Hugging Face's logo

mootez
/
mean_codet5-base_L5_codetrans_442_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
44ccbf4
·
verified ·
1 Parent(s): eabda34

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-15444/config.json +71 -0
  2. checkpoint-15444/generation_config.json +7 -0
  3. checkpoint-15444/model.safetensors +3 -0
  4. checkpoint-15444/optimizer.pt +3 -0
  5. checkpoint-15444/rng_state.pth +3 -0
  6. checkpoint-15444/scheduler.pt +3 -0
  7. checkpoint-15444/trainer_state.json +276 -0
  8. checkpoint-15444/training_args.bin +3 -0
  9. config.json +71 -0
  10. events.out.tfevents.1751425033.gra5 +3 -0
  11. generation_config.json +7 -0
  12. model.safetensors +3 -0
  13. results.json +17 -0
  14. training_args.bin +3 -0
checkpoint-15444/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mootez/projects/def-tusharma/mootez/local_models/codet5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "merge_layer_index": 5,
28
+ "merger_type": "mean",
29
+ "model_type": "t5",
30
+ "n_positions": 512,
31
+ "num_decoder_layers": 12,
32
+ "num_heads": 12,
33
+ "num_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 0,
36
+ "relative_attention_max_distance": 128,
37
+ "relative_attention_num_buckets": 32,
38
+ "task_specific_params": {
39
+ "summarization": {
40
+ "early_stopping": true,
41
+ "length_penalty": 2.0,
42
+ "max_length": 200,
43
+ "min_length": 30,
44
+ "no_repeat_ngram_size": 3,
45
+ "num_beams": 4,
46
+ "prefix": "summarize: "
47
+ },
48
+ "translation_en_to_de": {
49
+ "early_stopping": true,
50
+ "max_length": 300,
51
+ "num_beams": 4,
52
+ "prefix": "translate English to German: "
53
+ },
54
+ "translation_en_to_fr": {
55
+ "early_stopping": true,
56
+ "max_length": 300,
57
+ "num_beams": 4,
58
+ "prefix": "translate English to French: "
59
+ },
60
+ "translation_en_to_ro": {
61
+ "early_stopping": true,
62
+ "max_length": 300,
63
+ "num_beams": 4,
64
+ "prefix": "translate English to Romanian: "
65
+ }
66
+ },
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.48.2",
69
+ "use_cache": true,
70
+ "vocab_size": 32100
71
+ }
checkpoint-15444/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.48.2"
7
+ }
checkpoint-15444/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6673baddd8cecb785562bdcb811474312efddc8b308f4e752273661f64540e
3
+ size 891558696
checkpoint-15444/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461e1d858204d1668e0017e5f0fee9b9968652f1273ced88680b18186e96f86c
3
+ size 1783272762
checkpoint-15444/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d396262d31146c3d957b734c7ee011292a83eded735d51211e93cfb10cf7a7
3
+ size 14308
checkpoint-15444/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6469020b1665fafe3d4c80af3d2eacefd7930000c02c184ecc7c50cf6b9ed0
3
+ size 1064
checkpoint-15444/trainer_state.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1843522951887535,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L5_codetrans_442_src_java_tgt_c_sharp/checkpoint-15444",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 15444,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.3885003885003885,
13
+ "grad_norm": 6.753764629364014,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.9062,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 1.937056064605713,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.5978,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.1767740815066557,
28
+ "eval_brevity_penalty": 0.1985162951937014,
29
+ "eval_length_ratio": 0.3821338528535411,
30
+ "eval_loss": 0.3178876042366028,
31
+ "eval_precision": [
32
+ 0.9390998864683076,
33
+ 0.8988394249090594,
34
+ 0.8733720039400241,
35
+ 0.8528969149736644
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5582202799854111,
39
+ "eval_rouge2": 0.4707800817996478,
40
+ "eval_rougeL": 0.5571292685114562,
41
+ "eval_rougeLsum": 0.5567871853581606,
42
+ "eval_runtime": 18.9145,
43
+ "eval_samples_per_second": 26.382,
44
+ "eval_steps_per_second": 1.692,
45
+ "eval_translation_length": 46683,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 1.9576139450073242,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.4171,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 1.5954126119613647,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3269,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 2.0106043815612793,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.2871,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.18234884849847863,
