add MT model
Browse files- all_results.json +15 -0
- config.json +38 -0
- generated_predictions.txt +0 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +841 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"predict_bleu": 43.3806,
|
4 |
+
"predict_gen_len": 23.3453,
|
5 |
+
"predict_loss": 0.9619347453117371,
|
6 |
+
"predict_runtime": 316.4208,
|
7 |
+
"predict_samples": 1500,
|
8 |
+
"predict_samples_per_second": 4.741,
|
9 |
+
"predict_steps_per_second": 0.474,
|
10 |
+
"train_loss": 1.233144689885432,
|
11 |
+
"train_runtime": 17748.5921,
|
12 |
+
"train_samples": 228257,
|
13 |
+
"train_samples_per_second": 38.582,
|
14 |
+
"train_steps_per_second": 3.858
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/m2m100_418M",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"M2M100ForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"d_model": 1024,
|
11 |
+
"decoder_attention_heads": 16,
|
12 |
+
"decoder_ffn_dim": 4096,
|
13 |
+
"decoder_layerdrop": 0.05,
|
14 |
+
"decoder_layers": 12,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"early_stopping": true,
|
18 |
+
"encoder_attention_heads": 16,
|
19 |
+
"encoder_ffn_dim": 4096,
|
20 |
+
"encoder_layerdrop": 0.05,
|
21 |
+
"encoder_layers": 12,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"forced_bos_token_id": 128022,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"init_std": 0.02,
|
26 |
+
"is_encoder_decoder": true,
|
27 |
+
"max_length": 200,
|
28 |
+
"max_position_embeddings": 1024,
|
29 |
+
"model_type": "m2m_100",
|
30 |
+
"num_beams": 5,
|
31 |
+
"num_hidden_layers": 12,
|
32 |
+
"pad_token_id": 1,
|
33 |
+
"scale_embedding": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.10.3",
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 128112
|
38 |
+
}
|
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": 43.3806,
|
3 |
+
"predict_gen_len": 23.3453,
|
4 |
+
"predict_loss": 0.9619347453117371,
|
5 |
+
"predict_runtime": 316.4208,
|
6 |
+
"predict_samples": 1500,
|
7 |
+
"predict_samples_per_second": 4.741,
|
8 |
+
"predict_steps_per_second": 0.474
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f56b5d8c929acc9f37a0b25b78e6e3dbeeec8e05af549bb955340dc65ddadaf
|
3 |
+
size 1935792071
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
|
3 |
+
size 2423393
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"src_lang": null, "tgt_lang": null, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "facebook/m2m100_418M", "model_max_length": 1024, "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"], "tokenizer_class": "M2M100Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 1.233144689885432,
|
4 |
+
"train_runtime": 17748.5921,
|
5 |
+
"train_samples": 228257,
|
6 |
+
"train_samples_per_second": 38.582,
|
7 |
+
"train_steps_per_second": 3.858
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,841 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 68478,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.02,
|
12 |
+
"learning_rate": 4.963491924413681e-05,
|
13 |
+
"loss": 2.5929,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 4.9269838488273604e-05,
|
19 |
+
"loss": 2.2003,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.07,
|
24 |
+
"learning_rate": 4.890475773241041e-05,
|
25 |
+
"loss": 2.0692,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.09,
|
30 |
+
"learning_rate": 4.853967697654722e-05,
|
31 |
+
"loss": 1.9485,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.11,
|
36 |
+
"learning_rate": 4.817459622068401e-05,
|
37 |
+
"loss": 1.9084,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.13,
|
42 |
+
"learning_rate": 4.780951546482082e-05,
|
43 |
+
"loss": 1.8495,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.15,
|
48 |
+
"learning_rate": 4.744443470895763e-05,
|
49 |
+
"loss": 1.8025,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.18,
|
54 |
+
"learning_rate": 4.707935395309443e-05,
