'instruction'
Browse files- added_tokens.json +3 -0
- bpe.codes +0 -0
- config.json +37 -0
- generation_config.json +9 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +12 -0
- trainer_state.json +618 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask>": 64000
|
3 |
+
}
|
bpe.codes
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "vinai/bartpho-word-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"MBartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 768,
|
12 |
+
"decoder_attention_heads": 12,
|
13 |
+
"decoder_ffn_dim": 3072,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 6,
|
16 |
+
"decoder_start_token_id": 2,
|
17 |
+
"dropout": 0.1,
|
18 |
+
"encoder_attention_heads": 12,
|
19 |
+
"encoder_ffn_dim": 3072,
|
20 |
+
"encoder_layerdrop": 0.0,
|
21 |
+
"encoder_layers": 6,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"forced_eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"init_std": 0.02,
|
26 |
+
"is_encoder_decoder": true,
|
27 |
+
"max_position_embeddings": 1024,
|
28 |
+
"model_type": "mbart",
|
29 |
+
"num_hidden_layers": 6,
|
30 |
+
"pad_token_id": 1,
|
31 |
+
"scale_embedding": false,
|
32 |
+
"tokenizer_class": "PhobertTokenizer",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.30.2",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 64001
|
37 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"forced_eos_token_id": 2,
|
7 |
+
"pad_token_id": 1,
|
8 |
+
"transformers_version": "4.30.2"
|
9 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24673b9c8e0e617f8a638a76a3f64552d24d0a2a3a93bd6941932a56652346f3
|
3 |
+
size 1199936197
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8b7481c14ace3faf9e8941683afa2bbbca47d5563202ac634562867b7a9dc67
|
3 |
+
size 600236781
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a2f80d31b05869407919f8c3e4048d72f1b48d3fc011014515bda593159c127
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf928355da597edad3b10c86cba6df7361b9e35e5e45cc85d1ee1a4d4fa92559
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "</s>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": "<mask>",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"pad_token": "<pad>",
|
9 |
+
"sep_token": "</s>",
|
10 |
+
"tokenizer_class": "PhobertTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,618 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.974948758824869,
|
5 |
+
"global_step": 10950,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.23,
|
12 |
+
"learning_rate": 4.553734061930783e-05,
|
13 |
+
"loss": 1.3816,
|
14 |
+
"step": 250
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.23,
|
18 |
+
"eval_loss": 0.1994573473930359,
|
19 |
+
"eval_runtime": 49.3939,
|
20 |
+
"eval_samples_per_second": 50.553,
|
21 |
+
"eval_steps_per_second": 6.337,
|
22 |
+
"step": 250
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 0.46,
|
26 |
+
"learning_rate": 9.107468123861566e-05,
|
27 |
+
"loss": 0.1818,
|
28 |
+
"step": 500
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.46,
|
32 |
+
"eval_loss": 0.18140748143196106,
|
33 |
+
"eval_runtime": 49.3506,
|
34 |
+
"eval_samples_per_second": 50.597,
|
35 |
+
"eval_steps_per_second": 6.342,
|
36 |
+
"step": 500
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.68,
|
40 |
+
"learning_rate": 9.807120237981e-05,
|
41 |
+
"loss": 0.1716,
|
42 |
+
"step": 750
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 0.68,
|
46 |
+
"eval_loss": 0.1712454855442047,
|
47 |
+
"eval_runtime": 49.3274,
|
48 |
+
"eval_samples_per_second": 50.621,
|
49 |
+
"eval_steps_per_second": 6.345,
|
50 |
+
"step": 750
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.91,
|
54 |
+
"learning_rate": 9.567220036464831e-05,
|
55 |
+
"loss": 0.1501,
|
56 |
+
"step": 1000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.91,
|
60 |
+
"eval_loss": 0.1643093228340149,
|
61 |
+
"eval_runtime": 49.3431,
|
62 |
+
"eval_samples_per_second": 50.605,
|
63 |
+
"eval_steps_per_second": 6.343,
|
64 |
+
"step": 1000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 1.14,
