Gaetano-Rossiello
commited on
Commit
•
88ec0f7
1
Parent(s):
f3b261c
GenRL LC-QuAD 2.0 model upload
Browse files- all_results.json +15 -0
- config.json +72 -0
- eval_results.json +12 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +6 -0
- trainer_state.json +743 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_gen_len": 18.8189,
|
4 |
+
"eval_loss": 0.2656216621398926,
|
5 |
+
"eval_rouge1": 92.2292,
|
6 |
+
"eval_rouge2": 88.0059,
|
7 |
+
"eval_rougeL": 91.8249,
|
8 |
+
"eval_rougeLsum": 91.8356,
|
9 |
+
"eval_runtime": 724.7809,
|
10 |
+
"eval_samples": 6046,
|
11 |
+
"eval_samples_per_second": 8.342,
|
12 |
+
"train_runtime": 40850.056,
|
13 |
+
"train_samples": 24050,
|
14 |
+
"train_samples_per_second": 1.472
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
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": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 4096,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
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 |
+
"num_beams": 4,
|
46 |
+
"num_hidden_layers": 12,
|
47 |
+
"pad_token_id": 1,
|
48 |
+
"scale_embedding": false,
|
49 |
+
"task_specific_params": {
|
50 |
+
"summarization": {
|
51 |
+
"length_penalty": 1.0,
|
52 |
+
"max_length": 128,
|
53 |
+
"min_length": 12,
|
54 |
+
"num_beams": 4
|
55 |
+
},
|
56 |
+
"summarization_cnn": {
|
57 |
+
"length_penalty": 2.0,
|
58 |
+
"max_length": 142,
|
59 |
+
"min_length": 56,
|
60 |
+
"num_beams": 4
|
61 |
+
},
|
62 |
+
"summarization_xsum": {
|
63 |
+
"length_penalty": 1.0,
|
64 |
+
"max_length": 62,
|
65 |
+
"min_length": 11,
|
66 |
+
"num_beams": 6
|
67 |
+
}
|
68 |
+
},
|
69 |
+
"transformers_version": "4.5.0.dev0",
|
70 |
+
"use_cache": true,
|
71 |
+
"vocab_size": 50265
|
72 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_gen_len": 18.8189,
|
4 |
+
"eval_loss": 0.2656216621398926,
|
5 |
+
"eval_rouge1": 92.2292,
|
6 |
+
"eval_rouge2": 88.0059,
|
7 |
+
"eval_rougeL": 91.8249,
|
8 |
+
"eval_rougeLsum": 91.8356,
|
9 |
+
"eval_runtime": 724.7809,
|
10 |
+
"eval_samples": 6046,
|
11 |
+
"eval_samples_per_second": 8.342
|
12 |
+
}
|
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 sha256:4a6e69cbbdd292662ef763e8f9afd0f9209fd9c04d84f3be8ccd0cef9294d320
|
3 |
+
size 1625569391
|
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_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-large"}
|
train_results.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_runtime": 40850.056,
|
4 |
+
"train_samples": 24050,
|
5 |
+
"train_samples_per_second": 1.472
|
6 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,743 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 60130,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.08,
|
12 |
+
"learning_rate": 4.9584234159321475e-05,
|
13 |
+
"loss": 0.6379,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.17,
|
18 |
+
"learning_rate": 4.916846831864294e-05,
|
19 |
+
"loss": 0.4095,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.25,
|
24 |
+
"learning_rate": 4.875270247796441e-05,
|
25 |
+
"loss": 0.3395,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.33,
|
30 |
+
"learning_rate": 4.8336936637285885e-05,
|
31 |
+
"loss": 0.3274,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.42,
|
36 |
+
"learning_rate": 4.792117079660735e-05,
|
37 |
+
"loss": 0.3223,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.5,
|
42 |
+
"learning_rate": 4.750540495592882e-05,
|
43 |
+
"loss": 0.3417,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.58,
|
48 |
+
"learning_rate": 4.7089639115250295e-05,
|
49 |
+
"loss": 0.3072,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.67,
|
54 |
+
"learning_rate": 4.667387327457176e-05,
|
55 |
+
"loss": 0.2396,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.75,
|
60 |
+
"learning_rate": 4.625810743389323e-05,
|
61 |
+
"loss": 0.2277,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.83,
|
66 |
+
"learning_rate": 4.5842341593214705e-05,
|
67 |
+
"loss": 0.224,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.91,
|
72 |
+
"learning_rate": 4.542657575253617e-05,
|
73 |
+