|
55 |
+
"loss": 1.7957,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.2,
|
60 |
+
"learning_rate": 4.671427319723123e-05,
|
61 |
+
"loss": 1.7414,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.22,
|
66 |
+
"learning_rate": 4.634919244136804e-05,
|
67 |
+
"loss": 1.7284,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.24,
|
72 |
+
"learning_rate": 4.598411168550484e-05,
|
73 |
+
"loss": 1.7033,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.26,
|
78 |
+
"learning_rate": 4.561903092964164e-05,
|
79 |
+
"loss": 1.705,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.28,
|
84 |
+
"learning_rate": 4.525395017377844e-05,
|
85 |
+
"loss": 1.667,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.31,
|
90 |
+
"learning_rate": 4.4888869417915246e-05,
|
91 |
+
"loss": 1.6606,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.33,
|
96 |
+
"learning_rate": 4.452378866205205e-05,
|
97 |
+
"loss": 1.6179,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.35,
|
102 |
+
"learning_rate": 4.415870790618885e-05,
|
103 |
+
"loss": 1.5977,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.37,
|
108 |
+
"learning_rate": 4.3793627150325655e-05,
|
109 |
+
"loss": 1.5827,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.39,
|
114 |
+
"learning_rate": 4.3428546394462456e-05,
|
115 |
+
"loss": 1.5621,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.42,
|
120 |
+
"learning_rate": 4.306346563859926e-05,
|
121 |
+
"loss": 1.5675,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.44,
|
126 |
+
"learning_rate": 4.2698384882736064e-05,
|
127 |
+
"loss": 1.5729,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.46,
|
132 |
+
"learning_rate": 4.2333304126872865e-05,
|
133 |
+
"loss": 1.546,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.48,
|
138 |
+
"learning_rate": 4.1968223371009666e-05,
|
139 |
+
"loss": 1.5546,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.5,
|
144 |
+
"learning_rate": 4.160314261514647e-05,
|
145 |
+
"loss": 1.5163,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.53,
|
150 |
+
"learning_rate": 4.123806185928328e-05,
|
151 |
+
"loss": 1.5097,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.55,
|
156 |
+
"learning_rate": 4.0872981103420075e-05,
|
157 |
+
"loss": 1.5074,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.57,
|
162 |
+
"learning_rate": 4.050790034755688e-05,
|
163 |
+
"loss": 1.4856,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.59,
|
168 |
+
"learning_rate": 4.014281959169369e-05,
|
169 |
+
"loss": 1.5068,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.61,
|
174 |
+
"learning_rate": 3.9777738835830483e-05,
|
175 |
+
"loss": 1.5035,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.64,
|
180 |
+
"learning_rate": 3.941265807996729e-05,
|
181 |
+
"loss": 1.4676,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.66,
|
186 |
+
"learning_rate": 3.90475773241041e-05,
|
187 |
+
"loss": 1.4623,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.68,
|
192 |
+
"learning_rate": 3.868249656824089e-05,
|
193 |
+
"loss": 1.4472,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.7,
|
198 |
+
"learning_rate": 3.83174158123777e-05,
|
199 |
+
"loss": 1.447,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.72,
|
204 |
+
"learning_rate": 3.795233505651451e-05,
|
205 |
+
"loss": 1.4557,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.74,
|
210 |
+
"learning_rate": 3.75872543006513e-05,
|
211 |
+
"loss": 1.4439,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.77,
|
216 |
+
"learning_rate": 3.722217354478811e-05,
|
217 |
+
"loss": 1.4332,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.79,
|
222 |
+
"learning_rate": 3.685709278892491e-05,
|
223 |
+
"loss": 1.4365,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.81,
|
228 |
+
"learning_rate": 3.649201203306172e-05,
|
229 |
+
