Upload 15 files
Browse files- added_tokens.json +5 -0
- all_results.json +22 -0
- config.json +75 -0
- eval_results.json +10 -0
- generated_predictions.txt +0 -0
- merges.txt +0 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +8 -0
- trainer_state.json +723 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<CTX>": 50266,
|
| 3 |
+
"<PS>": 50265,
|
| 4 |
+
"<SEP>": 50267
|
| 5 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_bleu": 1.736,
|
| 4 |
+
"eval_gen_len": 18.7597,
|
| 5 |
+
"eval_loss": 4.376501083374023,
|
| 6 |
+
"eval_runtime": 211.2917,
|
| 7 |
+
"eval_samples": 5651,
|
| 8 |
+
"eval_samples_per_second": 26.745,
|
| 9 |
+
"eval_steps_per_second": 1.339,
|
| 10 |
+
"predict_bleu": 1.8687,
|
| 11 |
+
"predict_gen_len": 19.1795,
|
| 12 |
+
"predict_loss": 4.367978572845459,
|
| 13 |
+
"predict_runtime": 206.3106,
|
| 14 |
+
"predict_samples": 5482,
|
| 15 |
+
"predict_samples_per_second": 26.572,
|
| 16 |
+
"predict_steps_per_second": 1.333,
|
| 17 |
+
"train_loss": 1.262480049472888,
|
| 18 |
+
"train_runtime": 34907.6333,
|
| 19 |
+
"train_samples": 27018,
|
| 20 |
+
"train_samples_per_second": 38.699,
|
| 21 |
+
"train_steps_per_second": 0.483
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.24.0",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50268
|
| 75 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_bleu": 1.736,
|
| 4 |
+
"eval_gen_len": 18.7597,
|
| 5 |
+
"eval_loss": 4.376501083374023,
|
| 6 |
+
"eval_runtime": 211.2917,
|
| 7 |
+
"eval_samples": 5651,
|
| 8 |
+
"eval_samples_per_second": 26.745,
|
| 9 |
+
"eval_steps_per_second": 1.339
|
| 10 |
+
}
|
generated_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
merges.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": 1.8687,
|
| 3 |
+
"predict_gen_len": 19.1795,
|
| 4 |
+
"predict_loss": 4.367978572845459,
|
| 5 |
+
"predict_runtime": 206.3106,
|
| 6 |
+
"predict_samples": 5482,
|
| 7 |
+
"predict_samples_per_second": 26.572,
|
| 8 |
+
"predict_steps_per_second": 1.333
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64b0ca21acb92f7e23d8577623ef77f2953bd6cf4a9ecc1bf959b39162bdbdd9
|
| 3 |
+
size 557980445
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 1024,
|
| 9 |
+
"name_or_path": "facebook/bart-base",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "BartTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 1.262480049472888,
|
| 4 |
+
"train_runtime": 34907.6333,
|
| 5 |
+
"train_samples": 27018,
|
| 6 |
+
"train_samples_per_second": 38.699,
|
| 7 |
+
"train_steps_per_second": 0.483
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,723 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.99777942264989,
|
| 5 |
+
"global_step": 16850,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_bleu": 1.7639,
|
| 13 |
+
"eval_gen_len": 17.0476,
|
| 14 |
+
"eval_loss": 2.9241816997528076,
|
| 15 |
+
"eval_runtime": 161.7821,
|
| 16 |
+
"eval_samples_per_second": 34.93,
|
| 17 |
+
"eval_steps_per_second": 1.749,
|
| 18 |
+
"step": 337
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.48,
|
| 22 |
+
"learning_rate": 4.851632047477745e-05,
|
| 23 |
+
