luizapzbn commited on
Commit
233187b
·
verified ·
1 Parent(s): 5ae5b05

Training in progress, step 500

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: cc-by-nc-4.0
4
+ base_model: facebook/musicgen-small
5
+ tags:
6
+ - text-to-audio
7
+ - chords
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: musicgen-small-lora-aminmaj-chords
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # musicgen-small-lora-aminmaj-chords
18
+
19
+ This model is a fine-tuned version of [facebook/musicgen-small](https://huggingface.co/facebook/musicgen-small) on the megwei/syntheory dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 16
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.99) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 4
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.14.0
56
+ - Transformers 4.48.1
57
+ - Pytorch 2.1.2+cu121
58
+ - Datasets 3.2.0
59
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "MusicgenForConditionalGeneration",
5
+ "parent_library": "transformers.models.musicgen.modeling_musicgen"
6
+ },
7
+ "base_model_name_or_path": "facebook/musicgen-small",
8
+ "bias": "none",
9
+ "eva_config": null,
10
+ "exclude_modules": null,
11
+ "fan_in_fan_out": false,
12
+ "inference_mode": true,
13
+ "init_lora_weights": true,
14
+ "layer_replication": null,
15
+ "layers_pattern": null,
16
+ "layers_to_transform": null,
17
+ "loftq_config": {},
18
+ "lora_alpha": 16,
19
+ "lora_bias": false,
20
+ "lora_dropout": 0.05,
21
+ "megatron_config": null,
22
+ "megatron_core": "megatron.core",
23
+ "modules_to_save": null,
24
+ "peft_type": "LORA",
25
+ "r": 16,
26
+ "rank_pattern": {},
27
+ "revision": null,
28
+ "target_modules": [
29
+ "embed_tokens.3",
30
+ "lm_heads.1",
31
+ "enc_to_dec_proj",
32
+ "lm_heads.0",
33
+ "embed_tokens.1",
34
+ "embed_tokens.2",
35
+ "lm_heads.2",
36
+ "embed_tokens.0",
37
+ "v_proj",
38
+ "audio_enc_to_dec_proj",
39
+ "fc2",
40
+ "q_proj",
41
+ "k_proj",
42
+ "fc1",
43
+ "out_proj",
44
+ "lm_heads.3"
45
+ ],
46
+ "task_type": null,
47
+ "use_dora": false,
48
+ "use_rslora": false
49
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9199088bf211370f0e575555b81353ca889a7e02612a42e9d91d1983a145b8e9
3
+ size 42656200
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length_s": null,
3
+ "feature_extractor_type": "EncodecFeatureExtractor",
4
+ "feature_size": 1,
5
+ "overlap": null,
6
+ "padding_side": "left",
7
+ "padding_value": 0.0,
8
+ "processor_class": "MusicgenProcessor",
9
+ "return_attention_mask": true,
10
+ "sampling_rate": 32000
11
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "processor_class": "MusicgenProcessor",
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
trainer_state.json ADDED
@@ -0,0 +1,518 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.898550724637681,
5
+ "eval_steps": 500,
6
+ "global_step": 136,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.057971014492753624,
13
+ "grad_norm": 55.32845687866211,
14
+ "learning_rate": 0.0001985294117647059,
15
+ "loss": 76.4214,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.11594202898550725,
20
+ "grad_norm": 59.647117614746094,
21
