tarikdincer
commited on
Commit
•
8186ce3
1
Parent(s):
38b33b4
model files are added
Browse files- .DS_Store +0 -0
- config.json +75 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +739 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
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": "4.38.2",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_bos_token_id": 0,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"no_repeat_ngram_size": 3,
|
| 9 |
+
"num_beams": 4,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.38.2"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc96341a118cd5e143be21b2facdd4ab838539a7bba52af1bcbfed486690c664
|
| 3 |
+
size 557912620
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24165cc88b9488949bb4e552f6b04151e6dd6cdde1fab6dd427e8e5a5d80caab
|
| 3 |
+
size 1115579898
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d97f8b6459373c118b1617234bf9c04bd797322db8c55570f4ebf6dbe844bbb
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac36bc24c0dcde8780c73dbb5e6ec02976f9779e9bcd724560176dc11c0c4e85
|
| 3 |
+
size 1064
|
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": true,
|
| 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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1024,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,739 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.56,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 8.571518898010254,
|
| 14 |
+
"learning_rate": 0.0003965811965811966,
|
| 15 |
+
"loss": 6.0892,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 2.477086067199707,
|
| 21 |
+
"learning_rate": 0.00039316239316239317,
|
| 22 |
+
"loss": 1.4485,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 0.7137540578842163,
|
| 28 |
+
"learning_rate": 0.00038974358974358975,
|
| 29 |
+
"loss": 0.9732,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1,
|
| 34 |
+
"grad_norm": 0.5362057685852051,
|
| 35 |
+
"learning_rate": 0.0003863247863247863,
|
| 36 |
+
"loss": 0.7804,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.13,
|
| 41 |
+
"grad_norm": 0.6810179948806763,
|
| 42 |
+
"learning_rate": 0.00038290598290598296,
|
| 43 |
+
"loss": 0.665,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"grad_norm": 0.4986821115016937,
|
| 49 |
+
"learning_rate": 0.0003794871794871795,
|
| 50 |
+
"loss": 0.6091,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18,
|
| 55 |
+
"grad_norm": 0.4309682250022888,
|
| 56 |
+
"learning_rate": 0.00037606837606837606,
|
| 57 |
+
"loss": 0.5502,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2,
|
| 62 |
+
"grad_norm": 0.3824257552623749,
|
| 63 |
+
"learning_rate": 0.0003726495726495727,
|
| 64 |
+
"loss": 0.5164,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.23,
|
| 69 |
+
"grad_norm": 0.3188970386981964,
|
| 70 |
+
"learning_rate": 0.00036923076923076927,
|
| 71 |
+
"loss": 0.4883,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.26,
|
| 76 |
+
"grad_norm": 0.3359103202819824,
|
| 77 |
+
"learning_rate": 0.00036581196581196584,
|
| 78 |
+
"loss": 0.4612,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.28,
|
| 83 |
+
"grad_norm": 0.4327464699745178,
|
| 84 |
+
"learning_rate": 0.0003623931623931624,
|
| 85 |
+
"loss": 0.4351,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.31,
|
| 90 |
+
"grad_norm": 0.4424777030944824,
|
| 91 |
+
"learning_rate": 0.000358974358974359,
|
| 92 |
+
"loss": 0.4217,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.33,
|
| 97 |
+
"grad_norm": 0.520322322845459,