"loss": 3.1098,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_bleu": 1.7951,
|
| 29 |
+
"eval_gen_len": 15.622,
|
| 30 |
+
"eval_loss": 2.894585609436035,
|
| 31 |
+
"eval_runtime": 158.8854,
|
| 32 |
+
"eval_samples_per_second": 35.567,
|
| 33 |
+
"eval_steps_per_second": 1.781,
|
| 34 |
+
"step": 674
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.97,
|
| 38 |
+
"learning_rate": 4.70326409495549e-05,
|
| 39 |
+
"loss": 2.8138,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.0,
|
| 44 |
+
"eval_bleu": 1.9954,
|
| 45 |
+
"eval_gen_len": 16.75,
|
| 46 |
+
"eval_loss": 2.8898093700408936,
|
| 47 |
+
"eval_runtime": 161.5184,
|
| 48 |
+
"eval_samples_per_second": 34.987,
|
| 49 |
+
"eval_steps_per_second": 1.752,
|
| 50 |
+
"step": 1011
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"eval_bleu": 1.9243,
|
| 55 |
+
"eval_gen_len": 16.4229,
|
| 56 |
+
"eval_loss": 2.903644323348999,
|
| 57 |
+
"eval_runtime": 160.1198,
|
| 58 |
+
"eval_samples_per_second": 35.292,
|
| 59 |
+
"eval_steps_per_second": 1.767,
|
| 60 |
+
"step": 1348
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.45,
|
| 64 |
+
"learning_rate": 4.554896142433235e-05,
|
| 65 |
+
"loss": 2.594,
|
| 66 |
+
"step": 1500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.0,
|
| 70 |
+
"eval_bleu": 1.9376,
|
| 71 |
+
"eval_gen_len": 16.8443,
|
| 72 |
+
"eval_loss": 2.9253323078155518,
|
| 73 |
+
"eval_runtime": 159.7166,
|
| 74 |
+
"eval_samples_per_second": 35.381,
|
| 75 |
+
"eval_steps_per_second": 1.772,
|
| 76 |
+
"step": 1685
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.93,
|
| 80 |
+
"learning_rate": 4.4065281899109794e-05,
|
| 81 |
+
"loss": 2.4374,
|
| 82 |
+
"step": 2000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 6.0,
|
| 86 |
+
"eval_bleu": 2.0055,
|
| 87 |
+
"eval_gen_len": 16.2769,
|
| 88 |
+
"eval_loss": 2.9406914710998535,
|
| 89 |
+
"eval_runtime": 159.0512,
|
| 90 |
+
"eval_samples_per_second": 35.529,
|
| 91 |
+
"eval_steps_per_second": 1.779,
|
| 92 |
+
"step": 2022
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"eval_bleu": 1.9174,
|
| 97 |
+
"eval_gen_len": 15.7742,
|
| 98 |
+
"eval_loss": 2.978670358657837,
|
| 99 |
+
"eval_runtime": 158.3136,
|
| 100 |
+
"eval_samples_per_second": 35.695,
|
| 101 |
+
"eval_steps_per_second": 1.788,
|
| 102 |
+
"step": 2359
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7.42,
|
| 106 |
+
"learning_rate": 4.258160237388724e-05,
|
| 107 |
+
"loss": 2.2623,
|
| 108 |
+
"step": 2500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 8.0,
|
| 112 |
+
"eval_bleu": 1.9378,
|
| 113 |
+
"eval_gen_len": 15.8482,
|
| 114 |
+
"eval_loss": 3.0429296493530273,
|
| 115 |
+
"eval_runtime": 157.9591,
|
| 116 |
+
"eval_samples_per_second": 35.775,
|
| 117 |
+
"eval_steps_per_second": 1.792,
|
| 118 |
+
"step": 2696
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 8.9,
|
| 122 |
+
"learning_rate": 4.109792284866469e-05,
|
| 123 |
+
"loss": 2.1323,
|
| 124 |
+
"step": 3000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 9.0,
|
| 128 |
+
"eval_bleu": 1.9663,
|
| 129 |
+
"eval_gen_len": 16.4675,
|
| 130 |
+
