Commit
•
379dc1c
1
Parent(s):
8dbf3d5
Upload 13 files
Browse files- config.json +180 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- preprocessor_config.json +18 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +66 -0
- trainer_state.json +724 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": "5c48f939de25655eeca55d31e7893ada48d300d9",
|
| 3 |
+
"_name_or_path": "microsoft/trocr-base-stage1",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"VisionEncoderDecoderModel"
|
| 6 |
+
],
|
| 7 |
+
"decoder": {
|
| 8 |
+
"_name_or_path": "",
|
| 9 |
+
"activation_dropout": 0.0,
|
| 10 |
+
"activation_function": "relu",
|
| 11 |
+
"add_cross_attention": true,
|
| 12 |
+
"architectures": null,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bad_words_ids": null,
|
| 15 |
+
"begin_suppress_tokens": null,
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"chunk_size_feed_forward": 0,
|
| 18 |
+
"classifier_dropout": 0.0,
|
| 19 |
+
"cross_attention_hidden_size": 768,
|
| 20 |
+
"d_model": 1024,
|
| 21 |
+
"decoder_attention_heads": 16,
|
| 22 |
+
"decoder_ffn_dim": 4096,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 12,
|
| 25 |
+
"decoder_start_token_id": 2,
|
| 26 |
+
"diversity_penalty": 0.0,
|
| 27 |
+
"do_sample": false,
|
| 28 |
+
"dropout": 0.1,
|
| 29 |
+
"early_stopping": false,
|
| 30 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 31 |
+
"eos_token_id": 2,
|
| 32 |
+
"exponential_decay_length_penalty": null,
|
| 33 |
+
"finetuning_task": null,
|
| 34 |
+
"forced_bos_token_id": null,
|
| 35 |
+
"forced_eos_token_id": null,
|
| 36 |
+
"id2label": {
|
| 37 |
+
"0": "LABEL_0",
|
| 38 |
+
"1": "LABEL_1"
|
| 39 |
+
},
|
| 40 |
+
"init_std": 0.02,
|
| 41 |
+
"is_decoder": true,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layernorm_embedding": false,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 1024,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "trocr",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_beam_groups": 1,
|
| 55 |
+
"num_beams": 1,
|
| 56 |
+
"num_return_sequences": 1,
|
| 57 |
+
"output_attentions": false,
|
| 58 |
+
"output_hidden_states": false,
|
| 59 |
+
"output_scores": false,
|
| 60 |
+
"pad_token_id": 1,
|
| 61 |
+
"prefix": null,
|
| 62 |
+
"problem_type": null,
|
| 63 |
+
"pruned_heads": {},
|
| 64 |
+
"remove_invalid_values": false,
|
| 65 |
+
"repetition_penalty": 1.0,
|
| 66 |
+
"return_dict": true,
|
| 67 |
+
"return_dict_in_generate": false,
|
| 68 |
+
"scale_embedding": true,
|
| 69 |
+
"sep_token_id": null,
|
| 70 |
+
"suppress_tokens": null,
|
| 71 |
+
"task_specific_params": null,
|
| 72 |
+
"temperature": 1.0,
|
| 73 |
+
"tf_legacy_loss": false,
|
| 74 |
+
"tie_encoder_decoder": false,
|
| 75 |
+
"tie_word_embeddings": false,
|
| 76 |
+
"tokenizer_class": null,
|
| 77 |
+
"top_k": 50,
|
| 78 |
+
"top_p": 1.0,
|
| 79 |
+
"torch_dtype": null,
|
| 80 |
+
"torchscript": false,
|
| 81 |
+
"transformers_version": "4.24.0",
|
| 82 |
+
"typical_p": 1.0,
|
| 83 |
+
"use_bfloat16": false,
|
| 84 |
+
"use_cache": false,
|
| 85 |
+
"use_learned_position_embeddings": false,
|
| 86 |
+
"vocab_size": 50265
|
| 87 |
+
},
|
| 88 |
+
"decoder_start_token_id": 0,
|
| 89 |
+
"early_stopping": true,
|
| 90 |
+
"encoder": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_probs_dropout_prob": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"begin_suppress_tokens": null,
|
| 97 |
+
"bos_token_id": null,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"cross_attention_hidden_size": null,
|
| 100 |
+
