npedrazzini
commited on
Commit
•
097448d
1
Parent(s):
b50e633
Upload 11 files
Browse files- all_results.json +16 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- train_results.json +9 -0
- trainer_state.json +707 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.7412841854934602,
|
4 |
+
"eval_loss": 1.3002870082855225,
|
5 |
+
"eval_runtime": 68.5496,
|
6 |
+
"eval_samples": 2962,
|
7 |
+
"eval_samples_per_second": 43.21,
|
8 |
+
"eval_steps_per_second": 21.605,
|
9 |
+
"perplexity": 3.6703499373062245,
|
10 |
+
"total_flos": 2.514865055648973e+16,
|
11 |
+
"train_loss": 1.8108088482396418,
|
12 |
+
"train_runtime": 10130.0955,
|
13 |
+
"train_samples": 31816,
|
14 |
+
"train_samples_per_second": 9.422,
|
15 |
+
"train_steps_per_second": 4.711
|
16 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"pad_token_id": 0,
|
4 |
+
"transformers_version": "4.41.0.dev0"
|
5 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6fb2067053c1a4ef19ad6b879cbe03c4105cd39d90df1b9d79911009cf8a6e2
|
3 |
+
size 713739728
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4973d34e28f67b65ffa83bbcdf54a25d6f4a550c0d852f38dcc84a025bdbef9
|
3 |
+
size 713496552
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 2.514865055648973e+16,
|
4 |
+
"train_loss": 1.8108088482396418,
|
5 |
+
"train_runtime": 10130.0955,
|
6 |
+
"train_samples": 31816,
|
7 |
+
"train_samples_per_second": 9.422,
|
8 |
+
"train_steps_per_second": 4.711
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,707 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 47724,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03143072667840081,
|
13 |
+
"grad_norm": 12.45950698852539,
|
14 |
+
"learning_rate": 4.947615455535999e-05,
|
15 |
+
"loss": 3.2597,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.06286145335680161,
|
20 |
+
"grad_norm": 10.082228660583496,
|
21 |
+
"learning_rate": 4.895230911071997e-05,
|
22 |
+
"loss": 2.8456,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.09429218003520241,
|
27 |
+
"grad_norm": 11.17715835571289,
|
28 |
+
"learning_rate": 4.842846366607996e-05,
|
29 |
+
"loss": 2.7087,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.12572290671360323,
|
34 |
+
"grad_norm": 13.012718200683594,
|
35 |
+
"learning_rate": 4.790461822143995e-05,
|
36 |
+
"loss": 2.5935,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.15715363339200403,
|
41 |
+
"grad_norm": 11.075544357299805,
|
42 |
+
"learning_rate": 4.738077277679994e-05,
|
43 |
+
"loss": 2.4862,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.18858436007040483,
|
48 |
+
"grad_norm": 13.529458045959473,
|
49 |
+
"learning_rate": 4.685692733215992e-05,
|
50 |
+
"loss": 2.4535,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.22001508674880563,
|
55 |
+
"grad_norm": 10.073129653930664,
|
56 |
+
"learning_rate": 4.633308188751991e-05,
|
57 |
+
"loss": 2.346,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.25144581342720645,
|
62 |
+
"grad_norm": 11.378911018371582,
|
63 |
+
"learning_rate": 4.580923644287989e-05,
|
64 |
+
"loss": 2.3565,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.28287654010560725,
|
69 |
+
"grad_norm": 10.559321403503418,
|
70 |
+
"learning_rate": 4.528539099823988e-05,
|
71 |
+
"loss": 2.2937,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.31430726678400805,
|
76 |
+
"grad_norm": 10.023640632629395,
|
77 |
+
"learning_rate": 4.476154555359987e-05,
|
78 |
+
"loss": 2.2474,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.34573799346240885,
|
83 |
+
"grad_norm": 9.890427589416504,
|
84 |
+
"learning_rate": 4.423770010895986e-05,
|
85 |
+
"loss": 2.1995,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.37716872014080965,