"eval_loss": 3.058178663253784,
|
| 131 |
+
"eval_runtime": 158.2119,
|
| 132 |
+
"eval_samples_per_second": 35.718,
|
| 133 |
+
"eval_steps_per_second": 1.789,
|
| 134 |
+
"step": 3033
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"eval_bleu": 1.9412,
|
| 139 |
+
"eval_gen_len": 16.0646,
|
| 140 |
+
"eval_loss": 3.107869863510132,
|
| 141 |
+
"eval_runtime": 157.8461,
|
| 142 |
+
"eval_samples_per_second": 35.801,
|
| 143 |
+
"eval_steps_per_second": 1.793,
|
| 144 |
+
"step": 3370
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 10.38,
|
| 148 |
+
"learning_rate": 3.961424332344214e-05,
|
| 149 |
+
"loss": 1.9817,
|
| 150 |
+
"step": 3500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 11.0,
|
| 154 |
+
"eval_bleu": 2.0972,
|
| 155 |
+
"eval_gen_len": 16.4849,
|
| 156 |
+
"eval_loss": 3.1683783531188965,
|
| 157 |
+
"eval_runtime": 158.1876,
|
| 158 |
+
"eval_samples_per_second": 35.723,
|
| 159 |
+
"eval_steps_per_second": 1.789,
|
| 160 |
+
"step": 3707
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 11.87,
|
| 164 |
+
"learning_rate": 3.8130563798219586e-05,
|
| 165 |
+
"loss": 1.864,
|
| 166 |
+
"step": 4000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 12.0,
|
| 170 |
+
"eval_bleu": 1.8631,
|
| 171 |
+
"eval_gen_len": 16.3084,
|
| 172 |
+
"eval_loss": 3.224560022354126,
|
| 173 |
+
"eval_runtime": 158.1833,
|
| 174 |
+
"eval_samples_per_second": 35.724,
|
| 175 |
+
"eval_steps_per_second": 1.789,
|
| 176 |
+
"step": 4044
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"eval_bleu": 1.9812,
|
| 181 |
+
"eval_gen_len": 16.2702,
|
| 182 |
+
"eval_loss": 3.256418228149414,
|
| 183 |
+
"eval_runtime": 157.9844,
|
| 184 |
+
"eval_samples_per_second": 35.769,
|
| 185 |
+
"eval_steps_per_second": 1.791,
|
| 186 |
+
"step": 4381
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 13.35,
|
| 190 |
+
"learning_rate": 3.664688427299703e-05,
|
| 191 |
+
"loss": 1.7319,
|
| 192 |
+
"step": 4500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 14.0,
|
| 196 |
+
"eval_bleu": 1.8518,
|
| 197 |
+
"eval_gen_len": 16.6208,
|
| 198 |
+
"eval_loss": 3.321943759918213,
|
| 199 |
+
"eval_runtime": 158.399,
|
| 200 |
+
"eval_samples_per_second": 35.676,
|
| 201 |
+
"eval_steps_per_second": 1.787,
|
| 202 |
+
"step": 4718
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 14.83,
|
| 206 |
+
"learning_rate": 3.516320474777448e-05,
|
| 207 |
+
"loss": 1.6291,
|
| 208 |
+
"step": 5000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 15.0,
|
| 212 |
+
"eval_bleu": 1.8638,
|
| 213 |
+
"eval_gen_len": 15.8876,
|
| 214 |
+
"eval_loss": 3.3599555492401123,
|
| 215 |
+
"eval_runtime": 157.6851,
|
| 216 |
+
"eval_samples_per_second": 35.837,
|
| 217 |
+
"eval_steps_per_second": 1.795,
|
| 218 |
+
"step": 5055
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.0,
|
| 222 |
+
"eval_bleu": 1.9703,
|
| 223 |
+
"eval_gen_len": 16.2079,
|
| 224 |
+
"eval_loss": 3.4334099292755127,
|
| 225 |
+
"eval_runtime": 157.9443,
|
| 226 |
+
"eval_samples_per_second": 35.778,
|
| 227 |
+
"eval_steps_per_second": 1.792,
|
| 228 |
+
"step": 5392
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 16.32,