+ "learning_rate": 0.00019558823529411764,
22
+ "loss": 66.9992,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.17391304347826086,
27
+ "grad_norm": 37.24838638305664,
28
+ "learning_rate": 0.00019264705882352944,
29
+ "loss": 53.3101,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.2318840579710145,
34
+ "grad_norm": 31.579923629760742,
35
+ "learning_rate": 0.00018970588235294117,
36
+ "loss": 43.1133,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 0.2898550724637681,
41
+ "grad_norm": 33.05708312988281,
42
+ "learning_rate": 0.00018676470588235297,
43
+ "loss": 41.4356,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 0.34782608695652173,
48
+ "grad_norm": 19.261913299560547,
49
+ "learning_rate": 0.0001838235294117647,
50
+ "loss": 40.5694,
51
+ "step": 12
52
+ },
53
+ {
54
+ "epoch": 0.4057971014492754,
55
+ "grad_norm": 10.231746673583984,
56
+ "learning_rate": 0.00018088235294117647,
57
+ "loss": 35.4952,
58
+ "step": 14
59
+ },
60
+ {
61
+ "epoch": 0.463768115942029,
62
+ "grad_norm": 12.686185836791992,
63
+ "learning_rate": 0.00017794117647058823,
64
+ "loss": 35.9178,
65
+ "step": 16
66
+ },
67
+ {
68
+ "epoch": 0.5217391304347826,
69
+ "grad_norm": 5.934300899505615,
70
+ "learning_rate": 0.000175,
71
+ "loss": 36.0789,
72
+ "step": 18
73
+ },
74
+ {
75
+ "epoch": 0.5797101449275363,
76
+ "grad_norm": 6.5412092208862305,
77
+ "learning_rate": 0.0001720588235294118,
78
+ "loss": 36.4717,
79
+ "step": 20
80
+ },
81
+ {
82
+ "epoch": 0.6376811594202898,
83
+ "grad_norm": 7.47074031829834,
84
+ "learning_rate": 0.00016911764705882353,
85
+ "loss": 36.1205,
86
+ "step": 22
87
+ },
88
+ {
89
+ "epoch": 0.6956521739130435,
90
+ "grad_norm": 7.197345733642578,
91
+ "learning_rate": 0.00016617647058823532,
92
+ "loss": 35.8026,
93
+ "step": 24
94
+ },
95
+ {
96
+ "epoch": 0.7536231884057971,
97
+ "grad_norm": 8.729438781738281,
98
+ "learning_rate": 0.00016323529411764706,
99
+ "loss": 36.109,
100
+ "step": 26
101
+ },
102
+ {
103
+ "epoch": 0.8115942028985508,
104
+ "grad_norm": 10.730180740356445,
105
+ "learning_rate": 0.00016029411764705885,
106
+ "loss": 34.3386,
107
+ "step": 28
108
+ },
109
+ {
110
+ "epoch": 0.8695652173913043,
111
+ "grad_norm": 8.981538772583008,
112
+ "learning_rate": 0.0001573529411764706,
113
+ "loss": 33.3324,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.927536231884058,
118
+ "grad_norm": 13.125741958618164,
119
+ "learning_rate": 0.00015441176470588238,
120
+ "loss": 34.8168,
121
+ "step": 32
122
+ },
123
+ {
124
+ "epoch": 0.9855072463768116,
125
+ "grad_norm": 7.202057361602783,
126
+ "learning_rate": 0.00015147058823529412,
127
+ "loss": 33.9379,
128
+ "step": 34
129
+ },
130
+ {
131
+ "epoch": 1.0289855072463767,
132
+ "grad_norm": 7.689969539642334,
133
+ "learning_rate": 0.00014852941176470588,
134
+ "loss": 26.4506,
135
+ "step": 36
136
+ },
137
+ {
138
+ "epoch": 1.0869565217391304,
139
+ "grad_norm": 12.119438171386719,
140
+ "learning_rate": 0.00014558823529411765,
141
+ "loss": 34.1455,
142
+ "step": 38
143
+ },
144
+ {
145
+ "epoch": 1.144927536231884,
146
+ "grad_norm": 10.431544303894043,
147