"decoder_start_token_id": null,
|
| 101 |
+
"diversity_penalty": 0.0,
|
| 102 |
+
"do_sample": false,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"encoder_stride": 16,
|
| 106 |
+
"eos_token_id": null,
|
| 107 |
+
"exponential_decay_length_penalty": null,
|
| 108 |
+
"finetuning_task": null,
|
| 109 |
+
"forced_bos_token_id": null,
|
| 110 |
+
"forced_eos_token_id": null,
|
| 111 |
+
"hidden_act": "gelu",
|
| 112 |
+
"hidden_dropout_prob": 0.0,
|
| 113 |
+
"hidden_size": 768,
|
| 114 |
+
"id2label": {
|
| 115 |
+
"0": "LABEL_0",
|
| 116 |
+
"1": "LABEL_1"
|
| 117 |
+
},
|
| 118 |
+
"image_size": 384,
|
| 119 |
+
"initializer_range": 0.02,
|
| 120 |
+
"intermediate_size": 3072,
|
| 121 |
+
"is_decoder": false,
|
| 122 |
+
"is_encoder_decoder": false,
|
| 123 |
+
"label2id": {
|
| 124 |
+
"LABEL_0": 0,
|
| 125 |
+
"LABEL_1": 1
|
| 126 |
+
},
|
| 127 |
+
"layer_norm_eps": 1e-12,
|
| 128 |
+
"length_penalty": 1.0,
|
| 129 |
+
"max_length": 20,
|
| 130 |
+
"min_length": 0,
|
| 131 |
+
"model_type": "vit",
|
| 132 |
+
"no_repeat_ngram_size": 0,
|
| 133 |
+
"num_attention_heads": 12,
|
| 134 |
+
"num_beam_groups": 1,
|
| 135 |
+
"num_beams": 1,
|
| 136 |
+
"num_channels": 3,
|
| 137 |
+
"num_hidden_layers": 12,
|
| 138 |
+
"num_return_sequences": 1,
|
| 139 |
+
"output_attentions": false,
|
| 140 |
+
"output_hidden_states": false,
|
| 141 |
+
"output_scores": false,
|
| 142 |
+
"pad_token_id": null,
|
| 143 |
+
"patch_size": 16,
|
| 144 |
+
"prefix": null,
|
| 145 |
+
"problem_type": null,
|
| 146 |
+
"pruned_heads": {},
|
| 147 |
+
"qkv_bias": false,
|
| 148 |
+
"remove_invalid_values": false,
|
| 149 |
+
"repetition_penalty": 1.0,
|
| 150 |
+
"return_dict": true,
|
| 151 |
+
"return_dict_in_generate": false,
|
| 152 |
+
"sep_token_id": null,
|
| 153 |
+
"suppress_tokens": null,
|
| 154 |
+
"task_specific_params": null,
|
| 155 |
+
"temperature": 1.0,
|
| 156 |
+
"tf_legacy_loss": false,
|
| 157 |
+
"tie_encoder_decoder": false,
|
| 158 |
+
"tie_word_embeddings": true,
|
| 159 |
+
"tokenizer_class": null,
|
| 160 |
+
"top_k": 50,
|
| 161 |
+
"top_p": 1.0,
|
| 162 |
+
"torch_dtype": null,
|
| 163 |
+
"torchscript": false,
|
| 164 |
+
"transformers_version": "4.24.0",
|
| 165 |
+
"typical_p": 1.0,
|
| 166 |
+
"use_bfloat16": false
|
| 167 |
+
},
|
| 168 |
+
"eos_token_id": 2,
|
| 169 |
+
"is_encoder_decoder": true,
|
| 170 |
+
"length_penalty": 2.0,
|
| 171 |
+
"max_length": 36,
|
| 172 |
+
"model_type": "vision-encoder-decoder",
|
| 173 |
+
"no_repeat_ngram_size": 3,
|
| 174 |
+
"num_beams": 4,
|
| 175 |
+
"pad_token_id": 1,
|
| 176 |
+
"tie_word_embeddings": false,
|
| 177 |
+
"torch_dtype": "float32",
|
| 178 |
+
"transformers_version": null,
|
| 179 |
+
"vocab_size": 50265
|
| 180 |
+
}
|
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:d4c97f69ee41290bcc71e70f72fda1d95cdedccc1bf46b05a540444718ff9355
|
| 3 |
+
size 3074473541
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_std": [
|
| 11 |
+
0.5,
|
| 12 |
+
0.5,
|
| 13 |
+
0.5
|
| 14 |
+
],
|
| 15 |
+
"processor_class": "TrOCRProcessor",
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"size": 384
|
| 18 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48c30f4b4660ec1b6bdbdb2cf35e362d3102e597cc9993f2b16fc991a2a5ffff
|
| 3 |
+
size 1539625673
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4aee5adbfab97a9adfd8580e4c853534a1a67e63c8d9454230544a7727c74e
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed373d8b695820c18a06c1f883fea8fc9d8e11cafc54bdfc114c75360d01e57d
