Upload folder using huggingface_hub
Browse files- added_tokens.json +0 -0
- config.json +75 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- trainer_state.json +1654 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "voidful/bart-base-unit",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"NARBartForConditionalGeneration"
|
| 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": "4.29.2",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 59481
|
| 75 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.29.2"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2846825dba3601966d5d9fb65c669eff1bb7f6e9505aaff2df67532c0c226351
|
| 3 |
+
size 1172138949
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f9bad05ad040924c041c89a611965fe7b71ab75bd5790e0514bdd055757d95f
|
| 3 |
+
size 586319645
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8732ebd9aef331b32f81fcae8b60856cb3fa51300f3d5f0f6207cd82e89f8f59
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c22b0efa74c0ea51aaa81ff9bd71f93186397aedae6997f714a3b7d4d34c55d
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed0ab915bd8123c15c508d4856a51a3f4b99525ea13637609ab1679599e2298f
|
| 3 |
+
size 627
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 1024,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "BartTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1654 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9568377501956837,
|
| 5 |
+
"global_step": 105000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 5.73025856044724e-06,
|
| 13 |
+
"loss": 11.2906,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 1.1553692056836711e-05,
|
| 19 |
+
"loss": 7.0039,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.03,
|
| 24 |
+
"learning_rate": 1.7377125553226185e-05,
|
| 25 |
+
"loss": 6.1153,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.04,
|
| 30 |
+
"learning_rate": 2.3200559049615657e-05,
|
| 31 |
+
"loss": 5.7832,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.05,
|
| 36 |
+
"learning_rate": 2.9023992546005126e-05,
|
| 37 |
+
"loss": 5.6146,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05,
|
| 42 |
+
"eval_loss": 5.421965599060059,
|
| 43 |
+
"eval_runtime": 411.32,
|
| 44 |
+
"eval_samples_per_second": 41.389,
|
| 45 |
+
"eval_steps_per_second": 5.174,
|
| 46 |
+
"eval_wer": 0.9239681855833133,
|
| 47 |
+
"step": 2500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.06,
|
| 51 |
+
"learning_rate": 3.48474260423946e-05,
|
| 52 |
+
"loss": 5.5165,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.07,
|
| 57 |
+
"learning_rate": 4.067085953878407e-05,
|
| 58 |
+
"loss": 5.446,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07,
|
| 63 |
+
"learning_rate": 4.649429303517354e-05,
|
| 64 |
+
"loss": 5.3865,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.08,
|
| 69 |
+
"learning_rate": 5.2317726531563014e-05,
|
| 70 |
+
"loss": 5.3516,
|
| 71 |
+
"step": 4500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.09,
|
| 75 |
+
"learning_rate": 5.814116002795248e-05,
|
| 76 |
+
"loss": 5.3348,
|
| 77 |
+
"step": 5000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.09,
|
| 81 |
+
"eval_loss": 5.211235046386719,
|
| 82 |
+
"eval_runtime": 409.8837,
|
| 83 |
+
"eval_samples_per_second": 41.534,
|
| 84 |
+
"eval_steps_per_second": 5.192,
|
| 85 |
+
"eval_wer": 0.9147464109993301,
|
| 86 |
+
"step": 5000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1,
|
| 90 |
+
"learning_rate": 6.396459352434195e-05,
|
| 91 |
+
"loss": 5.2944,
|
| 92 |
+
"step": 5500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.11,
|
| 96 |
+
"learning_rate": 6.978802702073143e-05,
|
| 97 |
+
"loss": 5.2642,
|
| 98 |
+
"step": 6000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.12,
|
| 102 |
+
"learning_rate": 7.56114605171209e-05,
|
| 103 |
+
"loss": 5.2581,
|
| 104 |
+
"step": 6500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.13,
|
| 108 |
+
"learning_rate": 8.143489401351036e-05,
|
| 109 |
+
"loss": 5.2314,
|
| 110 |
+
"step": 7000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.14,
|
| 114 |
+
"learning_rate": 8.725832750989984e-05,
|
| 115 |
+
"loss": 5.2119,
|
| 116 |
+
"step": 7500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.14,
|
| 120 |
+
"eval_loss": 5.13909912109375,
|
| 121 |
+
"eval_runtime": 409.6938,
|
| 122 |
+
"eval_samples_per_second": 41.553,
|
| 123 |
+
"eval_steps_per_second": 5.194,
|
| 124 |
+
"eval_wer": 0.9114111424157333,
|
| 125 |
+
"step": 7500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.15,
|
| 129 |
+
"learning_rate": 9.308176100628931e-05,
|
| 130 |
+
"loss": 5.1866,
|
| 131 |
+
"step": 8000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.16,
|
| 135 |
+
"learning_rate": 9.890519450267879e-05,
|
| 136 |
+
"loss": 5.1807,
|
| 137 |
+
"step": 8500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.17,
|
| 141 |
+
"learning_rate": 9.958877747391876e-05,
|
| 142 |
+
"loss": 5.1441,
|
| 143 |
+
"step": 9000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.18,
|
| 147 |
+
"learning_rate": 9.908234579155272e-05,
|
| 148 |
+
"loss": 5.1273,
|
| 149 |
+
"step": 9500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.19,
|
| 153 |
+
"learning_rate": 9.857591410918667e-05,
|
| 154 |
+
"loss": 5.1076,
|
| 155 |
+
"step": 10000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.19,
|
| 159 |
+
"eval_loss": 5.045482158660889,
|
| 160 |
+
"eval_runtime": 412.0168,
|
| 161 |
+
"eval_samples_per_second": 41.319,
|
| 162 |
+
"eval_steps_per_second": 5.165,
|
| 163 |
+
"eval_wer": 0.9043837403957815,
|
| 164 |
+
"step": 10000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2,
|
| 168 |
+
"learning_rate": 9.806948242682062e-05,
|
| 169 |
+
"loss": 5.0971,
|
| 170 |
+
"step": 10500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.21,
|
| 174 |
+
"learning_rate": 9.756305074445458e-05,
|
| 175 |
+
"loss": 5.0834,
|
| 176 |
+
"step": 11000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.21,
|
| 180 |
+
"learning_rate": 9.705661906208853e-05,
|
| 181 |
+
"loss": 5.0678,
|
| 182 |
+
"step": 11500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.22,
