Hugging Face's logo

nour4286
/
MyDrive

Transformers
TensorBoard
Safetensors
mbart
text2text-generation
Model card Files
xet
Metrics Community
nour4286 commited on
Commit
31658c0
·
verified ·
1 Parent(s): 8882524

Training in progress, step 26500

Browse files
Files changed (38) hide show
  1. Arabart/checkpoint-11229/config.json +59 -0
  2. Arabart/checkpoint-11229/generation_config.json +12 -0
  3. Arabart/checkpoint-11229/model.safetensors +3 -0
  4. Arabart/checkpoint-11229/optimizer.pt +3 -0
  5. Arabart/checkpoint-11229/rng_state.pth +3 -0
  6. Arabart/checkpoint-11229/scheduler.pt +3 -0
  7. Arabart/checkpoint-11229/sentencepiece.bpe.model +3 -0
  8. Arabart/checkpoint-11229/special_tokens_map.json +15 -0
  9. Arabart/checkpoint-11229/tokenizer.json +0 -0
  10. Arabart/checkpoint-11229/tokenizer_config.json +55 -0
  11. Arabart/checkpoint-11229/trainer_state.json +220 -0
  12. Arabart/checkpoint-11229/training_args.bin +3 -0
  13. Arabart/checkpoint-7486/config.json +59 -0
  14. Arabart/checkpoint-7486/generation_config.json +12 -0
  15. Arabart/checkpoint-7486/model.safetensors +3 -0
  16. Arabart/checkpoint-7486/optimizer.pt +3 -0
  17. Arabart/checkpoint-7486/rng_state.pth +3 -0
  18. Arabart/checkpoint-7486/scheduler.pt +3 -0
  19. Arabart/checkpoint-7486/sentencepiece.bpe.model +3 -0
  20. Arabart/checkpoint-7486/special_tokens_map.json +15 -0
  21. Arabart/checkpoint-7486/tokenizer.json +0 -0
  22. Arabart/checkpoint-7486/tokenizer_config.json +55 -0
  23. Arabart/checkpoint-7486/trainer_state.json +153 -0
  24. Arabart/checkpoint-7486/training_args.bin +3 -0
  25. Arabart/config.json +59 -0
  26. Arabart/model.safetensors +3 -0
  27. Arabart/runs/Jul08_21-30-37_098dceed67d8/events.out.tfevents.1720474243.098dceed67d8.988.0 +3 -0
  28. Arabart/runs/Jul10_20-57-08_7543933ae34b/events.out.tfevents.1720645062.7543933ae34b.231.0 +3 -0
  29. Arabart/runs/Jul13_09-10-33_4a1f101fa37a/events.out.tfevents.1720861877.4a1f101fa37a.232.0 +3 -0
  30. Arabart/sentencepiece.bpe.model +3 -0
  31. Arabart/special_tokens_map.json +15 -0
  32. Arabart/tokenizer.json +0 -0
  33. Arabart/tokenizer_config.json +55 -0
  34. Arabart/training_args.bin +3 -0
  35. model.safetensors +1 -1
  36. runs/Jul07_12-23-33_3dfb12a32582/events.out.tfevents.1720355052.3dfb12a32582.414.0 +2 -2
  37. runs/Jul15_10-38-20_7e260361dc4a/events.out.tfevents.1721039988.7e260361dc4a.700.0 +3 -0
  38. training_args.bin +1 -1
Arabart/checkpoint-11229/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "moussakam/Arabart",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
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
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 2,
31
+ "gradient_checkpointing": false,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1",
35
+ "2": "LABEL_2"
36
+ },
37
+ "init_std": 0.02,
38
+ "is_encoder_decoder": true,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "no_repeat_ngram_size": 3,
47
+ "normalize_before": true,
48
+ "normalize_embedding": true,
49
+ "num_beams": 4,
50
+ "num_hidden_layers": 6,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": false,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "BarthezTokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.42.4",
57
+ "use_cache": true,
58
+ "vocab_size": 50002
59
+ }
Arabart/checkpoint-11229/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_eos_token_id": 2,
7
+ "max_new_tokens": 100,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 3,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.42.4"
12
+ }
Arabart/checkpoint-11229/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a94d480f8a2cf70df3261bfa86d8863efb7bd732ad18a386b94623e5ed3b3a7b
3
+ size 557116312
Arabart/checkpoint-11229/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cfcf8fb634c5ebb91e3f6464b465774ef45a8e1462ca20fe0e53a0b82bbae26
3
+ size 1113991930
Arabart/checkpoint-11229/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee825e6b3dff3616323912484effbd7f179b6dca5928110c0803c83caf9e1fe6
