upload graphcodebert base, more training = more assign to majority class, poor f1 score T_T
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- graphcodebert-focal/checkpoint-200/config.json +28 -0
- graphcodebert-focal/checkpoint-200/merges.txt +0 -0
- graphcodebert-focal/checkpoint-200/model.safetensors +3 -0
- graphcodebert-focal/checkpoint-200/optimizer.pt +3 -0
- graphcodebert-focal/checkpoint-200/rng_state.pth +3 -0
- graphcodebert-focal/checkpoint-200/scheduler.pt +3 -0
- graphcodebert-focal/checkpoint-200/special_tokens_map.json +51 -0
- graphcodebert-focal/checkpoint-200/tokenizer.json +0 -0
- graphcodebert-focal/checkpoint-200/tokenizer_config.json +58 -0
- graphcodebert-focal/checkpoint-200/trainer_state.json +183 -0
- graphcodebert-focal/checkpoint-200/training_args.bin +3 -0
- graphcodebert-focal/checkpoint-200/vocab.json +0 -0
- graphcodebert-focal/training.log +58 -0
- graphcodebert-rdrop/checkpoint-1000/config.json +28 -0
- graphcodebert-rdrop/checkpoint-1000/merges.txt +0 -0
- graphcodebert-rdrop/checkpoint-1000/model.safetensors +3 -0
- graphcodebert-rdrop/checkpoint-1000/optimizer.pt +3 -0
- graphcodebert-rdrop/checkpoint-1000/rng_state.pth +3 -0
- graphcodebert-rdrop/checkpoint-1000/scaler.pt +3 -0
- graphcodebert-rdrop/checkpoint-1000/scheduler.pt +3 -0
- graphcodebert-rdrop/checkpoint-1000/special_tokens_map.json +51 -0
- graphcodebert-rdrop/checkpoint-1000/tokenizer.json +0 -0
- graphcodebert-rdrop/checkpoint-1000/tokenizer_config.json +58 -0
- graphcodebert-rdrop/checkpoint-1000/trainer_state.json +755 -0
- graphcodebert-rdrop/checkpoint-1000/training_args.bin +3 -0
- graphcodebert-rdrop/checkpoint-1000/vocab.json +0 -0
- graphcodebert-rdrop/checkpoint-400/model.safetensors +1 -1
- graphcodebert-rdrop/checkpoint-400/optimizer.pt +1 -1
- graphcodebert-rdrop/checkpoint-400/rng_state.pth +1 -1
- graphcodebert-rdrop/checkpoint-400/scaler.pt +3 -0
- graphcodebert-rdrop/checkpoint-400/trainer_state.json +80 -80
- graphcodebert-rdrop/checkpoint-400/training_args.bin +1 -1
- graphcodebert-rdrop/checkpoint-600/model.safetensors +1 -1
- graphcodebert-rdrop/checkpoint-600/optimizer.pt +1 -1
- graphcodebert-rdrop/checkpoint-600/rng_state.pth +1 -1
- graphcodebert-rdrop/checkpoint-600/scaler.pt +3 -0
- graphcodebert-rdrop/checkpoint-600/trainer_state.json +120 -120
- graphcodebert-rdrop/checkpoint-600/training_args.bin +1 -1
- graphcodebert-rdrop/checkpoint-800/config.json +28 -0
- graphcodebert-rdrop/checkpoint-800/merges.txt +0 -0
- graphcodebert-rdrop/checkpoint-800/model.safetensors +3 -0
- graphcodebert-rdrop/checkpoint-800/optimizer.pt +3 -0
- graphcodebert-rdrop/checkpoint-800/rng_state.pth +3 -0
- graphcodebert-rdrop/checkpoint-800/scaler.pt +3 -0
- graphcodebert-rdrop/checkpoint-800/scheduler.pt +3 -0
- graphcodebert-rdrop/checkpoint-800/special_tokens_map.json +51 -0
- graphcodebert-rdrop/checkpoint-800/tokenizer.json +0 -0
- graphcodebert-rdrop/checkpoint-800/tokenizer_config.json +58 -0
- graphcodebert-rdrop/checkpoint-800/trainer_state.json +603 -0
- graphcodebert-rdrop/checkpoint-800/training_args.bin +3 -0
graphcodebert-focal/checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.2,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.2,
|
| 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 |
+
"transformers_version": "4.56.0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
graphcodebert-focal/checkpoint-200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-focal/checkpoint-200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d51fd56ccff09e10299217033b2ea166baee2ca42845d378e6737c9b07e8e32f
|
| 3 |
+
size 498612824
|
graphcodebert-focal/checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4b2aca589412ab916678ce8d9e00aeb607955c6f721e38f8415fd21948a1c92
|
| 3 |
+
size 4741923
|
graphcodebert-focal/checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f22808e1c30d56a5058dde00551aa995ebf4f87566ca63fc16a2a5b1b2a20d4
|
| 3 |
+
size 14645
|
graphcodebert-focal/checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b91e66f421c38847c52a87847777c6247c8ebe6edef14a199414dfbdfe6d70b2
|
| 3 |
+
size 1465
|
graphcodebert-focal/checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
graphcodebert-focal/checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-focal/checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
graphcodebert-focal/checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.01223540927444023,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0006117704637220115,
|
| 14 |
+
"grad_norm": 1.647070050239563,
|
| 15 |
+
"learning_rate": 3.671221700999388e-08,
|
| 16 |
+
"loss": 0.1895,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.001223540927444023,
|
| 21 |
+
"grad_norm": 1.2862460613250732,
|
| 22 |
+
"learning_rate": 7.750356924332042e-08,
|
| 23 |
+
"loss": 0.1824,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0018353113911660345,
|
| 28 |
+
"grad_norm": 1.6323548555374146,
|
| 29 |
+
"learning_rate": 1.1829492147664697e-07,
|
| 30 |
+
"loss": 0.1927,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.002447081854888046,
|
| 35 |
+
"grad_norm": 1.4893640279769897,
|
| 36 |
+
"learning_rate": 1.590862737099735e-07,
|
| 37 |
+
"loss": 0.1911,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0030588523186100575,
|
| 42 |
+
"grad_norm": 1.0960227251052856,
|
| 43 |
+
"learning_rate": 1.9987762594330002e-07,
|
| 44 |
+
"loss": 0.1801,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.003670622782332069,
|
| 49 |
+
"grad_norm": 0.6325238943099976,
|
| 50 |
+
"learning_rate": 2.406689781766266e-07,
|
| 51 |
+
"loss": 0.1818,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0042823932460540805,
|
| 56 |
+
"grad_norm": 2.047482490539551,
|
| 57 |
+
"learning_rate": 2.814603304099531e-07,
|
| 58 |
+
"loss": 0.192,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.004894163709776092,
|
| 63 |
+
"grad_norm": 2.4107882976531982,
|
| 64 |
+
"learning_rate": 3.222516826432796e-07,
|
| 65 |
+
"loss": 0.1897,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0055059341734981036,
|
| 70 |
+
"grad_norm": 0.7147008180618286,
|
| 71 |
+
"learning_rate": 3.630430348766062e-07,
|
| 72 |
+
"loss": 0.1833,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.006117704637220115,
|
| 77 |
+
"grad_norm": 0.7912544012069702,
|
| 78 |
+
"learning_rate": 4.0383438710993277e-07,
|
| 79 |
+
"loss": 0.1869,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.006729475100942127,
|
| 84 |
+
"grad_norm": 1.3714642524719238,
|
| 85 |
+
"learning_rate": 4.4462573934325923e-07,
|
| 86 |
+
"loss": 0.1861,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.007341245564664138,
|
| 91 |
+
"grad_norm": 1.2271082401275635,
|
| 92 |
+
"learning_rate": 4.854170915765858e-07,
|
| 93 |
+
"loss": 0.1843,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.00795301602838615,
|
| 98 |
+
"grad_norm": 0.6724980473518372,
|
| 99 |
+
"learning_rate": 5.262084438099123e-07,
|
| 100 |
+
"loss": 0.1819,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.008564786492108161,
|
| 105 |
+
"grad_norm": 1.4163967370986938,
|
| 106 |
+
"learning_rate": 5.669997960432388e-07,
|
| 107 |
+
"loss": 0.182,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.009176556955830173,
|
| 112 |
+
"grad_norm": 1.1623996496200562,
|
| 113 |
+
"learning_rate": 6.077911482765654e-07,
|
| 114 |
+
"loss": 0.1834,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.009788327419552184,
|
| 119 |
+
"grad_norm": 1.2043864727020264,
|
| 120 |
+
"learning_rate": 6.48582500509892e-07,
|
| 121 |
+
"loss": 0.1806,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.010400097883274196,
|
| 126 |
+
"grad_norm": 0.9487743973731995,
|
| 127 |
+
"learning_rate": 6.893738527432185e-07,
|
| 128 |
+
"loss": 0.1806,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.011011868346996207,
|
| 133 |
+
"grad_norm": 1.135107159614563,
|
| 134 |
+
"learning_rate": 7.301652049765451e-07,
|
| 135 |
+
"loss": 0.178,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.011623638810718219,
|
| 140 |
+
"grad_norm": 1.8040673732757568,
|
| 141 |
+
"learning_rate": 7.709565572098715e-07,
|
| 142 |
+
"loss": 0.1776,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.01223540927444023,
|
| 147 |
+
"grad_norm": 0.6054055690765381,
|
| 148 |
+
"learning_rate": 8.117479094431981e-07,
|
| 149 |
+
"loss": 0.1781,
|
| 150 |
+
"step": 200
|
| 151 |
+
}
|
| 152 |
+
],
|
| 153 |
+
"logging_steps": 10,
|
| 154 |
+
"max_steps": 49038,
|
| 155 |
+
"num_input_tokens_seen": 0,
|
| 156 |
+
"num_train_epochs": 3,
|
| 157 |
+
"save_steps": 200,
|
| 158 |
+
"stateful_callbacks": {
|
| 159 |
+
"EarlyStoppingCallback": {
|
| 160 |
+
"args": {
|
| 161 |
+
"early_stopping_patience": 3,
|
| 162 |
+
"early_stopping_threshold": 0.0
|
| 163 |
+
},
|
| 164 |
+
"attributes": {
|
| 165 |
+
"early_stopping_patience_counter": 0
|
| 166 |
+
}
|
| 167 |
+
},
|
| 168 |
+
"TrainerControl": {
|
| 169 |
+
"args": {
|
| 170 |
+
"should_epoch_stop": false,
|
| 171 |
+
"should_evaluate": false,
|
| 172 |
+
"should_log": false,
|
| 173 |
+
"should_save": true,
|
| 174 |
+
"should_training_stop": false
|
| 175 |
+
},
|
| 176 |
+
"attributes": {}
|
| 177 |
+
}
|
| 178 |
+
},
|
| 179 |
+
"total_flos": 1683910754304000.0,
|
| 180 |
+
"train_batch_size": 32,
|
| 181 |
+
"trial_name": null,
|
| 182 |
+
"trial_params": null
|
| 183 |
+
}
|
graphcodebert-focal/checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:145afc62f33e66235dc7e780d87723128ed03df9823c7e83b2b2a20bc180074f
|
| 3 |
+
size 5841
|
graphcodebert-focal/checkpoint-200/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-focal/training.log
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-04-15 16:22:36,752 - INFO - train_pipeline - Logging to ./output_checkpoints/graphcodebert-focal/training.log
|
| 2 |
+
2026-04-15 16:22:36,755 - INFO - train_pipeline - Loading model & tokenizer for 'microsoft/graphcodebert-base'
|
| 3 |
+
2026-04-15 16:22:39,187 - INFO - train_pipeline - Model placed on cuda
|
| 4 |
+
2026-04-15 16:22:39,191 - INFO - train_pipeline - Base model weights frozen – only classifier head will be trained.