|
| 186 |
+
"learning_rate": 9.655018737972249e-05,
|
| 187 |
+
"loss": 5.0522,
|
| 188 |
+
"step": 12000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.23,
|
| 192 |
+
"learning_rate": 9.604375569735643e-05,
|
| 193 |
+
"loss": 5.0557,
|
| 194 |
+
"step": 12500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.23,
|
| 198 |
+
"eval_loss": 4.983465671539307,
|
| 199 |
+
"eval_runtime": 410.6819,
|
| 200 |
+
"eval_samples_per_second": 41.453,
|
| 201 |
+
"eval_steps_per_second": 5.182,
|
| 202 |
+
"eval_wer": 0.8979804271846081,
|
| 203 |
+
"step": 12500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.24,
|
| 207 |
+
"learning_rate": 9.553732401499038e-05,
|
| 208 |
+
"loss": 5.0332,
|
| 209 |
+
"step": 13000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.25,
|
| 213 |
+
"learning_rate": 9.503089233262434e-05,
|
| 214 |
+
"loss": 5.0225,
|
| 215 |
+
"step": 13500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.26,
|
| 219 |
+
"learning_rate": 9.452446065025829e-05,
|
| 220 |
+
"loss": 5.0201,
|
| 221 |
+
"step": 14000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.27,
|
| 225 |
+
"learning_rate": 9.401802896789223e-05,
|
| 226 |
+
"loss": 5.0077,
|
| 227 |
+
"step": 14500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.28,
|
| 231 |
+
"learning_rate": 9.35115972855262e-05,
|
| 232 |
+
"loss": 4.9969,
|
| 233 |
+
"step": 15000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.28,
|
| 237 |
+
"eval_loss": 4.943966388702393,
|
| 238 |
+
"eval_runtime": 411.257,
|
| 239 |
+
"eval_samples_per_second": 41.395,
|
| 240 |
+
"eval_steps_per_second": 5.174,
|
| 241 |
+
"eval_wer": 0.896159514799699,
|
| 242 |
+
"step": 15000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.29,
|
| 246 |
+
"learning_rate": 9.300516560316014e-05,
|
| 247 |
+
"loss": 4.9911,
|
| 248 |
+
"step": 15500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3,
|
| 252 |
+
"learning_rate": 9.249873392079409e-05,
|
| 253 |
+
"loss": 4.9935,
|
| 254 |
+
"step": 16000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.31,
|
| 258 |
+
"learning_rate": 9.199230223842805e-05,
|
| 259 |
+
"loss": 4.9755,
|
| 260 |
+
"step": 16500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.32,
|
| 264 |
+
"learning_rate": 9.1485870556062e-05,
|
| 265 |
+
"loss": 4.9771,
|
| 266 |
+
"step": 17000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.33,
|
| 270 |
+
"learning_rate": 9.097943887369594e-05,
|
| 271 |
+
"loss": 4.9577,
|
| 272 |
+
"step": 17500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.33,
|
| 276 |
+
"eval_loss": 4.906991481781006,
|
| 277 |
+
"eval_runtime": 410.7324,
|
| 278 |
+
"eval_samples_per_second": 41.448,
|
| 279 |
+
"eval_steps_per_second": 5.181,
|
| 280 |
+
"eval_wer": 0.8942902538261701,
|
| 281 |
+
"step": 17500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.34,
|
| 285 |
+
"learning_rate": 9.04730071913299e-05,
|
| 286 |
+
"loss": 4.953,
|
| 287 |
+
"step": 18000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.34,
|
| 291 |
+
"learning_rate": 8.996657550896385e-05,
|
| 292 |
+
"loss": 4.9515,
|
| 293 |
+
"step": 18500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.35,
|
| 297 |
+
"learning_rate": 8.94601438265978e-05,
|
| 298 |
+
"loss": 4.9314,
|
| 299 |
+
"step": 19000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.36,
|
| 303 |
+
"learning_rate": 8.895371214423176e-05,
|
| 304 |
+
"loss": 4.9529,
|
| 305 |
+
"step": 19500
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.37,
|
| 309 |
+
"learning_rate": 8.84472804618657e-05,
|
| 310 |
+
"loss": 4.9298,
|
| 311 |
+
"step": 20000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.37,
|
| 315 |
+
"eval_loss": 4.876424312591553,
|
| 316 |
+
"eval_runtime": 410.0694,
|
| 317 |
+
"eval_samples_per_second": 41.515,
|
| 318 |
+
"eval_steps_per_second": 5.189,
|
| 319 |
+
"eval_wer": 0.8924795338464294,
|
| 320 |
+
"step": 20000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.38,
|
| 324 |
+
"learning_rate": 8.794084877949965e-05,
|
| 325 |
+
"loss": 4.9117,
|
| 326 |
+
"step": 20500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.39,
|
| 330 |
+
"learning_rate": 8.743542996049834e-05,
|
| 331 |
+
"loss": 4.9273,
|
| 332 |
+
"step": 21000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4,
|
| 336 |
+
"learning_rate": 8.693001114149701e-05,
|
| 337 |
+
"loss": 4.9357,
|
| 338 |
+
"step": 21500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.41,
|
| 342 |
+
"learning_rate": 8.642357945913097e-05,
|
| 343 |
+
"loss": 4.9211,
|
| 344 |
+
"step": 22000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.42,
|
| 348 |
+
"learning_rate": 8.591714777676492e-05,
|
| 349 |
+
"loss": 4.9096,
|
| 350 |
+
"step": 22500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.42,
|
| 354 |
+
"eval_loss": 4.8509111404418945,
|
| 355 |
+
"eval_runtime": 411.3063,
|
| 356 |
+
"eval_samples_per_second": 41.39,
|
| 357 |
+
"eval_steps_per_second": 5.174,
|
| 358 |
+
"eval_wer": 0.8897156933115739,
|
| 359 |
+
"step": 22500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.43,
|
| 363 |
+
"learning_rate": 8.541071609439886e-05,
|
| 364 |
+
"loss": 4.9029,
|
| 365 |
+
"step": 23000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.44,
|
| 369 |
+
"learning_rate": 8.490428441203282e-05,
|
| 370 |
+
"loss": 4.9012,
|
| 371 |
+
"step": 23500
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.45,
|
| 375 |
+
"learning_rate": 8.439785272966677e-05,
|
| 376 |
+
"loss": 4.8984,
|
| 377 |
+
"step": 24000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.46,
|
| 381 |
+
"learning_rate": 8.389142104730072e-05,
|
| 382 |
+
"loss": 4.8971,
|
| 383 |
+
"step": 24500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.47,
|
| 387 |
+
"learning_rate": 8.338498936493468e-05,
|
| 388 |
+
"loss": 4.896,
|
| 389 |
+
"step": 25000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.47,
|
| 393 |
+
"eval_loss": 4.833607196807861,
|
| 394 |
+
"eval_runtime": 411.6309,
|
| 395 |
+
"eval_samples_per_second": 41.357,
|
| 396 |
+
"eval_steps_per_second": 5.17,
|
| 397 |
+
