upload checkpoints
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- graphcodebert-vanilla/checkpoint-100/config.json +29 -0
- graphcodebert-vanilla/checkpoint-100/config_hyperparams.json +53 -0
- graphcodebert-vanilla/checkpoint-100/hyperparams.json +39 -0
- graphcodebert-vanilla/checkpoint-100/merges.txt +0 -0
- graphcodebert-vanilla/checkpoint-100/model.safetensors +3 -0
- graphcodebert-vanilla/checkpoint-100/optimizer.pt +3 -0
- graphcodebert-vanilla/checkpoint-100/rng_state.pth +3 -0
- graphcodebert-vanilla/checkpoint-100/scaler.pt +3 -0
- graphcodebert-vanilla/checkpoint-100/scheduler.pt +3 -0
- graphcodebert-vanilla/checkpoint-100/special_tokens_map.json +51 -0
- graphcodebert-vanilla/checkpoint-100/tokenizer.json +0 -0
- graphcodebert-vanilla/checkpoint-100/tokenizer_config.json +58 -0
- graphcodebert-vanilla/checkpoint-100/trainer_state.json +207 -0
- graphcodebert-vanilla/checkpoint-100/training_args.bin +3 -0
- graphcodebert-vanilla/checkpoint-100/vocab.json +0 -0
- graphcodebert-vanilla/checkpoint-200/config.json +29 -0
- graphcodebert-vanilla/checkpoint-200/config_hyperparams.json +53 -0
- graphcodebert-vanilla/checkpoint-200/hyperparams.json +39 -0
- graphcodebert-vanilla/checkpoint-200/merges.txt +0 -0
- graphcodebert-vanilla/checkpoint-200/model.safetensors +3 -0
- graphcodebert-vanilla/checkpoint-200/optimizer.pt +3 -0
- graphcodebert-vanilla/checkpoint-200/rng_state.pth +3 -0
- graphcodebert-vanilla/checkpoint-200/scaler.pt +3 -0
- graphcodebert-vanilla/checkpoint-200/scheduler.pt +3 -0
- graphcodebert-vanilla/checkpoint-200/special_tokens_map.json +51 -0
- graphcodebert-vanilla/checkpoint-200/tokenizer.json +0 -0
- graphcodebert-vanilla/checkpoint-200/tokenizer_config.json +58 -0
- graphcodebert-vanilla/checkpoint-200/trainer_state.json +371 -0
- graphcodebert-vanilla/checkpoint-200/training_args.bin +3 -0
- graphcodebert-vanilla/checkpoint-200/vocab.json +0 -0
- graphcodebert-vanilla/checkpoint-300/config.json +29 -0
- graphcodebert-vanilla/checkpoint-300/config_hyperparams.json +53 -0
- graphcodebert-vanilla/checkpoint-300/hyperparams.json +39 -0
- graphcodebert-vanilla/checkpoint-300/merges.txt +0 -0
- graphcodebert-vanilla/checkpoint-300/model.safetensors +3 -0
- graphcodebert-vanilla/checkpoint-300/optimizer.pt +3 -0
- graphcodebert-vanilla/checkpoint-300/rng_state.pth +3 -0
- graphcodebert-vanilla/checkpoint-300/scaler.pt +3 -0
- graphcodebert-vanilla/checkpoint-300/scheduler.pt +3 -0
- graphcodebert-vanilla/checkpoint-300/special_tokens_map.json +51 -0
- graphcodebert-vanilla/checkpoint-300/tokenizer.json +0 -0
- graphcodebert-vanilla/checkpoint-300/tokenizer_config.json +58 -0
- graphcodebert-vanilla/checkpoint-300/trainer_state.json +535 -0
- graphcodebert-vanilla/checkpoint-300/training_args.bin +3 -0
- graphcodebert-vanilla/checkpoint-300/vocab.json +0 -0
- graphcodebert-vanilla/final_model/config.json +29 -0
- graphcodebert-vanilla/final_model/merges.txt +0 -0
- graphcodebert-vanilla/final_model/model.safetensors +3 -0
- graphcodebert-vanilla/final_model/special_tokens_map.json +51 -0
- graphcodebert-vanilla/final_model/tokenizer.json +0 -0
graphcodebert-vanilla/checkpoint-100/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.3,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": 0.3,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.3,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"transformers_version": "4.56.0",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50265
|
| 29 |
+
}
|
graphcodebert-vanilla/checkpoint-100/config_hyperparams.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train_config": {
|
| 3 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 4 |
+
"num_epochs": 3,
|
| 5 |
+
"batch_size": 256,
|
| 6 |
+
"learning_rate": 2e-05,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"num_labels": 2,
|
| 9 |
+
"loss_type": "ce",
|
| 10 |
+
"focal_alpha": 1.0,
|
| 11 |
+
"focal_gamma": 2.0,
|
| 12 |
+
"r_drop_alpha": 6.0,
|
| 13 |
+
"infonce_temperature": 0.07,
|
| 14 |
+
"infonce_weight": 0.5,
|
| 15 |
+
"label_smoothing": 0,
|
| 16 |
+
"adversarial_epsilon": 0,
|
| 17 |
+
"use_swa": false,
|
| 18 |
+
"swa_start_epoch": 0,
|
| 19 |
+
"swa_lr": 1e-05,
|
| 20 |
+
"data_augmentation": false,
|
| 21 |
+
"aug_rename_prob": 0.0,
|
| 22 |
+
"aug_format_prob": 0.0,
|
| 23 |
+
"freeze_base": true,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"use_wandb": true,
|
| 26 |
+
"mixup_alpha": 0.0,
|
| 27 |
+
"low_pass_keep_ratio": 0.5,
|
| 28 |
+
"freq_consistency_weight": 0.0
|
| 29 |
+
},
|
| 30 |
+
"training_arguments": {
|
| 31 |
+
"output_dir": "output_checkpoints/graphcodebert-vanilla/",
|
| 32 |
+
"num_train_epochs": 3,
|
| 33 |
+
"per_device_train_batch_size": 256,
|
| 34 |
+
"per_device_eval_batch_size": 512,
|
| 35 |
+
"learning_rate": 2e-05,
|
| 36 |
+
"warmup_steps": 612,
|
| 37 |
+
"weight_decay": 0.1,
|
| 38 |
+
"logging_steps": 5,
|
| 39 |
+
"eval_steps": 50,
|
| 40 |
+
"save_steps": 100,
|
| 41 |
+
"metric_for_best_model": "macro_f1",
|
| 42 |
+
"greater_is_better": true,
|
| 43 |
+
"save_total_limit": 5,
|
| 44 |
+
"fp16": true,
|
| 45 |
+
"seed": 42
|
| 46 |
+
},
|
| 47 |
+
"training_state": {
|
| 48 |
+
"global_step": 100,
|
| 49 |
+
"epoch": 0.09784735812133072,
|
| 50 |
+
"best_metric": 0.5260673147136775,
|
| 51 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-100"
|
| 52 |
+
}
|
| 53 |
+
}
|
graphcodebert-vanilla/checkpoint-100/hyperparams.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 3 |
+
"output_dir": "output_checkpoints/graphcodebert-vanilla/",
|
| 4 |
+
"num_epochs": 3,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"batch_size": 256,
|
| 7 |
+
"learning_rate": 2e-05,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"num_labels": 2,
|
| 10 |
+
"use_wandb": true,
|
| 11 |
+
"freeze_base": true,
|
| 12 |
+
"loss_type": "ce",
|
| 13 |
+
"focal_alpha": 1.0,
|
| 14 |
+
"focal_gamma": 2.0,
|
| 15 |
+
"r_drop_alpha": 6.0,
|
| 16 |
+
"infonce_temperature": 0.07,
|
| 17 |
+
"infonce_weight": 0.5,
|
| 18 |
+
"seed": 42,
|
| 19 |
+
"wandb_run_name": "graphcodebert-vanilla",
|
| 20 |
+
"resume_from_checkpoint": null,
|
| 21 |
+
"save_steps": 100,
|
| 22 |
+
"eval_steps": 50,
|
| 23 |
+
"logging_steps": 5,
|
| 24 |
+
"label_smoothing": 0,
|
| 25 |
+
"adversarial_epsilon": 0,
|
| 26 |
+
"use_swa": false,
|
| 27 |
+
"swa_start_epoch": 0,
|
| 28 |
+
"swa_lr": 1e-05,
|
| 29 |
+
"data_augmentation": false,
|
| 30 |
+
"aug_rename_prob": 0.0,
|
| 31 |
+
"aug_format_prob": 0.0,
|
| 32 |
+
"mixup_alpha": 0.0,
|
| 33 |
+
"low_pass_keep_ratio": 0.5,
|
| 34 |
+
"freq_consistency_weight": 0.0,
|
| 35 |
