": 20480
289
+ },
290
+ {
291
+ "epoch": 2.12,
292
+ "learning_rate": 2.8853152355660473e-05,
293
+ "loss": 0.2397,
294
+ "step": 21504
295
+ },
296
+ {
297
+ "epoch": 2.12,
298
+ "eval_loss": 0.42707231640815735,
299
+ "eval_runtime": 32.3373,
300
+ "eval_samples_per_second": 106.286,
301
+ "eval_steps_per_second": 3.34,
302
+ "step": 21504
303
+ },
304
+ {
305
+ "epoch": 2.22,
306
+ "learning_rate": 2.7846955837513527e-05,
307
+ "loss": 0.2397,
308
+ "step": 22528
309
+ },
310
+ {
311
+ "epoch": 2.22,
312
+ "eval_loss": 0.42262786626815796,
313
+ "eval_runtime": 32.3328,
314
+ "eval_samples_per_second": 106.301,
315
+ "eval_steps_per_second": 3.34,
316
+ "step": 22528
317
+ },
318
+ {
319
+ "epoch": 2.32,
320
+ "learning_rate": 2.6839775745057538e-05,
321
+ "loss": 0.2411,
322
+ "step": 23552
323
+ },
324
+ {
325
+ "epoch": 2.32,
326
+ "eval_loss": 0.42685696482658386,
327
+ "eval_runtime": 32.3962,
328
+ "eval_samples_per_second": 106.093,
329
+ "eval_steps_per_second": 3.334,
330
+ "step": 23552
331
+ },
332
+ {
333
+ "epoch": 2.42,
334
+ "learning_rate": 2.5832595652601556e-05,
335
+ "loss": 0.2408,
336
+ "step": 24576
337
+ },
338
+ {
339
+ "epoch": 2.42,
340
+ "eval_loss": 0.42877742648124695,
341
+ "eval_runtime": 32.3163,
342
+ "eval_samples_per_second": 106.355,
343
+ "eval_steps_per_second": 3.342,
344
+ "step": 24576
345
+ },
346
+ {
347
+ "epoch": 2.52,
348
+ "learning_rate": 2.482541556014557e-05,
349
+ "loss": 0.2392,
350
+ "step": 25600
351
+ },
352
+ {
353
+ "epoch": 2.52,
354
+ "eval_loss": 0.42227810621261597,
355
+ "eval_runtime": 32.369,
356
+ "eval_samples_per_second": 106.182,
357
+ "eval_steps_per_second": 3.337,
358
+ "step": 25600
359
+ },
360
+ {
361
+ "epoch": 2.62,
362
+ "learning_rate": 2.3819219041998624e-05,
363
+ "loss": 0.2391,
364
+ "step": 26624
365
+ },
366
+ {
367
+ "epoch": 2.62,
368
+ "eval_loss": 0.4296777546405792,
369
+ "eval_runtime": 32.4315,
370
+ "eval_samples_per_second": 105.977,
371
+ "eval_steps_per_second": 3.33,
372
+ "step": 26624
373
+ },
374
+ {
375
+ "epoch": 2.72,
376
+ "learning_rate": 2.2812038949542638e-05,
377
+ "loss": 0.2385,
378
+ "step": 27648
379
+ },
380
+ {
381
+ "epoch": 2.72,
382
+ "eval_loss": 0.4252742528915405,
383
+ "eval_runtime": 32.4362,
384
+ "eval_samples_per_second": 105.962,
385
+ "eval_steps_per_second": 3.33,
386
+ "step": 27648
387
+ },
388
+ {
389
+ "epoch": 2.82,
390
+ "learning_rate": 2.180584243139569e-05,
391
+ "loss": 0.2371,
392
+ "step": 28672
393
+ },
394
+ {
395
+ "epoch": 2.82,
396
+ "eval_loss": 0.42966845631599426,
397
+ "eval_runtime": 32.3834,
398
+ "eval_samples_per_second": 106.135,
399
+ "eval_steps_per_second": 3.335,
400
+ "step": 28672
401
+ },
402
+ {
403
+ "epoch": 2.92,
404
+ "learning_rate": 2.079866233893971e-05,
405
+ "loss": 0.2373,
406
+ "step": 29696
407
+ },
408
+ {
409
+ "epoch": 2.92,
410
+ "eval_loss": 0.4231690466403961,
411
+ "eval_runtime": 32.3708,
412
+ "eval_samples_per_second": 106.176,
413
+ "eval_steps_per_second": 3.336,
414
+ "step": 29696
415
+ },
416
+ {
417
+ "epoch": 3.02,
418
+ "learning_rate": 1.97934493951018e-05,
419
+ "loss": 0.2368,
420
+ "step": 30720
421
+ },
422
+ {
423
+ "epoch": 3.02,
424
+ "eval_loss": 0.42956846952438354,
425
+ "eval_runtime": 32.3442,
426
+ "eval_samples_per_second": 106.263,
427
+ "eval_steps_per_second": 3.339,
428
+ "step": 30720
429
+ },
430
+ {
431
+ "epoch": 3.12,
432
+ "learning_rate": 1.8786269302645816e-05,
433
+ "loss": 0.2355,
434
+ "step": 31744
435
+ },
436
+ {
437
+ "epoch": 3.12,
438
+ "eval_loss": 0.43274641036987305,
439
+ "eval_runtime": 32.3365,
440
+ "eval_samples_per_second": 106.289,
441
+ "eval_steps_per_second": 3.34,
442
+ "step": 31744
443
+ },
444
+ {
445
+ "epoch": 3.22,
446
+ "learning_rate": 1.777908921018983e-05,
447
+ "loss": 0.2354,
448
+ "step": 32768
449
+ },
450
+ {
451
+ "epoch": 3.22,
452
+ "eval_loss": 0.4304845929145813,
453
+ "eval_runtime": 32.2799,
454
+ "eval_samples_per_second": 106.475,
455
+ "eval_steps_per_second": 3.346,
456
+ "step": 32768
457
+ },
458
+ {
459
+ "epoch": 3.32,
460
+ "learning_rate": 1.6771909117733845e-05,
461
+ "loss": 0.2345,
462
+ "step": 33792
463
+ },
464
+ {
465
+ "epoch": 3.32,
466
+ "eval_loss": 0.4286292791366577,
467
+ "eval_runtime": 32.4389,
468
+ "eval_samples_per_second": 105.953,
469
+ "eval_steps_per_second": 3.329,
470
+ "step": 33792
471
+ },
472
+ {
473
+ "epoch": 3.42,
474
+ "learning_rate": 1.5765712599586898e-05,
475
+ "loss": 0.2355,
476
+ "step": 34816
477
+ },
478
+ {
479
+ "epoch": 3.42,
480
+ "eval_loss": 0.4350430965423584,
481
+ "eval_runtime": 32.3371,
482
+ "eval_samples_per_second": 106.287,
483
+ "eval_steps_per_second": 3.34,
484
+ "step": 34816
485
+ },
486
+ {
487
+ "epoch": 3.53,
488
+ "learning_rate": 1.4758532507130915e-05,
489
+ "loss": 0.2353,
490
+ "step": 35840
491
+ },
492
+ {
493
+ "epoch": 3.53,
494
+ "eval_loss": 0.4268806278705597,
495
+ "eval_runtime": 32.3956,
496
+ "eval_samples_per_second": 106.095,
497
+ "eval_steps_per_second": 3.334,
498
+ "step": 35840
499
+ },
500
+ {
501
+ "epoch": 3.63,
502
+ "learning_rate": 1.375233598898397e-05,
503
+ "loss": 0.2351,
504
+ "step": 36864
505
+ },
506
+ {
507
+ "epoch": 3.63,
508
+ "eval_loss": 0.43005427718162537,
509
+ "eval_runtime": 32.3262,
510
+ "eval_samples_per_second": 106.323,
511
+ "eval_steps_per_second": 3.341,
512
+ "step": 36864
513
+ },
514
+ {
515
+ "epoch": 3.73,
516
+ "learning_rate": 1.2745155896527982e-05,
517
+ "loss": 0.2336,
518
+ "step": 37888
519
+ },
520
+ {
521
+ "epoch": 3.73,
522
+ "eval_loss": 0.4301435649394989,
523
+ "eval_runtime": 32.4031,
524
+ "eval_samples_per_second": 106.07,
525
+ "eval_steps_per_second": 3.333,
526
+ "step": 37888
527
+ },
528
+ {
529
+ "epoch": 3.83,
530
+ "learning_rate": 1.1737975804071997e-05,
531
+ "loss": 0.2344,
532
+ "step": 38912
533
+ },
534
+ {
535
+ "epoch": 3.83,
536
+ "eval_loss": 0.43188127875328064,
537
+ "eval_runtime": 32.3893,
538
+ "eval_samples_per_second": 106.115,
539
+ "eval_steps_per_second": 3.334,
540
+ "step": 38912
541
+ },
542
+ {
543
+ "epoch": 3.93,
544
+ "learning_rate": 1.0730795711616013e-05,
545
+ "loss": 0.2339,
546
+ "step": 39936
547
+ },
548
+ {
549
+ "epoch": 3.93,
550
+ "eval_loss": 0.4304964244365692,
551
+ "eval_runtime": 32.4411,
552
+ "eval_samples_per_second": 105.946,
553
+ "eval_steps_per_second": 3.329,
554