|
| 232 |
+
"learning_rate": 3.3679525222551934e-05,
|
| 233 |
+
"loss": 1.5185,
|
| 234 |
+
"step": 5500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 17.0,
|
| 238 |
+
"eval_bleu": 1.67,
|
| 239 |
+
"eval_gen_len": 15.4355,
|
| 240 |
+
"eval_loss": 3.4718282222747803,
|
| 241 |
+
"eval_runtime": 157.5031,
|
| 242 |
+
"eval_samples_per_second": 35.879,
|
| 243 |
+
"eval_steps_per_second": 1.797,
|
| 244 |
+
"step": 5729
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 17.8,
|
| 248 |
+
"learning_rate": 3.219584569732938e-05,
|
| 249 |
+
"loss": 1.423,
|
| 250 |
+
"step": 6000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 18.0,
|
| 254 |
+
"eval_bleu": 1.834,
|
| 255 |
+
"eval_gen_len": 16.5098,
|
| 256 |
+
"eval_loss": 3.5062952041625977,
|
| 257 |
+
"eval_runtime": 158.3097,
|
| 258 |
+
"eval_samples_per_second": 35.696,
|
| 259 |
+
"eval_steps_per_second": 1.788,
|
| 260 |
+
"step": 6066
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"eval_bleu": 1.6657,
|
| 265 |
+
"eval_gen_len": 16.0078,
|
| 266 |
+
"eval_loss": 3.5681209564208984,
|
| 267 |
+
"eval_runtime": 157.9659,
|
| 268 |
+
"eval_samples_per_second": 35.774,
|
| 269 |
+
"eval_steps_per_second": 1.792,
|
| 270 |
+
"step": 6403
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 19.29,
|
| 274 |
+
"learning_rate": 3.071216617210683e-05,
|
| 275 |
+
"loss": 1.3274,
|
| 276 |
+
"step": 6500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 20.0,
|
| 280 |
+
"eval_bleu": 1.9141,
|
| 281 |
+
"eval_gen_len": 16.8841,
|
| 282 |
+
"eval_loss": 3.612222194671631,
|
| 283 |
+
"eval_runtime": 158.8209,
|
| 284 |
+
"eval_samples_per_second": 35.581,
|
| 285 |
+
"eval_steps_per_second": 1.782,
|
| 286 |
+
"step": 6740
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 20.77,
|
| 290 |
+
"learning_rate": 2.9228486646884274e-05,
|
| 291 |
+
"loss": 1.2461,
|
| 292 |
+
"step": 7000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 21.0,
|
| 296 |
+
"eval_bleu": 1.7505,
|
| 297 |
+
"eval_gen_len": 16.1793,
|
| 298 |
+
"eval_loss": 3.6515696048736572,
|
| 299 |
+
"eval_runtime": 158.234,
|
| 300 |
+
"eval_samples_per_second": 35.713,
|
| 301 |
+
"eval_steps_per_second": 1.788,
|
| 302 |
+
"step": 7077
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 22.0,
|
| 306 |
+
"eval_bleu": 1.6842,
|
| 307 |
+
"eval_gen_len": 16.2152,
|
| 308 |
+
"eval_loss": 3.6844277381896973,
|
| 309 |
+
"eval_runtime": 158.2358,
|
| 310 |
+
"eval_samples_per_second": 35.713,
|
| 311 |
+
"eval_steps_per_second": 1.788,
|
| 312 |
+
"step": 7414
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 22.25,
|
| 316 |
+
"learning_rate": 2.774480712166172e-05,
|
| 317 |
+
"loss": 1.1661,
|
| 318 |
+
"step": 7500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 23.0,
|
| 322 |
+
"eval_bleu": 1.6847,
|
| 323 |
+
"eval_gen_len": 16.0894,
|
| 324 |
+
"eval_loss": 3.7410662174224854,
|
| 325 |
+
"eval_runtime": 158.234,
|
| 326 |
+
"eval_samples_per_second": 35.713,
|
| 327 |
+
"eval_steps_per_second": 1.788,
|
| 328 |
+
"step": 7751
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 23.74,
|