"eval_wer": 0.8886487575654107,
|
| 398 |
+
"step": 25000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.48,
|
| 402 |
+
"learning_rate": 8.287855768256862e-05,
|
| 403 |
+
"loss": 4.8776,
|
| 404 |
+
"step": 25500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.48,
|
| 408 |
+
"learning_rate": 8.237415172693204e-05,
|
| 409 |
+
"loss": 4.8729,
|
| 410 |
+
"step": 26000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.49,
|
| 414 |
+
"learning_rate": 8.186772004456598e-05,
|
| 415 |
+
"loss": 4.8781,
|
| 416 |
+
"step": 26500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5,
|
| 420 |
+
"learning_rate": 8.136128836219995e-05,
|
| 421 |
+
"loss": 4.8726,
|
| 422 |
+
"step": 27000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.51,
|
| 426 |
+
"learning_rate": 8.085485667983389e-05,
|
| 427 |
+
"loss": 4.8724,
|
| 428 |
+
"step": 27500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.51,
|
| 432 |
+
"eval_loss": 4.81581449508667,
|
| 433 |
+
"eval_runtime": 411.4914,
|
| 434 |
+
"eval_samples_per_second": 41.371,
|
| 435 |
+
"eval_steps_per_second": 5.171,
|
| 436 |
+
"eval_wer": 0.8873070188952817,
|
| 437 |
+
"step": 27500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.52,
|
| 441 |
+
"learning_rate": 8.034943786083258e-05,
|
| 442 |
+
"loss": 4.8579,
|
| 443 |
+
"step": 28000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.53,
|
| 447 |
+
"learning_rate": 7.984300617846653e-05,
|
| 448 |
+
"loss": 4.8618,
|
| 449 |
+
"step": 28500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.54,
|
| 453 |
+
"learning_rate": 7.933657449610049e-05,
|
| 454 |
+
"loss": 4.8674,
|
| 455 |
+
"step": 29000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.55,
|
| 459 |
+
"learning_rate": 7.883014281373443e-05,
|
| 460 |
+
"loss": 4.8535,
|
| 461 |
+
"step": 29500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.56,
|
| 465 |
+
"learning_rate": 7.832573685809785e-05,
|
| 466 |
+
"loss": 4.8488,
|
| 467 |
+
"step": 30000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.56,
|
| 471 |
+
"eval_loss": 4.8011603355407715,
|
| 472 |
+
"eval_runtime": 410.5634,
|
| 473 |
+
"eval_samples_per_second": 41.465,
|
| 474 |
+
"eval_steps_per_second": 5.183,
|
| 475 |
+
"eval_wer": 0.8869696241498325,
|
| 476 |
+
"step": 30000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.57,
|
| 480 |
+
"learning_rate": 7.78193051757318e-05,
|
| 481 |
+
"loss": 4.8533,
|
| 482 |
+
"step": 30500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.58,
|
| 486 |
+
"learning_rate": 7.731287349336574e-05,
|
| 487 |
+
"loss": 4.8563,
|
| 488 |
+
"step": 31000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.59,
|
| 492 |
+
"learning_rate": 7.68064418109997e-05,
|
| 493 |
+
"loss": 4.852,
|
| 494 |
+
"step": 31500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.6,
|
| 498 |
+
"learning_rate": 7.630001012863365e-05,
|
| 499 |
+
"loss": 4.8502,
|
| 500 |
+
"step": 32000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.61,
|
| 504 |
+
"learning_rate": 7.57935784462676e-05,
|
| 505 |
+
"loss": 4.829,
|
| 506 |
+
"step": 32500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.61,
|
| 510 |
+
"eval_loss": 4.784905910491943,
|
| 511 |
+
"eval_runtime": 412.2149,
|
| 512 |
+
"eval_samples_per_second": 41.299,
|
| 513 |
+
"eval_steps_per_second": 5.162,
|
| 514 |
+
"eval_wer": 0.8847121370768731,
|
| 515 |
+
"step": 32500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.62,
|
| 519 |
+
"learning_rate": 7.528714676390155e-05,
|
| 520 |
+
"loss": 4.8315,
|
| 521 |
+
"step": 33000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.62,
|
| 525 |
+
"learning_rate": 7.478172794490024e-05,
|
| 526 |
+
"loss": 4.8269,
|
| 527 |
+
"step": 33500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.63,
|
| 531 |
+
"learning_rate": 7.427529626253419e-05,
|
| 532 |
+
"loss": 4.823,
|
| 533 |
+
"step": 34000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.64,
|
| 537 |
+
"learning_rate": 7.376886458016814e-05,
|
| 538 |
+
"loss": 4.8282,
|
| 539 |
+
"step": 34500
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.65,
|
| 543 |
+
"learning_rate": 7.32624328978021e-05,
|
| 544 |
+
"loss": 4.8415,
|
| 545 |
+
"step": 35000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.65,
|
| 549 |
+
"eval_loss": 4.774867057800293,
|
| 550 |
+
"eval_runtime": 411.0732,
|
| 551 |
+
"eval_samples_per_second": 41.414,
|
| 552 |
+
"eval_steps_per_second": 5.177,
|
| 553 |
+
"eval_wer": 0.8846529427237791,
|
| 554 |
+
"step": 35000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.66,
|
| 558 |
+
"learning_rate": 7.275600121543604e-05,
|
| 559 |
+
"loss": 4.827,
|
| 560 |
+
"step": 35500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.67,
|
| 564 |
+
"learning_rate": 7.225058239643473e-05,
|
| 565 |
+
"loss": 4.8117,
|
| 566 |
+
"step": 36000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.68,
|
| 570 |
+
"learning_rate": 7.174415071406868e-05,
|
| 571 |
+
"loss": 4.8178,
|
| 572 |
+
"step": 36500
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.69,
|
| 576 |
+
"learning_rate": 7.123771903170264e-05,
|
| 577 |
+
"loss": 4.8036,
|
| 578 |
+
"step": 37000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.7,
|
| 582 |
+
"learning_rate": 7.073128734933657e-05,
|
| 583 |
+
"loss": 4.7941,
|
| 584 |
+
"step": 37500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7,
|
| 588 |
+
"eval_loss": 4.765619277954102,
|
| 589 |
+
"eval_runtime": 410.9966,
|
| 590 |
+
"eval_samples_per_second": 41.421,
|
| 591 |
+
"eval_steps_per_second": 5.178,
|
| 592 |
+
"eval_wer": 0.8833543257678246,
|
| 593 |
+
"step": 37500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.71,
|
| 597 |
+
"learning_rate": 7.022586853033526e-05,
|
| 598 |
+
"loss": 4.8074,
|
| 599 |
+
"step": 38000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.72,
|
| 603 |
+
"learning_rate": 6.971943684796922e-05,
|
| 604 |
+
"loss": 4.8097,
|
| 605 |
+
"step": 38500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.73,
|
| 609 |
+
"learning_rate": 6.921401802896789e-05,
|
| 610 |
+
"loss": 4.8156,
|
| 611 |
+
