Commit
•
f1a5ca0
1
Parent(s):
4db3bd6
Saving train state of step 160000
Browse files- checkpoint-160000-epoch-11/config.json +278 -0
- checkpoint-160000-epoch-11/generation_config.json +12 -0
- checkpoint-160000-epoch-11/optimizer.bin +3 -0
- checkpoint-160000-epoch-11/pytorch_model.bin +3 -0
- checkpoint-160000-epoch-11/random_states_0.pkl +3 -0
- checkpoint-160000-epoch-11/random_states_1.pkl +3 -0
- checkpoint-160000-epoch-11/random_states_2.pkl +3 -0
- checkpoint-160000-epoch-11/random_states_3.pkl +3 -0
- checkpoint-160000-epoch-11/random_states_4.pkl +3 -0
- checkpoint-160000-epoch-11/random_states_5.pkl +3 -0
- checkpoint-160000-epoch-11/random_states_6.pkl +3 -0
- checkpoint-160000-epoch-11/random_states_7.pkl +3 -0
- checkpoint-160000-epoch-11/scheduler.bin +3 -0
checkpoint-160000-epoch-11/config.json
ADDED
@@ -0,0 +1,278 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"ParlerTTSForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"audio_encoder": {
|
6 |
+
"_name_or_path": "parler-tts/dac_44khZ_8kbps",
|
7 |
+
"add_cross_attention": false,
|
8 |
+
"architectures": [
|
9 |
+
"DACModel"
|
10 |
+
],
|
11 |
+
"bad_words_ids": null,
|
12 |
+
"begin_suppress_tokens": null,
|
13 |
+
"bos_token_id": null,
|
14 |
+
"chunk_size_feed_forward": 0,
|
15 |
+
"codebook_size": 1024,
|
16 |
+
"cross_attention_hidden_size": null,
|
17 |
+
"decoder_start_token_id": null,
|
18 |
+
"diversity_penalty": 0.0,
|
19 |
+
"do_sample": false,
|
20 |
+
"early_stopping": false,
|
21 |
+
"encoder_no_repeat_ngram_size": 0,
|
22 |
+
"eos_token_id": null,
|
23 |
+
"exponential_decay_length_penalty": null,
|
24 |
+
"finetuning_task": null,
|
25 |
+
"forced_bos_token_id": null,
|
26 |
+
"forced_eos_token_id": null,
|
27 |
+
"frame_rate": 86,
|
28 |
+
"id2label": {
|
29 |
+
"0": "LABEL_0",
|
30 |
+
"1": "LABEL_1"
|
31 |
+
},
|
32 |
+
"is_decoder": false,
|
33 |
+
"is_encoder_decoder": false,
|
34 |
+
"label2id": {
|
35 |
+
"LABEL_0": 0,
|
36 |
+
"LABEL_1": 1
|
37 |
+
},
|
38 |
+
"latent_dim": 1024,
|
39 |
+
"length_penalty": 1.0,
|
40 |
+
"max_length": 20,
|
41 |
+
"min_length": 0,
|
42 |
+
"model_bitrate": 8,
|
43 |
+
"model_type": "dac",
|
44 |
+
"no_repeat_ngram_size": 0,
|
45 |
+
"num_beam_groups": 1,
|
46 |
+
"num_beams": 1,
|
47 |
+
"num_codebooks": 9,
|
48 |
+
"num_return_sequences": 1,
|
49 |
+
"output_attentions": false,
|
50 |
+
"output_hidden_states": false,
|
51 |
+
"output_scores": false,
|
52 |
+
"pad_token_id": null,
|
53 |
+
"prefix": null,
|
54 |
+
"problem_type": null,
|
55 |
+
"pruned_heads": {},
|
56 |
+
"remove_invalid_values": false,
|
57 |
+
"repetition_penalty": 1.0,
|
58 |
+
"return_dict": true,
|
59 |
+
"return_dict_in_generate": false,
|
60 |
+
"sampling_rate": 44100,
|
61 |
+
"sep_token_id": null,
|
62 |
+
"suppress_tokens": null,
|
63 |
+
"task_specific_params": null,
|
64 |
+
"temperature": 1.0,
|
65 |
+
"tf_legacy_loss": false,
|
66 |
+
"tie_encoder_decoder": false,
|
67 |
+
"tie_word_embeddings": true,
|
68 |
+
"tokenizer_class": null,
|
69 |
+
"top_k": 50,