| 332 |
+
"learning_rate": 2.6261127596439174e-05,
|
| 333 |
+
"loss": 1.092,
|
| 334 |
+
"step": 8000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 24.0,
|
| 338 |
+
"eval_bleu": 1.6662,
|
| 339 |
+
"eval_gen_len": 16.6121,
|
| 340 |
+
"eval_loss": 3.7708585262298584,
|
| 341 |
+
"eval_runtime": 158.583,
|
| 342 |
+
"eval_samples_per_second": 35.634,
|
| 343 |
+
"eval_steps_per_second": 1.785,
|
| 344 |
+
"step": 8088
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 25.0,
|
| 348 |
+
"eval_bleu": 1.7985,
|
| 349 |
+
"eval_gen_len": 16.3143,
|
| 350 |
+
"eval_loss": 3.8098456859588623,
|
| 351 |
+
"eval_runtime": 158.302,
|
| 352 |
+
"eval_samples_per_second": 35.698,
|
| 353 |
+
"eval_steps_per_second": 1.788,
|
| 354 |
+
"step": 8425
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 25.22,
|
| 358 |
+
"learning_rate": 2.4777448071216618e-05,
|
| 359 |
+
"loss": 1.0302,
|
| 360 |
+
"step": 8500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 26.0,
|
| 364 |
+
"eval_bleu": 1.7239,
|
| 365 |
+
"eval_gen_len": 16.3467,
|
| 366 |
+
"eval_loss": 3.866185426712036,
|
| 367 |
+
"eval_runtime": 158.3049,
|
| 368 |
+
"eval_samples_per_second": 35.697,
|
| 369 |
+
"eval_steps_per_second": 1.788,
|
| 370 |
+
"step": 8762
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 26.7,
|
| 374 |
+
"learning_rate": 2.3293768545994066e-05,
|
| 375 |
+
"loss": 0.9626,
|
| 376 |
+
"step": 9000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 27.0,
|
| 380 |
+
"eval_bleu": 1.7687,
|
| 381 |
+
"eval_gen_len": 16.8252,
|
| 382 |
+
"eval_loss": 3.9026572704315186,
|
| 383 |
+
"eval_runtime": 158.776,
|
| 384 |
+
"eval_samples_per_second": 35.591,
|
| 385 |
+
"eval_steps_per_second": 1.782,
|
| 386 |
+
"step": 9099
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 28.0,
|
| 390 |
+
"eval_bleu": 1.6071,
|
| 391 |
+
"eval_gen_len": 16.8395,
|
| 392 |
+
"eval_loss": 3.9381048679351807,
|
| 393 |
+
"eval_runtime": 158.8794,
|
| 394 |
+
"eval_samples_per_second": 35.568,
|
| 395 |
+
"eval_steps_per_second": 1.781,
|
| 396 |
+
"step": 9436
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 28.19,
|
| 400 |
+
"learning_rate": 2.1810089020771514e-05,
|
| 401 |
+
"loss": 0.9076,
|
| 402 |
+
"step": 9500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 29.0,
|
| 406 |
+
"eval_bleu": 1.7271,
|
| 407 |
+
"eval_gen_len": 16.5845,
|
| 408 |
+
"eval_loss": 3.9773497581481934,
|
| 409 |
+
"eval_runtime": 158.5329,
|
| 410 |
+
"eval_samples_per_second": 35.646,
|
| 411 |
+
"eval_steps_per_second": 1.785,
|
| 412 |
+
"step": 9773
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 29.67,
|
| 416 |
+
"learning_rate": 2.0326409495548962e-05,
|
| 417 |
+
"loss": 0.8523,
|
| 418 |
+
"step": 10000
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 30.0,
|
| 422 |
+
"eval_bleu": 1.6689,
|
| 423 |
+
"eval_gen_len": 16.5388,
|
| 424 |
+
"eval_loss": 3.987967014312744,
|
| 425 |
+
"eval_runtime": 158.4608,
|
| 426 |
+
"eval_samples_per_second": 35.662,
|
| 427 |
+
"eval_steps_per_second": 1.786,
|
| 428 |
+
"step": 10110
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 31.0,
|
| 432 |
