Hugging Face's logo

mootez
/
mean_codet5-base_L7_codetrans_442_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
9cc02cc
·
verified ·
1 Parent(s): b09f524

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.1751436097.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": 7,
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:db57f2bb141255c8c473b7e19bbd933ea84673db3115a52dd290afdf740f5bdc
3
+ size 891558696
checkpoint-12870/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9078f5d00c778478b130ac94322ec6dba6a8170360b396238bd50742cf0a47b
3
+ size 1783272762
checkpoint-12870/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b7345a3aa08f3e5e490afa69ad9b0fa6a4b713ede7f3cdf0dad785319a60de3
3
+ size 14308
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": 0.18551164301133388,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L7_codetrans_442_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": 6.495007514953613,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.5448,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 1.7273328304290771,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.563,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.1787074252070195,
28
+ "eval_brevity_penalty": 0.19950727876449212,
29
+ "eval_length_ratio": 0.38286238171638126,
30
+ "eval_loss": 0.30551767349243164,
31
+ "eval_precision": [
32
+ 0.9421234926879329,
33
+ 0.9039180515635468,
34
+ 0.8791016734390702,
35
+ 0.8599226946438432
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5642371053445977,
39
+ "eval_rouge2": 0.48076165164861834,
40
+ "eval_rougeL": 0.5624538384580327,
41
+ "eval_rougeLsum": 0.5617830792278664,
42
+ "eval_runtime": 19.1277,
43
+ "eval_samples_per_second": 26.088,
44
+ "eval_steps_per_second": 1.673,
45
+ "eval_translation_length": 46772,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 1.8221752643585205,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.3981,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 1.4747304916381836,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3117,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 2.1533384323120117,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.2756,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.18383999203142062,
72
+ "eval_brevity_penalty": 0.201448032993067,
73
+ "eval_length_ratio": 0.38428669657182146,
74
+ "eval_loss": 0.2143673449754715,
75
+ "eval_precision": [
76
+ 0.9456183700421761,
77
+ 0.9176480719960385,
78
+ 0.9004309219117262,
79
+ 0.8876982991925015
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.5828807652876636,
83
+ "eval_rouge2": 0.5136653805682427,
84
+ "eval_rougeL": 0.581186639780386,
85
+ "eval_rougeLsum": 0.5807404455392673,
86
+ "eval_runtime": 19.1868,
87
+ "eval_samples_per_second": 26.007,
88
+ "eval_steps_per_second": 1.668,
89
+ "eval_translation_length": 46946,
90
+ "step": 5148
91
+ },
92
+ {
93
+ "epoch": 2.331002331002331,
94
+ "grad_norm": 0.6225597858428955,
95
+ "learning_rate": 1.7041481417533562e-05,
96
+ "loss": 0.2209,
97
+ "step": 6000
98
+ },
99
+ {
100
+ "epoch": 2.7195027195027195,
101
+ "grad_norm": 1.138798713684082,
102
+ "learning_rate": 1.6178184486554153e-05,
103
+ "loss": 0.205,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "eval_bleu": 0.18480701105889244,
109
+ "eval_brevity_penalty": 0.20093453521864071,
110
+ "eval_length_ratio": 0.38391015356406144,
111
+ "eval_loss": 0.18702617287635803,
112
+ "eval_precision": [
113
+ 0.9495309168443496,
114
+ 0.923773194543221,
115
+ 0.9085442900091499,
116
+ 0.8979142347421977
117
+ ],
118
+ "eval_reference_length": 122164,
119
+ "eval_rouge1": 0.5901999828777156,
120