|
70 |
+
"top_p": 1.0,
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"torchscript": false,
|
73 |
+
"typical_p": 1.0,
|
74 |
+
"use_bfloat16": false
|
75 |
+
},
|
76 |
+
"decoder": {
|
77 |
+
"_name_or_path": "./parler-tts-untrained-600M/decoder",
|
78 |
+
"activation_dropout": 0.0,
|
79 |
+
"activation_function": "gelu",
|
80 |
+
"add_cross_attention": true,
|
81 |
+
"architectures": [
|
82 |
+
"ParlerTTSForCausalLM"
|
83 |
+
],
|
84 |
+
"attention_dropout": 0.0,
|
85 |
+
"bad_words_ids": null,
|
86 |
+
"begin_suppress_tokens": null,
|
87 |
+
"bos_token_id": 1025,
|
88 |
+
"chunk_size_feed_forward": 0,
|
89 |
+
"cross_attention_hidden_size": null,
|
90 |
+
"decoder_start_token_id": null,
|
91 |
+
"diversity_penalty": 0.0,
|
92 |
+
"do_sample": false,
|
93 |
+
"dropout": 0.1,
|
94 |
+
"early_stopping": false,
|
95 |
+
"encoder_no_repeat_ngram_size": 0,
|
96 |
+
"eos_token_id": 1024,
|
97 |
+
"exponential_decay_length_penalty": null,
|
98 |
+
"ffn_dim": 4096,
|
99 |
+
"finetuning_task": null,
|
100 |
+
"forced_bos_token_id": null,
|
101 |
+
"forced_eos_token_id": null,
|
102 |
+
"hidden_size": 1024,
|
103 |
+
"id2label": {
|
104 |
+
"0": "LABEL_0",
|
105 |
+
"1": "LABEL_1"
|
106 |
+
},
|
107 |
+
"initializer_factor": 0.02,
|
108 |
+
"is_decoder": true,
|
109 |
+
"is_encoder_decoder": false,
|
110 |
+
"label2id": {
|
111 |
+
"LABEL_0": 0,
|
112 |
+
"LABEL_1": 1
|
113 |
+
},
|
114 |
+
"layerdrop": 0.0,
|
115 |
+
"length_penalty": 1.0,
|
116 |
+
"max_length": 20,
|
117 |
+
"max_position_embeddings": 4096,
|
118 |
+
"min_length": 0,
|
119 |
+
"model_type": "parler_tts_decoder",
|
120 |
+
"no_repeat_ngram_size": 0,
|
121 |
+
"num_attention_heads": 16,
|
122 |
+
"num_beam_groups": 1,
|
123 |
+
"num_beams": 1,
|
124 |
+
"num_codebooks": 9,
|
125 |
+
"num_hidden_layers": 24,
|
126 |
+
"num_return_sequences": 1,
|
127 |
+
"output_attentions": false,
|
128 |
+
"output_hidden_states": false,
|
129 |
+
"output_scores": false,
|
130 |
+
"pad_token_id": 1024,
|
131 |
+
"prefix": null,
|
132 |
+
"problem_type": null,
|
133 |
+
"pruned_heads": {},
|
134 |
+
"remove_invalid_values": false,
|
135 |
+
"repetition_penalty": 1.0,
|
136 |
+
"return_dict": true,
|
137 |
+
"return_dict_in_generate": false,
|
138 |
+
"rope_embeddings": false,
|
139 |
+
"rope_theta": 10000.0,
|
140 |
+
"scale_embedding": false,
|
141 |
+
"sep_token_id": null,
|
142 |
+
"suppress_tokens": null,
|
143 |
+
"task_specific_params": null,
|
144 |
+
"temperature": 1.0,
|
145 |
+
"tf_legacy_loss": false,
|
146 |
+
"tie_encoder_decoder": false,
|
147 |
+
"tie_word_embeddings": false,
|
148 |
+
"tokenizer_class": null,
|
149 |
+
"top_k": 50,
|
150 |
+
"top_p": 1.0,
|
151 |
+
"torch_dtype": "float32",
|
152 |
+
"torchscript": false,
|
153 |
+
"typical_p": 1.0,
|
154 |
+
"use_bfloat16": false,
|
155 |
+
"use_cache": true,
|
156 |
+
"vocab_size": 1088
|
157 |
+
},
|
158 |
+
"decoder_start_token_id": 1025,
|
159 |
+
"is_encoder_decoder": true,
|
160 |
+
"model_type": "parler_tts",
|
161 |
+
"pad_token_id": 1024,
|
162 |
