upload checkpoints
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/config.json +29 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/config_hyperparams.json +53 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/hyperparams.json +35 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/merges.txt +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/model.safetensors +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/optimizer.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/rng_state.pth +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/scaler.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/scheduler.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/special_tokens_map.json +51 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/tokenizer.json +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/tokenizer_config.json +58 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/trainer_state.json +863 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/training_args.bin +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/vocab.json +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/config.json +29 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/config_hyperparams.json +53 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/hyperparams.json +35 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/merges.txt +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/model.safetensors +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/optimizer.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/rng_state.pth +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/scaler.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/scheduler.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/special_tokens_map.json +51 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/tokenizer.json +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/tokenizer_config.json +58 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/trainer_state.json +877 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/training_args.bin +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/vocab.json +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/config.json +29 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/config_hyperparams.json +53 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/hyperparams.json +35 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/merges.txt +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/model.safetensors +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/optimizer.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/rng_state.pth +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/scaler.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/scheduler.pt +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/special_tokens_map.json +51 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/tokenizer.json +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/tokenizer_config.json +58 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/trainer_state.json +722 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/training_args.bin +3 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-850/vocab.json +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-900/config.json +29 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-900/config_hyperparams.json +53 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-900/hyperparams.json +35 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-900/merges.txt +0 -0
- graphcodebert-base-lowLR-highBatchSize/checkpoint-900/model.safetensors +3 -0
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/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-base-lowLR-highBatchSize/checkpoint-1000/config_hyperparams.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train_config": {
|
| 3 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 4 |
+
"num_epochs": 1,
|
| 5 |
+
"batch_size": 256,
|
| 6 |
+
"learning_rate": 1e-06,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"num_labels": 2,
|
| 9 |
+
"loss_type": "r-drop",
|
| 10 |
+
"focal_alpha": 1.0,
|
| 11 |
+
"focal_gamma": 2.0,
|
| 12 |
+
"r_drop_alpha": 10.0,
|
| 13 |
+
"infonce_temperature": 0.07,
|
| 14 |
+
"infonce_weight": 0.5,
|
| 15 |
+
"label_smoothing": 0.5,
|
| 16 |
+
"adversarial_epsilon": 0.5,
|
| 17 |
+
"use_swa": false,
|
| 18 |
+
"swa_start_epoch": 0,
|
| 19 |
+
"swa_lr": 1e-05,
|
| 20 |
+
"data_augmentation": true,
|
| 21 |
+
"aug_rename_prob": 0.8,
|
| 22 |
+
"aug_format_prob": 0.8,
|
| 23 |
+
"freeze_base": true,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"use_wandb": true,
|
| 26 |
+
"mixup_alpha": 1.0,
|
| 27 |
+
"low_pass_keep_ratio": 0.5,
|
| 28 |
+
"freq_consistency_weight": 0.5
|
| 29 |
+
},
|
| 30 |
+
"training_arguments": {
|
| 31 |
+
"output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
|
| 32 |
+
"num_train_epochs": 1,
|
| 33 |
+
"per_device_train_batch_size": 256,
|
| 34 |
+
"per_device_eval_batch_size": 512,
|
| 35 |
+
"learning_rate": 1e-06,
|
| 36 |
+
"warmup_steps": 204,
|
| 37 |
+
"weight_decay": 0.1,
|
| 38 |
+
"logging_steps": 10,
|
| 39 |
+
"eval_steps": 50,
|
| 40 |
+
"save_steps": 50,
|
| 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": 1000,
|
| 49 |
+
"epoch": 0.9784735812133072,
|
| 50 |
+
"best_metric": 0.5584519389438943,
|
| 51 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-900"
|
| 52 |
+
}
|
| 53 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/hyperparams.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 3 |
+
"output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
|
| 4 |
+
"num_epochs": 1,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"batch_size": 256,
|
| 7 |
+
"learning_rate": 1e-06,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"num_labels": 2,
|
| 10 |
+
"use_wandb": true,
|
| 11 |
+
"freeze_base": true,
|
| 12 |
+
"loss_type": "r-drop",
|
| 13 |
+
"focal_alpha": 1.0,
|
| 14 |
+
"focal_gamma": 2.0,
|
| 15 |
+
"r_drop_alpha": 10.0,
|
| 16 |
+
"infonce_temperature": 0.07,
|
| 17 |
+
"infonce_weight": 0.5,
|
| 18 |
+
"seed": 42,
|
| 19 |
+
"resume_from_checkpoint": "checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-500",
|
| 20 |
+
"label_smoothing": 0.5,
|
| 21 |
+
"adversarial_epsilon": 0.5,
|
| 22 |
+
"use_swa": false,
|
| 23 |
+
"swa_start_epoch": 0,
|
| 24 |
+
"swa_lr": 1e-05,
|
| 25 |
+
"data_augmentation": true,
|
| 26 |
+
"aug_rename_prob": 0.8,
|
| 27 |
+
"aug_format_prob": 0.8,
|
| 28 |
+
"mixup_alpha": 1.0,
|
| 29 |
+
"low_pass_keep_ratio": 0.5,
|
| 30 |
+
"freq_consistency_weight": 0.5,
|
| 31 |
+
"hidden_dropout_prob": 0.3,
|
| 32 |
+
"attention_probs_dropout_prob": 0.3,
|
| 33 |
+
"classifier_dropout": 0.3,
|
| 34 |
+
"device": "cuda"
|
| 35 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce2c655bc88524b2b24a5769ffd30d15b8fb4dadc6531be416f2723b135ae619
|
| 3 |
+
size 498612824
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1f93d4528d9aba86d394451b0fb00538d689b14cc49f195ade71c8126f9807a
|
| 3 |
+
size 4741859
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95c54f1bfe3ad63d4a84ab4d893ea72e8cf876619b55a8d4a246b343613af58c
|
| 3 |
+
size 14645
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
|
| 3 |
+
size 1383
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac5d09b7e45e1cd11796cf49852e18771997ad3dffc320a12c4418112d739574
|
| 3 |
+
size 1465
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/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-base-lowLR-highBatchSize/checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/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-base-lowLR-highBatchSize/checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,863 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 900,
|
| 3 |
+
"best_metric": 0.5584519389438943,
|
| 4 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-900",
|
| 5 |
+
"epoch": 0.9784735812133072,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009784735812133072,
|
| 14 |
+
"grad_norm": 165951.1875,
|
| 15 |
+
"learning_rate": 4.411764705882353e-08,
|
| 16 |
+
"loss": 0.8416,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.019569471624266144,
|
| 21 |
+
"grad_norm": 206132.796875,
|
| 22 |
+
"learning_rate": 9.313725490196079e-08,
|
| 23 |
+
"loss": 0.8378,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.029354207436399216,
|
| 28 |
+
"grad_norm": 171197.53125,
|
| 29 |
+
"learning_rate": 1.4215686274509803e-07,
|
| 30 |
+
"loss": 0.8388,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03913894324853229,
|
| 35 |
+
"grad_norm": 206661.828125,
|
| 36 |
+
"learning_rate": 1.9117647058823527e-07,
|
| 37 |
+
"loss": 0.847,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04892367906066536,
|
| 42 |
+
"grad_norm": 230268.96875,
|
| 43 |
+
"learning_rate": 2.4019607843137255e-07,
|
| 44 |
+
"loss": 0.8411,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05870841487279843,
|
| 49 |
+
"grad_norm": 133248.28125,
|
| 50 |
+
"learning_rate": 2.8921568627450984e-07,
|
| 51 |
+
"loss": 0.8412,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0684931506849315,
|
| 56 |
+
"grad_norm": 147768.828125,
|
| 57 |
+
"learning_rate": 3.3823529411764707e-07,
|
| 58 |
+
"loss": 0.8431,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07827788649706457,
|
| 63 |
+
"grad_norm": 167327.53125,
|
| 64 |
+
"learning_rate": 3.872549019607843e-07,
|
| 65 |
+
"loss": 0.8431,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08806262230919765,
|
| 70 |
+
"grad_norm": 151943.75,
|
| 71 |
+
"learning_rate": 4.3627450980392154e-07,
|
| 72 |
+
"loss": 0.8311,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09784735812133072,
|
| 77 |
+
"grad_norm": 149971.59375,
|
| 78 |
+
"learning_rate": 4.852941176470588e-07,
|
| 79 |
+
"loss": 0.8412,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10763209393346379,
|
| 84 |
+
"grad_norm": 162329.40625,
|
| 85 |
+
"learning_rate": 5.34313725490196e-07,
|
| 86 |
+
"loss": 0.8356,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.11741682974559686,
|
| 91 |
+
"grad_norm": 158769.765625,
|
| 92 |
+
"learning_rate": 5.833333333333334e-07,
|
| 93 |
+
"loss": 0.8351,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12720156555772993,
|
| 98 |
+
"grad_norm": 157725.59375,
|
| 99 |
+
"learning_rate": 6.323529411764706e-07,
|
| 100 |
+
"loss": 0.8331,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.136986301369863,
|
| 105 |
+
"grad_norm": 205733.0,
|
| 106 |
+
"learning_rate": 6.813725490196079e-07,
|
| 107 |
+
"loss": 0.8366,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.14677103718199608,
|
| 112 |
+
"grad_norm": 172581.328125,
|
| 113 |
+
"learning_rate": 7.30392156862745e-07,
|
| 114 |
+
"loss": 0.831,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15655577299412915,
|
| 119 |
+
"grad_norm": 137428.0,
|
| 120 |
+
"learning_rate": 7.794117647058823e-07,
|
| 121 |
+
"loss": 0.8326,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16634050880626222,
|
| 126 |
+
"grad_norm": 151189.203125,
|
| 127 |
+
"learning_rate": 8.284313725490196e-07,
|
| 128 |
+
"loss": 0.8281,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1761252446183953,
|
| 133 |
+
"grad_norm": 145620.625,
|
| 134 |
+
"learning_rate": 8.774509803921568e-07,
|
| 135 |
+
"loss": 0.8252,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.18590998043052837,
|
| 140 |
+
"grad_norm": 169938.84375,
|
| 141 |
+
"learning_rate": 9.264705882352941e-07,
|
| 142 |
+
"loss": 0.8308,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.19569471624266144,
|
| 147 |
+
"grad_norm": 138760.015625,
|
| 148 |
+