+ "learning_rate": 0.0001426470588235294,
148
+ "loss": 33.6817,
149
+ "step": 40
150
+ },
151
+ {
152
+ "epoch": 1.2028985507246377,
153
+ "grad_norm": 6.7350311279296875,
154
+ "learning_rate": 0.00013970588235294118,
155
+ "loss": 34.3042,
156
+ "step": 42
157
+ },
158
+ {
159
+ "epoch": 1.2608695652173914,
160
+ "grad_norm": 7.63714599609375,
161
+ "learning_rate": 0.00013676470588235294,
162
+ "loss": 33.6539,
163
+ "step": 44
164
+ },
165
+ {
166
+ "epoch": 1.318840579710145,
167
+ "grad_norm": 14.94995403289795,
168
+ "learning_rate": 0.0001338235294117647,
169
+ "loss": 34.8423,
170
+ "step": 46
171
+ },
172
+ {
173
+ "epoch": 1.3768115942028984,
174
+ "grad_norm": 5.653194904327393,
175
+ "learning_rate": 0.00013088235294117647,
176
+ "loss": 33.6543,
177
+ "step": 48
178
+ },
179
+ {
180
+ "epoch": 1.434782608695652,
181
+ "grad_norm": 7.0490946769714355,
182
+ "learning_rate": 0.00012794117647058824,
183
+ "loss": 34.4564,
184
+ "step": 50
185
+ },
186
+ {
187
+ "epoch": 1.4927536231884058,
188
+ "grad_norm": 9.5311279296875,
189
+ "learning_rate": 0.000125,
190
+ "loss": 34.0708,
191
+ "step": 52
192
+ },
193
+ {
194
+ "epoch": 1.5507246376811594,
195
+ "grad_norm": 9.313169479370117,
196
+ "learning_rate": 0.00012205882352941178,
197
+ "loss": 35.0762,
198
+ "step": 54
199
+ },
200
+ {
201
+ "epoch": 1.608695652173913,
202
+ "grad_norm": 6.120841026306152,
203
+ "learning_rate": 0.00011911764705882353,
204
+ "loss": 33.5708,
205
+ "step": 56
206
+ },
207
+ {
208
+ "epoch": 1.6666666666666665,
209
+ "grad_norm": 19.58426856994629,
210
+ "learning_rate": 0.00011617647058823531,
211
+ "loss": 32.583,
212
+ "step": 58
213
+ },
214
+ {
215
+ "epoch": 1.7246376811594204,
216
+ "grad_norm": 10.036286354064941,
217
+ "learning_rate": 0.00011323529411764706,
218
+ "loss": 35.4897,
219
+ "step": 60
220
+ },
221
+ {
222
+ "epoch": 1.7826086956521738,
223
+ "grad_norm": 9.211186408996582,
224
+ "learning_rate": 0.00011029411764705884,
225
+ "loss": 33.5828,
226
+ "step": 62
227
+ },
228
+ {
229
+ "epoch": 1.8405797101449275,
230
+ "grad_norm": 7.165535926818848,
231
+ "learning_rate": 0.00010735294117647059,
232
+ "loss": 34.0128,
233
+ "step": 64
234
+ },
235
+ {
236
+ "epoch": 1.8985507246376812,
237
+ "grad_norm": 8.84890079498291,
238
+ "learning_rate": 0.00010441176470588237,
239
+ "loss": 34.0061,
240
+ "step": 66
241
+ },
242
+ {
243
+ "epoch": 1.9565217391304348,
244
+ "grad_norm": 6.122589111328125,
245
+ "learning_rate": 0.00010147058823529412,
246
+ "loss": 34.1371,
247
+ "step": 68
248
+ },
249
+ {
250
+ "epoch": 2.0,
251
+ "grad_norm": 5.6373186111450195,
252
+ "learning_rate": 9.852941176470589e-05,
253
+ "loss": 25.4753,
254
+ "step": 70
255
+ },
256
+ {
257
+ "epoch": 2.0579710144927534,
258
+ "grad_norm": 10.314593315124512,
259
+ "learning_rate": 9.558823529411765e-05,
260
+ "loss": 33.9195,
261
+ "step": 72
262
+ },
263
+ {
264
+ "epoch": 2.1159420289855073,
265
+ "grad_norm": 8.193323135375977,
266
+ "learning_rate": 9.264705882352942e-05,
267
+ "loss": 33.1874,
268
+ "step": 74
269
+ },
270
+ {
271
+ "epoch": 2.1739130434782608,
272
+ "grad_norm": 9.070418357849121,
273