+
"prompt_cross_attention": true,
|
163 |
+
"text_encoder": {
|
164 |
+
"_name_or_path": "google/flan-t5-base",
|
165 |
+
"add_cross_attention": false,
|
166 |
+
"architectures": [
|
167 |
+
"T5ForConditionalGeneration"
|
168 |
+
],
|
169 |
+
"bad_words_ids": null,
|
170 |
+
"begin_suppress_tokens": null,
|
171 |
+
"bos_token_id": null,
|
172 |
+
"chunk_size_feed_forward": 0,
|
173 |
+
"classifier_dropout": 0.0,
|
174 |
+
"cross_attention_hidden_size": null,
|
175 |
+
"d_ff": 2048,
|
176 |
+
"d_kv": 64,
|
177 |
+
"d_model": 768,
|
178 |
+
"decoder_start_token_id": 0,
|
179 |
+
"dense_act_fn": "gelu_new",
|
180 |
+
"diversity_penalty": 0.0,
|
181 |
+
"do_sample": false,
|
182 |
+
"dropout_rate": 0.1,
|
183 |
+
"early_stopping": false,
|
184 |
+
"encoder_no_repeat_ngram_size": 0,
|
185 |
+
"eos_token_id": 1,
|
186 |
+
"exponential_decay_length_penalty": null,
|
187 |
+
"feed_forward_proj": "gated-gelu",
|
188 |
+
"finetuning_task": null,
|
189 |
+
"forced_bos_token_id": null,
|
190 |
+
"forced_eos_token_id": null,
|
191 |
+
"id2label": {
|
192 |
+
"0": "LABEL_0",
|
193 |
+
"1": "LABEL_1"
|
194 |
+
},
|
195 |
+
"initializer_factor": 1.0,
|
196 |
+
"is_decoder": false,
|
197 |
+
"is_encoder_decoder": true,
|
198 |
+
"is_gated_act": true,
|
199 |
+
"label2id": {
|
200 |
+
"LABEL_0": 0,
|
201 |
+
"LABEL_1": 1
|
202 |
+
},
|
203 |
+
"layer_norm_epsilon": 1e-06,
|
204 |
+
"length_penalty": 1.0,
|
205 |
+
"max_length": 20,
|
206 |
+
"min_length": 0,
|
207 |
+
"model_type": "t5",
|
208 |
+
"n_positions": 512,
|
209 |
+
"no_repeat_ngram_size": 0,
|
210 |
+
"num_beam_groups": 1,
|
211 |
+
"num_beams": 1,
|
212 |
+
"num_decoder_layers": 12,
|
213 |
+
"num_heads": 12,
|
214 |
+
"num_layers": 12,
|
215 |
+
"num_return_sequences": 1,
|
216 |
+
"output_attentions": false,
|
217 |
+
"output_hidden_states": false,
|
218 |
+
"output_past": true,
|
219 |
+
"output_scores": false,
|
220 |
+
"pad_token_id": 0,
|
221 |
+
"prefix": null,
|
222 |
+
"problem_type": null,
|
223 |
+
"pruned_heads": {},
|
224 |
+
"relative_attention_max_distance": 128,
|
225 |
+
"relative_attention_num_buckets": 32,
|
226 |
+
"remove_invalid_values": false,
|
227 |
+
"repetition_penalty": 1.0,
|
228 |
+
"return_dict": true,
|
229 |
+
"return_dict_in_generate": false,
|
230 |
+
"sep_token_id": null,
|
231 |
+
"suppress_tokens": null,
|
232 |
+
"task_specific_params": {
|
233 |
+
"summarization": {
|
234 |
+
"early_stopping": true,
|
235 |
+
"length_penalty": 2.0,
|
236 |
+
"max_length": 200,
|
237 |
+
"min_length": 30,
|
238 |
+
"no_repeat_ngram_size": 3,
|
239 |
+
"num_beams": 4,
|
240 |
+
"prefix": "summarize: "
|
241 |
+
},
|
242 |
+
"translation_en_to_de": {
|
243 |
+
"early_stopping": true,
|
244 |
+
"max_length": 300,
|
245 |
+
"num_beams": 4,
|
246 |
+
"prefix": "translate English to German: "
|
247 |
+
},
|
248 |
+
"translation_en_to_fr": {
|
249 |
+
"early_stopping": true,
|
250 |
+
"max_length": 300,
|
251 |
+
"num_beams": 4,
|
252 |
+
"prefix": "translate English to French: "
|
253 |
+
},
|
254 |
+