"learning_rate": 9.754901960784313e-07,
|
| 149 |
+
"loss": 0.824,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2054794520547945,
|
| 154 |
+
"grad_norm": 107872.125,
|
| 155 |
+
"learning_rate": 9.99631294374483e-07,
|
| 156 |
+
"loss": 0.8254,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.21526418786692758,
|
| 161 |
+
"grad_norm": 113610.8359375,
|
| 162 |
+
"learning_rate": 9.966849112204936e-07,
|
| 163 |
+
"loss": 0.8267,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.22504892367906065,
|
| 168 |
+
"grad_norm": 172441.515625,
|
| 169 |
+
"learning_rate": 9.908095200725339e-07,
|
| 170 |
+
"loss": 0.8198,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.23483365949119372,
|
| 175 |
+
"grad_norm": 128079.9140625,
|
| 176 |
+
"learning_rate": 9.82039768787326e-07,
|
| 177 |
+
"loss": 0.8143,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2446183953033268,
|
| 182 |
+
"grad_norm": 98149.8984375,
|
| 183 |
+
"learning_rate": 9.70427373595903e-07,
|
| 184 |
+
"loss": 0.8191,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.25440313111545987,
|
| 189 |
+
"grad_norm": 147377.4375,
|
| 190 |
+
"learning_rate": 9.560408141270531e-07,
|
| 191 |
+
"loss": 0.8178,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.26418786692759294,
|
| 196 |
+
"grad_norm": 156439.40625,
|
| 197 |
+
"learning_rate": 9.389649295750781e-07,
|
| 198 |
+
"loss": 0.8085,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.273972602739726,
|
| 203 |
+
"grad_norm": 131892.015625,
|
| 204 |
+
"learning_rate": 9.193004183933174e-07,
|
| 205 |
+
"loss": 0.8172,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2837573385518591,
|
| 210 |
+
"grad_norm": 132474.5,
|
| 211 |
+
"learning_rate": 8.971632444637971e-07,
|
| 212 |
+
"loss": 0.8136,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.29354207436399216,
|
| 217 |
+
"grad_norm": 112619.109375,
|
| 218 |
+
"learning_rate": 8.726839532448928e-07,
|
| 219 |
+
"loss": 0.8065,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.30332681017612523,
|
| 224 |
+
"grad_norm": 94225.5703125,
|
| 225 |
+
"learning_rate": 8.460069019297606e-07,
|
| 226 |
+
"loss": 0.813,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3131115459882583,
|
| 231 |
+
"grad_norm": 117812.8203125,
|
| 232 |
+
"learning_rate": 8.172894081553822e-07,
|
| 233 |
+
"loss": 0.8022,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.32289628180039137,
|
| 238 |
+
"grad_norm": 143287.125,
|
| 239 |
+
"learning_rate": 7.86700822282382e-07,
|
| 240 |
+
"loss": 0.8061,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.33268101761252444,
|
| 245 |
+
"grad_norm": 107456.25,
|
| 246 |
+
"learning_rate": 7.544215287164917e-07,
|
| 247 |
+
"loss": 0.8006,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3424657534246575,
|
| 252 |
+
"grad_norm": 101521.171875,
|
| 253 |
+
"learning_rate": 7.206418821609812e-07,
|
| 254 |
+
"loss": 0.8055,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3522504892367906,
|
| 259 |
+
"grad_norm": 118311.5234375,
|
| 260 |
+
"learning_rate": 6.855610850731017e-07,
|
| 261 |
+
"loss": 0.8081,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.36203522504892366,
|
| 266 |
+
"grad_norm": 89621.828125,
|
| 267 |
+
"learning_rate": 6.493860129443046e-07,
|
| 268 |
+
"loss": 0.8058,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.37181996086105673,
|
| 273 |
+
"grad_norm": 143168.65625,
|
| 274 |
+
"learning_rate": 6.123299943316975e-07,
|
| 275 |
+
"loss": 0.8028,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3816046966731898,
|
| 280 |
+
"grad_norm": 118598.2890625,
|
| 281 |
+
"learning_rate": 5.746115528350295e-07,
|
| 282 |
+
"loss": 0.8032,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3913894324853229,
|
| 287 |
+
"grad_norm": 111807.8203125,
|
| 288 |
+
"learning_rate": 5.364531184379139e-07,
|
| 289 |
+
"loss": 0.8014,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.40117416829745595,
|
| 294 |
+
"grad_norm": 124106.1328125,
|
| 295 |
+
"learning_rate": 4.980797158126566e-07,
|
| 296 |
+
"loss": 0.8045,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.410958904109589,
|
| 301 |
+
"grad_norm": 102746.4765625,
|
| 302 |
+
"learning_rate": 4.597176373239061e-07,
|
| 303 |
+
"loss": 0.7996,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4207436399217221,
|
| 308 |
+
"grad_norm": 108317.5859375,
|
| 309 |
+
"learning_rate": 4.215931085565761e-07,
|
| 310 |
+
"loss": 0.8037,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.43052837573385516,
|
| 315 |
+
"grad_norm": 113342.515625,
|
| 316 |
+
"learning_rate": 3.8393095423757764e-07,
|
| 317 |
+
"loss": 0.8047,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.44031311154598823,
|
| 322 |
+
"grad_norm": 111908.90625,
|
| 323 |
+
"learning_rate": 3.469532724185699e-07,
|
| 324 |
+
"loss": 0.8021,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4500978473581213,
|
| 329 |
+
"grad_norm": 85004.15625,
|
| 330 |
+
"learning_rate": 3.1087812473822845e-07,
|
| 331 |
+
"loss": 0.8012,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4598825831702544,
|
| 336 |
+
"grad_norm": 98335.1796875,
|
| 337 |
+
"learning_rate": 2.7591825048770643e-07,
|
| 338 |
+
"loss": 0.7977,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.46966731898238745,
|
| 343 |
+
"grad_norm": 110674.03125,
|
| 344 |
+
"learning_rate": 2.422798120625886e-07,
|
| 345 |
+
"loss": 0.7979,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4794520547945205,
|
| 350 |
+
"grad_norm": 114861.5390625,
|
| 351 |
+
"learning_rate": 2.1016117919955512e-07,
|
| 352 |
+
"loss": 0.8014,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4892367906066536,
|
| 357 |
+
"grad_norm": 130109.5703125,
|
| 358 |
+
"learning_rate": 1.7975175916725031e-07,
|
| 359 |
+
"loss": 0.7994,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.49902152641878667,
|
| 364 |
+
"grad_norm": 93286.4296875,
|
| 365 |
+
"learning_rate": 1.5123087980985606e-07,
|
| 366 |
+
"loss": 0.8039,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5088062622309197,
|
| 371 |
+
"grad_norm": 123646.703125,
|
| 372 |
+
"learning_rate": 1.2476673203018728e-07,
|
| 373 |
+
"loss": 0.7917,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5185909980430529,
|
| 378 |
+
"grad_norm": 98060.2265625,
|
| 379 |
+
"learning_rate": 1.0051537794861287e-07,
|
| 380 |
+
"loss": 0.7945,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5283757338551859,
|
| 385 |
+
"grad_norm": 91181.1796875,
|
| 386 |
+
"learning_rate": 7.861983058679871e-08,
|
| 387 |
+
"loss": 0.7952,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.538160469667319,
|
| 392 |
+
"grad_norm": 97605.3984375,
|
| 393 |
+
"learning_rate": 5.920921050348626e-08,
|
| 394 |
+
"loss": 0.7963,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.538160469667319,
|
| 399 |
+
"eval_accuracy": 0.767,
|
| 400 |
+
"eval_loss": 0.662277102470398,
|
| 401 |
+
"eval_macro_f1": 0.5341406895117674,
|
| 402 |
+
"eval_precision": 0.6105222734254993,
|
| 403 |
+
"eval_recall": 0.5415245482510056,
|
| 404 |
+
"eval_runtime": 16.9722,
|
| 405 |
+
"eval_samples_per_second": 58.92,
|
| 406 |
+
"eval_steps_per_second": 0.059,
|
| 407 |
+
"step": 550
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.547945205479452,
|
| 411 |
+
"grad_norm": 101627.8046875,
|
| 412 |
+
"learning_rate": 4.23979843557199e-08,
|
| 413 |
+
"loss": 0.7962,
|
| 414 |
+
"step": 560
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.5577299412915852,
|
| 418 |
+
"grad_norm": 73889.578125,
|
| 419 |
+
"learning_rate": 2.8285289875818407e-08,
|
| 420 |
+
"loss": 0.794,
|
| 421 |
+
"step": 570
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.5675146771037182,
|
| 425 |
+
"grad_norm": 87191.0546875,
|
| 426 |
+
"learning_rate": 1.695435124477512e-08,
|
| 427 |
+
"loss": 0.7984,
|
| 428 |
+
"step": 580
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.5772994129158513,
|
| 432 |
+
"grad_norm": 105470.234375,
|
| 433 |
+
"learning_rate": 8.471988309699807e-09,
|
| 434 |
+
"loss": 0.7924,
|
| 435 |
+
"step": 590
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.5870841487279843,
|
| 439 |
+
"grad_norm": 81710.7265625,
|
| 440 |
+
"learning_rate": 2.8882225395023275e-09,
|
| 441 |
+
"loss": 0.8005,
|
| 442 |
+
"step": 600
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.5870841487279843,
|
| 446 |
+
"eval_accuracy": 0.767,
|
| 447 |
+
"eval_loss": 0.6623347401618958,
|
| 448 |
+
"eval_macro_f1": 0.5341406895117674,
|
| 449 |
+
"eval_precision": 0.6105222734254993,
|
| 450 |
+
"eval_recall": 0.5415245482510056,
|
| 451 |
+
"eval_runtime": 17.0174,
|
| 452 |
+
"eval_samples_per_second": 58.763,
|
| 453 |
+
"eval_steps_per_second": 0.059,
|
| 454 |
+
"step": 600
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.5968688845401174,
|
| 458 |
+
"grad_norm": 97212.125,
|
| 459 |
+
"learning_rate": 2.35982042542604e-10,
|
| 460 |
+
"loss": 0.7981,
|
| 461 |
+
"step": 610
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.6066536203522505,
|
| 465 |
+
"grad_norm": 100700.640625,
|
| 466 |
+
"learning_rate": 9.994690926142082e-07,
|
| 467 |
+
"loss": 0.8006,
|
| 468 |
+
"step": 620
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.6164383561643836,
|
| 472 |
+
"grad_norm": 88023.046875,
|
| 473 |
+
"learning_rate": 9.962287406393883e-07,
|
| 474 |
+
"loss": 0.7976,
|
| 475 |
+
"step": 630
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.6262230919765166,
|
| 479 |
+
"grad_norm": 118936.609375,
|
| 480 |
+
"learning_rate": 9.900620707609317e-07,
|
| 481 |
+
"loss": 0.7961,
|
| 482 |
+
"step": 640
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.6360078277886497,
|
| 486 |
+
"grad_norm": 91811.3984375,
|
| 487 |
+
"learning_rate": 9.810054485397043e-07,
|
| 488 |
+
"loss": 0.7904,
|
| 489 |
+
"step": 650
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.6360078277886497,
|
| 493 |
+
"eval_accuracy": 0.757,
|
| 494 |
+
"eval_loss": 0.6629467606544495,
|
| 495 |
+
"eval_macro_f1": 0.5299579283330915,
|
| 496 |
+
"eval_precision": 0.5844492268452096,
|
| 497 |
+
"eval_recall": 0.5366881936388663,
|
| 498 |
+
"eval_runtime": 17.0504,
|
| 499 |
+
"eval_samples_per_second": 58.65,
|
| 500 |
+
"eval_steps_per_second": 0.059,
|
| 501 |
+
"step": 650
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.6457925636007827,
|
| 505 |
+
"grad_norm": 118632.46875,
|
| 506 |
+
"learning_rate": 9.69112281917613e-07,
|
| 507 |
+
"loss": 0.7927,
|
| 508 |
+
"step": 660
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.6555772994129159,
|
| 512 |
+
"grad_norm": 70413.0390625,
|
| 513 |
+
"learning_rate": 9.544527062648345e-07,
|
| 514 |
+
"loss": 0.785,
|
| 515 |
+
"step": 670
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.6653620352250489,
|
| 519 |
+
"grad_norm": 84746.4453125,
|
| 520 |
+
"learning_rate": 9.371131707834789e-07,
|
| 521 |
+
"loss": 0.7861,
|
| 522 |
+
"step": 680
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.675146771037182,
|
| 526 |
+
"grad_norm": 92019.0390625,
|
| 527 |
+
"learning_rate": 9.171959287067115e-07,
|
| 528 |
+
"loss": 0.7892,
|
| 529 |
+
"step": 690
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.684931506849315,
|
| 533 |
+
"grad_norm": 70649.2578125,
|
| 534 |
+
"learning_rate": 8.948184342996868e-07,
|
| 535 |
+
"loss": 0.789,
|
| 536 |
+
"step": 700
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.684931506849315,
|
| 540 |
+
"eval_accuracy": 0.751,
|
| 541 |
+
"eval_loss": 0.6648359894752502,
|
| 542 |
+
"eval_macro_f1": 0.5514410631387237,
|
| 543 |
+
"eval_precision": 0.589223697650664,
|
| 544 |
+
"eval_recall": 0.5504123598294002,
|
| 545 |
+
"eval_runtime": 17.0124,
|
| 546 |
+