"loss": 0.2246,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.0,
|
78 |
+
"learning_rate": 4.501080991185764e-05,
|
79 |
+
"loss": 0.2104,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.08,
|
84 |
+
"learning_rate": 4.4595044071179116e-05,
|
85 |
+
"loss": 0.183,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.16,
|
90 |
+
"learning_rate": 4.417927823050058e-05,
|
91 |
+
"loss": 0.2578,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.25,
|
96 |
+
"learning_rate": 4.3763512389822053e-05,
|
97 |
+
"loss": 0.2557,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.33,
|
102 |
+
"learning_rate": 4.3347746549143526e-05,
|
103 |
+
"loss": 0.2352,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.41,
|
108 |
+
"learning_rate": 4.2931980708465e-05,
|
109 |
+
"loss": 0.2227,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.5,
|
114 |
+
"learning_rate": 4.2516214867786464e-05,
|
115 |
+
"loss": 0.1994,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.58,
|
120 |
+
"learning_rate": 4.2100449027107936e-05,
|
121 |
+
"loss": 0.2145,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.66,
|
126 |
+
"learning_rate": 4.168468318642941e-05,
|
127 |
+
"loss": 0.1487,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.75,
|
132 |
+
"learning_rate": 4.1268917345750874e-05,
|
133 |
+
"loss": 0.159,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.83,
|
138 |
+
"learning_rate": 4.0853151505072346e-05,
|
139 |
+
"loss": 0.1803,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.91,
|
144 |
+
"learning_rate": 4.043738566439382e-05,
|
145 |
+
"loss": 0.1679,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.0,
|
150 |
+
"learning_rate": 4.0021619823715284e-05,
|
151 |
+
"loss": 0.1332,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.08,
|
156 |
+
"learning_rate": 3.9605853983036756e-05,
|
157 |
+
"loss": 0.1288,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.16,
|
162 |
+
"learning_rate": 3.919008814235823e-05,
|
163 |
+
"loss": 0.1164,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.25,
|
168 |
+
"learning_rate": 3.8774322301679694e-05,
|
169 |
+
"loss": 0.1237,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.33,
|
174 |
+
"learning_rate": 3.8358556461001167e-05,
|
175 |
+
"loss": 0.1533,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.41,
|
180 |
+
"learning_rate": 3.794279062032264e-05,
|
181 |
+
"loss": 0.1282,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.49,
|
186 |
+
"learning_rate": 3.7527024779644104e-05,
|
187 |
+
"loss": 0.5156,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.58,
|
192 |
+
"learning_rate": 3.711125893896558e-05,
|
193 |
+
"loss": 0.1689,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.66,
|
198 |
+
"learning_rate": 3.669549309828705e-05,
|
199 |
+
"loss": 0.2002,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.74,
|
204 |
+
"learning_rate": 3.6279727257608515e-05,
|
205 |
+
"loss": 0.1226,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.83,
|
210 |
+
"learning_rate": 3.586396141692999e-05,
|
211 |
+
"loss": 0.1192,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.91,
|
216 |
+
"learning_rate": 3.544819557625146e-05,
|
217 |
+
"loss": 0.1264,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.99,
|
222 |
+
"learning_rate": 3.5032429735572925e-05,
|
223 |
+
"loss": 0.138,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 3.08,
|
228 |
+
"learning_rate": 3.46166638948944e-05,
|
229 |
+
"loss": 0.116,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 3.16,
|
234 |
+
"learning_rate": 3.420089805421587e-05,
|
235 |
+
"loss": 0.168,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 3.24,
|
240 |
+
"learning_rate": 3.3785132213537335e-05,
|
241 |
+
"loss": 0.0882,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 3.33,
|
246 |
+
"learning_rate": 3.336936637285881e-05,
|
247 |
+
"loss": 0.0959,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.41,
|
252 |
+
"learning_rate": 3.295360053218028e-05,
|
253 |
+
"loss": 0.0865,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.49,
|
258 |
+
"learning_rate": 3.2537834691501745e-05,
|
259 |
+