|
| 98 |
+
"learning_rate": 0.00035555555555555557,
|
| 99 |
+
"loss": 0.4076,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.36,
|
| 104 |
+
"grad_norm": 0.48572778701782227,
|
| 105 |
+
"learning_rate": 0.00035213675213675215,
|
| 106 |
+
"loss": 0.3948,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.38,
|
| 111 |
+
"grad_norm": 0.2985605001449585,
|
| 112 |
+
"learning_rate": 0.0003487179487179487,
|
| 113 |
+
"loss": 0.3823,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.41,
|
| 118 |
+
"grad_norm": 0.28738752007484436,
|
| 119 |
+
"learning_rate": 0.00034529914529914536,
|
| 120 |
+
"loss": 0.375,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.44,
|
| 125 |
+
"grad_norm": 0.29423144459724426,
|
| 126 |
+
"learning_rate": 0.0003418803418803419,
|
| 127 |
+
"loss": 0.3591,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.46,
|
| 132 |
+
"grad_norm": 0.26430046558380127,
|
| 133 |
+
"learning_rate": 0.00033846153846153846,
|
| 134 |
+
"loss": 0.3494,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.49,
|
| 139 |
+
"grad_norm": 0.2734215259552002,
|
| 140 |
+
"learning_rate": 0.0003350427350427351,
|
| 141 |
+
"loss": 0.3396,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.51,
|
| 146 |
+
"grad_norm": 0.3005197048187256,
|
| 147 |
+
"learning_rate": 0.00033162393162393166,
|
| 148 |
+
"loss": 0.3352,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.54,
|
| 153 |
+
"grad_norm": 0.2822723686695099,
|
| 154 |
+
"learning_rate": 0.0003282051282051282,
|
| 155 |
+
"loss": 0.3241,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.56,
|
| 160 |
+
"grad_norm": 0.2792316973209381,
|
| 161 |
+
"learning_rate": 0.0003247863247863248,
|
| 162 |
+
"loss": 0.3208,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.59,
|
| 167 |
+
"grad_norm": 0.2761669158935547,
|
| 168 |
+
"learning_rate": 0.0003213675213675214,
|
| 169 |
+
"loss": 0.3148,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.61,
|
| 174 |
+
"grad_norm": 0.2733113467693329,
|
| 175 |
+
"learning_rate": 0.0003179487179487179,
|
| 176 |
+
"loss": 0.311,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.64,
|
| 181 |
+
"grad_norm": 0.3393694758415222,
|
| 182 |
+
"learning_rate": 0.00031452991452991455,
|
| 183 |
+
"loss": 0.3056,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.67,
|
| 188 |
+
"grad_norm": 0.29316985607147217,
|
| 189 |
+
"learning_rate": 0.0003111111111111111,
|
| 190 |
+
"loss": 0.2975,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.69,
|
| 195 |
+
"grad_norm": 0.29134783148765564,
|
| 196 |
+
"learning_rate": 0.0003076923076923077,
|
| 197 |
+
"loss": 0.2898,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.72,
|
| 202 |
+
"grad_norm": 0.41234660148620605,
|
| 203 |
+
"learning_rate": 0.0003042735042735043,
|
| 204 |
+
"loss": 0.2895,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.74,
|
| 209 |
+
"grad_norm": 0.26693716645240784,
|
| 210 |
+
"learning_rate": 0.00030085470085470086,
|
| 211 |
+
"loss": 0.2835,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.77,
|
| 216 |
+
"grad_norm": 0.2862294614315033,
|
| 217 |
+
"learning_rate": 0.00029743589743589743,
|
| 218 |
+
"loss": 0.2747,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.79,
|
| 223 |
+
"grad_norm": 0.2596249282360077,
|
| 224 |
+
"learning_rate": 0.00029401709401709406,
|
| 225 |
+
"loss": 0.2752,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.82,
|
| 230 |
+
"grad_norm": 0.2555866241455078,
|
| 231 |
+
"learning_rate": 0.0002905982905982906,