|
90 |
+
"grad_norm": 11.694580078125,
|
91 |
+
"learning_rate": 4.3713854664319845e-05,
|
92 |
+
"loss": 2.2092,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.40859944681921045,
|
97 |
+
"grad_norm": 10.519980430603027,
|
98 |
+
"learning_rate": 4.319000921967983e-05,
|
99 |
+
"loss": 2.1238,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.44003017349761125,
|
104 |
+
"grad_norm": 9.350607872009277,
|
105 |
+
"learning_rate": 4.2666163775039816e-05,
|
106 |
+
"loss": 2.1271,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.47146090017601205,
|
111 |
+
"grad_norm": 10.53451919555664,
|
112 |
+
"learning_rate": 4.21423183303998e-05,
|
113 |
+
"loss": 2.167,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5028916268544129,
|
118 |
+
"grad_norm": 11.468996047973633,
|
119 |
+
"learning_rate": 4.1618472885759786e-05,
|
120 |
+
"loss": 2.1129,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5343223535328137,
|
125 |
+
"grad_norm": 8.491691589355469,
|
126 |
+
"learning_rate": 4.1094627441119775e-05,
|
127 |
+
"loss": 2.0646,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.5657530802112145,
|
132 |
+
"grad_norm": 20.68869400024414,
|
133 |
+
"learning_rate": 4.0570781996479764e-05,
|
134 |
+
"loss": 2.091,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.5971838068896153,
|
139 |
+
"grad_norm": 8.865952491760254,
|
140 |
+
"learning_rate": 4.0046936551839745e-05,
|
141 |
+
"loss": 2.0602,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.6286145335680161,
|
146 |
+
"grad_norm": 12.874096870422363,
|
147 |
+
"learning_rate": 3.9523091107199734e-05,
|
148 |
+
"loss": 2.0064,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.6600452602464169,
|
153 |
+
"grad_norm": 9.40224838256836,
|
154 |
+
"learning_rate": 3.8999245662559716e-05,
|
155 |
+
"loss": 2.0428,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.6914759869248177,
|
160 |
+
"grad_norm": 10.570882797241211,
|
161 |
+
"learning_rate": 3.8475400217919705e-05,
|
162 |
+
"loss": 2.0254,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7229067136032185,
|
167 |
+
"grad_norm": 12.117438316345215,
|
168 |
+
"learning_rate": 3.795155477327969e-05,
|
169 |
+
"loss": 2.003,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.7543374402816193,
|
174 |
+
"grad_norm": 11.80452823638916,
|
175 |
+
"learning_rate": 3.742770932863968e-05,
|
176 |
+
"loss": 1.9471,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.7857681669600202,
|
181 |
+
"grad_norm": 9.42381477355957,
|
182 |
+
"learning_rate": 3.690386388399967e-05,
|
183 |
+
"loss": 1.92,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8171988936384209,
|
188 |
+
"grad_norm": 14.402335166931152,
|
189 |
+
"learning_rate": 3.638001843935965e-05,
|
190 |
+
"loss": 1.939,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.8486296203168218,
|
195 |
+
"grad_norm": 7.873473644256592,
|
196 |
+
"learning_rate": 3.585617299471964e-05,
|
197 |
+
"loss": 1.9271,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.8800603469952225,
|
202 |
+
"grad_norm": 8.49427604675293,
|
203 |
+
"learning_rate": 3.533232755007962e-05,
|
204 |
+
"loss": 1.962,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9114910736736234,
|
209 |
+
"grad_norm": 9.598845481872559,
|
210 |
+
"learning_rate": 3.480848210543961e-05,
|
211 |
+
"loss": 1.8921,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.9429218003520241,
|
216 |
+
"grad_norm": 10.971700668334961,
|
217 |
+
"learning_rate": 3.42846366607996e-05,
|
218 |
+
"loss": 1.8815,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.974352527030425,
|
223 |
+
"grad_norm": 8.383946418762207,
|
224 |
+