3
+ size 14244
Arabart/checkpoint-11229/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c45ac9068e4a7bf53253808a14586b66bb10866e8ed83071246f4a4ec1e8ec2
3
+ size 1064
Arabart/checkpoint-11229/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
3
+ size 1315170
Arabart/checkpoint-11229/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
Arabart/checkpoint-11229/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Arabart/checkpoint-11229/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "50001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "BarthezTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
Arabart/checkpoint-11229/trainer_state.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 27.2064,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Arabart/checkpoint-11229",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11229,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1335826876836762,
13
+ "grad_norm": 3.386234998703003,
14
+ "learning_rate": 3.7102997922232118e-06,
15
+ "loss": 1.0678,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.2671653753673524,
20
+ "grad_norm": 3.5773236751556396,
21
+ "learning_rate": 7.4205995844464235e-06,
22
+ "loss": 1.0284,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.4007480630510286,
27
+ "grad_norm": 3.3108386993408203,
28
+ "learning_rate": 1.1130899376669635e-05,
29
+ "loss": 1.0298,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.5343307507347048,
34
+ "grad_norm": 3.4388937950134277,
35
+ "learning_rate": 1.4841199168892847e-05,
36
+ "loss": 1.0412,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.667913438418381,
41
+ "grad_norm": 3.6874964237213135,
42
+ "learning_rate": 1.855149896111606e-05,
43
+ "loss": 1.0445,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.8014961261020572,
48
+ "grad_norm": 3.868025541305542,
49
+ "learning_rate": 2.226179875333927e-05,
50
+ "loss": 1.0759,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.9350788137857333,
55
+ "grad_norm": 3.5139052867889404,
56
+ "learning_rate": 2.5972098545562486e-05,
57
+ "loss": 1.0966,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 1.0,
62
+ "eval_loss": 2.939680814743042,
63
+ "eval_rouge1": 26.8205,
64
+ "eval_rouge2": 11.1497,
65
+ "eval_rougeL": 23.3343,
66
+ "eval_runtime": 806.3685,
67
+ "eval_samples_per_second": 5.815,
68
+ "eval_steps_per_second": 0.582,
69
+ "step": 3743
70
+ },
71
+ {
72
+ "epoch": 1.0686615014694096,
73
+ "grad_norm": 3.590301036834717,
74
+ "learning_rate": 2.9682398337785694e-05,
75
+ "loss": 1.0519,
76
+ "step": 4000
77
+ },
78
+ {
79
+ "epoch": 1.2022441891530857,
80
+ "grad_norm": 4.0262770652771,
81
+ "learning_rate": 3.33926981300089e-05,
82
+ "loss": 1.0335,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 1.3358268768367618,
87
+ "grad_norm": 3.4733996391296387,
88
+ "learning_rate": 3.710299792223212e-05,
89
+ "loss": 1.0759,
90
+ "step": 5000
91
+ },
92
+ {
93
+ "epoch": 1.4694095645204381,
94
+ "grad_norm": 4.025749206542969,
95
+ "learning_rate": 4.0813297714455326e-05,
96
+ "loss": 1.1336,
97
+ "step": 5500
98
+ },
99
+ {
100
+ "epoch": 1.6029922522041145,
101
+ "grad_norm": 3.807826280593872,
102
+ "learning_rate": 4.452359750667854e-05,
103
+ "loss": 1.1922,
104
+ "step": 6000
105
+ },
106
+ {
107
+ "epoch": 1.7365749398877905,
108
+ "grad_norm": 4.066860198974609,
109
+ "learning_rate": 4.8233897298901756e-05,
110
+ "loss": 1.2401,
111
+ "step": 6500
112
+ },
113
+ {
114
+ "epoch": 1.8701576275714666,
115
+ "grad_norm": 4.048403739929199,
116
+ "learning_rate": 4.708305499888667e-05,
117
+ "loss": 1.2936,
118
+ "step": 7000
119
+ },
120
+ {
121
+ "epoch": 2.0,
122
+ "eval_loss": 2.8382859230041504,
123
+ "eval_rouge1": 27.0396,
124
+ "eval_rouge2": 11.288,
125
+ "eval_rougeL": 23.5434,
126
+ "eval_runtime": 802.1911,
127
+ "eval_samples_per_second": 5.845,
128
+ "eval_steps_per_second": 0.585,
129
+ "step": 7486
130
+ },
131
+ {
132