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"cls_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"__type": "AddedToken",
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"errors": "replace",
|
| 28 |
+
"mask_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<mask>",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"model_max_length": 512,
|
| 37 |
+
"name_or_path": "microsoft/trocr-base-stage1",
|
| 38 |
+
"pad_token": {
|
| 39 |
+
"__type": "AddedToken",
|
| 40 |
+
"content": "<pad>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"processor_class": "TrOCRProcessor",
|
| 47 |
+
"sep_token": {
|
| 48 |
+
"__type": "AddedToken",
|
| 49 |
+
"content": "</s>",
|
| 50 |
+
"lstrip": false,
|
| 51 |
+
"normalized": true,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"single_word": false
|
| 54 |
+
},
|
| 55 |
+
"special_tokens_map_file": null,
|
| 56 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 57 |
+
"trim_offsets": true,
|
| 58 |
+
"unk_token": {
|
| 59 |
+
"__type": "AddedToken",
|
| 60 |
+
"content": "<unk>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
}
|
| 66 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,724 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.004195804195804196,
|
| 3 |
+
"best_model_checkpoint": "custom_model_stage1_base_concat_synth/checkpoint-900",
|
| 4 |
+
"epoch": 2.9605263157894735,
|
| 5 |
+
"global_step": 900,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.9945175438596495e-05,
|
| 13 |
+
"loss": 9.5118,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 4.9451754385964915e-05,
|
| 19 |
+
"loss": 3.2727,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 4.890350877192983e-05,
|
| 25 |
+
"loss": 2.6133,
|
| 26 |
+
"step": 20
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 4.8355263157894734e-05,
|
| 31 |
+
"loss": 3.1323,
|
| 32 |
+
"step": 30
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.13,
|
| 36 |
+
"learning_rate": 4.780701754385965e-05,
|
| 37 |
+
"loss": 2.6306,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16,
|
| 42 |
+
"learning_rate": 4.7258771929824566e-05,
|
| 43 |
+
"loss": 2.9819,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"eval_cer": 0.3053536021150033,
|
| 49 |
+
"eval_loss": 1.6067169904708862,
|
| 50 |
+
"eval_runtime": 22.608,
|
| 51 |
+
"eval_samples_per_second": 6.281,
|
| 52 |
+
"eval_steps_per_second": 0.796,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.2,
|
| 57 |
+
"learning_rate": 4.671052631578948e-05,
|
| 58 |
+
"loss": 2.3285,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.23,
|
| 63 |
+
"learning_rate": 4.616228070175439e-05,
|
| 64 |
+
"loss": 1.9334,
|
| 65 |
+
"step": 70
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.26,
|
| 69 |
+
"learning_rate": 4.56140350877193e-05,
|
| 70 |
+
"loss": 1.9042,
|
| 71 |
+
"step": 80
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.3,
|
| 75 |
+
"learning_rate": 4.506578947368421e-05,
|
| 76 |
+
"loss": 2.0802,
|
| 77 |
+
"step": 90
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.33,
|
| 81 |
+
"learning_rate": 4.451754385964912e-05,
|
| 82 |
+
"loss": 2.144,
|
| 83 |
+
"step": 100
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.33,
|
| 87 |
+
"eval_cer": 0.08821502412129566,
|
| 88 |
+
"eval_loss": 0.9317633509635925,
|
| 89 |
+
"eval_runtime": 27.231,
|
| 90 |
+
"eval_samples_per_second": 5.215,
|
| 91 |
+
"eval_steps_per_second": 0.661,
|
| 92 |
+
"step": 100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.36,
|
| 96 |
+
"learning_rate": 4.3969298245614036e-05,
|
| 97 |
+