"step": 39000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.74,
|
| 615 |
+
"learning_rate": 6.870758634660185e-05,
|
| 616 |
+
"loss": 4.7991,
|
| 617 |
+
"step": 39500
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.75,
|
| 621 |
+
"learning_rate": 6.82011546642358e-05,
|
| 622 |
+
"loss": 4.7913,
|
| 623 |
+
"step": 40000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.75,
|
| 627 |
+
"eval_loss": 4.773669719696045,
|
| 628 |
+
"eval_runtime": 410.7775,
|
| 629 |
+
"eval_samples_per_second": 41.443,
|
| 630 |
+
"eval_steps_per_second": 5.18,
|
| 631 |
+
"eval_wer": 0.8835782973378091,
|
| 632 |
+
"step": 40000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.75,
|
| 636 |
+
"learning_rate": 6.769472298186974e-05,
|
| 637 |
+
"loss": 4.7988,
|
| 638 |
+
"step": 40500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.76,
|
| 642 |
+
"learning_rate": 6.71882912995037e-05,
|
| 643 |
+
"loss": 4.7993,
|
| 644 |
+
"step": 41000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.77,
|
| 648 |
+
"learning_rate": 6.668185961713765e-05,
|
| 649 |
+
"loss": 4.8082,
|
| 650 |
+
"step": 41500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.78,
|
| 654 |
+
"learning_rate": 6.617542793477161e-05,
|
| 655 |
+
"loss": 4.797,
|
| 656 |
+
"step": 42000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.79,
|
| 660 |
+
"learning_rate": 6.566899625240556e-05,
|
| 661 |
+
"loss": 4.7943,
|
| 662 |
+
"step": 42500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.79,
|
| 666 |
+
"eval_loss": 4.763143539428711,
|
| 667 |
+
"eval_runtime": 411.3255,
|
| 668 |
+
"eval_samples_per_second": 41.388,
|
| 669 |
+
"eval_steps_per_second": 5.174,
|
| 670 |
+
"eval_wer": 0.8824108749304336,
|
| 671 |
+
"step": 42500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.8,
|
| 675 |
+
"learning_rate": 6.51625645700395e-05,
|
| 676 |
+
"loss": 4.7916,
|
| 677 |
+
"step": 43000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.81,
|
| 681 |
+
"learning_rate": 6.465613288767347e-05,
|
| 682 |
+
"loss": 4.8082,
|
| 683 |
+
"step": 43500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.82,
|
| 687 |
+
"learning_rate": 6.414970120530741e-05,
|
| 688 |
+
"loss": 4.7677,
|
| 689 |
+
"step": 44000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.83,
|
| 693 |
+
"learning_rate": 6.364326952294136e-05,
|
| 694 |
+
"loss": 4.7947,
|
| 695 |
+
"step": 44500
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.84,
|
| 699 |
+
"learning_rate": 6.313683784057532e-05,
|
| 700 |
+
"loss": 4.7802,
|
| 701 |
+
"step": 45000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.84,
|
| 705 |
+
"eval_loss": 4.7554545402526855,
|
| 706 |
+
"eval_runtime": 410.6533,
|
| 707 |
+
"eval_samples_per_second": 41.456,
|
| 708 |
+
"eval_steps_per_second": 5.182,
|
| 709 |
+
"eval_wer": 0.8823350852509756,
|
| 710 |
+
"step": 45000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.85,
|
| 714 |
+
"learning_rate": 6.2631419021574e-05,
|
| 715 |
+
"loss": 4.79,
|
| 716 |
+
"step": 45500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.86,
|
| 720 |
+
"learning_rate": 6.212498733920794e-05,
|
| 721 |
+
"loss": 4.7812,
|
| 722 |
+
"step": 46000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.87,
|
| 726 |
+
"learning_rate": 6.161956852020663e-05,
|
| 727 |
+
"loss": 4.7822,
|
| 728 |
+
"step": 46500
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.88,
|
| 732 |
+
"learning_rate": 6.111313683784057e-05,
|
| 733 |
+
"loss": 4.7653,
|
| 734 |
+
"step": 47000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.89,
|
| 738 |
+
"learning_rate": 6.060670515547453e-05,
|
| 739 |
+
"loss": 4.7809,
|
| 740 |
+
"step": 47500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.89,
|
| 744 |
+
"eval_loss": 4.742018222808838,
|
| 745 |
+
"eval_runtime": 411.2108,
|
| 746 |
+
"eval_samples_per_second": 41.4,
|
| 747 |
+
"eval_steps_per_second": 5.175,
|
| 748 |
+
"eval_wer": 0.8812212383066652,
|
| 749 |
+
"step": 47500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.89,
|
| 753 |
+
"learning_rate": 6.010027347310848e-05,
|
| 754 |
+
"loss": 4.78,
|
| 755 |
+
"step": 48000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.9,
|
| 759 |
+
"learning_rate": 5.9593841790742435e-05,
|
| 760 |
+
"loss": 4.7755,
|
| 761 |
+
"step": 48500
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.91,
|
| 765 |
+
"learning_rate": 5.908741010837638e-05,
|
| 766 |
+
"loss": 4.7692,
|
| 767 |
+
"step": 49000
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.92,
|
| 771 |
+
"learning_rate": 5.8580978426010335e-05,
|
| 772 |
+
"loss": 4.7752,
|
| 773 |
+
"step": 49500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.93,
|
| 777 |
+
"learning_rate": 5.807454674364429e-05,
|
| 778 |
+
"loss": 4.7655,
|
| 779 |
+
"step": 50000
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.93,
|
| 783 |
+
"eval_loss": 4.738577842712402,
|
| 784 |
+
"eval_runtime": 410.9533,
|
| 785 |
+
"eval_samples_per_second": 41.426,
|
| 786 |
+
"eval_steps_per_second": 5.178,
|
| 787 |
+
"eval_wer": 0.8806589572882034,
|
| 788 |
+
"step": 50000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.94,
|
| 792 |
+
"learning_rate": 5.7568115061278236e-05,
|
| 793 |
+
"loss": 4.7728,
|
| 794 |
+
"step": 50500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.95,
|
| 798 |
+
"learning_rate": 5.706168337891219e-05,
|
| 799 |
+
"loss": 4.7684,
|
| 800 |
+
"step": 51000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.96,
|
| 804 |
+
"learning_rate": 5.655525169654614e-05,
|
| 805 |
+
"loss": 4.7651,
|
| 806 |
+
"step": 51500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.97,
|
| 810 |
+
"learning_rate": 5.604882001418009e-05,
|
| 811 |
+
"loss": 4.7577,
|
| 812 |
+
"step": 52000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.98,
|
| 816 |
+
"learning_rate": 5.554238833181404e-05,
|
| 817 |
+
"loss": 4.7753,
|
| 818 |
+
"step": 52500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.98,
|
| 822 |
+
"eval_loss": 4.731768608093262,
|
| 823 |
+
"eval_runtime": 411.2946,
|
| 824 |
+
"eval_samples_per_second": 41.391,
|
| 825 |
+
"eval_steps_per_second": 5.174,