+
"hidden_dropout_prob": 0.3,
|
| 36 |
+
"attention_probs_dropout_prob": 0.3,
|
| 37 |
+
"classifier_dropout": 0.3,
|
| 38 |
+
"device": "cuda"
|
| 39 |
+
}
|
graphcodebert-vanilla/checkpoint-100/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/checkpoint-100/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da3f281851fd71b6943f4e6fc58ef17ba54c6d167a319cabac7deab1eafcd599
|
| 3 |
+
size 498612824
|
graphcodebert-vanilla/checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54f9e03da26cb2cf86cb6f1f437f201f3cbc236e6729b9abd7d153a24ce31ee8
|
| 3 |
+
size 4741859
|
graphcodebert-vanilla/checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddddccf76b63f161c92bc8774c3df6f375bf2ce43e44a910de13434d0630025e
|
| 3 |
+
size 14645
|
graphcodebert-vanilla/checkpoint-100/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
|
| 3 |
+
size 1383
|
graphcodebert-vanilla/checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b683a9e0270ef59bda524139bbaf1cd9071993f5d3a698ac0dcacdd374cee064
|
| 3 |
+
size 1465
|
graphcodebert-vanilla/checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
graphcodebert-vanilla/checkpoint-100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
graphcodebert-vanilla/checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 100,
|
| 3 |
+
"best_metric": 0.5260673147136775,
|
| 4 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-100",
|
| 5 |
+
"epoch": 0.09784735812133072,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004892367906066536,
|
| 14 |
+
"grad_norm": 33435.953125,
|
| 15 |
+
"learning_rate": 1.3071895424836603e-07,
|
| 16 |
+
"loss": 0.7006,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.009784735812133072,
|
| 21 |
+
"grad_norm": 34831.7421875,
|
| 22 |
+
"learning_rate": 2.9411764705882356e-07,
|
| 23 |
+
"loss": 0.7023,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.014677103718199608,
|
| 28 |
+
"grad_norm": 32986.62109375,
|
| 29 |
+
"learning_rate": 4.5751633986928105e-07,
|
| 30 |
+
"loss": 0.7019,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.019569471624266144,
|
| 35 |
+
"grad_norm": 34257.4921875,
|
| 36 |
+
"learning_rate": 6.209150326797386e-07,
|
| 37 |
+
"loss": 0.7025,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02446183953033268,
|
| 42 |
+
"grad_norm": 35511.3359375,
|
| 43 |
+
"learning_rate": 7.843137254901962e-07,
|
| 44 |
+
"loss": 0.7032,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.029354207436399216,
|
| 49 |
+
"grad_norm": 33043.3515625,
|
| 50 |
+
"learning_rate": 9.477124183006536e-07,
|
| 51 |
+
"loss": 0.6968,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03424657534246575,
|
| 56 |
+
"grad_norm": 38538.30078125,
|
| 57 |
+
"learning_rate": 1.111111111111111e-06,
|
| 58 |
+
"loss": 0.6992,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03913894324853229,
|
| 63 |
+
"grad_norm": 43255.37890625,
|
| 64 |
+
"learning_rate": 1.2745098039215686e-06,
|
| 65 |
+
"loss": 0.6991,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04403131115459882,
|
| 70 |
+
"grad_norm": 34170.8046875,
|
| 71 |
+
"learning_rate": 1.4379084967320261e-06,
|
| 72 |
+
"loss": 0.6996,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04892367906066536,
|
| 77 |
+
"grad_norm": 35399.70703125,
|
| 78 |
+
"learning_rate": 1.6013071895424837e-06,
|
| 79 |
+
"loss": 0.6937,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04892367906066536,
|
| 84 |
+
"eval_accuracy": 0.771,
|
| 85 |
+
"eval_loss": 0.6569265127182007,
|
| 86 |
+
"eval_macro_f1": 0.5082027063884254,
|
| 87 |
+
"eval_precision": 0.6109971743687904,
|
| 88 |
+
"eval_recall": 0.5281120325963375,
|
| 89 |
+
"eval_runtime": 17.5156,
|
| 90 |
+
"eval_samples_per_second": 57.092,
|
| 91 |
+
"eval_steps_per_second": 0.057,
|
| 92 |
+
"step": 50
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.053816046966731895,
|
| 96 |
+
"grad_norm": 34677.1796875,
|
| 97 |
+
"learning_rate": 1.7647058823529414e-06,
|
| 98 |
+
"loss": 0.6963,
|
| 99 |
+
"step": 55
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05870841487279843,
|
| 103 |
+
"grad_norm": 31789.291015625,
|
| 104 |
+
"learning_rate": 1.928104575163399e-06,
|
| 105 |
+
"loss": 0.6971,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.06360078277886497,
|
| 110 |
+
"grad_norm": 30762.345703125,
|
| 111 |
+
"learning_rate": 2.0915032679738565e-06,
|
| 112 |
+
"loss": 0.6946,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.0684931506849315,
|
| 117 |
+
"grad_norm": 29590.083984375,
|
| 118 |
+
"learning_rate": 2.254901960784314e-06,
|
| 119 |
+
"loss": 0.693,
|
| 120 |
+
"step": 70
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.07338551859099804,
|
| 124 |
+
"grad_norm": 29346.84765625,
|
| 125 |
+
"learning_rate": 2.4183006535947716e-06,
|
| 126 |
+
"loss": 0.6905,
|
| 127 |
+
"step": 75
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.07827788649706457,
|
| 131 |
+
"grad_norm": 37289.77734375,
|
| 132 |
+
"learning_rate": 2.581699346405229e-06,
|
| 133 |
+
"loss": 0.6942,
|
| 134 |
+
"step": 80
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.08317025440313111,
|
| 138 |
+
"grad_norm": 33970.94140625,
|
| 139 |
+
"learning_rate": 2.7450980392156867e-06,
|
| 140 |
+
"loss": 0.69,
|
| 141 |
+
"step": 85
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.08806262230919765,
|
| 145 |
+
"grad_norm": 28671.583984375,
|
| 146 |
+
"learning_rate": 2.9084967320261443e-06,
|
| 147 |
+
"loss": 0.6889,
|
| 148 |
+
"step": 90
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.09295499021526418,
|
| 152 |
+
"grad_norm": 30156.005859375,
|
| 153 |
+
"learning_rate": 3.071895424836602e-06,
|
| 154 |
+
"loss": 0.6866,
|
| 155 |
+
"step": 95
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.09784735812133072,
|
| 159 |
+
"grad_norm": 33484.71484375,
|
| 160 |
+
"learning_rate": 3.2352941176470594e-06,
|
| 161 |
+
"loss": 0.6888,
|
| 162 |
+
"step": 100
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.09784735812133072,
|
| 166 |
+
"eval_accuracy": 0.767,
|
| 167 |
+
"eval_loss": 0.6559821367263794,
|
| 168 |
+
"eval_macro_f1": 0.5260673147136775,
|
| 169 |
+
"eval_precision": 0.6062366452991452,
|
| 170 |
+
"eval_recall": 0.5367285927824044,
|
| 171 |
+
"eval_runtime": 17.3972,
|
| 172 |
+
"eval_samples_per_second": 57.481,
|
| 173 |
+
"eval_steps_per_second": 0.057,
|
| 174 |
+
"step": 100
|
| 175 |
+
}
|
| 176 |
+
],
|
| 177 |
+
"logging_steps": 5,
|
| 178 |
+
"max_steps": 3066,
|
| 179 |
+
"num_input_tokens_seen": 0,
|
| 180 |
+
"num_train_epochs": 3,
|
| 181 |
+
"save_steps": 100,
|
| 182 |
+
"stateful_callbacks": {
|
| 183 |
+
"EarlyStoppingCallback": {
