Hugging Face's logo

mootez
/
mean_codet5-base_L4_codetrans_442_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
e00c6a2
·
verified ·
1 Parent(s): f2a80e4

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.1751418458.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": 4,
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:f411ce517ec9848141441ddf441df24be09aa9cb2121f85ea25d40c1d2a4ab55
3
+ size 891558696
checkpoint-15444/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f07e4d29f53829bda0f1e0e9ab2bd66db0d757056191dfc80b727b87e622456
3
+ size 1783272762
checkpoint-15444/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:946d8861fc2147d336e3bf43c4925febdfd9e4c70a48dfa241408975f10884d1
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": 0.18496451578634862,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L4_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": 7.8172454833984375,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.9727,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 1.7814570665359497,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.6182,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.17666940217542107,
28
+ "eval_brevity_penalty": 0.19844952910717162,
29
+ "eval_length_ratio": 0.38208473854818115,
30
+ "eval_loss": 0.32743653655052185,
31
+ "eval_precision": [
32
+ 0.9402275210489106,
33
+ 0.8993676642557061,
34
+ 0.8724796952647825,
35
+ 0.8513722886232846
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5557642179701372,
39
+ "eval_rouge2": 0.46739850795881027,
40
+ "eval_rougeL": 0.5546897069876796,
41
+ "eval_rougeLsum": 0.5543308862962758,
42
+ "eval_runtime": 18.8796,
43
+ "eval_samples_per_second": 26.431,
44
+ "eval_steps_per_second": 1.695,
45
+ "eval_translation_length": 46677,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 2.2902028560638428,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.4295,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 1.775067925453186,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3368,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 2.7991623878479004,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.2944,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.1817123612498402,
72
+ "eval_brevity_penalty": 0.19871662520362823,
73
+ "eval_length_ratio": 0.38228119576962116,
74
+ "eval_loss": 0.22722125053405762,
75
+ "eval_precision": [
76
+ 0.9497869424637588,
77
+ 0.9197437340374875,
78
+ 0.9016038334463821,
79
+ 0.8877532961684806
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.5818762374022723,
83
+ "eval_rouge2": 0.5135427369579433,
84
+ "eval_rougeL": 0.5800832137490466,
85
+ "eval_rougeLsum": 0.5800964013675849,
86
+ "eval_runtime": 18.7432,
87
+ "eval_samples_per_second": 26.623,
88
+ "eval_steps_per_second": 1.707,
89
+ "eval_translation_length": 46701,
90
+ "step": 5148
91
+ },
92
+ {
93
+ "epoch": 2.331002331002331,
94
+ "grad_norm": 0.7832148671150208,
95
+ "learning_rate": 1.7041481417533562e-05,
96
+ "loss": 0.2364,
97
+ "step": 6000
98
+ },
99
+ {
100
+ "epoch": 2.7195027195027195,
101
+ "grad_norm": 1.3141729831695557,
102
+ "learning_rate": 1.6178184486554153e-05,
103
+ "loss": 0.2199,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "eval_bleu": 0.18004884174080807,
109
+ "eval_brevity_penalty": 0.1927719958806599,
110
+ "eval_length_ratio": 0.3778936511574605,
111
+ "eval_loss": 0.19581326842308044,
112
+ "eval_precision": [
113
+ 0.9635438102458572,
114
+ 0.9385538475014233,
115
+ 0.9229304580778002,
116
+ 0.9117712904092415
117
+ ],
118
+ "eval_reference_length": 122164,
119
+ "eval_rouge1": 0.5979415497525762,
120
+ "eval_rouge2": 0.535486051938719,
121
+ "eval_rougeL": 0.5968533080514113,
122
+ "eval_rougeLsum": 0.5966116444826575,
123
+ "eval_runtime": 18.8326,
124
+ "eval_samples_per_second": 26.497,
125
+ "eval_steps_per_second": 1.699,
126
+ "eval_translation_length": 46165,
127
+ "step": 7722
128
+ },
129
+ {
130
+ "epoch": 3.108003108003108,
131
+ "grad_norm": 0.8118874430656433,
132
+ "learning_rate": 1.5314887555574744e-05,
133
+ "loss": 0.2004,
134
+ "step": 8000
135
+ },
136
+ {
137
+ "epoch": 3.4965034965034967,
138
+ "grad_norm": 1.8628580570220947,
139
+ "learning_rate": 1.4451590624595331e-05,
140
