add MT model
Browse files- all_results.json +15 -0
- config.json +30 -0
- generated_predictions.txt +0 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +391 -0
- training_args.bin +3 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"predict_bleu": 29.274,
|
4 |
+
"predict_gen_len": 111.7499,
|
5 |
+
"predict_loss": 0.5117401480674744,
|
6 |
+
"predict_runtime": 953.1451,
|
7 |
+
"predict_samples": 1835,
|
8 |
+
"predict_samples_per_second": 1.925,
|
9 |
+
"predict_steps_per_second": 0.193,
|
10 |
+
"train_loss": 0.5257373959726233,
|
11 |
+
"train_runtime": 23699.3965,
|
12 |
+
"train_samples": 30782,
|
13 |
+
"train_samples_per_second": 12.989,
|
14 |
+
"train_steps_per_second": 1.299
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/byt5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 3968,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1536,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "gated-gelu",
|
13 |
+
"gradient_checkpointing": false,
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "t5",
|
18 |
+
"num_decoder_layers": 6,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 18,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"tokenizer_class": "ByT5Tokenizer",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.12.0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 384
|
30 |
+
}
|
generated_predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
predict_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"predict_bleu": 29.274,
|
3 |
+
"predict_gen_len": 111.7499,
|
4 |
+
"predict_loss": 0.5117401480674744,
|
5 |
+
"predict_runtime": 953.1451,
|
6 |
+
"predict_samples": 1835,
|
7 |
+
"predict_samples_per_second": 1.925,
|
8 |
+
"predict_steps_per_second": 0.193
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bc03934149d81f5b0e37a54363438f5fa95ce52eecb2aff9ddfaa3043c3be92
|
3 |
+
size 2326733259
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "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>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "extra_ids": 125, "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>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"], "special_tokens_map_file": "/nethome/didelani/.cache/huggingface/transformers/f22e687c418a9ed3e651ca340d6a5880bbb312bc24bbe893f5cd47288891b89d.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109", "tokenizer_file": null, "name_or_path": "google/byt5-base", "tokenizer_class": "ByT5Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.5257373959726233,
|
4 |
+
"train_runtime": 23699.3965,
|
5 |
+
"train_samples": 30782,
|
6 |
+
"train_samples_per_second": 12.989,
|
7 |
+
"train_steps_per_second": 1.299
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,391 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 30790,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.16,
|
12 |
+
"learning_rate": 4.91880480675544e-05,
|
13 |
+
"loss": 1.1084,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.32,
|
18 |
+
"learning_rate": 4.8376096135108804e-05,
|
19 |
+
"loss": 0.8396,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.49,
|
24 |
+
"learning_rate": 4.7564144202663205e-05,
|
25 |
+
"loss": 0.7548,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.65,
|
30 |
+
"learning_rate": 4.6752192270217606e-05,
|
31 |
+
"loss": 0.7172,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.81,
|
36 |
+
"learning_rate": 4.5940240337772006e-05,
|
37 |
+
"loss": 0.6923,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.97,
|
42 |
+
"learning_rate": 4.512828840532641e-05,
|
43 |
+
"loss": 0.6761,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.14,
|
48 |
+
"learning_rate": 4.431633647288081e-05,
|
49 |
+
"loss": 0.6416,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.3,
|
54 |
+
"learning_rate": 4.350438454043521e-05,
|
55 |
+
"loss": 0.6304,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.46,
|
60 |
+
"learning_rate": 4.269243260798961e-05,
|
61 |
+
"loss": 0.6153,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.62,
|
66 |
+
"learning_rate": 4.188048067554401e-05,
|
67 |
+
"loss": 0.6141,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.79,
|
72 |
+
"learning_rate": 4.106852874309841e-05,
|
73 |
+
"loss": 0.6091,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.95,
|
78 |
+
"learning_rate": 4.025657681065281e-05,
|
79 |
+
"loss": 0.6,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.11,
|
84 |
+
"learning_rate": 3.944462487820721e-05,
|
85 |
+
"loss": 0.5758,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.27,
|
90 |
+
"learning_rate": 3.8632672945761614e-05,
|
91 |
+
"loss": 0.571,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.44,
|
96 |
+
"learning_rate": 3.7820721013316015e-05,
|
97 |
+
"loss": 0.5656,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.6,
|
102 |
+
"learning_rate": 3.7008769080870415e-05,
|
103 |
+
"loss": 0.5625,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.76,
|
108 |
+
"learning_rate": 3.6196817148424816e-05,
|
109 |
+
"loss": 0.5592,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 2.92,
|
114 |
+
"learning_rate": 3.538486521597922e-05,
|
115 |
+
"loss": 0.553,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 3.09,
|
120 |
+
"learning_rate": 3.457291328353362e-05,
|
121 |
+
"loss": 0.5394,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 3.25,
|
126 |
+
"learning_rate": 3.376096135108802e-05,
|
127 |
+
"loss": 0.529,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.41,
|
132 |
+
"learning_rate": 3.294900941864242e-05,
|
133 |
+
"loss": 0.531,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.57,
|
138 |
+
"learning_rate": 3.213705748619682e-05,
|
139 |
+
"loss": 0.5196,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 3.73,
|
144 |
+
"learning_rate": 3.132510555375122e-05,