"eval_samples_per_second": 58.781,
|
| 547 |
+
"eval_steps_per_second": 0.059,
|
| 548 |
+
"step": 700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.6947162426614482,
|
| 552 |
+
"grad_norm": 80338.796875,
|
| 553 |
+
"learning_rate": 8.701126502182503e-07,
|
| 554 |
+
"loss": 0.7907,
|
| 555 |
+
"step": 710
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7045009784735812,
|
| 559 |
+
"grad_norm": 69257.328125,
|
| 560 |
+
"learning_rate": 8.432242693099946e-07,
|
| 561 |
+
"loss": 0.7881,
|
| 562 |
+
"step": 720
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7142857142857143,
|
| 566 |
+
"grad_norm": 95345.15625,
|
| 567 |
+
"learning_rate": 8.14311855446795e-07,
|
| 568 |
+
"loss": 0.7849,
|
| 569 |
+
"step": 730
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7240704500978473,
|
| 573 |
+
"grad_norm": 94407.8984375,
|
| 574 |
+
"learning_rate": 7.835459084554374e-07,
|
| 575 |
+
"loss": 0.7868,
|
| 576 |
+
"step": 740
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7338551859099804,
|
| 580 |
+
"grad_norm": 74418.0625,
|
| 581 |
+
"learning_rate": 7.511078586605484e-07,
|
| 582 |
+
"loss": 0.783,
|
| 583 |
+
"step": 750
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7338551859099804,
|
| 587 |
+
"eval_accuracy": 0.742,
|
| 588 |
+
"eval_loss": 0.6660248637199402,
|
| 589 |
+
"eval_macro_f1": 0.5532467532467532,
|
| 590 |
+
"eval_precision": 0.579727791757989,
|
| 591 |
+
"eval_recall": 0.5510154613293626,
|
| 592 |
+
"eval_runtime": 16.9303,
|
| 593 |
+
"eval_samples_per_second": 59.066,
|
| 594 |
+
"eval_steps_per_second": 0.059,
|
| 595 |
+
"step": 750
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.7436399217221135,
|
| 599 |
+
"grad_norm": 95142.0546875,
|
| 600 |
+
"learning_rate": 7.171889969691225e-07,
|
| 601 |
+
"loss": 0.7861,
|
| 602 |
+
"step": 760
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.7534246575342466,
|
| 606 |
+
"grad_norm": 118907.203125,
|
| 607 |
+
"learning_rate": 6.819893468060643e-07,
|
| 608 |
+
"loss": 0.7878,
|
| 609 |
+
"step": 770
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.7632093933463796,
|
| 613 |
+
"grad_norm": 66268.78125,
|
| 614 |
+
"learning_rate": 6.457164845530662e-07,
|
| 615 |
+
"loss": 0.7859,
|
| 616 |
+
"step": 780
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.7729941291585127,
|
| 620 |
+
"grad_norm": 81464.265625,
|
| 621 |
+
"learning_rate": 6.085843154468354e-07,
|
| 622 |
+
"loss": 0.7819,
|
| 623 |
+
"step": 790
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.7827788649706457,
|
| 627 |
+
"grad_norm": 87098.984375,
|
| 628 |
+
"learning_rate": 5.708118121553318e-07,
|
| 629 |
+
"loss": 0.7801,
|
| 630 |
+
"step": 800
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7827788649706457,
|
| 634 |
+
"eval_accuracy": 0.734,
|
| 635 |
+
"eval_loss": 0.667039155960083,
|
| 636 |
+
"eval_macro_f1": 0.5514001038862917,
|
| 637 |
+
"eval_precision": 0.5710358542434345,
|
| 638 |
+
"eval_recall": 0.5490647598270917,
|
| 639 |
+
"eval_runtime": 17.0236,
|
| 640 |
+
"eval_samples_per_second": 58.742,
|
| 641 |
+
"eval_steps_per_second": 0.059,
|
| 642 |
+
"step": 800
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.7925636007827789,
|
| 646 |
+
"grad_norm": 70466.7109375,
|
| 647 |
+
"learning_rate": 5.326217234707852e-07,
|
| 648 |
+
"loss": 0.7782,
|
| 649 |
+
"step": 810
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.8023483365949119,
|
| 653 |
+
"grad_norm": 78038.6015625,
|
| 654 |
+
"learning_rate": 4.942392607344717e-07,
|
| 655 |
+
"loss": 0.786,
|
| 656 |
+
"step": 820
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.812133072407045,
|
| 660 |
+
"grad_norm": 91227.28125,
|
| 661 |
+
"learning_rate": 4.558907697395553e-07,
|
| 662 |
+
"loss": 0.7781,
|
| 663 |
+
"step": 830
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.821917808219178,
|
| 667 |
+
"grad_norm": 85470.5625,
|
| 668 |
+
"learning_rate": 4.1780239594393807e-07,
|
| 669 |
+
"loss": 0.7806,
|
| 670 |
+
"step": 840
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.8317025440313112,
|
| 674 |
+
"grad_norm": 73229.96875,
|
| 675 |
+
"learning_rate": 3.8019875086450787e-07,
|
| 676 |
+
"loss": 0.7823,
|
| 677 |
+
"step": 850
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.8317025440313112,
|
| 681 |
+
"eval_accuracy": 0.725,
|
| 682 |
+
"eval_loss": 0.668379545211792,
|
| 683 |
+
"eval_macro_f1": 0.5541786430494829,
|
| 684 |
+
"eval_precision": 0.5667714002224962,
|
| 685 |
+
"eval_recall": 0.5512665131499213,
|
| 686 |
+
"eval_runtime": 16.9299,
|
| 687 |
+
"eval_samples_per_second": 59.067,
|
| 688 |
+
"eval_steps_per_second": 0.059,
|
| 689 |
+
"step": 850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.8414872798434442,
|
| 693 |
+
"grad_norm": 84347.0546875,
|
| 694 |
+
"learning_rate": 3.4330158751721504e-07,
|
| 695 |
+
"loss": 0.7805,
|
| 696 |
+
"step": 860
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.8512720156555773,
|
| 700 |
+
"grad_norm": 60984.21875,
|
| 701 |
+
"learning_rate": 3.0732849271405547e-07,
|
| 702 |
+
"loss": 0.779,
|
| 703 |
+
"step": 870
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.8610567514677103,
|
| 707 |
+
"grad_norm": 72854.8046875,
|
| 708 |
+
"learning_rate": 2.7249160392863903e-07,
|
| 709 |
+
"loss": 0.7811,
|
| 710 |
+
"step": 880
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.8708414872798435,
|
| 714 |
+
"grad_norm": 69136.65625,
|
| 715 |
+
"learning_rate": 2.3899635829713077e-07,
|
| 716 |
+
"loss": 0.7811,
|
| 717 |
+
"step": 890
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8806262230919765,
|
| 721 |
+
"grad_norm": 74345.7421875,
|
| 722 |
+
"learning_rate": 2.0704028113185306e-07,
|
| 723 |
+
"loss": 0.7845,
|
| 724 |
+
"step": 900
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8806262230919765,
|
| 728 |
+
"eval_accuracy": 0.726,
|
| 729 |
+
"eval_loss": 0.6684988737106323,
|
| 730 |
+
"eval_macro_f1": 0.5584519389438943,
|
| 731 |
+
"eval_precision": 0.5706882639048261,
|
| 732 |
+
"eval_recall": 0.555107317439156,
|
| 733 |
+
"eval_runtime": 16.9904,
|
| 734 |
+
"eval_samples_per_second": 58.857,
|
| 735 |
+
"eval_steps_per_second": 0.059,
|
| 736 |
+
"step": 900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.8904109589041096,
|
| 740 |
+
"grad_norm": 75862.8046875,
|
| 741 |
+
"learning_rate": 1.768118210918219e-07,
|
| 742 |
+
"loss": 0.7821,
|
| 743 |
+
"step": 910
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.9001956947162426,
|
| 747 |
+
"grad_norm": 60382.25,
|
| 748 |
+
"learning_rate": 1.484892388793511e-07,
|
| 749 |
+
"loss": 0.7811,
|
| 750 |
+
"step": 920
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.9099804305283757,
|
| 754 |
+
"grad_norm": 67346.859375,
|
| 755 |
+
"learning_rate": 1.2223955601620633e-07,
|
| 756 |
+
"loss": 0.781,
|
| 757 |
+
"step": 930
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.9197651663405088,
|
| 761 |
+
"grad_norm": 81895.7265625,
|
| 762 |
+
"learning_rate": 9.821756989850016e-08,
|
| 763 |
+
"loss": 0.7816,
|
| 764 |
+
"step": 940
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.9295499021526419,
|
| 768 |
+
"grad_norm": 87715.9453125,
|
| 769 |
+
"learning_rate": 7.656494093865984e-08,
|
| 770 |
+
"loss": 0.7815,
|
| 771 |
+
"step": 950
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.9295499021526419,
|
| 775 |
+
"eval_accuracy": 0.723,
|
| 776 |
+
"eval_loss": 0.6687072515487671,
|
| 777 |
+
"eval_macro_f1": 0.5562540149399822,
|
| 778 |
+
"eval_precision": 0.5672044579297467,
|
| 779 |
+
"eval_recall": 0.553176815508654,
|
| 780 |
+
"eval_runtime": 16.997,
|
| 781 |
+
"eval_samples_per_second": 58.834,
|
| 782 |
+
"eval_steps_per_second": 0.059,
|
| 783 |
+
"step": 950
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.9393346379647749,
|
| 787 |
+
"grad_norm": 62333.75390625,
|
| 788 |
+
"learning_rate": 5.740935717769707e-08,
|
| 789 |
+
"loss": 0.775,
|
| 790 |
+
"step": 960
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.949119373776908,
|
| 794 |
+
"grad_norm": 67404.265625,
|
| 795 |
+
"learning_rate": 4.0863781294158185e-08,
|
| 796 |
+
"loss": 0.78,
|
| 797 |
+
"step": 970
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.958904109589041,
|
| 801 |
+
"grad_norm": 75798.1328125,
|
| 802 |
+
"learning_rate": 2.702578445022852e-08,
|
| 803 |
+
"loss": 0.7808,
|
| 804 |
+
"step": 980
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9686888454011742,
|
| 808 |
+
"grad_norm": 77483.9609375,
|
| 809 |
+
"learning_rate": 1.597697090337763e-08,
|
| 810 |
+
"loss": 0.7804,
|
| 811 |
+
"step": 990
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.9784735812133072,
|
| 815 |
+
"grad_norm": 82261.78125,
|
| 816 |
+
"learning_rate": 7.782496776675695e-09,
|
| 817 |
+
"loss": 0.7795,
|
| 818 |
+
"step": 1000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.9784735812133072,
|
| 822 |
+
"eval_accuracy": 0.723,
|
| 823 |
+
"eval_loss": 0.6687466502189636,
|
| 824 |
+
"eval_macro_f1": 0.5579874225879597,
|
| 825 |
+
"eval_precision": 0.5685547947184422,
|
| 826 |
+
"eval_recall": 0.5547754673315212,
|
| 827 |
+
"eval_runtime": 16.934,
|
| 828 |
+
"eval_samples_per_second": 59.053,
|
| 829 |
+
"eval_steps_per_second": 0.059,
|
| 830 |
+
"step": 1000
|
| 831 |
+
}
|
| 832 |
+
],
|
| 833 |
+
"logging_steps": 10,
|
| 834 |
+
"max_steps": 1022,
|
| 835 |
+
"num_input_tokens_seen": 0,
|
| 836 |
+
"num_train_epochs": 1,
|
| 837 |
+
"save_steps": 50,
|
| 838 |
+
"stateful_callbacks": {
|
| 839 |
+
"EarlyStoppingCallback": {
|
| 840 |
+
"args": {
|
| 841 |
+
"early_stopping_patience": 3,
|
| 842 |
+
"early_stopping_threshold": 0.0
|
| 843 |
+
},
|
| 844 |
+
"attributes": {
|
| 845 |
+
"early_stopping_patience_counter": 2
|
| 846 |
+
}
|
| 847 |
+
},
|
| 848 |
+
"TrainerControl": {
|
| 849 |
+
"args": {
|
| 850 |
+
"should_epoch_stop": false,
|
| 851 |
+
"should_evaluate": false,
|
| 852 |
+
"should_log": false,
|
| 853 |
+
"should_save": true,
|
| 854 |
+
"should_training_stop": false
|
| 855 |
+
},
|
| 856 |
+
"attributes": {}
|
| 857 |
+
}
|
| 858 |
+
},
|
| 859 |
+
"total_flos": 1.3471286034432e+17,
|
| 860 |
+
"train_batch_size": 512,
|
| 861 |
+
"trial_name": null,
|
| 862 |
+
"trial_params": null
|
| 863 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8307116b3e23cecae8ec65819b3c2e7993d8af193c50142730ae3c50bce70d6
|
| 3 |
+
size 5905
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/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-base-lowLR-highBatchSize/checkpoint-1022/config_hyperparams.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train_config": {
|
| 3 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 4 |
+
"num_epochs": 1,
|
| 5 |
+
"batch_size": 256,
|
| 6 |
+
"learning_rate": 1e-06,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"num_labels": 2,
|
| 9 |
+
"loss_type": "r-drop",
|
| 10 |
+
"focal_alpha": 1.0,
|
| 11 |
+
"focal_gamma": 2.0,
|
| 12 |
+
"r_drop_alpha": 10.0,
|
| 13 |
+
"infonce_temperature": 0.07,
|
| 14 |
+
"infonce_weight": 0.5,
|
| 15 |
+
"label_smoothing": 0.5,
|
| 16 |
+
"adversarial_epsilon": 0.5,
|
| 17 |
+
"use_swa": false,
|
| 18 |
+
"swa_start_epoch": 0,
|
| 19 |
+
"swa_lr": 1e-05,
|
| 20 |
+
"data_augmentation": true,
|
| 21 |
+
"aug_rename_prob": 0.8,
|
| 22 |
+
"aug_format_prob": 0.8,
|
| 23 |
+
"freeze_base": true,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"use_wandb": true,
|
| 26 |
+
"mixup_alpha": 1.0,
|
| 27 |
+
"low_pass_keep_ratio": 0.5,
|
| 28 |
+
"freq_consistency_weight": 0.5
|
| 29 |
+
},
|
| 30 |
+
"training_arguments": {
|
| 31 |
+
"output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
|
| 32 |
+
"num_train_epochs": 1,
|
| 33 |
+
"per_device_train_batch_size": 256,