|
| 232 |
+
"loss": 0.2662,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.84,
|
| 237 |
+
"grad_norm": 0.3845195472240448,
|
| 238 |
+
"learning_rate": 0.0002871794871794872,
|
| 239 |
+
"loss": 0.2625,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.87,
|
| 244 |
+
"grad_norm": 0.23550209403038025,
|
| 245 |
+
"learning_rate": 0.0002837606837606838,
|
| 246 |
+
"loss": 0.256,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9,
|
| 251 |
+
"grad_norm": 0.2434936910867691,
|
| 252 |
+
"learning_rate": 0.0002803418803418803,
|
| 253 |
+
"loss": 0.2545,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.92,
|
| 258 |
+
"grad_norm": 0.23562268912792206,
|
| 259 |
+
"learning_rate": 0.00027692307692307695,
|
| 260 |
+
"loss": 0.2536,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.95,
|
| 265 |
+
"grad_norm": 0.3110085427761078,
|
| 266 |
+
"learning_rate": 0.0002735042735042735,
|
| 267 |
+
"loss": 0.2497,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.97,
|
| 272 |
+
"grad_norm": 0.2646142244338989,
|
| 273 |
+
"learning_rate": 0.0002700854700854701,
|
| 274 |
+
"loss": 0.2448,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.0,
|
| 279 |
+
"grad_norm": 0.22812116146087646,
|
| 280 |
+
"learning_rate": 0.0002666666666666667,
|
| 281 |
+
"loss": 0.2409,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.02,
|
| 286 |
+
"grad_norm": 0.21481893956661224,
|
| 287 |
+
"learning_rate": 0.00026324786324786326,
|
| 288 |
+
"loss": 0.225,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.05,
|
| 293 |
+
"grad_norm": 0.2561526298522949,
|
| 294 |
+
"learning_rate": 0.00025982905982905983,
|
| 295 |
+
"loss": 0.2194,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.08,
|
| 300 |
+
"grad_norm": 0.2297515720129013,
|
| 301 |
+
"learning_rate": 0.00025641025641025646,
|
| 302 |
+
"loss": 0.216,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.1,
|
| 307 |
+
"grad_norm": 0.25526463985443115,
|
| 308 |
+
"learning_rate": 0.000252991452991453,
|
| 309 |
+
"loss": 0.2171,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.13,
|
| 314 |
+
"grad_norm": 0.24202637374401093,
|
| 315 |
+
"learning_rate": 0.00024957264957264956,
|
| 316 |
+
"loss": 0.2149,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.15,
|
| 321 |
+
"grad_norm": 0.20644807815551758,
|
| 322 |
+
"learning_rate": 0.0002461538461538462,
|
| 323 |
+
"loss": 0.209,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.18,
|
| 328 |
+
"grad_norm": 0.2795998454093933,
|
| 329 |
+
"learning_rate": 0.00024273504273504272,
|
| 330 |
+
"loss": 0.2071,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.2,
|
| 335 |
+
"grad_norm": 0.306149959564209,
|
| 336 |
+
"learning_rate": 0.00023931623931623932,
|
| 337 |
+
"loss": 0.208,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.23,
|
| 342 |
+
"grad_norm": 0.2355523407459259,
|
| 343 |
+
"learning_rate": 0.00023589743589743593,
|
| 344 |
+
"loss": 0.2051,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.25,
|
| 349 |
+
"grad_norm": 0.2909263074398041,
|
| 350 |
+
"learning_rate": 0.0002324786324786325,
|
| 351 |
+
"loss": 0.2023,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.28,
|
| 356 |
+
"grad_norm": 0.5298261642456055,
|
| 357 |
+
"learning_rate": 0.00022905982905982905,
|
| 358 |
+
"loss": 0.2018,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.28,
|
| 363 |
+
"eval_cer": 0.9319083335386478,
|
| 364 |
+
"eval_loss": 0.17038685083389282,
|
| 365 |
+
"eval_runtime": 138.0008,
|
| 366 |