+
"eval_bleu": 1.6433,
|
| 433 |
+
"eval_gen_len": 16.6489,
|
| 434 |
+
"eval_loss": 4.056297302246094,
|
| 435 |
+
"eval_runtime": 158.7288,
|
| 436 |
+
"eval_samples_per_second": 35.602,
|
| 437 |
+
"eval_steps_per_second": 1.783,
|
| 438 |
+
"step": 10447
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 31.16,
|
| 442 |
+
"learning_rate": 1.884272997032641e-05,
|
| 443 |
+
"loss": 0.8051,
|
| 444 |
+
"step": 10500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 32.0,
|
| 448 |
+
"eval_bleu": 1.6298,
|
| 449 |
+
"eval_gen_len": 16.6305,
|
| 450 |
+
"eval_loss": 4.071838855743408,
|
| 451 |
+
"eval_runtime": 158.6637,
|
| 452 |
+
"eval_samples_per_second": 35.616,
|
| 453 |
+
"eval_steps_per_second": 1.784,
|
| 454 |
+
"step": 10784
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 32.64,
|
| 458 |
+
"learning_rate": 1.7359050445103858e-05,
|
| 459 |
+
"loss": 0.7621,
|
| 460 |
+
"step": 11000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 33.0,
|
| 464 |
+
"eval_bleu": 1.5555,
|
| 465 |
+
"eval_gen_len": 16.7367,
|
| 466 |
+
"eval_loss": 4.104060649871826,
|
| 467 |
+
"eval_runtime": 158.7329,
|
| 468 |
+
"eval_samples_per_second": 35.601,
|
| 469 |
+
"eval_steps_per_second": 1.783,
|
| 470 |
+
"step": 11121
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 34.0,
|
| 474 |
+
"eval_bleu": 1.5922,
|
| 475 |
+
"eval_gen_len": 17.4091,
|
| 476 |
+
"eval_loss": 4.128782272338867,
|
| 477 |
+
"eval_runtime": 159.2897,
|
| 478 |
+
"eval_samples_per_second": 35.476,
|
| 479 |
+
"eval_steps_per_second": 1.777,
|
| 480 |
+
"step": 11458
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 34.12,
|
| 484 |
+
"learning_rate": 1.5875370919881306e-05,
|
| 485 |
+
"loss": 0.7257,
|
| 486 |
+
"step": 11500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 35.0,
|
| 490 |
+
"eval_bleu": 1.6243,
|
| 491 |
+
"eval_gen_len": 16.8432,
|
| 492 |
+
"eval_loss": 4.1702704429626465,
|
| 493 |
+
"eval_runtime": 158.8223,
|
| 494 |
+
"eval_samples_per_second": 35.581,
|
| 495 |
+
"eval_steps_per_second": 1.782,
|
| 496 |
+
"step": 11795
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 35.61,
|
| 500 |
+
"learning_rate": 1.4391691394658754e-05,
|
| 501 |
+
"loss": 0.6835,
|
| 502 |
+
"step": 12000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 36.0,
|
| 506 |
+
"eval_bleu": 1.589,
|
| 507 |
+
"eval_gen_len": 17.0446,
|
| 508 |
+
"eval_loss": 4.1908135414123535,
|
| 509 |
+
"eval_runtime": 159.0745,
|
| 510 |
+
"eval_samples_per_second": 35.524,
|
| 511 |
+
"eval_steps_per_second": 1.779,
|
| 512 |
+
"step": 12132
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 37.0,
|
| 516 |
+
"eval_bleu": 1.5549,
|
| 517 |
+
"eval_gen_len": 17.0649,
|
| 518 |
+
"eval_loss": 4.204710006713867,
|
| 519 |
+
"eval_runtime": 159.0216,
|
| 520 |
+
"eval_samples_per_second": 35.536,
|
| 521 |
+
"eval_steps_per_second": 1.78,
|
| 522 |
+
"step": 12469
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 37.09,
|
| 526 |
+
"learning_rate": 1.29080118694362e-05,
|
| 527 |
+
"loss": 0.6586,
|
| 528 |
+
"step": 12500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 38.0,
|