|
| 34 |
+
"per_device_eval_batch_size": 512,
|
| 35 |
+
"learning_rate": 1e-06,
|
| 36 |
+
"warmup_steps": 204,
|
| 37 |
+
"weight_decay": 0.1,
|
| 38 |
+
"logging_steps": 10,
|
| 39 |
+
"eval_steps": 50,
|
| 40 |
+
"save_steps": 50,
|
| 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": 1022,
|
| 49 |
+
"epoch": 1.0,
|
| 50 |
+
"best_metric": 0.5584519389438943,
|
| 51 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-900"
|
| 52 |
+
}
|
| 53 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/hyperparams.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 3 |
+
"output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
|
| 4 |
+
"num_epochs": 1,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"batch_size": 256,
|
| 7 |
+
"learning_rate": 1e-06,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"num_labels": 2,
|
| 10 |
+
"use_wandb": true,
|
| 11 |
+
"freeze_base": true,
|
| 12 |
+
"loss_type": "r-drop",
|
| 13 |
+
"focal_alpha": 1.0,
|
| 14 |
+
"focal_gamma": 2.0,
|
| 15 |
+
"r_drop_alpha": 10.0,
|
| 16 |
+
"infonce_temperature": 0.07,
|
| 17 |
+
"infonce_weight": 0.5,
|
| 18 |
+
"seed": 42,
|
| 19 |
+
"resume_from_checkpoint": "checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-500",
|
| 20 |
+
"label_smoothing": 0.5,
|
| 21 |
+
"adversarial_epsilon": 0.5,
|
| 22 |
+
"use_swa": false,
|
| 23 |
+
"swa_start_epoch": 0,
|
| 24 |
+
"swa_lr": 1e-05,
|
| 25 |
+
"data_augmentation": true,
|
| 26 |
+
"aug_rename_prob": 0.8,
|
| 27 |
+
"aug_format_prob": 0.8,
|
| 28 |
+
"mixup_alpha": 1.0,
|
| 29 |
+
"low_pass_keep_ratio": 0.5,
|
| 30 |
+
"freq_consistency_weight": 0.5,
|
| 31 |
+
"hidden_dropout_prob": 0.3,
|
| 32 |
+
"attention_probs_dropout_prob": 0.3,
|
| 33 |
+
"classifier_dropout": 0.3,
|
| 34 |
+
"device": "cuda"
|
| 35 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:007997eaa459b87c8c3017ef28539ea952197e645a14c6e2fe3bb37f8d4ede5c
|
| 3 |
+
size 498612824
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14570faac475f55376f6ac26bdbbf15b3ee3a6f9abcd17d2521f8e05a2c814a0
|
| 3 |
+
size 4741859
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45e955ee2f646a917a4a15bf15b609d5a6b8a482b57701dd2c7d5f4d9d0def51
|
| 3 |
+
size 14645
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
|
| 3 |
+
size 1383
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7956fe29eeb8c96b8b73aab40a1822303157f9bb955825e841b2c375612ea5f
|
| 3 |
+
size 1465
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/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-base-lowLR-highBatchSize/checkpoint-1022/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/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-base-lowLR-highBatchSize/checkpoint-1022/trainer_state.json
ADDED
|
@@ -0,0 +1,877 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 900,
|
| 3 |
+
"best_metric": 0.5584519389438943,
|
| 4 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-900",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 1022,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009784735812133072,
|
| 14 |
+
"grad_norm": 165951.1875,
|
| 15 |
+
"learning_rate": 4.411764705882353e-08,
|
| 16 |
+
"loss": 0.8416,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.019569471624266144,
|
| 21 |
+
"grad_norm": 206132.796875,
|
| 22 |
+
"learning_rate": 9.313725490196079e-08,
|
| 23 |
+
"loss": 0.8378,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.029354207436399216,
|
| 28 |
+
"grad_norm": 171197.53125,
|
| 29 |
+
"learning_rate": 1.4215686274509803e-07,
|
| 30 |
+
"loss": 0.8388,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03913894324853229,
|
| 35 |
+
"grad_norm": 206661.828125,
|
| 36 |
+
"learning_rate": 1.9117647058823527e-07,
|
| 37 |
+
"loss": 0.847,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04892367906066536,
|
| 42 |
+
"grad_norm": 230268.96875,
|
| 43 |
+
"learning_rate": 2.4019607843137255e-07,
|
| 44 |
+
"loss": 0.8411,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05870841487279843,
|
| 49 |
+
"grad_norm": 133248.28125,
|
| 50 |
+
"learning_rate": 2.8921568627450984e-07,
|
| 51 |
+
"loss": 0.8412,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0684931506849315,
|
| 56 |
+
"grad_norm": 147768.828125,
|
| 57 |
+
"learning_rate": 3.3823529411764707e-07,
|
| 58 |
+
"loss": 0.8431,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07827788649706457,
|
| 63 |
+
"grad_norm": 167327.53125,
|
| 64 |
+
"learning_rate": 3.872549019607843e-07,
|
| 65 |
+
"loss": 0.8431,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08806262230919765,
|
| 70 |
+
"grad_norm": 151943.75,
|
| 71 |
+
"learning_rate": 4.3627450980392154e-07,
|
| 72 |
+
"loss": 0.8311,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09784735812133072,
|
| 77 |
+
"grad_norm": 149971.59375,
|
| 78 |
+
"learning_rate": 4.852941176470588e-07,
|
| 79 |
+
"loss": 0.8412,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10763209393346379,
|
| 84 |
+
"grad_norm": 162329.40625,
|
| 85 |
+
"learning_rate": 5.34313725490196e-07,
|
| 86 |
+
"loss": 0.8356,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.11741682974559686,
|
| 91 |
+
"grad_norm": 158769.765625,
|
| 92 |
+
"learning_rate": 5.833333333333334e-07,
|
| 93 |
+
"loss": 0.8351,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12720156555772993,
|
| 98 |
+
"grad_norm": 157725.59375,
|
| 99 |
+
"learning_rate": 6.323529411764706e-07,
|
| 100 |
+
"loss": 0.8331,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.136986301369863,
|
| 105 |
+
"grad_norm": 205733.0,
|
| 106 |
+
"learning_rate": 6.813725490196079e-07,
|
| 107 |
+
"loss": 0.8366,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.14677103718199608,
|
| 112 |
+
"grad_norm": 172581.328125,
|
| 113 |
+
"learning_rate": 7.30392156862745e-07,
|
| 114 |
+
"loss": 0.831,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15655577299412915,
|
| 119 |
+
"grad_norm": 137428.0,
|
| 120 |
+
"learning_rate": 7.794117647058823e-07,
|
| 121 |
+
"loss": 0.8326,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16634050880626222,
|
| 126 |
+
"grad_norm": 151189.203125,
|
| 127 |
+
"learning_rate": 8.284313725490196e-07,
|
| 128 |
+
"loss": 0.8281,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1761252446183953,
|
| 133 |
+
"grad_norm": 145620.625,
|
| 134 |
+
"learning_rate": 8.774509803921568e-07,
|
| 135 |
+
"loss": 0.8252,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.18590998043052837,
|
| 140 |
+
"grad_norm": 169938.84375,
|
| 141 |
+
"learning_rate": 9.264705882352941e-07,
|
| 142 |
+
"loss": 0.8308,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.19569471624266144,
|
| 147 |
+
"grad_norm": 138760.015625,
|
| 148 |
+
"learning_rate": 9.754901960784313e-07,
|
| 149 |
+
"loss": 0.824,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2054794520547945,
|
| 154 |
+
"grad_norm": 107872.125,
|
| 155 |
+
"learning_rate": 9.99631294374483e-07,
|
| 156 |
+
"loss": 0.8254,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.21526418786692758,
|
| 161 |
+
"grad_norm": 113610.8359375,
|
| 162 |
+
"learning_rate": 9.966849112204936e-07,
|
| 163 |
+
"loss": 0.8267,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.22504892367906065,
|
| 168 |
+
"grad_norm": 172441.515625,
|
| 169 |
+
"learning_rate": 9.908095200725339e-07,
|
| 170 |
+
"loss": 0.8198,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.23483365949119372,
|
| 175 |
+
"grad_norm": 128079.9140625,
|
| 176 |
+
"learning_rate": 9.82039768787326e-07,
|
| 177 |
+
"loss": 0.8143,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2446183953033268,
|
| 182 |
+
"grad_norm": 98149.8984375,
|
| 183 |
+
"learning_rate": 9.70427373595903e-07,
|
| 184 |
+
"loss": 0.8191,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.25440313111545987,
|
| 189 |
+
"grad_norm": 147377.4375,
|
| 190 |
+
"learning_rate": 9.560408141270531e-07,
|
| 191 |
+
"loss": 0.8178,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.26418786692759294,
|
| 196 |
+
"grad_norm": 156439.40625,
|
| 197 |
+
"learning_rate": 9.389649295750781e-07,
|
| 198 |
+
"loss": 0.8085,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.273972602739726,
|
| 203 |
+
"grad_norm": 131892.015625,
|
| 204 |
+
"learning_rate": 9.193004183933174e-07,
|
| 205 |
+
"loss": 0.8172,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2837573385518591,
|
| 210 |
+
"grad_norm": 132474.5,
|
| 211 |
+
"learning_rate": 8.971632444637971e-07,
|
| 212 |
+
"loss": 0.8136,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.29354207436399216,
|
| 217 |
+
"grad_norm": 112619.109375,
|
| 218 |
+
"learning_rate": 8.726839532448928e-07,
|
| 219 |
+
"loss": 0.8065,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.30332681017612523,
|
| 224 |
+
"grad_norm": 94225.5703125,
|
| 225 |
+
"learning_rate": 8.460069019297606e-07,
|
| 226 |
+
"loss": 0.813,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3131115459882583,
|
| 231 |
+
"grad_norm": 117812.8203125,
|
| 232 |
+
"learning_rate": 8.172894081553822e-07,
|
| 233 |
+
"loss": 0.8022,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.32289628180039137,
|
| 238 |
+
"grad_norm": 143287.125,
|
| 239 |
+
"learning_rate": 7.86700822282382e-07,
|
| 240 |
+
"loss": 0.8061,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.33268101761252444,
|
| 245 |
+
"grad_norm": 107456.25,
|
| 246 |
+
"learning_rate": 7.544215287164917e-07,
|
| 247 |
+
"loss": 0.8006,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3424657534246575,
|
| 252 |
+
"grad_norm": 101521.171875,
|
| 253 |
+
"learning_rate": 7.206418821609812e-07,
|
| 254 |
+
"loss": 0.8055,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3522504892367906,
|
| 259 |
+
"grad_norm": 118311.5234375,
|
| 260 |
+
"learning_rate": 6.855610850731017e-07,
|
| 261 |
+
"loss": 0.8081,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.36203522504892366,
|
| 266 |
+
"grad_norm": 89621.828125,
|
| 267 |
+
"learning_rate": 6.493860129443046e-07,
|
| 268 |
+
"loss": 0.8058,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.37181996086105673,
|
| 273 |
+
"grad_norm": 143168.65625,
|
| 274 |
+
"learning_rate": 6.123299943316975e-07,
|
| 275 |
+
"loss": 0.8028,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3816046966731898,
|
| 280 |
+
"grad_norm": 118598.2890625,
|
| 281 |
+
"learning_rate": 5.746115528350295e-07,
|
| 282 |
+
"loss": 0.8032,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3913894324853229,
|
| 287 |
+
"grad_norm": 111807.8203125,
|
| 288 |
+
"learning_rate": 5.364531184379139e-07,
|
| 289 |
+
"loss": 0.8014,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.40117416829745595,
|
| 294 |
+
"grad_norm": 124106.1328125,
|
| 295 |
+
"learning_rate": 4.980797158126566e-07,
|
| 296 |
+
"loss": 0.8045,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.410958904109589,
|
| 301 |
+
"grad_norm": 102746.4765625,
|
| 302 |
+
"learning_rate": 4.597176373239061e-07,
|
| 303 |
+
"loss": 0.7996,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4207436399217221,
|
| 308 |
+
"grad_norm": 108317.5859375,
|
| 309 |
+
"learning_rate": 4.215931085565761e-07,
|
| 310 |
+
"loss": 0.8037,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.43052837573385516,
|
| 315 |
+
"grad_norm": 113342.515625,
|
| 316 |
+
"learning_rate": 3.8393095423757764e-07,
|
| 317 |
+
"loss": 0.8047,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.44031311154598823,
|
| 322 |
+
"grad_norm": 111908.90625,
|
| 323 |
+
"learning_rate": 3.469532724185699e-07,
|
| 324 |
+
"loss": 0.8021,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4500978473581213,
|
| 329 |
+
"grad_norm": 85004.15625,
|
| 330 |
+
"learning_rate": 3.1087812473822845e-07,
