gagan3012 commited on
Commit
762c469
1 Parent(s): 4b78321

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/trocr-small-stage1",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "relu",
10
+ "add_cross_attention": true,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 0,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": 0.0,
17
+ "cross_attention_hidden_size": 384,
18
+ "d_model": 256,
19
+ "decoder_attention_heads": 8,
20
+ "decoder_ffn_dim": 1024,
21
+ "decoder_layerdrop": 0.0,
22
+ "decoder_layers": 6,
23
+ "decoder_start_token_id": 2,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "dropout": 0.1,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": 2,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "init_std": 0.02,
38
+ "is_decoder": true,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layernorm_embedding": true,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 512,
48
+ "min_length": 0,
49
+ "model_type": "trocr",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 1,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "scale_embedding": true,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": false,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.17.0",
77
+ "typical_p": 1.0,
78
+ "use_bfloat16": false,
79
+ "use_cache": false,
80
+ "use_learned_position_embeddings": true,
81
+ "vocab_size": 64044
82
+ },
83
+ "decoder_start_token_id": 0,
84
+ "early_stopping": true,
85
+ "encoder": {
86
+ "_name_or_path": "",
87
+ "add_cross_attention": false,
88
+ "architectures": null,
89
+ "attention_probs_dropout_prob": 0.0,
90
+ "bad_words_ids": null,
91
+ "bos_token_id": null,
92
+ "chunk_size_feed_forward": 0,
93
+ "cross_attention_hidden_size": null,
94
+ "decoder_start_token_id": null,
95
+ "diversity_penalty": 0.0,
96
+ "do_sample": false,
97
+ "early_stopping": false,
98
+ "encoder_no_repeat_ngram_size": 0,
99
+ "encoder_stride": 16,
100
+ "eos_token_id": null,
101
+ "finetuning_task": null,
102
+ "forced_bos_token_id": null,
103
+ "forced_eos_token_id": null,
104
+ "hidden_act": "gelu",
105
+ "hidden_dropout_prob": 0.0,
106
+ "hidden_size": 384,
107
+ "id2label": {
108
+ "0": "LABEL_0",
109
+ "1": "LABEL_1"
110
+ },
111
+ "image_size": 384,
112
+ "initializer_range": 0.02,
113
+ "intermediate_size": 1536,
114
+ "is_decoder": false,
115
+ "is_encoder_decoder": false,
116
+ "label2id": {
117
+ "LABEL_0": 0,
118
+ "LABEL_1": 1
119
+ },
120
+ "layer_norm_eps": 1e-12,
121
+ "length_penalty": 1.0,
122
+ "max_length": 20,
123
+ "min_length": 0,
124
+ "model_type": "deit",
125
+ "no_repeat_ngram_size": 0,
126
+ "num_attention_heads": 6,
127
+ "num_beam_groups": 1,
128
+ "num_beams": 1,
129
+ "num_channels": 3,
130
+ "num_hidden_layers": 12,
131
+ "num_return_sequences": 1,
132
+ "output_attentions": false,
133
+ "output_hidden_states": false,
134
+ "output_scores": false,
135
+ "pad_token_id": null,
136
+ "patch_size": 16,
137
+ "prefix": null,
138
+ "problem_type": null,
139
+ "pruned_heads": {},
140
+ "qkv_bias": true,
141
+ "remove_invalid_values": false,
142
+ "repetition_penalty": 1.0,
143
+ "return_dict": true,
144
+ "return_dict_in_generate": false,
145
+ "sep_token_id": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tie_encoder_decoder": false,
149
+ "tie_word_embeddings": true,
150
+ "tokenizer_class": null,
151
+ "top_k": 50,
152
+ "top_p": 1.0,
153
+ "torch_dtype": null,
154
+ "torchscript": false,
155
+ "transformers_version": "4.17.0",
156
+ "typical_p": 1.0,
157
+ "use_bfloat16": false
158
+ },
159
+ "eos_token_id": 2,
160
+ "is_encoder_decoder": true,
161
+ "length_penalty": 2.0,
162
+ "max_length": 64,
163
+ "model_type": "vision-encoder-decoder",
164
+ "no_repeat_ngram_size": 3,
165
+ "num_beams": 4,
166
+ "pad_token_id": 1,
167
+ "tie_word_embeddings": false,
168
+ "torch_dtype": "float32",
169
