Hugging Face's logo

mootez
/
mean_codet5-base_L-1_codetrans_123456_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
9239169
·
verified ·
1 Parent(s): 857c159

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-12870/config.json +71 -0
  2. checkpoint-12870/generation_config.json +7 -0
  3. checkpoint-12870/model.safetensors +3 -0
  4. checkpoint-12870/optimizer.pt +3 -0
  5. checkpoint-12870/rng_state.pth +3 -0
  6. checkpoint-12870/scheduler.pt +3 -0
  7. checkpoint-12870/trainer_state.json +232 -0
  8. checkpoint-12870/training_args.bin +3 -0
  9. config.json +71 -0
  10. events.out.tfevents.1751331117.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-12870/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": -1,
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-12870/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-12870/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2155bd898f7d682310830260ee9d5dfb795a85286cc7ba4135bed4e3f31aa56
3
+ size 891558696
checkpoint-12870/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac1171480d15881a1aff3d38f7cd80ef7c359e505bc4e0f77454729ea37a019
3
+ size 1783272762
checkpoint-12870/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899c571ef24564b40fa7bd65e06f9ee81ad1948c7c048d5fe66a96148402b954
3
+ size 14244
checkpoint-12870/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1db8d949a216affb89182da9c2ef3ba19d289845b5e378bf1256011fe425ed
3
+ size 1064
checkpoint-12870/trainer_state.json ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1823442196189086,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L-1_codetrans_123456_src_java_tgt_c_sharp/checkpoint-12870",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 12870,
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": 10.190895080566406,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 3.079,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 5.316028594970703,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.7638,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.17401372208421842,
28
+ "eval_brevity_penalty": 0.20008681540190465,
29
+ "eval_length_ratio": 0.3832880390295013,
30
+ "eval_loss": 0.4109351634979248,
31
+ "eval_precision": [
32
+ 0.9353536647872885,
33
+ 0.8807555315704263,
34
+ 0.8465281717802121,
35
+ 0.8203278399188122
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5385625631823885,
39
+ "eval_rouge2": 0.4372431207490999,
40
+ "eval_rougeL": 0.5361516538904678,
41
+ "eval_rougeLsum": 0.5358346714690086,
42
+ "eval_runtime": 18.8231,
43
+ "eval_samples_per_second": 26.51,
44
+ "eval_steps_per_second": 1.7,
45
+ "eval_translation_length": 46824,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 4.63295841217041,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.5192,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 2.102656841278076,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3999,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 3.7660560607910156,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.3627,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.17799700881224312,
72
+ "eval_brevity_penalty": 0.19571671648502198,
73
+ "eval_length_ratio": 0.3800710520284208,
74
+ "eval_loss": 0.2773875892162323,
75
+ "eval_precision": [
76
+ 0.9528547737502961,
77
+ 0.917073064530175,
78
+ 0.8938436819052231,
79
+ 0.875884630791828
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.5692662083983997,
83
+ "eval_rouge2": 0.49014124678390214,
84
+ "eval_rougeL": 0.5669068816793206,
85
+ "eval_rougeLsum": 0.5667463510179136,
86
+ "eval_runtime": 18.779,
87
+ "eval_samples_per_second": 26.572,
88
+ "eval_steps_per_second": 1.704,
89
+ "eval_translation_length": 46431,
90
+ "step": 5148
91
+ },
92
+ {
93
+ "epoch": 2.331002331002331,
94
+ "grad_norm": 4.401015758514404,
95
+ "learning_rate": 1.7041481417533562e-05,
96
+ "loss": 0.2785,
97
+ "step": 6000
98
+ },
99
+ {
100
+ "epoch": 2.7195027195027195,
101
+ "grad_norm": 4.332099437713623,
102
+ "learning_rate": 1.6178184486554153e-05,
103
+ "loss": 0.2675,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "eval_bleu": 0.1808116458772577,
109
+ "eval_brevity_penalty": 0.19861645424842622,
110
+ "eval_length_ratio": 0.38220752431158117,
111
+ "eval_loss": 0.23520636558532715,
112
+ "eval_precision": [
113
+ 0.9478925726034438,
114
+ 0.9158530513281233,
115
+ 0.8966822777607564,
116
+ 0.8823099900431464
