Hugging Face's logo

mootez
/
mean_codet5-base_L2_codetrans_442_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
3da1f9a
·
verified ·
1 Parent(s): e1a313b

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.1751395527.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": 2,
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:edd3623a0c7a5ae08fc087b96eb0f352724616622a1324f2c8a7a60fc558ac0b
3
+ size 891558696
checkpoint-10296/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad6d0e54ea11524b06f97739a4c71b9c88b7f85b7c68c458e0f3fbaa1cb2dc8
3
+ size 1783272762
checkpoint-10296/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b348006ce2192ead4a773f09061e077a6d8e9bfdc89cf29b8b08becd515b6ab
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": 0.1819113462104956,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L2_codetrans_442_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": 11.437652587890625,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.9544,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 2.074025869369507,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.6614,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.17581799183418562,
28
+ "eval_brevity_penalty": 0.19771545244825556,
29
+ "eval_length_ratio": 0.3815444811892211,
30
+ "eval_loss": 0.34343767166137695,
31
+ "eval_precision": [
32
+ 0.9410439595803566,
33
+ 0.8987465301873698,
34
+ 0.8707166816477758,
35
+ 0.8491155738795052
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5527980080964796,
39
+ "eval_rouge2": 0.4592757695774039,
40
+ "eval_rougeL": 0.5508506529848021,
41
+ "eval_rougeLsum": 0.5499347189800947,
42
+ "eval_runtime": 19.0103,
43
+ "eval_samples_per_second": 26.249,
44
+ "eval_steps_per_second": 1.683,
45
+ "eval_translation_length": 46611,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 1.7023669481277466,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.4541,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 2.068265914916992,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3561,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 2.4472858905792236,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.3104,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.18033709283012186,
72
+ "eval_brevity_penalty": 0.1974597892223877,
73
+ "eval_length_ratio": 0.381356209685341,
74
+ "eval_loss": 0.23533561825752258,
75
+ "eval_precision": [
76
+ 0.9504593457542715,
77
+ 0.919698843541843,
78
+ 0.8997148497477517,
79
+ 0.8845889423610033
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.579125596297132,
83
+ "eval_rouge2": 0.5078281042760053,
84
+ "eval_rougeL": 0.5770340195932717,
85
+ "eval_rougeLsum": 0.5768180395149111,
86
+ "eval_runtime": 18.7409,
87
+ "eval_samples_per_second": 26.626,
88
+ "eval_steps_per_second": 1.707,
89
+ "eval_translation_length": 46588,
90
+ "step": 5148
91
+ },
92
+ {
93
+ "epoch": 2.331002331002331,
94
+ "grad_norm": 0.5705050826072693,
95
+ "learning_rate": 1.7041481417533562e-05,
96
+ "loss": 0.2487,
97
+ "step": 6000
98
+ },
99
+ {
100
+ "epoch": 2.7195027195027195,
101
+ "grad_norm": 0.9405382871627808,
102
+ "learning_rate": 1.6178184486554153e-05,
103
+ "loss": 0.2302,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "eval_bleu": 0.1813550657687129,
109
+ "eval_brevity_penalty": 0.19657113853740538,
110
+ "eval_length_ratio": 0.3807013522805409,
111
+ "eval_loss": 0.20334023237228394,
112
+ "eval_precision": [
113
+ 0.9557065451105187,
114
+ 0.927709795909496,
115
+ 0.9103493737640079,
116
+ 0.8976250249938904
117
+ ],
118
+ "eval_reference_length": 122164,
119
+ "eval_rouge1": 0.588127467997223,
120
+ "eval_rouge2": 0.5222627263750141,
121
+ "eval_rougeL": 0.5863215561719027,
122
+ "eval_rougeLsum": 0.5861403106249515,
123
+ "eval_runtime": 18.7138,
124
+ "eval_samples_per_second": 26.665,
125
+ "eval_steps_per_second": 1.71,
126
+ "eval_translation_length": 46508,
127
+ "step": 7722
128
+ },
129
+ {
130
+ "epoch": 3.108003108003108,
131
+ "grad_norm": 1.5927886962890625,
132
+ "learning_rate": 1.5314887555574744e-05,
133
+ "loss": 0.2107,
134
+ "step": 8000
135
+ },
136
+ {
137
+ "epoch": 3.4965034965034967,
138
+ "grad_norm": 2.392258644104004,
139
+ "learning_rate": 1.4451590624595331e-05,
140
+ "loss": 0.1768,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 3.885003885003885,
145
+ "grad_norm": 3.214343786239624,
146
+ "learning_rate": 1.358829369361592e-05,
147
+ "loss": 0.1756,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 4.0,
152
+ "eval_bleu": 0.1819113462104956,
153
+ "eval_brevity_penalty": 0.1961604609718297,
154
+ "eval_length_ratio": 0.3803984807308209,
155
+ "eval_loss": 0.19017913937568665,
156
+ "eval_precision": [
157
+ 0.9550041961653505,
158
+ 0.9314800313234143,
159
+ 0.9170716689024256,
160
+ 0.9065904744963756
161
+ ],
162
+ "eval_reference_length": 122164,
163
+ "eval_rouge1": 0.5922705004192614,
164
+ "eval_rouge2": 0.5295522158979451,
165
+ "eval_rougeL": 0.5890987630109429,
166
+ "eval_rougeLsum": 0.5888372485854158,
167
+ "eval_runtime": 18.7406,
168
+ "eval_samples_per_second": 26.627,
169
+ "eval_steps_per_second": 1.708,
170
+ "eval_translation_length": 46471,
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:e0344ae8f7fe731d4073f31647ef18611e9b7ad495f425da7eb2465fe2642579
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": 2,
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.1751395527.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dcfe8b044fbf46659bcde37a9df71d27e8d84365d4bcaf2236bf59c2544999
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:edd3623a0c7a5ae08fc087b96eb0f352724616622a1324f2c8a7a60fc558ac0b
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.7205357142262272,
3
+ "rouge2": 0.6634753268701523,
4
+ "rougeL": 0.718802168034474,
5
+ "rougeLsum": 0.7184898885038276,
6
+ "bleu": 0.6235991102849054,
7
+ "precision": [
8
+ 0.6481904283645537,
9
+ 0.6263762327531682,
10
+ 0.614618574382107,
11
+ 0.6060080350620891
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 1.5042578888425306,
15
+ "translation_length": 342512,
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:e0344ae8f7fe731d4073f31647ef18611e9b7ad495f425da7eb2465fe2642579
3
+ size 5496