|
68 |
+
"learning_rate": 9.327319834948663e-05,
|
69 |
+
"loss": 0.122,
|
70 |
+
"step": 1250
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 1.14,
|
74 |
+
"eval_loss": 0.16473376750946045,
|
75 |
+
"eval_runtime": 49.4257,
|
76 |
+
"eval_samples_per_second": 50.52,
|
77 |
+
"eval_steps_per_second": 6.333,
|
78 |
+
"step": 1250
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.37,
|
82 |
+
"learning_rate": 9.087419633432492e-05,
|
83 |
+
"loss": 0.1143,
|
84 |
+
"step": 1500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.37,
|
88 |
+
"eval_loss": 0.15297986567020416,
|
89 |
+
"eval_runtime": 49.4063,
|
90 |
+
"eval_samples_per_second": 50.54,
|
91 |
+
"eval_steps_per_second": 6.335,
|
92 |
+
"step": 1500
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.59,
|
96 |
+
"learning_rate": 8.847519431916324e-05,
|
97 |
+
"loss": 0.1121,
|
98 |
+
"step": 1750
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.59,
|
102 |
+
"eval_loss": 0.16007670760154724,
|
103 |
+
"eval_runtime": 49.3369,
|
104 |
+
"eval_samples_per_second": 50.611,
|
105 |
+
"eval_steps_per_second": 6.344,
|
106 |
+
"step": 1750
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 1.82,
|
110 |
+
"learning_rate": 8.607619230400153e-05,
|
111 |
+
"loss": 0.1078,
|
112 |
+
"step": 2000
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 1.82,
|
116 |
+
"eval_loss": 0.14469072222709656,
|
117 |
+
"eval_runtime": 49.3439,
|
118 |
+
"eval_samples_per_second": 50.604,
|
119 |
+
"eval_steps_per_second": 6.343,
|
120 |
+
"step": 2000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 2.05,
|
124 |
+
"learning_rate": 8.367719028883985e-05,
|
125 |
+
"loss": 0.0954,
|
126 |
+
"step": 2250
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 2.05,
|
130 |
+
"eval_loss": 0.14710724353790283,
|
131 |
+
"eval_runtime": 49.3536,
|
132 |
+
"eval_samples_per_second": 50.594,
|
133 |
+
"eval_steps_per_second": 6.342,
|
134 |
+
"step": 2250
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.28,
|
138 |
+
"learning_rate": 8.127818827367816e-05,
|
139 |
+
"loss": 0.0804,
|
140 |
+
"step": 2500
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.28,
|
144 |
+
"eval_loss": 0.13685058057308197,
|
145 |
+
"eval_runtime": 49.355,
|
146 |
+
"eval_samples_per_second": 50.593,
|
147 |
+
"eval_steps_per_second": 6.342,
|
148 |
+
"step": 2500
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 2.51,
|
152 |
+
"learning_rate": 7.887918625851645e-05,
|
153 |
+
"loss": 0.08,
|
154 |
+
"step": 2750
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 2.51,
|
158 |
+
"eval_loss": 0.13740722835063934,
|
159 |
+
"eval_runtime": 49.3607,
|
160 |
+
"eval_samples_per_second": 50.587,
|
161 |
+
"eval_steps_per_second": 6.341,
|
162 |
+
"step": 2750
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 2.73,
|
166 |
+
"learning_rate": 7.648018424335477e-05,
|
167 |
+
"loss": 0.0769,
|
168 |
+
"step": 3000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 2.73,
|
172 |
+
"eval_loss": 0.1370161473751068,
|
173 |
+
"eval_runtime": 49.3701,
|
174 |
+
"eval_samples_per_second": 50.577,
|
175 |
+
"eval_steps_per_second": 6.34,
|
176 |
+
"step": 3000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.96,
|
180 |
+
"learning_rate": 7.408118222819308e-05,
|
181 |
+
"loss": 0.0782,
|
182 |
+
"step": 3250
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.96,
|
186 |
+
"eval_loss": 0.13374929130077362,
|
187 |
+
"eval_runtime": 49.4074,
|
188 |
+
"eval_samples_per_second": 50.539,
|
189 |
+
"eval_steps_per_second": 6.335,
|
190 |
+
"step": 3250
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 3.19,
|
194 |
+
"learning_rate": 7.168218021303138e-05,
|
195 |
+
"loss": 0.0591,
|
196 |
+
"step": 3500
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 3.19,
|
200 |
+
"eval_loss": 0.13687731325626373,
|
201 |
+
"eval_runtime": 49.344,
|
202 |
+
"eval_samples_per_second": 50.604,
|
203 |
+
"eval_steps_per_second": 6.343,
|
204 |
+
"step": 3500
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 3.42,
|
208 |
+