+ "epoch": 2.003740315255143,
133
+ "grad_norm": 4.089428901672363,
134
+ "learning_rate": 3.3302164039540476e-05,
135
+ "loss": 1.2334,
136
+ "step": 7500
137
+ },
138
+ {
139
+ "epoch": 2.1373230029388193,
140
+ "grad_norm": 3.9481818675994873,
141
+ "learning_rate": 3.218897497550984e-05,
142
+ "loss": 1.1406,
143
+ "step": 8000
144
+ },
145
+ {
146
+ "epoch": 2.270905690622495,
147
+ "grad_norm": 4.022891521453857,
148
+ "learning_rate": 3.10757859114792e-05,
149
+ "loss": 1.193,
150
+ "step": 8500
151
+ },
152
+ {
153
+ "epoch": 2.4044883783061715,
154
+ "grad_norm": 4.349768161773682,
155
+ "learning_rate": 2.9962596847448572e-05,
156
+ "loss": 1.2447,
157
+ "step": 9000
158
+ },
159
+ {
160
+ "epoch": 2.5380710659898478,
161
+ "grad_norm": 4.266928672790527,
162
+ "learning_rate": 2.8849407783417938e-05,
163
+ "loss": 1.2706,
164
+ "step": 9500
165
+ },
166
+ {
167
+ "epoch": 2.6716537536735236,
168
+ "grad_norm": 3.9516377449035645,
169
+ "learning_rate": 2.77362187193873e-05,
170
+ "loss": 1.3529,
171
+ "step": 10000
172
+ },
173
+ {
174
+ "epoch": 2.8052364413572,
175
+ "grad_norm": 3.882983922958374,
176
+ "learning_rate": 2.6623029655356667e-05,
177
+ "loss": 1.3834,
178
+ "step": 10500
179
+ },
180
+ {
181
+ "epoch": 2.9388191290408763,
182
+ "grad_norm": 3.9039924144744873,
183
+ "learning_rate": 2.5509840591326034e-05,
184
+ "loss": 1.4255,
185
+ "step": 11000
186
+ },
187
+ {
188
+ "epoch": 3.0,
189
+ "eval_loss": 2.6909232139587402,
190
+ "eval_rouge1": 27.2064,
191
+ "eval_rouge2": 11.3801,
192
+ "eval_rougeL": 23.5876,
193
+ "eval_runtime": 854.0016,
194
+ "eval_samples_per_second": 5.491,
195
+ "eval_steps_per_second": 0.549,
196
+ "step": 11229
197
+ }
198
+ ],
199
+ "logging_steps": 500,
200
+ "max_steps": 22458,
201
+ "num_input_tokens_seen": 0,
202
+ "num_train_epochs": 6,
203
+ "save_steps": 500,
204
+ "stateful_callbacks": {
205
+ "TrainerControl": {
206
+ "args": {
207
+ "should_epoch_stop": false,
208
+ "should_evaluate": false,
209
+ "should_log": false,
210
+ "should_save": true,
211
+ "should_training_stop": false
212
+ },
213
+ "attributes": {}
214
+ }
215
+ },
216
+ "total_flos": 6.587894865088512e+16,
217
+ "train_batch_size": 10,
218
+ "trial_name": null,
219
+ "trial_params": null
220
+ }
Arabart/checkpoint-11229/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5103a1cc20a62bbf719377c5305821e259a6bc6f0aac737a4f89a07445f87b4
3
+ size 7032
Arabart/checkpoint-7486/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nour4286/ArabartModel",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
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
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 2,
31
+ "gradient_checkpointing": false,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1",
35
+ "2": "LABEL_2"
36
+ },
37
+ "init_std": 0.02,
38
+ "is_encoder_decoder": true,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "no_repeat_ngram_size": 3,
47
+ "normalize_before": true,
48
+ "normalize_embedding": true,
49
+ "num_beams": 4,
50
+ "num_hidden_layers": 6,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": false,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "BarthezTokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.42.3",
57
+ "use_cache": true,
58
+ "vocab_size": 50002
59
+ }
Arabart/checkpoint-7486/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_eos_token_id": 2,
7
+ "max_new_tokens": 100,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 3,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.42.3"
12
+ }
Arabart/checkpoint-7486/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff36ceec5644fd3f33c54f7df20745f002afee034d3ad1cb03834e760fe8b833
3
+ size 557116312
Arabart/checkpoint-7486/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88965dd84507e4c94a284e42b27c516cc5781816e8dfb6d51a9c2bc9841081b8
3
+ size 1113991930
Arabart/checkpoint-7486/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbfd2e272a31850aa6ba9f85fce31b68682b5b792f76342d9305bf77e9f3add5