"loss": 1.4098,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.83,
|
234 |
+
"learning_rate": 3.612693127719852e-05,
|
235 |
+
"loss": 1.4125,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.85,
|
240 |
+
"learning_rate": 3.576185052133532e-05,
|
241 |
+
"loss": 1.4088,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.88,
|
246 |
+
"learning_rate": 3.5396769765472126e-05,
|
247 |
+
"loss": 1.3968,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.9,
|
252 |
+
"learning_rate": 3.503168900960893e-05,
|
253 |
+
"loss": 1.4125,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.92,
|
258 |
+
"learning_rate": 3.466660825374573e-05,
|
259 |
+
"loss": 1.385,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.94,
|
264 |
+
"learning_rate": 3.4301527497882535e-05,
|
265 |
+
"loss": 1.3985,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.96,
|
270 |
+
"learning_rate": 3.3936446742019336e-05,
|
271 |
+
"loss": 1.3747,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.99,
|
276 |
+
"learning_rate": 3.3571365986156136e-05,
|
277 |
+
"loss": 1.3743,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.01,
|
282 |
+
"learning_rate": 3.3206285230292944e-05,
|
283 |
+
"loss": 1.3065,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.03,
|
288 |
+
"learning_rate": 3.2841204474429745e-05,
|
289 |
+
"loss": 1.1883,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.05,
|
294 |
+
"learning_rate": 3.2476123718566545e-05,
|
295 |
+
"loss": 1.2017,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.07,
|
300 |
+
"learning_rate": 3.211104296270335e-05,
|
301 |
+
"loss": 1.1919,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.1,
|
306 |
+
"learning_rate": 3.1745962206840153e-05,
|
307 |
+
"loss": 1.1873,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.12,
|
312 |
+
"learning_rate": 3.1380881450976954e-05,
|
313 |
+
"loss": 1.2045,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.14,
|
318 |
+
"learning_rate": 3.101580069511376e-05,
|
319 |
+
"loss": 1.1915,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.16,
|
324 |
+
"learning_rate": 3.065071993925057e-05,
|
325 |
+
"loss": 1.1932,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.18,
|
330 |
+
"learning_rate": 3.0285639183387367e-05,
|
331 |
+
"loss": 1.1793,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.2,
|
336 |
+
"learning_rate": 2.992055842752417e-05,
|
337 |
+
"loss": 1.2086,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.23,
|
342 |
+
"learning_rate": 2.9555477671660975e-05,
|
343 |
+
"loss": 1.2023,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.25,
|
348 |
+
"learning_rate": 2.9190396915797775e-05,
|
349 |
+
"loss": 1.1953,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.27,
|
354 |
+
"learning_rate": 2.882531615993458e-05,
|
355 |
+
"loss": 1.2049,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.29,
|
360 |
+
"learning_rate": 2.8460235404071384e-05,
|
361 |
+
"loss": 1.1931,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.31,
|
366 |
+
"learning_rate": 2.8095154648208184e-05,
|
367 |
+
"loss": 1.197,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.34,
|
372 |
+
"learning_rate": 2.773007389234499e-05,
|
373 |
+
"loss": 1.1704,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.36,
|
378 |
+
"learning_rate": 2.7364993136481793e-05,
|
379 |
+
"loss": 1.1548,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.38,
|
384 |
+
"learning_rate": 2.6999912380618593e-05,
|
385 |
+
"loss": 1.187,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 1.4,
|
390 |
+
"learning_rate": 2.6634831624755397e-05,
|
391 |
+
"loss": 1.1769,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.42,
|
396 |
+
"learning_rate": 2.62697508688922e-05,
|
397 |
+
"loss": 1.181,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.45,
|
402 |
+
"learning_rate": 2.5904670113029006e-05,
|
403 |
+
"loss": 1.1564,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.47,