+ "step": 39936
555
+ },
556
+ {
557
+ "epoch": 4.03,
558
+ "learning_rate": 9.724599193469066e-06,
559
+ "loss": 0.2326,
560
+ "step": 40960
561
+ },
562
+ {
563
+ "epoch": 4.03,
564
+ "eval_loss": 0.4298175573348999,
565
+ "eval_runtime": 32.3377,
566
+ "eval_samples_per_second": 106.285,
567
+ "eval_steps_per_second": 3.34,
568
+ "step": 40960
569
+ }
570
+ ],
571
+ "max_steps": 50835,
572
+ "num_train_epochs": 5,
573
+ "total_flos": 3.427221683544392e+17,
574
+ "trial_name": null,
575
+ "trial_params": null
576
+ }
manual_upload/checkpoint-40960/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf489f059ab44f9bc26200d314d3fc5954dabfb501b51ecc19cdc4d4be8a527
3
+ size 3579
manual_upload/checkpoint-45056/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "JammyMachina/elec-gmusic-familized-model-13-12__17-35-53",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 512,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 6,
18
+ "n_positions": 2048,
19
+ "pad_token_id": 1,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.26.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 301
33
+ }
manual_upload/checkpoint-45056/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb25a88b4f868be37a211bbfe71588d79f1c927d69f5d3f11133e0cbe67517d
3
+ size 160988613
manual_upload/checkpoint-45056/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2a69e8041c07b0e1b540e5b51b1b044c092342f9fd2232de400c7e53171958
3
+ size 105666297
manual_upload/checkpoint-45056/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:607ec2b514f7c4db26f95270a92ea283778558468bedb1530ef4abddb3181280
3
+ size 17641
manual_upload/checkpoint-45056/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ee5373288a1b404edc3bf8f1daf186df8ebf4b253d245d2ab25ee604c2c6d8
3
+ size 557
manual_upload/checkpoint-45056/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f4bc96987f4affa8d95c834faa24ef6b88121c6d49156ae5db03f559ceb3af
3
+ size 627
manual_upload/checkpoint-45056/trainer_state.json ADDED
@@ -0,0 +1,632 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.431592406806335,
5
+ "global_step": 45056,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 4.899281990754402e-05,
13
+ "loss": 0.2509,
14
+ "step": 1024
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "eval_loss": 0.42676058411598206,
19
+ "eval_runtime": 32.3598,
20
+ "eval_samples_per_second": 106.212,
21
+ "eval_steps_per_second": 3.337,
22
+ "step": 1024
23
+ },
24
+ {
25
+ "epoch": 0.2,
26
+ "learning_rate": 4.798563981508803e-05,
27
+ "loss": 0.2521,
28
+ "step": 2048
29
+ },
30
+ {
31
+ "epoch": 0.2,
32
+ "eval_loss": 0.4283539652824402,
33
+ "eval_runtime": 32.4193,
34
+ "eval_samples_per_second": 106.017,
35
+ "eval_steps_per_second": 3.331,
36
+ "step": 2048
37
+ },
38
+ {
39
+ "epoch": 0.3,
40
+ "learning_rate": 4.697845972263204e-05,
41
+ "loss": 0.2533,
42
+ "step": 3072
43
+ },
44
+ {
45
+ "epoch": 0.3,
46
+ "eval_loss": 0.42187923192977905,
47
+ "eval_runtime": 32.3798,
48
+ "eval_samples_per_second": 106.146,
49
+ "eval_steps_per_second": 3.335,
50
+ "step": 3072
51
+ },
52
+ {
53
+ "epoch": 0.4,
54
+ "learning_rate": 4.597127963017606e-05,
55
+ "loss": 0.2517,
56
+ "step": 4096
57
+ },
58
+ {
59
+ "epoch": 0.4,
60
+ "eval_loss": 0.42451202869415283,
61
+ "eval_runtime": 32.3385,
62
+ "eval_samples_per_second": 106.282,
63
+ "eval_steps_per_second": 3.34,
64
+ "step": 4096
65
+ },
66
+ {
67
+ "epoch": 0.5,
68
+ "learning_rate": 4.496409953772008e-05,
69
+ "loss": 0.2512,
70
+ "step": 5120
71
+ },
72
+ {
73
+ "epoch": 0.5,
74
+ "eval_loss": 0.42285656929016113,
75
+ "eval_runtime": 32.3235,
76
+ "eval_samples_per_second": 106.331,
77
+ "eval_steps_per_second": 3.341,
78
+ "step": 5120
79
+ },
80
+ {
81
+ "epoch": 0.6,
82
+ "learning_rate": 4.3956919445264097e-05,
83
+ "loss": 0.2506,
84
+ "step": 6144
85
+ },
86
+ {
87
+ "epoch": 0.6,
88
+ "eval_loss": 0.4190705716609955,
89
+ "eval_runtime": 32.4437,
90
+ "eval_samples_per_second": 105.937,
91
+ "eval_steps_per_second": 3.329,
92
+ "step": 6144
93
+ },
94
+ {
95
+ "epoch": 0.71,
96
+ "learning_rate": 4.294973935280811e-05,
97
+ "loss": 0.2512,
98
+ "step": 7168
99
+ },
100
+ {
101
+ "epoch": 0.71,
102
+ "eval_loss": 0.4247213900089264,
103
+ "eval_runtime": 32.3289,
104
+ "eval_samples_per_second": 106.314,
105
+ "eval_steps_per_second": 3.341,
106
+ "step": 7168
107
+ },
108
+ {
109
+ "epoch": 0.81,
110
+ "learning_rate": 4.194255926035212e-05,
111
+ "loss": 0.2483,
112
+ "step": 8192
113
+ },
114
+ {
115
+ "epoch": 0.81,
116
+ "eval_loss": 0.4238651394844055,
117
+ "eval_runtime": 32.3862,
118
+ "eval_samples_per_second": 106.126,
119
+ "eval_steps_per_second": 3.335,
120
+ "step": 8192
121
+ },
122
+ {
123
+ "epoch": 0.91,
124
+ "learning_rate": 4.093537916789614e-05,
125
+ "loss": 0.2479,
126
+ "step": 9216
127
+ },
128
+ {
129
+ "epoch": 0.91,
130
+ "eval_loss": 0.4259129762649536,
131
+ "eval_runtime": 32.4627,
132
+ "eval_samples_per_second": 105.875,
133
+ "eval_steps_per_second": 3.327,
134
+ "step": 9216
135
+ },
136
+ {
137
+ "epoch": 1.01,
138
+ "learning_rate": 3.9928199075440155e-05,
139
+ "loss": 0.2498,
140
+ "step": 10240
141
+ },
142
+ {
143
+ "epoch": 1.01,
144
+ "eval_loss": 0.4262418746948242,
145
+ "eval_runtime": 32.3999,
146
+ "eval_samples_per_second": 106.081,
147
+ "eval_steps_per_second": 3.333,
148
+ "step": 10240
149
+ },
150
+ {
151
+ "epoch": 1.11,
152
+ "learning_rate": 3.8921018982984166e-05,
153
+ "loss": 0.2467,
154
+ "step": 11264
155
+ },
156
+ {
157
+ "epoch": 1.11,
158
+ "eval_loss": 0.4267333149909973,
159
+ "eval_runtime": 32.3308,
160
+ "eval_samples_per_second": 106.307,
161
+ "eval_steps_per_second": 3.34,
162
+ "step": 11264
163
+ },
164
+ {
165
+ "epoch": 1.21,
166
+ "learning_rate": 3.791482246483722e-05,
167
+ "loss": 0.2466,
168
+ "step": 12288
169
+ },
170
+ {
171
+ "epoch": 1.21,
172
+ "eval_loss": 0.4263165295124054,
173
+ "eval_runtime": 32.4348,
174
+ "eval_samples_per_second": 105.967,
175
+ "eval_steps_per_second": 3.33,
176
+ "step": 12288
177
+ },
178
+ {
179
+ "epoch": 1.31,
180
+ "learning_rate": 3.690764237238124e-05,
181
+ "loss": 0.2449,
182
+ "step": 13312
183
+ },
184
+ {
185
+ "epoch": 1.31,
186
+ "eval_loss": 0.42505738139152527,
187
+ "eval_runtime": 32.3762,
188
+ "eval_samples_per_second": 106.158,
189
+ "eval_steps_per_second": 3.336,
190
+ "step": 13312
191
+ },
192
+ {
193