|
| 826 |
+
"eval_wer": 0.880302876466612,
|
| 827 |
+
"step": 52500
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.99,
|
| 831 |
+
"learning_rate": 5.5035956649448e-05,
|
| 832 |
+
"loss": 4.7567,
|
| 833 |
+
"step": 53000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.0,
|
| 837 |
+
"learning_rate": 5.4529524967081944e-05,
|
| 838 |
+
"loss": 4.7649,
|
| 839 |
+
"step": 53500
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.01,
|
| 843 |
+
"learning_rate": 5.40230932847159e-05,
|
| 844 |
+
"loss": 4.7431,
|
| 845 |
+
"step": 54000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 1.02,
|
| 849 |
+
"learning_rate": 5.351666160234985e-05,
|
| 850 |
+
"loss": 4.7517,
|
| 851 |
+
"step": 54500
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 1.03,
|
| 855 |
+
"learning_rate": 5.3011242783348524e-05,
|
| 856 |
+
"loss": 4.7622,
|
| 857 |
+
"step": 55000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.03,
|
| 861 |
+
"eval_loss": 4.7267656326293945,
|
| 862 |
+
"eval_runtime": 410.5389,
|
| 863 |
+
"eval_samples_per_second": 41.467,
|
| 864 |
+
"eval_steps_per_second": 5.183,
|
| 865 |
+
"eval_wer": 0.8803810182395704,
|
| 866 |
+
"step": 55000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.03,
|
| 870 |
+
"learning_rate": 5.250481110098248e-05,
|
| 871 |
+
"loss": 4.7505,
|
| 872 |
+
"step": 55500
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.04,
|
| 876 |
+
"learning_rate": 5.1998379418616425e-05,
|
| 877 |
+
"loss": 4.7562,
|
| 878 |
+
"step": 56000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.05,
|
| 882 |
+
"learning_rate": 5.149194773625038e-05,
|
| 883 |
+
"loss": 4.7565,
|
| 884 |
+
"step": 56500
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 1.06,
|
| 888 |
+
"learning_rate": 5.0986528917249065e-05,
|
| 889 |
+
"loss": 4.7486,
|
| 890 |
+
"step": 57000
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.07,
|
| 894 |
+
"learning_rate": 5.048009723488302e-05,
|
| 895 |
+
"loss": 4.7511,
|
| 896 |
+
"step": 57500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 1.07,
|
| 900 |
+
"eval_loss": 4.725167751312256,
|
| 901 |
+
"eval_runtime": 411.131,
|
| 902 |
+
"eval_samples_per_second": 41.408,
|
| 903 |
+
"eval_steps_per_second": 5.176,
|
| 904 |
+
"eval_wer": 0.8796747368301385,
|
| 905 |
+
"step": 57500
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 1.08,
|
| 909 |
+
"learning_rate": 4.9973665552516966e-05,
|
| 910 |
+
"loss": 4.7501,
|
| 911 |
+
"step": 58000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.09,
|
| 915 |
+
"learning_rate": 4.946723387015092e-05,
|
| 916 |
+
"loss": 4.7481,
|
| 917 |
+
"step": 58500
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 1.1,
|
| 921 |
+
"learning_rate": 4.896080218778487e-05,
|
| 922 |
+
"loss": 4.7376,
|
| 923 |
+
"step": 59000
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 1.11,
|
| 927 |
+
"learning_rate": 4.845538336878355e-05,
|
| 928 |
+
"loss": 4.7516,
|
| 929 |
+
"step": 59500
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 1.12,
|
| 933 |
+
"learning_rate": 4.7948951686417507e-05,
|
| 934 |
+
"loss": 4.7508,
|
| 935 |
+
"step": 60000
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 1.12,
|
| 939 |
+
"eval_loss": 4.714947700500488,
|
| 940 |
+
"eval_runtime": 410.7042,
|
| 941 |
+
"eval_samples_per_second": 41.451,
|
| 942 |
+
"eval_steps_per_second": 5.181,
|
| 943 |
+
"eval_wer": 0.878954342859704,
|
| 944 |
+
"step": 60000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 1.13,
|
| 948 |
+
"learning_rate": 4.744252000405145e-05,
|
| 949 |
+
"loss": 4.7489,
|
| 950 |
+
"step": 60500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 1.14,
|
| 954 |
+
"learning_rate": 4.693608832168541e-05,
|
| 955 |
+
"loss": 4.7324,
|
| 956 |
+
"step": 61000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 1.15,
|
| 960 |
+
"learning_rate": 4.643066950268409e-05,
|
| 961 |
+
"loss": 4.7485,
|
| 962 |
+
"step": 61500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.16,
|
| 966 |
+
"learning_rate": 4.592423782031804e-05,
|
| 967 |
+
"loss": 4.7337,
|
| 968 |
+
"step": 62000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 1.16,
|
| 972 |
+
"learning_rate": 4.541780613795199e-05,
|
| 973 |
+
"loss": 4.7299,
|
| 974 |
+
"step": 62500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.16,
|
| 978 |
+
"eval_loss": 4.713499069213867,
|
| 979 |
+
"eval_runtime": 410.0852,
|
| 980 |
+
"eval_samples_per_second": 41.513,
|
| 981 |
+
"eval_steps_per_second": 5.189,
|
| 982 |
+
"eval_wer": 0.8791197734359003,
|
| 983 |
+
"step": 62500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.17,
|
| 987 |
+
"learning_rate": 4.4912387318950675e-05,
|
| 988 |
+
"loss": 4.7385,
|
| 989 |
+
"step": 63000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.18,
|
| 993 |
+
"learning_rate": 4.440595563658463e-05,
|
| 994 |
+
"loss": 4.7339,
|
| 995 |
+
"step": 63500
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.19,
|
| 999 |
+
"learning_rate": 4.389952395421858e-05,
|
| 1000 |
+
"loss": 4.7351,
|
| 1001 |
+
"step": 64000
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.2,
|
| 1005 |
+
"learning_rate": 4.339309227185253e-05,
|
| 1006 |
+
"loss": 4.7472,
|
| 1007 |
+
"step": 64500
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.21,
|
| 1011 |
+
"learning_rate": 4.288666058948648e-05,
|
| 1012 |
+
"loss": 4.7382,
|
| 1013 |
+
"step": 65000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.21,
|
| 1017 |
+
"eval_loss": 4.706689357757568,
|
| 1018 |
+
"eval_runtime": 411.4243,
|
| 1019 |
+
"eval_samples_per_second": 41.378,
|
| 1020 |
+
"eval_steps_per_second": 5.172,
|
| 1021 |
+
"eval_wer": 0.8785633726511897,
|
| 1022 |
+
"step": 65000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.22,
|
| 1026 |
+
"learning_rate": 4.2380228907120436e-05,
|
| 1027 |
+
"loss": 4.7372,
|
| 1028 |
+
"step": 65500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.23,
|
| 1032 |
+
"learning_rate": 4.187379722475438e-05,
|
| 1033 |
+
"loss": 4.7344,
|
| 1034 |
+
"step": 66000
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.24,
|