|
408 |
+
"learning_rate": 2.5539589357165806e-05,
|
409 |
+
"loss": 1.1742,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.49,
|
414 |
+
"learning_rate": 2.517450860130261e-05,
|
415 |
+
"loss": 1.1651,
|
416 |
+
"step": 34000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.51,
|
420 |
+
"learning_rate": 2.480942784543941e-05,
|
421 |
+
"loss": 1.1637,
|
422 |
+
"step": 34500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.53,
|
426 |
+
"learning_rate": 2.4444347089576215e-05,
|
427 |
+
"loss": 1.1531,
|
428 |
+
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.56,
|
432 |
+
"learning_rate": 2.407926633371302e-05,
|
433 |
+
"loss": 1.1703,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.58,
|
438 |
+
"learning_rate": 2.371418557784982e-05,
|
439 |
+
"loss": 1.1482,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.6,
|
444 |
+
"learning_rate": 2.3349104821986624e-05,
|
445 |
+
"loss": 1.1501,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.62,
|
450 |
+
"learning_rate": 2.2984024066123428e-05,
|
451 |
+
"loss": 1.1525,
|
452 |
+
"step": 37000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.64,
|
456 |
+
"learning_rate": 2.261894331026023e-05,
|
457 |
+
"loss": 1.1576,
|
458 |
+
"step": 37500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.66,
|
462 |
+
"learning_rate": 2.2253862554397033e-05,
|
463 |
+
"loss": 1.1518,
|
464 |
+
"step": 38000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.69,
|
468 |
+
"learning_rate": 2.1888781798533837e-05,
|
469 |
+
"loss": 1.1594,
|
470 |
+
"step": 38500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.71,
|
474 |
+
"learning_rate": 2.152370104267064e-05,
|
475 |
+
"loss": 1.1614,
|
476 |
+
"step": 39000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.73,
|
480 |
+
"learning_rate": 2.1158620286807442e-05,
|
481 |
+
"loss": 1.185,
|
482 |
+
"step": 39500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.75,
|
486 |
+
"learning_rate": 2.0793539530944246e-05,
|
487 |
+
"loss": 1.1399,
|
488 |
+
"step": 40000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 1.77,
|
492 |
+
"learning_rate": 2.042845877508105e-05,
|
493 |
+
"loss": 1.1262,
|
494 |
+
"step": 40500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.8,
|
498 |
+
"learning_rate": 2.006337801921785e-05,
|
499 |
+
"loss": 1.1458,
|
500 |
+
"step": 41000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.82,
|
504 |
+
"learning_rate": 1.9698297263354655e-05,
|
505 |
+
"loss": 1.1379,
|
506 |
+
"step": 41500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.84,
|
510 |
+
"learning_rate": 1.933321650749146e-05,
|
511 |
+
"loss": 1.1437,
|
512 |
+
"step": 42000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 1.86,
|
516 |
+
"learning_rate": 1.896813575162826e-05,
|
517 |
+
"loss": 1.1161,
|
518 |
+
"step": 42500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 1.88,
|
522 |
+
"learning_rate": 1.8603054995765064e-05,
|
523 |
+
"loss": 1.1205,
|
524 |
+
"step": 43000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 1.91,
|
528 |
+
"learning_rate": 1.8237974239901868e-05,
|
529 |
+
"loss": 1.1422,
|
530 |
+
"step": 43500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 1.93,
|
534 |
+
"learning_rate": 1.787289348403867e-05,
|
535 |
+
"loss": 1.1265,
|
536 |
+
"step": 44000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 1.95,
|
540 |
+
"learning_rate": 1.7507812728175473e-05,
|
541 |
+
"loss": 1.0999,
|
542 |
+
"step": 44500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.97,
|
546 |
+
"learning_rate": 1.7142731972312277e-05,
|
547 |
+
"loss": 1.11,
|
548 |
+
"step": 45000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 1.99,
|
552 |
+
"learning_rate": 1.677765121644908e-05,
|
553 |
+
"loss": 1.1267,
|
554 |
+
"step": 45500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 2.02,
|
558 |
+