|
| 331 |
+
"loss": 0.8012,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4598825831702544,
|
| 336 |
+
"grad_norm": 98335.1796875,
|
| 337 |
+
"learning_rate": 2.7591825048770643e-07,
|
| 338 |
+
"loss": 0.7977,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.46966731898238745,
|
| 343 |
+
"grad_norm": 110674.03125,
|
| 344 |
+
"learning_rate": 2.422798120625886e-07,
|
| 345 |
+
"loss": 0.7979,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4794520547945205,
|
| 350 |
+
"grad_norm": 114861.5390625,
|
| 351 |
+
"learning_rate": 2.1016117919955512e-07,
|
| 352 |
+
"loss": 0.8014,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4892367906066536,
|
| 357 |
+
"grad_norm": 130109.5703125,
|
| 358 |
+
"learning_rate": 1.7975175916725031e-07,
|
| 359 |
+
"loss": 0.7994,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.49902152641878667,
|
| 364 |
+
"grad_norm": 93286.4296875,
|
| 365 |
+
"learning_rate": 1.5123087980985606e-07,
|
| 366 |
+
"loss": 0.8039,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5088062622309197,
|
| 371 |
+
"grad_norm": 123646.703125,
|
| 372 |
+
"learning_rate": 1.2476673203018728e-07,
|
| 373 |
+
"loss": 0.7917,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5185909980430529,
|
| 378 |
+
"grad_norm": 98060.2265625,
|
| 379 |
+
"learning_rate": 1.0051537794861287e-07,
|
| 380 |
+
"loss": 0.7945,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5283757338551859,
|
| 385 |
+
"grad_norm": 91181.1796875,
|
| 386 |
+
"learning_rate": 7.861983058679871e-08,
|
| 387 |
+
"loss": 0.7952,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.538160469667319,
|
| 392 |
+
"grad_norm": 97605.3984375,
|
| 393 |
+
"learning_rate": 5.920921050348626e-08,
|
| 394 |
+
"loss": 0.7963,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.538160469667319,
|
| 399 |
+
"eval_accuracy": 0.767,
|
| 400 |
+
"eval_loss": 0.662277102470398,
|
| 401 |
+
"eval_macro_f1": 0.5341406895117674,
|
| 402 |
+
"eval_precision": 0.6105222734254993,
|
| 403 |
+
"eval_recall": 0.5415245482510056,
|
| 404 |
+
"eval_runtime": 16.9722,
|
| 405 |
+
"eval_samples_per_second": 58.92,
|
| 406 |
+
"eval_steps_per_second": 0.059,
|
| 407 |
+
"step": 550
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.547945205479452,
|
| 411 |
+
"grad_norm": 101627.8046875,
|
| 412 |
+
"learning_rate": 4.23979843557199e-08,
|
| 413 |
+
"loss": 0.7962,
|
| 414 |
+
"step": 560
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.5577299412915852,
|
| 418 |
+
"grad_norm": 73889.578125,
|
| 419 |
+
"learning_rate": 2.8285289875818407e-08,
|
| 420 |
+
"loss": 0.794,
|
| 421 |
+
"step": 570
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.5675146771037182,
|
| 425 |
+
"grad_norm": 87191.0546875,
|
| 426 |
+
"learning_rate": 1.695435124477512e-08,
|
| 427 |
+
"loss": 0.7984,
|
| 428 |
+
"step": 580
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.5772994129158513,
|
| 432 |
+
"grad_norm": 105470.234375,
|
| 433 |
+
"learning_rate": 8.471988309699807e-09,
|
| 434 |
+
"loss": 0.7924,
|
| 435 |
+
"step": 590
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.5870841487279843,
|
| 439 |
+
"grad_norm": 81710.7265625,
|
| 440 |
+
"learning_rate": 2.8882225395023275e-09,
|
| 441 |
+
"loss": 0.8005,
|
| 442 |
+
"step": 600
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.5870841487279843,
|
| 446 |
+
"eval_accuracy": 0.767,
|
| 447 |
+
"eval_loss": 0.6623347401618958,
|
| 448 |
+
"eval_macro_f1": 0.5341406895117674,
|
| 449 |
+
"eval_precision": 0.6105222734254993,
|
| 450 |
+
"eval_recall": 0.5415245482510056,
|
| 451 |
+
"eval_runtime": 17.0174,
|
| 452 |
+
"eval_samples_per_second": 58.763,
|
| 453 |
+
"eval_steps_per_second": 0.059,
|
| 454 |
+
"step": 600
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.5968688845401174,
|
| 458 |
+
"grad_norm": 97212.125,
|
| 459 |
+
"learning_rate": 2.35982042542604e-10,
|
| 460 |
+
"loss": 0.7981,
|
| 461 |
+
"step": 610
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.6066536203522505,
|
| 465 |
+
"grad_norm": 100700.640625,
|
| 466 |
+
"learning_rate": 9.994690926142082e-07,
|
| 467 |
+
"loss": 0.8006,
|
| 468 |
+
"step": 620
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.6164383561643836,
|
| 472 |
+
"grad_norm": 88023.046875,
|
| 473 |
+
"learning_rate": 9.962287406393883e-07,
|
| 474 |
+
"loss": 0.7976,
|
| 475 |
+
"step": 630
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.6262230919765166,
|
| 479 |
+
"grad_norm": 118936.609375,
|
| 480 |
+
"learning_rate": 9.900620707609317e-07,
|
| 481 |
+
"loss": 0.7961,
|
| 482 |
+
"step": 640
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.6360078277886497,
|
| 486 |
+
"grad_norm": 91811.3984375,
|
| 487 |
+
"learning_rate": 9.810054485397043e-07,
|
| 488 |
+
"loss": 0.7904,
|
| 489 |
+
"step": 650
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.6360078277886497,
|
| 493 |
+
"eval_accuracy": 0.757,
|
| 494 |
+
"eval_loss": 0.6629467606544495,
|
| 495 |
+
"eval_macro_f1": 0.5299579283330915,
|
| 496 |
+
"eval_precision": 0.5844492268452096,
|
| 497 |
+
"eval_recall": 0.5366881936388663,
|
| 498 |
+
"eval_runtime": 17.0504,
|
| 499 |
+
"eval_samples_per_second": 58.65,
|
| 500 |
+
"eval_steps_per_second": 0.059,
|
| 501 |
+
"step": 650
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.6457925636007827,
|
| 505 |
+
"grad_norm": 118632.46875,
|
| 506 |
+
"learning_rate": 9.69112281917613e-07,
|
| 507 |
+
"loss": 0.7927,
|
| 508 |
+
"step": 660
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.6555772994129159,
|
| 512 |
+
"grad_norm": 70413.0390625,
|
| 513 |
+
"learning_rate": 9.544527062648345e-07,
|
| 514 |
+
"loss": 0.785,
|
| 515 |
+
"step": 670
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.6653620352250489,
|
| 519 |
+
"grad_norm": 84746.4453125,
|
| 520 |
+
"learning_rate": 9.371131707834789e-07,
|
| 521 |
+
"loss": 0.7861,
|
| 522 |
+
"step": 680
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.675146771037182,
|
| 526 |
+
"grad_norm": 92019.0390625,
|
| 527 |
+
"learning_rate": 9.171959287067115e-07,
|
| 528 |
+
"loss": 0.7892,
|
| 529 |
+
"step": 690
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.684931506849315,
|
| 533 |
+
"grad_norm": 70649.2578125,
|
| 534 |
+
"learning_rate": 8.948184342996868e-07,
|
| 535 |
+
"loss": 0.789,
|
| 536 |
+
"step": 700
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.684931506849315,
|
| 540 |
+
"eval_accuracy": 0.751,
|
| 541 |
+
"eval_loss": 0.6648359894752502,
|
| 542 |
+
"eval_macro_f1": 0.5514410631387237,
|
| 543 |
+
"eval_precision": 0.589223697650664,
|
| 544 |
+
"eval_recall": 0.5504123598294002,
|
| 545 |
+
"eval_runtime": 17.0124,
|
| 546 |
+
"eval_samples_per_second": 58.781,
|
| 547 |
+
"eval_steps_per_second": 0.059,
|
| 548 |
+
"step": 700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.6947162426614482,
|
| 552 |
+
"grad_norm": 80338.796875,
|
| 553 |
+
"learning_rate": 8.701126502182503e-07,
|
| 554 |
+
"loss": 0.7907,
|
| 555 |
+
"step": 710
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7045009784735812,
|
| 559 |
+
"grad_norm": 69257.328125,
|
| 560 |
+
"learning_rate": 8.432242693099946e-07,
|
| 561 |
+
"loss": 0.7881,
|
| 562 |
+
"step": 720
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7142857142857143,
|
| 566 |
+
"grad_norm": 95345.15625,
|
| 567 |
+
"learning_rate": 8.14311855446795e-07,
|
| 568 |
+
"loss": 0.7849,
|
| 569 |
+
"step": 730
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7240704500978473,
|
| 573 |
+
"grad_norm": 94407.8984375,
|
| 574 |
+
"learning_rate": 7.835459084554374e-07,
|
| 575 |
+
"loss": 0.7868,
|
| 576 |
+
"step": 740
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7338551859099804,
|
| 580 |
+
"grad_norm": 74418.0625,
|
| 581 |
+
"learning_rate": 7.511078586605484e-07,
|
| 582 |
+
"loss": 0.783,
|
| 583 |
+
"step": 750
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7338551859099804,
|
| 587 |
+
"eval_accuracy": 0.742,
|
| 588 |
+
"eval_loss": 0.6660248637199402,
|
| 589 |
+
"eval_macro_f1": 0.5532467532467532,
|
| 590 |
+
"eval_precision": 0.579727791757989,
|
| 591 |
+
"eval_recall": 0.5510154613293626,
|
| 592 |
+
"eval_runtime": 16.9303,
|
| 593 |
+
"eval_samples_per_second": 59.066,
|
| 594 |
+
"eval_steps_per_second": 0.059,
|
| 595 |
+
"step": 750
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.7436399217221135,
|
| 599 |
+
"grad_norm": 95142.0546875,
|
| 600 |
+
"learning_rate": 7.171889969691225e-07,
|
| 601 |
+
"loss": 0.7861,
|
| 602 |
+
"step": 760
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.7534246575342466,
|
| 606 |
+
"grad_norm": 118907.203125,
|
| 607 |
+
"learning_rate": 6.819893468060643e-07,
|
| 608 |
+
"loss": 0.7878,
|
| 609 |
+
"step": 770
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.7632093933463796,
|
| 613 |
+
"grad_norm": 66268.78125,
|
| 614 |
+
"learning_rate": 6.457164845530662e-07,
|
| 615 |
+
"loss": 0.7859,
|
| 616 |
+
"step": 780
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.7729941291585127,
|
| 620 |
+
"grad_norm": 81464.265625,
|
| 621 |
+
"learning_rate": 6.085843154468354e-07,
|
| 622 |
+
"loss": 0.7819,
|
| 623 |
+
"step": 790
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.7827788649706457,
|
| 627 |
+
"grad_norm": 87098.984375,
|
| 628 |
+
"learning_rate": 5.708118121553318e-07,
|
| 629 |
+
"loss": 0.7801,
|
| 630 |
+
"step": 800
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7827788649706457,
|
| 634 |
+
"eval_accuracy": 0.734,
|
| 635 |
+
"eval_loss": 0.667039155960083,
|
| 636 |
+
"eval_macro_f1": 0.5514001038862917,
|
| 637 |
+
"eval_precision": 0.5710358542434345,
|
| 638 |
+
"eval_recall": 0.5490647598270917,
|
| 639 |
+
"eval_runtime": 17.0236,
|
| 640 |
+
"eval_samples_per_second": 58.742,
|
| 641 |
+
"eval_steps_per_second": 0.059,
|
| 642 |
+
"step": 800
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.7925636007827789,
|
| 646 |
+
"grad_norm": 70466.7109375,
|
| 647 |
+
"learning_rate": 5.326217234707852e-07,
|
| 648 |
+
"loss": 0.7782,
|
| 649 |
+
"step": 810
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.8023483365949119,
|
| 653 |
+
"grad_norm": 78038.6015625,
|
| 654 |
+
"learning_rate": 4.942392607344717e-07,
|
| 655 |
+
"loss": 0.786,
|
| 656 |
+
"step": 820
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.812133072407045,
|
| 660 |
+
"grad_norm": 91227.28125,
|
| 661 |
+
"learning_rate": 4.558907697395553e-07,
|
| 662 |
+
"loss": 0.7781,
|
| 663 |
+
"step": 830
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.821917808219178,
|
| 667 |
+
"grad_norm": 85470.5625,
|
| 668 |
+
"learning_rate": 4.1780239594393807e-07,
|
| 669 |
+
"loss": 0.7806,
|
| 670 |
+
"step": 840
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.8317025440313112,
|
| 674 |
+
"grad_norm": 73229.96875,
|
| 675 |
+
"learning_rate": 3.8019875086450787e-07,
|
| 676 |
+
"loss": 0.7823,
|
| 677 |
+
"step": 850
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.8317025440313112,
|
| 681 |
+
"eval_accuracy": 0.725,
|
| 682 |
+
"eval_loss": 0.668379545211792,
|
| 683 |
+
"eval_macro_f1": 0.5541786430494829,
|
| 684 |
+
"eval_precision": 0.5667714002224962,
|
| 685 |
+
"eval_recall": 0.5512665131499213,
|
| 686 |
+
"eval_runtime": 16.9299,
|
| 687 |
+
"eval_samples_per_second": 59.067,
|
| 688 |
+
"eval_steps_per_second": 0.059,
|
| 689 |
+
"step": 850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.8414872798434442,
|
| 693 |
+
"grad_norm": 84347.0546875,
|
| 694 |
+
"learning_rate": 3.4330158751721504e-07,
|
| 695 |
+
"loss": 0.7805,
|
| 696 |
+
"step": 860
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.8512720156555773,
|
| 700 |
+