+ "learning_rate": 8.970588235294118e-05,
274
+ "loss": 33.3055,
275
+ "step": 76
276
+ },
277
+ {
278
+ "epoch": 2.2318840579710146,
279
+ "grad_norm": 8.063404083251953,
280
+ "learning_rate": 8.676470588235295e-05,
281
+ "loss": 34.1831,
282
+ "step": 78
283
+ },
284
+ {
285
+ "epoch": 2.289855072463768,
286
+ "grad_norm": 7.3460516929626465,
287
+ "learning_rate": 8.382352941176471e-05,
288
+ "loss": 32.5002,
289
+ "step": 80
290
+ },
291
+ {
292
+ "epoch": 2.3478260869565215,
293
+ "grad_norm": 7.9106974601745605,
294
+ "learning_rate": 8.088235294117648e-05,
295
+ "loss": 33.9427,
296
+ "step": 82
297
+ },
298
+ {
299
+ "epoch": 2.4057971014492754,
300
+ "grad_norm": 6.9293532371521,
301
+ "learning_rate": 7.794117647058824e-05,
302
+ "loss": 32.7437,
303
+ "step": 84
304
+ },
305
+ {
306
+ "epoch": 2.463768115942029,
307
+ "grad_norm": 5.583312511444092,
308
+ "learning_rate": 7.500000000000001e-05,
309
+ "loss": 32.4636,
310
+ "step": 86
311
+ },
312
+ {
313
+ "epoch": 2.5217391304347827,
314
+ "grad_norm": 9.602357864379883,
315
+ "learning_rate": 7.205882352941177e-05,
316
+ "loss": 34.4266,
317
+ "step": 88
318
+ },
319
+ {
320
+ "epoch": 2.579710144927536,
321
+ "grad_norm": 7.29642391204834,
322
+ "learning_rate": 6.911764705882354e-05,
323
+ "loss": 33.2233,
324
+ "step": 90
325
+ },
326
+ {
327
+ "epoch": 2.63768115942029,
328
+ "grad_norm": 7.916087627410889,
329
+ "learning_rate": 6.61764705882353e-05,
330
+ "loss": 32.328,
331
+ "step": 92
332
+ },
333
+ {
334
+ "epoch": 2.6956521739130435,
335
+ "grad_norm": 9.700789451599121,
336
+ "learning_rate": 6.323529411764705e-05,
337
+ "loss": 33.3864,
338
+ "step": 94
339
+ },
340
+ {
341
+ "epoch": 2.753623188405797,
342
+ "grad_norm": 7.925725936889648,
343
+ "learning_rate": 6.0294117647058825e-05,
344
+ "loss": 33.0956,
345
+ "step": 96
346
+ },
347
+ {
348
+ "epoch": 2.8115942028985508,
349
+ "grad_norm": 7.136451721191406,
350
+ "learning_rate": 5.735294117647059e-05,
351
+ "loss": 34.077,
352
+ "step": 98
353
+ },
354
+ {
355
+ "epoch": 2.869565217391304,
356
+ "grad_norm": 7.057907581329346,
357
+ "learning_rate": 5.441176470588235e-05,
358
+ "loss": 32.854,
359
+ "step": 100
360
+ },
361
+ {
362
+ "epoch": 2.927536231884058,
363
+ "grad_norm": 8.482731819152832,
364
+ "learning_rate": 5.147058823529411e-05,
365
+ "loss": 31.9702,
366
+ "step": 102
367
+ },
368
+ {
369
+ "epoch": 2.9855072463768115,
370
+ "grad_norm": 8.195663452148438,
371
+ "learning_rate": 4.8529411764705885e-05,
372
+ "loss": 32.0516,
373
+ "step": 104
374
+ },
375
+ {
376
+ "epoch": 3.028985507246377,
377
+ "grad_norm": 13.711084365844727,
378
+ "learning_rate": 4.558823529411765e-05,
379
+ "loss": 23.3778,
380
+ "step": 106
381
+ },
382
+ {
383
+ "epoch": 3.0869565217391304,
384
+ "grad_norm": 13.546501159667969,
385
+ "learning_rate": 4.2647058823529415e-05,
386
+ "loss": 32.14,
387
+ "step": 108
388
+ },
389
+ {
390
+ "epoch": 3.1449275362318843,
391
+ "grad_norm": 11.532342910766602,
392
+ "learning_rate": 3.970588235294117e-05,
393
+ "loss": 32.6737,
394
+ "step": 110
395
+ },
396
+ {
397
+ "epoch": 3.2028985507246377,
398
+ "grad_norm": 9.859041213989258,