"learning_rate": 6.928317819786969e-05,
|
209 |
+
"loss": 0.0575,
|
210 |
+
"step": 3750
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 3.42,
|
214 |
+
"eval_loss": 0.13442662358283997,
|
215 |
+
"eval_runtime": 49.347,
|
216 |
+
"eval_samples_per_second": 50.601,
|
217 |
+
"eval_steps_per_second": 6.343,
|
218 |
+
"step": 3750
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 3.64,
|
222 |
+
"learning_rate": 6.6884176182708e-05,
|
223 |
+
"loss": 0.0579,
|
224 |
+
"step": 4000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 3.64,
|
228 |
+
"eval_loss": 0.13463211059570312,
|
229 |
+
"eval_runtime": 49.3532,
|
230 |
+
"eval_samples_per_second": 50.595,
|
231 |
+
"eval_steps_per_second": 6.342,
|
232 |
+
"step": 4000
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 3.87,
|
236 |
+
"learning_rate": 6.44851741675463e-05,
|
237 |
+
"loss": 0.0541,
|
238 |
+
"step": 4250
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 3.87,
|
242 |
+
"eval_loss": 0.12762367725372314,
|
243 |
+
"eval_runtime": 49.3131,
|
244 |
+
"eval_samples_per_second": 50.636,
|
245 |
+
"eval_steps_per_second": 6.347,
|
246 |
+
"step": 4250
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 4.1,
|
250 |
+
"learning_rate": 6.208617215238462e-05,
|
251 |
+
"loss": 0.0469,
|
252 |
+
"step": 4500
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 4.1,
|
256 |
+
"eval_loss": 0.1321054846048355,
|
257 |
+
"eval_runtime": 49.3382,
|
258 |
+
"eval_samples_per_second": 50.61,
|
259 |
+
"eval_steps_per_second": 6.344,
|
260 |
+
"step": 4500
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 4.33,
|
264 |
+
"learning_rate": 5.968717013722291e-05,
|
265 |
+
"loss": 0.0367,
|
266 |
+
"step": 4750
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 4.33,
|
270 |
+
"eval_loss": 0.13329076766967773,
|
271 |
+
"eval_runtime": 49.3411,
|
272 |
+
"eval_samples_per_second": 50.607,
|
273 |
+
"eval_steps_per_second": 6.344,
|
274 |
+
"step": 4750
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 4.55,
|
278 |
+
"learning_rate": 5.7288168122061226e-05,
|
279 |
+
"loss": 0.0409,
|
280 |
+
"step": 5000
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 4.55,
|
284 |
+
"eval_loss": 0.13458645343780518,
|
285 |
+
"eval_runtime": 49.3393,
|
286 |
+
"eval_samples_per_second": 50.609,
|
287 |
+
"eval_steps_per_second": 6.344,
|
288 |
+
"step": 5000
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 4.78,
|
292 |
+
"learning_rate": 5.488916610689954e-05,
|
293 |
+
"loss": 0.0402,
|
294 |
+
"step": 5250
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 4.78,
|
298 |
+
"eval_loss": 0.12923233211040497,
|
299 |
+
"eval_runtime": 49.4868,
|
300 |
+
"eval_samples_per_second": 50.458,
|
301 |
+
"eval_steps_per_second": 6.325,
|
302 |
+
"step": 5250
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 5.01,
|
306 |
+
"learning_rate": 5.249016409173784e-05,
|
307 |
+
"loss": 0.0378,
|
308 |
+
"step": 5500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 5.01,
|
312 |
+
"eval_loss": 0.12460647523403168,
|
313 |
+
"eval_runtime": 49.3719,
|
314 |
+
"eval_samples_per_second": 50.575,
|
315 |
+
"eval_steps_per_second": 6.34,
|
316 |
+
"step": 5500
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 5.24,
|
320 |
+
"learning_rate": 5.009116207657615e-05,
|
321 |
+
"loss": 0.0258,
|
322 |
+
"step": 5750
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 5.24,
|
326 |
+
"eval_loss": 0.1305789053440094,
|
327 |
+
"eval_runtime": 49.3929,
|
328 |
+
"eval_samples_per_second": 50.554,
|
329 |
+
"eval_steps_per_second": 6.337,
|
330 |
+
"step": 5750
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 5.47,
|
334 |
+
"learning_rate": 4.769216006141446e-05,
|
335 |
+
"loss": 0.0252,
|
336 |
+
"step": 6000
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 5.47,
|
340 |
+
"eval_loss": 0.13075487315654755,
|
341 |
+
"eval_runtime": 49.3793,
|
342 |
+
"eval_samples_per_second": 50.568,
|
343 |
+
"eval_steps_per_second": 6.339,
|
344 |
+
"step": 6000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 5.69,