|
| 184 |
+
"args": {
|
| 185 |
+
"early_stopping_patience": 3,
|
| 186 |
+
"early_stopping_threshold": 0.0
|
| 187 |
+
},
|
| 188 |
+
"attributes": {
|
| 189 |
+
"early_stopping_patience_counter": 0
|
| 190 |
+
}
|
| 191 |
+
},
|
| 192 |
+
"TrainerControl": {
|
| 193 |
+
"args": {
|
| 194 |
+
"should_epoch_stop": false,
|
| 195 |
+
"should_evaluate": false,
|
| 196 |
+
"should_log": false,
|
| 197 |
+
"should_save": true,
|
| 198 |
+
"should_training_stop": false
|
| 199 |
+
},
|
| 200 |
+
"attributes": {}
|
| 201 |
+
}
|
| 202 |
+
},
|
| 203 |
+
"total_flos": 1.3471286034432e+16,
|
| 204 |
+
"train_batch_size": 512,
|
| 205 |
+
"trial_name": null,
|
| 206 |
+
"trial_params": null
|
| 207 |
+
}
|
graphcodebert-vanilla/checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3d448040cc8193c39a3aa43e3972db0566234234cb8950ae351de6781f2f556
|
| 3 |
+
size 5905
|
graphcodebert-vanilla/checkpoint-100/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.3,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": 0.3,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.3,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"transformers_version": "4.56.0",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50265
|
| 29 |
+
}
|
graphcodebert-vanilla/checkpoint-200/config_hyperparams.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train_config": {
|
| 3 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 4 |
+
"num_epochs": 3,
|
| 5 |
+
"batch_size": 256,
|
| 6 |
+
"learning_rate": 2e-05,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"num_labels": 2,
|
| 9 |
+
"loss_type": "ce",
|
| 10 |
+
"focal_alpha": 1.0,
|
| 11 |
+
"focal_gamma": 2.0,
|
| 12 |
+
"r_drop_alpha": 6.0,
|
| 13 |
+
"infonce_temperature": 0.07,
|
| 14 |
+
"infonce_weight": 0.5,
|
| 15 |
+
"label_smoothing": 0,
|
| 16 |
+
"adversarial_epsilon": 0,
|
| 17 |
+
"use_swa": false,
|
| 18 |
+
"swa_start_epoch": 0,
|
| 19 |
+
"swa_lr": 1e-05,
|
| 20 |
+
"data_augmentation": false,
|
| 21 |
+
"aug_rename_prob": 0.0,
|
| 22 |
+
"aug_format_prob": 0.0,
|
| 23 |
+
"freeze_base": true,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"use_wandb": true,
|
| 26 |
+
"mixup_alpha": 0.0,
|
| 27 |
+
"low_pass_keep_ratio": 0.5,
|
| 28 |
+
"freq_consistency_weight": 0.0
|
| 29 |
+
},
|
| 30 |
+
"training_arguments": {
|
| 31 |
+
"output_dir": "output_checkpoints/graphcodebert-vanilla/",
|
| 32 |
+
"num_train_epochs": 3,
|
| 33 |
+
"per_device_train_batch_size": 256,
|
| 34 |
+
"per_device_eval_batch_size": 512,
|
| 35 |
+
"learning_rate": 2e-05,
|
| 36 |
+
"warmup_steps": 612,
|
| 37 |
+
"weight_decay": 0.1,
|
| 38 |
+
"logging_steps": 5,
|
| 39 |
+
"eval_steps": 50,
|
| 40 |
+
"save_steps": 100,
|
| 41 |
+
"metric_for_best_model": "macro_f1",
|
| 42 |
+
"greater_is_better": true,
|
| 43 |
+
"save_total_limit": 5,
|
| 44 |
+
"fp16": true,
|
| 45 |
+
"seed": 42
|
| 46 |
+
},
|
| 47 |
+
"training_state": {
|
| 48 |
+
"global_step": 200,
|
| 49 |
+
"epoch": 0.19569471624266144,
|
| 50 |
+
"best_metric": 0.5962545254252696,
|
| 51 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-200"
|
| 52 |
+
}
|
| 53 |
+
}
|
graphcodebert-vanilla/checkpoint-200/hyperparams.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 3 |
+
"output_dir": "output_checkpoints/graphcodebert-vanilla/",
|
| 4 |
+
"num_epochs": 3,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"batch_size": 256,
|
| 7 |
+
"learning_rate": 2e-05,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"num_labels": 2,
|
| 10 |
+
"use_wandb": true,
|
| 11 |
+
"freeze_base": true,
|
| 12 |
+
"loss_type": "ce",
|
| 13 |
+
"focal_alpha": 1.0,
|
| 14 |
+
"focal_gamma": 2.0,
|
| 15 |
+
"r_drop_alpha": 6.0,
|
| 16 |
+
"infonce_temperature": 0.07,
|
| 17 |
+
"infonce_weight": 0.5,
|
| 18 |
+
"seed": 42,
|
| 19 |
+
"wandb_run_name": "graphcodebert-vanilla",
|
| 20 |
+
"resume_from_checkpoint": null,
|
| 21 |
+
"save_steps": 100,
|
| 22 |
+
"eval_steps": 50,
|
| 23 |
+
"logging_steps": 5,
|
| 24 |
+
"label_smoothing": 0,
|
| 25 |
+
"adversarial_epsilon": 0,
|
| 26 |
+
"use_swa": false,
|
| 27 |
+
"swa_start_epoch": 0,
|
| 28 |
+
"swa_lr": 1e-05,
|
| 29 |
+
"data_augmentation": false,
|
| 30 |
+
"aug_rename_prob": 0.0,
|
| 31 |
+
"aug_format_prob": 0.0,
|
| 32 |
+
"mixup_alpha": 0.0,
|
| 33 |
+
"low_pass_keep_ratio": 0.5,
|
| 34 |
+
"freq_consistency_weight": 0.0,
|
| 35 |
+
"hidden_dropout_prob": 0.3,
|
| 36 |
+
"attention_probs_dropout_prob": 0.3,
|
| 37 |
+
"classifier_dropout": 0.3,
|
| 38 |
+
"device": "cuda"
|
| 39 |
+
}
|
graphcodebert-vanilla/checkpoint-200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/checkpoint-200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aeaccc7446a00f35bec59d86fa902e66ebf161710cff77f1fbc7e23c5c62aa4
|
| 3 |
+
size 498612824
|
graphcodebert-vanilla/checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b722cecb86725f9e176547eea1fa82aaf7883c091259493a9743214cfe3e4807
|
| 3 |
+
size 4741859
|
graphcodebert-vanilla/checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2533ee5d1fa769cc2164b95d88e0df14f136fb5e6d1e47fc9541a03a10815bcb
|
| 3 |
+
size 14645
|
graphcodebert-vanilla/checkpoint-200/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
|
| 3 |
+
size 1383
|
graphcodebert-vanilla/checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1a24cde04d57e738ef50ad7ff8ffdc9c34b1e5155cdccf9430834307ea21fd7
|
| 3 |
+
size 1465
|
graphcodebert-vanilla/checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
graphcodebert-vanilla/checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
graphcodebert-vanilla/checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,371 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 200,
|
| 3 |
+
"best_metric": 0.5962545254252696,
|
| 4 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-200",
|
| 5 |
+
"epoch": 0.19569471624266144,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004892367906066536,
|
| 14 |
+
"grad_norm": 33435.953125,
|
| 15 |
+
"learning_rate": 1.3071895424836603e-07,
|
| 16 |
+
"loss": 0.7006,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.009784735812133072,
|
| 21 |
+
"grad_norm": 34831.7421875,
|
| 22 |
+
"learning_rate": 2.9411764705882356e-07,
|
| 23 |
+
"loss": 0.7023,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.014677103718199608,
|
| 28 |
+
"grad_norm": 32986.62109375,
|
| 29 |
+
"learning_rate": 4.5751633986928105e-07,
|
| 30 |
+
"loss": 0.7019,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.019569471624266144,
|
| 35 |
+
"grad_norm": 34257.4921875,
|
| 36 |
+
"learning_rate": 6.209150326797386e-07,
|
| 37 |
+