"loss": 1.7753,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.39,
|
| 102 |
+
"learning_rate": 4.342105263157895e-05,
|
| 103 |
+
"loss": 1.9885,
|
| 104 |
+
"step": 120
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.43,
|
| 108 |
+
"learning_rate": 4.287280701754386e-05,
|
| 109 |
+
"loss": 1.8163,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.46,
|
| 114 |
+
"learning_rate": 4.2324561403508774e-05,
|
| 115 |
+
"loss": 1.8354,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.49,
|
| 120 |
+
"learning_rate": 4.177631578947369e-05,
|
| 121 |
+
"loss": 2.1775,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.49,
|
| 126 |
+
"eval_cer": 0.05823293172690763,
|
| 127 |
+
"eval_loss": 0.8989996314048767,
|
| 128 |
+
"eval_runtime": 24.7772,
|
| 129 |
+
"eval_samples_per_second": 5.731,
|
| 130 |
+
"eval_steps_per_second": 0.726,
|
| 131 |
+
"step": 150
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.53,
|
| 135 |
+
"learning_rate": 4.12280701754386e-05,
|
| 136 |
+
"loss": 2.0764,
|
| 137 |
+
"step": 160
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.56,
|
| 141 |
+
"learning_rate": 4.067982456140351e-05,
|
| 142 |
+
"loss": 2.1435,
|
| 143 |
+
"step": 170
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.59,
|
| 147 |
+
"learning_rate": 4.0131578947368425e-05,
|
| 148 |
+
"loss": 1.9279,
|
| 149 |
+
"step": 180
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.62,
|
| 153 |
+
"learning_rate": 3.958333333333333e-05,
|
| 154 |
+
"loss": 1.6143,
|
| 155 |
+
"step": 190
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.66,
|
| 159 |
+
"learning_rate": 3.9035087719298244e-05,
|
| 160 |
+
"loss": 1.6676,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.66,
|
| 165 |
+
"eval_cer": 0.05952380952380952,
|
| 166 |
+
"eval_loss": 0.6604741215705872,
|
| 167 |
+
"eval_runtime": 25.9554,
|
| 168 |
+
"eval_samples_per_second": 5.471,
|
| 169 |
+
"eval_steps_per_second": 0.693,
|
| 170 |
+
"step": 200
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.69,
|
| 174 |
+
"learning_rate": 3.848684210526316e-05,
|
| 175 |
+
"loss": 1.5091,
|
| 176 |
+
"step": 210
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.72,
|
| 180 |
+
"learning_rate": 3.7938596491228076e-05,
|
| 181 |
+
"loss": 1.5469,
|
| 182 |
+
"step": 220
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.76,
|
| 186 |
+
"learning_rate": 3.739035087719299e-05,
|
| 187 |
+
"loss": 1.7522,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.79,
|
| 192 |
+
"learning_rate": 3.6842105263157895e-05,
|
| 193 |
+
"loss": 1.6574,
|
| 194 |
+
"step": 240
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.82,
|
| 198 |
+
"learning_rate": 3.629385964912281e-05,
|
| 199 |
+
"loss": 1.2664,
|
| 200 |
+
"step": 250
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.82,
|
| 204 |
+
"eval_cer": 0.019313304721030045,
|
| 205 |
+
"eval_loss": 0.6368018388748169,
|
| 206 |
+
"eval_runtime": 26.7506,
|
| 207 |
+
"eval_samples_per_second": 5.308,
|
| 208 |
+
"eval_steps_per_second": 0.673,
|
| 209 |
+
"step": 250
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.86,
|
| 213 |
+
"learning_rate": 3.574561403508772e-05,
|
| 214 |
+
"loss": 1.481,
|
| 215 |
+
"step": 260
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.89,
|
| 219 |
+
"learning_rate": 3.519736842105263e-05,
|
| 220 |
+
"loss": 1.404,
|
| 221 |
+
"step": 270
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.92,
|
| 225 |
+
"learning_rate": 3.4649122807017546e-05,
|
| 226 |
+
"loss": 1.2388,
|
| 227 |
+
"step": 280