"learning_rate": 1.6412570460585882e-05,
|
559 |
+
"loss": 1.0115,
|
560 |
+
"step": 46000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 2.04,
|
564 |
+
"learning_rate": 1.6047489704722686e-05,
|
565 |
+
"loss": 0.9535,
|
566 |
+
"step": 46500
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 2.06,
|
570 |
+
"learning_rate": 1.568240894885949e-05,
|
571 |
+
"loss": 0.9458,
|
572 |
+
"step": 47000
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 2.08,
|
576 |
+
"learning_rate": 1.531732819299629e-05,
|
577 |
+
"loss": 0.9517,
|
578 |
+
"step": 47500
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 2.1,
|
582 |
+
"learning_rate": 1.4952247437133093e-05,
|
583 |
+
"loss": 0.9496,
|
584 |
+
"step": 48000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 2.12,
|
588 |
+
"learning_rate": 1.4587166681269897e-05,
|
589 |
+
"loss": 0.9649,
|
590 |
+
"step": 48500
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 2.15,
|
594 |
+
"learning_rate": 1.42220859254067e-05,
|
595 |
+
"loss": 0.934,
|
596 |
+
"step": 49000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 2.17,
|
600 |
+
"learning_rate": 1.3857005169543506e-05,
|
601 |
+
"loss": 0.9757,
|
602 |
+
"step": 49500
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 2.19,
|
606 |
+
"learning_rate": 1.3491924413680306e-05,
|
607 |
+
"loss": 0.9349,
|
608 |
+
"step": 50000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 2.21,
|
612 |
+
"learning_rate": 1.3126843657817109e-05,
|
613 |
+
"loss": 0.9548,
|
614 |
+
"step": 50500
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 2.23,
|
618 |
+
"learning_rate": 1.2761762901953914e-05,
|
619 |
+
"loss": 0.9426,
|
620 |
+
"step": 51000
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.26,
|
624 |
+
"learning_rate": 1.2396682146090715e-05,
|
625 |
+
"loss": 0.9543,
|
626 |
+
"step": 51500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 2.28,
|
630 |
+
"learning_rate": 1.203160139022752e-05,
|
631 |
+
"loss": 0.9438,
|
632 |
+
"step": 52000
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.3,
|
636 |
+
"learning_rate": 1.1666520634364322e-05,
|
637 |
+
"loss": 0.963,
|
638 |
+
"step": 52500
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 2.32,
|
642 |
+
"learning_rate": 1.1301439878501124e-05,
|
643 |
+
"loss": 0.9334,
|
644 |
+
"step": 53000
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 2.34,
|
648 |
+
"learning_rate": 1.0936359122637928e-05,
|
649 |
+
"loss": 0.9526,
|
650 |
+
"step": 53500
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 2.37,
|
654 |
+
"learning_rate": 1.057127836677473e-05,
|
655 |
+
"loss": 0.9397,
|
656 |
+
"step": 54000
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 2.39,
|
660 |
+
"learning_rate": 1.0206197610911535e-05,
|
661 |
+
"loss": 0.9569,
|
662 |
+
"step": 54500
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.41,
|
666 |
+
"learning_rate": 9.841116855048337e-06,
|
667 |
+
"loss": 0.94,
|
668 |
+
"step": 55000
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 2.43,
|
672 |
+
"learning_rate": 9.47603609918514e-06,
|
673 |
+
"loss": 0.9345,
|
674 |
+
"step": 55500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 2.45,
|
678 |
+
"learning_rate": 9.110955343321944e-06,
|
679 |
+
"loss": 0.933,
|
680 |
+
"step": 56000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 2.48,
|
684 |
+
"learning_rate": 8.745874587458746e-06,
|
685 |
+
"loss": 0.9289,
|
686 |
+
"step": 56500
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 2.5,
|
690 |
+
"learning_rate": 8.380793831595548e-06,
|
691 |
+
"loss": 0.9581,
|
692 |
+
"step": 57000
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 2.52,
|
696 |
+
"learning_rate": 8.015713075732353e-06,
|
697 |
+
"loss": 0.9203,
|
698 |
+
"step": 57500
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 2.54,
|
702 |
+
"learning_rate": 7.650632319869155e-06,
|
703 |
+
"loss": 0.9539,
|
704 |
+
