Hugging Face's logo

mootez
/
mean_codet5-base_L4_codetrans_42_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
8a68447
·
verified ·
1 Parent(s): f3f4b51

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.1751271826.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:f761fb21be013bb9dca2b5bbb6900c7a42f000acaa1dc10d8d9d531e383cb162
3
+ size 891558696
checkpoint-10296/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceaf8854ee61f7286fc46fc8f012277df10368d37b513809fdd62eeb5d1ed731
3
+ size 1783272762
checkpoint-10296/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5abe837a917ac021c4e7c67a79bbfa9a4176a54ee3ded27e97e7de090ba8d051
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": 0.18502690833725535,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L4_codetrans_42_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": 5.059429168701172,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.9198,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 8.028949737548828,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.6301,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.17513153335078996,
28
+ "eval_brevity_penalty": 0.19501830836999579,
29
+ "eval_length_ratio": 0.37955535182214073,
30
+ "eval_loss": 0.3206598162651062,
31
+ "eval_precision": [
32
+ 0.9479166666666666,
33
+ 0.9063201726656347,
34
+ 0.8802733083535376,
35
+ 0.8599763767243876
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5574049075503735,
39
+ "eval_rouge2": 0.46807419203017747,
40
+ "eval_rougeL": 0.5560015875426754,
41
+ "eval_rougeLsum": 0.5555459907606788,
42
+ "eval_runtime": 18.805,
43
+ "eval_samples_per_second": 26.536,
44
+ "eval_steps_per_second": 1.702,
45
+ "eval_translation_length": 46368,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 1.6692451238632202,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.4306,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 41.96001052856445,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3436,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 0.8263127207756042,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.2852,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.1838696657590005,
72
+ "eval_brevity_penalty": 0.20177191571465775,
73
+ "eval_length_ratio": 0.3845240823810615,
74
+ "eval_loss": 0.23108235001564026,
75
+ "eval_precision": [
76
+ 0.9467376263970196,
77
+ 0.917140029262415,
78
+ 0.8982099745524936,
79
+ 0.8842077488016183
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.580490766066877,
83
+ "eval_rouge2": 0.5096987216086977,
84
+ "eval_rougeL": 0.5781306493262742,
85
+ "eval_rougeLsum": 0.5788605499902097,
86
+ "eval_runtime": 18.8877,
87
+ "eval_samples_per_second": 26.419,
88
+ "eval_steps_per_second": 1.694,
89
+ "eval_translation_length": 46975,
90
+ "step": 5148
91
+ },
92
+ {
93
+ "epoch": 2.331002331002331,
94
+ "grad_norm": 4.286065578460693,
95
+ "learning_rate": 1.7041481417533562e-05,
96
+ "loss": 0.2414,
97
+ "step": 6000
98
+ },
99
+ {
100
+ "epoch": 2.7195027195027195,
101
+ "grad_norm": 1.2189191579818726,
102
+ "learning_rate": 1.6178184486554153e-05,
103
+ "loss": 0.2144,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "eval_bleu": 0.1843215083480773,
109
+ "eval_brevity_penalty": 0.19927334672994573,
110
+ "eval_length_ratio": 0.3826904816476212,
111
+ "eval_loss": 0.19521166384220123,
112
+ "eval_precision": [
113
+ 0.9533913713075656,
114
+ 0.9296679062527026,
115
+ 0.9145629794767556,
116
+ 0.903014098201264
117
+ ],
118
+ "eval_reference_length": 122164,
119
+ "eval_rouge1": 0.5940572498733779,
120
+ "eval_rouge2": 0.5314994433063771,
121
+ "eval_rougeL": 0.5924544378127226,
122
+ "eval_rougeLsum": 0.5915398871320761,
123
+ "eval_runtime": 18.8157,
124
+ "eval_samples_per_second": 26.52,
125
+ "eval_steps_per_second": 1.701,
126
+ "eval_translation_length": 46751,
127
+ "step": 7722
128
+ },
129
+ {
130
+ "epoch": 3.108003108003108,
131
+ "grad_norm": 2.464669942855835,
132
+ "learning_rate": 1.5314887555574744e-05,
133
+ "loss": 0.1947,
134
+ "step": 8000
135
+ },
136
+ {
137
+ "epoch": 3.4965034965034967,
138
+ "grad_norm": 3.54685378074646,
139
+ "learning_rate": 1.4451590624595331e-05,
140
+ "loss": 0.1698,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 3.885003885003885,
145
+ "grad_norm": 2.13301682472229,
146
+ "learning_rate": 1.358829369361592e-05,
147
+ "loss": 0.1603,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 4.0,
152
+ "eval_bleu": 0.18502690833725535,
153
+ "eval_brevity_penalty": 0.1996632691728262,
154
+ "eval_length_ratio": 0.3829769817622213,
155
+ "eval_loss": 0.1788550317287445,
156
+ "eval_precision": [
157
+ 0.95280639507545,
158
+ 0.9303260094627002,
159
+ 0.9169433039224251,
160
+ 0.907328490361898
161
+ ],
162
+ "eval_reference_length": 122164,
163
+ "eval_rouge1": 0.5951919077794819,
164
+ "eval_rouge2": 0.536819313999854,
165
+ "eval_rougeL": 0.5935692291004774,
166
+ "eval_rougeLsum": 0.593401448924133,
167
+ "eval_runtime": 18.885,
168
+ "eval_samples_per_second": 26.423,
169
+ "eval_steps_per_second": 1.694,
170
+ "eval_translation_length": 46786,
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 sha256:3683877c79bcd23c5ba783eec15e135ab6ea6a7a716f3bf0a54a5105fb854850
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.1751271826.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f348babf972614f159ecebf92ffc156b982a1c731ec16eca3ea44f82436cc2e
3
+ size 19656
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:f761fb21be013bb9dca2b5bbb6900c7a42f000acaa1dc10d8d9d531e383cb162
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.6973602156680194,
3
+ "rouge2": 0.6457183277002405,
4
+ "rougeL": 0.6952217366983899,
5
+ "rougeLsum": 0.6955099363126505,
6
+ "bleu": 0.5783348358666442,
7
+ "precision": [
8
+ 0.6005673484518802,
9
+ 0.5810460650006195,
10
+ 0.5702159035051234,
11
+ 0.5622193696548213
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 1.6348975603329015,
15
+ "translation_length": 372258,
16
+ "reference_length": 227695
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3683877c79bcd23c5ba783eec15e135ab6ea6a7a716f3bf0a54a5105fb854850
3
+ size 5496