|
| 5 |
+
2026-04-15 16:22:39,192 - INFO - train_pipeline - ===== Model Architecture =====
|
| 6 |
+
2026-04-15 16:22:39,196 - INFO - train_pipeline -
|
| 7 |
+
RobertaForSequenceClassification(
|
| 8 |
+
(roberta): RobertaModel(
|
| 9 |
+
(embeddings): RobertaEmbeddings(
|
| 10 |
+
(word_embeddings): Embedding(50265, 768, padding_idx=1)
|
| 11 |
+
(position_embeddings): Embedding(514, 768, padding_idx=1)
|
| 12 |
+
(token_type_embeddings): Embedding(1, 768)
|
| 13 |
+
(LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
|
| 14 |
+
(dropout): Dropout(p=0.2, inplace=False)
|
| 15 |
+
)
|
| 16 |
+
(encoder): RobertaEncoder(
|
| 17 |
+
(layer): ModuleList(
|
| 18 |
+
(0-11): 12 x RobertaLayer(
|
| 19 |
+
(attention): RobertaAttention(
|
| 20 |
+
(self): RobertaSdpaSelfAttention(
|
| 21 |
+
(query): Linear(in_features=768, out_features=768, bias=True)
|
| 22 |
+
(key): Linear(in_features=768, out_features=768, bias=True)
|
| 23 |
+
(value): Linear(in_features=768, out_features=768, bias=True)
|
| 24 |
+
(dropout): Dropout(p=0.2, inplace=False)
|
| 25 |
+
)
|
| 26 |
+
(output): RobertaSelfOutput(
|
| 27 |
+
(dense): Linear(in_features=768, out_features=768, bias=True)
|
| 28 |
+
(LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
|
| 29 |
+
(dropout): Dropout(p=0.2, inplace=False)
|
| 30 |
+
)
|
| 31 |
+
)
|
| 32 |
+
(intermediate): RobertaIntermediate(
|
| 33 |
+
(dense): Linear(in_features=768, out_features=3072, bias=True)
|
| 34 |
+
(intermediate_act_fn): GELUActivation()
|
| 35 |
+
)
|
| 36 |
+
(output): RobertaOutput(
|
| 37 |
+
(dense): Linear(in_features=3072, out_features=768, bias=True)
|
| 38 |
+
(LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
|
| 39 |
+
(dropout): Dropout(p=0.2, inplace=False)
|
| 40 |
+
)
|
| 41 |
+
)
|
| 42 |
+
)
|
| 43 |
+
)
|
| 44 |
+
)
|
| 45 |
+
(classifier): RobertaClassificationHead(
|
| 46 |
+
(dense): Linear(in_features=768, out_features=768, bias=True)
|
| 47 |
+
(dropout): Dropout(p=0.2, inplace=False)
|
| 48 |
+
(out_proj): Linear(in_features=768, out_features=2, bias=True)
|
| 49 |
+
)
|
| 50 |
+
)
|
| 51 |
+
2026-04-15 16:22:39,199 - INFO - train_pipeline - ===== Parameter Summary =====
|
| 52 |
+
2026-04-15 16:22:39,200 - INFO - train_pipeline - Total Parameters: 124,647,170
|
| 53 |
+
2026-04-15 16:22:39,201 - INFO - train_pipeline - Trainable Parameters: 592,130
|
| 54 |
+
2026-04-15 16:22:39,204 - INFO - train_pipeline - Non-trainable Parameters: 124,055,040
|
| 55 |
+
2026-04-15 16:22:39,205 - INFO - train_pipeline - ===== Tokenizer Summary =====
|
| 56 |
+
2026-04-15 16:22:39,227 - INFO - train_pipeline - Vocab size: 50265 | Special tokens: ['<s>', '</s>', '<unk>', '<pad>', '<mask>']
|
| 57 |
+
2026-04-15 16:22:39,230 - INFO - train_pipeline - ===== End of Architecture Log =====
|
| 58 |
+
2026-04-15 16:23:26,328 - INFO - train_pipeline - === Starting training ===
|
graphcodebert-rdrop/checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.2,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.2,
|
| 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 |
+
"transformers_version": "4.56.0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
graphcodebert-rdrop/checkpoint-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-rdrop/checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77ef8b30f9d2d2e1ee145cf5902f638aed3b40960b6adbc29b7ae3619d721d15
|
| 3 |
+
size 498612824
|
graphcodebert-rdrop/checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6463d936c9004d9610dc37c3709533220325775d0fee173d8a65fa040c277349
|
| 3 |
+
size 4741923
|
graphcodebert-rdrop/checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13f963e0d9b8f27bd9541c3a0022f1242ced7e92ff3eacae2aae62aa4a928fc8
|
| 3 |
+
size 14645
|
graphcodebert-rdrop/checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
|
| 3 |
+
size 1383
|
graphcodebert-rdrop/checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f25fe7731b9278a60bff9cc7fd3ead4df1aef9e341ef501c56c76de421b4c24
|
| 3 |
+
size 1465
|
graphcodebert-rdrop/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-rdrop/checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-rdrop/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-rdrop/checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,755 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1000,
|
| 3 |
+
"best_metric": 0.7657238614598489,
|
| 4 |
+
"best_model_checkpoint": "./output_checkpoints/graphcodebert-rdrop/checkpoint-1000",
|
| 5 |
+
"epoch": 0.064,
|
| 6 |
+
"eval_steps": 1000,
|
| 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": 0.00064,
|
| 14 |
+
"grad_norm": 1.8688431978225708,
|
| 15 |
+
"learning_rate": 3.840409643695328e-08,
|
| 16 |
+
"loss": 0.7168,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00128,
|
| 21 |
+
"grad_norm": 1.835353970527649,
|
| 22 |
+
"learning_rate": 8.10753147002347e-08,
|
| 23 |
+
"loss": 0.7179,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00192,
|
| 28 |
+
"grad_norm": 1.2541388273239136,
|
| 29 |
+
"learning_rate": 1.2374653296351612e-07,
|
| 30 |
+
"loss": 0.7177,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.00256,
|
| 35 |
+
"grad_norm": 1.1381633281707764,
|
| 36 |
+
"learning_rate": 1.6641775122679754e-07,
|
| 37 |
+
"loss": 0.7312,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0032,
|
| 42 |
+
"grad_norm": 1.6313824653625488,
|
| 43 |
+
"learning_rate": 2.0908896949007894e-07,
|
| 44 |
+
"loss": 0.7167,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.00384,
|
| 49 |
+
"grad_norm": 1.092464566230774,
|
| 50 |
+
"learning_rate": 2.517601877533604e-07,
|
| 51 |
+
"loss": 0.7201,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.00448,
|
| 56 |
+
"grad_norm": 1.164099097251892,
|
| 57 |
+
"learning_rate": 2.944314060166418e-07,
|
| 58 |
+
"loss": 0.7195,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.00512,
|
| 63 |
+
"grad_norm": 1.9283920526504517,
|
| 64 |
+
"learning_rate": 3.371026242799232e-07,
|
| 65 |
+
"loss": 0.7223,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.00576,
|
| 70 |
+
"grad_norm": 1.8716129064559937,
|
| 71 |
+
"learning_rate": 3.7977384254320464e-07,
|
| 72 |
+
"loss": 0.7151,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0064,
|
| 77 |
+
"grad_norm": 1.5499262809753418,
|
| 78 |
+
"learning_rate": 4.22445060806486e-07,
|
| 79 |
+
"loss": 0.7211,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.00704,
|
| 84 |
+
"grad_norm": 1.375114917755127,
|
| 85 |
+
"learning_rate": 4.651162790697675e-07,
|
| 86 |
+
"loss": 0.7247,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.00768,
|
| 91 |
+
"grad_norm": 1.384915828704834,
|
| 92 |
+
"learning_rate": 5.077874973330489e-07,
|
| 93 |
+
"loss": 0.7156,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.00832,
|
| 98 |
+
"grad_norm": 1.6376659870147705,
|
| 99 |
+
"learning_rate": 5.504587155963304e-07,
|
| 100 |
+
"loss": 0.7196,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.00896,
|
| 105 |
+
"grad_norm": 1.709489345550537,
|
| 106 |
+
"learning_rate": 5.931299338596117e-07,
|
| 107 |
+
"loss": 0.7215,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.0096,
|
| 112 |
+
"grad_norm": 1.350512146949768,
|
| 113 |
+
"learning_rate": 6.358011521228932e-07,
|
| 114 |
+
"loss": 0.71,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.01024,
|
| 119 |
+
"grad_norm": 2.33050537109375,
|
| 120 |
+
"learning_rate": 6.784723703861745e-07,
|
| 121 |
+
"loss": 0.7191,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01088,
|
| 126 |
+
"grad_norm": 1.0042874813079834,
|
| 127 |
+
"learning_rate": 7.21143588649456e-07,
|
| 128 |
+
"loss": 0.72,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.01152,
|
| 133 |
+
"grad_norm": 1.1835744380950928,
|
| 134 |
+
"learning_rate": 7.638148069127374e-07,
|
| 135 |
+
"loss": 0.7122,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.01216,
|
| 140 |
+
"grad_norm": 1.949506402015686,
|
| 141 |
+
"learning_rate": 8.064860251760189e-07,
|
| 142 |
+
"loss": 0.7091,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0128,
|
| 147 |
+
"grad_norm": 1.139626383781433,
|
| 148 |
+
"learning_rate": 8.491572434393003e-07,
|
| 149 |
+
"loss": 0.7046,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.01344,
|
| 154 |
+
"grad_norm": 1.7734779119491577,
|
| 155 |
+
"learning_rate": 8.918284617025817e-07,
|
| 156 |
+
"loss": 0.7135,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.01408,
|
| 161 |
+
"grad_norm": 1.3442974090576172,
|
| 162 |
+
"learning_rate": 9.344996799658632e-07,
|
| 163 |
+
"loss": 0.7127,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.01472,
|
| 168 |
+
"grad_norm": 1.6148335933685303,
|
| 169 |
+
"learning_rate": 9.771708982291445e-07,
|
| 170 |
+
"loss": 0.7168,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.01536,
|
| 175 |
+
"grad_norm": 0.9220213294029236,
|
| 176 |
+
"learning_rate": 1.0198421164924258e-06,
|
| 177 |
+
"loss": 0.7109,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.016,
|
| 182 |
+
"grad_norm": 1.5631815195083618,
|
| 183 |
+
"learning_rate": 1.0625133347557074e-06,
|
| 184 |
+
"loss": 0.7149,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.01664,
|
| 189 |
+
"grad_norm": 1.5052822828292847,
|
| 190 |
+
"learning_rate": 1.1051845530189888e-06,
|
| 191 |
+
"loss": 0.7112,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.01728,
|
| 196 |
+
"grad_norm": 1.6714903116226196,
|
| 197 |
+
"learning_rate": 1.1478557712822702e-06,
|
| 198 |
+
"loss": 0.7128,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.01792,
|
| 203 |
+
"grad_norm": 1.6667262315750122,
|
| 204 |
+
"learning_rate": 1.1905269895455517e-06,
|
| 205 |
+
"loss": 0.7091,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.01856,
|
| 210 |
+
"grad_norm": 1.6861907243728638,
|
| 211 |
+
"learning_rate": 1.233198207808833e-06,
|
| 212 |
+
"loss": 0.7078,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0192,
|
| 217 |
+
"grad_norm": 1.6259212493896484,
|
| 218 |
+
"learning_rate": 1.2758694260721145e-06,
|
| 219 |
+
"loss": 0.7087,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.01984,
|
| 224 |
+
"grad_norm": 1.207320213317871,
|
| 225 |
+
"learning_rate": 1.318540644335396e-06,
|
| 226 |
+
"loss": 0.7087,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.02048,
|
| 231 |
+
"grad_norm": 1.087124228477478,
|
| 232 |
+
"learning_rate": 1.3612118625986772e-06,
|
| 233 |
+
"loss": 0.7174,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.02112,
|
| 238 |
+
"grad_norm": 1.5668721199035645,
|
| 239 |
+
"learning_rate": 1.4038830808619588e-06,
|
| 240 |
+
"loss": 0.7066,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.02176,
|
| 245 |
+
"grad_norm": 1.5332859754562378,
|
| 246 |
+
"learning_rate": 1.4465542991252401e-06,
|
| 247 |
+
"loss": 0.7115,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.0224,
|
| 252 |
+