"translation_en_to_ro": {
|
255 |
+
"early_stopping": true,
|
256 |
+
"max_length": 300,
|
257 |
+
"num_beams": 4,
|
258 |
+
"prefix": "translate English to Romanian: "
|
259 |
+
}
|
260 |
+
},
|
261 |
+
"temperature": 1.0,
|
262 |
+
"tf_legacy_loss": false,
|
263 |
+
"tie_encoder_decoder": false,
|
264 |
+
"tie_word_embeddings": false,
|
265 |
+
"tokenizer_class": null,
|
266 |
+
"top_k": 50,
|
267 |
+
"top_p": 1.0,
|
268 |
+
"torch_dtype": null,
|
269 |
+
"torchscript": false,
|
270 |
+
"typical_p": 1.0,
|
271 |
+
"use_bfloat16": false,
|
272 |
+
"use_cache": true,
|
273 |
+
"vocab_size": 32128
|
274 |
+
},
|
275 |
+
"torch_dtype": "float32",
|
276 |
+
"transformers_version": "4.40.2",
|
277 |
+
"vocab_size": 32128
|
278 |
+
}
|
checkpoint-160000-epoch-11/generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1025,
|
4 |
+
"decoder_start_token_id": 1025,
|
5 |
+
"do_sample": true,
|
6 |
+
"eos_token_id": 1024,
|
7 |
+
"guidance_scale": 1,
|
8 |
+
"key": 10,
|
9 |
+
"max_length": 2580,
|
10 |
+
"pad_token_id": 1024,
|
11 |
+
"transformers_version": "4.40.2"
|
12 |
+
}
|
checkpoint-160000-epoch-11/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f46f379c04d53c2107689a63ad2b683696d43ca49c735f024f010f04f21f89c
|
3 |
+
size 3652769047
|
checkpoint-160000-epoch-11/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a87b943ab6e42072e3a5554827103960ab2bd24a9abdbcb261ac1d1ae63d026d
|
3 |
+
size 2605239710
|
checkpoint-160000-epoch-11/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc936b7868d3f254794873408ef7b6c3dedd4b004c853f8771384360f66bd45e
|
3 |
+
size 16100
|
checkpoint-160000-epoch-11/random_states_1.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a6db8d4924524207edbd0eff940630c7a3021f59569ef62bcba6aaf1398c015
|
3 |
+
size 16036
|
checkpoint-160000-epoch-11/random_states_2.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bbad5b1bcb63d4d192703950b15abc65a3b4276737e471dec209b539f7a178a
|
3 |
+
size 16036
|
checkpoint-160000-epoch-11/random_states_3.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae959316da78c63a9865196303eae3b275669af417e95d17ca3597018d823f2f
|
3 |
+
size 16100
|
checkpoint-160000-epoch-11/random_states_4.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:539c6088ae5cca89eecd56f6e8292c5e884a36b7087c51958f553431fd6720dc
|
3 |
+
size 16100
|
checkpoint-160000-epoch-11/random_states_5.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24bd61eeef250270477ad31f74821667d862ee7ae6deeaa4a6e5c3f5bda67e3a
|
3 |
+
size 16100
|
checkpoint-160000-epoch-11/random_states_6.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98efb80efd86bd45f7763a6cca013e9ee0501b7ef8c87ff08ff28b3f5cd19923
|
3 |
+
size 16100
|
checkpoint-160000-epoch-11/random_states_7.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c490c414f888a50b5007b57dc89c10759755676d1c33498955abc00509bb61e6
|
3 |
+
size 16100
|
checkpoint-160000-epoch-11/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:625504f5c43abd700888e5f20f20c0aa70dba36bf393ead976c489ce707bc71b
|
3 |
+
size 1000
|