"learning_rate": 3.376079121615959e-05,
|
225 |
+
"loss": 1.8714,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.0057832537088258,
|
230 |
+
"grad_norm": 12.830138206481934,
|
231 |
+
"learning_rate": 3.323694577151957e-05,
|
232 |
+
"loss": 1.8797,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.0372139803872265,
|
237 |
+
"grad_norm": 11.94987964630127,
|
238 |
+
"learning_rate": 3.271310032687956e-05,
|
239 |
+
"loss": 1.8339,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.0686447070656273,
|
244 |
+
"grad_norm": 9.588113784790039,
|
245 |
+
"learning_rate": 3.218925488223955e-05,
|
246 |
+
"loss": 1.7749,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.1000754337440282,
|
251 |
+
"grad_norm": 10.824664115905762,
|
252 |
+
"learning_rate": 3.166540943759953e-05,
|
253 |
+
"loss": 1.8145,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.131506160422429,
|
258 |
+
"grad_norm": 11.03293228149414,
|
259 |
+
"learning_rate": 3.114156399295952e-05,
|
260 |
+
"loss": 1.7979,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.1629368871008299,
|
265 |
+
"grad_norm": 8.919577598571777,
|
266 |
+
"learning_rate": 3.061771854831951e-05,
|
267 |
+
"loss": 1.8023,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.1943676137792305,
|
272 |
+
"grad_norm": 7.814962863922119,
|
273 |
+
"learning_rate": 3.0093873103679492e-05,
|
274 |
+
"loss": 1.7587,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.2257983404576314,
|
279 |
+
"grad_norm": 7.930530071258545,
|
280 |
+
"learning_rate": 2.9570027659039477e-05,
|
281 |
+
"loss": 1.7956,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.2572290671360322,
|
286 |
+
"grad_norm": 12.548938751220703,
|
287 |
+
"learning_rate": 2.9046182214399466e-05,
|
288 |
+
"loss": 1.7925,
|
289 |
+
"step": 20000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.2886597938144329,
|
293 |
+
"grad_norm": 9.993666648864746,
|
294 |
+
"learning_rate": 2.852233676975945e-05,
|
295 |
+
"loss": 1.7609,
|
296 |
+
"step": 20500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.3200905204928337,
|
300 |
+
"grad_norm": 15.507658958435059,
|
301 |
+
"learning_rate": 2.7998491325119436e-05,
|
302 |
+
"loss": 1.7692,
|
303 |
+
"step": 21000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.3515212471712346,
|
307 |
+
"grad_norm": 11.69993782043457,
|
308 |
+
"learning_rate": 2.7474645880479428e-05,
|
309 |
+
"loss": 1.7253,
|
310 |
+
"step": 21500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.3829519738496354,
|
314 |
+
"grad_norm": 10.937728881835938,
|
315 |
+
"learning_rate": 2.6950800435839413e-05,
|
316 |
+
"loss": 1.732,
|
317 |
+
"step": 22000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.4143827005280363,
|
321 |
+
"grad_norm": 8.787737846374512,
|
322 |
+
"learning_rate": 2.64269549911994e-05,
|
323 |
+
"loss": 1.7335,
|
324 |
+
"step": 22500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.4458134272064371,
|
328 |
+
"grad_norm": 6.934820652008057,
|
329 |
+
"learning_rate": 2.5903109546559384e-05,
|
330 |
+
"loss": 1.6903,
|
331 |
+
"step": 23000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.4772441538848378,
|
335 |
+
"grad_norm": 9.452235221862793,
|
336 |
+
"learning_rate": 2.537926410191937e-05,
|
337 |
+
"loss": 1.7124,
|
338 |
+
"step": 23500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.5086748805632386,
|
342 |
+
"grad_norm": 7.406110763549805,
|
343 |
+
"learning_rate": 2.4855418657279358e-05,
|
344 |
+
"loss": 1.6978,
|
345 |
+
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.5401056072416395,
|
349 |
+
"grad_norm": 8.471650123596191,
|
350 |
+
"learning_rate": 2.4331573212639343e-05,
|
351 |
+
"loss": 1.6761,
|