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.95,
|
| 231 |
+
"learning_rate": 3.410087719298246e-05,
|
| 232 |
+
"loss": 1.6538,
|
| 233 |
+
"step": 290
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.99,
|
| 237 |
+
"learning_rate": 3.355263157894737e-05,
|
| 238 |
+
"loss": 1.2714,
|
| 239 |
+
"step": 300
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.99,
|
| 243 |
+
"eval_cer": 0.04748982360922659,
|
| 244 |
+
"eval_loss": 0.6383101344108582,
|
| 245 |
+
"eval_runtime": 27.9443,
|
| 246 |
+
"eval_samples_per_second": 5.082,
|
| 247 |
+
"eval_steps_per_second": 0.644,
|
| 248 |
+
"step": 300
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.02,
|
| 252 |
+
"learning_rate": 3.3004385964912284e-05,
|
| 253 |
+
"loss": 1.2309,
|
| 254 |
+
"step": 310
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.05,
|
| 258 |
+
"learning_rate": 3.24561403508772e-05,
|
| 259 |
+
"loss": 1.2347,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.09,
|
| 264 |
+
"learning_rate": 3.190789473684211e-05,
|
| 265 |
+
"loss": 1.1184,
|
| 266 |
+
"step": 330
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.12,
|
| 270 |
+
"learning_rate": 3.1359649122807015e-05,
|
| 271 |
+
"loss": 1.2385,
|
| 272 |
+
"step": 340
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.15,
|
| 276 |
+
"learning_rate": 3.081140350877193e-05,
|
| 277 |
+
"loss": 0.9966,
|
| 278 |
+
"step": 350
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.15,
|
| 282 |
+
"eval_cer": 0.025748086290883786,
|
| 283 |
+
"eval_loss": 0.5416922569274902,
|
| 284 |
+
"eval_runtime": 27.2235,
|
| 285 |
+
"eval_samples_per_second": 5.216,
|
| 286 |
+
"eval_steps_per_second": 0.661,
|
| 287 |
+
"step": 350
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.18,
|
| 291 |
+
"learning_rate": 3.0263157894736844e-05,
|
| 292 |
+
"loss": 0.9694,
|
| 293 |
+
"step": 360
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.22,
|
| 297 |
+
"learning_rate": 2.9714912280701757e-05,
|
| 298 |
+
"loss": 1.0465,
|
| 299 |
+
"step": 370
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.25,
|
| 303 |
+
"learning_rate": 2.916666666666667e-05,
|
| 304 |
+
"loss": 0.9811,
|
| 305 |
+
"step": 380
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.28,
|
| 309 |
+
"learning_rate": 2.861842105263158e-05,
|
| 310 |
+
"loss": 1.0744,
|
| 311 |
+
"step": 390
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.32,
|
| 315 |
+
"learning_rate": 2.8070175438596492e-05,
|
| 316 |
+
"loss": 1.0068,
|
| 317 |
+
"step": 400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.32,
|
| 321 |
+
"eval_cer": 0.02813127930341594,
|
| 322 |
+
"eval_loss": 0.4663618803024292,
|
| 323 |
+
"eval_runtime": 28.8768,
|
| 324 |
+
"eval_samples_per_second": 4.917,
|
| 325 |
+
"eval_steps_per_second": 0.623,
|
| 326 |
+
"step": 400
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.35,
|
| 330 |
+
"learning_rate": 2.7521929824561405e-05,
|
| 331 |
+
"loss": 1.1744,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.38,
|
| 336 |
+
"learning_rate": 2.6973684210526317e-05,
|
| 337 |
+
"loss": 1.0358,
|
| 338 |
+
"step": 420
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.41,
|
| 342 |
+
"learning_rate": 2.642543859649123e-05,
|
| 343 |
+
"loss": 0.8434,
|
| 344 |
+
"step": 430
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.45,
|
| 348 |
+
"learning_rate": 2.5877192982456143e-05,
|
| 349 |
+
"loss": 0.901,
|
| 350 |
+
"step": 440
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.48,
|
| 354 |
+
"learning_rate": 2.5328947368421052e-05,