+ "loss": 0.1676,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 3.885003885003885,
145
+ "grad_norm": 2.951091766357422,
146
+ "learning_rate": 1.358829369361592e-05,
147
+ "loss": 0.1674,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 4.0,
152
+ "eval_bleu": 0.1798670061585405,
153
+ "eval_brevity_penalty": 0.1924626571198797,
154
+ "eval_length_ratio": 0.37766445106578045,
155
+ "eval_loss": 0.18435858190059662,
156
+ "eval_precision": [
157
+ 0.9611591564254286,
158
+ 0.9385380603882729,
159
+ 0.9244777243625246,
160
+ 0.9146953405017921
161
+ ],
162
+ "eval_reference_length": 122164,
163
+ "eval_rouge1": 0.5983011064950774,
164
+ "eval_rouge2": 0.5378180703691149,
165
+ "eval_rougeL": 0.5956153998221425,
166
+ "eval_rougeLsum": 0.5950704983586383,
167
+ "eval_runtime": 18.8049,
168
+ "eval_samples_per_second": 26.536,
169
+ "eval_steps_per_second": 1.702,
170
+ "eval_translation_length": 46137,
171
+ "step": 10296
172
+ },
173
+ {
174
+ "epoch": 4.273504273504273,
175
+ "grad_norm": 1.9819480180740356,
176
+ "learning_rate": 1.272499676263651e-05,
177
+ "loss": 0.1375,
178
+ "step": 11000
179
+ },
180
+ {
181
+ "epoch": 4.662004662004662,
182
+ "grad_norm": 1.7047138214111328,
183
+ "learning_rate": 1.1861699831657098e-05,
184
+ "loss": 0.1318,
185
+ "step": 12000
186
+ },
187
+ {
188
+ "epoch": 5.0,
189
+ "eval_bleu": 0.18248162987493657,
190
+ "eval_brevity_penalty": 0.19563908597035667,
191
+ "eval_length_ratio": 0.3800137520055008,
192
+ "eval_loss": 0.17377576231956482,
193
+ "eval_precision": [
194
+ 0.9579527830432535,
195
+ 0.9362003266194883,
196
+ 0.9232598071588958,
197
+ 0.9141496204954704
198
+ ],
199
+ "eval_reference_length": 122164,
200
+ "eval_rouge1": 0.5981391231235088,
201
+ "eval_rouge2": 0.540846798142377,
202
+ "eval_rougeL": 0.5973899967168005,
203
+ "eval_rougeLsum": 0.5972707117632804,
204
+ "eval_runtime": 18.8361,
205
+ "eval_samples_per_second": 26.492,
206
+ "eval_steps_per_second": 1.699,
207
+ "eval_translation_length": 46424,
208
+ "step": 12870
209
+ },
210
+ {
211
+ "epoch": 5.05050505050505,
212
+ "grad_norm": 1.4322117567062378,
213
+ "learning_rate": 1.0998402900677689e-05,
214
+ "loss": 0.1273,
215
+ "step": 13000
216
+ },
217
+ {
218
+ "epoch": 5.439005439005439,
219
+ "grad_norm": 0.4661947190761566,
220
+ "learning_rate": 1.0135105969698278e-05,
221
+ "loss": 0.1093,
222
+ "step": 14000
223
+ },
224
+ {
225
+ "epoch": 5.827505827505828,
226
+ "grad_norm": 2.2284674644470215,
227
+ "learning_rate": 9.271809038718868e-06,
228
+ "loss": 0.1066,
229
+ "step": 15000
230
+ },
231
+ {
232
+ "epoch": 6.0,
233
+ "eval_bleu": 0.18496451578634862,
234
+ "eval_brevity_penalty": 0.1985385517324379,
235
+ "eval_length_ratio": 0.38215022428866113,
236
+ "eval_loss": 0.17140471935272217,
237
+ "eval_precision": [
238
+ 0.9552747135054086,
239
+ 0.9350885549733685,
240
+ 0.9227570205966686,
241
+ 0.9139151987253253
242
+ ],
243
+ "eval_reference_length": 122164,
244
+ "eval_rouge1": 0.5986792590724679,
245
+ "eval_rouge2": 0.5413560446441072,
246
+ "eval_rougeL": 0.596096052663762,
247
+ "eval_rougeLsum": 0.5965180238416565,
248
+ "eval_runtime": 18.7672,
249
+ "eval_samples_per_second": 26.589,
250
+ "eval_steps_per_second": 1.705,
251
+ "eval_translation_length": 46685,
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:a1f2eb6e0a2ffb3795e08ba89c4daaaedbe3983b182e8208b99531bf91c84b48
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": 4,
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.1751418458.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbad237faf296fb06abcfaea3dfe5d35f0fa45ed3c3950ebf5f6270e63990cea
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:f411ce517ec9848141441ddf441df24be09aa9cb2121f85ea25d40c1d2a4ab55
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.6679232284790685,
3
+ "rouge2": 0.6166862317036648,
4
+ "rougeL": 0.6649245665279973,
5
+ "rougeLsum": 0.6650365562315177,
6
+ "bleu": 0.5396946337734961,
7
+ "precision": [
8
+ 0.558698691638341,
9
+ 0.5421613638472166,
10
+ 0.5326924962230998,
11
+ 0.5257867055766822
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 1.7559147104679504,
15
+ "translation_length": 399813,
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:a1f2eb6e0a2ffb3795e08ba89c4daaaedbe3983b182e8208b99531bf91c84b48
3
+ size 5496