"grad_norm": 60984.21875,
|
| 701 |
+
"learning_rate": 3.0732849271405547e-07,
|
| 702 |
+
"loss": 0.779,
|
| 703 |
+
"step": 870
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.8610567514677103,
|
| 707 |
+
"grad_norm": 72854.8046875,
|
| 708 |
+
"learning_rate": 2.7249160392863903e-07,
|
| 709 |
+
"loss": 0.7811,
|
| 710 |
+
"step": 880
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.8708414872798435,
|
| 714 |
+
"grad_norm": 69136.65625,
|
| 715 |
+
"learning_rate": 2.3899635829713077e-07,
|
| 716 |
+
"loss": 0.7811,
|
| 717 |
+
"step": 890
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8806262230919765,
|
| 721 |
+
"grad_norm": 74345.7421875,
|
| 722 |
+
"learning_rate": 2.0704028113185306e-07,
|
| 723 |
+
"loss": 0.7845,
|
| 724 |
+
"step": 900
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8806262230919765,
|
| 728 |
+
"eval_accuracy": 0.726,
|
| 729 |
+
"eval_loss": 0.6684988737106323,
|
| 730 |
+
"eval_macro_f1": 0.5584519389438943,
|
| 731 |
+
"eval_precision": 0.5706882639048261,
|
| 732 |
+
"eval_recall": 0.555107317439156,
|
| 733 |
+
"eval_runtime": 16.9904,
|
| 734 |
+
"eval_samples_per_second": 58.857,
|
| 735 |
+
"eval_steps_per_second": 0.059,
|
| 736 |
+
"step": 900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.8904109589041096,
|
| 740 |
+
"grad_norm": 75862.8046875,
|
| 741 |
+
"learning_rate": 1.768118210918219e-07,
|
| 742 |
+
"loss": 0.7821,
|
| 743 |
+
"step": 910
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.9001956947162426,
|
| 747 |
+
"grad_norm": 60382.25,
|
| 748 |
+
"learning_rate": 1.484892388793511e-07,
|
| 749 |
+
"loss": 0.7811,
|
| 750 |
+
"step": 920
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.9099804305283757,
|
| 754 |
+
"grad_norm": 67346.859375,
|
| 755 |
+
"learning_rate": 1.2223955601620633e-07,
|
| 756 |
+
"loss": 0.781,
|
| 757 |
+
"step": 930
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.9197651663405088,
|
| 761 |
+
"grad_norm": 81895.7265625,
|
| 762 |
+
"learning_rate": 9.821756989850016e-08,
|
| 763 |
+
"loss": 0.7816,
|
| 764 |
+
"step": 940
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.9295499021526419,
|
| 768 |
+
"grad_norm": 87715.9453125,
|
| 769 |
+
"learning_rate": 7.656494093865984e-08,
|
| 770 |
+
"loss": 0.7815,
|
| 771 |
+
"step": 950
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.9295499021526419,
|
| 775 |
+
"eval_accuracy": 0.723,
|
| 776 |
+
"eval_loss": 0.6687072515487671,
|
| 777 |
+
"eval_macro_f1": 0.5562540149399822,
|
| 778 |
+
"eval_precision": 0.5672044579297467,
|
| 779 |
+
"eval_recall": 0.553176815508654,
|
| 780 |
+
"eval_runtime": 16.997,
|
| 781 |
+
"eval_samples_per_second": 58.834,
|
| 782 |
+
"eval_steps_per_second": 0.059,
|
| 783 |
+
"step": 950
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.9393346379647749,
|
| 787 |
+
"grad_norm": 62333.75390625,
|
| 788 |
+
"learning_rate": 5.740935717769707e-08,
|
| 789 |
+
"loss": 0.775,
|
| 790 |
+
"step": 960
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.949119373776908,
|
| 794 |
+
"grad_norm": 67404.265625,
|
| 795 |
+
"learning_rate": 4.0863781294158185e-08,
|
| 796 |
+
"loss": 0.78,
|
| 797 |
+
"step": 970
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.958904109589041,
|
| 801 |
+
"grad_norm": 75798.1328125,
|
| 802 |
+
"learning_rate": 2.702578445022852e-08,
|
| 803 |
+
"loss": 0.7808,
|
| 804 |
+
"step": 980
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9686888454011742,
|
| 808 |
+
"grad_norm": 77483.9609375,
|
| 809 |
+
"learning_rate": 1.597697090337763e-08,
|
| 810 |
+
"loss": 0.7804,
|
| 811 |
+
"step": 990
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.9784735812133072,
|
| 815 |
+
"grad_norm": 82261.78125,
|
| 816 |
+
"learning_rate": 7.782496776675695e-09,
|
| 817 |
+
"loss": 0.7795,
|
| 818 |
+
"step": 1000
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.9784735812133072,
|
| 822 |
+
"eval_accuracy": 0.723,
|
| 823 |
+
"eval_loss": 0.6687466502189636,
|
| 824 |
+
"eval_macro_f1": 0.5579874225879597,
|
| 825 |
+
"eval_precision": 0.5685547947184422,
|
| 826 |
+
"eval_recall": 0.5547754673315212,
|
| 827 |
+
"eval_runtime": 16.934,
|
| 828 |
+
"eval_samples_per_second": 59.053,
|
| 829 |
+
"eval_steps_per_second": 0.059,
|
| 830 |
+
"step": 1000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.9882583170254403,
|
| 834 |
+
"grad_norm": 68659.8671875,
|
| 835 |
+
"learning_rate": 2.4906858256491524e-09,
|
| 836 |
+
"loss": 0.78,
|
| 837 |
+
"step": 1010
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.9980430528375733,
|
| 841 |
+
"grad_norm": 92298.78125,
|
| 842 |
+
"learning_rate": 1.3274446754157898e-10,
|
| 843 |
+
"loss": 0.7824,
|
| 844 |
+
"step": 1020
|
| 845 |
+
}
|
| 846 |
+
],
|
| 847 |
+
"logging_steps": 10,
|
| 848 |
+
"max_steps": 1022,
|
| 849 |
+
"num_input_tokens_seen": 0,
|
| 850 |
+
"num_train_epochs": 1,
|
| 851 |
+
"save_steps": 50,
|
| 852 |
+
"stateful_callbacks": {
|
| 853 |
+
"EarlyStoppingCallback": {
|
| 854 |
+
"args": {
|
| 855 |
+
"early_stopping_patience": 3,
|
| 856 |
+
"early_stopping_threshold": 0.0
|
| 857 |
+
},
|
| 858 |
+
"attributes": {
|
| 859 |
+
"early_stopping_patience_counter": 2
|
| 860 |
+
}
|
| 861 |
+
},
|
| 862 |
+
"TrainerControl": {
|
| 863 |
+
"args": {
|
| 864 |
+
"should_epoch_stop": false,
|
| 865 |
+
"should_evaluate": false,
|
| 866 |
+
"should_log": false,
|
| 867 |
+
"should_save": true,
|
| 868 |
+
"should_training_stop": true
|
| 869 |
+
},
|
| 870 |
+
"attributes": {}
|
| 871 |
+
}
|
| 872 |
+
},
|
| 873 |
+
"total_flos": 1.37620237506048e+17,
|
| 874 |
+
"train_batch_size": 512,
|
| 875 |
+
"trial_name": null,
|
| 876 |
+
"trial_params": null
|
| 877 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8307116b3e23cecae8ec65819b3c2e7993d8af193c50142730ae3c50bce70d6
|
| 3 |
+
size 5905
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-1022/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/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-base-lowLR-highBatchSize/checkpoint-850/config_hyperparams.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train_config": {
|
| 3 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 4 |
+
"num_epochs": 1,
|
| 5 |
+
"batch_size": 256,
|
| 6 |
+
"learning_rate": 1e-06,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"num_labels": 2,
|
| 9 |
+
"loss_type": "r-drop",
|
| 10 |
+
"focal_alpha": 1.0,
|
| 11 |
+
"focal_gamma": 2.0,
|
| 12 |
+
"r_drop_alpha": 10.0,
|
| 13 |
+
"infonce_temperature": 0.07,
|
| 14 |
+
"infonce_weight": 0.5,
|
| 15 |
+
"label_smoothing": 0.5,
|
| 16 |
+
"adversarial_epsilon": 0.5,
|
| 17 |
+
"use_swa": false,
|
| 18 |
+
"swa_start_epoch": 0,
|
| 19 |
+
"swa_lr": 1e-05,
|
| 20 |
+
"data_augmentation": true,
|
| 21 |
+
"aug_rename_prob": 0.8,
|
| 22 |
+
"aug_format_prob": 0.8,
|
| 23 |
+
"freeze_base": true,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"use_wandb": true,
|
| 26 |
+
"mixup_alpha": 1.0,
|
| 27 |
+
"low_pass_keep_ratio": 0.5,
|
| 28 |
+
"freq_consistency_weight": 0.5
|
| 29 |
+
},
|
| 30 |
+
"training_arguments": {
|
| 31 |
+
"output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
|
| 32 |
+
"num_train_epochs": 1,
|
| 33 |
+
"per_device_train_batch_size": 256,
|
| 34 |
+
"per_device_eval_batch_size": 512,
|
| 35 |
+
"learning_rate": 1e-06,
|
| 36 |
+
"warmup_steps": 204,
|
| 37 |
+
"weight_decay": 0.1,
|
| 38 |
+
"logging_steps": 10,
|
| 39 |
+
"eval_steps": 50,
|
| 40 |
+
"save_steps": 50,
|
| 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": 850,
|
| 49 |
+
"epoch": 0.8317025440313112,
|
| 50 |
+
"best_metric": 0.5541786430494829,
|
| 51 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-850"
|
| 52 |
+
}
|
| 53 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/hyperparams.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 3 |
+
"output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
|
| 4 |
+
"num_epochs": 1,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"batch_size": 256,
|
| 7 |
+
"learning_rate": 1e-06,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"num_labels": 2,
|
| 10 |
+
"use_wandb": true,
|
| 11 |
+
"freeze_base": true,
|
| 12 |
+
"loss_type": "r-drop",
|
| 13 |
+
"focal_alpha": 1.0,
|
| 14 |
+
"focal_gamma": 2.0,
|
| 15 |
+
"r_drop_alpha": 10.0,
|
| 16 |
+
"infonce_temperature": 0.07,
|
| 17 |
+
"infonce_weight": 0.5,
|
| 18 |
+
"seed": 42,
|
| 19 |
+
"resume_from_checkpoint": "checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-500",
|
| 20 |
+
"label_smoothing": 0.5,
|
| 21 |
+
"adversarial_epsilon": 0.5,
|
| 22 |
+
"use_swa": false,
|
| 23 |
+
"swa_start_epoch": 0,
|
| 24 |
+
"swa_lr": 1e-05,
|
| 25 |
+
"data_augmentation": true,
|
| 26 |
+
"aug_rename_prob": 0.8,
|
| 27 |
+
"aug_format_prob": 0.8,
|
| 28 |
+
"mixup_alpha": 1.0,
|
| 29 |
+
"low_pass_keep_ratio": 0.5,
|
| 30 |
+
"freq_consistency_weight": 0.5,
|
| 31 |
+
"hidden_dropout_prob": 0.3,
|
| 32 |
+
"attention_probs_dropout_prob": 0.3,
|
| 33 |
+
"classifier_dropout": 0.3,
|
| 34 |
+
"device": "cuda"
|
| 35 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23fc0a49f14d9c3ac275c51cb0281f89df63a96f1370307127916a3c1975b161
|
| 3 |
+
size 498612824
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7f1c9b52df0b678bf75a4d7b875905960def809f53de2d9da13098a62b5482d
|
| 3 |
+
size 4741859
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89f0f406618b5197fae4c6d900acbd98b2b79bf347c744c857d3d77432494a61
|
| 3 |
+
size 14645
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b21c5349d5e7d02de630ebc1cb53ade1d9c6079eeb8594d223bb786011a0428b
|
| 3 |
+
size 1383
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3d9e58740bbb7712ef6b1d4dee40c5511fac2847366fd6784a1b91ec00f9680
|
| 3 |
+
size 1465
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/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-base-lowLR-highBatchSize/checkpoint-850/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/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-base-lowLR-highBatchSize/checkpoint-850/trainer_state.json
ADDED
|
@@ -0,0 +1,722 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 850,
|
| 3 |
+
"best_metric": 0.5541786430494829,
|
| 4 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-850",
|
| 5 |
+
"epoch": 0.8317025440313112,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 850,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009784735812133072,
|
| 14 |
+
"grad_norm": 165951.1875,
|
| 15 |
+
"learning_rate": 4.411764705882353e-08,
|
| 16 |
+
"loss": 0.8416,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.019569471624266144,
|
| 21 |
+
"grad_norm": 206132.796875,
|
| 22 |
+
"learning_rate": 9.313725490196079e-08,
|
| 23 |
+
"loss": 0.8378,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.029354207436399216,
|
| 28 |
+
"grad_norm": 171197.53125,
|
| 29 |
+
"learning_rate": 1.4215686274509803e-07,
|
| 30 |
+
"loss": 0.8388,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03913894324853229,
|
| 35 |
+
"grad_norm": 206661.828125,
|
| 36 |
+
"learning_rate": 1.9117647058823527e-07,
|
| 37 |
+
"loss": 0.847,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04892367906066536,
|
| 42 |
+
"grad_norm": 230268.96875,
|
| 43 |
+
"learning_rate": 2.4019607843137255e-07,
|
| 44 |
+
"loss": 0.8411,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05870841487279843,
|
| 49 |
+
"grad_norm": 133248.28125,
|
| 50 |
+
"learning_rate": 2.8921568627450984e-07,
|
| 51 |
+
"loss": 0.8412,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0684931506849315,
|
| 56 |
+
"grad_norm": 147768.828125,
|
| 57 |
+
"learning_rate": 3.3823529411764707e-07,
|
| 58 |
+
"loss": 0.8431,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07827788649706457,