"loss": 0.7025,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02446183953033268,
|
| 42 |
+
"grad_norm": 35511.3359375,
|
| 43 |
+
"learning_rate": 7.843137254901962e-07,
|
| 44 |
+
"loss": 0.7032,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.029354207436399216,
|
| 49 |
+
"grad_norm": 33043.3515625,
|
| 50 |
+
"learning_rate": 9.477124183006536e-07,
|
| 51 |
+
"loss": 0.6968,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03424657534246575,
|
| 56 |
+
"grad_norm": 38538.30078125,
|
| 57 |
+
"learning_rate": 1.111111111111111e-06,
|
| 58 |
+
"loss": 0.6992,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03913894324853229,
|
| 63 |
+
"grad_norm": 43255.37890625,
|
| 64 |
+
"learning_rate": 1.2745098039215686e-06,
|
| 65 |
+
"loss": 0.6991,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04403131115459882,
|
| 70 |
+
"grad_norm": 34170.8046875,
|
| 71 |
+
"learning_rate": 1.4379084967320261e-06,
|
| 72 |
+
"loss": 0.6996,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04892367906066536,
|
| 77 |
+
"grad_norm": 35399.70703125,
|
| 78 |
+
"learning_rate": 1.6013071895424837e-06,
|
| 79 |
+
"loss": 0.6937,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04892367906066536,
|
| 84 |
+
"eval_accuracy": 0.771,
|
| 85 |
+
"eval_loss": 0.6569265127182007,
|
| 86 |
+
"eval_macro_f1": 0.5082027063884254,
|
| 87 |
+
"eval_precision": 0.6109971743687904,
|
| 88 |
+
"eval_recall": 0.5281120325963375,
|
| 89 |
+
"eval_runtime": 17.5156,
|
| 90 |
+
"eval_samples_per_second": 57.092,
|
| 91 |
+
"eval_steps_per_second": 0.057,
|
| 92 |
+
"step": 50
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.053816046966731895,
|
| 96 |
+
"grad_norm": 34677.1796875,
|
| 97 |
+
"learning_rate": 1.7647058823529414e-06,
|
| 98 |
+
"loss": 0.6963,
|
| 99 |
+
"step": 55
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05870841487279843,
|
| 103 |
+
"grad_norm": 31789.291015625,
|
| 104 |
+
"learning_rate": 1.928104575163399e-06,
|
| 105 |
+
"loss": 0.6971,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.06360078277886497,
|
| 110 |
+
"grad_norm": 30762.345703125,
|
| 111 |
+
"learning_rate": 2.0915032679738565e-06,
|
| 112 |
+
"loss": 0.6946,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.0684931506849315,
|
| 117 |
+
"grad_norm": 29590.083984375,
|
| 118 |
+
"learning_rate": 2.254901960784314e-06,
|
| 119 |
+
"loss": 0.693,
|
| 120 |
+
"step": 70
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.07338551859099804,
|
| 124 |
+
"grad_norm": 29346.84765625,
|
| 125 |
+
"learning_rate": 2.4183006535947716e-06,
|
| 126 |
+
"loss": 0.6905,
|
| 127 |
+
"step": 75
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.07827788649706457,
|
| 131 |
+
"grad_norm": 37289.77734375,
|
| 132 |
+
"learning_rate": 2.581699346405229e-06,
|
| 133 |
+
"loss": 0.6942,
|
| 134 |
+
"step": 80
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.08317025440313111,
|
| 138 |
+
"grad_norm": 33970.94140625,
|
| 139 |
+
"learning_rate": 2.7450980392156867e-06,
|
| 140 |
+
"loss": 0.69,
|
| 141 |
+
"step": 85
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.08806262230919765,
|
| 145 |
+
"grad_norm": 28671.583984375,
|
| 146 |
+
"learning_rate": 2.9084967320261443e-06,
|
| 147 |
+
"loss": 0.6889,
|
| 148 |
+
"step": 90
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.09295499021526418,
|
| 152 |
+
"grad_norm": 30156.005859375,
|
| 153 |
+
"learning_rate": 3.071895424836602e-06,
|
| 154 |
+
"loss": 0.6866,
|
| 155 |
+
"step": 95
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.09784735812133072,
|
| 159 |
+
"grad_norm": 33484.71484375,
|
| 160 |
+
"learning_rate": 3.2352941176470594e-06,
|
| 161 |
+
"loss": 0.6888,
|
| 162 |
+
"step": 100
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.09784735812133072,
|
| 166 |
+
"eval_accuracy": 0.767,
|
| 167 |
+
"eval_loss": 0.6559821367263794,
|
| 168 |
+
"eval_macro_f1": 0.5260673147136775,
|
| 169 |
+
"eval_precision": 0.6062366452991452,
|
| 170 |
+
"eval_recall": 0.5367285927824044,
|
| 171 |
+
"eval_runtime": 17.3972,
|
| 172 |
+
"eval_samples_per_second": 57.481,
|
| 173 |
+
"eval_steps_per_second": 0.057,
|
| 174 |
+
"step": 100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.10273972602739725,
|
| 178 |
+
"grad_norm": 35390.96484375,
|
| 179 |
+
"learning_rate": 3.398692810457517e-06,
|
| 180 |
+
"loss": 0.6893,
|
| 181 |
+
"step": 105
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.10763209393346379,
|
| 185 |
+
"grad_norm": 34452.11328125,
|
| 186 |
+
"learning_rate": 3.562091503267974e-06,
|
| 187 |
+
"loss": 0.6849,
|
| 188 |
+
"step": 110
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.11252446183953033,
|
| 192 |
+
"grad_norm": 41847.0625,
|
| 193 |
+
"learning_rate": 3.7254901960784316e-06,
|
| 194 |
+
"loss": 0.6853,
|
| 195 |
+
"step": 115
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.11741682974559686,
|
| 199 |
+
"grad_norm": 31951.4140625,
|
| 200 |
+
"learning_rate": 3.88888888888889e-06,
|
| 201 |
+
"loss": 0.6802,
|
| 202 |
+
"step": 120
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.1223091976516634,
|
| 206 |
+
"grad_norm": 34176.79296875,
|
| 207 |
+
"learning_rate": 4.052287581699347e-06,
|
| 208 |
+
"loss": 0.6871,
|
| 209 |
+
"step": 125
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.12720156555772993,
|
| 213 |
+
"grad_norm": 35482.6640625,
|
| 214 |
+
"learning_rate": 4.215686274509805e-06,
|
| 215 |
+
"loss": 0.6789,
|
| 216 |
+
"step": 130
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.13209393346379647,
|
| 220 |
+
"grad_norm": 60289.4296875,
|
| 221 |
+
"learning_rate": 4.379084967320262e-06,
|
| 222 |
+
"loss": 0.6844,
|
| 223 |
+
"step": 135
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.136986301369863,
|
| 227 |
+
"grad_norm": 41964.47265625,
|
| 228 |
+
"learning_rate": 4.542483660130719e-06,
|
| 229 |
+
"loss": 0.6808,
|
| 230 |
+
"step": 140
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.14187866927592954,
|
| 234 |
+
"grad_norm": 35805.8203125,
|
| 235 |
+
"learning_rate": 4.705882352941177e-06,
|
| 236 |
+
"loss": 0.6748,
|
| 237 |
+
"step": 145
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.14677103718199608,
|
| 241 |
+
"grad_norm": 25688.607421875,
|
| 242 |
+
"learning_rate": 4.869281045751634e-06,
|
| 243 |
+
"loss": 0.6769,
|
| 244 |
+
"step": 150
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.14677103718199608,
|
| 248 |
+
"eval_accuracy": 0.728,
|
| 249 |
+
"eval_loss": 0.6580190658569336,
|
| 250 |
+
"eval_macro_f1": 0.5668100015926103,
|
| 251 |
+
"eval_precision": 0.5782073308365263,
|
| 252 |
+
"eval_recall": 0.5627889260176255,
|
| 253 |
+