"step": 58000
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.56,
|
708 |
+
"learning_rate": 7.285551564005959e-06,
|
709 |
+
"loss": 0.9482,
|
710 |
+
"step": 58500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 2.58,
|
714 |
+
"learning_rate": 6.920470808142762e-06,
|
715 |
+
"loss": 0.9206,
|
716 |
+
"step": 59000
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 2.61,
|
720 |
+
"learning_rate": 6.555390052279564e-06,
|
721 |
+
"loss": 0.9186,
|
722 |
+
"step": 59500
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 2.63,
|
726 |
+
"learning_rate": 6.190309296416367e-06,
|
727 |
+
"loss": 0.9168,
|
728 |
+
"step": 60000
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 2.65,
|
732 |
+
"learning_rate": 5.825228540553171e-06,
|
733 |
+
"loss": 0.9151,
|
734 |
+
"step": 60500
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 2.67,
|
738 |
+
"learning_rate": 5.460147784689974e-06,
|
739 |
+
"loss": 0.924,
|
740 |
+
"step": 61000
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 2.69,
|
744 |
+
"learning_rate": 5.095067028826777e-06,
|
745 |
+
"loss": 0.916,
|
746 |
+
"step": 61500
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.72,
|
750 |
+
"learning_rate": 4.729986272963579e-06,
|
751 |
+
"loss": 0.9311,
|
752 |
+
"step": 62000
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 2.74,
|
756 |
+
"learning_rate": 4.364905517100383e-06,
|
757 |
+
"loss": 0.9175,
|
758 |
+
"step": 62500
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 2.76,
|
762 |
+
"learning_rate": 3.999824761237186e-06,
|
763 |
+
"loss": 0.9121,
|
764 |
+
"step": 63000
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 2.78,
|
768 |
+
"learning_rate": 3.634744005373989e-06,
|
769 |
+
"loss": 0.9226,
|
770 |
+
"step": 63500
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 2.8,
|
774 |
+
"learning_rate": 3.269663249510792e-06,
|
775 |
+
"loss": 0.9335,
|
776 |
+
"step": 64000
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 2.83,
|
780 |
+
"learning_rate": 2.9045824936475953e-06,
|
781 |
+
"loss": 0.9104,
|
782 |
+
"step": 64500
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 2.85,
|
786 |
+
"learning_rate": 2.539501737784398e-06,
|
787 |
+
"loss": 0.9197,
|
788 |
+
"step": 65000
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.87,
|
792 |
+
"learning_rate": 2.1744209819212013e-06,
|
793 |
+
"loss": 0.8976,
|
794 |
+
"step": 65500
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 2.89,
|
798 |
+
"learning_rate": 1.8093402260580042e-06,
|
799 |
+
"loss": 0.9401,
|
800 |
+
"step": 66000
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 2.91,
|
804 |
+
"learning_rate": 1.444259470194807e-06,
|
805 |
+
"loss": 0.9265,
|
806 |
+
"step": 66500
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 2.94,
|
810 |
+
"learning_rate": 1.07917871433161e-06,
|
811 |
+
"loss": 0.9255,
|
812 |
+
"step": 67000
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 2.96,
|
816 |
+
"learning_rate": 7.140979584684132e-07,
|
817 |
+
"loss": 0.9099,
|
818 |
+
"step": 67500
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 2.98,
|
822 |
+
"learning_rate": 3.490172026052163e-07,
|
823 |
+
"loss": 0.9033,
|
824 |
+
"step": 68000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 3.0,
|
828 |
+
"step": 68478,
|
829 |
+
"total_flos": 9.218136679415808e+16,
|
830 |
+
"train_loss": 1.233144689885432,
|
831 |
+
"train_runtime": 17748.5921,
|
832 |
+
"train_samples_per_second": 38.582,
|
833 |
+
"train_steps_per_second": 3.858
|
834 |
+
}
|
835 |
+
],
|
836 |
+
"max_steps": 68478,
|
837 |
+
"num_train_epochs": 3,
|
838 |
+
"total_flos": 9.218136679415808e+16,
|
839 |
+
"trial_name": null,
|
840 |
+
"trial_params": null
|
841 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c3fde6d683b6b44c9e7e43eeb27b84de422a6a879f6ab8055c4d42de0d70c03
|
3 |
+
size 2735
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|