72
+ "eval_brevity_penalty": 0.19919538369246892,
73
+ "eval_length_ratio": 0.3826331816247012,
74
+ "eval_loss": 0.22080473601818085,
75
+ "eval_precision": [
76
+ 0.9485495464658565,
77
+ 0.9207698129527516,
78
+ 0.9033576706160101,
79
+ 0.8900700598934737
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.5837166658348287,
83
+ "eval_rouge2": 0.5148785461929274,
84
+ "eval_rougeL": 0.5813845803817681,
85
+ "eval_rougeLsum": 0.5811545716537936,
86
+ "eval_runtime": 18.8948,
87
+ "eval_samples_per_second": 26.409,
88
+ "eval_steps_per_second": 1.694,
89
+ "eval_translation_length": 46744,
90
+ "step": 5148
91
+ },
92
+ {
93
+ "epoch": 2.331002331002331,
94
+ "grad_norm": 0.6272425651550293,
95
+ "learning_rate": 1.7041481417533562e-05,
96
+ "loss": 0.2291,
97
+ "step": 6000
98
+ },
99
+ {
100
+ "epoch": 2.7195027195027195,
101
+ "grad_norm": 1.1777029037475586,
102
+ "learning_rate": 1.6178184486554153e-05,
103
+ "loss": 0.2118,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "eval_bleu": 0.18375107621364303,
109
+ "eval_brevity_penalty": 0.1998081429546045,
110
+ "eval_length_ratio": 0.3830833960905013,
111
+ "eval_loss": 0.19292110204696655,
112
+ "eval_precision": [
113
+ 0.9509391226308255,
114
+ 0.9239092872570195,
115
+ 0.9079059409183206,
116
+ 0.8966933027239415
117
+ ],
118
+ "eval_reference_length": 122164,
119
+ "eval_rouge1": 0.5908467977685097,
120
+ "eval_rouge2": 0.5280094377356734,
121
+ "eval_rougeL": 0.5896799595326705,
122
+ "eval_rougeLsum": 0.589363155574119,
123
+ "eval_runtime": 18.84,
124
+ "eval_samples_per_second": 26.486,
125
+ "eval_steps_per_second": 1.699,
126
+ "eval_translation_length": 46799,
127
+ "step": 7722
128
+ },
129
+ {
130
+ "epoch": 3.108003108003108,
131
+ "grad_norm": 1.5857670307159424,
132
+ "learning_rate": 1.5314887555574744e-05,
133
+ "loss": 0.1935,
134
+ "step": 8000
135
+ },
136
+ {
137
+ "epoch": 3.4965034965034967,
138
+ "grad_norm": 1.686398983001709,
139
+ "learning_rate": 1.4451590624595331e-05,
140
+ "loss": 0.1622,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 3.885003885003885,
145
+ "grad_norm": 3.3837764263153076,
146
+ "learning_rate": 1.358829369361592e-05,
147
+ "loss": 0.1617,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 4.0,
152
+ "eval_bleu": 0.18159679041620141,
153
+ "eval_brevity_penalty": 0.19571671648502198,
154
+ "eval_length_ratio": 0.3800710520284208,
155
+ "eval_loss": 0.1816253811120987,
156
+ "eval_precision": [
157
+ 0.9540608645086257,
158
+ 0.9318557868152921,
159
+ 0.9180771685779059,
160
+ 0.908065162237949
161
+ ],
162
+ "eval_reference_length": 122164,
163
+ "eval_rouge1": 0.5953360755276207,
164
+ "eval_rouge2": 0.5351951403483757,
165
+ "eval_rougeL": 0.5926027850186174,
166
+ "eval_rougeLsum": 0.5925059653029646,
167
+ "eval_runtime": 18.9982,
168
+ "eval_samples_per_second": 26.266,
169
+ "eval_steps_per_second": 1.684,
170
+ "eval_translation_length": 46431,
171
+ "step": 10296
172
+ },
173
+ {
174
+ "epoch": 4.273504273504273,
175
+ "grad_norm": 1.486075520515442,
176
+ "learning_rate": 1.272499676263651e-05,
177
+ "loss": 0.1331,
178
+ "step": 11000
179
+ },
180
+ {
181
+ "epoch": 4.662004662004662,
182
+ "grad_norm": 1.3379559516906738,
183
+ "learning_rate": 1.1861699831657098e-05,
184
+ "loss": 0.1274,
185
+ "step": 12000
186
+ },
187
+ {
188
+ "epoch": 5.0,
189
+ "eval_bleu": 0.18347435276809382,
190
+ "eval_brevity_penalty": 0.19704866974409233,
191
+ "eval_length_ratio": 0.381053338135621,
192
+ "eval_loss": 0.17392456531524658,
193
+ "eval_precision": [
194
+ 0.9555326416188696,
195
+ 0.9345522452879353,
196
+ 0.9219370842754594,
197
+ 0.9129711013450525
198
+ ],
199
+ "eval_reference_length": 122164,
200
+ "eval_rouge1": 0.5980705472676723,
201
+ "eval_rouge2": 0.5420321387343544,
202
+ "eval_rougeL": 0.596654951443683,
203
+ "eval_rougeLsum": 0.5964028436319165,
204
+ "eval_runtime": 18.9239,
205
+ "eval_samples_per_second": 26.369,
206
+ "eval_steps_per_second": 1.691,
207
+ "eval_translation_length": 46551,
208