"loss": 0.0853,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.58,
|
264 |
+
"learning_rate": 3.212206885082322e-05,
|
265 |
+
"loss": 0.0783,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.66,
|
270 |
+
"learning_rate": 3.170630301014469e-05,
|
271 |
+
"loss": 0.0671,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.74,
|
276 |
+
"learning_rate": 3.129053716946616e-05,
|
277 |
+
"loss": 0.0762,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.83,
|
282 |
+
"learning_rate": 3.087477132878763e-05,
|
283 |
+
"loss": 0.0759,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 3.91,
|
288 |
+
"learning_rate": 3.04590054881091e-05,
|
289 |
+
"loss": 0.0786,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.99,
|
294 |
+
"learning_rate": 3.0043239647430572e-05,
|
295 |
+
"loss": 0.0696,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 4.07,
|
300 |
+
"learning_rate": 2.9627473806752038e-05,
|
301 |
+
"loss": 0.0561,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 4.16,
|
306 |
+
"learning_rate": 2.921170796607351e-05,
|
307 |
+
"loss": 0.0567,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 4.24,
|
312 |
+
"learning_rate": 2.8795942125394983e-05,
|
313 |
+
"loss": 0.0553,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 4.32,
|
318 |
+
"learning_rate": 2.8380176284716448e-05,
|
319 |
+
"loss": 0.0618,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 4.41,
|
324 |
+
"learning_rate": 2.796441044403792e-05,
|
325 |
+
"loss": 0.0601,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 4.49,
|
330 |
+
"learning_rate": 2.7548644603359393e-05,
|
331 |
+
"loss": 0.0572,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 4.57,
|
336 |
+
"learning_rate": 2.713287876268086e-05,
|
337 |
+
"loss": 0.055,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 4.66,
|
342 |
+
"learning_rate": 2.671711292200233e-05,
|
343 |
+
"loss": 0.0592,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 4.74,
|
348 |
+
"learning_rate": 2.6301347081323803e-05,
|
349 |
+
"loss": 0.0582,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 4.82,
|
354 |
+
"learning_rate": 2.588558124064527e-05,
|
355 |
+
"loss": 0.0605,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 4.91,
|
360 |
+
"learning_rate": 2.546981539996674e-05,
|
361 |
+
"loss": 0.0511,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 4.99,
|
366 |
+
"learning_rate": 2.5054049559288213e-05,
|
367 |
+
"loss": 0.052,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 5.07,
|
372 |
+
"learning_rate": 2.4638283718609682e-05,
|
373 |
+
"loss": 0.0387,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 5.16,
|
378 |
+
"learning_rate": 2.422251787793115e-05,
|
379 |
+
"loss": 0.0408,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 5.24,
|
384 |
+
"learning_rate": 2.380675203725262e-05,
|
385 |
+
"loss": 0.038,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 5.32,
|
390 |
+
"learning_rate": 2.3390986196574092e-05,
|
391 |
+
"loss": 0.0415,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 5.4,
|
396 |
+
"learning_rate": 2.297522035589556e-05,
|
397 |
+
"loss": 0.0529,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 5.49,
|
402 |
+
"learning_rate": 2.2559454515217034e-05,
|
403 |
+
"loss": 0.0436,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 5.57,
|
408 |
+
"learning_rate": 2.2143688674538503e-05,
|
409 |
+
"loss": 0.0388,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 5.65,
|
414 |
+
"learning_rate": 2.172792283385997e-05,
|
415 |
+
"loss": 0.0362,
|
416 |
+
"step": 34000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 5.74,
|
420 |
+
"learning_rate": 2.1312156993181444e-05,
|
421 |
+
"loss": 0.0369,
|
422 |
+
"step": 34500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 5.82,
|
426 |
+
"learning_rate": 2.0896391152502913e-05,
|
427 |
+
"loss": 0.0385,
|
428 |
+
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 5.9,
|
432 |
+
"learning_rate": 2.048062531182438e-05,
|
433 |
+
"loss": 0.0391,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 5.99,
|
438 |
+
"learning_rate": 2.0064859471145854e-05,
|
439 |
+