399
+ "learning_rate": 3.6764705882352945e-05,
400
+ "loss": 32.2716,
401
+ "step": 112
402
+ },
403
+ {
404
+ "epoch": 3.260869565217391,
405
+ "grad_norm": 7.993894577026367,
406
+ "learning_rate": 3.382352941176471e-05,
407
+ "loss": 32.8686,
408
+ "step": 114
409
+ },
410
+ {
411
+ "epoch": 3.318840579710145,
412
+ "grad_norm": 5.935787677764893,
413
+ "learning_rate": 3.0882352941176475e-05,
414
+ "loss": 33.3099,
415
+ "step": 116
416
+ },
417
+ {
418
+ "epoch": 3.3768115942028984,
419
+ "grad_norm": 8.535140037536621,
420
+ "learning_rate": 2.7941176470588236e-05,
421
+ "loss": 33.1781,
422
+ "step": 118
423
+ },
424
+ {
425
+ "epoch": 3.4347826086956523,
426
+ "grad_norm": 8.691988945007324,
427
+ "learning_rate": 2.5e-05,
428
+ "loss": 31.1977,
429
+ "step": 120
430
+ },
431
+ {
432
+ "epoch": 3.4927536231884058,
433
+ "grad_norm": 7.092562675476074,
434
+ "learning_rate": 2.2058823529411766e-05,
435
+ "loss": 32.9427,
436
+ "step": 122
437
+ },
438
+ {
439
+ "epoch": 3.550724637681159,
440
+ "grad_norm": 10.397586822509766,
441
+ "learning_rate": 1.9117647058823528e-05,
442
+ "loss": 32.8582,
443
+ "step": 124
444
+ },
445
+ {
446
+ "epoch": 3.608695652173913,
447
+ "grad_norm": 7.606701374053955,
448
+ "learning_rate": 1.6176470588235296e-05,
449
+ "loss": 33.5666,
450
+ "step": 126
451
+ },
452
+ {
453
+ "epoch": 3.6666666666666665,
454
+ "grad_norm": 9.118799209594727,
455
+ "learning_rate": 1.323529411764706e-05,
456
+ "loss": 32.2489,
457
+ "step": 128
458
+ },
459
+ {
460
+ "epoch": 3.7246376811594204,
461
+ "grad_norm": 8.418676376342773,
462
+ "learning_rate": 1.0294117647058824e-05,
463
+ "loss": 32.8995,
464
+ "step": 130
465
+ },
466
+ {
467
+ "epoch": 3.782608695652174,
468
+ "grad_norm": 7.379878044128418,
469
+ "learning_rate": 7.3529411764705884e-06,
470
+ "loss": 33.5503,
471
+ "step": 132
472
+ },
473
+ {
474
+ "epoch": 3.8405797101449277,
475
+ "grad_norm": 7.183637619018555,
476
+ "learning_rate": 4.411764705882353e-06,
477
+ "loss": 31.911,
478
+ "step": 134
479
+ },
480
+ {
481
+ "epoch": 3.898550724637681,
482
+ "grad_norm": 12.431236267089844,
483
+ "learning_rate": 1.4705882352941177e-06,
484
+ "loss": 31.6491,
485
+ "step": 136
486
+ },
487
+ {
488
+ "epoch": 3.898550724637681,
489
+ "step": 136,
490
+ "total_flos": 29261690983296.0,
491
+ "train_loss": 35.055379671208996,
492
+ "train_runtime": 354.4991,
493
+ "train_samples_per_second": 6.229,
494
+ "train_steps_per_second": 0.384
495
+ }
496
+ ],
497
+ "logging_steps": 2,
498
+ "max_steps": 136,
499
+ "num_input_tokens_seen": 0,
500
+ "num_train_epochs": 4,
501
+ "save_steps": 500,
502
+ "stateful_callbacks": {
503
+ "TrainerControl": {
504
+ "args": {
505
+ "should_epoch_stop": false,
506
+ "should_evaluate": false,
507
+ "should_log": false,
508
+ "should_save": true,
509
+ "should_training_stop": true
510
+ },
511
+ "attributes": {}
512
+ }
513
+ },
514
+ "total_flos": 29261690983296.0,
515
+ "train_batch_size": 2,
516
+ "trial_name": null,
517
+ "trial_params": null
518
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6ce4f69b48a9ef09bce85a7392345fe0247e844f88b82be926a34a333e6fa8
3
+ size 5496