Upload 12 files
Browse files- config.json +74 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +223 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-base",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_eos_token_id": 2,
|
28 |
+
"gradient_checkpointing": false,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1024,
|
42 |
+
"model_type": "bart",
|
43 |
+
"no_repeat_ngram_size": 3,
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": true,
|
46 |
+
"num_beams": 4,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 1,
|
49 |
+
"scale_embedding": false,
|
50 |
+
"task_specific_params": {
|
51 |
+
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
+
"length_penalty": 2.0,
|
59 |
+
"max_length": 142,
|
60 |
+
"min_length": 56,
|
61 |
+
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.14.0.dev0",
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 50265
|
74 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae34eed4a32ba8e6cdc0d15fbd2127b69e539eaa604904f9c3867e5bb191b526
|
3 |
+
size 1115513717
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:063fc5ece11ef88aa3fc6702a085bc307dacb57a8bcdc697c9a3f9e8ee849e7a
|
3 |
+
size 557979193
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0878cf52e8bb39ef5c8851a5f4b3dd6efd29bb6a9713f5f2af5fb855013c2e47
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d50f9976c236ac9c5ed1065d4d629550e5b691f0af78590e9fa338216295201c
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,223 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 14403,
|
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": 4.479275151010207e-05,
|
13 |
+
"loss": 0.8616,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.21,
|
18 |
+
"learning_rate": 3.9585503020204125e-05,
|
19 |
+
"loss": 0.7086,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.31,
|
24 |
+
"learning_rate": 3.437825453030619e-05,
|
25 |
+
"loss": 0.6876,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.42,
|
30 |
+
"learning_rate": 2.917100604040825e-05,
|
31 |
+
"loss": 0.6658,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.52,
|
36 |
+
"learning_rate": 2.396375755051031e-05,
|
37 |
+
"loss": 0.6513,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.62,
|
42 |
+
"learning_rate": 1.8756509060612374e-05,
|
43 |
+
"loss": 0.6115,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.73,
|
48 |
+
"learning_rate": 1.3549260570714433e-05,
|
49 |
+
"loss": 0.5986,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.83,
|
54 |
+
"learning_rate": 8.342012080816496e-06,
|
55 |
+
"loss": 0.6065,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.94,
|
60 |
+
"learning_rate": 3.134763590918559e-06,
|
61 |
+
"loss": 0.5997,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.0,
|
66 |
+
"eval_gen_len": 20.0,
|
67 |
+
"eval_loss": 0.7166666984558105,
|
68 |
+
"eval_rouge1": 15.1597,
|
69 |
+
"eval_rouge2": 11.4975,
|
70 |
+
"eval_rougeL": 14.0709,
|
71 |
+
"eval_rougeLsum": 14.9737,
|
72 |
+
"eval_runtime": 13.0755,
|
73 |
+
"eval_samples_per_second": 6.501,
|
74 |
+
"eval_steps_per_second": 3.289,
|
75 |
+
"step": 4801
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 1.04,
|
79 |
+
"learning_rate": 2.396375755051031e-05,
|
80 |
+
"loss": 0.535,
|
81 |
+
"step": 5000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 1.15,
|
85 |
+
"learning_rate": 2.136013330556134e-05,
|
86 |
+
"loss": 0.5328,
|
87 |
+
"step": 5500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.25,
|
91 |
+
"learning_rate": 1.8756509060612374e-05,
|
92 |
+
"loss": 0.555,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.35,
|
97 |
+
"learning_rate": 1.6152884815663406e-05,