| 532 |
+
"eval_bleu": 1.5035,
|
| 533 |
+
"eval_gen_len": 16.8954,
|
| 534 |
+
"eval_loss": 4.236845970153809,
|
| 535 |
+
"eval_runtime": 158.8765,
|
| 536 |
+
"eval_samples_per_second": 35.569,
|
| 537 |
+
"eval_steps_per_second": 1.781,
|
| 538 |
+
"step": 12806
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 38.57,
|
| 542 |
+
"learning_rate": 1.142433234421365e-05,
|
| 543 |
+
"loss": 0.6247,
|
| 544 |
+
"step": 13000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 39.0,
|
| 548 |
+
"eval_bleu": 1.5845,
|
| 549 |
+
"eval_gen_len": 16.7616,
|
| 550 |
+
"eval_loss": 4.257309436798096,
|
| 551 |
+
"eval_runtime": 158.8065,
|
| 552 |
+
"eval_samples_per_second": 35.584,
|
| 553 |
+
"eval_steps_per_second": 1.782,
|
| 554 |
+
"step": 13143
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 40.0,
|
| 558 |
+
"eval_bleu": 1.5144,
|
| 559 |
+
"eval_gen_len": 16.803,
|
| 560 |
+
"eval_loss": 4.269469738006592,
|
| 561 |
+
"eval_runtime": 158.8495,
|
| 562 |
+
"eval_samples_per_second": 35.575,
|
| 563 |
+
"eval_steps_per_second": 1.782,
|
| 564 |
+
"step": 13480
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 40.06,
|
| 568 |
+
"learning_rate": 9.940652818991098e-06,
|
| 569 |
+
"loss": 0.604,
|
| 570 |
+
"step": 13500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 41.0,
|
| 574 |
+
"eval_bleu": 1.5398,
|
| 575 |
+
"eval_gen_len": 17.1295,
|
| 576 |
+
"eval_loss": 4.295245170593262,
|
| 577 |
+
"eval_runtime": 159.0688,
|
| 578 |
+
"eval_samples_per_second": 35.526,
|
| 579 |
+
"eval_steps_per_second": 1.779,
|
| 580 |
+
"step": 13817
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 41.54,
|
| 584 |
+
"learning_rate": 8.456973293768548e-06,
|
| 585 |
+
"loss": 0.5781,
|
| 586 |
+
"step": 14000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 42.0,
|
| 590 |
+
"eval_bleu": 1.6057,
|
| 591 |
+
"eval_gen_len": 17.0359,
|
| 592 |
+
"eval_loss": 4.318183422088623,
|
| 593 |
+
"eval_runtime": 158.942,
|
| 594 |
+
"eval_samples_per_second": 35.554,
|
| 595 |
+
"eval_steps_per_second": 1.781,
|
| 596 |
+
"step": 14154
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 43.0,
|
| 600 |
+
"eval_bleu": 1.5114,
|
| 601 |
+
"eval_gen_len": 16.6418,
|
| 602 |
+
"eval_loss": 4.331396102905273,
|
| 603 |
+
"eval_runtime": 158.745,
|
| 604 |
+
"eval_samples_per_second": 35.598,
|
| 605 |
+
"eval_steps_per_second": 1.783,
|
| 606 |
+
"step": 14491
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 43.03,
|
| 610 |
+
"learning_rate": 6.973293768545995e-06,
|
| 611 |
+
"loss": 0.5636,
|
| 612 |
+
"step": 14500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 44.0,
|
| 616 |
+
"eval_bleu": 1.5443,
|
| 617 |
+
"eval_gen_len": 16.745,
|
| 618 |
+
"eval_loss": 4.341202259063721,
|
| 619 |
+
"eval_runtime": 158.7765,
|
| 620 |
+
"eval_samples_per_second": 35.591,
|
| 621 |
+
"eval_steps_per_second": 1.782,
|
| 622 |
+
"step": 14828
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 44.51,
|
| 626 |
+
"learning_rate": 5.489614243323442e-06,
|
| 627 |
+
"loss": 0.5429,
|
| 628 |
+
"step": 15000
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 45.0,
|