|
| 63 |
+
"grad_norm": 167327.53125,
|
| 64 |
+
"learning_rate": 3.872549019607843e-07,
|
| 65 |
+
"loss": 0.8431,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08806262230919765,
|
| 70 |
+
"grad_norm": 151943.75,
|
| 71 |
+
"learning_rate": 4.3627450980392154e-07,
|
| 72 |
+
"loss": 0.8311,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09784735812133072,
|
| 77 |
+
"grad_norm": 149971.59375,
|
| 78 |
+
"learning_rate": 4.852941176470588e-07,
|
| 79 |
+
"loss": 0.8412,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10763209393346379,
|
| 84 |
+
"grad_norm": 162329.40625,
|
| 85 |
+
"learning_rate": 5.34313725490196e-07,
|
| 86 |
+
"loss": 0.8356,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.11741682974559686,
|
| 91 |
+
"grad_norm": 158769.765625,
|
| 92 |
+
"learning_rate": 5.833333333333334e-07,
|
| 93 |
+
"loss": 0.8351,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12720156555772993,
|
| 98 |
+
"grad_norm": 157725.59375,
|
| 99 |
+
"learning_rate": 6.323529411764706e-07,
|
| 100 |
+
"loss": 0.8331,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.136986301369863,
|
| 105 |
+
"grad_norm": 205733.0,
|
| 106 |
+
"learning_rate": 6.813725490196079e-07,
|
| 107 |
+
"loss": 0.8366,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.14677103718199608,
|
| 112 |
+
"grad_norm": 172581.328125,
|
| 113 |
+
"learning_rate": 7.30392156862745e-07,
|
| 114 |
+
"loss": 0.831,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15655577299412915,
|
| 119 |
+
"grad_norm": 137428.0,
|
| 120 |
+
"learning_rate": 7.794117647058823e-07,
|
| 121 |
+
"loss": 0.8326,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16634050880626222,
|
| 126 |
+
"grad_norm": 151189.203125,
|
| 127 |
+
"learning_rate": 8.284313725490196e-07,
|
| 128 |
+
"loss": 0.8281,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1761252446183953,
|
| 133 |
+
"grad_norm": 145620.625,
|
| 134 |
+
"learning_rate": 8.774509803921568e-07,
|
| 135 |
+
"loss": 0.8252,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.18590998043052837,
|
| 140 |
+
"grad_norm": 169938.84375,
|
| 141 |
+
"learning_rate": 9.264705882352941e-07,
|
| 142 |
+
"loss": 0.8308,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.19569471624266144,
|
| 147 |
+
"grad_norm": 138760.015625,
|
| 148 |
+
"learning_rate": 9.754901960784313e-07,
|
| 149 |
+
"loss": 0.824,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2054794520547945,
|
| 154 |
+
"grad_norm": 107872.125,
|
| 155 |
+
"learning_rate": 9.99631294374483e-07,
|
| 156 |
+
"loss": 0.8254,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.21526418786692758,
|
| 161 |
+
"grad_norm": 113610.8359375,
|
| 162 |
+
"learning_rate": 9.966849112204936e-07,
|
| 163 |
+
"loss": 0.8267,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.22504892367906065,
|
| 168 |
+
"grad_norm": 172441.515625,
|
| 169 |
+
"learning_rate": 9.908095200725339e-07,
|
| 170 |
+
"loss": 0.8198,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.23483365949119372,
|
| 175 |
+
"grad_norm": 128079.9140625,
|
| 176 |
+
"learning_rate": 9.82039768787326e-07,
|
| 177 |
+
"loss": 0.8143,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2446183953033268,
|
| 182 |
+
"grad_norm": 98149.8984375,
|
| 183 |
+
"learning_rate": 9.70427373595903e-07,
|
| 184 |
+
"loss": 0.8191,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.25440313111545987,
|
| 189 |
+
"grad_norm": 147377.4375,
|
| 190 |
+
"learning_rate": 9.560408141270531e-07,
|
| 191 |
+
"loss": 0.8178,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.26418786692759294,
|
| 196 |
+
"grad_norm": 156439.40625,
|
| 197 |
+
"learning_rate": 9.389649295750781e-07,
|
| 198 |
+
"loss": 0.8085,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.273972602739726,
|
| 203 |
+
"grad_norm": 131892.015625,
|
| 204 |
+
"learning_rate": 9.193004183933174e-07,
|
| 205 |
+
"loss": 0.8172,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2837573385518591,
|
| 210 |
+
"grad_norm": 132474.5,
|
| 211 |
+
"learning_rate": 8.971632444637971e-07,
|
| 212 |
+
"loss": 0.8136,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.29354207436399216,
|
| 217 |
+
"grad_norm": 112619.109375,
|
| 218 |
+
"learning_rate": 8.726839532448928e-07,
|
| 219 |
+
"loss": 0.8065,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.30332681017612523,
|
| 224 |
+
"grad_norm": 94225.5703125,
|
| 225 |
+
"learning_rate": 8.460069019297606e-07,
|
| 226 |
+
"loss": 0.813,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3131115459882583,
|
| 231 |
+
"grad_norm": 117812.8203125,
|
| 232 |
+
"learning_rate": 8.172894081553822e-07,
|
| 233 |
+
"loss": 0.8022,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.32289628180039137,
|
| 238 |
+
"grad_norm": 143287.125,
|
| 239 |
+
"learning_rate": 7.86700822282382e-07,
|
| 240 |
+
"loss": 0.8061,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.33268101761252444,
|
| 245 |
+
"grad_norm": 107456.25,
|
| 246 |
+
"learning_rate": 7.544215287164917e-07,
|
| 247 |
+
"loss": 0.8006,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3424657534246575,
|
| 252 |
+
"grad_norm": 101521.171875,
|
| 253 |
+
"learning_rate": 7.206418821609812e-07,
|
| 254 |
+
"loss": 0.8055,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3522504892367906,
|
| 259 |
+
"grad_norm": 118311.5234375,
|
| 260 |
+
"learning_rate": 6.855610850731017e-07,
|
| 261 |
+
"loss": 0.8081,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.36203522504892366,
|
| 266 |
+
"grad_norm": 89621.828125,
|
| 267 |
+
"learning_rate": 6.493860129443046e-07,
|
| 268 |
+
"loss": 0.8058,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.37181996086105673,
|
| 273 |
+
"grad_norm": 143168.65625,
|
| 274 |
+
"learning_rate": 6.123299943316975e-07,
|
| 275 |
+
"loss": 0.8028,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3816046966731898,
|
| 280 |
+
"grad_norm": 118598.2890625,
|
| 281 |
+
"learning_rate": 5.746115528350295e-07,
|
| 282 |
+
"loss": 0.8032,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3913894324853229,
|
| 287 |
+
"grad_norm": 111807.8203125,
|
| 288 |
+
"learning_rate": 5.364531184379139e-07,
|
| 289 |
+
"loss": 0.8014,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.40117416829745595,
|
| 294 |
+
"grad_norm": 124106.1328125,
|
| 295 |
+
"learning_rate": 4.980797158126566e-07,
|
| 296 |
+
"loss": 0.8045,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.410958904109589,
|
| 301 |
+
"grad_norm": 102746.4765625,
|
| 302 |
+
"learning_rate": 4.597176373239061e-07,
|
| 303 |
+
"loss": 0.7996,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4207436399217221,
|
| 308 |
+
"grad_norm": 108317.5859375,
|
| 309 |
+
"learning_rate": 4.215931085565761e-07,
|
| 310 |
+
"loss": 0.8037,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.43052837573385516,
|
| 315 |
+
"grad_norm": 113342.515625,
|
| 316 |
+
"learning_rate": 3.8393095423757764e-07,
|
| 317 |
+
"loss": 0.8047,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.44031311154598823,
|
| 322 |
+
"grad_norm": 111908.90625,
|
| 323 |
+
"learning_rate": 3.469532724185699e-07,
|
| 324 |
+
"loss": 0.8021,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4500978473581213,
|
| 329 |
+
"grad_norm": 85004.15625,
|
| 330 |
+
"learning_rate": 3.1087812473822845e-07,
|
| 331 |
+
"loss": 0.8012,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4598825831702544,
|
| 336 |
+
"grad_norm": 98335.1796875,
|
| 337 |
+
"learning_rate": 2.7591825048770643e-07,
|
| 338 |
+
"loss": 0.7977,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.46966731898238745,
|
| 343 |
+
"grad_norm": 110674.03125,
|
| 344 |
+
"learning_rate": 2.422798120625886e-07,
|
| 345 |
+
"loss": 0.7979,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4794520547945205,
|
| 350 |
+
"grad_norm": 114861.5390625,
|
| 351 |
+
"learning_rate": 2.1016117919955512e-07,
|
| 352 |
+
"loss": 0.8014,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4892367906066536,
|
| 357 |
+
"grad_norm": 130109.5703125,
|
| 358 |
+
"learning_rate": 1.7975175916725031e-07,
|
| 359 |
+
"loss": 0.7994,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.49902152641878667,
|
| 364 |
+
"grad_norm": 93286.4296875,
|
| 365 |
+
"learning_rate": 1.5123087980985606e-07,
|
| 366 |
+
"loss": 0.8039,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5088062622309197,
|
| 371 |
+
"grad_norm": 123646.703125,
|
| 372 |
+
"learning_rate": 1.2476673203018728e-07,
|
| 373 |
+
"loss": 0.7917,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5185909980430529,
|
| 378 |
+
"grad_norm": 98060.2265625,
|
| 379 |
+
"learning_rate": 1.0051537794861287e-07,
|
| 380 |
+
"loss": 0.7945,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5283757338551859,
|
| 385 |
+
"grad_norm": 91181.1796875,
|
| 386 |
+
"learning_rate": 7.861983058679871e-08,
|
| 387 |
+
"loss": 0.7952,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.538160469667319,
|
| 392 |
+
"grad_norm": 97605.3984375,
|
| 393 |
+
"learning_rate": 5.920921050348626e-08,
|
| 394 |
+
"loss": 0.7963,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.538160469667319,
|
| 399 |
+
"eval_accuracy": 0.767,
|
| 400 |
+
"eval_loss": 0.662277102470398,
|
| 401 |
+
"eval_macro_f1": 0.5341406895117674,
|
| 402 |
+
"eval_precision": 0.6105222734254993,
|
| 403 |
+
"eval_recall": 0.5415245482510056,
|
| 404 |
+
"eval_runtime": 16.9722,
|
| 405 |
+
"eval_samples_per_second": 58.92,
|
| 406 |
+
"eval_steps_per_second": 0.059,
|
| 407 |
+
"step": 550
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.547945205479452,
|
| 411 |
+
"grad_norm": 101627.8046875,
|
| 412 |
+
"learning_rate": 4.23979843557199e-08,
|
| 413 |
+
"loss": 0.7962,
|
| 414 |
+
"step": 560
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.5577299412915852,
|
| 418 |
+
"grad_norm": 73889.578125,
|
| 419 |
+
"learning_rate": 2.8285289875818407e-08,
|
| 420 |
+
"loss": 0.794,
|
| 421 |
+
"step": 570
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.5675146771037182,
|
| 425 |
+
"grad_norm": 87191.0546875,
|
| 426 |
+
"learning_rate": 1.695435124477512e-08,
|
| 427 |
+
"loss": 0.7984,
|
| 428 |
+
"step": 580
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.5772994129158513,
|
| 432 |
+
"grad_norm": 105470.234375,
|
| 433 |
+
"learning_rate": 8.471988309699807e-09,
|
| 434 |
+
"loss": 0.7924,
|
| 435 |
+
"step": 590
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.5870841487279843,
|
| 439 |
+
"grad_norm": 81710.7265625,
|
| 440 |
+
"learning_rate": 2.8882225395023275e-09,
|
| 441 |
+
"loss": 0.8005,
|
| 442 |
+
"step": 600
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.5870841487279843,
|
| 446 |
+
"eval_accuracy": 0.767,
|
| 447 |
+
"eval_loss": 0.6623347401618958,
|
| 448 |
+
"eval_macro_f1": 0.5341406895117674,
|
| 449 |
+
"eval_precision": 0.6105222734254993,
|
| 450 |
+
"eval_recall": 0.5415245482510056,
|
| 451 |
+
"eval_runtime": 17.0174,
|
| 452 |
+
"eval_samples_per_second": 58.763,
|
| 453 |
+
"eval_steps_per_second": 0.059,
|
| 454 |
+
"step": 600
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.5968688845401174,
|
| 458 |
+
"grad_norm": 97212.125,
|
| 459 |
+
"learning_rate": 2.35982042542604e-10,
|
| 460 |
+
"loss": 0.7981,
|
| 461 |
+
"step": 610
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.6066536203522505,
|
| 465 |
+
"grad_norm": 100700.640625,
|
| 466 |
+
"learning_rate": 9.994690926142082e-07,
|
| 467 |
+
"loss": 0.8006,
|
| 468 |
+
"step": 620
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.6164383561643836,
|
| 472 |
+
"grad_norm": 88023.046875,
|
| 473 |
+
"learning_rate": 9.962287406393883e-07,
|
| 474 |
+
"loss": 0.7976,