+ "epoch": 1.41,
194
+ "learning_rate": 3.590144585423429e-05,
195
+ "loss": 0.2452,
196
+ "step": 14336
197
+ },
198
+ {
199
+ "epoch": 1.41,
200
+ "eval_loss": 0.42740598320961,
201
+ "eval_runtime": 32.44,
202
+ "eval_samples_per_second": 105.949,
203
+ "eval_steps_per_second": 3.329,
204
+ "step": 14336
205
+ },
206
+ {
207
+ "epoch": 1.51,
208
+ "learning_rate": 3.489426576177831e-05,
209
+ "loss": 0.2449,
210
+ "step": 15360
211
+ },
212
+ {
213
+ "epoch": 1.51,
214
+ "eval_loss": 0.42628249526023865,
215
+ "eval_runtime": 32.3172,
216
+ "eval_samples_per_second": 106.352,
217
+ "eval_steps_per_second": 3.342,
218
+ "step": 15360
219
+ },
220
+ {
221
+ "epoch": 1.61,
222
+ "learning_rate": 3.388708566932232e-05,
223
+ "loss": 0.2444,
224
+ "step": 16384
225
+ },
226
+ {
227
+ "epoch": 1.61,
228
+ "eval_loss": 0.42398524284362793,
229
+ "eval_runtime": 32.2909,
230
+ "eval_samples_per_second": 106.439,
231
+ "eval_steps_per_second": 3.345,
232
+ "step": 16384
233
+ },
234
+ {
235
+ "epoch": 1.71,
236
+ "learning_rate": 3.287990557686633e-05,
237
+ "loss": 0.2428,
238
+ "step": 17408
239
+ },
240
+ {
241
+ "epoch": 1.71,
242
+ "eval_loss": 0.42891454696655273,
243
+ "eval_runtime": 32.3773,
244
+ "eval_samples_per_second": 106.155,
245
+ "eval_steps_per_second": 3.336,
246
+ "step": 17408
247
+ },
248
+ {
249
+ "epoch": 1.81,
250
+ "learning_rate": 3.1873709058719384e-05,
251
+ "loss": 0.2425,
252
+ "step": 18432
253
+ },
254
+ {
255
+ "epoch": 1.81,
256
+ "eval_loss": 0.4228712022304535,
257
+ "eval_runtime": 32.4341,
258
+ "eval_samples_per_second": 105.969,
259
+ "eval_steps_per_second": 3.33,
260
+ "step": 18432
261
+ },
262
+ {
263
+ "epoch": 1.91,
264
+ "learning_rate": 3.08665289662634e-05,
265
+ "loss": 0.2424,
266
+ "step": 19456
267
+ },
268
+ {
269
+ "epoch": 1.91,
270
+ "eval_loss": 0.4291061758995056,
271
+ "eval_runtime": 32.3192,
272
+ "eval_samples_per_second": 106.345,
273
+ "eval_steps_per_second": 3.342,
274
+ "step": 19456
275
+ },
276
+ {
277
+ "epoch": 2.01,
278
+ "learning_rate": 2.985934887380742e-05,
279
+ "loss": 0.2422,
280
+ "step": 20480
281
+ },
282
+ {
283
+ "epoch": 2.01,
284
+ "eval_loss": 0.4246675968170166,
285
+ "eval_runtime": 32.2862,
286
+ "eval_samples_per_second": 106.454,
287
+ "eval_steps_per_second": 3.345,
288
+ "step": 20480
289
+ },
290
+ {
291
+ "epoch": 2.12,
292
+ "learning_rate": 2.8853152355660473e-05,
293
+ "loss": 0.2397,
294
+ "step": 21504
295
+ },
296
+ {
297
+ "epoch": 2.12,
298
+ "eval_loss": 0.42707231640815735,
299
+ "eval_runtime": 32.3373,
300
+ "eval_samples_per_second": 106.286,
301
+ "eval_steps_per_second": 3.34,
302
+ "step": 21504
303
+ },
304
+ {
305
+ "epoch": 2.22,
306
+ "learning_rate": 2.7846955837513527e-05,
307
+ "loss": 0.2397,
308
+ "step": 22528
309
+ },
310
+ {
311
+ "epoch": 2.22,
312
+ "eval_loss": 0.42262786626815796,
313
+ "eval_runtime": 32.3328,
314
+ "eval_samples_per_second": 106.301,
315
+ "eval_steps_per_second": 3.34,
316
+ "step": 22528
317
+ },
318
+ {
319
+ "epoch": 2.32,
320
+ "learning_rate": 2.6839775745057538e-05,
321
+ "loss": 0.2411,
322
+ "step": 23552
323
+ },
324
+ {
325
+ "epoch": 2.32,
326
+ "eval_loss": 0.42685696482658386,
327
+ "eval_runtime": 32.3962,
328
+ "eval_samples_per_second": 106.093,
329
+ "eval_steps_per_second": 3.334,
330
+ "step": 23552
331
+ },
332
+ {
333
+ "epoch": 2.42,
334
+ "learning_rate": 2.5832595652601556e-05,
335
+ "loss": 0.2408,
336
+ "step": 24576
337
+ },
338
+ {
339
+ "epoch": 2.42,
340
+ "eval_loss": 0.42877742648124695,
341
+ "eval_runtime": 32.3163,
342
+ "eval_samples_per_second": 106.355,
343
+ "eval_steps_per_second": 3.342,
344
+ "step": 24576
345
+ },
346
+ {
347
+ "epoch": 2.52,
348
+ "learning_rate": 2.482541556014557e-05,
349
+ "loss": 0.2392,
350
+ "step": 25600
351
+ },
352
+ {
353
+ "epoch": 2.52,
354
+ "eval_loss": 0.42227810621261597,
355
+ "eval_runtime": 32.369,
356
+ "eval_samples_per_second": 106.182,
357
+ "eval_steps_per_second": 3.337,
358
+ "step": 25600
359
+ },
360
+ {
361
+ "epoch": 2.62,
362
+ "learning_rate": 2.3819219041998624e-05,
363
+ "loss": 0.2391,
364
+ "step": 26624
365
+ },
366
+ {
367
+ "epoch": 2.62,
368
+ "eval_loss": 0.4296777546405792,
369
+ "eval_runtime": 32.4315,
370
+ "eval_samples_per_second": 105.977,
371
+ "eval_steps_per_second": 3.33,
372
+ "step": 26624
373
+ },
374
+ {
375
+ "epoch": 2.72,
376
+ "learning_rate": 2.2812038949542638e-05,
377
+ "loss": 0.2385,
378
+ "step": 27648
379
+ },
380
+ {
381
+ "epoch": 2.72,
382
+ "eval_loss": 0.4252742528915405,
383
+ "eval_runtime": 32.4362,
384
+ "eval_samples_per_second": 105.962,
385
+ "eval_steps_per_second": 3.33,
386
+ "step": 27648
387
+ },
388
+ {
389
+ "epoch": 2.82,
390
+ "learning_rate": 2.180584243139569e-05,
391
+ "loss": 0.2371,
392
+ "step": 28672
393
+ },
394
+ {
395
+ "epoch": 2.82,
396
+ "eval_loss": 0.42966845631599426,
397
+ "eval_runtime": 32.3834,
398
+ "eval_samples_per_second": 106.135,
399
+ "eval_steps_per_second": 3.335,
400
+ "step": 28672
401
+ },
402
+ {
403
+ "epoch": 2.92,
404
+ "learning_rate": 2.079866233893971e-05,
405
+ "loss": 0.2373,
406
+ "step": 29696
407
+ },
408
+ {
409
+ "epoch": 2.92,
410
+ "eval_loss": 0.4231690466403961,
411
+ "eval_runtime": 32.3708,
412
+ "eval_samples_per_second": 106.176,
413
+ "eval_steps_per_second": 3.336,
414
+ "step": 29696
415
+ },
416
+ {
417
+ "epoch": 3.02,
418
+ "learning_rate": 1.97934493951018e-05,
419
+ "loss": 0.2368,
420
+ "step": 30720
421
+ },
422
+ {
423
+ "epoch": 3.02,
424
+ "eval_loss": 0.42956846952438354,
425
+ "eval_runtime": 32.3442,
426
+ "eval_samples_per_second": 106.263,
427
+ "eval_steps_per_second": 3.339,
428
+ "step": 30720
429
+ },
430
+ {
431
+ "epoch": 3.12,
432
+ "learning_rate": 1.8786269302645816e-05,
433
+ "loss": 0.2355,
434
+ "step": 31744
435
+ },
436
+ {
437
+ "epoch": 3.12,
438
+ "eval_loss": 0.43274641036987305,
439
+ "eval_runtime": 32.3365,
440
+ "eval_samples_per_second": 106.289,
441
+ "eval_steps_per_second": 3.34,
442
+ "step": 31744
443
+ },
444
+ {
445
+ "epoch": 3.22,
446
+ "learning_rate": 1.777908921018983e-05,
447
+ "loss": 0.2354,
448
+ "step": 32768
449
+ },
450
+ {
451
+ "epoch": 3.22,
452
+ "eval_loss": 0.4304845929145813,
453
+ "eval_runtime": 32.2799,
454
+ "eval_samples_per_second": 106.475,
455
+ "eval_steps_per_second": 3.346,
456
+ "step": 32768
457
+ },
458
+ {
459