352 |
+
"step": 24500
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.57153633392004,
|
356 |
+
"grad_norm": 8.462206840515137,
|
357 |
+
"learning_rate": 2.380772776799933e-05,
|
358 |
+
"loss": 1.723,
|
359 |
+
"step": 25000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.602967060598441,
|
363 |
+
"grad_norm": 10.058784484863281,
|
364 |
+
"learning_rate": 2.3283882323359317e-05,
|
365 |
+
"loss": 1.687,
|
366 |
+
"step": 25500
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.6343977872768418,
|
370 |
+
"grad_norm": 8.863463401794434,
|
371 |
+
"learning_rate": 2.2760036878719305e-05,
|
372 |
+
"loss": 1.6844,
|
373 |
+
"step": 26000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.6658285139552427,
|
377 |
+
"grad_norm": 10.471988677978516,
|
378 |
+
"learning_rate": 2.223619143407929e-05,
|
379 |
+
"loss": 1.7151,
|
380 |
+
"step": 26500
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.6972592406336435,
|
384 |
+
"grad_norm": 9.061573028564453,
|
385 |
+
"learning_rate": 2.1712345989439276e-05,
|
386 |
+
"loss": 1.5916,
|
387 |
+
"step": 27000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.7286899673120444,
|
391 |
+
"grad_norm": 8.41381549835205,
|
392 |
+
"learning_rate": 2.1188500544799264e-05,
|
393 |
+
"loss": 1.6388,
|
394 |
+
"step": 27500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.760120693990445,
|
398 |
+
"grad_norm": 9.17684268951416,
|
399 |
+
"learning_rate": 2.066465510015925e-05,
|
400 |
+
"loss": 1.7045,
|
401 |
+
"step": 28000
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.7915514206688459,
|
405 |
+
"grad_norm": 10.983583450317383,
|
406 |
+
"learning_rate": 2.0140809655519235e-05,
|
407 |
+
"loss": 1.6749,
|
408 |
+
"step": 28500
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.8229821473472465,
|
412 |
+
"grad_norm": 8.048336029052734,
|
413 |
+
"learning_rate": 1.9616964210879224e-05,
|
414 |
+
"loss": 1.6347,
|
415 |
+
"step": 29000
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.8544128740256474,
|
419 |
+
"grad_norm": 9.640363693237305,
|
420 |
+
"learning_rate": 1.909311876623921e-05,
|
421 |
+
"loss": 1.6424,
|
422 |
+
"step": 29500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.8858436007040482,
|
426 |
+
"grad_norm": 10.264333724975586,
|
427 |
+
"learning_rate": 1.8569273321599194e-05,
|
428 |
+
"loss": 1.5919,
|
429 |
+
"step": 30000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.917274327382449,
|
433 |
+
"grad_norm": 10.100754737854004,
|
434 |
+
"learning_rate": 1.8045427876959183e-05,
|
435 |
+
"loss": 1.6477,
|
436 |
+
"step": 30500
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 1.94870505406085,
|
440 |
+
"grad_norm": 7.901167392730713,
|
441 |
+
"learning_rate": 1.752158243231917e-05,
|
442 |
+
"loss": 1.636,
|
443 |
+
"step": 31000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.9801357807392508,
|
447 |
+
"grad_norm": 10.34730339050293,
|
448 |
+
"learning_rate": 1.6997736987679156e-05,
|
449 |
+
"loss": 1.639,
|
450 |
+
"step": 31500
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.0115665074176516,
|
454 |
+
"grad_norm": 9.00157642364502,
|
455 |
+
"learning_rate": 1.6473891543039145e-05,
|
456 |
+
"loss": 1.6027,
|
457 |
+
"step": 32000
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.0429972340960525,
|
461 |
+
"grad_norm": 8.343816757202148,
|
462 |
+
"learning_rate": 1.595004609839913e-05,
|
463 |
+
"loss": 1.5728,
|
464 |
+
"step": 32500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.074427960774453,
|
468 |
+
"grad_norm": 9.560211181640625,
|
469 |
+
"learning_rate": 1.5426200653759116e-05,
|
470 |
+
"loss": 1.5924,
|
471 |
+
"step": 33000