+ "step": 12870
209
+ },
210
+ {
211
+ "epoch": 5.05050505050505,
212
+ "grad_norm": 1.5791140794754028,
213
+ "learning_rate": 1.0998402900677689e-05,
214
+ "loss": 0.1229,
215
+ "step": 13000
216
+ },
217
+ {
218
+ "epoch": 5.439005439005439,
219
+ "grad_norm": 0.5601959228515625,
220
+ "learning_rate": 1.0135105969698278e-05,
221
+ "loss": 0.1047,
222
+ "step": 14000
223
+ },
224
+ {
225
+ "epoch": 5.827505827505828,
226
+ "grad_norm": 1.971771240234375,
227
+ "learning_rate": 9.271809038718868e-06,
228
+ "loss": 0.1023,
229
+ "step": 15000
230
+ },
231
+ {
232
+ "epoch": 6.0,
233
+ "eval_bleu": 0.1843522951887535,
234
+ "eval_brevity_penalty": 0.19742644763036346,
235
+ "eval_length_ratio": 0.381331652532661,
236
+ "eval_loss": 0.16913104057312012,
237
+ "eval_precision": [
238
+ 0.9558226897069872,
239
+ 0.93677038580046,
240
+ 0.9253953978107794,
241
+ 0.9175612136266856
242
+ ],
243
+ "eval_reference_length": 122164,
244
+ "eval_rouge1": 0.6009002573197968,
245
+ "eval_rouge2": 0.5473629719092964,
246
+ "eval_rougeL": 0.5988844154649049,
247
+ "eval_rougeLsum": 0.5993705487241847,
248
+ "eval_runtime": 18.8009,
249
+ "eval_samples_per_second": 26.541,
250
+ "eval_steps_per_second": 1.702,
251
+ "eval_translation_length": 46585,
252
+ "step": 15444
253
+ }
254
+ ],
255
+ "logging_steps": 1000,
256
+ "max_steps": 25740,
257
+ "num_input_tokens_seen": 0,
258
+ "num_train_epochs": 10,
259
+ "save_steps": 500,
260
+ "stateful_callbacks": {
261
+ "TrainerControl": {
262
+ "args": {
263
+ "should_epoch_stop": false,
264
+ "should_evaluate": false,
265
+ "should_log": false,
266
+ "should_save": true,
267
+ "should_training_stop": false
268
+ },
269
+ "attributes": {}
270
+ }
271
+ },
272
+ "total_flos": 1.8734197010688e+16,
273
+ "train_batch_size": 4,
274
+ "trial_name": null,
275
+ "trial_params": null
276
+ }
checkpoint-15444/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a93bbb1f7319f0911df9bd3d28b98591abe9979f9354f8a5a1f801dbcf56d3
3
+ size 5496
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mootez/projects/def-tusharma/mootez/local_models/codet5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "merge_layer_index": 5,
28
+ "merger_type": "mean",
29
+ "model_type": "t5",
30
+ "n_positions": 512,
31
+ "num_decoder_layers": 12,
32
+ "num_heads": 12,
33
+ "num_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 0,
36
+ "relative_attention_max_distance": 128,
37
+ "relative_attention_num_buckets": 32,
38
+ "task_specific_params": {
39
+ "summarization": {
40
+ "early_stopping": true,
41
+ "length_penalty": 2.0,
42
+ "max_length": 200,
43
+ "min_length": 30,
44
+ "no_repeat_ngram_size": 3,
45
+ "num_beams": 4,
46
+ "prefix": "summarize: "
47
+ },
48
+ "translation_en_to_de": {
49
+ "early_stopping": true,
50
+ "max_length": 300,
51
+ "num_beams": 4,
52
+ "prefix": "translate English to German: "
53
+ },
54
+ "translation_en_to_fr": {
55
+ "early_stopping": true,
56
+ "max_length": 300,
57
+ "num_beams": 4,
58
+ "prefix": "translate English to French: "
59
+ },
60
+ "translation_en_to_ro": {
61
+ "early_stopping": true,
62
+ "max_length": 300,
63
+ "num_beams": 4,
64
+ "prefix": "translate English to Romanian: "
65
+ }
66
+ },
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.48.2",
69
+ "use_cache": true,
70
+ "vocab_size": 32100
71
+ }
events.out.tfevents.1751425033.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee62c62935a4383e661d512d61aa74f305c8ff220bb6001a7926e409828cfe3f
3
+ size 19660
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.48.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6673baddd8cecb785562bdcb811474312efddc8b308f4e752273661f64540e
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.7010104890056643,
3
+ "rouge2": 0.6507772522607165,
4
+ "rougeL": 0.6988387657126893,
5
+ "rougeLsum": 0.6984573915357692,
6
+ "bleu": 0.597469534956504,
7
+ "precision": [
8
+ 0.618334629320186,
9
+ 0.5998844211935033,
10
+ 0.5898025276023269,
11
+ 0.5824588915024829
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 1.592735896703924,
15
+ "translation_length": 362658,
16
+ "reference_length": 227695
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a93bbb1f7319f0911df9bd3d28b98591abe9979f9354f8a5a1f801dbcf56d3
3
+ size 5496