| 1038 |
+
"learning_rate": 4.136736554238833e-05,
|
| 1039 |
+
"loss": 4.7225,
|
| 1040 |
+
"step": 66500
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.25,
|
| 1044 |
+
"learning_rate": 4.086093386002228e-05,
|
| 1045 |
+
"loss": 4.7339,
|
| 1046 |
+
"step": 67000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.26,
|
| 1050 |
+
"learning_rate": 4.0354502177656236e-05,
|
| 1051 |
+
"loss": 4.723,
|
| 1052 |
+
"step": 67500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.26,
|
| 1056 |
+
"eval_loss": 4.703372001647949,
|
| 1057 |
+
"eval_runtime": 411.6733,
|
| 1058 |
+
"eval_samples_per_second": 41.353,
|
| 1059 |
+
"eval_steps_per_second": 5.169,
|
| 1060 |
+
"eval_wer": 0.8783083011782551,
|
| 1061 |
+
"step": 67500
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.27,
|
| 1065 |
+
"learning_rate": 3.984807049529018e-05,
|
| 1066 |
+
"loss": 4.7498,
|
| 1067 |
+
"step": 68000
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.28,
|
| 1071 |
+
"learning_rate": 3.934163881292414e-05,
|
| 1072 |
+
"loss": 4.7296,
|
| 1073 |
+
"step": 68500
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.29,
|
| 1077 |
+
"learning_rate": 3.8836219993922824e-05,
|
| 1078 |
+
"loss": 4.7201,
|
| 1079 |
+
"step": 69000
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.3,
|
| 1083 |
+
"learning_rate": 3.832978831155678e-05,
|
| 1084 |
+
"loss": 4.7328,
|
| 1085 |
+
"step": 69500
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.3,
|
| 1089 |
+
"learning_rate": 3.782436949255546e-05,
|
| 1090 |
+
"loss": 4.7321,
|
| 1091 |
+
"step": 70000
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.3,
|
| 1095 |
+
"eval_loss": 4.700106143951416,
|
| 1096 |
+
"eval_runtime": 411.0597,
|
| 1097 |
+
"eval_samples_per_second": 41.415,
|
| 1098 |
+
"eval_steps_per_second": 5.177,
|
| 1099 |
+
"eval_wer": 0.8781452226955593,
|
| 1100 |
+
"step": 70000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.31,
|
| 1104 |
+
"learning_rate": 3.7317937810189405e-05,
|
| 1105 |
+
"loss": 4.7226,
|
| 1106 |
+
"step": 70500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.32,
|
| 1110 |
+
"learning_rate": 3.681150612782336e-05,
|
| 1111 |
+
"loss": 4.7271,
|
| 1112 |
+
"step": 71000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.33,
|
| 1116 |
+
"learning_rate": 3.630507444545731e-05,
|
| 1117 |
+
"loss": 4.7245,
|
| 1118 |
+
"step": 71500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.34,
|
| 1122 |
+
"learning_rate": 3.579864276309126e-05,
|
| 1123 |
+
"loss": 4.717,
|
| 1124 |
+
"step": 72000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.35,
|
| 1128 |
+
"learning_rate": 3.529221108072521e-05,
|
| 1129 |
+
"loss": 4.7261,
|
| 1130 |
+
"step": 72500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.35,
|
| 1134 |
+
"eval_loss": 4.695710182189941,
|
| 1135 |
+
"eval_runtime": 410.4939,
|
| 1136 |
+
"eval_samples_per_second": 41.472,
|
| 1137 |
+
"eval_steps_per_second": 5.184,
|
| 1138 |
+
"eval_wer": 0.8775924807229604,
|
| 1139 |
+
"step": 72500
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.36,
|
| 1143 |
+
"learning_rate": 3.4785779398359166e-05,
|
| 1144 |
+
"loss": 4.7225,
|
| 1145 |
+
"step": 73000
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.37,
|
| 1149 |
+
"learning_rate": 3.427934771599311e-05,
|
| 1150 |
+
"loss": 4.7112,
|
| 1151 |
+
"step": 73500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.38,
|
| 1155 |
+
"learning_rate": 3.3772916033627066e-05,
|
| 1156 |
+
"loss": 4.7178,
|
| 1157 |
+
"step": 74000
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.39,
|
| 1161 |
+
"learning_rate": 3.326648435126102e-05,
|
| 1162 |
+
"loss": 4.7221,
|
| 1163 |
+
"step": 74500
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.4,
|
| 1167 |
+
"learning_rate": 3.27610655322597e-05,
|
| 1168 |
+
"loss": 4.6915,
|
| 1169 |
+
"step": 75000
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 1.4,
|
| 1173 |
+
"eval_loss": 4.690956115722656,
|
| 1174 |
+
"eval_runtime": 411.7522,
|
| 1175 |
+
"eval_samples_per_second": 41.345,
|
| 1176 |
+
"eval_steps_per_second": 5.168,
|
| 1177 |
+
"eval_wer": 0.8773312676725525,
|
| 1178 |
+
"step": 75000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.41,
|
| 1182 |
+
"learning_rate": 3.2254633849893653e-05,
|
| 1183 |
+
"loss": 4.7246,
|
| 1184 |
+
"step": 75500
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.42,
|
| 1188 |
+
"learning_rate": 3.17482021675276e-05,
|
| 1189 |
+
"loss": 4.7043,
|
| 1190 |
+
"step": 76000
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.43,
|
| 1194 |
+
"learning_rate": 3.1241770485161554e-05,
|
| 1195 |
+
"loss": 4.7311,
|
| 1196 |
+
"step": 76500
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.44,
|
| 1200 |
+
"learning_rate": 3.073533880279551e-05,
|
| 1201 |
+
"loss": 4.7179,
|
| 1202 |
+
"step": 77000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.44,
|
| 1206 |
+
"learning_rate": 3.0228907120429458e-05,
|
| 1207 |
+
"loss": 4.7233,
|
| 1208 |
+
"step": 77500
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.44,
|
| 1212 |
+
"eval_loss": 4.687117576599121,
|
| 1213 |
+
"eval_runtime": 411.0114,
|
| 1214 |
+
"eval_samples_per_second": 41.42,
|
| 1215 |
+
"eval_steps_per_second": 5.177,
|
| 1216 |
+
"eval_wer": 0.8769715280388493,
|
| 1217 |
+
"step": 77500
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.45,
|
| 1221 |
+
"learning_rate": 2.9723488301428138e-05,
|
| 1222 |
+
"loss": 4.7019,
|
| 1223 |
+
"step": 78000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 1.46,
|
| 1227 |
+
"learning_rate": 2.9217056619062088e-05,
|
| 1228 |
+
"loss": 4.7193,
|
| 1229 |
+
"step": 78500
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 1.47,
|
| 1233 |
+
"learning_rate": 2.871062493669604e-05,
|
| 1234 |
+
"loss": 4.7011,
|
| 1235 |
+
"step": 79000
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.48,
|
| 1239 |
+
"learning_rate": 2.8204193254329992e-05,
|
| 1240 |
+
"loss": 4.7246,
|
| 1241 |
+
"step": 79500
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.49,
|
| 1245 |
+
"learning_rate": 2.769877443532868e-05,
|
| 1246 |
+
"loss": 4.7245,