+
"eval_samples_per_second": 14.493,
|
| 367 |
+
"eval_steps_per_second": 0.457,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.31,
|
| 372 |
+
"grad_norm": 0.23548871278762817,
|
| 373 |
+
"learning_rate": 0.00022564102564102566,
|
| 374 |
+
"loss": 0.2008,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.33,
|
| 379 |
+
"grad_norm": 0.20162977278232574,
|
| 380 |
+
"learning_rate": 0.00022222222222222223,
|
| 381 |
+
"loss": 0.1975,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.36,
|
| 386 |
+
"grad_norm": 0.2593408524990082,
|
| 387 |
+
"learning_rate": 0.00021880341880341884,
|
| 388 |
+
"loss": 0.1959,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.38,
|
| 393 |
+
"grad_norm": 0.21452312171459198,
|
| 394 |
+
"learning_rate": 0.0002153846153846154,
|
| 395 |
+
"loss": 0.194,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.41,
|
| 400 |
+
"grad_norm": 0.2637544274330139,
|
| 401 |
+
"learning_rate": 0.000211965811965812,
|
| 402 |
+
"loss": 0.1909,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.43,
|
| 407 |
+
"grad_norm": 0.24357128143310547,
|
| 408 |
+
"learning_rate": 0.00020854700854700857,
|
| 409 |
+
"loss": 0.19,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.46,
|
| 414 |
+
"grad_norm": 0.2084117978811264,
|
| 415 |
+
"learning_rate": 0.00020512820512820512,
|
| 416 |
+
"loss": 0.1857,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.48,
|
| 421 |
+
"grad_norm": 0.23245294392108917,
|
| 422 |
+
"learning_rate": 0.00020170940170940172,
|
| 423 |
+
"loss": 0.1858,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.51,
|
| 428 |
+
"grad_norm": 0.23836293816566467,
|
| 429 |
+
"learning_rate": 0.0001982905982905983,
|
| 430 |
+
"loss": 0.183,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.54,
|
| 435 |
+
"grad_norm": 0.19184565544128418,
|
| 436 |
+
"learning_rate": 0.00019487179487179487,
|
| 437 |
+
"loss": 0.183,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.56,
|
| 442 |
+
"grad_norm": 0.20401564240455627,
|
| 443 |
+
"learning_rate": 0.00019145299145299148,
|
| 444 |
+
"loss": 0.1829,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.59,
|
| 449 |
+
"grad_norm": 0.21579188108444214,
|
| 450 |
+
"learning_rate": 0.00018803418803418803,
|
| 451 |
+
"loss": 0.1812,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.61,
|
| 456 |
+
"grad_norm": 0.23108145594596863,
|
| 457 |
+
"learning_rate": 0.00018461538461538463,
|
| 458 |
+
"loss": 0.1781,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.64,
|
| 463 |
+
"grad_norm": 0.2311713844537735,
|
| 464 |
+
"learning_rate": 0.0001811965811965812,
|
| 465 |
+
"loss": 0.1755,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.66,
|
| 470 |
+
"grad_norm": 0.19794794917106628,
|
| 471 |
+
"learning_rate": 0.00017777777777777779,
|
| 472 |
+
"loss": 0.1768,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.69,
|
| 477 |
+
"grad_norm": 0.2516119182109833,
|
| 478 |
+
"learning_rate": 0.00017435897435897436,
|
| 479 |
+
"loss": 0.1737,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.72,
|
| 484 |
+
"grad_norm": 0.20975567400455475,
|
| 485 |
+
"learning_rate": 0.00017094017094017094,
|
| 486 |
+
"loss": 0.1712,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.74,
|
| 491 |
+
"grad_norm": 0.22168505191802979,
|
| 492 |
+
"learning_rate": 0.00016752136752136754,
|
| 493 |
+
"loss": 0.1693,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.77,
|
| 498 |
+
"grad_norm": 0.22844062745571136,
|
| 499 |
+