|
348 |
+
"learning_rate": 4.5293158046252756e-05,
|
349 |
+
"loss": 0.0266,
|
350 |
+
"step": 6250
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 5.69,
|
354 |
+
"eval_loss": 0.13152019679546356,
|
355 |
+
"eval_runtime": 49.3918,
|
356 |
+
"eval_samples_per_second": 50.555,
|
357 |
+
"eval_steps_per_second": 6.337,
|
358 |
+
"step": 6250
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 5.92,
|
362 |
+
"learning_rate": 4.289415603109107e-05,
|
363 |
+
"loss": 0.0264,
|
364 |
+
"step": 6500
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 5.92,
|
368 |
+
"eval_loss": 0.12978705763816833,
|
369 |
+
"eval_runtime": 49.4158,
|
370 |
+
"eval_samples_per_second": 50.53,
|
371 |
+
"eval_steps_per_second": 6.334,
|
372 |
+
"step": 6500
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 6.15,
|
376 |
+
"learning_rate": 4.0495154015929375e-05,
|
377 |
+
"loss": 0.0204,
|
378 |
+
"step": 6750
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 6.15,
|
382 |
+
"eval_loss": 0.1330789029598236,
|
383 |
+
"eval_runtime": 49.4096,
|
384 |
+
"eval_samples_per_second": 50.537,
|
385 |
+
"eval_steps_per_second": 6.335,
|
386 |
+
"step": 6750
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 6.38,
|
390 |
+
"learning_rate": 3.809615200076768e-05,
|
391 |
+
"loss": 0.0176,
|
392 |
+
"step": 7000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 6.38,
|
396 |
+
"eval_loss": 0.13327623903751373,
|
397 |
+
"eval_runtime": 49.4281,
|
398 |
+
"eval_samples_per_second": 50.518,
|
399 |
+
"eval_steps_per_second": 6.332,
|
400 |
+
"step": 7000
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 6.6,
|
404 |
+
"learning_rate": 3.569714998560599e-05,
|
405 |
+
"loss": 0.0177,
|
406 |
+
"step": 7250
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 6.6,
|
410 |
+
"eval_loss": 0.13123974204063416,
|
411 |
+
"eval_runtime": 49.4644,
|
412 |
+
"eval_samples_per_second": 50.481,
|
413 |
+
"eval_steps_per_second": 6.328,
|
414 |
+
"step": 7250
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 6.83,
|
418 |
+
"learning_rate": 3.32981479704443e-05,
|
419 |
+
"loss": 0.0161,
|
420 |
+
"step": 7500
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 6.83,
|
424 |
+
"eval_loss": 0.1328614354133606,
|
425 |
+
"eval_runtime": 49.4499,
|
426 |
+
"eval_samples_per_second": 50.496,
|
427 |
+
"eval_steps_per_second": 6.33,
|
428 |
+
"step": 7500
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 7.06,
|
432 |
+
"learning_rate": 3.0899145955282606e-05,
|
433 |
+
"loss": 0.016,
|
434 |
+
"step": 7750
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 7.06,
|
438 |
+
"eval_loss": 0.13026753067970276,
|
439 |
+
"eval_runtime": 49.4661,
|
440 |
+
"eval_samples_per_second": 50.479,
|
441 |
+
"eval_steps_per_second": 6.328,
|
442 |
+
"step": 7750
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"epoch": 7.29,
|
446 |
+
"learning_rate": 2.850014394012091e-05,
|
447 |
+
"loss": 0.0104,
|
448 |
+
"step": 8000
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 7.29,
|
452 |
+
"eval_loss": 0.13250969350337982,
|
453 |
+
"eval_runtime": 49.5109,
|
454 |
+
"eval_samples_per_second": 50.433,
|
455 |
+
"eval_steps_per_second": 6.322,
|
456 |
+
"step": 8000
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 7.52,
|
460 |
+
"learning_rate": 2.6101141924959215e-05,
|
461 |
+
"loss": 0.0104,
|
462 |
+
"step": 8250
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 7.52,
|
466 |
+
"eval_loss": 0.1344473958015442,
|
467 |
+
"eval_runtime": 49.4545,
|
468 |
+
"eval_samples_per_second": 50.491,
|
469 |
+
"eval_steps_per_second": 6.329,
|
470 |
+
"step": 8250
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 7.74,
|
474 |
+
"learning_rate": 2.3702139909797524e-05,
|
475 |
+
"loss": 0.0107,
|
476 |
+
"step": 8500
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 7.74,
|
480 |
+
"eval_loss": 0.13361412286758423,
|
481 |
+
"eval_runtime": 49.4611,
|
482 |
+
"eval_samples_per_second": 50.484,
|
483 |
+
"eval_steps_per_second": 6.328,
|
484 |
+
"step": 8500