+ "epoch": 3.32,
460
+ "learning_rate": 1.6771909117733845e-05,
461
+ "loss": 0.2345,
462
+ "step": 33792
463
+ },
464
+ {
465
+ "epoch": 3.32,
466
+ "eval_loss": 0.4286292791366577,
467
+ "eval_runtime": 32.4389,
468
+ "eval_samples_per_second": 105.953,
469
+ "eval_steps_per_second": 3.329,
470
+ "step": 33792
471
+ },
472
+ {
473
+ "epoch": 3.42,
474
+ "learning_rate": 1.5765712599586898e-05,
475
+ "loss": 0.2355,
476
+ "step": 34816
477
+ },
478
+ {
479
+ "epoch": 3.42,
480
+ "eval_loss": 0.4350430965423584,
481
+ "eval_runtime": 32.3371,
482
+ "eval_samples_per_second": 106.287,
483
+ "eval_steps_per_second": 3.34,
484
+ "step": 34816
485
+ },
486
+ {
487
+ "epoch": 3.53,
488
+ "learning_rate": 1.4758532507130915e-05,
489
+ "loss": 0.2353,
490
+ "step": 35840
491
+ },
492
+ {
493
+ "epoch": 3.53,
494
+ "eval_loss": 0.4268806278705597,
495
+ "eval_runtime": 32.3956,
496
+ "eval_samples_per_second": 106.095,
497
+ "eval_steps_per_second": 3.334,
498
+ "step": 35840
499
+ },
500
+ {
501
+ "epoch": 3.63,
502
+ "learning_rate": 1.375233598898397e-05,
503
+ "loss": 0.2351,
504
+ "step": 36864
505
+ },
506
+ {
507
+ "epoch": 3.63,
508
+ "eval_loss": 0.43005427718162537,
509
+ "eval_runtime": 32.3262,
510
+ "eval_samples_per_second": 106.323,
511
+ "eval_steps_per_second": 3.341,
512
+ "step": 36864
513
+ },
514
+ {
515
+ "epoch": 3.73,
516
+ "learning_rate": 1.2745155896527982e-05,
517
+ "loss": 0.2336,
518
+ "step": 37888
519
+ },
520
+ {
521
+ "epoch": 3.73,
522
+ "eval_loss": 0.4301435649394989,
523
+ "eval_runtime": 32.4031,
524
+ "eval_samples_per_second": 106.07,
525
+ "eval_steps_per_second": 3.333,
526
+ "step": 37888
527
+ },
528
+ {
529
+ "epoch": 3.83,
530
+ "learning_rate": 1.1737975804071997e-05,
531
+ "loss": 0.2344,
532
+ "step": 38912
533
+ },
534
+ {
535
+ "epoch": 3.83,
536
+ "eval_loss": 0.43188127875328064,
537
+ "eval_runtime": 32.3893,
538
+ "eval_samples_per_second": 106.115,
539
+ "eval_steps_per_second": 3.334,
540
+ "step": 38912
541
+ },
542
+ {
543
+ "epoch": 3.93,
544
+ "learning_rate": 1.0730795711616013e-05,
545
+ "loss": 0.2339,
546
+ "step": 39936
547
+ },
548
+ {
549
+ "epoch": 3.93,
550
+ "eval_loss": 0.4304964244365692,
551
+ "eval_runtime": 32.4411,
552
+ "eval_samples_per_second": 105.946,
553
+ "eval_steps_per_second": 3.329,
554
+ "step": 39936
555
+ },
556
+ {
557
+ "epoch": 4.03,
558
+ "learning_rate": 9.724599193469066e-06,
559
+ "loss": 0.2326,
560
+ "step": 40960
561
+ },
562
+ {
563
+ "epoch": 4.03,
564
+ "eval_loss": 0.4298175573348999,
565
+ "eval_runtime": 32.3377,
566
+ "eval_samples_per_second": 106.285,
567
+ "eval_steps_per_second": 3.34,
568
+ "step": 40960
569
+ },
570
+ {
571
+ "epoch": 4.13,
572
+ "learning_rate": 8.718402675322121e-06,
573
+ "loss": 0.2316,
574
+ "step": 41984
575
+ },
576
+ {
577
+ "epoch": 4.13,
578
+ "eval_loss": 0.43077352643013,
579
+ "eval_runtime": 32.3835,
580
+ "eval_samples_per_second": 106.134,
581
+ "eval_steps_per_second": 3.335,
582
+ "step": 41984
583
+ },
584
+ {
585
+ "epoch": 4.23,
586
+ "learning_rate": 7.711222582866136e-06,
587
+ "loss": 0.2311,
588
+ "step": 43008
589
+ },
590
+ {
591
+ "epoch": 4.23,
592
+ "eval_loss": 0.43301910161972046,
593
+ "eval_runtime": 32.3178,
594
+ "eval_samples_per_second": 106.35,
595
+ "eval_steps_per_second": 3.342,
596
+ "step": 43008
597
+ },
598
+ {
599
+ "epoch": 4.33,
600
+ "learning_rate": 6.704042490410151e-06,
601
+ "loss": 0.2315,
602
+ "step": 44032
603
+ },
604
+ {
605
+ "epoch": 4.33,
606
+ "eval_loss": 0.4313049912452698,
607
+ "eval_runtime": 32.3292,
608
+ "eval_samples_per_second": 106.313,
609
+ "eval_steps_per_second": 3.341,
610
+ "step": 44032
611
+ },
612
+ {
613
+ "epoch": 4.43,
614
+ "learning_rate": 5.697845972263205e-06,
615
+ "loss": 0.2305,
616
+ "step": 45056
617
+ },
618
+ {
619
+ "epoch": 4.43,
620
+ "eval_loss": 0.43192604184150696,
621
+ "eval_runtime": 32.2814,
622
+ "eval_samples_per_second": 106.47,
623
+ "eval_steps_per_second": 3.346,
624
+ "step": 45056
625
+ }
626
+ ],
627
+ "max_steps": 50835,
628
+ "num_train_epochs": 5,
629
+ "total_flos": 3.7699559505965875e+17,
630
+ "trial_name": null,
631
+ "trial_params": null
632
+ }
manual_upload/checkpoint-45056/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf489f059ab44f9bc26200d314d3fc5954dabfb501b51ecc19cdc4d4be8a527
3
+ size 3579
manual_upload/checkpoint-49152/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "JammyMachina/elec-gmusic-familized-model-13-12__17-35-53",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 512,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 6,
18
+ "n_positions": 2048,
19
+ "pad_token_id": 1,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.26.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 301
33
+ }
manual_upload/checkpoint-49152/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7e2a0740ea7af2c820feefc87f6bb5d5fb3ea9d38943e7d92bb41fe6d22336
3
+ size 160988613
manual_upload/checkpoint-49152/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d6da6afb62de8c2fa4fdfb2e9a3ca92e20dcd5098fa2cd9b8378c3874a8dda
3
+ size 105666297
manual_upload/checkpoint-49152/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73950719406f404be311f8a4ce16f99b065695c64745fd75c4afbd36d6abc6a1
3
+ size 17641
manual_upload/checkpoint-49152/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e38ca102a5d144e05116c24a90abd23d8a0607bdf7add251bbd55f4d724fdd7
3
+ size 557
manual_upload/checkpoint-49152/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24782e94a439d25d01c08ba8e2f88a577cf001123dd31e97300ec78f3c46fa0
3
+ size 627
manual_upload/checkpoint-49152/trainer_state.json ADDED
@@ -0,0 +1,688 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.834464443788728,
5
+ "global_step": 49152,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 4.899281990754402e-05,
13
+ "loss": 0.2509,
14
+ "step": 1024
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "eval_loss": 0.42676058411598206,
19
+ "eval_runtime": 32.3598,
20
+ "eval_samples_per_second": 106.212,
21
+ "eval_steps_per_second": 3.337,
22
+ "step": 1024
23
+ },
24
+ {
25
+ "epoch": 0.2,
26
+ "learning_rate": 4.798563981508803e-05,
27
+ "loss": 0.2521,
28
+ "step": 2048
29
+ },
30
+ {
31
+ "epoch": 0.2,
32
+ "eval_loss": 0.4283539652824402,
33
+ "eval_runtime": 32.4193,
34
+ "eval_samples_per_second": 106.017,
35
+ "eval_steps_per_second": 3.331,