|
| 355 |
+
"loss": 1.1405,
|
| 356 |
+
"step": 450
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.48,
|
| 360 |
+
"eval_cer": 0.020134228187919462,
|
| 361 |
+
"eval_loss": 0.5748289823532104,
|
| 362 |
+
"eval_runtime": 28.573,
|
| 363 |
+
"eval_samples_per_second": 4.97,
|
| 364 |
+
"eval_steps_per_second": 0.63,
|
| 365 |
+
"step": 450
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.51,
|
| 369 |
+
"learning_rate": 2.4780701754385965e-05,
|
| 370 |
+
"loss": 0.9414,
|
| 371 |
+
"step": 460
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.55,
|
| 375 |
+
"learning_rate": 2.4232456140350878e-05,
|
| 376 |
+
"loss": 1.1748,
|
| 377 |
+
"step": 470
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.58,
|
| 381 |
+
"learning_rate": 2.368421052631579e-05,
|
| 382 |
+
"loss": 1.0134,
|
| 383 |
+
"step": 480
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.61,
|
| 387 |
+
"learning_rate": 2.3135964912280703e-05,
|
| 388 |
+
"loss": 1.0102,
|
| 389 |
+
"step": 490
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.64,
|
| 393 |
+
"learning_rate": 2.2587719298245616e-05,
|
| 394 |
+
"loss": 0.9627,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.64,
|
| 399 |
+
"eval_cer": 0.02203856749311295,
|
| 400 |
+
"eval_loss": 0.4435074031352997,
|
| 401 |
+
"eval_runtime": 27.4558,
|
| 402 |
+
"eval_samples_per_second": 5.172,
|
| 403 |
+
"eval_steps_per_second": 0.656,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.68,
|
| 408 |
+
"learning_rate": 2.2039473684210525e-05,
|
| 409 |
+
"loss": 1.0858,
|
| 410 |
+
"step": 510
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.71,
|
| 414 |
+
"learning_rate": 2.149122807017544e-05,
|
| 415 |
+
"loss": 0.8016,
|
| 416 |
+
"step": 520
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.74,
|
| 420 |
+
"learning_rate": 2.0942982456140354e-05,
|
| 421 |
+
"loss": 0.813,
|
| 422 |
+
"step": 530
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.78,
|
| 426 |
+
"learning_rate": 2.0394736842105264e-05,
|
| 427 |
+
"loss": 0.792,
|
| 428 |
+
"step": 540
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.81,
|
| 432 |
+
"learning_rate": 1.9846491228070176e-05,
|
| 433 |
+
"loss": 0.8551,
|
| 434 |
+
"step": 550
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.81,
|
| 438 |
+
"eval_cer": 0.0291583830351226,
|
| 439 |
+
"eval_loss": 0.5917633771896362,
|
| 440 |
+
"eval_runtime": 30.3337,
|
| 441 |
+
"eval_samples_per_second": 4.681,
|
| 442 |
+
"eval_steps_per_second": 0.593,
|
| 443 |
+
"step": 550
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.84,
|
| 447 |
+
"learning_rate": 1.929824561403509e-05,
|
| 448 |
+
"loss": 0.8459,
|
| 449 |
+
"step": 560
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.88,
|
| 453 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 454 |
+
"loss": 0.8129,
|
| 455 |
+
"step": 570
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.91,
|
| 459 |
+
"learning_rate": 1.8201754385964914e-05,
|
| 460 |
+
"loss": 0.8238,
|
| 461 |
+
"step": 580
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.94,
|
| 465 |
+
"learning_rate": 1.7653508771929824e-05,
|
| 466 |
+
"loss": 0.9552,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.97,
|
| 471 |
+
"learning_rate": 1.7105263157894737e-05,
|
| 472 |
+
"loss": 0.6585,
|
| 473 |
+
"step": 600
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.97,
|
| 477 |
+
"eval_cer": 0.01694915254237288,
|
| 478 |
+
"eval_loss": 0.4142173230648041,
|
| 479 |
+
"eval_runtime": 28.0204,
|
| 480 |
+
"eval_samples_per_second": 5.068,