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.1058586874528538,
|
475 |
+
"grad_norm": 9.660225868225098,
|
476 |
+
"learning_rate": 1.49023552091191e-05,
|
477 |
+
"loss": 1.5557,
|
478 |
+
"step": 33500
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 2.1372894141312546,
|
482 |
+
"grad_norm": 10.864439964294434,
|
483 |
+
"learning_rate": 1.437850976447909e-05,
|
484 |
+
"loss": 1.5636,
|
485 |
+
"step": 34000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.1687201408096555,
|
489 |
+
"grad_norm": 9.609240531921387,
|
490 |
+
"learning_rate": 1.3854664319839075e-05,
|
491 |
+
"loss": 1.5643,
|
492 |
+
"step": 34500
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.2001508674880563,
|
496 |
+
"grad_norm": 9.839557647705078,
|
497 |
+
"learning_rate": 1.3330818875199062e-05,
|
498 |
+
"loss": 1.5742,
|
499 |
+
"step": 35000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.231581594166457,
|
503 |
+
"grad_norm": 9.829071998596191,
|
504 |
+
"learning_rate": 1.280697343055905e-05,
|
505 |
+
"loss": 1.551,
|
506 |
+
"step": 35500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 2.263012320844858,
|
510 |
+
"grad_norm": 8.181549072265625,
|
511 |
+
"learning_rate": 1.2283127985919035e-05,
|
512 |
+
"loss": 1.5712,
|
513 |
+
"step": 36000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 2.294443047523259,
|
517 |
+
"grad_norm": 7.759120464324951,
|
518 |
+
"learning_rate": 1.1759282541279022e-05,
|
519 |
+
"loss": 1.5383,
|
520 |
+
"step": 36500
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 2.3258737742016597,
|
524 |
+
"grad_norm": 8.53459644317627,
|
525 |
+
"learning_rate": 1.1235437096639008e-05,
|
526 |
+
"loss": 1.5472,
|
527 |
+
"step": 37000
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 2.35730450088006,
|
531 |
+
"grad_norm": 9.845288276672363,
|
532 |
+
"learning_rate": 1.0711591651998994e-05,
|
533 |
+
"loss": 1.5299,
|
534 |
+
"step": 37500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.388735227558461,
|
538 |
+
"grad_norm": 9.097940444946289,
|
539 |
+
"learning_rate": 1.0187746207358981e-05,
|
540 |
+
"loss": 1.5513,
|
541 |
+
"step": 38000
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 2.420165954236862,
|
545 |
+
"grad_norm": 10.140700340270996,
|
546 |
+
"learning_rate": 9.663900762718968e-06,
|
547 |
+
"loss": 1.5314,
|
548 |
+
"step": 38500
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 2.4515966809152627,
|
552 |
+
"grad_norm": 8.499448776245117,
|
553 |
+
"learning_rate": 9.140055318078955e-06,
|
554 |
+
"loss": 1.5381,
|
555 |
+
"step": 39000
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 2.4830274075936636,
|
559 |
+
"grad_norm": 10.239831924438477,
|
560 |
+
"learning_rate": 8.61620987343894e-06,
|
561 |
+
"loss": 1.5338,
|
562 |
+
"step": 39500
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 2.5144581342720644,
|
566 |
+
"grad_norm": 12.466906547546387,
|
567 |
+
"learning_rate": 8.092364428798927e-06,
|
568 |
+
"loss": 1.5361,
|
569 |
+
"step": 40000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 2.5458888609504653,
|
573 |
+
"grad_norm": 5.410431385040283,
|
574 |
+
"learning_rate": 7.568518984158913e-06,
|
575 |
+
"loss": 1.5506,
|
576 |
+
"step": 40500
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 2.5773195876288657,
|
580 |
+
"grad_norm": 10.963549613952637,
|
581 |
+
"learning_rate": 7.0446735395189e-06,
|
582 |
+
"loss": 1.5383,
|
583 |
+
"step": 41000
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 2.608750314307267,
|
587 |
+
"grad_norm": 9.227997779846191,
|
588 |
+
"learning_rate": 6.520828094878888e-06,
|
589 |
+
"loss": 1.5007,
|
590 |
+
"step": 41500
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 2.6401810409856674,