36
+ "step": 2048
37
+ },
38
+ {
39
+ "epoch": 0.3,
40
+ "learning_rate": 4.697845972263204e-05,
41
+ "loss": 0.2533,
42
+ "step": 3072
43
+ },
44
+ {
45
+ "epoch": 0.3,
46
+ "eval_loss": 0.42187923192977905,
47
+ "eval_runtime": 32.3798,
48
+ "eval_samples_per_second": 106.146,
49
+ "eval_steps_per_second": 3.335,
50
+ "step": 3072
51
+ },
52
+ {
53
+ "epoch": 0.4,
54
+ "learning_rate": 4.597127963017606e-05,
55
+ "loss": 0.2517,
56
+ "step": 4096
57
+ },
58
+ {
59
+ "epoch": 0.4,
60
+ "eval_loss": 0.42451202869415283,
61
+ "eval_runtime": 32.3385,
62
+ "eval_samples_per_second": 106.282,
63
+ "eval_steps_per_second": 3.34,
64
+ "step": 4096
65
+ },
66
+ {
67
+ "epoch": 0.5,
68
+ "learning_rate": 4.496409953772008e-05,
69
+ "loss": 0.2512,
70
+ "step": 5120
71
+ },
72
+ {
73
+ "epoch": 0.5,
74
+ "eval_loss": 0.42285656929016113,
75
+ "eval_runtime": 32.3235,
76
+ "eval_samples_per_second": 106.331,
77
+ "eval_steps_per_second": 3.341,
78
+ "step": 5120
79
+ },
80
+ {
81
+ "epoch": 0.6,
82
+ "learning_rate": 4.3956919445264097e-05,
83
+ "loss": 0.2506,
84
+ "step": 6144
85
+ },
86
+ {
87
+ "epoch": 0.6,
88
+ "eval_loss": 0.4190705716609955,
89
+ "eval_runtime": 32.4437,
90
+ "eval_samples_per_second": 105.937,
91
+ "eval_steps_per_second": 3.329,
92
+ "step": 6144
93
+ },
94
+ {
95
+ "epoch": 0.71,
96
+ "learning_rate": 4.294973935280811e-05,
97
+ "loss": 0.2512,
98
+ "step": 7168
99
+ },
100
+ {
101
+ "epoch": 0.71,
102
+ "eval_loss": 0.4247213900089264,
103
+ "eval_runtime": 32.3289,
104
+ "eval_samples_per_second": 106.314,
105
+ "eval_steps_per_second": 3.341,
106
+ "step": 7168
107
+ },
108
+ {
109
+ "epoch": 0.81,
110
+ "learning_rate": 4.194255926035212e-05,
111
+ "loss": 0.2483,
112
+ "step": 8192
113
+ },
114
+ {
115
+ "epoch": 0.81,
116
+ "eval_loss": 0.4238651394844055,
117
+ "eval_runtime": 32.3862,
118
+ "eval_samples_per_second": 106.126,
119
+ "eval_steps_per_second": 3.335,
120
+ "step": 8192
121
+ },
122
+ {
123
+ "epoch": 0.91,
124
+ "learning_rate": 4.093537916789614e-05,
125
+ "loss": 0.2479,
126
+ "step": 9216
127
+ },
128
+ {
129
+ "epoch": 0.91,
130
+ "eval_loss": 0.4259129762649536,
131
+ "eval_runtime": 32.4627,
132
+ "eval_samples_per_second": 105.875,
133
+ "eval_steps_per_second": 3.327,
134
+ "step": 9216
135
+ },
136
+ {
137
+ "epoch": 1.01,
138
+ "learning_rate": 3.9928199075440155e-05,
139
+ "loss": 0.2498,
140
+ "step": 10240
141
+ },
142
+ {
143
+ "epoch": 1.01,
144
+ "eval_loss": 0.4262418746948242,
145
+ "eval_runtime": 32.3999,
146
+ "eval_samples_per_second": 106.081,
147
+ "eval_steps_per_second": 3.333,
148
+ "step": 10240
149
+ },
150
+ {
151
+ "epoch": 1.11,
152
+ "learning_rate": 3.8921018982984166e-05,
153
+ "loss": 0.2467,
154
+ "step": 11264
155
+ },
156
+ {
157
+ "epoch": 1.11,
158
+ "eval_loss": 0.4267333149909973,
159
+ "eval_runtime": 32.3308,
160
+ "eval_samples_per_second": 106.307,
161
+ "eval_steps_per_second": 3.34,
162
+ "step": 11264
163
+ },
164
+ {
165
+ "epoch": 1.21,
166
+ "learning_rate": 3.791482246483722e-05,
167
+ "loss": 0.2466,
168
+ "step": 12288
169
+ },
170
+ {
171
+ "epoch": 1.21,
172
+ "eval_loss": 0.4263165295124054,
173
+ "eval_runtime": 32.4348,
174
+ "eval_samples_per_second": 105.967,
175
+ "eval_steps_per_second": 3.33,
176
+ "step": 12288
177
+ },
178
+ {
179
+ "epoch": 1.31,
180
+ "learning_rate": 3.690764237238124e-05,
181
+ "loss": 0.2449,
182
+ "step": 13312
183
+ },
184
+ {
185
+ "epoch": 1.31,
186
+ "eval_loss": 0.42505738139152527,
187
+ "eval_runtime": 32.3762,
188
+ "eval_samples_per_second": 106.158,
189
+ "eval_steps_per_second": 3.336,
190
+ "step": 13312
191
+ },
192
+ {
193
+ "epoch": 1.41,
194
+ "learning_rate": 3.590144585423429e-05,
195
+ "loss": 0.2452,
196
+ "step": 14336
197
+ },
198
+ {
199
+ "epoch": 1.41,
200
+ "eval_loss": 0.42740598320961,
201
+ "eval_runtime": 32.44,
202
+ "eval_samples_per_second": 105.949,
203
+ "eval_steps_per_second": 3.329,
204
+ "step": 14336
205
+ },
206
+ {
207
+ "epoch": 1.51,
208
+ "learning_rate": 3.489426576177831e-05,
209
+ "loss": 0.2449,
210
+ "step": 15360
211
+ },
212
+ {
213
+ "epoch": 1.51,
214
+ "eval_loss": 0.42628249526023865,
215
+ "eval_runtime": 32.3172,
216
+ "eval_samples_per_second": 106.352,
217
+ "eval_steps_per_second": 3.342,
218
+ "step": 15360
219
+ },
220
+ {
221
+ "epoch": 1.61,
222
+ "learning_rate": 3.388708566932232e-05,
223
+ "loss": 0.2444,
224
+ "step": 16384
225
+ },
226
+ {
227
+ "epoch": 1.61,
228
+ "eval_loss": 0.42398524284362793,
229
+ "eval_runtime": 32.2909,
230
+ "eval_samples_per_second": 106.439,
231
+ "eval_steps_per_second": 3.345,
232
+ "step": 16384
233
+ },
234
+ {
235
+ "epoch": 1.71,
236
+ "learning_rate": 3.287990557686633e-05,
237
+ "loss": 0.2428,
238
+ "step": 17408
239
+ },
240
+ {
241
+ "epoch": 1.71,
242
+ "eval_loss": 0.42891454696655273,
243
+ "eval_runtime": 32.3773,
244
+ "eval_samples_per_second": 106.155,
245
+ "eval_steps_per_second": 3.336,
246
+ "step": 17408
247
+ },
248
+ {
249
+ "epoch": 1.81,
250
+ "learning_rate": 3.1873709058719384e-05,
251
+ "loss": 0.2425,
252
+ "step": 18432
253
+ },
254
+ {
255
+ "epoch": 1.81,
256
+ "eval_loss": 0.4228712022304535,
257
+ "eval_runtime": 32.4341,
258
+ "eval_samples_per_second": 105.969,
259
+ "eval_steps_per_second": 3.33,
260
+ "step": 18432
261
+ },
262
+ {
263
+ "epoch": 1.91,
264
+ "learning_rate": 3.08665289662634e-05,
265
+ "loss": 0.2424,
266
+ "step": 19456
267
+ },
268
+ {
269
+ "epoch": 1.91,
270
+ "eval_loss": 0.4291061758995056,
271
+ "eval_runtime": 32.3192,
272
+ "eval_samples_per_second": 106.345,
273
+ "eval_steps_per_second": 3.342,
274
+ "step": 19456
275
+ },
276
+ {
277
+ "epoch": 2.01,
278
+ "learning_rate": 2.985934887380742e-05,
279
+ "loss": 0.2422,
280
+ "step": 20480
281
+ },
282
+ {
283
+ "epoch": 2.01,
284
+ "eval_loss": 0.4246675968170166,
285
+ "eval_runtime": 32.2862,
286
+ "eval_samples_per_second": 106.454,
287
+ "eval_steps_per_second": 3.345,
288
+ "step": 20480
289
+ },
290
+ {
291
+ "epoch": 2.12,
292
+ "learning_rate": 2.8853152355660473e-05,
293
+ "loss": 0.2397,
294
+ "step": 21504
295
+ },
296
+ {
297
+ "epoch": 2.12,
298
+ "eval_loss": 0.42707231640815735,
299
+ "eval_runtime": 32.3373,
300
+ "eval_samples_per_second": 106.286,
301
+ "eval_steps_per_second": 3.34,
302
+ "step": 21504
303
+ },
304
+ {
305
+ "epoch": 2.22,
306