"learning_rate": 0.0001641025641025641,
|
| 500 |
+
"loss": 0.168,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.79,
|
| 505 |
+
"grad_norm": 0.22804197669029236,
|
| 506 |
+
"learning_rate": 0.0001606837606837607,
|
| 507 |
+
"loss": 0.1721,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.82,
|
| 512 |
+
"grad_norm": 0.22620578110218048,
|
| 513 |
+
"learning_rate": 0.00015726495726495727,
|
| 514 |
+
"loss": 0.1703,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.84,
|
| 519 |
+
"grad_norm": 0.21445313096046448,
|
| 520 |
+
"learning_rate": 0.00015384615384615385,
|
| 521 |
+
"loss": 0.1673,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.87,
|
| 526 |
+
"grad_norm": 0.207479327917099,
|
| 527 |
+
"learning_rate": 0.00015042735042735043,
|
| 528 |
+
"loss": 0.1648,
|
| 529 |
+
"step": 730
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.89,
|
| 533 |
+
"grad_norm": 0.22134087979793549,
|
| 534 |
+
"learning_rate": 0.00014700854700854703,
|
| 535 |
+
"loss": 0.1629,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.92,
|
| 540 |
+
"grad_norm": 0.20121484994888306,
|
| 541 |
+
"learning_rate": 0.0001435897435897436,
|
| 542 |
+
"loss": 0.1638,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.95,
|
| 547 |
+
"grad_norm": 0.2002618908882141,
|
| 548 |
+
"learning_rate": 0.00014017094017094016,
|
| 549 |
+
"loss": 0.1621,
|
| 550 |
+
"step": 760
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.97,
|
| 554 |
+
"grad_norm": 0.19750453531742096,
|
| 555 |
+
"learning_rate": 0.00013675213675213676,
|
| 556 |
+
"loss": 0.1667,
|
| 557 |
+
"step": 770
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.0,
|
| 561 |
+
"grad_norm": 0.22286508977413177,
|
| 562 |
+
"learning_rate": 0.00013333333333333334,
|
| 563 |
+
"loss": 0.1642,
|
| 564 |
+
"step": 780
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.02,
|
| 568 |
+
"grad_norm": 0.21668635308742523,
|
| 569 |
+
"learning_rate": 0.00012991452991452992,
|
| 570 |
+
"loss": 0.1482,
|
| 571 |
+
"step": 790
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.05,
|
| 575 |
+
"grad_norm": 0.233961820602417,
|
| 576 |
+
"learning_rate": 0.0001264957264957265,
|
| 577 |
+
"loss": 0.1453,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.07,
|
| 582 |
+
"grad_norm": 0.1865084022283554,
|
| 583 |
+
"learning_rate": 0.0001230769230769231,
|
| 584 |
+
"loss": 0.1455,
|
| 585 |
+
"step": 810
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.1,
|
| 589 |
+
"grad_norm": 0.1853141337633133,
|
| 590 |
+
"learning_rate": 0.00011965811965811966,
|
| 591 |
+
"loss": 0.1442,
|
| 592 |
+
"step": 820
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.12,
|
| 596 |
+
"grad_norm": 0.17371739447116852,
|
| 597 |
+
"learning_rate": 0.00011623931623931625,
|
| 598 |
+
"loss": 0.1382,
|
| 599 |
+
"step": 830
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.15,
|
| 603 |
+
"grad_norm": 0.19631154835224152,
|
| 604 |
+
"learning_rate": 0.00011282051282051283,
|
| 605 |
+
"loss": 0.1415,
|
| 606 |
+
"step": 840
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.18,
|
| 610 |
+
"grad_norm": 0.194850891828537,
|
| 611 |
+
"learning_rate": 0.00010940170940170942,
|
| 612 |
+
"loss": 0.141,
|
| 613 |
+
"step": 850
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.2,
|
| 617 |
+
"grad_norm": 0.18121449649333954,
|
| 618 |
+
"learning_rate": 0.000105982905982906,
|
| 619 |
+
"loss": 0.1388,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.23,
|
| 624 |
+
"grad_norm": 0.2176773101091385,
|
| 625 |