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 7.97,
|
488 |
+
"learning_rate": 2.1303137894635834e-05,
|
489 |
+
"loss": 0.0105,
|
490 |
+
"step": 8750
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 7.97,
|
494 |
+
"eval_loss": 0.1311049610376358,
|
495 |
+
"eval_runtime": 49.3899,
|
496 |
+
"eval_samples_per_second": 50.557,
|
497 |
+
"eval_steps_per_second": 6.337,
|
498 |
+
"step": 8750
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 8.2,
|
502 |
+
"learning_rate": 1.890413587947414e-05,
|
503 |
+
"loss": 0.0072,
|
504 |
+
"step": 9000
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 8.2,
|
508 |
+
"eval_loss": 0.1345677375793457,
|
509 |
+
"eval_runtime": 49.4945,
|
510 |
+
"eval_samples_per_second": 50.45,
|
511 |
+
"eval_steps_per_second": 6.324,
|
512 |
+
"step": 9000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 8.43,
|
516 |
+
"learning_rate": 1.6505133864312446e-05,
|
517 |
+
"loss": 0.0065,
|
518 |
+
"step": 9250
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 8.43,
|
522 |
+
"eval_loss": 0.13423801958560944,
|
523 |
+
"eval_runtime": 49.4363,
|
524 |
+
"eval_samples_per_second": 50.509,
|
525 |
+
"eval_steps_per_second": 6.331,
|
526 |
+
"step": 9250
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 8.65,
|
530 |
+
"learning_rate": 1.4106131849150753e-05,
|
531 |
+
"loss": 0.0062,
|
532 |
+
"step": 9500
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 8.65,
|
536 |
+
"eval_loss": 0.13279776275157928,
|
537 |
+
"eval_runtime": 49.5198,
|
538 |
+
"eval_samples_per_second": 50.424,
|
539 |
+
"eval_steps_per_second": 6.321,
|
540 |
+
"step": 9500
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 8.88,
|
544 |
+
"learning_rate": 1.1707129833989061e-05,
|
545 |
+
"loss": 0.006,
|
546 |
+
"step": 9750
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 8.88,
|
550 |
+
"eval_loss": 0.13258913159370422,
|
551 |
+
"eval_runtime": 49.511,
|
552 |
+
"eval_samples_per_second": 50.433,
|
553 |
+
"eval_steps_per_second": 6.322,
|
554 |
+
"step": 9750
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 9.11,
|
558 |
+
"learning_rate": 9.308127818827369e-06,
|
559 |
+
"loss": 0.0052,
|
560 |
+
"step": 10000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 9.11,
|
564 |
+
"eval_loss": 0.13228829205036163,
|
565 |
+
"eval_runtime": 49.4456,
|
566 |
+
"eval_samples_per_second": 50.5,
|
567 |
+
"eval_steps_per_second": 6.33,
|
568 |
+
"step": 10000
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 9.34,
|
572 |
+
"learning_rate": 6.909125803665675e-06,
|
573 |
+
"loss": 0.0039,
|
574 |
+
"step": 10250
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 9.34,
|
578 |
+
"eval_loss": 0.13294672966003418,
|
579 |
+
"eval_runtime": 49.4619,
|
580 |
+
"eval_samples_per_second": 50.483,
|
581 |
+
"eval_steps_per_second": 6.328,
|
582 |
+
"step": 10250
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 9.57,
|
586 |
+
"learning_rate": 4.510123788503983e-06,
|
587 |
+
"loss": 0.0039,
|
588 |
+
"step": 10500
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 9.57,
|
592 |
+
"eval_loss": 0.13272705674171448,
|
593 |
+
"eval_runtime": 49.4568,
|
594 |
+
"eval_samples_per_second": 50.489,
|
595 |
+
"eval_steps_per_second": 6.329,
|
596 |
+
"step": 10500
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 9.79,
|
600 |
+
"learning_rate": 2.11112177334229e-06,
|
601 |
+
"loss": 0.004,
|
602 |
+
"step": 10750
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 9.79,
|
606 |
+
"eval_loss": 0.13220719993114471,
|
607 |
+
"eval_runtime": 49.465,
|
608 |
+
"eval_samples_per_second": 50.48,
|
609 |
+
"eval_steps_per_second": 6.328,
|
610 |
+
"step": 10750
|
611 |
+
}
|
612 |
+
],
|
613 |
+
"max_steps": 10970,
|
614 |
+
"num_train_epochs": 10,
|
615 |
+
"total_flos": 8.710540889772442e+16,
|
616 |
+
"trial_name": null,
|
617 |
+
"trial_params": null
|
618 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3efa9b12ba9d3638df5286a4ecf173371d214385a5a7c0b228d6521a49c54c2e
|
3 |
+
size 4027
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|