"grad_norm": 2.092994451522827,
|
| 253 |
+
"learning_rate": 1.4892255173885215e-06,
|
| 254 |
+
"loss": 0.7085,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.02304,
|
| 259 |
+
"grad_norm": 1.266851544380188,
|
| 260 |
+
"learning_rate": 1.531896735651803e-06,
|
| 261 |
+
"loss": 0.7091,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.02368,
|
| 266 |
+
"grad_norm": 1.290616512298584,
|
| 267 |
+
"learning_rate": 1.5745679539150842e-06,
|
| 268 |
+
"loss": 0.7103,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.02432,
|
| 273 |
+
"grad_norm": 1.2045000791549683,
|
| 274 |
+
"learning_rate": 1.6172391721783658e-06,
|
| 275 |
+
"loss": 0.705,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.02496,
|
| 280 |
+
"grad_norm": 1.828832983970642,
|
| 281 |
+
"learning_rate": 1.6599103904416472e-06,
|
| 282 |
+
"loss": 0.7038,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.0256,
|
| 287 |
+
"grad_norm": 1.7793196439743042,
|
| 288 |
+
"learning_rate": 1.7025816087049288e-06,
|
| 289 |
+
"loss": 0.7085,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.02624,
|
| 294 |
+
"grad_norm": 0.8949472904205322,
|
| 295 |
+
"learning_rate": 1.7452528269682101e-06,
|
| 296 |
+
"loss": 0.7045,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.02688,
|
| 301 |
+
"grad_norm": 1.3071945905685425,
|
| 302 |
+
"learning_rate": 1.7879240452314913e-06,
|
| 303 |
+
"loss": 0.702,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.02752,
|
| 308 |
+
"grad_norm": 1.7497148513793945,
|
| 309 |
+
"learning_rate": 1.8305952634947729e-06,
|
| 310 |
+
"loss": 0.7073,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.02816,
|
| 315 |
+
"grad_norm": 1.0856297016143799,
|
| 316 |
+
"learning_rate": 1.8732664817580542e-06,
|
| 317 |
+
"loss": 0.7008,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.0288,
|
| 322 |
+
"grad_norm": 1.369019627571106,
|
| 323 |
+
"learning_rate": 1.915937700021336e-06,
|
| 324 |
+
"loss": 0.7059,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.02944,
|
| 329 |
+
"grad_norm": 2.0961010456085205,
|
| 330 |
+
"learning_rate": 1.958608918284617e-06,
|
| 331 |
+
"loss": 0.6952,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.03008,
|
| 336 |
+
"grad_norm": 1.6076347827911377,
|
| 337 |
+
"learning_rate": 2.0012801365478988e-06,
|
| 338 |
+
"loss": 0.7074,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.03072,
|
| 343 |
+
"grad_norm": 1.3129311800003052,
|
| 344 |
+
"learning_rate": 2.04395135481118e-06,
|
| 345 |
+
"loss": 0.6994,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.03136,
|
| 350 |
+
"grad_norm": 1.3621476888656616,
|
| 351 |
+
"learning_rate": 2.0866225730744615e-06,
|
| 352 |
+
"loss": 0.696,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.032,
|
| 357 |
+
"grad_norm": 0.9786806106567383,
|
| 358 |
+
"learning_rate": 2.129293791337743e-06,
|
| 359 |
+
"loss": 0.7011,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.03264,
|
| 364 |
+
"grad_norm": 1.4611176252365112,
|
| 365 |
+
"learning_rate": 2.1719650096010242e-06,
|
| 366 |
+
"loss": 0.699,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.03328,
|
| 371 |
+
"grad_norm": 1.0675945281982422,
|
| 372 |
+
"learning_rate": 2.214636227864306e-06,
|
| 373 |
+
"loss": 0.6906,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.03392,
|
| 378 |
+
"grad_norm": 1.6564017534255981,
|
| 379 |
+
"learning_rate": 2.257307446127587e-06,
|
| 380 |
+
"loss": 0.6923,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.03456,
|
| 385 |
+
"grad_norm": 1.228119134902954,
|
| 386 |
+
"learning_rate": 2.2999786643908685e-06,
|
| 387 |
+
"loss": 0.6928,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0352,
|
| 392 |
+
"grad_norm": 1.9868593215942383,
|
| 393 |
+
"learning_rate": 2.34264988265415e-06,
|
| 394 |
+
"loss": 0.6912,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.03584,
|
| 399 |
+
"grad_norm": 1.2531176805496216,
|
| 400 |
+
"learning_rate": 2.3853211009174317e-06,
|
| 401 |
+
"loss": 0.6923,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.03648,
|
| 406 |
+
"grad_norm": 1.413602352142334,
|
| 407 |
+
"learning_rate": 2.427992319180713e-06,
|
| 408 |
+
"loss": 0.6993,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.03712,
|
| 413 |
+
"grad_norm": 0.9655390977859497,
|
| 414 |
+
"learning_rate": 2.470663537443994e-06,
|
| 415 |
+
"loss": 0.7017,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.03776,
|
| 420 |
+
"grad_norm": 1.962438941001892,
|
| 421 |
+
"learning_rate": 2.5133347557072756e-06,
|
| 422 |
+
"loss": 0.6933,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.0384,
|
| 427 |
+
"grad_norm": 1.1099931001663208,
|
| 428 |
+
"learning_rate": 2.556005973970557e-06,
|
| 429 |
+
"loss": 0.6925,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.03904,
|
| 434 |
+
"grad_norm": 1.1766624450683594,
|
| 435 |
+
"learning_rate": 2.5986771922338383e-06,
|
| 436 |
+
"loss": 0.6894,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.03968,
|
| 441 |
+
"grad_norm": 1.574353814125061,
|
| 442 |
+
"learning_rate": 2.64134841049712e-06,
|
| 443 |
+
"loss": 0.6923,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.04032,
|
| 448 |
+
"grad_norm": 1.194074273109436,
|
| 449 |
+
"learning_rate": 2.6840196287604015e-06,
|
| 450 |
+
"loss": 0.6855,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.04096,
|
| 455 |
+
"grad_norm": 1.1750593185424805,
|
| 456 |
+
"learning_rate": 2.7266908470236826e-06,
|
| 457 |
+
"loss": 0.7002,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.0416,
|
| 462 |
+
"grad_norm": 1.3165347576141357,
|
| 463 |
+
"learning_rate": 2.7693620652869642e-06,
|
| 464 |
+
"loss": 0.6893,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.04224,
|
| 469 |
+
"grad_norm": 1.1079384088516235,
|
| 470 |
+
"learning_rate": 2.812033283550246e-06,
|
| 471 |
+
"loss": 0.6852,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.04288,
|
| 476 |
+
"grad_norm": 1.231327772140503,
|
| 477 |
+
"learning_rate": 2.8547045018135274e-06,
|
| 478 |
+
"loss": 0.695,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.04352,
|
| 483 |
+
"grad_norm": 1.966036319732666,
|
| 484 |
+
"learning_rate": 2.897375720076808e-06,
|
| 485 |
+
"loss": 0.6833,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.04416,
|
| 490 |
+
"grad_norm": 1.0460131168365479,
|
| 491 |
+
"learning_rate": 2.9400469383400897e-06,
|
| 492 |
+
"loss": 0.6802,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.0448,
|
| 497 |
+
"grad_norm": 1.2445200681686401,
|
| 498 |
+
"learning_rate": 2.9827181566033713e-06,
|
| 499 |
+
"loss": 0.6883,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.04544,
|
| 504 |
+
"grad_norm": 1.1759636402130127,
|
| 505 |
+
"learning_rate": 3.025389374866653e-06,
|
| 506 |
+
"loss": 0.682,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.04608,
|
| 511 |
+
"grad_norm": 1.2478561401367188,
|
| 512 |
+
"learning_rate": 3.068060593129934e-06,
|
| 513 |
+
"loss": 0.6802,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.04672,
|
| 518 |
+
"grad_norm": 0.8945108652114868,
|
| 519 |
+
"learning_rate": 3.1107318113932156e-06,
|
| 520 |
+
"loss": 0.6873,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.04736,
|
| 525 |
+
"grad_norm": 1.6810317039489746,
|
| 526 |
+
"learning_rate": 3.153403029656497e-06,
|
| 527 |
+
"loss": 0.6828,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.048,
|
| 532 |
+
"grad_norm": 2.882283926010132,
|
| 533 |
+
"learning_rate": 3.1960742479197783e-06,
|
| 534 |
+
"loss": 0.6797,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.04864,
|
| 539 |
+
"grad_norm": 1.575766921043396,
|
| 540 |
+
"learning_rate": 3.23874546618306e-06,
|
| 541 |
+
"loss": 0.6826,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.04928,
|
| 546 |
+
"grad_norm": 1.8044737577438354,
|
| 547 |
+
"learning_rate": 3.2814166844463415e-06,
|
| 548 |
+
"loss": 0.6837,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.04992,
|
| 553 |
+
"grad_norm": 1.4755513668060303,
|
| 554 |
+
"learning_rate": 3.324087902709623e-06,
|
| 555 |
+
"loss": 0.6815,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.05056,
|
| 560 |
+
"grad_norm": 2.0735654830932617,
|
| 561 |
+
"learning_rate": 3.3667591209729038e-06,
|
| 562 |
+
"loss": 0.6773,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.0512,
|
| 567 |
+
"grad_norm": 0.9823655486106873,
|
| 568 |
+
"learning_rate": 3.4094303392361854e-06,
|
| 569 |
+
"loss": 0.6689,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.05184,
|
| 574 |
+
"grad_norm": 1.0731920003890991,
|
| 575 |
+
"learning_rate": 3.452101557499467e-06,
|
| 576 |
+
"loss": 0.6689,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.05248,
|
| 581 |
+
"grad_norm": 1.1081087589263916,
|
| 582 |
+
"learning_rate": 3.494772775762748e-06,
|
| 583 |
+
"loss": 0.6694,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.05312,
|
| 588 |
+
"grad_norm": 1.2130361795425415,
|
| 589 |
+
"learning_rate": 3.5374439940260297e-06,
|
| 590 |
+
"loss": 0.682,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.05376,
|
| 595 |
+
"grad_norm": 1.170345664024353,
|
| 596 |
+
"learning_rate": 3.5801152122893113e-06,
|
| 597 |
+
"loss": 0.6756,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.0544,
|
| 602 |
+
"grad_norm": 1.2610124349594116,
|
| 603 |
+
"learning_rate": 3.622786430552593e-06,
|
| 604 |
+
"loss": 0.67,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.05504,
|
| 609 |
+
"grad_norm": 1.0138545036315918,
|
| 610 |
+
"learning_rate": 3.665457648815874e-06,
|
| 611 |
+
"loss": 0.6807,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.05568,
|
| 616 |
+
"grad_norm": 1.0937036275863647,
|
| 617 |
+
"learning_rate": 3.7081288670791556e-06,
|
| 618 |
+
"loss": 0.6774,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.05632,
|
| 623 |
+
"grad_norm": 1.119221568107605,
|
| 624 |
+
"learning_rate": 3.750800085342437e-06,
|
| 625 |
+
"loss": 0.6728,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.05696,
|
| 630 |
+
"grad_norm": 1.9351646900177002,
|
| 631 |
+
"learning_rate": 3.793471303605718e-06,
|
| 632 |
+
"loss": 0.6664,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.0576,
|
| 637 |
+
"grad_norm": 1.6208665370941162,
|
| 638 |
+
"learning_rate": 3.836142521869e-06,
|
| 639 |
+
"loss": 0.6653,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.05824,
|
| 644 |
+
"grad_norm": 1.3460793495178223,
|
| 645 |
+
"learning_rate": 3.8788137401322815e-06,
|
| 646 |
+
"loss": 0.6651,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.05888,
|
| 651 |
+
"grad_norm": 1.8987629413604736,
|
| 652 |
+
"learning_rate": 3.921484958395563e-06,
|
| 653 |
+
"loss": 0.6694,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.05952,
|
| 658 |
+
"grad_norm": 1.3637055158615112,
|
| 659 |
+
"learning_rate": 3.964156176658844e-06,
|
| 660 |
+