| 632 |
+
"eval_bleu": 1.5719,
|
| 633 |
+
"eval_gen_len": 16.8237,
|
| 634 |
+
"eval_loss": 4.341938495635986,
|
| 635 |
+
"eval_runtime": 158.7306,
|
| 636 |
+
"eval_samples_per_second": 35.601,
|
| 637 |
+
"eval_steps_per_second": 1.783,
|
| 638 |
+
"step": 15165
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 45.99,
|
| 642 |
+
"learning_rate": 4.005934718100891e-06,
|
| 643 |
+
"loss": 0.5309,
|
| 644 |
+
"step": 15500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 46.0,
|
| 648 |
+
"eval_bleu": 1.5445,
|
| 649 |
+
"eval_gen_len": 16.7997,
|
| 650 |
+
"eval_loss": 4.355504512786865,
|
| 651 |
+
"eval_runtime": 158.7779,
|
| 652 |
+
"eval_samples_per_second": 35.591,
|
| 653 |
+
"eval_steps_per_second": 1.782,
|
| 654 |
+
"step": 15502
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 47.0,
|
| 658 |
+
"eval_bleu": 1.5689,
|
| 659 |
+
"eval_gen_len": 16.8358,
|
| 660 |
+
"eval_loss": 4.362900733947754,
|
| 661 |
+
"eval_runtime": 158.7996,
|
| 662 |
+
"eval_samples_per_second": 35.586,
|
| 663 |
+
"eval_steps_per_second": 1.782,
|
| 664 |
+
"step": 15839
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 47.48,
|
| 668 |
+
"learning_rate": 2.5222551928783385e-06,
|
| 669 |
+
"loss": 0.5206,
|
| 670 |
+
"step": 16000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 48.0,
|
| 674 |
+
"eval_bleu": 1.5208,
|
| 675 |
+
"eval_gen_len": 17.0039,
|
| 676 |
+
"eval_loss": 4.370855808258057,
|
| 677 |
+
"eval_runtime": 158.9053,
|
| 678 |
+
"eval_samples_per_second": 35.562,
|
| 679 |
+
"eval_steps_per_second": 1.781,
|
| 680 |
+
"step": 16176
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 48.96,
|
| 684 |
+
"learning_rate": 1.0385756676557863e-06,
|
| 685 |
+
"loss": 0.51,
|
| 686 |
+
"step": 16500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 49.0,
|
| 690 |
+
"eval_bleu": 1.5581,
|
| 691 |
+
"eval_gen_len": 16.8577,
|
| 692 |
+
"eval_loss": 4.374205589294434,
|
| 693 |
+
"eval_runtime": 158.7365,
|
| 694 |
+
"eval_samples_per_second": 35.6,
|
| 695 |
+
"eval_steps_per_second": 1.783,
|
| 696 |
+
"step": 16513
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 50.0,
|
| 700 |
+
"eval_bleu": 1.5873,
|
| 701 |
+
"eval_gen_len": 16.9289,
|
| 702 |
+
"eval_loss": 4.376501083374023,
|
| 703 |
+
"eval_runtime": 158.7713,
|
| 704 |
+
"eval_samples_per_second": 35.592,
|
| 705 |
+
"eval_steps_per_second": 1.782,
|
| 706 |
+
"step": 16850
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 50.0,
|
| 710 |
+
"step": 16850,
|
| 711 |
+
"total_flos": 1.8872801391015936e+17,
|
| 712 |
+
"train_loss": 1.262480049472888,
|
| 713 |
+
"train_runtime": 34907.6333,
|
| 714 |
+
"train_samples_per_second": 38.699,
|
| 715 |
+
"train_steps_per_second": 0.483
|
| 716 |
+
}
|
| 717 |
+
],
|
| 718 |
+
"max_steps": 16850,
|
| 719 |
+
"num_train_epochs": 50,
|
| 720 |
+
"total_flos": 1.8872801391015936e+17,
|
| 721 |
+
"trial_name": null,
|
| 722 |
+
"trial_params": null
|
| 723 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6afd61829a6a83d3a7d180ca7912bd8902399c40311f69beaba6c0a20773c30f
|
| 3 |
+
size 3515
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|