"loss": 0.0395,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 6.07,
|
444 |
+
"learning_rate": 1.9649093630467323e-05,
|
445 |
+
"loss": 0.0262,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 6.15,
|
450 |
+
"learning_rate": 1.9233327789788792e-05,
|
451 |
+
"loss": 0.0473,
|
452 |
+
"step": 37000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 6.24,
|
456 |
+
"learning_rate": 1.8817561949110264e-05,
|
457 |
+
"loss": 0.0306,
|
458 |
+
"step": 37500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 6.32,
|
462 |
+
"learning_rate": 1.8401796108431733e-05,
|
463 |
+
"loss": 0.0258,
|
464 |
+
"step": 38000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 6.4,
|
468 |
+
"learning_rate": 1.7986030267753202e-05,
|
469 |
+
"loss": 0.0284,
|
470 |
+
"step": 38500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 6.49,
|
474 |
+
"learning_rate": 1.7570264427074674e-05,
|
475 |
+
"loss": 0.0223,
|
476 |
+
"step": 39000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 6.57,
|
480 |
+
"learning_rate": 1.7154498586396143e-05,
|
481 |
+
"loss": 0.0259,
|
482 |
+
"step": 39500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 6.65,
|
486 |
+
"learning_rate": 1.6738732745717612e-05,
|
487 |
+
"loss": 0.0282,
|
488 |
+
"step": 40000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 6.74,
|
492 |
+
"learning_rate": 1.6322966905039085e-05,
|
493 |
+
"loss": 0.024,
|
494 |
+
"step": 40500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 6.82,
|
498 |
+
"learning_rate": 1.5907201064360554e-05,
|
499 |
+
"loss": 0.026,
|
500 |
+
"step": 41000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 6.9,
|
504 |
+
"learning_rate": 1.5491435223682026e-05,
|
505 |
+
"loss": 0.0263,
|
506 |
+
"step": 41500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 6.98,
|
510 |
+
"learning_rate": 1.5075669383003493e-05,
|
511 |
+
"loss": 0.0257,
|
512 |
+
"step": 42000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 7.07,
|
516 |
+
"learning_rate": 1.4659903542324962e-05,
|
517 |
+
"loss": 0.0272,
|
518 |
+
"step": 42500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 7.15,
|
522 |
+
"learning_rate": 1.4244137701646434e-05,
|
523 |
+
"loss": 0.0194,
|
524 |
+
"step": 43000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 7.23,
|
528 |
+
"learning_rate": 1.3828371860967903e-05,
|
529 |
+
"loss": 0.014,
|
530 |
+
"step": 43500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 7.32,
|
534 |
+
"learning_rate": 1.3412606020289372e-05,
|
535 |
+
"loss": 0.0151,
|
536 |
+
"step": 44000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 7.4,
|
540 |
+
"learning_rate": 1.2996840179610845e-05,
|
541 |
+
"loss": 0.0173,
|
542 |
+
"step": 44500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 7.48,
|
546 |
+
"learning_rate": 1.2581074338932313e-05,
|
547 |
+
"loss": 0.0138,
|
548 |
+
"step": 45000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 7.57,
|
552 |
+
"learning_rate": 1.2165308498253784e-05,
|
553 |
+
"loss": 0.0245,
|
554 |
+
"step": 45500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 7.65,
|
558 |
+
"learning_rate": 1.1749542657575255e-05,
|
559 |
+
"loss": 0.0162,
|
560 |
+
"step": 46000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 7.73,
|
564 |
+
"learning_rate": 1.1333776816896724e-05,
|
565 |
+
"loss": 0.0162,
|
566 |
+
"step": 46500
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 7.82,
|
570 |
+
"learning_rate": 1.0918010976218194e-05,
|
571 |
+
"loss": 0.0158,
|
572 |
+
"step": 47000
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 7.9,
|
576 |
+
"learning_rate": 1.0502245135539665e-05,
|
577 |
+
"loss": 0.0186,
|
578 |
+
"step": 47500
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 7.98,
|
582 |
+
"learning_rate": 1.0086479294861134e-05,
|
583 |
+
"loss": 0.0189,
|
584 |
+
"step": 48000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 8.07,
|
588 |
+
"learning_rate": 9.670713454182605e-06,
|
589 |
+
"loss": 0.0138,
|
590 |
+
"step": 48500
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 8.15,
|
594 |
+
"learning_rate": 9.254947613504075e-06,
|
595 |
+
"loss": 0.0076,
|
596 |
+