|
| 481 |
+
"eval_steps_per_second": 0.642,
|
| 482 |
+
"step": 600
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.01,
|
| 486 |
+
"learning_rate": 1.655701754385965e-05,
|
| 487 |
+
"loss": 0.6229,
|
| 488 |
+
"step": 610
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.04,
|
| 492 |
+
"learning_rate": 1.6008771929824562e-05,
|
| 493 |
+
"loss": 0.8082,
|
| 494 |
+
"step": 620
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.07,
|
| 498 |
+
"learning_rate": 1.5460526315789475e-05,
|
| 499 |
+
"loss": 0.751,
|
| 500 |
+
"step": 630
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.11,
|
| 504 |
+
"learning_rate": 1.4912280701754386e-05,
|
| 505 |
+
"loss": 0.6503,
|
| 506 |
+
"step": 640
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.14,
|
| 510 |
+
"learning_rate": 1.4364035087719299e-05,
|
| 511 |
+
"loss": 0.6518,
|
| 512 |
+
"step": 650
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.14,
|
| 516 |
+
"eval_cer": 0.008419689119170985,
|
| 517 |
+
"eval_loss": 0.3558412492275238,
|
| 518 |
+
"eval_runtime": 28.5056,
|
| 519 |
+
"eval_samples_per_second": 4.981,
|
| 520 |
+
"eval_steps_per_second": 0.631,
|
| 521 |
+
"step": 650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.17,
|
| 525 |
+
"learning_rate": 1.3815789473684213e-05,
|
| 526 |
+
"loss": 0.6165,
|
| 527 |
+
"step": 660
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.2,
|
| 531 |
+
"learning_rate": 1.3267543859649122e-05,
|
| 532 |
+
"loss": 0.7267,
|
| 533 |
+
"step": 670
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.24,
|
| 537 |
+
"learning_rate": 1.2719298245614037e-05,
|
| 538 |
+
"loss": 0.8219,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.27,
|
| 543 |
+
"learning_rate": 1.2171052631578948e-05,
|
| 544 |
+
"loss": 0.7055,
|
| 545 |
+
"step": 690
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.3,
|
| 549 |
+
"learning_rate": 1.162280701754386e-05,
|
| 550 |
+
"loss": 0.5255,
|
| 551 |
+
"step": 700
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.3,
|
| 555 |
+
"eval_cer": 0.0047879616963064295,
|
| 556 |
+
"eval_loss": 0.3521033823490143,
|
| 557 |
+
"eval_runtime": 27.0564,
|
| 558 |
+
"eval_samples_per_second": 5.248,
|
| 559 |
+
"eval_steps_per_second": 0.665,
|
| 560 |
+
"step": 700
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.34,
|
| 564 |
+
"learning_rate": 1.1074561403508772e-05,
|
| 565 |
+
"loss": 0.7562,
|
| 566 |
+
"step": 710
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.37,
|
| 570 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 571 |
+
"loss": 0.6348,
|
| 572 |
+
"step": 720
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.4,
|
| 576 |
+
"learning_rate": 9.978070175438597e-06,
|
| 577 |
+
"loss": 0.7211,
|
| 578 |
+
"step": 730
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.43,
|
| 582 |
+
"learning_rate": 9.42982456140351e-06,
|
| 583 |
+
"loss": 0.488,
|
| 584 |
+
"step": 740
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.47,
|
| 588 |
+
"learning_rate": 8.881578947368421e-06,
|
| 589 |
+
"loss": 0.469,
|
| 590 |
+
"step": 750
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.47,
|
| 594 |
+
"eval_cer": 0.004864489228630994,
|
| 595 |
+
"eval_loss": 0.32997873425483704,
|
| 596 |
+
"eval_runtime": 26.4415,
|
| 597 |
+
"eval_samples_per_second": 5.37,
|
| 598 |
+
"eval_steps_per_second": 0.681,
|
| 599 |
+
"step": 750
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.5,
|
| 603 |
+
"learning_rate": 8.333333333333334e-06,
|
| 604 |
+
"loss": 0.4705,
|
| 605 |
+
