End of training
Browse files- .gitignore +1 -0
- all_results.json +14 -0
- config.json +57 -0
- eval_results.json +9 -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 +301 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
checkpoint-*/
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_accuracy": 0.7986,
|
4 |
+
"eval_loss": 0.33286044001579285,
|
5 |
+
"eval_runtime": 151.7682,
|
6 |
+
"eval_samples": 4887,
|
7 |
+
"eval_samples_per_second": 32.2,
|
8 |
+
"eval_steps_per_second": 2.016,
|
9 |
+
"train_loss": 0.0,
|
10 |
+
"train_runtime": 0.057,
|
11 |
+
"train_samples": 87866,
|
12 |
+
"train_samples_per_second": 1541330.369,
|
13 |
+
"train_steps_per_second": 192661.911
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 4096,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1024,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 24,
|
19 |
+
"num_heads": 16,
|
20 |
+
"num_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"task_specific_params": {
|
25 |
+
"summarization": {
|
26 |
+
"early_stopping": true,
|
27 |
+
"length_penalty": 2.0,
|
28 |
+
"max_length": 200,
|
29 |
+
"min_length": 30,
|
30 |
+
"no_repeat_ngram_size": 3,
|
31 |
+
"num_beams": 4,
|
32 |
+
"prefix": "summarize: "
|
33 |
+
},
|
34 |
+
"translation_en_to_de": {
|
35 |
+
"early_stopping": true,
|
36 |
+
"max_length": 300,
|
37 |
+
"num_beams": 4,
|
38 |
+
"prefix": "translate English to German: "
|
39 |
+
},
|
40 |
+
"translation_en_to_fr": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"max_length": 300,
|
43 |
+
"num_beams": 4,
|
44 |
+
"prefix": "translate English to French: "
|
45 |
+
},
|
46 |
+
"translation_en_to_ro": {
|
47 |
+
"early_stopping": true,
|
48 |
+
"max_length": 300,
|
49 |
+
"num_beams": 4,
|
50 |
+
"prefix": "translate English to Romanian: "
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.11.3",
|
55 |
+
"use_cache": true,
|
56 |
+
"vocab_size": 32100
|
57 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_accuracy": 0.7986,
|
4 |
+
"eval_loss": 0.33286044001579285,
|
5 |
+
"eval_runtime": 151.7682,
|
6 |
+
"eval_samples": 4887,
|
7 |
+
"eval_samples_per_second": 32.2,
|
8 |
+
"eval_steps_per_second": 2.016
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c129de941d14268599c41de3b73b6af275457445a117b4fb84eae464de58f04
|
3 |
+
size 2950790023
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-large", "tokenizer_class": "T5Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 0.057,
|
5 |
+
"train_samples": 87866,
|
6 |
+
"train_samples_per_second": 1541330.369,
|
7 |
+
"train_steps_per_second": 192661.911
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,301 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9999544771703008,
|
5 |
+
"global_step": 21966,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.05,
|
12 |
+
"learning_rate": 9.878230691954093e-05,
|
13 |
+
"loss": 0.7559,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.09,
|
18 |
+
"learning_rate": 9.726019056896709e-05,
|
19 |
+
"loss": 0.4773,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.14,
|
24 |
+
"learning_rate": 9.573807421839326e-05,
|
25 |
+
"loss": 0.4477,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.18,
|
30 |
+
"learning_rate": 9.421595786781941e-05,
|
31 |
+
"loss": 0.4385,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.23,
|
36 |
+
"learning_rate": 9.269384151724558e-05,
|
37 |
+
"loss": 0.4258,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.27,
|
42 |
+
"learning_rate": 9.117172516667175e-05,
|
43 |
+
"loss": 0.419,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.32,
|
48 |
+
"learning_rate": 8.964960881609791e-05,
|
49 |
+
"loss": 0.4017,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.36,
|
54 |
+
"learning_rate": 8.812749246552407e-05,
|
55 |
+
"loss": 0.4165,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.41,
|
60 |
+
"learning_rate": 8.660537611495024e-05,
|
61 |
+
"loss": 0.4148,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.46,
|
66 |
+
"learning_rate": 8.508325976437639e-05,
|
67 |
+
"loss": 0.406,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.5,
|
72 |
+
"learning_rate": 8.356114341380256e-05,
|
73 |
+
"loss": 0.395,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.55,
|
78 |
+
"learning_rate": 8.203902706322871e-05,
|
79 |
+
"loss": 0.3927,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.59,
|
84 |
+
"learning_rate": 8.051691071265488e-05,
|
85 |
+
"loss": 0.3776,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.64,
|
90 |
+
"learning_rate": 7.899479436208103e-05,
|
91 |
+
"loss": 0.3555,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.68,
|
96 |
+
"learning_rate": 7.74726780115072e-05,
|
97 |
+
"loss": 0.3731,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.73,
|
102 |
+
"learning_rate": 7.595056166093336e-05,
|
103 |
+
"loss": 0.3593,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.77,
|
108 |
+
"learning_rate": 7.442844531035952e-05,
|
109 |
+
"loss": 0.3643,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.82,
|
114 |
+
"learning_rate": 7.290632895978569e-05,
|
115 |
+