|
98 |
+
"loss": 0.5381,
|
99 |
+
"step": 6500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 1.46,
|
103 |
+
"learning_rate": 1.3549260570714433e-05,
|
104 |
+
"loss": 0.5375,
|
105 |
+
"step": 7000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 1.56,
|
109 |
+
"learning_rate": 1.0945636325765466e-05,
|
110 |
+
"loss": 0.5333,
|
111 |
+
"step": 7500
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.67,
|
115 |
+
"learning_rate": 8.342012080816496e-06,
|
116 |
+
"loss": 0.5291,
|
117 |
+
"step": 8000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 1.77,
|
121 |
+
"learning_rate": 5.738387835867528e-06,
|
122 |
+
"loss": 0.5196,
|
123 |
+
"step": 8500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.87,
|
127 |
+
"learning_rate": 3.134763590918559e-06,
|
128 |
+
"loss": 0.4995,
|
129 |
+
"step": 9000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.98,
|
133 |
+
"learning_rate": 5.311393459695897e-07,
|
134 |
+
"loss": 0.5057,
|
135 |
+
"step": 9500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.0,
|
139 |
+
"eval_gen_len": 20.0,
|
140 |
+
"eval_loss": 0.6984732747077942,
|
141 |
+
"eval_rouge1": 15.2746,
|
142 |
+
"eval_rouge2": 11.537,
|
143 |
+
"eval_rougeL": 14.1481,
|
144 |
+
"eval_rougeLsum": 15.1267,
|
145 |
+
"eval_runtime": 13.3919,
|
146 |
+
"eval_samples_per_second": 6.347,
|
147 |
+
"eval_steps_per_second": 3.211,
|
148 |
+
"step": 9602
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 2.08,
|
152 |
+
"learning_rate": 1.528501006734708e-05,
|
153 |
+
"loss": 0.4867,
|
154 |
+
"step": 10000
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 2.19,
|
158 |
+
"learning_rate": 1.3549260570714433e-05,
|
159 |
+
"loss": 0.4811,
|
160 |
+
"step": 10500
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 2.29,
|
164 |
+
"learning_rate": 1.181351107408179e-05,
|
165 |
+
"loss": 0.4842,
|
166 |
+
"step": 11000
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 2.4,
|
170 |
+
"learning_rate": 1.0077761577449144e-05,
|
171 |
+
"loss": 0.4909,
|
172 |
+
"step": 11500
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 2.5,
|
176 |
+
"learning_rate": 8.342012080816496e-06,
|
177 |
+
"loss": 0.4659,
|
178 |
+
"step": 12000
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 2.6,
|
182 |
+
"learning_rate": 6.606262584183851e-06,
|
183 |
+
"loss": 0.4747,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.71,
|
188 |
+
"learning_rate": 4.870513087551205e-06,
|
189 |
+
"loss": 0.473,
|
190 |
+
"step": 13000
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 2.81,
|
194 |
+
"learning_rate": 3.134763590918559e-06,
|
195 |
+
"loss": 0.4484,
|
196 |
+
"step": 13500
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 2.92,
|
200 |
+
"learning_rate": 1.3990140942859125e-06,
|
201 |
+
"loss": 0.4804,
|
202 |
+
"step": 14000
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 3.0,
|
206 |
+
"eval_gen_len": 20.0,
|
207 |
+
"eval_loss": 0.6930598020553589,
|
208 |
+
"eval_rouge1": 15.2658,
|
209 |
+
"eval_rouge2": 11.5104,
|
210 |
+
"eval_rougeL": 14.117,
|
211 |
+
"eval_rougeLsum": 15.1103,
|
212 |
+
"eval_runtime": 13.632,
|
213 |
+
"eval_samples_per_second": 6.235,
|
214 |
+
"eval_steps_per_second": 3.154,
|
215 |
+
"step": 14403
|
216 |
+
}
|
217 |
+
],
|
218 |
+
"max_steps": 14403,
|
219 |
+
"num_train_epochs": 3,
|
220 |
+
"total_flos": 1.113119515662336e+16,
|
221 |
+
"trial_name": null,
|
222 |
+
"trial_params": null
|
223 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8de6c5186a6156f89a8393be22a8689866202413f2ee93672a5f7a13ac15a6dd
|
3 |
+
size 3119
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|