|
594 |
+
"grad_norm": 9.551142692565918,
|
595 |
+
"learning_rate": 5.996982650238874e-06,
|
596 |
+
"loss": 1.5002,
|
597 |
+
"step": 42000
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 2.6716117676640683,
|
601 |
+
"grad_norm": 9.357813835144043,
|
602 |
+
"learning_rate": 5.47313720559886e-06,
|
603 |
+
"loss": 1.521,
|
604 |
+
"step": 42500
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 2.703042494342469,
|
608 |
+
"grad_norm": 9.11950969696045,
|
609 |
+
"learning_rate": 4.949291760958847e-06,
|
610 |
+
"loss": 1.5389,
|
611 |
+
"step": 43000
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 2.73447322102087,
|
615 |
+
"grad_norm": 10.955974578857422,
|
616 |
+
"learning_rate": 4.425446316318833e-06,
|
617 |
+
"loss": 1.5481,
|
618 |
+
"step": 43500
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 2.765903947699271,
|
622 |
+
"grad_norm": 9.225030899047852,
|
623 |
+
"learning_rate": 3.90160087167882e-06,
|
624 |
+
"loss": 1.5181,
|
625 |
+
"step": 44000
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 2.7973346743776717,
|
629 |
+
"grad_norm": 10.103915214538574,
|
630 |
+
"learning_rate": 3.377755427038807e-06,
|
631 |
+
"loss": 1.5013,
|
632 |
+
"step": 44500
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.8287654010560725,
|
636 |
+
"grad_norm": 8.871588706970215,
|
637 |
+
"learning_rate": 2.853909982398793e-06,
|
638 |
+
"loss": 1.5107,
|
639 |
+
"step": 45000
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 2.860196127734473,
|
643 |
+
"grad_norm": 8.05070686340332,
|
644 |
+
"learning_rate": 2.3300645377587797e-06,
|
645 |
+
"loss": 1.4924,
|
646 |
+
"step": 45500
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 2.8916268544128743,
|
650 |
+
"grad_norm": 10.415308952331543,
|
651 |
+
"learning_rate": 1.8062190931187664e-06,
|
652 |
+
"loss": 1.4606,
|
653 |
+
"step": 46000
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 2.9230575810912747,
|
657 |
+
"grad_norm": 8.8274507522583,
|
658 |
+
"learning_rate": 1.2823736484787529e-06,
|
659 |
+
"loss": 1.4867,
|
660 |
+
"step": 46500
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 2.9544883077696755,
|
664 |
+
"grad_norm": 7.306589126586914,
|
665 |
+
"learning_rate": 7.585282038387395e-07,
|
666 |
+
"loss": 1.4848,
|
667 |
+
"step": 47000
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 2.9859190344480764,
|
671 |
+
"grad_norm": 9.284761428833008,
|
672 |
+
"learning_rate": 2.34682759198726e-07,
|
673 |
+
"loss": 1.4519,
|
674 |
+
"step": 47500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 3.0,
|
678 |
+
"step": 47724,
|
679 |
+
"total_flos": 2.514865055648973e+16,
|
680 |
+
"train_loss": 1.8108088482396418,
|
681 |
+
"train_runtime": 10130.0955,
|
682 |
+
"train_samples_per_second": 9.422,
|
683 |
+
"train_steps_per_second": 4.711
|
684 |
+
}
|
685 |
+
],
|
686 |
+
"logging_steps": 500,
|
687 |
+
"max_steps": 47724,
|
688 |
+
"num_input_tokens_seen": 0,
|
689 |
+
"num_train_epochs": 3,
|
690 |
+
"save_steps": 500,
|
691 |
+
"stateful_callbacks": {
|
692 |
+
"TrainerControl": {
|
693 |
+
"args": {
|
694 |
+
"should_epoch_stop": false,
|
695 |
+
"should_evaluate": false,
|
696 |
+
"should_log": false,
|
697 |
+
"should_save": true,
|
698 |
+
"should_training_stop": false
|
699 |
+
},
|
700 |
+
"attributes": {}
|
701 |
+
}
|
702 |
+
},
|
703 |
+
"total_flos": 2.514865055648973e+16,
|
704 |
+
"train_batch_size": 1,
|
705 |
+
"trial_name": null,
|
706 |
+
"trial_params": null
|
707 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e319501945fe5548da129a4d3bc63348f2cab836f2cfb85a2821a845ae7e797b
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|