"eval_runtime": 17.3848,
|
| 254 |
+
"eval_samples_per_second": 57.521,
|
| 255 |
+
"eval_steps_per_second": 0.058,
|
| 256 |
+
"step": 150
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.15166340508806261,
|
| 260 |
+
"grad_norm": 30171.484375,
|
| 261 |
+
"learning_rate": 5.032679738562092e-06,
|
| 262 |
+
"loss": 0.6706,
|
| 263 |
+
"step": 155
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.15655577299412915,
|
| 267 |
+
"grad_norm": 29393.716796875,
|
| 268 |
+
"learning_rate": 5.19607843137255e-06,
|
| 269 |
+
"loss": 0.6764,
|
| 270 |
+
"step": 160
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.16144814090019569,
|
| 274 |
+
"grad_norm": 34377.2578125,
|
| 275 |
+
"learning_rate": 5.359477124183007e-06,
|
| 276 |
+
"loss": 0.6688,
|
| 277 |
+
"step": 165
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.16634050880626222,
|
| 281 |
+
"grad_norm": 34805.3671875,
|
| 282 |
+
"learning_rate": 5.522875816993465e-06,
|
| 283 |
+
"loss": 0.6673,
|
| 284 |
+
"step": 170
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.17123287671232876,
|
| 288 |
+
"grad_norm": 29948.095703125,
|
| 289 |
+
"learning_rate": 5.686274509803922e-06,
|
| 290 |
+
"loss": 0.6652,
|
| 291 |
+
"step": 175
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.1761252446183953,
|
| 295 |
+
"grad_norm": 34735.33984375,
|
| 296 |
+
"learning_rate": 5.84967320261438e-06,
|
| 297 |
+
"loss": 0.6709,
|
| 298 |
+
"step": 180
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.18101761252446183,
|
| 302 |
+
"grad_norm": 36469.0703125,
|
| 303 |
+
"learning_rate": 6.0130718954248365e-06,
|
| 304 |
+
"loss": 0.6606,
|
| 305 |
+
"step": 185
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.18590998043052837,
|
| 309 |
+
"grad_norm": 27843.798828125,
|
| 310 |
+
"learning_rate": 6.176470588235295e-06,
|
| 311 |
+
"loss": 0.6666,
|
| 312 |
+
"step": 190
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.1908023483365949,
|
| 316 |
+
"grad_norm": 27965.966796875,
|
| 317 |
+
"learning_rate": 6.3398692810457515e-06,
|
| 318 |
+
"loss": 0.6626,
|
| 319 |
+
"step": 195
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.19569471624266144,
|
| 323 |
+
"grad_norm": 28469.09375,
|
| 324 |
+
"learning_rate": 6.5032679738562095e-06,
|
| 325 |
+
"loss": 0.6601,
|
| 326 |
+
"step": 200
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.19569471624266144,
|
| 330 |
+
"eval_accuracy": 0.698,
|
| 331 |
+
"eval_loss": 0.6574791669845581,
|
| 332 |
+
"eval_macro_f1": 0.5962545254252696,
|
| 333 |
+
"eval_precision": 0.591974921630094,
|
| 334 |
+
"eval_recall": 0.605831327804422,
|
| 335 |
+
"eval_runtime": 17.3909,
|
| 336 |
+
"eval_samples_per_second": 57.501,
|
| 337 |
+
"eval_steps_per_second": 0.058,
|
| 338 |
+
"step": 200
|
| 339 |
+
}
|
| 340 |
+
],
|
| 341 |
+
"logging_steps": 5,
|
| 342 |
+
"max_steps": 3066,
|
| 343 |
+
"num_input_tokens_seen": 0,
|
| 344 |
+
"num_train_epochs": 3,
|
| 345 |
+
"save_steps": 100,
|
| 346 |
+
"stateful_callbacks": {
|
| 347 |
+
"EarlyStoppingCallback": {
|
| 348 |
+
"args": {
|
| 349 |
+
"early_stopping_patience": 3,
|
| 350 |
+
"early_stopping_threshold": 0.0
|
| 351 |
+
},
|
| 352 |
+
"attributes": {
|
| 353 |
+
"early_stopping_patience_counter": 0
|
| 354 |
+
}
|
| 355 |
+
},
|
| 356 |
+
"TrainerControl": {
|
| 357 |
+
"args": {
|
| 358 |
+
"should_epoch_stop": false,
|
| 359 |
+
"should_evaluate": false,
|
| 360 |
+
"should_log": false,
|
| 361 |
+
"should_save": true,
|
| 362 |
+
"should_training_stop": false
|
| 363 |
+
},
|
| 364 |
+
"attributes": {}
|
| 365 |
+
}
|
| 366 |
+
},
|
| 367 |
+
"total_flos": 2.6942572068864e+16,
|
| 368 |
+
"train_batch_size": 512,
|
| 369 |
+
"trial_name": null,
|
| 370 |
+
"trial_params": null
|
| 371 |
+
}
|
graphcodebert-vanilla/checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3d448040cc8193c39a3aa43e3972db0566234234cb8950ae351de6781f2f556
|
| 3 |
+
size 5905
|
graphcodebert-vanilla/checkpoint-200/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/checkpoint-300/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.3,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": 0.3,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.3,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"transformers_version": "4.56.0",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50265
|
| 29 |
+
}
|
graphcodebert-vanilla/checkpoint-300/config_hyperparams.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train_config": {
|
| 3 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 4 |
+
"num_epochs": 3,
|
| 5 |
+
"batch_size": 256,
|
| 6 |
+
"learning_rate": 2e-05,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"num_labels": 2,
|
| 9 |
+
"loss_type": "ce",
|
| 10 |
+
"focal_alpha": 1.0,
|
| 11 |
+
"focal_gamma": 2.0,
|
| 12 |
+
"r_drop_alpha": 6.0,
|
| 13 |
+
"infonce_temperature": 0.07,
|
| 14 |
+
"infonce_weight": 0.5,
|
| 15 |
+
"label_smoothing": 0,
|
| 16 |
+
"adversarial_epsilon": 0,
|
| 17 |
+
"use_swa": false,
|
| 18 |
+
"swa_start_epoch": 0,
|
| 19 |
+
"swa_lr": 1e-05,
|
| 20 |
+
"data_augmentation": false,
|
| 21 |
+
"aug_rename_prob": 0.0,
|
| 22 |
+
"aug_format_prob": 0.0,
|
| 23 |
+
"freeze_base": true,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"use_wandb": true,
|
| 26 |
+
"mixup_alpha": 0.0,
|
| 27 |
+
"low_pass_keep_ratio": 0.5,
|
| 28 |
+
"freq_consistency_weight": 0.0
|
| 29 |
+
},
|
| 30 |
+
"training_arguments": {
|
| 31 |
+
"output_dir": "output_checkpoints/graphcodebert-vanilla/",
|
| 32 |
+
"num_train_epochs": 3,
|
| 33 |
+
"per_device_train_batch_size": 256,
|
| 34 |
+
"per_device_eval_batch_size": 512,
|
| 35 |
+
"learning_rate": 2e-05,
|
| 36 |
+
"warmup_steps": 612,
|
| 37 |
+
"weight_decay": 0.1,
|
| 38 |
+
"logging_steps": 5,
|
| 39 |
+
"eval_steps": 50,
|
| 40 |
+
"save_steps": 100,
|
| 41 |
+
"metric_for_best_model": "macro_f1",
|
| 42 |
+
"greater_is_better": true,
|
| 43 |
+
"save_total_limit": 5,
|
| 44 |
+
"fp16": true,
|
| 45 |
+
"seed": 42
|
| 46 |
+
},
|
| 47 |
+
"training_state": {
|
| 48 |
+
"global_step": 300,
|
| 49 |
+
"epoch": 0.29354207436399216,
|
| 50 |
+
"best_metric": 0.5962545254252696,
|
| 51 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-200"
|
| 52 |
+
}
|
| 53 |
+
}
|
graphcodebert-vanilla/checkpoint-300/hyperparams.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 3 |
+
"output_dir": "output_checkpoints/graphcodebert-vanilla/",
|
| 4 |
+
"num_epochs": 3,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"batch_size": 256,
|
| 7 |
+
"learning_rate": 2e-05,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"num_labels": 2,
|
| 10 |
+