|
| 475 |
+
"step": 630
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.6262230919765166,
|
| 479 |
+
"grad_norm": 118936.609375,
|
| 480 |
+
"learning_rate": 9.900620707609317e-07,
|
| 481 |
+
"loss": 0.7961,
|
| 482 |
+
"step": 640
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.6360078277886497,
|
| 486 |
+
"grad_norm": 91811.3984375,
|
| 487 |
+
"learning_rate": 9.810054485397043e-07,
|
| 488 |
+
"loss": 0.7904,
|
| 489 |
+
"step": 650
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.6360078277886497,
|
| 493 |
+
"eval_accuracy": 0.757,
|
| 494 |
+
"eval_loss": 0.6629467606544495,
|
| 495 |
+
"eval_macro_f1": 0.5299579283330915,
|
| 496 |
+
"eval_precision": 0.5844492268452096,
|
| 497 |
+
"eval_recall": 0.5366881936388663,
|
| 498 |
+
"eval_runtime": 17.0504,
|
| 499 |
+
"eval_samples_per_second": 58.65,
|
| 500 |
+
"eval_steps_per_second": 0.059,
|
| 501 |
+
"step": 650
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.6457925636007827,
|
| 505 |
+
"grad_norm": 118632.46875,
|
| 506 |
+
"learning_rate": 9.69112281917613e-07,
|
| 507 |
+
"loss": 0.7927,
|
| 508 |
+
"step": 660
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.6555772994129159,
|
| 512 |
+
"grad_norm": 70413.0390625,
|
| 513 |
+
"learning_rate": 9.544527062648345e-07,
|
| 514 |
+
"loss": 0.785,
|
| 515 |
+
"step": 670
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.6653620352250489,
|
| 519 |
+
"grad_norm": 84746.4453125,
|
| 520 |
+
"learning_rate": 9.371131707834789e-07,
|
| 521 |
+
"loss": 0.7861,
|
| 522 |
+
"step": 680
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.675146771037182,
|
| 526 |
+
"grad_norm": 92019.0390625,
|
| 527 |
+
"learning_rate": 9.171959287067115e-07,
|
| 528 |
+
"loss": 0.7892,
|
| 529 |
+
"step": 690
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.684931506849315,
|
| 533 |
+
"grad_norm": 70649.2578125,
|
| 534 |
+
"learning_rate": 8.948184342996868e-07,
|
| 535 |
+
"loss": 0.789,
|
| 536 |
+
"step": 700
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.684931506849315,
|
| 540 |
+
"eval_accuracy": 0.751,
|
| 541 |
+
"eval_loss": 0.6648359894752502,
|
| 542 |
+
"eval_macro_f1": 0.5514410631387237,
|
| 543 |
+
"eval_precision": 0.589223697650664,
|
| 544 |
+
"eval_recall": 0.5504123598294002,
|
| 545 |
+
"eval_runtime": 17.0124,
|
| 546 |
+
"eval_samples_per_second": 58.781,
|
| 547 |
+
"eval_steps_per_second": 0.059,
|
| 548 |
+
"step": 700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.6947162426614482,
|
| 552 |
+
"grad_norm": 80338.796875,
|
| 553 |
+
"learning_rate": 8.701126502182503e-07,
|
| 554 |
+
"loss": 0.7907,
|
| 555 |
+
"step": 710
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7045009784735812,
|
| 559 |
+
"grad_norm": 69257.328125,
|
| 560 |
+
"learning_rate": 8.432242693099946e-07,
|
| 561 |
+
"loss": 0.7881,
|
| 562 |
+
"step": 720
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7142857142857143,
|
| 566 |
+
"grad_norm": 95345.15625,
|
| 567 |
+
"learning_rate": 8.14311855446795e-07,
|
| 568 |
+
"loss": 0.7849,
|
| 569 |
+
"step": 730
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7240704500978473,
|
| 573 |
+
"grad_norm": 94407.8984375,
|
| 574 |
+
"learning_rate": 7.835459084554374e-07,
|
| 575 |
+
"loss": 0.7868,
|
| 576 |
+
"step": 740
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7338551859099804,
|
| 580 |
+
"grad_norm": 74418.0625,
|
| 581 |
+
"learning_rate": 7.511078586605484e-07,
|
| 582 |
+
"loss": 0.783,
|
| 583 |
+
"step": 750
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7338551859099804,
|
| 587 |
+
"eval_accuracy": 0.742,
|
| 588 |
+
"eval_loss": 0.6660248637199402,
|
| 589 |
+
"eval_macro_f1": 0.5532467532467532,
|
| 590 |
+
"eval_precision": 0.579727791757989,
|
| 591 |
+
"eval_recall": 0.5510154613293626,
|
| 592 |
+
"eval_runtime": 16.9303,
|
| 593 |
+
"eval_samples_per_second": 59.066,
|
| 594 |
+
"eval_steps_per_second": 0.059,
|
| 595 |
+
"step": 750
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.7436399217221135,
|
| 599 |
+
"grad_norm": 95142.0546875,
|
| 600 |
+
"learning_rate": 7.171889969691225e-07,
|
| 601 |
+
"loss": 0.7861,
|
| 602 |
+
"step": 760
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.7534246575342466,
|
| 606 |
+
"grad_norm": 118907.203125,
|
| 607 |
+
"learning_rate": 6.819893468060643e-07,
|
| 608 |
+
"loss": 0.7878,
|
| 609 |
+
"step": 770
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.7632093933463796,
|
| 613 |
+
"grad_norm": 66268.78125,
|
| 614 |
+
"learning_rate": 6.457164845530662e-07,
|
| 615 |
+
"loss": 0.7859,
|
| 616 |
+
"step": 780
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.7729941291585127,
|
| 620 |
+
"grad_norm": 81464.265625,
|
| 621 |
+
"learning_rate": 6.085843154468354e-07,
|
| 622 |
+
"loss": 0.7819,
|
| 623 |
+
"step": 790
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.7827788649706457,
|
| 627 |
+
"grad_norm": 87098.984375,
|
| 628 |
+
"learning_rate": 5.708118121553318e-07,
|
| 629 |
+
"loss": 0.7801,
|
| 630 |
+
"step": 800
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7827788649706457,
|
| 634 |
+
"eval_accuracy": 0.734,
|
| 635 |
+
"eval_loss": 0.667039155960083,
|
| 636 |
+
"eval_macro_f1": 0.5514001038862917,
|
| 637 |
+
"eval_precision": 0.5710358542434345,
|
| 638 |
+
"eval_recall": 0.5490647598270917,
|
| 639 |
+
"eval_runtime": 17.0236,
|
| 640 |
+
"eval_samples_per_second": 58.742,
|
| 641 |
+
"eval_steps_per_second": 0.059,
|
| 642 |
+
"step": 800
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.7925636007827789,
|
| 646 |
+
"grad_norm": 70466.7109375,
|
| 647 |
+
"learning_rate": 5.326217234707852e-07,
|
| 648 |
+
"loss": 0.7782,
|
| 649 |
+
"step": 810
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.8023483365949119,
|
| 653 |
+
"grad_norm": 78038.6015625,
|
| 654 |
+
"learning_rate": 4.942392607344717e-07,
|
| 655 |
+
"loss": 0.786,
|
| 656 |
+
"step": 820
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.812133072407045,
|
| 660 |
+
"grad_norm": 91227.28125,
|
| 661 |
+
"learning_rate": 4.558907697395553e-07,
|
| 662 |
+
"loss": 0.7781,
|
| 663 |
+
"step": 830
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.821917808219178,
|
| 667 |
+
"grad_norm": 85470.5625,
|
| 668 |
+
"learning_rate": 4.1780239594393807e-07,
|
| 669 |
+
"loss": 0.7806,
|
| 670 |
+
"step": 840
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.8317025440313112,
|
| 674 |
+
"grad_norm": 73229.96875,
|
| 675 |
+
"learning_rate": 3.8019875086450787e-07,
|
| 676 |
+
"loss": 0.7823,
|
| 677 |
+
"step": 850
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.8317025440313112,
|
| 681 |
+
"eval_accuracy": 0.725,
|
| 682 |
+
"eval_loss": 0.668379545211792,
|
| 683 |
+
"eval_macro_f1": 0.5541786430494829,
|
| 684 |
+
"eval_precision": 0.5667714002224962,
|
| 685 |
+
"eval_recall": 0.5512665131499213,
|
| 686 |
+
"eval_runtime": 16.9299,
|
| 687 |
+
"eval_samples_per_second": 59.067,
|
| 688 |
+
"eval_steps_per_second": 0.059,
|
| 689 |
+
"step": 850
|
| 690 |
+
}
|
| 691 |
+
],
|
| 692 |
+
"logging_steps": 10,
|
| 693 |
+
"max_steps": 1022,
|
| 694 |
+
"num_input_tokens_seen": 0,
|
| 695 |
+
"num_train_epochs": 1,
|
| 696 |
+
"save_steps": 50,
|
| 697 |
+
"stateful_callbacks": {
|
| 698 |
+
"EarlyStoppingCallback": {
|
| 699 |
+
"args": {
|
| 700 |
+
"early_stopping_patience": 3,
|
| 701 |
+
"early_stopping_threshold": 0.0
|
| 702 |
+
},
|
| 703 |
+
"attributes": {
|
| 704 |
+
"early_stopping_patience_counter": 0
|
| 705 |
+
}
|
| 706 |
+
},
|
| 707 |
+
"TrainerControl": {
|
| 708 |
+
"args": {
|
| 709 |
+
"should_epoch_stop": false,
|
| 710 |
+
"should_evaluate": false,
|
| 711 |
+
"should_log": false,
|
| 712 |
+
"should_save": true,
|
| 713 |
+
"should_training_stop": false
|
| 714 |
+
},
|
| 715 |
+
"attributes": {}
|
| 716 |
+
}
|
| 717 |
+
},
|
| 718 |
+
"total_flos": 1.14505931292672e+17,
|
| 719 |
+
"train_batch_size": 512,
|
| 720 |
+
"trial_name": null,
|
| 721 |
+
"trial_params": null
|
| 722 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8307116b3e23cecae8ec65819b3c2e7993d8af193c50142730ae3c50bce70d6
|
| 3 |
+
size 5905
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-850/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-900/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-base-lowLR-highBatchSize/checkpoint-900/config_hyperparams.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train_config": {
|
| 3 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 4 |
+
"num_epochs": 1,
|
| 5 |
+
"batch_size": 256,
|
| 6 |
+
"learning_rate": 1e-06,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"num_labels": 2,
|
| 9 |
+
"loss_type": "r-drop",
|
| 10 |
+
"focal_alpha": 1.0,
|
| 11 |
+
"focal_gamma": 2.0,
|
| 12 |
+
"r_drop_alpha": 10.0,
|
| 13 |
+
"infonce_temperature": 0.07,
|
| 14 |
+
"infonce_weight": 0.5,
|
| 15 |
+
"label_smoothing": 0.5,
|
| 16 |
+
"adversarial_epsilon": 0.5,
|
| 17 |
+
"use_swa": false,
|
| 18 |
+
"swa_start_epoch": 0,
|
| 19 |
+
"swa_lr": 1e-05,
|
| 20 |
+
"data_augmentation": true,
|
| 21 |
+
"aug_rename_prob": 0.8,
|
| 22 |
+
"aug_format_prob": 0.8,
|
| 23 |
+
"freeze_base": true,
|
| 24 |
+
"seed": 42,
|
| 25 |
+
"use_wandb": true,
|
| 26 |
+
"mixup_alpha": 1.0,
|
| 27 |
+
"low_pass_keep_ratio": 0.5,
|
| 28 |
+
"freq_consistency_weight": 0.5
|
| 29 |
+
},
|
| 30 |
+
"training_arguments": {
|
| 31 |
+
"output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
|
| 32 |
+
"num_train_epochs": 1,
|
| 33 |
+
"per_device_train_batch_size": 256,
|
| 34 |
+
"per_device_eval_batch_size": 512,
|
| 35 |
+
"learning_rate": 1e-06,
|
| 36 |
+
"warmup_steps": 204,
|
| 37 |
+
"weight_decay": 0.1,
|
| 38 |
+
"logging_steps": 10,
|
| 39 |
+
"eval_steps": 50,
|
| 40 |
+
"save_steps": 50,
|
| 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": 900,
|
| 49 |
+
"epoch": 0.8806262230919765,
|
| 50 |
+
"best_metric": 0.5584519389438943,
|
| 51 |
+
"best_model_checkpoint": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-900"
|
| 52 |
+
}
|
| 53 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-900/hyperparams.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "microsoft/graphcodebert-base",
|
| 3 |
+
"output_dir": "output_checkpoints/graphcodebert-base-lowLR-highBatchSize/",
|
| 4 |
+
"num_epochs": 1,
|
| 5 |
+
"max_steps": -1,
|
| 6 |
+
"batch_size": 256,
|
| 7 |
+
"learning_rate": 1e-06,
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"num_labels": 2,
|
| 10 |
+
"use_wandb": true,
|
| 11 |
+
"freeze_base": true,
|
| 12 |
+
"loss_type": "r-drop",
|
| 13 |
+
"focal_alpha": 1.0,
|
| 14 |
+
"focal_gamma": 2.0,
|
| 15 |
+
"r_drop_alpha": 10.0,
|
| 16 |
+
"infonce_temperature": 0.07,
|
| 17 |
+
"infonce_weight": 0.5,
|
| 18 |
+
"seed": 42,
|
| 19 |
+
"resume_from_checkpoint": "checkpoints/graphcodebert-base-lowLR-highBatchSize/checkpoint-500",
|
| 20 |
+
"label_smoothing": 0.5,
|
| 21 |
+
"adversarial_epsilon": 0.5,
|
| 22 |
+
"use_swa": false,
|
| 23 |
+
"swa_start_epoch": 0,
|
| 24 |
+
"swa_lr": 1e-05,
|
| 25 |
+
"data_augmentation": true,
|
| 26 |
+
"aug_rename_prob": 0.8,
|
| 27 |
+
"aug_format_prob": 0.8,
|
| 28 |
+
"mixup_alpha": 1.0,
|
| 29 |
+
"low_pass_keep_ratio": 0.5,
|
| 30 |
+
"freq_consistency_weight": 0.5,
|
| 31 |
+
"hidden_dropout_prob": 0.3,
|
| 32 |
+
"attention_probs_dropout_prob": 0.3,
|
| 33 |
+
"classifier_dropout": 0.3,
|
| 34 |
+
"device": "cuda"
|
| 35 |
+
}
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-900/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-base-lowLR-highBatchSize/checkpoint-900/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2b4b28e3f41b50f1e79a215c3717c6cdbb00864d1d19a89b49453800d3a6498
|
| 3 |
+
size 498612824
|