3
+ size 14244
Arabart/checkpoint-7486/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2530cb9367e9a97e253d716557508627759abd16d160e2830b09e33266b8f7c
3
+ size 1064
Arabart/checkpoint-7486/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
3
+ size 1315170
Arabart/checkpoint-7486/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
Arabart/checkpoint-7486/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Arabart/checkpoint-7486/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "50001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "BarthezTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
Arabart/checkpoint-7486/trainer_state.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 27.0396,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Arabart/checkpoint-7486",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7486,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1335826876836762,
13
+ "grad_norm": 3.386234998703003,
14
+ "learning_rate": 3.7102997922232118e-06,
15
+ "loss": 1.0678,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.2671653753673524,
20
+ "grad_norm": 3.5773236751556396,
21
+ "learning_rate": 7.4205995844464235e-06,
22
+ "loss": 1.0284,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.4007480630510286,
27
+ "grad_norm": 3.3108386993408203,
28
+ "learning_rate": 1.1130899376669635e-05,
29
+ "loss": 1.0298,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.5343307507347048,
34
+ "grad_norm": 3.4388937950134277,
35
+ "learning_rate": 1.4841199168892847e-05,
36
+ "loss": 1.0412,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.667913438418381,
41
+ "grad_norm": 3.6874964237213135,
42
+ "learning_rate": 1.855149896111606e-05,
43
+ "loss": 1.0445,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.8014961261020572,
48
+ "grad_norm": 3.868025541305542,
49
+ "learning_rate": 2.226179875333927e-05,
50
+ "loss": 1.0759,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.9350788137857333,
55
+ "grad_norm": 3.5139052867889404,
56
+ "learning_rate": 2.5972098545562486e-05,
57
+ "loss": 1.0966,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 1.0,
62
+ "eval_loss": 2.939680814743042,
63
+ "eval_rouge1": 26.8205,
64
+ "eval_rouge2": 11.1497,
65
+ "eval_rougeL": 23.3343,
66
+ "eval_runtime": 806.3685,
67
+ "eval_samples_per_second": 5.815,
68
+ "eval_steps_per_second": 0.582,
69
+ "step": 3743
70
+ },
71
+ {
72
+ "epoch": 1.0686615014694096,
73
+ "grad_norm": 3.590301036834717,
74
+ "learning_rate": 2.9682398337785694e-05,
75
+ "loss": 1.0519,
76
+ "step": 4000
77
+ },
78
+ {
79
+ "epoch": 1.2022441891530857,
80
+ "grad_norm": 4.0262770652771,
81
+ "learning_rate": 3.33926981300089e-05,
82
+ "loss": 1.0335,
83
+ "step": 4500
84
+ },
85
+ {
86
+ "epoch": 1.3358268768367618,
87
+ "grad_norm": 3.4733996391296387,
88
+ "learning_rate": 3.710299792223212e-05,
89
+ "loss": 1.0759,
90
+ "step": 5000
91
+ },
92
+ {
93
+ "epoch": 1.4694095645204381,
94
+ "grad_norm": 4.025749206542969,
95
+ "learning_rate": 4.0813297714455326e-05,
96
+ "loss": 1.1336,
97
+ "step": 5500
98
+ },
99
+ {
100
+ "epoch": 1.6029922522041145,
101
+ "grad_norm": 3.807826280593872,
102
+ "learning_rate": 4.452359750667854e-05,
103
+ "loss": 1.1922,
104
+ "step": 6000
105
+ },
106
+ {
107
+ "epoch": 1.7365749398877905,
108
+ "grad_norm": 4.066860198974609,
109
+ "learning_rate": 4.8233897298901756e-05,
110
+ "loss": 1.2401,
111
+ "step": 6500
112
+ },
113
+ {
114
+ "epoch": 1.8701576275714666,
115
+ "grad_norm": 4.048403739929199,
116
+ "learning_rate": 4.708305499888667e-05,
117
+ "loss": 1.2936,
118
+ "step": 7000
119
+ },
120
+ {
121
+ "epoch": 2.0,
122
+ "eval_loss": 2.8382859230041504,
123
+ "eval_rouge1": 27.0396,
124
+ "eval_rouge2": 11.288,
125
+ "eval_rougeL": 23.5434,
126
+ "eval_runtime": 802.1911,
127
+ "eval_samples_per_second": 5.845,
128
+ "eval_steps_per_second": 0.585,
129
+ "step": 7486