"use_wandb": true,
|
| 11 |
+
"freeze_base": true,
|
| 12 |
+
"loss_type": "ce",
|
| 13 |
+
"focal_alpha": 1.0,
|
| 14 |
+
"focal_gamma": 2.0,
|
| 15 |
+
"r_drop_alpha": 6.0,
|
| 16 |
+
"infonce_temperature": 0.07,
|
| 17 |
+
"infonce_weight": 0.5,
|
| 18 |
+
"seed": 42,
|
| 19 |
+
"wandb_run_name": "graphcodebert-vanilla",
|
| 20 |
+
"resume_from_checkpoint": null,
|
| 21 |
+
"save_steps": 100,
|
| 22 |
+
"eval_steps": 50,
|
| 23 |
+
"logging_steps": 5,
|
| 24 |
+
"label_smoothing": 0,
|
| 25 |
+
"adversarial_epsilon": 0,
|
| 26 |
+
"use_swa": false,
|
| 27 |
+
"swa_start_epoch": 0,
|
| 28 |
+
"swa_lr": 1e-05,
|
| 29 |
+
"data_augmentation": false,
|
| 30 |
+
"aug_rename_prob": 0.0,
|
| 31 |
+
"aug_format_prob": 0.0,
|
| 32 |
+
"mixup_alpha": 0.0,
|
| 33 |
+
"low_pass_keep_ratio": 0.5,
|
| 34 |
+
"freq_consistency_weight": 0.0,
|
| 35 |
+
"hidden_dropout_prob": 0.3,
|
| 36 |
+
"attention_probs_dropout_prob": 0.3,
|
| 37 |
+
"classifier_dropout": 0.3,
|
| 38 |
+
"device": "cuda"
|
| 39 |
+
}
|
graphcodebert-vanilla/checkpoint-300/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/checkpoint-300/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edd3840232c2ce57c3ca99599da5b4b6c3d927d433e8f6cade8f19eb82e1c7d4
|
| 3 |
+
size 498612824
|
graphcodebert-vanilla/checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3bc2bb4faa59c5b4d4444402a371d35e399ec5c0395497516d5b8a18204541d
|
| 3 |
+
size 4741859
|
graphcodebert-vanilla/checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16d01df9df5e3d357f43a862c0d6dbd8af3871aefdeaa647afae0764a9686751
|
| 3 |
+
size 14645
|
graphcodebert-vanilla/checkpoint-300/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
|
| 3 |
+
size 1383
|
graphcodebert-vanilla/checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82af26824e4d089a1392ee4f564d426e3fd92b73b1c7ab1766017647df7f455d
|
| 3 |
+
size 1465
|
graphcodebert-vanilla/checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
graphcodebert-vanilla/checkpoint-300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
graphcodebert-vanilla/checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,535 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 200,
|
| 3 |
+
"best_metric": 0.5962545254252696,
|
| 4 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-vanilla/checkpoint-200",
|
| 5 |
+
"epoch": 0.29354207436399216,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 300,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004892367906066536,
|
| 14 |
+
"grad_norm": 33435.953125,
|
| 15 |
+
"learning_rate": 1.3071895424836603e-07,
|
| 16 |
+
"loss": 0.7006,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.009784735812133072,
|
| 21 |
+
"grad_norm": 34831.7421875,
|
| 22 |
+
"learning_rate": 2.9411764705882356e-07,
|
| 23 |
+
"loss": 0.7023,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.014677103718199608,
|
| 28 |
+
"grad_norm": 32986.62109375,
|
| 29 |
+
"learning_rate": 4.5751633986928105e-07,
|
| 30 |
+
"loss": 0.7019,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.019569471624266144,
|
| 35 |
+
"grad_norm": 34257.4921875,
|
| 36 |
+
"learning_rate": 6.209150326797386e-07,
|
| 37 |
+
"loss": 0.7025,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02446183953033268,
|
| 42 |
+
"grad_norm": 35511.3359375,
|
| 43 |
+
"learning_rate": 7.843137254901962e-07,
|
| 44 |
+
"loss": 0.7032,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.029354207436399216,
|
| 49 |
+
"grad_norm": 33043.3515625,
|
| 50 |
+
"learning_rate": 9.477124183006536e-07,
|
| 51 |
+
"loss": 0.6968,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03424657534246575,
|
| 56 |
+
"grad_norm": 38538.30078125,
|
| 57 |
+
"learning_rate": 1.111111111111111e-06,
|
| 58 |
+
"loss": 0.6992,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03913894324853229,
|
| 63 |
+
"grad_norm": 43255.37890625,
|
| 64 |
+
"learning_rate": 1.2745098039215686e-06,
|
| 65 |
+
"loss": 0.6991,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04403131115459882,
|
| 70 |
+
"grad_norm": 34170.8046875,
|
| 71 |
+
"learning_rate": 1.4379084967320261e-06,
|
| 72 |
+
"loss": 0.6996,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04892367906066536,
|
| 77 |
+
"grad_norm": 35399.70703125,
|
| 78 |
+
"learning_rate": 1.6013071895424837e-06,
|
| 79 |
+
"loss": 0.6937,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04892367906066536,
|
| 84 |
+
"eval_accuracy": 0.771,
|
| 85 |
+
"eval_loss": 0.6569265127182007,
|
| 86 |
+
"eval_macro_f1": 0.5082027063884254,
|
| 87 |
+
"eval_precision": 0.6109971743687904,
|
| 88 |
+
"eval_recall": 0.5281120325963375,
|
| 89 |
+
"eval_runtime": 17.5156,
|
| 90 |
+
"eval_samples_per_second": 57.092,
|
| 91 |
+
"eval_steps_per_second": 0.057,
|
| 92 |
+
"step": 50
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.053816046966731895,
|
| 96 |
+
"grad_norm": 34677.1796875,
|
| 97 |
+
"learning_rate": 1.7647058823529414e-06,
|
| 98 |
+
"loss": 0.6963,
|
| 99 |
+
"step": 55
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05870841487279843,
|
| 103 |
+
"grad_norm": 31789.291015625,
|
| 104 |
+
"learning_rate": 1.928104575163399e-06,
|
| 105 |
+
"loss": 0.6971,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.06360078277886497,
|
| 110 |
+
"grad_norm": 30762.345703125,
|
| 111 |
+
"learning_rate": 2.0915032679738565e-06,
|
| 112 |
+
"loss": 0.6946,
|
| 113 |
+
"step": 65
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.0684931506849315,
|
| 117 |
+
"grad_norm": 29590.083984375,
|
| 118 |
+
"learning_rate": 2.254901960784314e-06,
|
| 119 |
+
"loss": 0.693,
|
| 120 |
+
"step": 70
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.07338551859099804,
|
| 124 |
+
"grad_norm": 29346.84765625,
|
| 125 |
+
"learning_rate": 2.4183006535947716e-06,
|
| 126 |
+
"loss": 0.6905,
|
| 127 |
+
"step": 75
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.07827788649706457,
|
| 131 |
+
"grad_norm": 37289.77734375,
|
| 132 |
+
"learning_rate": 2.581699346405229e-06,
|
| 133 |
+
"loss": 0.6942,
|
| 134 |
+
"step": 80
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.08317025440313111,
|
| 138 |
+
"grad_norm": 33970.94140625,
|
| 139 |
+
"learning_rate": 2.7450980392156867e-06,
|
| 140 |
+
"loss": 0.69,
|
| 141 |
+
"step": 85
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.08806262230919765,
|
| 145 |
+
"grad_norm": 28671.583984375,
|
| 146 |
+
"learning_rate": 2.9084967320261443e-06,
|
| 147 |
+
"loss": 0.6889,
|
| 148 |
+
"step": 90
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.09295499021526418,
|
| 152 |
+
"grad_norm": 30156.005859375,
|
| 153 |
+
"learning_rate": 3.071895424836602e-06,
