Hugging Face's logo

Anwaarma
/
robertuito-esp

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
Anwaarma commited on
Commit
4fe8931
·
verified ·
1 Parent(s): f899731

Training in progress, step 500

Browse files
Files changed (22) hide show
  1. model.safetensors +1 -1
  2. run-23/checkpoint-500/config.json +26 -0
  3. run-23/checkpoint-500/model.safetensors +3 -0
  4. run-23/checkpoint-500/optimizer.pt +3 -0
  5. run-23/checkpoint-500/rng_state.pth +3 -0
  6. run-23/checkpoint-500/scaler.pt +3 -0
  7. run-23/checkpoint-500/scheduler.pt +3 -0
  8. run-23/checkpoint-500/special_tokens_map.json +51 -0
  9. run-23/checkpoint-500/tokenizer.json +0 -0
  10. run-23/checkpoint-500/tokenizer_config.json +62 -0
  11. run-23/checkpoint-500/trainer_state.json +208 -0
  12. run-23/checkpoint-500/training_args.bin +3 -0
  13. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959344.falcon-05.265234.15 +3 -0
  14. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959380.falcon-05.265234.16 +3 -0
  15. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959417.falcon-05.265234.17 +3 -0
  16. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959422.falcon-05.265234.18 +3 -0
  17. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959427.falcon-05.265234.19 +3 -0
  18. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959463.falcon-05.265234.20 +3 -0
  19. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959500.falcon-05.265234.21 +3 -0
  20. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959505.falcon-05.265234.22 +3 -0
  21. runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959529.falcon-05.265234.23 +3 -0
  22. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfcdb9a19a147f842593d365c1ecf9e6d515386ae5626d62a639f1d615c6263c
3
  size 435179080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94e3bf2d92b5b24ba2c31a7fbc2d7b0fb0f8f0335f4ba23a48f9c826dcf2323
3
  size 435179080
run-23/checkpoint-500/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 130,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.51.3",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 30000
26
+ }
run-23/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94e3bf2d92b5b24ba2c31a7fbc2d7b0fb0f8f0335f4ba23a48f9c826dcf2323
3
+ size 435179080
run-23/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02083b0f69932304e99e8ce614f82b6c700c05ff62da2c2ca544a6be5c278b24
3
+ size 870478475
run-23/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619776da0951c1c4afacf4e47900ce6d06a79bfce504c0895e1cd1bce504069e
3
+ size 14645
run-23/checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f3e33ea5e584b9654d542c3c2e7dfe4a9f4932bc331e5d128c470fff1918f4
3
+ size 1383
run-23/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:161dbc902cefcb998a08c612c0ec14076209354e9699aaef2778c66a1b89a161
3
+ size 1465
run-23/checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
run-23/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "max_length": 128,
51
+ "model_max_length": 128,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "<pad>",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "</s>",
57
+ "stride": 0,
58
+ "tokenizer_class": "PreTrainedTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }
run-23/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 450,
3
+ "best_metric": 0.8753227468205007,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.31308703819661865,
6
+ "eval_steps": 50,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.031308703819661866,
14
+ "grad_norm": 8.918027877807617,
15
+ "learning_rate": 3.586229780251654e-05,
16
+ "loss": 0.6806,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.031308703819661866,