"loss": 0.6691,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.06016,
|
| 665 |
+
"grad_norm": 1.3319580554962158,
|
| 666 |
+
"learning_rate": 4.006827394922125e-06,
|
| 667 |
+
"loss": 0.6749,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.0608,
|
| 672 |
+
"grad_norm": 1.3574756383895874,
|
| 673 |
+
"learning_rate": 4.049498613185407e-06,
|
| 674 |
+
"loss": 0.6688,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.06144,
|
| 679 |
+
"grad_norm": 1.136319637298584,
|
| 680 |
+
"learning_rate": 4.092169831448688e-06,
|
| 681 |
+
"loss": 0.6657,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.06208,
|
| 686 |
+
"grad_norm": 1.7666376829147339,
|
| 687 |
+
"learning_rate": 4.134841049711969e-06,
|
| 688 |
+
"loss": 0.6667,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.06272,
|
| 693 |
+
"grad_norm": 1.332014560699463,
|
| 694 |
+
"learning_rate": 4.177512267975251e-06,
|
| 695 |
+
"loss": 0.6715,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.06336,
|
| 700 |
+
"grad_norm": 1.3127824068069458,
|
| 701 |
+
"learning_rate": 4.220183486238532e-06,
|
| 702 |
+
"loss": 0.6737,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.064,
|
| 707 |
+
"grad_norm": 1.293678641319275,
|
| 708 |
+
"learning_rate": 4.262854704501814e-06,
|
| 709 |
+
"loss": 0.6557,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.064,
|
| 714 |
+
"eval_accuracy": 0.76589,
|
| 715 |
+
"eval_loss": 0.6282070279121399,
|
| 716 |
+
"eval_macro_f1": 0.7657238614598489,
|
| 717 |
+
"eval_precision": 0.7708542319194018,
|
| 718 |
+
"eval_recall": 0.7687514011652705,
|
| 719 |
+
"eval_runtime": 806.5969,
|
| 720 |
+
"eval_samples_per_second": 123.978,
|
| 721 |
+
"eval_steps_per_second": 1.938,
|
| 722 |
+
"step": 1000
|
| 723 |
+
}
|
| 724 |
+
],
|
| 725 |
+
"logging_steps": 10,
|
| 726 |
+
"max_steps": 46875,
|
| 727 |
+
"num_input_tokens_seen": 0,
|
| 728 |
+
"num_train_epochs": 3,
|
| 729 |
+
"save_steps": 200,
|
| 730 |
+
"stateful_callbacks": {
|
| 731 |
+
"EarlyStoppingCallback": {
|
| 732 |
+
"args": {
|
| 733 |
+
"early_stopping_patience": 3,
|
| 734 |
+
"early_stopping_threshold": 0.0
|
| 735 |
+
},
|
| 736 |
+
"attributes": {
|
| 737 |
+
"early_stopping_patience_counter": 0
|
| 738 |
+
}
|
| 739 |
+
},
|
| 740 |
+
"TrainerControl": {
|
| 741 |
+
"args": {
|
| 742 |
+
"should_epoch_stop": false,
|
| 743 |
+
"should_evaluate": false,
|
| 744 |
+
"should_log": false,
|
| 745 |
+
"should_save": true,
|
| 746 |
+
"should_training_stop": false
|
| 747 |
+
},
|
| 748 |
+
"attributes": {}
|
| 749 |
+
}
|
| 750 |
+
},
|
| 751 |
+
"total_flos": 8415853772304000.0,
|
| 752 |
+
"train_batch_size": 32,
|
| 753 |
+
"trial_name": null,
|
| 754 |
+
"trial_params": null
|
| 755 |
+
}
|
graphcodebert-rdrop/checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7cd390fef915efa37cfafbe6f2d5d365158faf1073058ef1c9ea09cda16a6a5
|
| 3 |
+
size 5841
|
graphcodebert-rdrop/checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-rdrop/checkpoint-400/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498612824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:292cfe21336cb12b3bf56dc19d1277e2ecf9cc8b44a5f5865109a36d91181279
|
| 3 |
size 498612824
|
graphcodebert-rdrop/checkpoint-400/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4741923
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb79b3cbce03f5020d0e6f215905ee96aba3ae887a18618564dada3b2bb5a7d9
|
| 3 |
size 4741923
|
graphcodebert-rdrop/checkpoint-400/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f14c596078dbcce9a0de4495a1f589a8de0bac9231ed72208ecb8d3c5ff798d9
|
| 3 |
size 14645
|
graphcodebert-rdrop/checkpoint-400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
|
| 3 |
+
size 1383
|
graphcodebert-rdrop/checkpoint-400/trainer_state.json
CHANGED
|
@@ -11,282 +11,282 @@
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.00064,
|
| 14 |
-
"grad_norm": 1.
|
| 15 |
"learning_rate": 3.840409643695328e-08,
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.00128,
|
| 21 |
-
"grad_norm": 1.
|
| 22 |
"learning_rate": 8.10753147002347e-08,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.00192,
|
| 28 |
-
"grad_norm":
|
| 29 |
"learning_rate": 1.2374653296351612e-07,
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.00256,
|
| 35 |
-
"grad_norm": 1.
|
| 36 |
"learning_rate": 1.6641775122679754e-07,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.0032,
|
| 42 |
-
"grad_norm": 1.
|
| 43 |
"learning_rate": 2.0908896949007894e-07,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.00384,
|
| 49 |
-
"grad_norm": 1.
|
| 50 |
"learning_rate": 2.517601877533604e-07,
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 60
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.00448,
|
| 56 |
-
"grad_norm": 1.
|
| 57 |
"learning_rate": 2.944314060166418e-07,
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.00512,
|
| 63 |
-
"grad_norm": 1.
|
| 64 |
"learning_rate": 3.371026242799232e-07,
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.00576,
|
| 70 |
-
"grad_norm":
|
| 71 |
"learning_rate": 3.7977384254320464e-07,
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 90
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.0064,
|
| 77 |
-
"grad_norm": 1.
|
| 78 |
"learning_rate": 4.22445060806486e-07,
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.00704,
|
| 84 |
-
"grad_norm":
|
| 85 |
"learning_rate": 4.651162790697675e-07,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 110
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.00768,
|
| 91 |
-
"grad_norm": 1.
|
| 92 |
"learning_rate": 5.077874973330489e-07,
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 120
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.00832,
|
| 98 |
-
"grad_norm": 1.
|
| 99 |
"learning_rate": 5.504587155963304e-07,
|
| 100 |
-
"loss": 0.
|
| 101 |
"step": 130
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.00896,
|
| 105 |
-
"grad_norm": 1.
|
| 106 |
"learning_rate": 5.931299338596117e-07,
|
| 107 |
-
"loss": 0.
|
| 108 |
"step": 140
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.0096,
|
| 112 |
-
"grad_norm":
|
| 113 |
"learning_rate": 6.358011521228932e-07,
|
| 114 |
-
"loss": 0.
|
| 115 |
"step": 150
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.01024,
|
| 119 |
-
"grad_norm":
|
| 120 |
"learning_rate": 6.784723703861745e-07,
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 160
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.01088,
|
| 126 |
-
"grad_norm": 1.
|
| 127 |
"learning_rate": 7.21143588649456e-07,
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 170
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.01152,
|
| 133 |
-
"grad_norm": 1.
|
| 134 |
"learning_rate": 7.638148069127374e-07,
|
| 135 |
-
"loss": 0.
|
| 136 |
"step": 180
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.01216,
|
| 140 |
-
"grad_norm": 1.
|
| 141 |
"learning_rate": 8.064860251760189e-07,
|
| 142 |
-
"loss": 0.
|
| 143 |
"step": 190
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.0128,
|
| 147 |
-
"grad_norm": 1.
|
| 148 |
"learning_rate": 8.491572434393003e-07,
|
| 149 |
-
"loss": 0.
|
| 150 |
"step": 200
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.01344,
|
| 154 |
-
"grad_norm": 1.
|
| 155 |
"learning_rate": 8.918284617025817e-07,
|
| 156 |
-
"loss": 0.
|
| 157 |
"step": 210
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.01408,
|
| 161 |
-
"grad_norm": 1.
|
| 162 |
"learning_rate": 9.344996799658632e-07,
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 220
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.01472,
|
| 168 |
-
"grad_norm": 1.
|
| 169 |
"learning_rate": 9.771708982291445e-07,
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 230
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.01536,
|
| 175 |
-
"grad_norm":
|
| 176 |
"learning_rate": 1.0198421164924258e-06,
|
| 177 |
-
"loss": 0.
|
| 178 |
"step": 240
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.016,
|
| 182 |
-
"grad_norm": 1.
|
| 183 |
"learning_rate": 1.0625133347557074e-06,
|
| 184 |
-
"loss": 0.
|
| 185 |
"step": 250
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 0.01664,
|
| 189 |
-
"grad_norm":
|
| 190 |
"learning_rate": 1.1051845530189888e-06,
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 260
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 0.01728,
|
| 196 |
-
"grad_norm": 1.
|
| 197 |
"learning_rate": 1.1478557712822702e-06,
|
| 198 |
-
"loss": 0.
|
| 199 |
"step": 270
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 0.01792,
|
| 203 |
-
"grad_norm": 1.
|
| 204 |
"learning_rate": 1.1905269895455517e-06,
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 280
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.01856,
|
| 210 |
-
"grad_norm": 1.
|
| 211 |
"learning_rate": 1.233198207808833e-06,
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 290
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.0192,
|
| 217 |
-
"grad_norm": 1.
|
| 218 |
"learning_rate": 1.2758694260721145e-06,
|
| 219 |
-
"loss": 0.
|
| 220 |
"step": 300
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 0.01984,
|
| 224 |
-
"grad_norm": 1.
|
| 225 |
"learning_rate": 1.318540644335396e-06,
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 310
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.02048,
|
| 231 |
-
"grad_norm": 1.
|
| 232 |
"learning_rate": 1.3612118625986772e-06,
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 320
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.02112,
|
| 238 |
-
"grad_norm": 1.
|
| 239 |
"learning_rate": 1.4038830808619588e-06,
|
| 240 |
-
"loss": 0.
|
| 241 |
"step": 330
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.02176,
|
| 245 |
-
"grad_norm": 1.
|
| 246 |
"learning_rate": 1.4465542991252401e-06,
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 340
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.0224,
|
| 252 |
-
"grad_norm": 2.
|
| 253 |
"learning_rate": 1.4892255173885215e-06,
|
| 254 |
-
"loss": 0.
|
| 255 |
"step": 350
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 0.02304,
|
| 259 |
-
"grad_norm": 1.
|
| 260 |
"learning_rate": 1.531896735651803e-06,
|
| 261 |
-
"loss": 0.
|
| 262 |
"step": 360
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 0.02368,
|
| 266 |
-
"grad_norm": 1.
|
| 267 |
"learning_rate": 1.5745679539150842e-06,
|
| 268 |
-
"loss": 0.
|
| 269 |
"step": 370
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 0.02432,
|
| 273 |
-
"grad_norm":
|
| 274 |
"learning_rate": 1.6172391721783658e-06,
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 380
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 0.02496,
|
| 280 |
-
"grad_norm": 1.
|
| 281 |
"learning_rate": 1.6599103904416472e-06,
|
| 282 |
-
"loss": 0.
|
| 283 |
"step": 390
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 0.0256,
|
| 287 |
-
"grad_norm": 1.