+ "learning_rate": 2.7846955837513527e-05,
307
+ "loss": 0.2397,
308
+ "step": 22528
309
+ },
310
+ {
311
+ "epoch": 2.22,
312
+ "eval_loss": 0.42262786626815796,
313
+ "eval_runtime": 32.3328,
314
+ "eval_samples_per_second": 106.301,
315
+ "eval_steps_per_second": 3.34,
316
+ "step": 22528
317
+ },
318
+ {
319
+ "epoch": 2.32,
320
+ "learning_rate": 2.6839775745057538e-05,
321
+ "loss": 0.2411,
322
+ "step": 23552
323
+ },
324
+ {
325
+ "epoch": 2.32,
326
+ "eval_loss": 0.42685696482658386,
327
+ "eval_runtime": 32.3962,
328
+ "eval_samples_per_second": 106.093,
329
+ "eval_steps_per_second": 3.334,
330
+ "step": 23552
331
+ },
332
+ {
333
+ "epoch": 2.42,
334
+ "learning_rate": 2.5832595652601556e-05,
335
+ "loss": 0.2408,
336
+ "step": 24576
337
+ },
338
+ {
339
+ "epoch": 2.42,
340
+ "eval_loss": 0.42877742648124695,
341
+ "eval_runtime": 32.3163,
342
+ "eval_samples_per_second": 106.355,
343
+ "eval_steps_per_second": 3.342,
344
+ "step": 24576
345
+ },
346
+ {
347
+ "epoch": 2.52,
348
+ "learning_rate": 2.482541556014557e-05,
349
+ "loss": 0.2392,
350
+ "step": 25600
351
+ },
352
+ {
353
+ "epoch": 2.52,
354
+ "eval_loss": 0.42227810621261597,
355
+ "eval_runtime": 32.369,
356
+ "eval_samples_per_second": 106.182,
357
+ "eval_steps_per_second": 3.337,
358
+ "step": 25600
359
+ },
360
+ {
361
+ "epoch": 2.62,
362
+ "learning_rate": 2.3819219041998624e-05,
363
+ "loss": 0.2391,
364
+ "step": 26624
365
+ },
366
+ {
367
+ "epoch": 2.62,
368
+ "eval_loss": 0.4296777546405792,
369
+ "eval_runtime": 32.4315,
370
+ "eval_samples_per_second": 105.977,
371
+ "eval_steps_per_second": 3.33,
372
+ "step": 26624
373
+ },
374
+ {
375
+ "epoch": 2.72,
376
+ "learning_rate": 2.2812038949542638e-05,
377
+ "loss": 0.2385,
378
+ "step": 27648
379
+ },
380
+ {
381
+ "epoch": 2.72,
382
+ "eval_loss": 0.4252742528915405,
383
+ "eval_runtime": 32.4362,
384
+ "eval_samples_per_second": 105.962,
385
+ "eval_steps_per_second": 3.33,
386
+ "step": 27648
387
+ },
388
+ {
389
+ "epoch": 2.82,
390
+ "learning_rate": 2.180584243139569e-05,
391
+ "loss": 0.2371,
392
+ "step": 28672
393
+ },
394
+ {
395
+ "epoch": 2.82,
396
+ "eval_loss": 0.42966845631599426,
397
+ "eval_runtime": 32.3834,
398
+ "eval_samples_per_second": 106.135,
399
+ "eval_steps_per_second": 3.335,
400
+ "step": 28672
401
+ },
402
+ {
403
+ "epoch": 2.92,
404
+ "learning_rate": 2.079866233893971e-05,
405
+ "loss": 0.2373,
406
+ "step": 29696
407
+ },
408
+ {
409
+ "epoch": 2.92,
410
+ "eval_loss": 0.4231690466403961,
411
+ "eval_runtime": 32.3708,
412
+ "eval_samples_per_second": 106.176,
413
+ "eval_steps_per_second": 3.336,
414
+ "step": 29696
415
+ },
416
+ {
417
+ "epoch": 3.02,
418
+ "learning_rate": 1.97934493951018e-05,
419
+ "loss": 0.2368,
420
+ "step": 30720
421
+ },
422
+ {
423
+ "epoch": 3.02,
424
+ "eval_loss": 0.42956846952438354,
425
+ "eval_runtime": 32.3442,
426
+ "eval_samples_per_second": 106.263,
427
+ "eval_steps_per_second": 3.339,
428
+ "step": 30720
429
+ },
430
+ {
431
+ "epoch": 3.12,
432
+ "learning_rate": 1.8786269302645816e-05,
433
+ "loss": 0.2355,
434
+ "step": 31744
435
+ },
436
+ {
437
+ "epoch": 3.12,
438
+ "eval_loss": 0.43274641036987305,
439
+ "eval_runtime": 32.3365,
440
+ "eval_samples_per_second": 106.289,
441
+ "eval_steps_per_second": 3.34,
442
+ "step": 31744
443
+ },
444
+ {
445
+ "epoch": 3.22,
446
+ "learning_rate": 1.777908921018983e-05,
447
+ "loss": 0.2354,
448
+ "step": 32768
449
+ },
450
+ {
451
+ "epoch": 3.22,
452
+ "eval_loss": 0.4304845929145813,
453
+ "eval_runtime": 32.2799,
454
+ "eval_samples_per_second": 106.475,
455
+ "eval_steps_per_second": 3.346,
456
+ "step": 32768
457
+ },
458
+ {
459
+ "epoch": 3.32,
460
+ "learning_rate": 1.6771909117733845e-05,
461
+ "loss": 0.2345,
462
+ "step": 33792
463
+ },
464
+ {
465
+ "epoch": 3.32,
466
+ "eval_loss": 0.4286292791366577,
467
+ "eval_runtime": 32.4389,
468
+ "eval_samples_per_second": 105.953,
469
+ "eval_steps_per_second": 3.329,
470
+ "step": 33792
471
+ },
472
+ {
473
+ "epoch": 3.42,
474
+ "learning_rate": 1.5765712599586898e-05,
475
+ "loss": 0.2355,
476
+ "step": 34816
477
+ },
478
+ {
479
+ "epoch": 3.42,
480
+ "eval_loss": 0.4350430965423584,
481
+ "eval_runtime": 32.3371,
482
+ "eval_samples_per_second": 106.287,
483
+ "eval_steps_per_second": 3.34,
484
+ "step": 34816
485
+ },
486
+ {
487
+ "epoch": 3.53,
488
+ "learning_rate": 1.4758532507130915e-05,
489
+ "loss": 0.2353,
490
+ "step": 35840
491
+ },
492
+ {
493
+ "epoch": 3.53,
494
+ "eval_loss": 0.4268806278705597,
495
+ "eval_runtime": 32.3956,
496
+ "eval_samples_per_second": 106.095,
497
+ "eval_steps_per_second": 3.334,
498
+ "step": 35840
499
+ },
500
+ {
501
+ "epoch": 3.63,
502
+ "learning_rate": 1.375233598898397e-05,
503
+ "loss": 0.2351,
504
+ "step": 36864
505
+ },
506
+ {
507
+ "epoch": 3.63,
508
+ "eval_loss": 0.43005427718162537,
509
+ "eval_runtime": 32.3262,
510
+ "eval_samples_per_second": 106.323,
511
+ "eval_steps_per_second": 3.341,
512
+ "step": 36864
513
+ },
514
+ {
515
+ "epoch": 3.73,
516
+ "learning_rate": 1.2745155896527982e-05,
517
+ "loss": 0.2336,
518
+ "step": 37888
519
+ },
520
+ {
521
+ "epoch": 3.73,
522
+ "eval_loss": 0.4301435649394989,
523
+ "eval_runtime": 32.4031,
524
+ "eval_samples_per_second": 106.07,
525
+ "eval_steps_per_second": 3.333,
526
+ "step": 37888
527
+ },
528
+ {
529
+ "epoch": 3.83,
530
+ "learning_rate": 1.1737975804071997e-05,
531
+ "loss": 0.2344,
532
+ "step": 38912
533
+ },
534
+ {
535
+ "epoch": 3.83,
536
+ "eval_loss": 0.43188127875328064,
537
+ "eval_runtime": 32.3893,
538
+ "eval_samples_per_second": 106.115,
539
+ "eval_steps_per_second": 3.334,
540
+ "step": 38912
541
+ },
542
+ {
543
+ "epoch": 3.93,
544
+ "learning_rate": 1.0730795711616013e-05,
545
+ "loss": 0.2339,
546
+ "step": 39936
547
+ },
548
+ {
549
+ "epoch": 3.93,
550
+ "eval_loss": 0.4304964244365692,
551
+ "eval_runtime": 32.4411,
552
+ "eval_samples_per_second": 105.946,
553
+ "eval_steps_per_second": 3.329,
554
+ "step": 39936
555
+ },
556
+ {
557
+ "epoch": 4.03,
558
+ "learning_rate": 9.724599193469066e-06,
559
+ "loss": 0.2326,
560
+ "step": 40960
561
+ },
562
+ {
563
+ "epoch": 4.03,
564
+ "eval_loss": 0.4298175573348999,
565
+ "eval_runtime": 32.3377,
566
+ "eval_samples_per_second": 106.285,
567
+ "eval_steps_per_second": 3.34,
568
+ "step": 40960
569
+ },
570
+ {
571
+ "epoch": 4.13,
572