+ "transformers_version": null,
170
+ "vocab_size": 64044
171
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/trocr-small-stage1",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "relu",
10
+ "add_cross_attention": true,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 0,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": 0.0,
17
+ "cross_attention_hidden_size": 384,
18
+ "d_model": 256,
19
+ "decoder_attention_heads": 8,
20
+ "decoder_ffn_dim": 1024,
21
+ "decoder_layerdrop": 0.0,
22
+ "decoder_layers": 6,
23
+ "decoder_start_token_id": 2,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "dropout": 0.1,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "eos_token_id": 2,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "init_std": 0.02,
38
+ "is_decoder": true,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layernorm_embedding": true,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 512,
48
+ "min_length": 0,
49
+ "model_type": "trocr",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 1,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "scale_embedding": true,
66
+ "sep_token_id": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tie_encoder_decoder": false,
70
+ "tie_word_embeddings": false,
71
+ "tokenizer_class": null,
72
+ "top_k": 50,
73
+ "top_p": 1.0,
74
+ "torch_dtype": null,
75
+ "torchscript": false,
76
+ "transformers_version": "4.17.0",
77
+ "typical_p": 1.0,
78
+ "use_bfloat16": false,
79
+ "use_cache": false,
80
+ "use_learned_position_embeddings": true,
81
+ "vocab_size": 64044
82
+ },
83
+ "decoder_start_token_id": 0,
84
+ "early_stopping": true,
85
+ "encoder": {
86
+ "_name_or_path": "",
87
+ "add_cross_attention": false,
88
+ "architectures": null,
89
+ "attention_probs_dropout_prob": 0.0,
90
+ "bad_words_ids": null,
91
+ "bos_token_id": null,
92
+ "chunk_size_feed_forward": 0,
93
+ "cross_attention_hidden_size": null,
94
+ "decoder_start_token_id": null,
95
+ "diversity_penalty": 0.0,
96
+ "do_sample": false,
97
+ "early_stopping": false,
98
+ "encoder_no_repeat_ngram_size": 0,
99
+ "encoder_stride": 16,
100
+ "eos_token_id": null,
101
+ "finetuning_task": null,
102
+ "forced_bos_token_id": null,
103
+ "forced_eos_token_id": null,
104
+ "hidden_act": "gelu",
105
+ "hidden_dropout_prob": 0.0,
106
+ "hidden_size": 384,
107
+ "id2label": {
108
+ "0": "LABEL_0",
109
+ "1": "LABEL_1"
110
+ },
111
+ "image_size": 384,
112
+ "initializer_range": 0.02,
113
+ "intermediate_size": 1536,
114
+ "is_decoder": false,
115
+ "is_encoder_decoder": false,
116
+ "label2id": {
117
+ "LABEL_0": 0,
118
+ "LABEL_1": 1
119
+ },
120
+ "layer_norm_eps": 1e-12,
121
+ "length_penalty": 1.0,
122
+ "max_length": 20,
123
+ "min_length": 0,
124
+ "model_type": "deit",
125
+ "no_repeat_ngram_size": 0,
126
+ "num_attention_heads": 6,
127
+ "num_beam_groups": 1,
128
+ "num_beams": 1,
129
+ "num_channels": 3,
130
+ "num_hidden_layers": 12,
131
+ "num_return_sequences": 1,
132
+ "output_attentions": false,
133
+ "output_hidden_states": false,
134
+ "output_scores": false,
135
+ "pad_token_id": null,
136
+ "patch_size": 16,
137
+ "prefix": null,
138
+ "problem_type": null,
139
+ "pruned_heads": {},
140
+ "qkv_bias": true,
141
+ "remove_invalid_values": false,
142
+ "repetition_penalty": 1.0,
143
+ "return_dict": true,
144
+ "return_dict_in_generate": false,
145
+ "sep_token_id": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tie_encoder_decoder": false,
149
+ "tie_word_embeddings": true,
150
+ "tokenizer_class": null,
151
+ "top_k": 50,
152
+ "top_p": 1.0,
153
+ "torch_dtype": null,
154
+ "torchscript": false,
155
+ "transformers_version": "4.17.0",
156
+ "typical_p": 1.0,
157
+ "use_bfloat16": false
158
+ },
159
+ "eos_token_id": 2,
160
+ "is_encoder_decoder": true,
161
+ "length_penalty": 2.0,
162
+ "max_length": 64,
163
