Hugging Face's logo

gagan3012
/
TrOCR-Ar-Small

Image-Text-to-Text
Transformers
PyTorch
TensorBoard
Arabic
vision-encoder-decoder
Generated from Trainer
trocr
Inference Endpoints
Model card Files Metrics Community
4
gagan3012 commited on
Commit
1c89e19
•
1 Parent(s): 27f5c0e

Training in progress, step 1000

Browse files
Files changed (16) hide show
  1. .gitignore +1 -0
  2. config.json +171 -0
  3. last-checkpoint/config.json +171 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/preprocessor_config.json +17 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scaler.pt +3 -0
  9. last-checkpoint/scheduler.pt +3 -0
  10. last-checkpoint/trainer_state.json +31 -0
  11. last-checkpoint/training_args.bin +3 -0
  12. preprocessor_config.json +17 -0
  13. pytorch_model.bin +3 -0
  14. runs/Mar21_09-18-11_087c1ea6372a/1647854315.71197/events.out.tfevents.1647854315.087c1ea6372a.76.1 +3 -0
  15. runs/Mar21_09-18-11_087c1ea6372a/events.out.tfevents.1647854315.087c1ea6372a.76.0 +3 -0
  16. training_args.bin +3 -0
.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 sha256:2ab4be5a77350763ddc4318155d668a7ca0d648a5c920554a4fcf87b3afa15a0
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:ee7f6bd27287cfbc78e254ce73f3f7d0a952d152b5603e7eb0cf1545e1b54b9c
3
+ size 246531565
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60db868db25d79a4a49d93a4ff950747420ee055dbacbef348e39ff3bd92b0bc
3
+ size 14439
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c839c3d694d8ceeeac85645a8e358f96300e44574d363a151fc00c07558d8d4
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a41d885b6e3951e39aa87ba36fccfeddb0170f9fbad0973e185208b29a2329b
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": 0.14338973329509608,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.14,
12
+ "learning_rate": 4.762451008507791e-05,
13
+ "loss": 3.6363,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "eval_cer": 0.9369978858350951,
19
+ "eval_loss": 2.759432792663574,
20
+ "eval_runtime": 76.0129,
21
+ "eval_samples_per_second": 0.658,
22
+ "eval_steps_per_second": 0.658,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "max_steps": 20922,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 1.19624687419392e+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 sha256:63c9d1e0fe7cc0380936724fc86865955016b860e61c849267a10b3d1b7b2c68
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:ee7f6bd27287cfbc78e254ce73f3f7d0a952d152b5603e7eb0cf1545e1b54b9c
3
+ size 246531565
runs/Mar21_09-18-11_087c1ea6372a/1647854315.71197/events.out.tfevents.1647854315.087c1ea6372a.76.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f407f7971f46d5bf79ef04d2d20c7731da93b50bda128a810577c373849b9c22
3
+ size 5012
runs/Mar21_09-18-11_087c1ea6372a/events.out.tfevents.1647854315.087c1ea6372a.76.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a10eb0e873a25b549bef2655bf0b4cdf005662c64faafbb888dd07fc8fa369
3
+ size 7801
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63c9d1e0fe7cc0380936724fc86865955016b860e61c849267a10b3d1b7b2c68
3
+ size 3183