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 +391 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"predict_bleu": 29.8521,
|
| 4 |
+
"predict_gen_len": 32.7951,
|
| 5 |
+
"predict_loss": 2.050637722015381,
|
| 6 |
+
"predict_runtime": 531.0496,
|
| 7 |
+
"predict_samples": 1835,
|
| 8 |
+
"predict_samples_per_second": 3.455,
|
| 9 |
+
"predict_steps_per_second": 0.346,
|
| 10 |
+
"train_loss": 0.8284636896126608,
|
| 11 |
+
"train_runtime": 8795.6186,
|
| 12 |
+
"train_samples": 30782,
|
| 13 |
+
"train_samples_per_second": 34.997,
|
| 14 |
+
"train_steps_per_second": 3.501
|
| 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": 29.8521,
|
| 3 |
+
"predict_gen_len": 32.7951,
|
| 4 |
+
"predict_loss": 2.050637722015381,
|
| 5 |
+
"predict_runtime": 531.0496,
|
| 6 |
+
"predict_samples": 1835,
|
| 7 |
+
"predict_samples_per_second": 3.455,
|
| 8 |
+
"predict_steps_per_second": 0.346
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2f8321adf42035ba8ef914beb2d354d319ca19e15151e77737b4745eea1bdf6
|
| 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": 10.0,
|
| 3 |
+
"train_loss": 0.8284636896126608,
|
| 4 |
+
"train_runtime": 8795.6186,
|
| 5 |
+
"train_samples": 30782,
|
| 6 |
+
"train_samples_per_second": 34.997,
|
| 7 |
+
"train_steps_per_second": 3.501
|
| 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": 2.252,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.32,
|
| 18 |
+
"learning_rate": 4.8376096135108804e-05,
|
| 19 |
+
"loss": 2.1774,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.49,
|
| 24 |
+
"learning_rate": 4.7564144202663205e-05,
|
| 25 |
+
"loss": 2.0499,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.65,
|
| 30 |
+
"learning_rate": 4.6752192270217606e-05,
|
| 31 |
+
"loss": 2.0078,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.81,
|
| 36 |
+
"learning_rate": 4.5940240337772006e-05,
|
| 37 |
+
"loss": 1.9559,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.97,
|
| 42 |
+
"learning_rate": 4.512828840532641e-05,
|
| 43 |
+
"loss": 1.9273,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.14,
|
| 48 |
+
"learning_rate": 4.431633647288081e-05,
|
| 49 |
+
"loss": 1.5932,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.3,
|
| 54 |
+
"learning_rate": 4.350438454043521e-05,
|
| 55 |
+
"loss": 1.5537,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.46,
|
| 60 |
+
"learning_rate": 4.269243260798961e-05,
|
| 61 |
+
"loss": 1.5351,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.62,
|
| 66 |
+
"learning_rate": 4.188048067554401e-05,
|
| 67 |
+
"loss": 1.5671,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.79,
|
| 72 |
+
"learning_rate": 4.106852874309841e-05,
|
| 73 |
+
"loss": 1.5523,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.95,
|
| 78 |
+
"learning_rate": 4.025657681065281e-05,
|
| 79 |
+
"loss": 1.5408,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.11,
|
| 84 |
+
"learning_rate": 3.944462487820721e-05,
|
| 85 |
+
"loss": 1.3004,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.27,
|
| 90 |
+
"learning_rate": 3.8632672945761614e-05,
|
| 91 |
+
"loss": 1.2221,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.44,
|
| 96 |
+
"learning_rate": 3.7820721013316015e-05,
|
| 97 |
+
"loss": 1.2221,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.6,
|
| 102 |
+
"learning_rate": 3.7008769080870415e-05,
|
| 103 |
+
"loss": 1.234,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.76,
|
| 108 |
+
"learning_rate": 3.6196817148424816e-05,
|
| 109 |
+
"loss": 1.239,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.92,
|
| 114 |
+
"learning_rate": 3.538486521597922e-05,
|
| 115 |
+
"loss": 1.2449,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.09,
|
| 120 |
+
"learning_rate": 3.457291328353362e-05,
|
| 121 |
+
"loss": 1.087,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.25,
|
| 126 |
+
"learning_rate": 3.376096135108802e-05,
|
| 127 |
+
"loss": 0.9434,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.41,
|
| 132 |
+
"learning_rate": 3.294900941864242e-05,
|
| 133 |
+
"loss": 0.9697,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.57,
|
| 138 |
+
"learning_rate": 3.213705748619682e-05,
|
| 139 |
+
"loss": 0.951,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.73,
|
| 144 |
+
"learning_rate": 3.132510555375122e-05,
|
| 145 |
+
"loss": 0.9865,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.9,
|
| 150 |
+
"learning_rate": 3.051315362130562e-05,
|
| 151 |
+
"loss": 0.9658,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.06,
|
| 156 |
+
"learning_rate": 2.970120168886002e-05,
|
| 157 |
+
"loss": 0.8827,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.22,
|
| 162 |
+
"learning_rate": 2.888924975641442e-05,
|
| 163 |
+
"loss": 0.7373,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.38,
|
| 168 |
+
"learning_rate": 2.8077297823968824e-05,
|
| 169 |
+
"loss": 0.7343,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.55,
|
| 174 |
+
"learning_rate": 2.7265345891523225e-05,
|
| 175 |
+
"loss": 0.7554,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.71,
|
| 180 |
+
"learning_rate": 2.6453393959077623e-05,