+ "model_type": "vision-encoder-decoder",
164
+ "no_repeat_ngram_size": 3,
165
+ "num_beams": 4,
166
+ "pad_token_id": 1,
167
+ "tie_word_embeddings": false,
168
+ "torch_dtype": "float32",
169
+ "transformers_version": null,
170
+ "vocab_size": 64044
171
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6f01fe8efe31b4742309c41792ff902d9d4023137256c17c374d5debf85755
3
+ size 491800161
last-checkpoint/preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "resample": 2,
16
+ "size": 384
17
+ }
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6088adddf4ccfbfbcbc69858545f391d9c66d839075e2a3960cd74b933d8407a
3
+ size 246531565
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6f05e26e56db968dcc98e6de37b4a5a88d80fdb8101f5f3022b5d7b5e80f63
3
+ size 14503
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65725e6f74c1a76777f848d1c32499753466866e08e36dea01cdb5d6bbb40c1a
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14179b29cfa72f964f47a7331e40ee3aee0088b0e020196fe741e22da29f72b7
3
+ size 623
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.573394495412844,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.57,
12
+ "learning_rate": 4.04625382262997e-05,
13
+ "loss": 2.8413,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.57,
18
+ "eval_cer": 0.7570755831351488,
19
+ "eval_loss": 2.5893969535827637,
20
+ "eval_runtime": 307.564,
21
+ "eval_samples_per_second": 4.981,
22
+ "eval_steps_per_second": 0.624,
23
+ "step": 500
24
+ }
25
+ ],
26
+ "max_steps": 2616,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 4.78498749677568e+17,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1547f9905f2b3b667f6d8f403e1cafbec1ea912a62e9f148b0536c5f5a91f2b5
3
+ size 3183
preprocessor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "resample": 2,
16
+ "size": 384
17
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6088adddf4ccfbfbcbc69858545f391d9c66d839075e2a3960cd74b933d8407a
3
+ size 246531565
runs/Mar20_06-06-46_cf0c2306017c/1647756428.2627215/events.out.tfevents.1647756428.cf0c2306017c.36.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d902033a546ac50a8e02415f6603349e232d914898b36dcafdab09b3ea3cb562
3
+ size 4982
runs/Mar20_06-06-46_cf0c2306017c/events.out.tfevents.1647756428.cf0c2306017c.36.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:120f0efbaff5cee053a777878138d06714c7c9a2e0ca3d19bc503234bf99e7c4
3
+ size 7457
runs/Mar20_06-35-18_cf0c2306017c/1647758132.6929758/events.out.tfevents.1647758132.cf0c2306017c.36.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62f7974f6a23d9a630d6a82fdf8d2ab927b3b54c7d5e1de7f14a349592988a76
3
+ size 4982
runs/Mar20_06-35-18_cf0c2306017c/events.out.tfevents.1647758132.cf0c2306017c.36.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0131b4b1626f728c1f86ea16a59a7f65339f2275a429e3ad8ca8d856562894bc
3
+ size 7457
runs/Mar20_06-46-59_cf0c2306017c/1647758832.8968248/events.out.tfevents.1647758832.cf0c2306017c.36.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7bf34ac50b29e237cd1a63422d329898bd9e56f35c494a657c20877c556c43
3
+ size 4982
runs/Mar20_06-46-59_cf0c2306017c/events.out.tfevents.1647758832.cf0c2306017c.36.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0119dccaf0fbec3068e4561fc5bcd760a5fc5c68be2eb485211f4fa334bf1837
3
+ size 7300
runs/Mar20_06-48-16_cf0c2306017c/1647758906.8672404/events.out.tfevents.1647758906.cf0c2306017c.36.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85e99a36fa9a872e5025bf9f02b4cf2f0979cd480b10dcc03bb45423fb5c73b
3
+ size 4982
runs/Mar20_06-48-16_cf0c2306017c/events.out.tfevents.1647758906.cf0c2306017c.36.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f9f26019c806abc1b05850d7d5a7b11fd5af834ff71f083d5f53f2d6c041c3
3
+ size 7772
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1547f9905f2b3b667f6d8f403e1cafbec1ea912a62e9f148b0536c5f5a91f2b5
3
+ size 3183