|
| 1247 |
+
"step": 80000
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.49,
|
| 1251 |
+
"eval_loss": 4.684831619262695,
|
| 1252 |
+
"eval_runtime": 411.3597,
|
| 1253 |
+
"eval_samples_per_second": 41.385,
|
| 1254 |
+
"eval_steps_per_second": 5.173,
|
| 1255 |
+
"eval_wer": 0.8767522606558656,
|
| 1256 |
+
"step": 80000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.5,
|
| 1260 |
+
"learning_rate": 2.7192342752962626e-05,
|
| 1261 |
+
"loss": 4.7072,
|
| 1262 |
+
"step": 80500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.51,
|
| 1266 |
+
"learning_rate": 2.6685911070596576e-05,
|
| 1267 |
+
"loss": 4.7038,
|
| 1268 |
+
"step": 81000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.52,
|
| 1272 |
+
"learning_rate": 2.6179479388230526e-05,
|
| 1273 |
+
"loss": 4.7019,
|
| 1274 |
+
"step": 81500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.53,
|
| 1278 |
+
"learning_rate": 2.5674060569229213e-05,
|
| 1279 |
+
"loss": 4.7023,
|
| 1280 |
+
"step": 82000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.54,
|
| 1284 |
+
"learning_rate": 2.5167628886863163e-05,
|
| 1285 |
+
"loss": 4.6995,
|
| 1286 |
+
"step": 82500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 1.54,
|
| 1290 |
+
"eval_loss": 4.683341979980469,
|
| 1291 |
+
"eval_runtime": 411.2621,
|
| 1292 |
+
"eval_samples_per_second": 41.395,
|
| 1293 |
+
"eval_steps_per_second": 5.174,
|
| 1294 |
+
"eval_wer": 0.8766509899634863,
|
| 1295 |
+
"step": 82500
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.55,
|
| 1299 |
+
"learning_rate": 2.4661197204497113e-05,
|
| 1300 |
+
"loss": 4.7139,
|
| 1301 |
+
"step": 83000
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.56,
|
| 1305 |
+
"learning_rate": 2.4154765522131064e-05,
|
| 1306 |
+
"loss": 4.6981,
|
| 1307 |
+
"step": 83500
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 1.57,
|
| 1311 |
+
"learning_rate": 2.3648333839765017e-05,
|
| 1312 |
+
"loss": 4.7053,
|
| 1313 |
+
"step": 84000
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.57,
|
| 1317 |
+
"learning_rate": 2.31429150207637e-05,
|
| 1318 |
+
"loss": 4.7152,
|
| 1319 |
+
"step": 84500
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.58,
|
| 1323 |
+
"learning_rate": 2.263648333839765e-05,
|
| 1324 |
+
"loss": 4.7084,
|
| 1325 |
+
"step": 85000
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.58,
|
| 1329 |
+
"eval_loss": 4.678108215332031,
|
| 1330 |
+
"eval_runtime": 411.2113,
|
| 1331 |
+
"eval_samples_per_second": 41.4,
|
| 1332 |
+
"eval_steps_per_second": 5.175,
|
| 1333 |
+
"eval_wer": 0.8766087829523399,
|
| 1334 |
+
"step": 85000
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.59,
|
| 1338 |
+
"learning_rate": 2.2130051656031605e-05,
|
| 1339 |
+
"loss": 4.6985,
|
| 1340 |
+
"step": 85500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.6,
|
| 1344 |
+
"learning_rate": 2.1623619973665555e-05,
|
| 1345 |
+
"loss": 4.7024,
|
| 1346 |
+
"step": 86000
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.61,
|
| 1350 |
+
"learning_rate": 2.1117188291299505e-05,
|
| 1351 |
+
"loss": 4.7015,
|
| 1352 |
+
"step": 86500
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 1.62,
|
| 1356 |
+
"learning_rate": 2.0611769472298185e-05,
|
| 1357 |
+
"loss": 4.6919,
|
| 1358 |
+
"step": 87000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.63,
|
| 1362 |
+
"learning_rate": 2.010533778993214e-05,
|
| 1363 |
+
"loss": 4.7115,
|
| 1364 |
+
"step": 87500
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.63,
|
| 1368 |
+
"eval_loss": 4.676379680633545,
|
| 1369 |
+
"eval_runtime": 410.905,
|
| 1370 |
+
"eval_samples_per_second": 41.431,
|
| 1371 |
+
"eval_steps_per_second": 5.179,
|
| 1372 |
+
"eval_wer": 0.8762864154709211,
|
| 1373 |
+
"step": 87500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.64,
|
| 1377 |
+
"learning_rate": 1.959890610756609e-05,
|
| 1378 |
+
"loss": 4.7144,
|
| 1379 |
+
"step": 88000
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 1.65,
|
| 1383 |
+
"learning_rate": 1.9092474425200043e-05,
|
| 1384 |
+
"loss": 4.6893,
|
| 1385 |
+
"step": 88500
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.66,
|
| 1389 |
+
"learning_rate": 1.8587055606198726e-05,
|
| 1390 |
+
"loss": 4.6977,
|
| 1391 |
+
"step": 89000
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 1.67,
|
| 1395 |
+
"learning_rate": 1.808163678719741e-05,
|
| 1396 |
+
"loss": 4.6987,
|
| 1397 |
+
"step": 89500
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.68,
|
| 1401 |
+
"learning_rate": 1.757520510483136e-05,
|
| 1402 |
+
"loss": 4.7072,
|
| 1403 |
+
"step": 90000
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.68,
|
| 1407 |
+
"eval_loss": 4.674571514129639,
|
| 1408 |
+
"eval_runtime": 410.8023,
|
| 1409 |
+
"eval_samples_per_second": 41.441,
|
| 1410 |
+
"eval_steps_per_second": 5.18,
|
| 1411 |
+
"eval_wer": 0.8756789219885069,
|
| 1412 |
+
"step": 90000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 1.69,
|
| 1416 |
+
"learning_rate": 1.706877342246531e-05,
|
| 1417 |
+
"loss": 4.7077,
|
| 1418 |
+
"step": 90500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.7,
|
| 1422 |
+
"learning_rate": 1.656234174009926e-05,
|
| 1423 |
+
"loss": 4.7049,
|
| 1424 |
+
"step": 91000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.71,
|
| 1428 |
+
"learning_rate": 1.605591005773321e-05,
|
| 1429 |
+
"loss": 4.7023,
|
| 1430 |
+
"step": 91500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.71,
|
| 1434 |
+
"learning_rate": 1.5549478375367164e-05,
|
| 1435 |
+
"loss": 4.695,
|
| 1436 |
+
"step": 92000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 1.72,
|
| 1440 |
+
"learning_rate": 1.5043046693001114e-05,
|
| 1441 |
+
"loss": 4.7036,
|
| 1442 |
+
"step": 92500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.72,
|
| 1446 |
+
"eval_loss": 4.672886848449707,
|
| 1447 |
+
"eval_runtime": 411.4353,
|
| 1448 |
+
"eval_samples_per_second": 41.377,
|
| 1449 |
+
"eval_steps_per_second": 5.172,
|
| 1450 |
+
"eval_wer": 0.8758804179983762,
|
| 1451 |
+
"step": 92500
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.73,