|
| 288 |
"learning_rate": 1.7025816087049288e-06,
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 400
|
| 291 |
}
|
| 292 |
],
|
|
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.00064,
|
| 14 |
+
"grad_norm": 1.8688431978225708,
|
| 15 |
"learning_rate": 3.840409643695328e-08,
|
| 16 |
+
"loss": 0.7168,
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.00128,
|
| 21 |
+
"grad_norm": 1.835353970527649,
|
| 22 |
"learning_rate": 8.10753147002347e-08,
|
| 23 |
+
"loss": 0.7179,
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.00192,
|
| 28 |
+
"grad_norm": 1.2541388273239136,
|
| 29 |
"learning_rate": 1.2374653296351612e-07,
|
| 30 |
+
"loss": 0.7177,
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.00256,
|
| 35 |
+
"grad_norm": 1.1381633281707764,
|
| 36 |
"learning_rate": 1.6641775122679754e-07,
|
| 37 |
+
"loss": 0.7312,
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.0032,
|
| 42 |
+
"grad_norm": 1.6313824653625488,
|
| 43 |
"learning_rate": 2.0908896949007894e-07,
|
| 44 |
+
"loss": 0.7167,
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.00384,
|
| 49 |
+
"grad_norm": 1.092464566230774,
|
| 50 |
"learning_rate": 2.517601877533604e-07,
|
| 51 |
+
"loss": 0.7201,
|
| 52 |
"step": 60
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.00448,
|
| 56 |
+
"grad_norm": 1.164099097251892,
|
| 57 |
"learning_rate": 2.944314060166418e-07,
|
| 58 |
+
"loss": 0.7195,
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.00512,
|
| 63 |
+
"grad_norm": 1.9283920526504517,
|
| 64 |
"learning_rate": 3.371026242799232e-07,
|
| 65 |
+
"loss": 0.7223,
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.00576,
|
| 70 |
+
"grad_norm": 1.8716129064559937,
|
| 71 |
"learning_rate": 3.7977384254320464e-07,
|
| 72 |
+
"loss": 0.7151,
|
| 73 |
"step": 90
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.0064,
|
| 77 |
+
"grad_norm": 1.5499262809753418,
|
| 78 |
"learning_rate": 4.22445060806486e-07,
|
| 79 |
+
"loss": 0.7211,
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.00704,
|
| 84 |
+
"grad_norm": 1.375114917755127,
|
| 85 |
"learning_rate": 4.651162790697675e-07,
|
| 86 |
+
"loss": 0.7247,
|
| 87 |
"step": 110
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.00768,
|
| 91 |
+
"grad_norm": 1.384915828704834,
|
| 92 |
"learning_rate": 5.077874973330489e-07,
|
| 93 |
+
"loss": 0.7156,
|
| 94 |
"step": 120
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.00832,
|
| 98 |
+
"grad_norm": 1.6376659870147705,
|
| 99 |
"learning_rate": 5.504587155963304e-07,
|
| 100 |
+
"loss": 0.7196,
|
| 101 |
"step": 130
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.00896,
|
| 105 |
+
"grad_norm": 1.709489345550537,
|
| 106 |
"learning_rate": 5.931299338596117e-07,
|
| 107 |
+
"loss": 0.7215,
|
| 108 |
"step": 140
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.0096,
|
| 112 |
+
"grad_norm": 1.350512146949768,
|
| 113 |
"learning_rate": 6.358011521228932e-07,
|
| 114 |
+
"loss": 0.71,
|
| 115 |
"step": 150
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.01024,
|
| 119 |
+
"grad_norm": 2.33050537109375,
|
| 120 |
"learning_rate": 6.784723703861745e-07,
|
| 121 |
+
"loss": 0.7191,
|
| 122 |
"step": 160
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.01088,
|
| 126 |
+
"grad_norm": 1.0042874813079834,
|
| 127 |
"learning_rate": 7.21143588649456e-07,
|
| 128 |
+
"loss": 0.72,
|
| 129 |
"step": 170
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.01152,
|
| 133 |
+
"grad_norm": 1.1835744380950928,
|
| 134 |
"learning_rate": 7.638148069127374e-07,
|
| 135 |
+
"loss": 0.7122,
|
| 136 |
"step": 180
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.01216,
|
| 140 |
+
"grad_norm": 1.949506402015686,
|
| 141 |
"learning_rate": 8.064860251760189e-07,
|
| 142 |
+
"loss": 0.7091,
|
| 143 |
"step": 190
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.0128,
|
| 147 |
+
"grad_norm": 1.139626383781433,
|
| 148 |
"learning_rate": 8.491572434393003e-07,
|
| 149 |
+
"loss": 0.7046,
|
| 150 |
"step": 200
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.01344,
|
| 154 |
+
"grad_norm": 1.7734779119491577,
|
| 155 |
"learning_rate": 8.918284617025817e-07,
|
| 156 |
+
"loss": 0.7135,
|
| 157 |
"step": 210
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.01408,
|
| 161 |
+
"grad_norm": 1.3442974090576172,
|
| 162 |
"learning_rate": 9.344996799658632e-07,
|
| 163 |
+
"loss": 0.7127,
|
| 164 |
"step": 220
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.01472,
|
| 168 |
+
"grad_norm": 1.6148335933685303,
|
| 169 |
"learning_rate": 9.771708982291445e-07,
|
| 170 |
+
"loss": 0.7168,
|
| 171 |
"step": 230
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.01536,
|
| 175 |
+
"grad_norm": 0.9220213294029236,
|
| 176 |
"learning_rate": 1.0198421164924258e-06,
|
| 177 |
+
"loss": 0.7109,
|
| 178 |
"step": 240
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.016,
|
| 182 |
+
"grad_norm": 1.5631815195083618,
|
| 183 |
"learning_rate": 1.0625133347557074e-06,
|
| 184 |
+
"loss": 0.7149,
|
| 185 |
"step": 250
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 0.01664,
|
| 189 |
+
"grad_norm": 1.5052822828292847,
|
| 190 |
"learning_rate": 1.1051845530189888e-06,
|
| 191 |
+
"loss": 0.7112,
|
| 192 |
"step": 260
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 0.01728,
|
| 196 |
+
"grad_norm": 1.6714903116226196,
|
| 197 |
"learning_rate": 1.1478557712822702e-06,
|
| 198 |
+
"loss": 0.7128,
|
| 199 |
"step": 270
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 0.01792,
|
| 203 |
+
"grad_norm": 1.6667262315750122,
|
| 204 |
"learning_rate": 1.1905269895455517e-06,
|
| 205 |
+
"loss": 0.7091,
|
| 206 |
"step": 280
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.01856,
|
| 210 |
+
"grad_norm": 1.6861907243728638,
|
| 211 |
"learning_rate": 1.233198207808833e-06,
|
| 212 |
+
"loss": 0.7078,
|
| 213 |
"step": 290
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.0192,
|
| 217 |
+
"grad_norm": 1.6259212493896484,
|
| 218 |
"learning_rate": 1.2758694260721145e-06,
|
| 219 |
+
"loss": 0.7087,
|
| 220 |
"step": 300
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 0.01984,
|
| 224 |
+
"grad_norm": 1.207320213317871,
|
| 225 |
"learning_rate": 1.318540644335396e-06,
|
| 226 |
+
"loss": 0.7087,
|
| 227 |
"step": 310
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.02048,
|
| 231 |
+
"grad_norm": 1.087124228477478,
|
| 232 |
"learning_rate": 1.3612118625986772e-06,
|
| 233 |
+
"loss": 0.7174,
|
| 234 |
"step": 320
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.02112,
|
| 238 |
+
"grad_norm": 1.5668721199035645,
|
| 239 |
"learning_rate": 1.4038830808619588e-06,
|
| 240 |
+
"loss": 0.7066,
|
| 241 |
"step": 330
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.02176,
|
| 245 |
+
"grad_norm": 1.5332859754562378,
|
| 246 |
"learning_rate": 1.4465542991252401e-06,
|
| 247 |
+
"loss": 0.7115,
|
| 248 |
"step": 340
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.0224,
|
| 252 |
+
"grad_norm": 2.092994451522827,
|
| 253 |
"learning_rate": 1.4892255173885215e-06,
|
| 254 |
+
"loss": 0.7085,
|
| 255 |
"step": 350
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 0.02304,
|
| 259 |
+
"grad_norm": 1.266851544380188,
|
| 260 |
"learning_rate": 1.531896735651803e-06,
|
| 261 |
+
"loss": 0.7091,
|
| 262 |
"step": 360
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 0.02368,
|
| 266 |
+
"grad_norm": 1.290616512298584,
|
| 267 |
"learning_rate": 1.5745679539150842e-06,
|
| 268 |
+
"loss": 0.7103,
|
| 269 |
"step": 370
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 0.02432,
|
| 273 |
+
"grad_norm": 1.2045000791549683,
|
| 274 |
"learning_rate": 1.6172391721783658e-06,
|
| 275 |
+
"loss": 0.705,
|
| 276 |
"step": 380
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 0.02496,
|
| 280 |
+
"grad_norm": 1.828832983970642,
|
| 281 |
"learning_rate": 1.6599103904416472e-06,
|
| 282 |
+
"loss": 0.7038,
|
| 283 |
"step": 390
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 0.0256,
|
| 287 |
+
"grad_norm": 1.7793196439743042,
|
| 288 |
"learning_rate": 1.7025816087049288e-06,
|
| 289 |
+
"loss": 0.7085,
|
| 290 |
"step": 400
|
| 291 |
}
|
| 292 |
],
|
graphcodebert-rdrop/checkpoint-400/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7cd390fef915efa37cfafbe6f2d5d365158faf1073058ef1c9ea09cda16a6a5
|
| 3 |
size 5841
|
graphcodebert-rdrop/checkpoint-600/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498612824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ea40da64ace017a3d50a5cdf20ef1bd619a8a7d5fcf4cdfe4673fd73b16598d
|
| 3 |
size 498612824
|
graphcodebert-rdrop/checkpoint-600/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4741923
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f39cd5d8d518892a6b1e06b53d57c464f4de0ca67339a27037e7e19879adf854
|
| 3 |
size 4741923
|
graphcodebert-rdrop/checkpoint-600/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86fc3427fb7e9d84ae47e638462150316077e8b19961d87422e2bfcc3d1beab3
|
| 3 |
size 14645
|
graphcodebert-rdrop/checkpoint-600/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb7fde5111803012042c93a73aa191336bb6e10b3ad44f6bd1d94fc7008a22b6
|
| 3 |
+
size 1383
|
graphcodebert-rdrop/checkpoint-600/trainer_state.json
CHANGED
|
@@ -11,422 +11,422 @@
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.00064,
|
| 14 |
-
"grad_norm": 1.
|
| 15 |
"learning_rate": 3.840409643695328e-08,
|
| 16 |
-
"loss": 0.
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.00128,
|
| 21 |
-
"grad_norm": 1.
|
| 22 |
"learning_rate": 8.10753147002347e-08,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.00192,
|
| 28 |
-
"grad_norm":
|
| 29 |
"learning_rate": 1.2374653296351612e-07,
|
| 30 |
-
"loss": 0.
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.00256,
|
| 35 |
-
"grad_norm": 1.
|
| 36 |
"learning_rate": 1.6641775122679754e-07,
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.0032,
|
| 42 |
-
"grad_norm": 1.
|
| 43 |
"learning_rate": 2.0908896949007894e-07,
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.00384,
|
| 49 |
-
"grad_norm": 1.
|
| 50 |
"learning_rate": 2.517601877533604e-07,
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 60
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.00448,
|
| 56 |
-
"grad_norm": 1.
|
| 57 |
"learning_rate": 2.944314060166418e-07,
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.00512,
|
| 63 |
-
"grad_norm": 1.
|
| 64 |
"learning_rate": 3.371026242799232e-07,
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.00576,
|
| 70 |
-
"grad_norm":
|
| 71 |
"learning_rate": 3.7977384254320464e-07,
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 90
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.0064,
|
| 77 |
-
"grad_norm": 1.
|
| 78 |
"learning_rate": 4.22445060806486e-07,
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.00704,
|
| 84 |
-
"grad_norm":
|
| 85 |
"learning_rate": 4.651162790697675e-07,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 110
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.00768,
|
| 91 |
-
"grad_norm": 1.
|
| 92 |
"learning_rate": 5.077874973330489e-07,
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 120
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.00832,
|
| 98 |
-
"grad_norm": 1.
|
| 99 |
"learning_rate": 5.504587155963304e-07,
|
| 100 |
-
"loss": 0.
|
| 101 |
"step": 130
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.00896,
|
| 105 |
-
"grad_norm": 1.
|
| 106 |
"learning_rate": 5.931299338596117e-07,
|
| 107 |
-
"loss": 0.
|
| 108 |
"step": 140
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.0096,
|
| 112 |
-
"grad_norm":
|
| 113 |
"learning_rate": 6.358011521228932e-07,
|
| 114 |
-
"loss": 0.
|
| 115 |
"step": 150
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.01024,
|
| 119 |
-
"grad_norm":
|
| 120 |
"learning_rate": 6.784723703861745e-07,
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 160
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.01088,
|
| 126 |
-
"grad_norm": 1.
|
| 127 |
"learning_rate": 7.21143588649456e-07,
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 170
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.01152,
|
| 133 |
-
"grad_norm": 1.
|
| 134 |
"learning_rate": 7.638148069127374e-07,
|
| 135 |
-
"loss": 0.
|
| 136 |
"step": 180
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.01216,
|
| 140 |
-
"grad_norm": 1.
|
| 141 |
"learning_rate": 8.064860251760189e-07,
|
| 142 |
-
"loss": 0.
|
| 143 |
"step": 190
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.0128,
|
| 147 |
-
"grad_norm": 1.
|
| 148 |
"learning_rate": 8.491572434393003e-07,
|
| 149 |
-
"loss": 0.
