Hugging Face's logo

mootez
/
mean_codet5-base_L4_codetrans_123456_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
5ddf9ac
·
verified ·
1 Parent(s): e5c8939

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-10296/config.json +71 -0
  2. checkpoint-10296/generation_config.json +7 -0
  3. checkpoint-10296/model.safetensors +3 -0
  4. checkpoint-10296/optimizer.pt +3 -0
  5. checkpoint-10296/rng_state.pth +3 -0
  6. checkpoint-10296/scheduler.pt +3 -0
  7. checkpoint-10296/trainer_state.json +195 -0
  8. checkpoint-10296/training_args.bin +3 -0
  9. config.json +71 -0
  10. events.out.tfevents.1751348775.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-10296/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-10296/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-10296/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86fe34e741e40e622abcfde4c1a3123f7184dc0ec35d8ac87599df06e92bb738
3
+ size 891558696
checkpoint-10296/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587fb006ba50347356897e9885b85eff937e0558236edc511c2310f1775c9804
3
+ size 1783272762
checkpoint-10296/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0594007f6406638a62604e82e2d87f2212f1896051c37e90e73c3e3e3781c1f3
3
+ size 14244
checkpoint-10296/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c28311f6399e25df902acc349a8d1c89c4b5fa45b22963b5ad8849f17036f75
3
+ size 1064
checkpoint-10296/trainer_state.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1855298314949407,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L4_codetrans_123456_src_java_tgt_c_sharp/checkpoint-10296",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10296,
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": 5.802654266357422,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.9578,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 4.857819080352783,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.6291,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.1772830345505683,
28
+ "eval_brevity_penalty": 0.19975241936026752,
29
+ "eval_length_ratio": 0.38304246750270127,
30
+ "eval_loss": 0.3279988467693329,
31
+ "eval_precision": [
32
+ 0.94093259819635,
33
+ 0.8966843071606005,
34
+ 0.8684601275220544,
35
+ 0.8467448175375852
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5509379066788893,
39
+ "eval_rouge2": 0.46051561399200247,
40
+ "eval_rougeL": 0.5482451711514551,
41
+ "eval_rougeLsum": 0.5487366798116411,
42
+ "eval_runtime": 18.8576,
43
+ "eval_samples_per_second": 26.461,
44
+ "eval_steps_per_second": 1.697,
45
+ "eval_translation_length": 46794,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 3.677903890609741,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.4293,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 1.9280270338058472,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3291,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 2.334867238998413,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.3018,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.18163008492339927,
72
+ "eval_brevity_penalty": 0.19901720936597375,
73
+ "eval_length_ratio": 0.3825022101437412,
74
+ "eval_loss": 0.2291223704814911,
75
+ "eval_precision": [
76
+ 0.9489171374764596,
77
+ 0.9188171926712669,
78
+ 0.899562650338946,
79
+ 0.8845039906258981
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.577217726624812,
83
+ "eval_rouge2": 0.5056665889432481,
84
+ "eval_rougeL": 0.5748070076808849,
85
+ "eval_rougeLsum": 0.5749545145284172,
86
+ "eval_runtime": 18.751,
87
+ "eval_samples_per_second": 26.612,
88
+ "eval_steps_per_second": 1.707,
89
+ "eval_translation_length": 46728,
90
+ "step": 5148
91
+ },
92
+ {
93
+ "epoch": 2.331002331002331,
94
+ "grad_norm": 4.064742088317871,
95
+ "learning_rate": 1.7041481417533562e-05,
96
+ "loss": 0.2324,
97