"step": 49000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 8.23,
|
600 |
+
"learning_rate": 8.839181772825546e-06,
|
601 |
+
"loss": 0.0109,
|
602 |
+
"step": 49500
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 8.32,
|
606 |
+
"learning_rate": 8.423415932147015e-06,
|
607 |
+
"loss": 0.0107,
|
608 |
+
"step": 50000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 8.4,
|
612 |
+
"learning_rate": 8.007650091468485e-06,
|
613 |
+
"loss": 0.0086,
|
614 |
+
"step": 50500
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 8.48,
|
618 |
+
"learning_rate": 7.591884250789956e-06,
|
619 |
+
"loss": 0.0132,
|
620 |
+
"step": 51000
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 8.56,
|
624 |
+
"learning_rate": 7.176118410111425e-06,
|
625 |
+
"loss": 0.0095,
|
626 |
+
"step": 51500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 8.65,
|
630 |
+
"learning_rate": 6.7603525694328956e-06,
|
631 |
+
"loss": 0.0101,
|
632 |
+
"step": 52000
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 8.73,
|
636 |
+
"learning_rate": 6.344586728754366e-06,
|
637 |
+
"loss": 0.0108,
|
638 |
+
"step": 52500
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 8.81,
|
642 |
+
"learning_rate": 5.928820888075836e-06,
|
643 |
+
"loss": 0.0088,
|
644 |
+
"step": 53000
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 8.9,
|
648 |
+
"learning_rate": 5.513055047397306e-06,
|
649 |
+
"loss": 0.0082,
|
650 |
+
"step": 53500
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 8.98,
|
654 |
+
"learning_rate": 5.097289206718776e-06,
|
655 |
+
"loss": 0.0086,
|
656 |
+
"step": 54000
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 9.06,
|
660 |
+
"learning_rate": 4.681523366040246e-06,
|
661 |
+
"loss": 0.0053,
|
662 |
+
"step": 54500
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 9.15,
|
666 |
+
"learning_rate": 4.265757525361717e-06,
|
667 |
+
"loss": 0.0053,
|
668 |
+
"step": 55000
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 9.23,
|
672 |
+
"learning_rate": 3.849991684683187e-06,
|
673 |
+
"loss": 0.0066,
|
674 |
+
"step": 55500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 9.31,
|
678 |
+
"learning_rate": 3.4342258440046572e-06,
|
679 |
+
"loss": 0.0041,
|
680 |
+
"step": 56000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 9.4,
|
684 |
+
"learning_rate": 3.018460003326127e-06,
|
685 |
+
"loss": 0.0047,
|
686 |
+
"step": 56500
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 9.48,
|
690 |
+
"learning_rate": 2.6026941626475972e-06,
|
691 |
+
"loss": 0.0065,
|
692 |
+
"step": 57000
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 9.56,
|
696 |
+
"learning_rate": 2.1869283219690674e-06,
|
697 |
+
"loss": 0.0059,
|
698 |
+
"step": 57500
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 9.65,
|
702 |
+
"learning_rate": 1.7711624812905372e-06,
|
703 |
+
"loss": 0.0066,
|
704 |
+
"step": 58000
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 9.73,
|
708 |
+
"learning_rate": 1.3553966406120074e-06,
|
709 |
+
"loss": 0.0043,
|
710 |
+
"step": 58500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 9.81,
|
714 |
+
"learning_rate": 9.396307999334775e-07,
|
715 |
+
"loss": 0.0055,
|
716 |
+
"step": 59000
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 9.9,
|
720 |
+
"learning_rate": 5.238649592549476e-07,
|
721 |
+
"loss": 0.0042,
|
722 |
+
"step": 59500
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 9.98,
|
726 |
+
"learning_rate": 1.0809911857641776e-07,
|
727 |
+
"loss": 0.0031,
|
728 |
+
"step": 60000
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 10.0,
|
732 |
+
"step": 60130,
|
733 |
+
"total_flos": 2.8632348630306816e+17,
|
734 |
+
"train_runtime": 40850.056,
|
735 |
+
"train_samples_per_second": 1.472
|
736 |
+
}
|
737 |
+
],
|
738 |
+
"max_steps": 60130,
|
739 |
+
"num_train_epochs": 10,
|
740 |
+
"total_flos": 2.8632348630306816e+17,
|
741 |
+
"trial_name": null,
|
742 |
+
"trial_params": null
|
743 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b240ba75beb9597b72c61f73e2bcbb164e241018a7b1ce0823f6a51c4da44d36
|
3 |
+
size 2415
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|