|
| 154 |
+
"loss": 0.6866,
|
| 155 |
+
"step": 95
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.09784735812133072,
|
| 159 |
+
"grad_norm": 33484.71484375,
|
| 160 |
+
"learning_rate": 3.2352941176470594e-06,
|
| 161 |
+
"loss": 0.6888,
|
| 162 |
+
"step": 100
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.09784735812133072,
|
| 166 |
+
"eval_accuracy": 0.767,
|
| 167 |
+
"eval_loss": 0.6559821367263794,
|
| 168 |
+
"eval_macro_f1": 0.5260673147136775,
|
| 169 |
+
"eval_precision": 0.6062366452991452,
|
| 170 |
+
"eval_recall": 0.5367285927824044,
|
| 171 |
+
"eval_runtime": 17.3972,
|
| 172 |
+
"eval_samples_per_second": 57.481,
|
| 173 |
+
"eval_steps_per_second": 0.057,
|
| 174 |
+
"step": 100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.10273972602739725,
|
| 178 |
+
"grad_norm": 35390.96484375,
|
| 179 |
+
"learning_rate": 3.398692810457517e-06,
|
| 180 |
+
"loss": 0.6893,
|
| 181 |
+
"step": 105
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.10763209393346379,
|
| 185 |
+
"grad_norm": 34452.11328125,
|
| 186 |
+
"learning_rate": 3.562091503267974e-06,
|
| 187 |
+
"loss": 0.6849,
|
| 188 |
+
"step": 110
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.11252446183953033,
|
| 192 |
+
"grad_norm": 41847.0625,
|
| 193 |
+
"learning_rate": 3.7254901960784316e-06,
|
| 194 |
+
"loss": 0.6853,
|
| 195 |
+
"step": 115
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.11741682974559686,
|
| 199 |
+
"grad_norm": 31951.4140625,
|
| 200 |
+
"learning_rate": 3.88888888888889e-06,
|
| 201 |
+
"loss": 0.6802,
|
| 202 |
+
"step": 120
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.1223091976516634,
|
| 206 |
+
"grad_norm": 34176.79296875,
|
| 207 |
+
"learning_rate": 4.052287581699347e-06,
|
| 208 |
+
"loss": 0.6871,
|
| 209 |
+
"step": 125
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.12720156555772993,
|
| 213 |
+
"grad_norm": 35482.6640625,
|
| 214 |
+
"learning_rate": 4.215686274509805e-06,
|
| 215 |
+
"loss": 0.6789,
|
| 216 |
+
"step": 130
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.13209393346379647,
|
| 220 |
+
"grad_norm": 60289.4296875,
|
| 221 |
+
"learning_rate": 4.379084967320262e-06,
|
| 222 |
+
"loss": 0.6844,
|
| 223 |
+
"step": 135
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.136986301369863,
|
| 227 |
+
"grad_norm": 41964.47265625,
|
| 228 |
+
"learning_rate": 4.542483660130719e-06,
|
| 229 |
+
"loss": 0.6808,
|
| 230 |
+
"step": 140
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.14187866927592954,
|
| 234 |
+
"grad_norm": 35805.8203125,
|
| 235 |
+
"learning_rate": 4.705882352941177e-06,
|
| 236 |
+
"loss": 0.6748,
|
| 237 |
+
"step": 145
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.14677103718199608,
|
| 241 |
+
"grad_norm": 25688.607421875,
|
| 242 |
+
"learning_rate": 4.869281045751634e-06,
|
| 243 |
+
"loss": 0.6769,
|
| 244 |
+
"step": 150
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.14677103718199608,
|
| 248 |
+
"eval_accuracy": 0.728,
|
| 249 |
+
"eval_loss": 0.6580190658569336,
|
| 250 |
+
"eval_macro_f1": 0.5668100015926103,
|
| 251 |
+
"eval_precision": 0.5782073308365263,
|
| 252 |
+
"eval_recall": 0.5627889260176255,
|
| 253 |
+
"eval_runtime": 17.3848,
|
| 254 |
+
"eval_samples_per_second": 57.521,
|
| 255 |
+
"eval_steps_per_second": 0.058,
|
| 256 |
+
"step": 150
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.15166340508806261,
|
| 260 |
+
"grad_norm": 30171.484375,
|
| 261 |
+
"learning_rate": 5.032679738562092e-06,
|
| 262 |
+
"loss": 0.6706,
|
| 263 |
+
"step": 155
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.15655577299412915,
|
| 267 |
+
"grad_norm": 29393.716796875,
|
| 268 |
+
"learning_rate": 5.19607843137255e-06,
|
| 269 |
+
"loss": 0.6764,
|
| 270 |
+
"step": 160
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.16144814090019569,
|
| 274 |
+
"grad_norm": 34377.2578125,
|
| 275 |
+
"learning_rate": 5.359477124183007e-06,
|
| 276 |
+
"loss": 0.6688,
|
| 277 |
+
"step": 165
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.16634050880626222,
|
| 281 |
+
"grad_norm": 34805.3671875,
|
| 282 |
+
"learning_rate": 5.522875816993465e-06,
|
| 283 |
+
"loss": 0.6673,
|
| 284 |
+
"step": 170
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.17123287671232876,
|
| 288 |
+
"grad_norm": 29948.095703125,
|
| 289 |
+
"learning_rate": 5.686274509803922e-06,
|
| 290 |
+
"loss": 0.6652,
|
| 291 |
+
"step": 175
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.1761252446183953,
|
| 295 |
+
"grad_norm": 34735.33984375,
|
| 296 |
+
"learning_rate": 5.84967320261438e-06,
|
| 297 |
+
"loss": 0.6709,
|
| 298 |
+
"step": 180
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.18101761252446183,
|
| 302 |
+
"grad_norm": 36469.0703125,
|
| 303 |
+
"learning_rate": 6.0130718954248365e-06,
|
| 304 |
+
"loss": 0.6606,
|
| 305 |
+
"step": 185
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.18590998043052837,
|
| 309 |
+
"grad_norm": 27843.798828125,
|
| 310 |
+
"learning_rate": 6.176470588235295e-06,
|
| 311 |
+
"loss": 0.6666,
|
| 312 |
+
"step": 190
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.1908023483365949,
|
| 316 |
+
"grad_norm": 27965.966796875,
|
| 317 |
+
"learning_rate": 6.3398692810457515e-06,
|
| 318 |
+
"loss": 0.6626,
|
| 319 |
+
"step": 195
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.19569471624266144,
|
| 323 |
+
"grad_norm": 28469.09375,
|
| 324 |
+
"learning_rate": 6.5032679738562095e-06,
|
| 325 |
+
"loss": 0.6601,
|
| 326 |
+
"step": 200
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.19569471624266144,
|
| 330 |
+
"eval_accuracy": 0.698,
|
| 331 |
+
"eval_loss": 0.6574791669845581,
|
| 332 |
+
"eval_macro_f1": 0.5962545254252696,
|
| 333 |
+
"eval_precision": 0.591974921630094,
|
| 334 |
+
"eval_recall": 0.605831327804422,
|
| 335 |
+
"eval_runtime": 17.3909,
|
| 336 |
+
"eval_samples_per_second": 57.501,
|
| 337 |
+
"eval_steps_per_second": 0.058,
|
| 338 |
+
"step": 200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.20058708414872797,
|
| 342 |
+
"grad_norm": 26626.736328125,
|
| 343 |
+
"learning_rate": 6.666666666666667e-06,
|
| 344 |
+
"loss": 0.6598,
|
| 345 |
+
"step": 205
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.2054794520547945,
|
| 349 |
+
"grad_norm": 26082.599609375,
|
| 350 |
+
"learning_rate": 6.830065359477125e-06,
|
| 351 |
+
"loss": 0.6568,
|
| 352 |
+
"step": 210
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.21037181996086105,
|
| 356 |
+
"grad_norm": 33339.375,
|
| 357 |
+
"learning_rate": 6.993464052287582e-06,
|
| 358 |
+
"loss": 0.6563,
|
| 359 |