"loss": 0.3607,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.86,
|
120 |
+
"learning_rate": 7.138421260921186e-05,
|
121 |
+
"loss": 0.3404,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.91,
|
126 |
+
"learning_rate": 6.986209625863801e-05,
|
127 |
+
"loss": 0.3527,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.96,
|
132 |
+
"learning_rate": 6.833997990806418e-05,
|
133 |
+
"loss": 0.3513,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.0,
|
138 |
+
"eval_accuracy": 0.7714,
|
139 |
+
"eval_loss": 0.3165387809276581,
|
140 |
+
"eval_runtime": 145.7923,
|
141 |
+
"eval_samples_per_second": 33.52,
|
142 |
+
"eval_steps_per_second": 2.099,
|
143 |
+
"step": 10983
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 1.0,
|
147 |
+
"learning_rate": 6.681786355749033e-05,
|
148 |
+
"loss": 0.3399,
|
149 |
+
"step": 11000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.05,
|
153 |
+
"learning_rate": 6.52957472069165e-05,
|
154 |
+
"loss": 0.2111,
|
155 |
+
"step": 11500
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 1.09,
|
159 |
+
"learning_rate": 6.377363085634266e-05,
|
160 |
+
"loss": 0.2117,
|
161 |
+
"step": 12000
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 1.14,
|
165 |
+
"learning_rate": 6.225151450576882e-05,
|
166 |
+
"loss": 0.2152,
|
167 |
+
"step": 12500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.18,
|
171 |
+
"learning_rate": 6.0729398155194985e-05,
|
172 |
+
"loss": 0.2217,
|
173 |
+
"step": 13000
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 1.23,
|
177 |
+
"learning_rate": 5.920728180462115e-05,
|
178 |
+
"loss": 0.2194,
|
179 |
+
"step": 13500
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.27,
|
183 |
+
"learning_rate": 5.768516545404731e-05,
|
184 |
+
"loss": 0.224,
|
185 |
+
"step": 14000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 1.32,
|
189 |
+
"learning_rate": 5.6163049103473475e-05,
|
190 |
+
"loss": 0.2262,
|
191 |
+
"step": 14500
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.37,
|
195 |
+
"learning_rate": 5.464093275289963e-05,
|
196 |
+
"loss": 0.2308,
|
197 |
+
"step": 15000
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.41,
|
201 |
+
"learning_rate": 5.31188164023258e-05,
|
202 |
+
"loss": 0.2266,
|
203 |
+
"step": 15500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 1.46,
|
207 |
+
"learning_rate": 5.159670005175196e-05,
|
208 |
+
"loss": 0.2162,
|
209 |
+
"step": 16000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.5,
|
213 |
+
"learning_rate": 5.0074583701178126e-05,
|
214 |
+
"loss": 0.2288,
|
215 |
+
"step": 16500
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 1.55,
|
219 |
+
"learning_rate": 4.855246735060428e-05,
|
220 |
+
"loss": 0.2268,
|
221 |
+
"step": 17000
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.59,
|
225 |
+
"learning_rate": 4.703035100003044e-05,
|
226 |
+
"loss": 0.2136,
|
227 |
+
"step": 17500
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.64,
|
231 |
+
"learning_rate": 4.55082346494566e-05,
|
232 |
+
"loss": 0.2199,
|
233 |
+
"step": 18000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.68,
|
237 |
+
"learning_rate": 4.398611829888277e-05,
|
238 |
+
"loss": 0.2187,
|
239 |
+
"step": 18500
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.73,
|
243 |
+
"learning_rate": 4.246400194830893e-05,
|
244 |
+
"loss": 0.2104,
|
245 |
+
"step": 19000
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 1.78,
|
249 |
+
"learning_rate": 4.094188559773509e-05,
|
250 |
+
"loss": 0.2093,
|
251 |
+
"step": 19500
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.82,
|
255 |
+
"learning_rate": 3.941976924716125e-05,
|
256 |
+
"loss": 0.2133,
|
257 |
+
"step": 20000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.87,
|
261 |
+
"learning_rate": 3.7897652896587414e-05,
|
262 |
+
"loss": 0.2122,
|
263 |
+
"step": 20500
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.91,
|
267 |
+
"learning_rate": 3.6375536546013575e-05,
|
268 |
+
"loss": 0.2103,
|
269 |
+
"step": 21000
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 1.96,
|
273 |
+
"learning_rate": 3.485342019543974e-05,
|
274 |
+
"loss": 0.2109,
|
275 |
+
"step": 21500
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 2.0,
|
279 |
+
"eval_accuracy": 0.7986,
|
280 |
+
"eval_loss": 0.33286044001579285,
|
281 |
+
"eval_runtime": 145.5877,
|
282 |
+
"eval_samples_per_second": 33.567,
|
283 |
+
"eval_steps_per_second": 2.102,
|
284 |
+
"step": 21966
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.0,
|
288 |
+
"step": 21966,
|
289 |
+
"total_flos": 3.80468091420672e+17,
|
290 |
+
"train_loss": 0.0,
|
291 |
+
"train_runtime": 0.057,
|
292 |
+
"train_samples_per_second": 1541330.369,
|
293 |
+
"train_steps_per_second": 192661.911
|
294 |
+
}
|
295 |
+
],
|
296 |
+
"max_steps": 10983,
|
297 |
+
"num_train_epochs": 1,
|
298 |
+
"total_flos": 3.80468091420672e+17,
|
299 |
+
"trial_name": null,
|
300 |
+
"trial_params": null
|
301 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a2565c39287ef9a560b024aded0fa87f7dd9a636e2ef6ff73357484ea0a21c7
|
3 |
+
size 2927
|