"step": 760
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.53,
|
| 609 |
+
"learning_rate": 7.785087719298246e-06,
|
| 610 |
+
"loss": 0.5315,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.57,
|
| 615 |
+
"learning_rate": 7.236842105263158e-06,
|
| 616 |
+
"loss": 0.4967,
|
| 617 |
+
"step": 780
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 2.6,
|
| 621 |
+
"learning_rate": 6.68859649122807e-06,
|
| 622 |
+
"loss": 0.6951,
|
| 623 |
+
"step": 790
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 2.63,
|
| 627 |
+
"learning_rate": 6.140350877192982e-06,
|
| 628 |
+
"loss": 0.434,
|
| 629 |
+
"step": 800
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.63,
|
| 633 |
+
"eval_cer": 0.005936675461741424,
|
| 634 |
+
"eval_loss": 0.3225802481174469,
|
| 635 |
+
"eval_runtime": 27.8587,
|
| 636 |
+
"eval_samples_per_second": 5.097,
|
| 637 |
+
"eval_steps_per_second": 0.646,
|
| 638 |
+
"step": 800
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.66,
|
| 642 |
+
"learning_rate": 5.592105263157895e-06,
|
| 643 |
+
"loss": 0.4898,
|
| 644 |
+
"step": 810
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.7,
|
| 648 |
+
"learning_rate": 5.043859649122807e-06,
|
| 649 |
+
"loss": 0.8127,
|
| 650 |
+
"step": 820
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.73,
|
| 654 |
+
"learning_rate": 4.4956140350877196e-06,
|
| 655 |
+
"loss": 0.5916,
|
| 656 |
+
"step": 830
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.76,
|
| 660 |
+
"learning_rate": 3.9473684210526315e-06,
|
| 661 |
+
"loss": 0.3977,
|
| 662 |
+
"step": 840
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.8,
|
| 666 |
+
"learning_rate": 3.399122807017544e-06,
|
| 667 |
+
"loss": 0.5842,
|
| 668 |
+
"step": 850
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.8,
|
| 672 |
+
"eval_cer": 0.006997900629811057,
|
| 673 |
+
"eval_loss": 0.3334667980670929,
|
| 674 |
+
"eval_runtime": 26.2691,
|
| 675 |
+
"eval_samples_per_second": 5.406,
|
| 676 |
+
"eval_steps_per_second": 0.685,
|
| 677 |
+
"step": 850
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.83,
|
| 681 |
+
"learning_rate": 2.850877192982456e-06,
|
| 682 |
+
"loss": 0.4293,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.86,
|
| 687 |
+
"learning_rate": 2.3026315789473684e-06,
|
| 688 |
+
"loss": 0.4953,
|
| 689 |
+
"step": 870
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.89,
|
| 693 |
+
"learning_rate": 1.7543859649122807e-06,
|
| 694 |
+
"loss": 0.6281,
|
| 695 |
+
"step": 880
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 2.93,
|
| 699 |
+
"learning_rate": 1.206140350877193e-06,
|
| 700 |
+
"loss": 0.5186,
|
| 701 |
+
"step": 890
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 2.96,
|
| 705 |
+
"learning_rate": 6.578947368421053e-07,
|
| 706 |
+
"loss": 0.5946,
|
| 707 |
+
"step": 900
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.96,
|
| 711 |
+
"eval_cer": 0.004195804195804196,
|
| 712 |
+
"eval_loss": 0.3096241056919098,
|
| 713 |
+
"eval_runtime": 27.0145,
|
| 714 |
+
"eval_samples_per_second": 5.256,
|
| 715 |
+
"eval_steps_per_second": 0.666,
|
| 716 |
+
"step": 900
|
| 717 |
+
}
|
| 718 |
+
],
|
| 719 |
+
"max_steps": 912,
|
| 720 |
+
"num_train_epochs": 3,
|
| 721 |
+
"total_flos": 6.369477453856899e+18,
|
| 722 |
+
"trial_name": null,
|
| 723 |
+
"trial_params": null
|
| 724 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44034dde030d525d7efd97f406c7a9cee13eb34247467fc93ccac0a3f2acca6f
|
| 3 |
+
size 3515
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|