+ "learning_rate": 8.718402675322121e-06,
573
+ "loss": 0.2316,
574
+ "step": 41984
575
+ },
576
+ {
577
+ "epoch": 4.13,
578
+ "eval_loss": 0.43077352643013,
579
+ "eval_runtime": 32.3835,
580
+ "eval_samples_per_second": 106.134,
581
+ "eval_steps_per_second": 3.335,
582
+ "step": 41984
583
+ },
584
+ {
585
+ "epoch": 4.23,
586
+ "learning_rate": 7.711222582866136e-06,
587
+ "loss": 0.2311,
588
+ "step": 43008
589
+ },
590
+ {
591
+ "epoch": 4.23,
592
+ "eval_loss": 0.43301910161972046,
593
+ "eval_runtime": 32.3178,
594
+ "eval_samples_per_second": 106.35,
595
+ "eval_steps_per_second": 3.342,
596
+ "step": 43008
597
+ },
598
+ {
599
+ "epoch": 4.33,
600
+ "learning_rate": 6.704042490410151e-06,
601
+ "loss": 0.2315,
602
+ "step": 44032
603
+ },
604
+ {
605
+ "epoch": 4.33,
606
+ "eval_loss": 0.4313049912452698,
607
+ "eval_runtime": 32.3292,
608
+ "eval_samples_per_second": 106.313,
609
+ "eval_steps_per_second": 3.341,
610
+ "step": 44032
611
+ },
612
+ {
613
+ "epoch": 4.43,
614
+ "learning_rate": 5.697845972263205e-06,
615
+ "loss": 0.2305,
616
+ "step": 45056
617
+ },
618
+ {
619
+ "epoch": 4.43,
620
+ "eval_loss": 0.43192604184150696,
621
+ "eval_runtime": 32.2814,
622
+ "eval_samples_per_second": 106.47,
623
+ "eval_steps_per_second": 3.346,
624
+ "step": 45056
625
+ },
626
+ {
627
+ "epoch": 4.53,
628
+ "learning_rate": 4.69066587980722e-06,
629
+ "loss": 0.2328,
630
+ "step": 46080
631
+ },
632
+ {
633
+ "epoch": 4.53,
634
+ "eval_loss": 0.42917123436927795,
635
+ "eval_runtime": 32.2788,
636
+ "eval_samples_per_second": 106.479,
637
+ "eval_steps_per_second": 3.346,
638
+ "step": 46080
639
+ },
640
+ {
641
+ "epoch": 4.63,
642
+ "learning_rate": 3.6834857873512347e-06,
643
+ "loss": 0.232,
644
+ "step": 47104
645
+ },
646
+ {
647
+ "epoch": 4.63,
648
+ "eval_loss": 0.4288509488105774,
649
+ "eval_runtime": 32.3263,
650
+ "eval_samples_per_second": 106.322,
651
+ "eval_steps_per_second": 3.341,
652
+ "step": 47104
653
+ },
654
+ {
655
+ "epoch": 4.73,
656
+ "learning_rate": 2.6763056948952493e-06,
657
+ "loss": 0.2309,
658
+ "step": 48128
659
+ },
660
+ {
661
+ "epoch": 4.73,
662
+ "eval_loss": 0.43027371168136597,
663
+ "eval_runtime": 32.3873,
664
+ "eval_samples_per_second": 106.122,
665
+ "eval_steps_per_second": 3.335,
666
+ "step": 48128
667
+ },
668
+ {
669
+ "epoch": 4.83,
670
+ "learning_rate": 1.6701091767483034e-06,
671
+ "loss": 0.23,
672
+ "step": 49152
673
+ },
674
+ {
675
+ "epoch": 4.83,
676
+ "eval_loss": 0.4316680133342743,
677
+ "eval_runtime": 32.3291,
678
+ "eval_samples_per_second": 106.313,
679
+ "eval_steps_per_second": 3.341,
680
+ "step": 49152
681
+ }
682
+ ],
683
+ "max_steps": 50835,
684
+ "num_train_epochs": 5,
685
+ "total_flos": 4.1126902176487834e+17,
686
+ "trial_name": null,
687
+ "trial_params": null
688
+ }
manual_upload/checkpoint-49152/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf489f059ab44f9bc26200d314d3fc5954dabfb501b51ecc19cdc4d4be8a527
3
+ size 3579
manual_upload/config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "activation_function": "gelu_new",
3
  "architectures": [
4
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "JammyMachina/elec-gmusic-familized-model-13-12__17-35-53",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
manual_upload/manual_upload/.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
manual_upload/manual_upload/.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
manual_upload/manual_upload/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_embd": 512,
14
+ "n_head": 8,
15
+ "n_inner": null,
16
+ "n_layer": 6,
17
+ "n_positions": 2048,
18
+ "pad_token_id": 1,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.26.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 301
32
+ }
manual_upload/manual_upload/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54af5d8875e2c2fd3cc37c56d33cad185fa27c7098ef23bdcb9ec77ecf847f0e
3
+ size 105666297
manual_upload/manual_upload/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "pad_token": "[PAD]"
3
+ }
manual_upload/manual_upload/tokenizer.json ADDED
@@ -0,0 +1,347 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[PAD]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[MASK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": null,
35
+ "pre_tokenizer": {
36
+ "type": "WhitespaceSplit"
37
+ },
38
+ "post_processor": null,
39
+ "decoder": null,
40
+ "model": {
41
+ "type": "WordLevel",
42
+ "vocab": {
43
+ "[UNK]": 0,
44
+ "[PAD]": 1,
45
+ "[MASK]": 2,
46
+ "TIME_DELTA=1": 3,
47
+ "TIME_DELTA=2": 4,
48
+ "BAR_END": 5,
49
+ "BAR_START": 6,
50
+ "NOTE_OFF=42": 7,
51
+ "NOTE_ON=42": 8,
52
+ "NOTE_OFF=36": 9,
53
+ "NOTE_ON=36": 10,
54
+ "TIME_DELTA=4": 11,
55
+ "NOTE_OFF=38": 12,
56
+ "NOTE_ON=38": 13,
57
+ "NOTE_OFF=40": 14,
58
+ "NOTE_ON=40": 15,
59
+ "NOTE_OFF=35": 16,
60
+ "NOTE_ON=35": 17,
61
+ "TIME_DELTA=3": 18,
62
+ "NOTE_OFF=64": 19,
63
+ "NOTE_ON=64": 20,
64
+ "NOTE_OFF=57": 21,
65
+ "NOTE_ON=57": 22,
66
+ "NOTE_OFF=62": 23,
67
+ "NOTE_ON=62": 24,
68
+ "NOTE_OFF=54": 25,
69
+ "NOTE_ON=54": 26,
70
+ "NOTE_OFF=59": 27,
71
+ "NOTE_ON=59": 28,
72
+ "NOTE_OFF=55": 29,
73
+ "NOTE_ON=55": 30,
74
+ "NOTE_OFF=69": 31,
75
+ "NOTE_ON=69": 32,
76
+ "NOTE_OFF=60": 33,
77
+ "NOTE_ON=60": 34,
78
+ "NOTE_OFF=46": 35,
79
+ "NOTE_ON=46": 36,
80
+ "NOTE_OFF=44": 37,
81
+ "NOTE_ON=44": 38,
82
+ "NOTE_OFF=50": 39,
83
+ "NOTE_ON=50": 40,
84
+ "NOTE_OFF=67": 41,
85
+ "NOTE_ON=67": 42,
86
+ "NOTE_OFF=45": 43,
87
+ "NOTE_ON=45": 44,
88
+ "NOTE_OFF=52": 45,
89
+ "NOTE_ON=52": 46,
90
+ "NOTE_OFF=70": 47,
91
+ "NOTE_ON=70": 48,
92
+ "NOTE_OFF=51": 49,
93
+ "NOTE_ON=51": 50,
94
+ "TRACK_END": 51,
95
+ "TRACK_START": 52,
96
+ "NOTE_OFF=61": 53,
97
+ "NOTE_ON=61": 54,
98
+ "NOTE_OFF=66": 55,
99
+ "NOTE_ON=66": 56,
100
+ "NOTE_OFF=48": 57,
101
+ "NOTE_ON=48": 58,
102
+ "NOTE_OFF=65": 59,
103
+ "NOTE_ON=65": 60,
104
+ "NOTE_OFF=43": 61,
105
+ "NOTE_ON=43": 62,
106
+ "NOTE_OFF=63": 63,
107
+ "NOTE_ON=63": 64,
108
+ "NOTE_OFF=53": 65,
109
+ "NOTE_ON=53": 66,
110
+ "NOTE_OFF=47": 67,
111
+ "NOTE_ON=47": 68,
112
+ "NOTE_OFF=49": 69,
113
+ "NOTE_ON=49": 70,
114
+ "NOTE_OFF=58": 71,
115
+ "NOTE_ON=58": 72,
116
+ "NOTE_OFF=56": 73,
117
+ "NOTE_ON=56": 74,
118
+ "NOTE_OFF=39": 75,
119
+ "NOTE_ON=39": 76,
120
+ "NOTE_OFF=41": 77,
121
+ "NOTE_ON=41": 78,
122
+ "NOTE_OFF=71": 79,
123
+ "NOTE_ON=71": 80,
124
+ "TIME_DELTA=6": 81,
125
