Import
Browse files- all_results.json +13 -0
- config.json +75 -0
- eval_results.json +8 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +187 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"eval_loss": 2.4415812492370605,
|
4 |
+
"eval_runtime": 3.2126,
|
5 |
+
"eval_samples": 1991,
|
6 |
+
"eval_samples_per_second": 619.755,
|
7 |
+
"eval_steps_per_second": 77.508,
|
8 |
+
"train_loss": 1.3588120859379202,
|
9 |
+
"train_runtime": 1049.6357,
|
10 |
+
"train_samples": 15931,
|
11 |
+
"train_samples_per_second": 106.244,
|
12 |
+
"train_steps_per_second": 13.285
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_bos_token_id": 0,
|
28 |
+
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1",
|
33 |
+
"2": "LABEL_2"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1,
|
40 |
+
"LABEL_2": 2
|
41 |
+
},
|
42 |
+
"max_position_embeddings": 1024,
|
43 |
+
"model_type": "bart",
|
44 |
+
"no_repeat_ngram_size": 3,
|
45 |
+
"normalize_before": false,
|
46 |
+
"normalize_embedding": true,
|
47 |
+
"num_beams": 4,
|
48 |
+
"num_hidden_layers": 6,
|
49 |
+
"pad_token_id": 1,
|
50 |
+
"scale_embedding": false,
|
51 |
+
"task_specific_params": {
|
52 |
+
"summarization": {
|
53 |
+
"length_penalty": 1.0,
|
54 |
+
"max_length": 128,
|
55 |
+
"min_length": 12,
|
56 |
+
"num_beams": 4
|
57 |
+
},
|
58 |
+
"summarization_cnn": {
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"num_beams": 4
|
63 |
+
},
|
64 |
+
"summarization_xsum": {
|
65 |
+
"length_penalty": 1.0,
|
66 |
+
"max_length": 62,
|
67 |
+
"min_length": 11,
|
68 |
+
"num_beams": 6
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.19.4",
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 50265
|
75 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"eval_loss": 2.4415812492370605,
|
4 |
+
"eval_runtime": 3.2126,
|
5 |
+
"eval_samples": 1991,
|
6 |
+
"eval_samples_per_second": 619.755,
|
7 |
+
"eval_steps_per_second": 77.508
|
8 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18ae528c94c737090152a30ace3e6e5ff222826b10ee460fd027b2e2db9eafea
|
3 |
+
size 557969145
|
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 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.0,
|
3 |
+
"train_loss": 1.3588120859379202,
|
4 |
+
"train_runtime": 1049.6357,
|
5 |
+
"train_samples": 15931,
|
6 |
+
"train_samples_per_second": 106.244,
|
7 |
+
"train_steps_per_second": 13.285
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.0,
|
5 |
+
"global_step": 13944,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.25,
|
12 |
+
"learning_rate": 4.8207114170969595e-05,
|
13 |
+
"loss": 2.3679,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.5,
|
18 |
+
"learning_rate": 4.641422834193919e-05,
|
19 |
+
"loss": 2.2289,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.75,
|
24 |
+
"learning_rate": 4.462134251290878e-05,
|
25 |
+
"loss": 2.1641,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.0,
|
30 |
+
"learning_rate": 4.2828456683878374e-05,
|
31 |
+
"loss": 2.1632,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.26,
|
36 |
+
"learning_rate": 4.1035570854847967e-05,
|
37 |
+
"loss": 1.7626,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.51,
|
42 |
+
"learning_rate": 3.924268502581756e-05,
|
43 |
+
"loss": 1.7654,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.76,
|
48 |
+
"learning_rate": 3.744979919678715e-05,
|
49 |
+
"loss": 1.7738,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.01,
|
54 |
+
"learning_rate": 3.5656913367756745e-05,
|
55 |
+
"loss": 1.7726,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.26,
|
60 |
+
"learning_rate": 3.386402753872633e-05,
|
61 |
+
"loss": 1.4475,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.51,
|
66 |
+
"learning_rate": 3.207114170969593e-05,
|
67 |
+
"loss": 1.465,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.76,
|
72 |
+
"learning_rate": 3.0278255880665517e-05,
|
73 |
+
"loss": 1.4945,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 3.01,
|
78 |
+
"learning_rate": 2.8485370051635113e-05,
|
79 |
+
"loss": 1.4736,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.26,
|
84 |
+
"learning_rate": 2.669248422260471e-05,
|
85 |
+
"loss": 1.2188,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 3.51,
|
90 |
+
"learning_rate": 2.48995983935743e-05,
|
91 |
+
"loss": 1.2392,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.77,
|
96 |
+
"learning_rate": 2.310671256454389e-05,
|
97 |
+
"loss": 1.244,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 4.02,
|
102 |
+
"learning_rate": 2.1313826735513484e-05,
|
103 |
+
"loss": 1.2268,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 4.27,
|
108 |
+
"learning_rate": 1.9520940906483077e-05,
|
109 |
+
"loss": 1.0412,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 4.52,
|
114 |
+
"learning_rate": 1.772805507745267e-05,
|
115 |
+
"loss": 1.0629,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 4.77,
|
120 |
+
"learning_rate": 1.593516924842226e-05,
|
121 |
+
"loss": 1.0673,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 5.02,
|
126 |
+
"learning_rate": 1.4142283419391852e-05,
|
127 |
+
"loss": 1.0521,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 5.27,
|
132 |
+
"learning_rate": 1.2349397590361447e-05,
|
133 |
+
"loss": 0.9034,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 5.52,
|
138 |
+
"learning_rate": 1.055651176133104e-05,
|
139 |
+
"loss": 0.9072,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 5.77,
|
144 |
+
"learning_rate": 8.763625932300632e-06,
|
145 |
+
"loss": 0.9298,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 6.02,
|
150 |
+
"learning_rate": 6.970740103270223e-06,
|
151 |
+
"loss": 0.9202,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 6.28,
|
156 |
+
"learning_rate": 5.177854274239816e-06,
|
157 |
+
"loss": 0.8249,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 6.53,
|
162 |
+
"learning_rate": 3.384968445209409e-06,
|
163 |
+
"loss": 0.8267,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 6.78,
|
168 |
+
"learning_rate": 1.5920826161790018e-06,
|
169 |
+
"loss": 0.8203,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 7.0,
|
174 |
+
"step": 13944,
|
175 |
+
"total_flos": 3714812226478080.0,
|
176 |
+
"train_loss": 1.3588120859379202,
|
177 |
+
"train_runtime": 1049.6357,
|
178 |
+
"train_samples_per_second": 106.244,
|
179 |
+
"train_steps_per_second": 13.285
|
180 |
+
}
|
181 |
+
],
|
182 |
+
"max_steps": 13944,
|
183 |
+
"num_train_epochs": 7,
|
184 |
+
"total_flos": 3714812226478080.0,
|
185 |
+
"trial_name": null,
|
186 |
+
"trial_params": null
|
187 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4f3fea89fbe614dfea025ac199544f102a69494361e0829f092bc033c14c960
|
3 |
+
size 3311
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|