|
145 |
+
"loss": 0.5244,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 3.9,
|
150 |
+
"learning_rate": 3.051315362130562e-05,
|
151 |
+
"loss": 0.5201,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 4.06,
|
156 |
+
"learning_rate": 2.970120168886002e-05,
|
157 |
+
"loss": 0.5142,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 4.22,
|
162 |
+
"learning_rate": 2.888924975641442e-05,
|
163 |
+
"loss": 0.5004,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 4.38,
|
168 |
+
"learning_rate": 2.8077297823968824e-05,
|
169 |
+
"loss": 0.4977,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.55,
|
174 |
+
"learning_rate": 2.7265345891523225e-05,
|
175 |
+
"loss": 0.5009,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 4.71,
|
180 |
+
"learning_rate": 2.6453393959077623e-05,
|
181 |
+
"loss": 0.5024,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 4.87,
|
186 |
+
"learning_rate": 2.5641442026632023e-05,
|
187 |
+
"loss": 0.5021,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 5.03,
|
192 |
+
"learning_rate": 2.4829490094186424e-05,
|
193 |
+
"loss": 0.4869,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 5.2,
|
198 |
+
"learning_rate": 2.401753816174083e-05,
|
199 |
+
"loss": 0.4865,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 5.36,
|
204 |
+
"learning_rate": 2.3205586229295226e-05,
|
205 |
+
"loss": 0.4768,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 5.52,
|
210 |
+
"learning_rate": 2.2393634296849627e-05,
|
211 |
+
"loss": 0.4785,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 5.68,
|
216 |
+
"learning_rate": 2.158168236440403e-05,
|
217 |
+
"loss": 0.4719,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 5.85,
|
222 |
+
"learning_rate": 2.0769730431958428e-05,
|
223 |
+
"loss": 0.4779,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 6.01,
|
228 |
+
"learning_rate": 1.995777849951283e-05,
|
229 |
+
"loss": 0.4796,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 6.17,
|
234 |
+
"learning_rate": 1.914582656706723e-05,
|
235 |
+
"loss": 0.4592,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 6.33,
|
240 |
+
"learning_rate": 1.833387463462163e-05,
|
241 |
+
"loss": 0.4595,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 6.5,
|
246 |
+
"learning_rate": 1.752192270217603e-05,
|
247 |
+
"loss": 0.4615,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 6.66,
|
252 |
+
"learning_rate": 1.6709970769730432e-05,
|
253 |
+
"loss": 0.4649,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 6.82,
|
258 |
+
"learning_rate": 1.5898018837284833e-05,
|
259 |
+
"loss": 0.4591,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 6.98,
|
264 |
+
"learning_rate": 1.5086066904839236e-05,
|
265 |
+
"loss": 0.464,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 7.15,
|
270 |
+
"learning_rate": 1.4274114972393635e-05,
|
271 |
+
"loss": 0.4513,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 7.31,
|
276 |
+
"learning_rate": 1.3462163039948036e-05,
|
277 |
+
"loss": 0.4458,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 7.47,
|
282 |
+
"learning_rate": 1.2650211107502435e-05,
|
283 |
+
"loss": 0.4498,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 7.63,
|
288 |
+
"learning_rate": 1.1838259175056837e-05,
|
289 |
+
"loss": 0.4516,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 7.79,
|
294 |
+
"learning_rate": 1.1026307242611238e-05,
|
295 |
+
"loss": 0.4475,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 7.96,
|
300 |
+
"learning_rate": 1.0214355310165639e-05,
|
301 |
+
"loss": 0.4458,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 8.12,
|
306 |
+
"learning_rate": 9.40240337772004e-06,
|
307 |
+
"loss": 0.4427,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 8.28,
|
312 |
+
"learning_rate": 8.59045144527444e-06,
|
313 |
+
"loss": 0.4413,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 8.44,
|
318 |
+
"learning_rate": 7.778499512828841e-06,
|
319 |
+
"loss": 0.4413,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 8.61,
|
324 |
+
"learning_rate": 6.966547580383241e-06,
|
325 |
+
"loss": 0.4417,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 8.77,
|
330 |
+
"learning_rate": 6.154595647937642e-06,
|
331 |
+
"loss": 0.4383,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 8.93,
|
336 |
+
"learning_rate": 5.342643715492044e-06,
|
337 |
+
"loss": 0.4377,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 9.09,
|
342 |
+
"learning_rate": 4.530691783046444e-06,
|
343 |
+
"loss": 0.4319,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 9.26,
|
348 |
+
"learning_rate": 3.718739850600845e-06,
|
349 |
+
"loss": 0.4319,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 9.42,
|
354 |
+
"learning_rate": 2.9067879181552453e-06,
|
355 |
+
"loss": 0.4386,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 9.58,
|
360 |
+
"learning_rate": 2.094835985709646e-06,
|
361 |
+
"loss": 0.4332,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 9.74,
|
366 |
+
"learning_rate": 1.2828840532640467e-06,
|
367 |
+
"loss": 0.4304,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 9.91,
|
372 |
+
"learning_rate": 4.7093212081844755e-07,
|
373 |
+
"loss": 0.4317,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 10.0,
|
378 |
+
"step": 30790,
|
379 |
+
"total_flos": 4.1886686457195725e+17,
|
380 |
+
"train_loss": 0.5257373959726233,
|
381 |
+
"train_runtime": 23699.3965,
|
382 |
+
"train_samples_per_second": 12.989,
|
383 |
+
"train_steps_per_second": 1.299
|
384 |
+
}
|
385 |
+
],
|
386 |
+
"max_steps": 30790,
|
387 |
+
"num_train_epochs": 10,
|
388 |
+
"total_flos": 4.1886686457195725e+17,
|
389 |
+
"trial_name": null,
|
390 |
+
"trial_params": null
|
391 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd341c3e46687e9d72cf96bfe9fed796f0364d5c257888bc234867996f64e528
|
3 |
+
size 2927
|