+ "NOTE_OFF=72": 82,
126
+ "NOTE_ON=72": 83,
127
+ "NOTE_OFF=33": 84,
128
+ "NOTE_ON=33": 85,
129
+ "NOTE_OFF=68": 86,
130
+ "NOTE_ON=68": 87,
131
+ "NOTE_OFF=74": 88,
132
+ "NOTE_ON=74": 89,
133
+ "TIME_DELTA=8": 90,
134
+ "TIME_DELTA=16": 91,
135
+ "NOTE_OFF=76": 92,
136
+ "NOTE_ON=76": 93,
137
+ "NOTE_OFF=82": 94,
138
+ "NOTE_ON=82": 95,
139
+ "NOTE_OFF=37": 96,
140
+ "NOTE_ON=37": 97,
141
+ "NOTE_OFF=31": 98,
142
+ "NOTE_ON=31": 99,
143
+ "NOTE_OFF=73": 100,
144
+ "NOTE_ON=73": 101,
145
+ "NOTE_OFF=28": 102,
146
+ "NOTE_ON=28": 103,
147
+ "NOTE_OFF=34": 104,
148
+ "NOTE_ON=34": 105,
149
+ "NOTE_OFF=75": 106,
150
+ "NOTE_ON=75": 107,
151
+ "TIME_DELTA=5": 108,
152
+ "NOTE_OFF=29": 109,
153
+ "NOTE_ON=29": 110,
154
+ "NOTE_OFF=32": 111,
155
+ "NOTE_ON=32": 112,
156
+ "NOTE_OFF=79": 113,
157
+ "NOTE_ON=79": 114,
158
+ "DENSITY=3": 115,
159
+ "NOTE_OFF=81": 116,
160
+ "NOTE_ON=81": 117,
161
+ "NOTE_OFF=77": 118,
162
+ "NOTE_ON=77": 119,
163
+ "NOTE_OFF=78": 120,
164
+ "NOTE_ON=78": 121,
165
+ "INST=3": 122,
166
+ "NOTE_OFF=30": 123,
167
+ "NOTE_ON=30": 124,
168
+ "DENSITY=2": 125,
169
+ "DENSITY=1": 126,
170
+ "TIME_DELTA=7": 127,
171
+ "DENSITY=0": 128,
172
+ "NOTE_OFF=26": 129,
173
+ "NOTE_ON=26": 130,
174
+ "INST=DRUMS": 131,
175
+ "NOTE_OFF=80": 132,
176
+ "NOTE_ON=80": 133,
177
+ "TIME_DELTA=12": 134,
178
+ "NOTE_OFF=27": 135,
179
+ "NOTE_ON=27": 136,
180
+ "PIECE_START": 137,
181
+ "TIME_DELTA=10": 138,
182
+ "NOTE_OFF=83": 139,
183
+ "NOTE_ON=83": 140,
184
+ "INST=4": 141,
185
+ "NOTE_OFF=84": 142,
186
+ "NOTE_ON=84": 143,
187
+ "NOTE_OFF=86": 144,
188
+ "NOTE_ON=86": 145,
189
+ "TIME_DELTA=14": 146,
190
+ "INST=0": 147,
191
+ "TIME_DELTA=15": 148,
192
+ "INST=6": 149,
193
+ "NOTE_OFF=85": 150,
194
+ "NOTE_ON=85": 151,
195
+ "NOTE_OFF=88": 152,
196
+ "NOTE_ON=88": 153,
197
+ "TIME_DELTA=9": 154,
198
+ "NOTE_OFF=24": 155,
199
+ "NOTE_ON=24": 156,
200
+ "NOTE_OFF=87": 157,
201
+ "NOTE_ON=87": 158,
202
+ "TIME_DELTA=11": 159,
203
+ "NOTE_OFF=91": 160,
204
+ "NOTE_ON=91": 161,
205
+ "INST=10": 162,
206
+ "TIME_DELTA=13": 163,
207
+ "NOTE_OFF=25": 164,
208
+ "NOTE_ON=25": 165,
209
+ "NOTE_OFF=89": 166,
210
+ "NOTE_ON=89": 167,
211
+ "INST=8": 168,
212
+ "NOTE_OFF=93": 169,
213
+ "NOTE_ON=93": 170,
214
+ "INST=7": 171,
215
+ "INST=11": 172,
216
+ "NOTE_OFF=90": 173,
217
+ "NOTE_ON=90": 174,
218
+ "NOTE_OFF=22": 175,
219
+ "NOTE_ON=22": 176,
220
+ "INST=2": 177,
221
+ "NOTE_OFF=23": 178,
222
+ "NOTE_ON=23": 179,
223
+ "NOTE_OFF=0": 180,
224
+ "NOTE_ON=0": 181,
225
+ "NOTE_OFF=94": 182,
226
+ "NOTE_ON=94": 183,
227
+ "NOTE_OFF=95": 184,
228
+ "NOTE_ON=95": 185,
229
+ "NOTE_OFF=96": 186,
230
+ "NOTE_ON=96": 187,
231
+ "INST=9": 188,
232
+ "INST=5": 189,
233
+ "INST=12": 190,
234
+ "NOTE_OFF=92": 191,
235
+ "NOTE_ON=92": 192,
236
+ "INST=1": 193,
237
+ "NOTE_OFF=98": 194,
238
+ "NOTE_ON=98": 195,
239
+ "INST=14": 196,
240
+ "NOTE_OFF=20": 197,
241
+ "NOTE_ON=20": 198,
242
+ "NOTE_OFF=100": 199,
243
+ "NOTE_ON=100": 200,
244
+ "INST=13": 201,
245
+ "INST=15": 202,
246
+ "NOTE_OFF=21": 203,
247
+ "NOTE_ON=21": 204,
248
+ "NOTE_OFF=99": 205,
249
+ "NOTE_ON=99": 206,
250
+ "NOTE_OFF=101": 207,
251
+ "NOTE_ON=101": 208,
252
+ "NOTE_OFF=16": 209,
253
+ "NOTE_ON=16": 210,
254
+ "NOTE_OFF=97": 211,
255
+ "NOTE_ON=97": 212,
256
+ "NOTE_OFF=102": 213,
257
+ "NOTE_ON=102": 214,
258
+ "NOTE_OFF=17": 215,
259
+ "NOTE_ON=17": 216,
260
+ "NOTE_OFF=19": 217,
261
+ "NOTE_ON=19": 218,
262
+ "NOTE_OFF=103": 219,
263
+ "NOTE_ON=103": 220,
264
+ "NOTE_OFF=107": 221,
265
+ "NOTE_ON=107": 222,
266
+ "NOTE_OFF=105": 223,
267
+ "NOTE_ON=105": 224,
268
+ "NOTE_OFF=18": 225,
269
+ "NOTE_ON=18": 226,
270
+ "NOTE_OFF=109": 227,
271
+ "NOTE_ON=109": 228,
272
+ "NOTE_OFF=110": 229,
273
+ "NOTE_ON=110": 230,
274
+ "NOTE_OFF=112": 231,
275
+ "NOTE_ON=112": 232,
276
+ "NOTE_OFF=15": 233,
277
+ "NOTE_ON=15": 234,
278
+ "NOTE_OFF=6": 235,
279
+ "NOTE_ON=6": 236,
280
+ "NOTE_OFF=108": 237,
281
+ "NOTE_ON=108": 238,
282
+ "NOTE_OFF=12": 239,
283
+ "NOTE_ON=12": 240,
284
+ "NOTE_OFF=126": 241,
285
+ "NOTE_ON=126": 242,
286
+ "NOTE_OFF=14": 243,
287
+ "NOTE_ON=14": 244,
288
+ "NOTE_OFF=104": 245,
289
+ "NOTE_ON=104": 246,
290
+ "NOTE_OFF=7": 247,
291
+ "NOTE_ON=7": 248,
292
+ "NOTE_OFF=8": 249,
293
+ "NOTE_ON=8": 250,
294
+ "NOTE_OFF=123": 251,
295
+ "NOTE_ON=123": 252,
296
+ "NOTE_OFF=106": 253,
297
+ "NOTE_ON=106": 254,
298
+ "NOTE_OFF=1": 255,
299
+ "NOTE_ON=1": 256,
300
+ "NOTE_OFF=122": 257,
301
+ "NOTE_ON=122": 258,
302
+ "NOTE_OFF=124": 259,
303
+ "NOTE_ON=124": 260,
304
+ "NOTE_OFF=127": 261,
305
+ "NOTE_ON=127": 262,
306
+ "NOTE_OFF=9": 263,
307
+ "NOTE_ON=9": 264,
308
+ "NOTE_OFF=125": 265,
309
+ "NOTE_ON=125": 266,
310
+ "NOTE_OFF=114": 267,
311
+ "NOTE_ON=114": 268,
312
+ "NOTE_OFF=117": 269,
313
+ "NOTE_ON=117": 270,
314
+ "NOTE_OFF=113": 271,
315
+ "NOTE_ON=113": 272,
316
+ "NOTE_OFF=119": 273,
317
+ "NOTE_ON=119": 274,
318
+ "NOTE_OFF=120": 275,
319
+ "NOTE_OFF=2": 276,
320
+ "NOTE_ON=120": 277,
321
+ "NOTE_ON=2": 278,
322
+ "NOTE_OFF=115": 279,
323
+ "NOTE_ON=115": 280,
324
+ "NOTE_OFF=111": 281,
325
+ "NOTE_ON=111": 282,
326
+ "NOTE_OFF=4": 283,
327
+ "NOTE_ON=4": 284,
328
+ "NOTE_OFF=116": 285,
329
+ "NOTE_ON=116": 286,
330
+ "NOTE_OFF=5": 287,
331
+ "NOTE_ON=5": 288,
332
+ "NOTE_OFF=3": 289,
333
+ "NOTE_ON=3": 290,
334
+ "NOTE_OFF=11": 291,
335
+ "NOTE_ON=11": 292,
336
+ "NOTE_OFF=10": 293,
337
+ "NOTE_OFF=118": 294,
338
+ "NOTE_OFF=121": 295,
339
+ "NOTE_ON=10": 296,
340
+ "NOTE_ON=118": 297,
341
+ "NOTE_ON=121": 298,
342
+ "NOTE_OFF=13": 299,
343
+ "NOTE_ON=13": 300
344
+ },
345
+ "unk_token": "[UNK]"
346
+ }
347
+ }
manual_upload/manual_upload/tokenizer_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "model_max_length": 1000000000000000019884624838656,
3
+ "name_or_path": "JammyMachina/elec-gmusic-familized-model-13-12__17-35-53",
4
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--JammyMachina--elec-gmusic-familized-model-13-12__17-35-53/snapshots/fbba9d2ac598a2e0fbec338593aceff49347aff4/special_tokens_map.json",
5
+ "tokenizer_class": "PreTrainedTokenizerFast"
6
+ }
manual_upload/manual_upload/trainer_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": null,
5
+ "global_step": 0,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 0,
11
+ "num_train_epochs": 0,
12
+ "total_flos": 0,
13
+ "trial_name": null,
14
+ "trial_params": null
15
+ }