|
| 181 |
+
"loss": 0.7597,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.87,
|
| 186 |
+
"learning_rate": 2.5641442026632023e-05,
|
| 187 |
+
"loss": 0.7742,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.03,
|
| 192 |
+
"learning_rate": 2.4829490094186424e-05,
|
| 193 |
+
"loss": 0.7066,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.2,
|
| 198 |
+
"learning_rate": 2.401753816174083e-05,
|
| 199 |
+
"loss": 0.5598,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 5.36,
|
| 204 |
+
"learning_rate": 2.3205586229295226e-05,
|
| 205 |
+
"loss": 0.5663,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 5.52,
|
| 210 |
+
"learning_rate": 2.2393634296849627e-05,
|
| 211 |
+
"loss": 0.5669,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 5.68,
|
| 216 |
+
"learning_rate": 2.158168236440403e-05,
|
| 217 |
+
"loss": 0.5647,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 5.85,
|
| 222 |
+
"learning_rate": 2.0769730431958428e-05,
|
| 223 |
+
"loss": 0.5689,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.01,
|
| 228 |
+
"learning_rate": 1.995777849951283e-05,
|
| 229 |
+
"loss": 0.5698,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 6.17,
|
| 234 |
+
"learning_rate": 1.914582656706723e-05,
|
| 235 |
+
"loss": 0.4044,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 6.33,
|
| 240 |
+
"learning_rate": 1.833387463462163e-05,
|
| 241 |
+
"loss": 0.4177,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 6.5,
|
| 246 |
+
"learning_rate": 1.752192270217603e-05,
|
| 247 |
+
"loss": 0.4278,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 6.66,
|
| 252 |
+
"learning_rate": 1.6709970769730432e-05,
|
| 253 |
+
"loss": 0.437,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.82,
|
| 258 |
+
"learning_rate": 1.5898018837284833e-05,
|
| 259 |
+
"loss": 0.4246,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.98,
|
| 264 |
+
"learning_rate": 1.5086066904839236e-05,
|
| 265 |
+
"loss": 0.427,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 7.15,
|
| 270 |
+
"learning_rate": 1.4274114972393635e-05,
|
| 271 |
+
"loss": 0.3301,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 7.31,
|
| 276 |
+
"learning_rate": 1.3462163039948036e-05,
|
| 277 |
+
"loss": 0.3066,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 7.47,
|
| 282 |
+
"learning_rate": 1.2650211107502435e-05,
|
| 283 |
+
"loss": 0.3174,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 7.63,
|
| 288 |
+
"learning_rate": 1.1838259175056837e-05,
|
| 289 |
+
"loss": 0.315,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 7.79,
|
| 294 |
+
"learning_rate": 1.1026307242611238e-05,
|
| 295 |
+
"loss": 0.3176,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 7.96,
|
| 300 |
+
"learning_rate": 1.0214355310165639e-05,
|
| 301 |
+
"loss": 0.3184,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 8.12,
|
| 306 |
+
"learning_rate": 9.40240337772004e-06,
|
| 307 |
+
"loss": 0.2636,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.28,
|
| 312 |
+
"learning_rate": 8.59045144527444e-06,
|
| 313 |
+
"loss": 0.2332,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 8.44,
|
| 318 |
+
"learning_rate": 7.778499512828841e-06,
|
| 319 |
+
"loss": 0.2402,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 8.61,
|
| 324 |
+
"learning_rate": 6.966547580383241e-06,
|
| 325 |
+
"loss": 0.2431,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 8.77,
|
| 330 |
+
"learning_rate": 6.154595647937642e-06,
|
| 331 |
+
"loss": 0.2429,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 8.93,
|
| 336 |
+
"learning_rate": 5.342643715492044e-06,
|
| 337 |
+
"loss": 0.2397,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 9.09,
|
| 342 |
+
"learning_rate": 4.530691783046444e-06,
|
| 343 |
+
"loss": 0.2138,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 9.26,
|
| 348 |
+
"learning_rate": 3.718739850600845e-06,
|
| 349 |
+
"loss": 0.2009,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 9.42,
|
| 354 |
+
"learning_rate": 2.9067879181552453e-06,
|
| 355 |
+
"loss": 0.1979,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 9.58,
|
| 360 |
+
"learning_rate": 2.094835985709646e-06,
|
| 361 |
+
"loss": 0.1927,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 9.74,
|
| 366 |
+
"learning_rate": 1.2828840532640467e-06,
|
| 367 |
+
"loss": 0.1859,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 9.91,
|
| 372 |
+
"learning_rate": 4.7093212081844755e-07,
|
| 373 |
+
"loss": 0.1849,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 10.0,
|
| 378 |
+
"step": 30790,
|
| 379 |
+
"total_flos": 5.041211966452531e+16,
|
| 380 |
+
"train_loss": 0.8284636896126608,
|
| 381 |
+
"train_runtime": 8795.6186,
|
| 382 |
+
"train_samples_per_second": 34.997,
|
| 383 |
+
"train_steps_per_second": 3.501
|
| 384 |
+
}
|
| 385 |
+
],
|
| 386 |
+
"max_steps": 30790,
|
| 387 |
+
"num_train_epochs": 10,
|
| 388 |
+
"total_flos": 5.041211966452531e+16,
|
| 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 sha256:30d6704d4a58a08cb262a82030dfaf174e38443de03f2dd4eb66e41ab1b8c22d
|
| 3 |
+
size 2799
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|