|
| 1455 |
+
"learning_rate": 1.4536615010635066e-05,
|
| 1456 |
+
"loss": 4.7079,
|
| 1457 |
+
"step": 93000
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.74,
|
| 1461 |
+
"learning_rate": 1.4030183328269016e-05,
|
| 1462 |
+
"loss": 4.7002,
|
| 1463 |
+
"step": 93500
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.75,
|
| 1467 |
+
"learning_rate": 1.3523751645902968e-05,
|
| 1468 |
+
"loss": 4.6982,
|
| 1469 |
+
"step": 94000
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 1.76,
|
| 1473 |
+
"learning_rate": 1.301731996353692e-05,
|
| 1474 |
+
"loss": 4.6883,
|
| 1475 |
+
"step": 94500
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 1.77,
|
| 1479 |
+
"learning_rate": 1.2511901144535604e-05,
|
| 1480 |
+
"loss": 4.6907,
|
| 1481 |
+
"step": 95000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.77,
|
| 1485 |
+
"eval_loss": 4.670739650726318,
|
| 1486 |
+
"eval_runtime": 410.8726,
|
| 1487 |
+
"eval_samples_per_second": 41.434,
|
| 1488 |
+
"eval_steps_per_second": 5.179,
|
| 1489 |
+
"eval_wer": 0.8756105806051335,
|
| 1490 |
+
"step": 95000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.78,
|
| 1494 |
+
"learning_rate": 1.2005469462169554e-05,
|
| 1495 |
+
"loss": 4.7006,
|
| 1496 |
+
"step": 95500
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 1.79,
|
| 1500 |
+
"learning_rate": 1.1499037779803506e-05,
|
| 1501 |
+
"loss": 4.6984,
|
| 1502 |
+
"step": 96000
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.8,
|
| 1506 |
+
"learning_rate": 1.0992606097437456e-05,
|
| 1507 |
+
"loss": 4.6942,
|
| 1508 |
+
"step": 96500
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.81,
|
| 1512 |
+
"learning_rate": 1.048718727843614e-05,
|
| 1513 |
+
"loss": 4.7016,
|
| 1514 |
+
"step": 97000
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.82,
|
| 1518 |
+
"learning_rate": 9.98075559607009e-06,
|
| 1519 |
+
"loss": 4.681,
|
| 1520 |
+
"step": 97500
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 1.82,
|
| 1524 |
+
"eval_loss": 4.668375492095947,
|
| 1525 |
+
"eval_runtime": 411.3728,
|
| 1526 |
+
"eval_samples_per_second": 41.383,
|
| 1527 |
+
"eval_steps_per_second": 5.173,
|
| 1528 |
+
"eval_wer": 0.875492453242668,
|
| 1529 |
+
"step": 97500
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.83,
|
| 1533 |
+
"learning_rate": 9.474323913704042e-06,
|
| 1534 |
+
"loss": 4.6988,
|
| 1535 |
+
"step": 98000
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.84,
|
| 1539 |
+
"learning_rate": 8.967892231337994e-06,
|
| 1540 |
+
"loss": 4.7063,
|
| 1541 |
+
"step": 98500
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.85,
|
| 1545 |
+
"learning_rate": 8.462473412336676e-06,
|
| 1546 |
+
"loss": 4.689,
|
| 1547 |
+
"step": 99000
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 1.85,
|
| 1551 |
+
"learning_rate": 7.956041729970628e-06,
|
| 1552 |
+
"loss": 4.6833,
|
| 1553 |
+
"step": 99500
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 1.86,
|
| 1557 |
+
"learning_rate": 7.449610047604579e-06,
|
| 1558 |
+
"loss": 4.6905,
|
| 1559 |
+
"step": 100000
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 1.86,
|
| 1563 |
+
"eval_loss": 4.668146133422852,
|
| 1564 |
+
"eval_runtime": 410.5824,
|
| 1565 |
+
"eval_samples_per_second": 41.463,
|
| 1566 |
+
"eval_steps_per_second": 5.183,
|
| 1567 |
+
"eval_wer": 0.8755806567489337,
|
| 1568 |
+
"step": 100000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.87,
|
| 1572 |
+
"learning_rate": 6.94317836523853e-06,
|
| 1573 |
+
"loss": 4.6848,
|
| 1574 |
+
"step": 100500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.88,
|
| 1578 |
+
"learning_rate": 6.4367466828724815e-06,
|
| 1579 |
+
"loss": 4.6882,
|
| 1580 |
+
"step": 101000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 1.89,
|
| 1584 |
+
"learning_rate": 5.930315000506432e-06,
|
| 1585 |
+
"loss": 4.6821,
|
| 1586 |
+
"step": 101500
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.9,
|
| 1590 |
+
"learning_rate": 5.4238833181403835e-06,
|
| 1591 |
+
"loss": 4.6908,
|
| 1592 |
+
"step": 102000
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.91,
|
| 1596 |
+
"learning_rate": 4.917451635774335e-06,
|
| 1597 |
+
"loss": 4.6975,
|
| 1598 |
+
"step": 102500
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.91,
|
| 1602 |
+
"eval_loss": 4.664699554443359,
|
| 1603 |
+
"eval_runtime": 411.5323,
|
| 1604 |
+
"eval_samples_per_second": 41.367,
|
| 1605 |
+
"eval_steps_per_second": 5.171,
|
| 1606 |
+
"eval_wer": 0.8751601546998029,
|
| 1607 |
+
"step": 102500
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.92,
|
| 1611 |
+
"learning_rate": 4.411019953408286e-06,
|
| 1612 |
+
"loss": 4.6878,
|
| 1613 |
+
"step": 103000
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.93,
|
| 1617 |
+
"learning_rate": 3.9056011344069684e-06,
|
| 1618 |
+
"loss": 4.6829,
|
| 1619 |
+
"step": 103500
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.94,
|
| 1623 |
+
"learning_rate": 3.400182315405652e-06,
|
| 1624 |
+
"loss": 4.6882,
|
| 1625 |
+
"step": 104000
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.95,
|
| 1629 |
+
"learning_rate": 2.893750633039603e-06,
|
| 1630 |
+
"loss": 4.6905,
|
| 1631 |
+
"step": 104500
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 1.96,
|
| 1635 |
+
"learning_rate": 2.387318950673554e-06,
|
| 1636 |
+
"loss": 4.6849,
|
| 1637 |
+
"step": 105000
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 1.96,
|
| 1641 |
+
"eval_loss": 4.664451599121094,
|
| 1642 |
+
"eval_runtime": 411.3214,
|
| 1643 |
+
"eval_samples_per_second": 41.389,
|
| 1644 |
+
"eval_steps_per_second": 5.174,
|
| 1645 |
+
"eval_wer": 0.8751350657024651,
|
| 1646 |
+
"step": 105000
|
| 1647 |
+
}
|
| 1648 |
+
],
|
| 1649 |
+
"max_steps": 107316,
|
| 1650 |
+
"num_train_epochs": 2,
|
| 1651 |
+
"total_flos": 1.0233532461203251e+18,
|
| 1652 |
+
"trial_name": null,
|
| 1653 |
+
"trial_params": null
|
| 1654 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cb56c1fa90990b23b6cd76b26882eb946745dcc06e60c8f303af048131c7c49
|
| 3 |
+
size 4027
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|