21
+ "eval_f1": 0.7527927927927928,
22
+ "eval_loss": 0.5741322636604309,
23
+ "eval_runtime": 2.2101,
24
+ "eval_samples_per_second": 443.422,
25
+ "eval_steps_per_second": 110.855,
26
+ "step": 50
27
+ },
28
+ {
29
+ "epoch": 0.06261740763932373,
30
+ "grad_norm": 8.658595085144043,
31
+ "learning_rate": 3.57757282621252e-05,
32
+ "loss": 0.5762,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.06261740763932373,
37
+ "eval_f1": 0.8141920751399081,
38
+ "eval_loss": 0.46491095423698425,
39
+ "eval_runtime": 2.2223,
40
+ "eval_samples_per_second": 440.992,
41
+ "eval_steps_per_second": 110.248,
42
+ "step": 100
43
+ },
44
+ {
45
+ "epoch": 0.09392611145898559,
46
+ "grad_norm": 11.193159103393555,
47
+ "learning_rate": 3.569089011254168e-05,
48
+ "loss": 0.5802,
49
+ "step": 150
50
+ },
51
+ {
52
+ "epoch": 0.09392611145898559,
53
+ "eval_f1": 0.8119160603184646,
54
+ "eval_loss": 0.46029770374298096,
55
+ "eval_runtime": 2.2545,
56
+ "eval_samples_per_second": 434.678,
57
+ "eval_steps_per_second": 108.67,
58
+ "step": 150
59
+ },
60
+ {
61
+ "epoch": 0.12523481527864747,
62
+ "grad_norm": 9.681838035583496,
63
+ "learning_rate": 3.560432057215035e-05,
64
+ "loss": 0.4903,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.12523481527864747,
69
+ "eval_f1": 0.7854979075101998,
70
+ "eval_loss": 0.5188441872596741,
71
+ "eval_runtime": 2.1759,
72
+ "eval_samples_per_second": 450.393,
73
+ "eval_steps_per_second": 112.598,
74
+ "step": 200
75
+ },
76
+ {
77
+ "epoch": 0.15654351909830932,
78
+ "grad_norm": 7.042013645172119,
79
+ "learning_rate": 3.5517751031759006e-05,
80
+ "loss": 0.5021,
81
+ "step": 250
82
+ },
83
+ {
84
+ "epoch": 0.15654351909830932,
85
+ "eval_f1": 0.8524318626712843,
86
+ "eval_loss": 0.4427223801612854,
87
+ "eval_runtime": 2.1922,
88
+ "eval_samples_per_second": 447.036,
89
+ "eval_steps_per_second": 111.759,
90
+ "step": 250
91
+ },
92
+ {
93
+ "epoch": 0.18785222291797118,
94
+ "grad_norm": 14.190439224243164,
95
+ "learning_rate": 3.5431181491367664e-05,
96
+ "loss": 0.5369,
97
+ "step": 300
98
+ },
99
+ {
100
+ "epoch": 0.18785222291797118,
101
+ "eval_f1": 0.8651623555310952,
102
+ "eval_loss": 0.44512054324150085,
103
+ "eval_runtime": 2.2127,
104
+ "eval_samples_per_second": 442.891,
105
+ "eval_steps_per_second": 110.723,
106
+ "step": 300
107
+ },
108
+ {
109
+ "epoch": 0.21916092673763307,
110
+ "grad_norm": 1.881115198135376,
111
+ "learning_rate": 3.534461195097632e-05,
112
+ "loss": 0.4495,
113
+ "step": 350
114
+ },
115
+ {
116
+ "epoch": 0.21916092673763307,
117
+ "eval_f1": 0.833581804221609,
118
+ "eval_loss": 0.4908888638019562,
119
+ "eval_runtime": 2.1886,
120
+ "eval_samples_per_second": 447.782,
121
+ "eval_steps_per_second": 111.945,
122
+ "step": 350
123
+ },
124
+ {
125
+ "epoch": 0.25046963055729493,
126
+ "grad_norm": 20.08529281616211,
127
+ "learning_rate": 3.5258042410584986e-05,
128
+ "loss": 0.4763,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.25046963055729493,
133
+ "eval_f1": 0.868828322374475,
134
+ "eval_loss": 0.43645554780960083,
135
+ "eval_runtime": 2.203,
136
+ "eval_samples_per_second": 444.845,
137
+ "eval_steps_per_second": 111.211,
138
+ "step": 400
139
+ },
140
+ {
141
+ "epoch": 0.2817783343769568,
142
+ "grad_norm": 10.516815185546875,
143
+ "learning_rate": 3.5171472870193644e-05,
144
+ "loss": 0.4276,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 0.2817783343769568,
149
+ "eval_f1": 0.8753227468205007,
150
+ "eval_loss": 0.4441089630126953,
151
+ "eval_runtime": 2.2497,
152
+ "eval_samples_per_second": 435.619,
153
+ "eval_steps_per_second": 108.905,