|
| 150 |
"step": 200
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.01344,
|
| 154 |
-
"grad_norm": 1.
|
| 155 |
"learning_rate": 8.918284617025817e-07,
|
| 156 |
-
"loss": 0.
|
| 157 |
"step": 210
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.01408,
|
| 161 |
-
"grad_norm": 1.
|
| 162 |
"learning_rate": 9.344996799658632e-07,
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 220
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.01472,
|
| 168 |
-
"grad_norm": 1.
|
| 169 |
"learning_rate": 9.771708982291445e-07,
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 230
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.01536,
|
| 175 |
-
"grad_norm":
|
| 176 |
"learning_rate": 1.0198421164924258e-06,
|
| 177 |
-
"loss": 0.
|
| 178 |
"step": 240
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.016,
|
| 182 |
-
"grad_norm": 1.
|
| 183 |
"learning_rate": 1.0625133347557074e-06,
|
| 184 |
-
"loss": 0.
|
| 185 |
"step": 250
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 0.01664,
|
| 189 |
-
"grad_norm":
|
| 190 |
"learning_rate": 1.1051845530189888e-06,
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 260
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 0.01728,
|
| 196 |
-
"grad_norm": 1.
|
| 197 |
"learning_rate": 1.1478557712822702e-06,
|
| 198 |
-
"loss": 0.
|
| 199 |
"step": 270
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 0.01792,
|
| 203 |
-
"grad_norm": 1.
|
| 204 |
"learning_rate": 1.1905269895455517e-06,
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 280
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.01856,
|
| 210 |
-
"grad_norm": 1.
|
| 211 |
"learning_rate": 1.233198207808833e-06,
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 290
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.0192,
|
| 217 |
-
"grad_norm": 1.
|
| 218 |
"learning_rate": 1.2758694260721145e-06,
|
| 219 |
-
"loss": 0.
|
| 220 |
"step": 300
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 0.01984,
|
| 224 |
-
"grad_norm": 1.
|
| 225 |
"learning_rate": 1.318540644335396e-06,
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 310
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.02048,
|
| 231 |
-
"grad_norm": 1.
|
| 232 |
"learning_rate": 1.3612118625986772e-06,
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 320
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.02112,
|
| 238 |
-
"grad_norm": 1.
|
| 239 |
"learning_rate": 1.4038830808619588e-06,
|
| 240 |
-
"loss": 0.
|
| 241 |
"step": 330
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.02176,
|
| 245 |
-
"grad_norm": 1.
|
| 246 |
"learning_rate": 1.4465542991252401e-06,
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 340
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.0224,
|
| 252 |
-
"grad_norm": 2.
|
| 253 |
"learning_rate": 1.4892255173885215e-06,
|
| 254 |
-
"loss": 0.
|
| 255 |
"step": 350
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 0.02304,
|
| 259 |
-
"grad_norm": 1.
|
| 260 |
"learning_rate": 1.531896735651803e-06,
|
| 261 |
-
"loss": 0.
|
| 262 |
"step": 360
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 0.02368,
|
| 266 |
-
"grad_norm": 1.
|
| 267 |
"learning_rate": 1.5745679539150842e-06,
|
| 268 |
-
"loss": 0.
|
| 269 |
"step": 370
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 0.02432,
|
| 273 |
-
"grad_norm":
|
| 274 |
"learning_rate": 1.6172391721783658e-06,
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 380
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 0.02496,
|
| 280 |
-
"grad_norm": 1.
|
| 281 |
"learning_rate": 1.6599103904416472e-06,
|
| 282 |
-
"loss": 0.
|
| 283 |
"step": 390
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 0.0256,
|
| 287 |
-
"grad_norm": 1.
|
| 288 |
"learning_rate": 1.7025816087049288e-06,
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 400
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.02624,
|
| 294 |
-
"grad_norm":
|
| 295 |
"learning_rate": 1.7452528269682101e-06,
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 410
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.02688,
|
| 301 |
-
"grad_norm": 1.
|
| 302 |
"learning_rate": 1.7879240452314913e-06,
|
| 303 |
-
"loss": 0.
|
| 304 |
"step": 420
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 0.02752,
|
| 308 |
-
"grad_norm": 1.
|
| 309 |
"learning_rate": 1.8305952634947729e-06,
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 430
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 0.02816,
|
| 315 |
-
"grad_norm": 1.
|
| 316 |
"learning_rate": 1.8732664817580542e-06,
|
| 317 |
-
"loss": 0.
|
| 318 |
"step": 440
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 0.0288,
|
| 322 |
-
"grad_norm": 1.
|
| 323 |
"learning_rate": 1.915937700021336e-06,
|
| 324 |
-
"loss": 0.
|
| 325 |
"step": 450
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 0.02944,
|
| 329 |
-
"grad_norm":
|
| 330 |
"learning_rate": 1.958608918284617e-06,
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 460
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 0.03008,
|
| 336 |
-
"grad_norm": 1.
|
| 337 |
"learning_rate": 2.0012801365478988e-06,
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 470
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.03072,
|
| 343 |
-
"grad_norm": 1.
|
| 344 |
"learning_rate": 2.04395135481118e-06,
|
| 345 |
-
"loss": 0.
|
| 346 |
"step": 480
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 0.03136,
|
| 350 |
-
"grad_norm": 1.
|
| 351 |
"learning_rate": 2.0866225730744615e-06,
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 490
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 0.032,
|
| 357 |
-
"grad_norm":
|
| 358 |
"learning_rate": 2.129293791337743e-06,
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 0.03264,
|
| 364 |
-
"grad_norm": 1.
|
| 365 |
"learning_rate": 2.1719650096010242e-06,
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 510
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 0.03328,
|
| 371 |
-
"grad_norm":
|
| 372 |
"learning_rate": 2.214636227864306e-06,
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 520
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 0.03392,
|
| 378 |
-
"grad_norm": 1.
|
| 379 |
"learning_rate": 2.257307446127587e-06,
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 530
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.03456,
|
| 385 |
-
"grad_norm":
|
| 386 |
"learning_rate": 2.2999786643908685e-06,
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 540
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 0.0352,
|
| 392 |
-
"grad_norm": 1.
|
| 393 |
"learning_rate": 2.34264988265415e-06,
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 550
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 0.03584,
|
| 399 |
-
"grad_norm": 1.
|
| 400 |
"learning_rate": 2.3853211009174317e-06,
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 560
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 0.03648,
|
| 406 |
-
"grad_norm": 1.
|
| 407 |
"learning_rate": 2.427992319180713e-06,
|
| 408 |
-
"loss": 0.
|
| 409 |
"step": 570
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 0.03712,
|
| 413 |
-
"grad_norm": 0.
|
| 414 |
"learning_rate": 2.470663537443994e-06,
|
| 415 |
-
"loss": 0.
|
| 416 |
"step": 580
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 0.03776,
|
| 420 |
-
"grad_norm":
|
| 421 |
"learning_rate": 2.5133347557072756e-06,
|
| 422 |
-
"loss": 0.
|
| 423 |
"step": 590
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 0.0384,
|
| 427 |
-
"grad_norm": 1.
|
| 428 |
"learning_rate": 2.556005973970557e-06,
|
| 429 |
-
"loss": 0.
|
| 430 |
"step": 600
|
| 431 |
}
|
| 432 |
],
|
|
|
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.00064,
|
| 14 |
+
"grad_norm": 1.8688431978225708,
|
| 15 |
"learning_rate": 3.840409643695328e-08,
|
| 16 |
+
"loss": 0.7168,
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.00128,
|
| 21 |
+
"grad_norm": 1.835353970527649,
|
| 22 |
"learning_rate": 8.10753147002347e-08,
|
| 23 |
+
"loss": 0.7179,
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.00192,
|
| 28 |
+
"grad_norm": 1.2541388273239136,
|
| 29 |
"learning_rate": 1.2374653296351612e-07,
|
| 30 |
+
"loss": 0.7177,
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.00256,
|
| 35 |
+
"grad_norm": 1.1381633281707764,
|
| 36 |
"learning_rate": 1.6641775122679754e-07,
|
| 37 |
+
"loss": 0.7312,
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.0032,
|
| 42 |
+
"grad_norm": 1.6313824653625488,
|
| 43 |
"learning_rate": 2.0908896949007894e-07,
|
| 44 |
+
"loss": 0.7167,
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.00384,
|
| 49 |
+
"grad_norm": 1.092464566230774,
|
| 50 |
"learning_rate": 2.517601877533604e-07,
|
| 51 |
+
"loss": 0.7201,
|
| 52 |
"step": 60
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.00448,
|
| 56 |
+
"grad_norm": 1.164099097251892,
|
| 57 |
"learning_rate": 2.944314060166418e-07,
|
| 58 |
+
"loss": 0.7195,
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.00512,
|
| 63 |
+
"grad_norm": 1.9283920526504517,
|
| 64 |
"learning_rate": 3.371026242799232e-07,
|
| 65 |
+
"loss": 0.7223,
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.00576,
|
| 70 |
+
"grad_norm": 1.8716129064559937,
|
| 71 |
"learning_rate": 3.7977384254320464e-07,
|
| 72 |
+
"loss": 0.7151,
|
| 73 |
"step": 90
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.0064,
|
| 77 |
+
"grad_norm": 1.5499262809753418,
|
| 78 |
"learning_rate": 4.22445060806486e-07,
|
| 79 |
+
"loss": 0.7211,
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.00704,
|
| 84 |
+
"grad_norm": 1.375114917755127,
|
| 85 |
"learning_rate": 4.651162790697675e-07,
|
| 86 |
+
"loss": 0.7247,
|
| 87 |
"step": 110
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.00768,
|
| 91 |
+
"grad_norm": 1.384915828704834,
|
| 92 |
"learning_rate": 5.077874973330489e-07,
|
| 93 |
+
"loss": 0.7156,
|
| 94 |
"step": 120
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 0.00832,
|
| 98 |
+
"grad_norm": 1.6376659870147705,
|
| 99 |
"learning_rate": 5.504587155963304e-07,
|
| 100 |
+
"loss": 0.7196,
|
| 101 |
"step": 130
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 0.00896,
|
| 105 |
+
"grad_norm": 1.709489345550537,
|
| 106 |
"learning_rate": 5.931299338596117e-07,
|
| 107 |
+
"loss": 0.7215,
|
| 108 |
"step": 140
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.0096,
|
| 112 |
+
"grad_norm": 1.350512146949768,
|
| 113 |
"learning_rate": 6.358011521228932e-07,
|
| 114 |
+
"loss": 0.71,
|
| 115 |
"step": 150
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 0.01024,
|
| 119 |
+
"grad_norm": 2.33050537109375,
|
| 120 |
"learning_rate": 6.784723703861745e-07,
|
| 121 |
+
"loss": 0.7191,
|
| 122 |
"step": 160
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.01088,
|
| 126 |
+
"grad_norm": 1.0042874813079834,
|
| 127 |
"learning_rate": 7.21143588649456e-07,
|
| 128 |
+
"loss": 0.72,
|
| 129 |
"step": 170
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.01152,
|
| 133 |
+
"grad_norm": 1.1835744380950928,
|
| 134 |
"learning_rate": 7.638148069127374e-07,
|
| 135 |
+
"loss": 0.7122,
|
| 136 |
"step": 180
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 0.01216,
|
| 140 |
+
"grad_norm": 1.949506402015686,
|
| 141 |
"learning_rate": 8.064860251760189e-07,