117
+ ],
118
+ "eval_reference_length": 122164,
119
+ "eval_rouge1": 0.5753014504995342,
120
+ "eval_rouge2": 0.5030760004413073,
121
+ "eval_rougeL": 0.5727839893077595,
122
+ "eval_rougeLsum": 0.5728460049962187,
123
+ "eval_runtime": 18.8244,
124
+ "eval_samples_per_second": 26.508,
125
+ "eval_steps_per_second": 1.7,
126
+ "eval_translation_length": 46692,
127
+ "step": 7722
128
+ },
129
+ {
130
+ "epoch": 3.108003108003108,
131
+ "grad_norm": 0.6161249876022339,
132
+ "learning_rate": 1.5314887555574744e-05,
133
+ "loss": 0.2398,
134
+ "step": 8000
135
+ },
136
+ {
137
+ "epoch": 3.4965034965034967,
138
+ "grad_norm": 1.6779487133026123,
139
+ "learning_rate": 1.4451590624595331e-05,
140
+ "loss": 0.2417,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 3.885003885003885,
145
+ "grad_norm": 2.843812942504883,
146
+ "learning_rate": 1.358829369361592e-05,
147
+ "loss": 0.2158,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 4.0,
152
+ "eval_bleu": 0.17801619314081785,
153
+ "eval_brevity_penalty": 0.191822271170218,
154
+ "eval_length_ratio": 0.37718967944730036,
155
+ "eval_loss": 0.2111208736896515,
156
+ "eval_precision": [
157
+ 0.9607413355324551,
158
+ 0.933106625713032,
159
+ 0.9160400168585435,
160
+ 0.9032120586783904
161
+ ],
162
+ "eval_reference_length": 122164,
163
+ "eval_rouge1": 0.5886785555645666,
164
+ "eval_rouge2": 0.5201397565281654,
165
+ "eval_rougeL": 0.5869242299058745,
166
+ "eval_rougeLsum": 0.5861840822637108,
167
+ "eval_runtime": 18.8078,
168
+ "eval_samples_per_second": 26.531,
169
+ "eval_steps_per_second": 1.701,
170
+ "eval_translation_length": 46079,
171
+ "step": 10296
172
+ },
173
+ {
174
+ "epoch": 4.273504273504273,
175
+ "grad_norm": 2.379423141479492,
176
+ "learning_rate": 1.272499676263651e-05,
177
+ "loss": 0.1729,
178
+ "step": 11000
179
+ },
180
+ {
181
+ "epoch": 4.662004662004662,
182
+ "grad_norm": 1.91653573513031,
183
+ "learning_rate": 1.1861699831657098e-05,
184
+ "loss": 0.1642,
185
+ "step": 12000
186
+ },
187
+ {
188
+ "epoch": 5.0,
189
+ "eval_bleu": 0.1823442196189086,
190
+ "eval_brevity_penalty": 0.19671547931653868,
191
+ "eval_length_ratio": 0.38080776660882093,
192
+ "eval_loss": 0.20280706882476807,
193
+ "eval_precision": [
194
+ 0.9568796887427183,
195
+ 0.9317065751162488,
196
+ 0.9159765393317664,
197
+ 0.9040511727078892
198
+ ],
199
+ "eval_reference_length": 122164,
200
+ "eval_rouge1": 0.5879582047830807,
201
+ "eval_rouge2": 0.5212475025432189,
202
+ "eval_rougeL": 0.585827617514701,
203
+ "eval_rougeLsum": 0.5861708445100655,
204
+ "eval_runtime": 18.7558,
205
+ "eval_samples_per_second": 26.605,
206
+ "eval_steps_per_second": 1.706,
207
+ "eval_translation_length": 46521,
208
+ "step": 12870
209
+ }
210
+ ],
211
+ "logging_steps": 1000,
212
+ "max_steps": 25740,
213
+ "num_input_tokens_seen": 0,
214
+ "num_train_epochs": 10,
215
+ "save_steps": 500,
216
+ "stateful_callbacks": {
217
+ "TrainerControl": {
218
+ "args": {
219
+ "should_epoch_stop": false,
220
+ "should_evaluate": false,
221
+ "should_log": false,
222
+ "should_save": true,
223
+ "should_training_stop": false
224
+ },
225
+ "attributes": {}
226
+ }
227
+ },
228
+ "total_flos": 1.561183084224e+16,
229
+ "train_batch_size": 4,
230
+ "trial_name": null,
231
+ "trial_params": null
232
+ }
checkpoint-12870/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a12054d6904e59239ad3e26f92b5dede560ea9f82e255a690b80c1458f2da49
3
+ size 5560
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": -1,
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.1751331117.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70463e8da76da778c5c69cc73fd5714ea607218d0448f32788b506a45c818d1
3
+ size 19676
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:b2155bd898f7d682310830260ee9d5dfb795a85286cc7ba4135bed4e3f31aa56
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.7687777535927394,
3
+ "rouge2": 0.701621647293527,
4
+ "rougeL": 0.7661955737535495,
5
+ "rougeLsum": 0.7662789955746854,
6
+ "bleu": 0.7076512154855271,
7
+ "precision": [
8
+ 0.7385320948140056,
9
+ 0.7112657935980163,
10
+ 0.6963966591897429,
11
+ 0.6855182993497079
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 1.3186543402358417,
15
+ "translation_length": 300251,
16
+ "reference_length": 227695
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a12054d6904e59239ad3e26f92b5dede560ea9f82e255a690b80c1458f2da49
3
+ size 5560