+ "eval_rouge2": 0.5297298196214844,
121
+ "eval_rougeL": 0.588797599784242,
122
+ "eval_rougeLsum": 0.5888212415746322,
123
+ "eval_runtime": 19.3596,
124
+ "eval_samples_per_second": 25.775,
125
+ "eval_steps_per_second": 1.653,
126
+ "eval_translation_length": 46900,
127
+ "step": 7722
128
+ },
129
+ {
130
+ "epoch": 3.108003108003108,
131
+ "grad_norm": 0.828457236289978,
132
+ "learning_rate": 1.5314887555574744e-05,
133
+ "loss": 0.1876,
134
+ "step": 8000
135
+ },
136
+ {
137
+ "epoch": 3.4965034965034967,
138
+ "grad_norm": 1.3880107402801514,
139
+ "learning_rate": 1.4451590624595331e-05,
140
+ "loss": 0.1563,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 3.885003885003885,
145
+ "grad_norm": 2.9686758518218994,
146
+ "learning_rate": 1.358829369361592e-05,
147
+ "loss": 0.1584,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 4.0,
152
+ "eval_bleu": 0.18300966391061504,
153
+ "eval_brevity_penalty": 0.19681542234269878,
154
+ "eval_length_ratio": 0.3808814380668609,
155
+ "eval_loss": 0.17582254111766815,
156
+ "eval_precision": [
157
+ 0.9553191489361702,
158
+ 0.9338923768764529,
159
+ 0.9201879996485988,
160
+ 0.910621100082162
161
+ ],
162
+ "eval_reference_length": 122164,
163
+ "eval_rouge1": 0.5975744821021296,
164
+ "eval_rouge2": 0.53787746936802,
165
+ "eval_rougeL": 0.5951149670507435,
166
+ "eval_rougeLsum": 0.5947690677861345,
167
+ "eval_runtime": 18.9238,
168
+ "eval_samples_per_second": 26.369,
169
+ "eval_steps_per_second": 1.691,
170
+ "eval_translation_length": 46530,
171
+ "step": 10296
172
+ },
173
+ {
174
+ "epoch": 4.273504273504273,
175
+ "grad_norm": 2.2694826126098633,
176
+ "learning_rate": 1.272499676263651e-05,
177
+ "loss": 0.1292,
178
+ "step": 11000
179
+ },
180
+ {
181
+ "epoch": 4.662004662004662,
182
+ "grad_norm": 1.614131212234497,
183
+ "learning_rate": 1.1861699831657098e-05,
184
+ "loss": 0.1269,
185
+ "step": 12000
186
+ },
187
+ {
188
+ "epoch": 5.0,
189
+ "eval_bleu": 0.18551164301133388,
190
+ "eval_brevity_penalty": 0.19945157482573786,
191
+ "eval_length_ratio": 0.38282145312858123,
192
+ "eval_loss": 0.16799628734588623,
193
+ "eval_precision": [
194
+ 0.9531293433403896,
195
+ 0.9332367943286937,
196
+ 0.9214752343289125,
197
+ 0.9130770929975701
198
+ ],
199
+ "eval_reference_length": 122164,
200
+ "eval_rouge1": 0.5982959367308609,
201
+ "eval_rouge2": 0.5395764381343156,
202
+ "eval_rougeL": 0.5974539411137365,
203
+ "eval_rougeLsum": 0.5970119750263054,
204
+ "eval_runtime": 19.2682,
205
+ "eval_samples_per_second": 25.898,
206
+ "eval_steps_per_second": 1.661,
207
+ "eval_translation_length": 46767,
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 sha256:75a727e81693568d5467fd069bcffcc52d2341ac80994b963b7d158dba286de4
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": 7,
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.1751436097.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e282247c89395da19923bc77a66875da45b97bf0e716ee34a78b641b9b37962
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:db57f2bb141255c8c473b7e19bbd933ea84673db3115a52dd290afdf740f5bdc
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.6909560114914022,
3
+ "rouge2": 0.64165528127345,
4
+ "rougeL": 0.6884189938617651,
5
+ "rougeLsum": 0.6881761076621264,
6
+ "bleu": 0.5866306854590718,
7
+ "precision": [
8
+ 0.606851717809207,
9
+ 0.5889646098768319,
10
+ 0.579176331735133,
11
+ 0.5721060155081983
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 1.620022398383803,
15
+ "translation_length": 368871,
16
+ "reference_length": 227695
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a727e81693568d5467fd069bcffcc52d2341ac80994b963b7d158dba286de4
3
+ size 5496