|
| 142 |
+
"loss": 0.7091,
|
| 143 |
"step": 190
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 0.0128,
|
| 147 |
+
"grad_norm": 1.139626383781433,
|
| 148 |
"learning_rate": 8.491572434393003e-07,
|
| 149 |
+
"loss": 0.7046,
|
| 150 |
"step": 200
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 0.01344,
|
| 154 |
+
"grad_norm": 1.7734779119491577,
|
| 155 |
"learning_rate": 8.918284617025817e-07,
|
| 156 |
+
"loss": 0.7135,
|
| 157 |
"step": 210
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 0.01408,
|
| 161 |
+
"grad_norm": 1.3442974090576172,
|
| 162 |
"learning_rate": 9.344996799658632e-07,
|
| 163 |
+
"loss": 0.7127,
|
| 164 |
"step": 220
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.01472,
|
| 168 |
+
"grad_norm": 1.6148335933685303,
|
| 169 |
"learning_rate": 9.771708982291445e-07,
|
| 170 |
+
"loss": 0.7168,
|
| 171 |
"step": 230
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.01536,
|
| 175 |
+
"grad_norm": 0.9220213294029236,
|
| 176 |
"learning_rate": 1.0198421164924258e-06,
|
| 177 |
+
"loss": 0.7109,
|
| 178 |
"step": 240
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 0.016,
|
| 182 |
+
"grad_norm": 1.5631815195083618,
|
| 183 |
"learning_rate": 1.0625133347557074e-06,
|
| 184 |
+
"loss": 0.7149,
|
| 185 |
"step": 250
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 0.01664,
|
| 189 |
+
"grad_norm": 1.5052822828292847,
|
| 190 |
"learning_rate": 1.1051845530189888e-06,
|
| 191 |
+
"loss": 0.7112,
|
| 192 |
"step": 260
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 0.01728,
|
| 196 |
+
"grad_norm": 1.6714903116226196,
|
| 197 |
"learning_rate": 1.1478557712822702e-06,
|
| 198 |
+
"loss": 0.7128,
|
| 199 |
"step": 270
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 0.01792,
|
| 203 |
+
"grad_norm": 1.6667262315750122,
|
| 204 |
"learning_rate": 1.1905269895455517e-06,
|
| 205 |
+
"loss": 0.7091,
|
| 206 |
"step": 280
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.01856,
|
| 210 |
+
"grad_norm": 1.6861907243728638,
|
| 211 |
"learning_rate": 1.233198207808833e-06,
|
| 212 |
+
"loss": 0.7078,
|
| 213 |
"step": 290
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.0192,
|
| 217 |
+
"grad_norm": 1.6259212493896484,
|
| 218 |
"learning_rate": 1.2758694260721145e-06,
|
| 219 |
+
"loss": 0.7087,
|
| 220 |
"step": 300
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 0.01984,
|
| 224 |
+
"grad_norm": 1.207320213317871,
|
| 225 |
"learning_rate": 1.318540644335396e-06,
|
| 226 |
+
"loss": 0.7087,
|
| 227 |
"step": 310
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 0.02048,
|
| 231 |
+
"grad_norm": 1.087124228477478,
|
| 232 |
"learning_rate": 1.3612118625986772e-06,
|
| 233 |
+
"loss": 0.7174,
|
| 234 |
"step": 320
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 0.02112,
|
| 238 |
+
"grad_norm": 1.5668721199035645,
|
| 239 |
"learning_rate": 1.4038830808619588e-06,
|
| 240 |
+
"loss": 0.7066,
|
| 241 |
"step": 330
|
| 242 |
},
|
| 243 |
{
|
| 244 |
"epoch": 0.02176,
|
| 245 |
+
"grad_norm": 1.5332859754562378,
|
| 246 |
"learning_rate": 1.4465542991252401e-06,
|
| 247 |
+
"loss": 0.7115,
|
| 248 |
"step": 340
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.0224,
|
| 252 |
+
"grad_norm": 2.092994451522827,
|
| 253 |
"learning_rate": 1.4892255173885215e-06,
|
| 254 |
+
"loss": 0.7085,
|
| 255 |
"step": 350
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 0.02304,
|
| 259 |
+
"grad_norm": 1.266851544380188,
|
| 260 |
"learning_rate": 1.531896735651803e-06,
|
| 261 |
+
"loss": 0.7091,
|
| 262 |
"step": 360
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 0.02368,
|
| 266 |
+
"grad_norm": 1.290616512298584,
|
| 267 |
"learning_rate": 1.5745679539150842e-06,
|
| 268 |
+
"loss": 0.7103,
|
| 269 |
"step": 370
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 0.02432,
|
| 273 |
+
"grad_norm": 1.2045000791549683,
|
| 274 |
"learning_rate": 1.6172391721783658e-06,
|
| 275 |
+
"loss": 0.705,
|
| 276 |
"step": 380
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 0.02496,
|
| 280 |
+
"grad_norm": 1.828832983970642,
|
| 281 |
"learning_rate": 1.6599103904416472e-06,
|
| 282 |
+
"loss": 0.7038,
|
| 283 |
"step": 390
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 0.0256,
|
| 287 |
+
"grad_norm": 1.7793196439743042,
|
| 288 |
"learning_rate": 1.7025816087049288e-06,
|
| 289 |
+
"loss": 0.7085,
|
| 290 |
"step": 400
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.02624,
|
| 294 |
+
"grad_norm": 0.8949472904205322,
|
| 295 |
"learning_rate": 1.7452528269682101e-06,
|
| 296 |
+
"loss": 0.7045,
|
| 297 |
"step": 410
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.02688,
|
| 301 |
+
"grad_norm": 1.3071945905685425,
|
| 302 |
"learning_rate": 1.7879240452314913e-06,
|
| 303 |
+
"loss": 0.702,
|
| 304 |
"step": 420
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 0.02752,
|
| 308 |
+
"grad_norm": 1.7497148513793945,
|
| 309 |
"learning_rate": 1.8305952634947729e-06,
|
| 310 |
+
"loss": 0.7073,
|
| 311 |
"step": 430
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 0.02816,
|
| 315 |
+
"grad_norm": 1.0856297016143799,
|
| 316 |
"learning_rate": 1.8732664817580542e-06,
|
| 317 |
+
"loss": 0.7008,
|
| 318 |
"step": 440
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 0.0288,
|
| 322 |
+
"grad_norm": 1.369019627571106,
|
| 323 |
"learning_rate": 1.915937700021336e-06,
|
| 324 |
+
"loss": 0.7059,
|
| 325 |
"step": 450
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 0.02944,
|
| 329 |
+
"grad_norm": 2.0961010456085205,
|
| 330 |
"learning_rate": 1.958608918284617e-06,
|
| 331 |
+
"loss": 0.6952,
|
| 332 |
"step": 460
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 0.03008,
|
| 336 |
+
"grad_norm": 1.6076347827911377,
|
| 337 |
"learning_rate": 2.0012801365478988e-06,
|
| 338 |
+
"loss": 0.7074,
|
| 339 |
"step": 470
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.03072,
|
| 343 |
+
"grad_norm": 1.3129311800003052,
|
| 344 |
"learning_rate": 2.04395135481118e-06,
|
| 345 |
+
"loss": 0.6994,
|
| 346 |
"step": 480
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 0.03136,
|
| 350 |
+
"grad_norm": 1.3621476888656616,
|
| 351 |
"learning_rate": 2.0866225730744615e-06,
|
| 352 |
+
"loss": 0.696,
|
| 353 |
"step": 490
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 0.032,
|
| 357 |
+
"grad_norm": 0.9786806106567383,
|
| 358 |
"learning_rate": 2.129293791337743e-06,
|
| 359 |
+
"loss": 0.7011,
|
| 360 |
"step": 500
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 0.03264,
|
| 364 |
+
"grad_norm": 1.4611176252365112,
|
| 365 |
"learning_rate": 2.1719650096010242e-06,
|
| 366 |
+
"loss": 0.699,
|
| 367 |
"step": 510
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 0.03328,
|
| 371 |
+
"grad_norm": 1.0675945281982422,
|
| 372 |
"learning_rate": 2.214636227864306e-06,
|
| 373 |
+
"loss": 0.6906,
|
| 374 |
"step": 520
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 0.03392,
|
| 378 |
+
"grad_norm": 1.6564017534255981,
|
| 379 |
"learning_rate": 2.257307446127587e-06,
|
| 380 |
+
"loss": 0.6923,
|
| 381 |
"step": 530
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 0.03456,
|
| 385 |
+
"grad_norm": 1.228119134902954,
|
| 386 |
"learning_rate": 2.2999786643908685e-06,
|
| 387 |
+
"loss": 0.6928,
|
| 388 |
"step": 540
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 0.0352,
|
| 392 |
+
"grad_norm": 1.9868593215942383,
|
| 393 |
"learning_rate": 2.34264988265415e-06,
|
| 394 |
+
"loss": 0.6912,
|
| 395 |
"step": 550
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 0.03584,
|
| 399 |
+
"grad_norm": 1.2531176805496216,
|
| 400 |
"learning_rate": 2.3853211009174317e-06,
|
| 401 |
+
"loss": 0.6923,
|
| 402 |
"step": 560
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 0.03648,
|
| 406 |
+
"grad_norm": 1.413602352142334,
|
| 407 |
"learning_rate": 2.427992319180713e-06,
|
| 408 |
+
"loss": 0.6993,
|
| 409 |
"step": 570
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 0.03712,
|
| 413 |
+
"grad_norm": 0.9655390977859497,
|
| 414 |
"learning_rate": 2.470663537443994e-06,
|
| 415 |
+
"loss": 0.7017,
|
| 416 |
"step": 580
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 0.03776,
|
| 420 |
+
"grad_norm": 1.962438941001892,
|
| 421 |
"learning_rate": 2.5133347557072756e-06,
|
| 422 |
+
"loss": 0.6933,
|
| 423 |
"step": 590
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 0.0384,
|
| 427 |
+
"grad_norm": 1.1099931001663208,
|
| 428 |
"learning_rate": 2.556005973970557e-06,
|
| 429 |
+
"loss": 0.6925,
|
| 430 |
"step": 600
|
| 431 |
}
|
| 432 |
],
|
graphcodebert-rdrop/checkpoint-600/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7cd390fef915efa37cfafbe6f2d5d365158faf1073058ef1c9ea09cda16a6a5
|
| 3 |
size 5841
|
graphcodebert-rdrop/checkpoint-800/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.2,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.2,
|
| 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 |
+
"transformers_version": "4.56.0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
graphcodebert-rdrop/checkpoint-800/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-rdrop/checkpoint-800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afab3d94bfe70f623cdf701d99f312bbd58e0df8a0424e3580373df46f964316
|
| 3 |
+
size 498612824
|
graphcodebert-rdrop/checkpoint-800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d3071ac1938039923cc4c0bd29f47bc8df5565b8ede7c7f146ce8b8049869ef
|
| 3 |
+
size 4741923
|
graphcodebert-rdrop/checkpoint-800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7f8420efd4033f2ee4b17a98ec6a1891ac23eab5039ea351d9587c7e33ce451
|
| 3 |
+
size 14645
|
graphcodebert-rdrop/checkpoint-800/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fef122931c86c2d2736773be787da21ac6460d41580735381e953556fb410be
|
| 3 |
+
size 1383
|
graphcodebert-rdrop/checkpoint-800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d272d19c634ee5c96583d515235f93fa1e9a1d0cbafcfc383818e21b41c8c444
|
| 3 |
+
size 1465
|
graphcodebert-rdrop/checkpoint-800/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-rdrop/checkpoint-800/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
graphcodebert-rdrop/checkpoint-800/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-rdrop/checkpoint-800/trainer_state.json
ADDED
|
@@ -0,0 +1,603 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0512,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00064,
|
| 14 |
+
"grad_norm": 1.8688431978225708,
|
| 15 |
+
"learning_rate": 3.840409643695328e-08,
|
| 16 |
+
"loss": 0.7168,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00128,
|
| 21 |
+
"grad_norm": 1.835353970527649,
|
| 22 |
+
"learning_rate": 8.10753147002347e-08,
|
| 23 |
+
"loss": 0.7179,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.00192,
|
| 28 |
+
"grad_norm": 1.2541388273239136,
|
| 29 |
+
"learning_rate": 1.2374653296351612e-07,
|
| 30 |
+
"loss": 0.7177,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.00256,
|
| 35 |
+
"grad_norm": 1.1381633281707764,
|
| 36 |
+
"learning_rate": 1.6641775122679754e-07,
|
| 37 |
+
"loss": 0.7312,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0032,
|
| 42 |
+
"grad_norm": 1.6313824653625488,
|
| 43 |
+
"learning_rate": 2.0908896949007894e-07,
|
| 44 |
+
"loss": 0.7167,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.00384,