+
"learning_rate": 0.00010256410256410256,
|
| 626 |
+
"loss": 0.1399,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.25,
|
| 631 |
+
"grad_norm": 0.19013133645057678,
|
| 632 |
+
"learning_rate": 9.914529914529915e-05,
|
| 633 |
+
"loss": 0.137,
|
| 634 |
+
"step": 880
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.28,
|
| 638 |
+
"grad_norm": 0.22148679196834564,
|
| 639 |
+
"learning_rate": 9.572649572649574e-05,
|
| 640 |
+
"loss": 0.139,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.3,
|
| 645 |
+
"grad_norm": 0.20861493051052094,
|
| 646 |
+
"learning_rate": 9.230769230769232e-05,
|
| 647 |
+
"loss": 0.139,
|
| 648 |
+
"step": 900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.33,
|
| 652 |
+
"grad_norm": 0.17541790008544922,
|
| 653 |
+
"learning_rate": 8.888888888888889e-05,
|
| 654 |
+
"loss": 0.1362,
|
| 655 |
+
"step": 910
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.36,
|
| 659 |
+
"grad_norm": 0.1971459984779358,
|
| 660 |
+
"learning_rate": 8.547008547008547e-05,
|
| 661 |
+
"loss": 0.1346,
|
| 662 |
+
"step": 920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.38,
|
| 666 |
+
"grad_norm": 0.20883004367351532,
|
| 667 |
+
"learning_rate": 8.205128205128205e-05,
|
| 668 |
+
"loss": 0.1351,
|
| 669 |
+
"step": 930
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.41,
|
| 673 |
+
"grad_norm": 0.18058577179908752,
|
| 674 |
+
"learning_rate": 7.863247863247864e-05,
|
| 675 |
+
"loss": 0.1363,
|
| 676 |
+
"step": 940
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.43,
|
| 680 |
+
"grad_norm": 0.19193512201309204,
|
| 681 |
+
"learning_rate": 7.521367521367521e-05,
|
| 682 |
+
"loss": 0.1359,
|
| 683 |
+
"step": 950
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.46,
|
| 687 |
+
"grad_norm": 0.17777132987976074,
|
| 688 |
+
"learning_rate": 7.17948717948718e-05,
|
| 689 |
+
"loss": 0.1363,
|
| 690 |
+
"step": 960
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.48,
|
| 694 |
+
"grad_norm": 0.1730206310749054,
|
| 695 |
+
"learning_rate": 6.837606837606838e-05,
|
| 696 |
+
"loss": 0.1339,
|
| 697 |
+
"step": 970
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.51,
|
| 701 |
+
"grad_norm": 0.172698512673378,
|
| 702 |
+
"learning_rate": 6.495726495726496e-05,
|
| 703 |
+
"loss": 0.1317,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.53,
|
| 708 |
+
"grad_norm": 0.1746242642402649,
|
| 709 |
+
"learning_rate": 6.153846153846155e-05,
|
| 710 |
+
"loss": 0.132,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.56,
|
| 715 |
+
"grad_norm": 0.1631608009338379,
|
| 716 |
+
"learning_rate": 5.8119658119658126e-05,
|
| 717 |
+
"loss": 0.1292,
|
| 718 |
+
"step": 1000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.56,
|
| 722 |
+
"eval_cer": 0.9320702386692806,
|
| 723 |
+
"eval_loss": 0.11450555920600891,
|
| 724 |
+
"eval_runtime": 136.638,
|
| 725 |
+
"eval_samples_per_second": 14.637,
|
| 726 |
+
"eval_steps_per_second": 0.461,
|
| 727 |
+
"step": 1000
|
| 728 |
+
}
|
| 729 |
+
],
|
| 730 |
+
"logging_steps": 10,
|
| 731 |
+
"max_steps": 1170,
|
| 732 |
+
"num_input_tokens_seen": 0,
|
| 733 |
+
"num_train_epochs": 3,
|
| 734 |
+
"save_steps": 500,
|
| 735 |
+
"total_flos": 6.737241075941376e+16,
|
| 736 |
+
"train_batch_size": 8,
|
| 737 |
+
"trial_name": null,
|
| 738 |
+
"trial_params": null
|
| 739 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c287b31111cf124ac69c0e9b53bdaf288743eceab9254160487882b78a64250
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|