154
+ "step": 450
155
+ },
156
+ {
157
+ "epoch": 0.31308703819661865,
158
+ "grad_norm": 5.49413537979126,
159
+ "learning_rate": 3.50849033298023e-05,
160
+ "loss": 0.4465,
161
+ "step": 500
162
+ },
163
+ {
164
+ "epoch": 0.31308703819661865,
165
+ "eval_f1": 0.864982214725873,
166
+ "eval_loss": 0.4431985020637512,
167
+ "eval_runtime": 2.1671,
168
+ "eval_samples_per_second": 452.219,
169
+ "eval_steps_per_second": 113.055,
170
+ "step": 500
171
+ }
172
+ ],
173
+ "logging_steps": 50,
174
+ "max_steps": 20761,
175
+ "num_input_tokens_seen": 0,
176
+ "num_train_epochs": 13,
177
+ "save_steps": 500,
178
+ "stateful_callbacks": {
179
+ "EarlyStoppingCallback": {
180
+ "args": {
181
+ "early_stopping_patience": 3,
182
+ "early_stopping_threshold": 0.0
183
+ },
184
+ "attributes": {
185
+ "early_stopping_patience_counter": 1
186
+ }
187
+ },
188
+ "TrainerControl": {
189
+ "args": {
190
+ "should_epoch_stop": false,
191
+ "should_evaluate": false,
192
+ "should_log": false,
193
+ "should_save": true,
194
+ "should_training_stop": false
195
+ },
196
+ "attributes": {}
197
+ }
198
+ },
199
+ "total_flos": 64618430752320.0,
200
+ "train_batch_size": 4,
201
+ "trial_name": null,
202
+ "trial_params": {
203
+ "learning_rate": 3.5945404561292224e-05,
204
+ "num_train_epochs": 13,
205
+ "per_device_train_batch_size": 4,
206
+ "weight_decay": 0.034672860784467796
207
+ }
208
+ }
run-23/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc101c7c48c7669de386f41ac3938215fd2ae0268ecd2f41e3c6ca62f8c31ce
3
+ size 5777
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959344.falcon-05.265234.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fde32b35dc79831789aa0c766859e86fba58dfffce29961046baa88e50de35
3
+ size 9214
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959380.falcon-05.265234.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e2ef0c59e478d725cc71958f09962a854ed73a32fbeb7628ea7bf922de3863f
3
+ size 9213
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959417.falcon-05.265234.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b26afc00867f413a3f1127100a91adb9cd027fa7d31451f320dc332f16d5dec
3
+ size 5526
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959422.falcon-05.265234.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b917733e77565bb3915360d447d0b6ef3874e2ef468004a980d7abcb5f29729e
3
+ size 5528
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959427.falcon-05.265234.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d3424504c0114467de61cdaad72cf895386e6b42e7f3475f9da1ffea0f7471b
3
+ size 9215
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959463.falcon-05.265234.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb55f02ff51432f94d838cebfd2a51149fe182984b1c182729c0d9de940fe210
3
+ size 9214
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959500.falcon-05.265234.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50502ee297a8f0d174e0e3adbd7cc6319800e10f4c1adc034f22db140e8c9a3b
3
+ size 5528
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959505.falcon-05.265234.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524a37c04b21f184c8d349dcd6acf03a6c0d15f56dd90c9e1427750d7fd7f4ca
3
+ size 7631
runs/May11_11-11-27_falcon-05/events.out.tfevents.1746959529.falcon-05.265234.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5290b670d652f61b01527384c4e472dfbc2f27b623da8aec186af34c70c61aa0
3
+ size 11682
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3abc600169a99313d6a85a82372c544ae653dd2ddee2342da0842a14b6c4fba7
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc101c7c48c7669de386f41ac3938215fd2ae0268ecd2f41e3c6ca62f8c31ce
3
  size 5777