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 11229,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 3,
136
+ "save_steps": 500,
137
+ "stateful_callbacks": {
138
+ "TrainerControl": {
139
+ "args": {
140
+ "should_epoch_stop": false,
141
+ "should_evaluate": false,
142
+ "should_log": false,
143
+ "should_save": true,
144
+ "should_training_stop": false
145
+ },
146
+ "attributes": {}
147
+ }
148
+ },
149
+ "total_flos": 4.390892214460416e+16,
150
+ "train_batch_size": 10,
151
+ "trial_name": null,
152
+ "trial_params": null
153
+ }
Arabart/checkpoint-7486/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76331aef1246e3dac8c5b8a8b0b0d4c08a9426a6e56fde87f4dc39d35372157
3
+ size 7032
Arabart/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "moussakam/Arabart",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
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
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 2,
31
+ "gradient_checkpointing": false,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1",
35
+ "2": "LABEL_2"
36
+ },
37
+ "init_std": 0.02,
38
+ "is_encoder_decoder": true,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "no_repeat_ngram_size": 3,
47
+ "normalize_before": true,
48
+ "normalize_embedding": true,
49
+ "num_beams": 4,
50
+ "num_hidden_layers": 6,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": false,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "BarthezTokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.42.4",
57
+ "use_cache": true,
58
+ "vocab_size": 50002
59
+ }
Arabart/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a94d480f8a2cf70df3261bfa86d8863efb7bd732ad18a386b94623e5ed3b3a7b
3
+ size 557116312
Arabart/runs/Jul08_21-30-37_098dceed67d8/events.out.tfevents.1720474243.098dceed67d8.988.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a732fa08f9236f6c44c0be63d43a3dbad553929bbcf4285a62dee367a6ed293d
3
+ size 7718
Arabart/runs/Jul10_20-57-08_7543933ae34b/events.out.tfevents.1720645062.7543933ae34b.231.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2531f3eee71f78e0c02a3d16d9c016ce494797405c4954c9c78e67e994caa29
3
+ size 11656
Arabart/runs/Jul13_09-10-33_4a1f101fa37a/events.out.tfevents.1720861877.4a1f101fa37a.232.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223e1933d6fdb7c34b54c4851a18f2657b22c55a5f6a9220951c3cbf3d1adf6e
3
+ size 11183
Arabart/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
3
+ size 1315170
Arabart/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
Arabart/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Arabart/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "50001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "sp_model_kwargs": {},
53
+ "tokenizer_class": "BarthezTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
Arabart/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5103a1cc20a62bbf719377c5305821e259a6bc6f0aac737a4f89a07445f87b4
3
+ size 7032
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4414de5c604c14cf72a8561addfb2deb9c1ab10c4a3c1db45db6c6c2f27052b3
3
  size 557116312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:895def3049804a3616191bedcdc0c766b140d5562042ba2d9e65e969096a5c1a
3
  size 557116312
runs/Jul07_12-23-33_3dfb12a32582/events.out.tfevents.1720355052.3dfb12a32582.414.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:703dfcde13dc753bf7c63ba043328b450c22ab386a19d065f92e79948965ff88
3
- size 9526
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2d8703c3e7518cc1b48e59dec197a78929b2213d06fc3a8c779e5101a5e6b7
3
+ size 9737
runs/Jul15_10-38-20_7e260361dc4a/events.out.tfevents.1721039988.7e260361dc4a.700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58eafc10f9bb77fcd93724fbeef521c3d2a4b2d704c2c1140dde9f6788ade63e
3
+ size 7792
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0137b428b0736d2124bf22d35ec516d8342d1ff6fd63477ed3420d2ddc592b3
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e7eb2d048753ea4db56818dc5d2fea7337e0101611f5f2c748e0838c9dae33
3
  size 7032