+
"step": 215
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.21526418786692758,
|
| 363 |
+
"grad_norm": 30894.603515625,
|
| 364 |
+
"learning_rate": 7.15686274509804e-06,
|
| 365 |
+
"loss": 0.652,
|
| 366 |
+
"step": 220
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.22015655577299412,
|
| 370 |
+
"grad_norm": 29593.958984375,
|
| 371 |
+
"learning_rate": 7.320261437908497e-06,
|
| 372 |
+
"loss": 0.6491,
|
| 373 |
+
"step": 225
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.22504892367906065,
|
| 377 |
+
"grad_norm": 39939.2890625,
|
| 378 |
+
"learning_rate": 7.483660130718955e-06,
|
| 379 |
+
"loss": 0.6479,
|
| 380 |
+
"step": 230
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.2299412915851272,
|
| 384 |
+
"grad_norm": 32097.01953125,
|
| 385 |
+
"learning_rate": 7.647058823529411e-06,
|
| 386 |
+
"loss": 0.6464,
|
| 387 |
+
"step": 235
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.23483365949119372,
|
| 391 |
+
"grad_norm": 31191.142578125,
|
| 392 |
+
"learning_rate": 7.81045751633987e-06,
|
| 393 |
+
"loss": 0.6469,
|
| 394 |
+
"step": 240
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.23972602739726026,
|
| 398 |
+
"grad_norm": 30402.431640625,
|
| 399 |
+
"learning_rate": 7.973856209150329e-06,
|
| 400 |
+
"loss": 0.6407,
|
| 401 |
+
"step": 245
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.2446183953033268,
|
| 405 |
+
"grad_norm": 30825.1328125,
|
| 406 |
+
"learning_rate": 8.137254901960784e-06,
|
| 407 |
+
"loss": 0.6391,
|
| 408 |
+
"step": 250
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.2446183953033268,
|
| 412 |
+
"eval_accuracy": 0.623,
|
| 413 |
+
"eval_loss": 0.6709860563278198,
|
| 414 |
+
"eval_macro_f1": 0.5814715106436125,
|
| 415 |
+
"eval_precision": 0.6025402726146221,
|
| 416 |
+
"eval_recall": 0.6470932816224296,
|
| 417 |
+
"eval_runtime": 17.5511,
|
| 418 |
+
"eval_samples_per_second": 56.977,
|
| 419 |
+
"eval_steps_per_second": 0.057,
|
| 420 |
+
"step": 250
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.24951076320939333,
|
| 424 |
+
"grad_norm": 26645.732421875,
|
| 425 |
+
"learning_rate": 8.300653594771243e-06,
|
| 426 |
+
"loss": 0.6397,
|
| 427 |
+
"step": 255
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.25440313111545987,
|
| 431 |
+
"grad_norm": 29653.92578125,
|
| 432 |
+
"learning_rate": 8.4640522875817e-06,
|
| 433 |
+
"loss": 0.6437,
|
| 434 |
+
"step": 260
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.25929549902152643,
|
| 438 |
+
"grad_norm": 31826.6484375,
|
| 439 |
+
"learning_rate": 8.627450980392157e-06,
|
| 440 |
+
"loss": 0.6373,
|
| 441 |
+
"step": 265
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.26418786692759294,
|
| 445 |
+
"grad_norm": 35353.4765625,
|
| 446 |
+
"learning_rate": 8.790849673202614e-06,
|
| 447 |
+
"loss": 0.6319,
|
| 448 |
+
"step": 270
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.2690802348336595,
|
| 452 |
+
"grad_norm": 30883.482421875,
|
| 453 |
+
"learning_rate": 8.954248366013073e-06,
|
| 454 |
+
"loss": 0.6355,
|
| 455 |
+
"step": 275
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.273972602739726,
|
| 459 |
+
"grad_norm": 26454.451171875,
|
| 460 |
+
"learning_rate": 9.11764705882353e-06,
|
| 461 |
+
"loss": 0.6261,
|
| 462 |
+
"step": 280
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.2788649706457926,
|
| 466 |
+
"grad_norm": 27102.65234375,
|
| 467 |
+
"learning_rate": 9.281045751633987e-06,
|
| 468 |
+
"loss": 0.6291,
|
| 469 |
+
"step": 285
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.2837573385518591,
|
| 473 |
+
"grad_norm": 26538.755859375,
|
| 474 |
+
"learning_rate": 9.444444444444445e-06,
|
| 475 |
+
"loss": 0.6265,
|
| 476 |
+
"step": 290
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.28864970645792565,
|
| 480 |
+
"grad_norm": 27230.40625,
|
| 481 |
+
"learning_rate": 9.607843137254903e-06,
|
| 482 |
+
"loss": 0.617,
|
| 483 |
+
"step": 295
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.29354207436399216,
|
| 487 |
+
"grad_norm": 27588.068359375,
|
| 488 |
+
"learning_rate": 9.77124183006536e-06,
|
| 489 |
+
"loss": 0.618,
|
| 490 |
+
"step": 300
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.29354207436399216,
|
| 494 |
+
"eval_accuracy": 0.59,
|
| 495 |
+
"eval_loss": 0.6805335283279419,
|
| 496 |
+
"eval_macro_f1": 0.5635902261241277,
|
| 497 |
+
"eval_precision": 0.6075875666060336,
|
| 498 |
+
"eval_recall": 0.6546334931985156,
|
| 499 |
+
"eval_runtime": 17.4391,
|
| 500 |
+
"eval_samples_per_second": 57.342,
|
| 501 |
+
"eval_steps_per_second": 0.057,
|
| 502 |
+
"step": 300
|
| 503 |
+
}
|
| 504 |
+
],
|
| 505 |
+
"logging_steps": 5,
|
| 506 |
+
"max_steps": 3066,
|
| 507 |
+
"num_input_tokens_seen": 0,
|
| 508 |
+
"num_train_epochs": 3,
|
| 509 |
+
"save_steps": 100,
|
| 510 |
+
"stateful_callbacks": {
|
| 511 |
+
"EarlyStoppingCallback": {
|
| 512 |
+
"args": {
|
| 513 |
+
"early_stopping_patience": 3,
|
| 514 |
+
"early_stopping_threshold": 0.0
|
| 515 |
+
},
|
| 516 |
+
"attributes": {
|
| 517 |
+
"early_stopping_patience_counter": 2
|
| 518 |
+
}
|
| 519 |
+
},
|
| 520 |
+
"TrainerControl": {
|
| 521 |
+
"args": {
|
| 522 |
+
"should_epoch_stop": false,
|
| 523 |
+
"should_evaluate": false,
|
| 524 |
+
"should_log": false,
|
| 525 |
+
"should_save": true,
|
| 526 |
+
"should_training_stop": false
|
| 527 |
+
},
|
| 528 |
+
"attributes": {}
|
| 529 |
+
}
|
| 530 |
+
},
|
| 531 |
+
"total_flos": 4.0413858103296e+16,
|
| 532 |
+
"train_batch_size": 512,
|
| 533 |
+
"trial_name": null,
|
| 534 |
+
"trial_params": null
|
| 535 |
+
}
|
graphcodebert-vanilla/checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3d448040cc8193c39a3aa43e3972db0566234234cb8950ae351de6781f2f556
|
| 3 |
+
size 5905
|
graphcodebert-vanilla/checkpoint-300/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/final_model/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.3,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": 0.3,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.3,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"transformers_version": "4.56.0",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50265
|
| 29 |
+
}
|
graphcodebert-vanilla/final_model/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-vanilla/final_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:babd5890473a83a2cc134eea6510f56a09e9b665511011c2ddbd1e2d9d7bbf66
|
| 3 |
+
size 498612824
|
graphcodebert-vanilla/final_model/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
graphcodebert-vanilla/final_model/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|