+ "step": 6000
98
+ },
99
+ {
100
+ "epoch": 2.7195027195027195,
101
+ "grad_norm": 3.501546621322632,
102
+ "learning_rate": 1.6178184486554153e-05,
103
+ "loss": 0.2237,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "eval_bleu": 0.18179321129068196,
109
+ "eval_brevity_penalty": 0.19594965232716222,
110
+ "eval_length_ratio": 0.38024295209718084,
111
+ "eval_loss": 0.19570493698120117,
112
+ "eval_precision": [
113
+ 0.9560406441057435,
114
+ 0.9324092007050683,
115
+ 0.9171690060280724,
116
+ 0.9061505950394839
117
+ ],
118
+ "eval_reference_length": 122164,
119
+ "eval_rouge1": 0.5926674273276937,
120
+ "eval_rouge2": 0.5298894808875569,
121
+ "eval_rougeL": 0.589722627964707,
122
+ "eval_rougeLsum": 0.5899626913539586,
123
+ "eval_runtime": 18.8095,
124
+ "eval_samples_per_second": 26.529,
125
+ "eval_steps_per_second": 1.701,
126
+ "eval_translation_length": 46452,
127
+ "step": 7722
128
+ },
129
+ {
130
+ "epoch": 3.108003108003108,
131
+ "grad_norm": 0.4406058192253113,
132
+ "learning_rate": 1.5314887555574744e-05,
133
+ "loss": 0.201,
134
+ "step": 8000
135
+ },
136
+ {
137
+ "epoch": 3.4965034965034967,
138
+ "grad_norm": 1.0749797821044922,
139
+ "learning_rate": 1.4451590624595331e-05,
140
+ "loss": 0.1631,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 3.885003885003885,
145
+ "grad_norm": 1.0471420288085938,
146
+ "learning_rate": 1.358829369361592e-05,
147
+ "loss": 0.1651,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 4.0,
152
+ "eval_bleu": 0.1855298314949407,
153
+ "eval_brevity_penalty": 0.20025406238559892,
154
+ "eval_length_ratio": 0.38341082479290134,
155
+ "eval_loss": 0.18395639955997467,
156
+ "eval_precision": [
157
+ 0.951194517389355,
158
+ 0.9301251618472163,
159
+ 0.9172356623982897,
160
+ 0.907899960301707
161
+ ],
162
+ "eval_reference_length": 122164,
163
+ "eval_rouge1": 0.5939747000734671,
164
+ "eval_rouge2": 0.5361698172603362,
165
+ "eval_rougeL": 0.592602683185397,
166
+ "eval_rougeLsum": 0.5918455400914109,
167
+ "eval_runtime": 18.798,
168
+ "eval_samples_per_second": 26.545,
169
+ "eval_steps_per_second": 1.702,
170
+ "eval_translation_length": 46839,
171
+ "step": 10296
172
+ }
173
+ ],
174
+ "logging_steps": 1000,
175
+ "max_steps": 25740,
176
+ "num_input_tokens_seen": 0,
177
+ "num_train_epochs": 10,
178
+ "save_steps": 500,
179
+ "stateful_callbacks": {
180
+ "TrainerControl": {
181
+ "args": {
182
+ "should_epoch_stop": false,
183
+ "should_evaluate": false,
184
+ "should_log": false,
185
+ "should_save": true,
186
+ "should_training_stop": false
187
+ },
188
+ "attributes": {}
189
+ }
190
+ },
191
+ "total_flos": 1.2489464673792e+16,
192
+ "train_batch_size": 4,
193
+ "trial_name": null,
194
+ "trial_params": null
195
+ }
checkpoint-10296/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b2d5008a4a00060d21462d0a036fc3a15de7c3d6ddb21af2c37777251523cc
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": 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.1751348775.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2264f9e4ada2ff117b6cee61a10dc1aedb12ddba905423886df9f80dfedb3dd5
3
+ size 19672
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 sha256:86fe34e741e40e622abcfde4c1a3123f7184dc0ec35d8ac87599df06e92bb738
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.6845874219603704,
3
+ "rouge2": 0.6288075544008674,
4
+ "rougeL": 0.6828323694639982,
5
+ "rougeLsum": 0.6824170832698826,
6
+ "bleu": 0.5875857588641488,
7
+ "precision": [
8
+ 0.6105206002369357,
9
+ 0.590181380205469,
10
+ 0.5792128077296391,
11
+ 0.5711643108368173
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 1.601510792946705,
15
+ "translation_length": 364656,
16
+ "reference_length": 227695
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b2d5008a4a00060d21462d0a036fc3a15de7c3d6ddb21af2c37777251523cc
3
+ size 5560