|
| 49 |
+
"grad_norm": 1.092464566230774,
|
| 50 |
+
"learning_rate": 2.517601877533604e-07,
|
| 51 |
+
"loss": 0.7201,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.00448,
|
| 56 |
+
"grad_norm": 1.164099097251892,
|
| 57 |
+
"learning_rate": 2.944314060166418e-07,
|
| 58 |
+
"loss": 0.7195,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.00512,
|
| 63 |
+
"grad_norm": 1.9283920526504517,
|
| 64 |
+
"learning_rate": 3.371026242799232e-07,
|
| 65 |
+
"loss": 0.7223,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.00576,
|
| 70 |
+
"grad_norm": 1.8716129064559937,
|
| 71 |
+
"learning_rate": 3.7977384254320464e-07,
|
| 72 |
+
"loss": 0.7151,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0064,
|
| 77 |
+
"grad_norm": 1.5499262809753418,
|
| 78 |
+
"learning_rate": 4.22445060806486e-07,
|
| 79 |
+
"loss": 0.7211,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.00704,
|
| 84 |
+
"grad_norm": 1.375114917755127,
|
| 85 |
+
"learning_rate": 4.651162790697675e-07,
|
| 86 |
+
"loss": 0.7247,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.00768,
|
| 91 |
+
"grad_norm": 1.384915828704834,
|
| 92 |
+
"learning_rate": 5.077874973330489e-07,
|
| 93 |
+
"loss": 0.7156,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.00832,
|
| 98 |
+
"grad_norm": 1.6376659870147705,
|
| 99 |
+
"learning_rate": 5.504587155963304e-07,
|
| 100 |
+
"loss": 0.7196,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.00896,
|
| 105 |
+
"grad_norm": 1.709489345550537,
|
| 106 |
+
"learning_rate": 5.931299338596117e-07,
|
| 107 |
+
"loss": 0.7215,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.0096,
|
| 112 |
+
"grad_norm": 1.350512146949768,
|
| 113 |
+
"learning_rate": 6.358011521228932e-07,
|
| 114 |
+
"loss": 0.71,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.01024,
|
| 119 |
+
"grad_norm": 2.33050537109375,
|
| 120 |
+
"learning_rate": 6.784723703861745e-07,
|
| 121 |
+
"loss": 0.7191,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01088,
|
| 126 |
+
"grad_norm": 1.0042874813079834,
|
| 127 |
+
"learning_rate": 7.21143588649456e-07,
|
| 128 |
+
"loss": 0.72,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.01152,
|
| 133 |
+
"grad_norm": 1.1835744380950928,
|
| 134 |
+
"learning_rate": 7.638148069127374e-07,
|
| 135 |
+
"loss": 0.7122,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.01216,
|
| 140 |
+
"grad_norm": 1.949506402015686,
|
| 141 |
+
"learning_rate": 8.064860251760189e-07,
|
| 142 |
+
"loss": 0.7091,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0128,
|
| 147 |
+
"grad_norm": 1.139626383781433,
|
| 148 |
+
"learning_rate": 8.491572434393003e-07,
|
| 149 |
+
"loss": 0.7046,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.01344,
|
| 154 |
+
"grad_norm": 1.7734779119491577,
|
| 155 |
+
"learning_rate": 8.918284617025817e-07,
|
| 156 |
+
"loss": 0.7135,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.01408,
|
| 161 |
+
"grad_norm": 1.3442974090576172,
|
| 162 |
+
"learning_rate": 9.344996799658632e-07,
|
| 163 |
+
"loss": 0.7127,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.01472,
|
| 168 |
+
"grad_norm": 1.6148335933685303,
|
| 169 |
+
"learning_rate": 9.771708982291445e-07,
|
| 170 |
+
"loss": 0.7168,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.01536,
|
| 175 |
+
"grad_norm": 0.9220213294029236,
|
| 176 |
+
"learning_rate": 1.0198421164924258e-06,
|
| 177 |
+
"loss": 0.7109,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.016,
|
| 182 |
+
"grad_norm": 1.5631815195083618,
|
| 183 |
+
"learning_rate": 1.0625133347557074e-06,
|
| 184 |
+
"loss": 0.7149,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.01664,
|
| 189 |
+
"grad_norm": 1.5052822828292847,
|
| 190 |
+
"learning_rate": 1.1051845530189888e-06,
|
| 191 |
+
"loss": 0.7112,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.01728,
|
| 196 |
+
"grad_norm": 1.6714903116226196,
|
| 197 |
+
"learning_rate": 1.1478557712822702e-06,
|
| 198 |
+
"loss": 0.7128,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.01792,
|
| 203 |
+
"grad_norm": 1.6667262315750122,
|
| 204 |
+
"learning_rate": 1.1905269895455517e-06,
|
| 205 |
+
"loss": 0.7091,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.01856,
|
| 210 |
+
"grad_norm": 1.6861907243728638,
|
| 211 |
+
"learning_rate": 1.233198207808833e-06,
|
| 212 |
+
"loss": 0.7078,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0192,
|
| 217 |
+
"grad_norm": 1.6259212493896484,
|
| 218 |
+
"learning_rate": 1.2758694260721145e-06,
|
| 219 |
+
"loss": 0.7087,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.01984,
|
| 224 |
+
"grad_norm": 1.207320213317871,
|
| 225 |
+
"learning_rate": 1.318540644335396e-06,
|
| 226 |
+
"loss": 0.7087,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.02048,
|
| 231 |
+
"grad_norm": 1.087124228477478,
|
| 232 |
+
"learning_rate": 1.3612118625986772e-06,
|
| 233 |
+
"loss": 0.7174,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.02112,
|
| 238 |
+
"grad_norm": 1.5668721199035645,
|
| 239 |
+
"learning_rate": 1.4038830808619588e-06,
|
| 240 |
+
"loss": 0.7066,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.02176,
|
| 245 |
+
"grad_norm": 1.5332859754562378,
|
| 246 |
+
"learning_rate": 1.4465542991252401e-06,
|
| 247 |
+
"loss": 0.7115,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.0224,
|
| 252 |
+
"grad_norm": 2.092994451522827,
|
| 253 |
+
"learning_rate": 1.4892255173885215e-06,
|
| 254 |
+
"loss": 0.7085,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.02304,
|
| 259 |
+
"grad_norm": 1.266851544380188,
|
| 260 |
+
"learning_rate": 1.531896735651803e-06,
|
| 261 |
+
"loss": 0.7091,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.02368,
|
| 266 |
+
"grad_norm": 1.290616512298584,
|
| 267 |
+
"learning_rate": 1.5745679539150842e-06,
|
| 268 |
+
"loss": 0.7103,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.02432,
|
| 273 |
+
"grad_norm": 1.2045000791549683,
|
| 274 |
+
"learning_rate": 1.6172391721783658e-06,
|
| 275 |
+
"loss": 0.705,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.02496,
|
| 280 |
+
"grad_norm": 1.828832983970642,
|
| 281 |
+
"learning_rate": 1.6599103904416472e-06,
|
| 282 |
+
"loss": 0.7038,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.0256,
|
| 287 |
+
"grad_norm": 1.7793196439743042,
|
| 288 |
+
"learning_rate": 1.7025816087049288e-06,
|
| 289 |
+
"loss": 0.7085,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.02624,
|
| 294 |
+
"grad_norm": 0.8949472904205322,
|
| 295 |
+
"learning_rate": 1.7452528269682101e-06,
|
| 296 |
+
"loss": 0.7045,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.02688,
|
| 301 |
+
"grad_norm": 1.3071945905685425,
|
| 302 |
+
"learning_rate": 1.7879240452314913e-06,
|
| 303 |
+
"loss": 0.702,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.02752,
|
| 308 |
+
"grad_norm": 1.7497148513793945,
|
| 309 |
+
"learning_rate": 1.8305952634947729e-06,
|
| 310 |
+
"loss": 0.7073,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.02816,
|
| 315 |
+
"grad_norm": 1.0856297016143799,
|
| 316 |
+
"learning_rate": 1.8732664817580542e-06,
|
| 317 |
+
"loss": 0.7008,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.0288,
|
| 322 |
+
"grad_norm": 1.369019627571106,
|
| 323 |
+
"learning_rate": 1.915937700021336e-06,
|
| 324 |
+
"loss": 0.7059,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.02944,
|
| 329 |
+
"grad_norm": 2.0961010456085205,
|
| 330 |
+
"learning_rate": 1.958608918284617e-06,
|
| 331 |
+
"loss": 0.6952,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.03008,
|
| 336 |
+
"grad_norm": 1.6076347827911377,
|
| 337 |
+
"learning_rate": 2.0012801365478988e-06,
|
| 338 |
+
"loss": 0.7074,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.03072,
|
| 343 |
+
"grad_norm": 1.3129311800003052,
|
| 344 |
+
"learning_rate": 2.04395135481118e-06,
|
| 345 |
+
"loss": 0.6994,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.03136,
|
| 350 |
+
"grad_norm": 1.3621476888656616,
|
| 351 |
+
"learning_rate": 2.0866225730744615e-06,
|
| 352 |
+
"loss": 0.696,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.032,
|
| 357 |
+
"grad_norm": 0.9786806106567383,
|
| 358 |
+
"learning_rate": 2.129293791337743e-06,
|
| 359 |
+
"loss": 0.7011,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.03264,
|
| 364 |
+
"grad_norm": 1.4611176252365112,
|
| 365 |
+
"learning_rate": 2.1719650096010242e-06,
|
| 366 |
+
"loss": 0.699,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.03328,
|
| 371 |
+
"grad_norm": 1.0675945281982422,
|
| 372 |
+
"learning_rate": 2.214636227864306e-06,
|
| 373 |
+
"loss": 0.6906,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.03392,
|
| 378 |
+
"grad_norm": 1.6564017534255981,
|
| 379 |
+
"learning_rate": 2.257307446127587e-06,
|
| 380 |
+
"loss": 0.6923,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.03456,
|
| 385 |
+
"grad_norm": 1.228119134902954,
|
| 386 |
+
"learning_rate": 2.2999786643908685e-06,
|
| 387 |
+
"loss": 0.6928,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0352,
|
| 392 |
+
"grad_norm": 1.9868593215942383,
|
| 393 |
+
"learning_rate": 2.34264988265415e-06,
|
| 394 |
+
"loss": 0.6912,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.03584,
|
| 399 |
+
"grad_norm": 1.2531176805496216,
|
| 400 |
+
"learning_rate": 2.3853211009174317e-06,
|
| 401 |
+
"loss": 0.6923,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.03648,
|
| 406 |
+
"grad_norm": 1.413602352142334,
|
| 407 |
+
"learning_rate": 2.427992319180713e-06,
|
| 408 |
+
"loss": 0.6993,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.03712,
|
| 413 |
+
"grad_norm": 0.9655390977859497,
|
| 414 |
+
"learning_rate": 2.470663537443994e-06,
|
| 415 |
+
"loss": 0.7017,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.03776,
|
| 420 |
+
"grad_norm": 1.962438941001892,
|
| 421 |
+
"learning_rate": 2.5133347557072756e-06,
|
| 422 |
+
"loss": 0.6933,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.0384,
|
| 427 |
+
"grad_norm": 1.1099931001663208,
|
| 428 |
+
"learning_rate": 2.556005973970557e-06,
|
| 429 |
+
"loss": 0.6925,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.03904,
|
| 434 |
+
"grad_norm": 1.1766624450683594,
|
| 435 |
+
"learning_rate": 2.5986771922338383e-06,
|
| 436 |
+
"loss": 0.6894,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.03968,
|
| 441 |
+
"grad_norm": 1.574353814125061,
|
| 442 |
+
"learning_rate": 2.64134841049712e-06,
|
| 443 |
+
"loss": 0.6923,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.04032,
|
| 448 |
+
"grad_norm": 1.194074273109436,
|
| 449 |
+
"learning_rate": 2.6840196287604015e-06,
|
| 450 |
+
"loss": 0.6855,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.04096,
|
| 455 |
+
"grad_norm": 1.1750593185424805,
|
| 456 |
+
"learning_rate": 2.7266908470236826e-06,
|
| 457 |
+
"loss": 0.7002,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.0416,
|
| 462 |
+
"grad_norm": 1.3165347576141357,
|
| 463 |
+
"learning_rate": 2.7693620652869642e-06,
|
| 464 |
+
"loss": 0.6893,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.04224,
|
| 469 |
+
"grad_norm": 1.1079384088516235,
|
| 470 |
+
"learning_rate": 2.812033283550246e-06,
|
| 471 |
+
"loss": 0.6852,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.04288,
|
| 476 |
+
"grad_norm": 1.231327772140503,
|
| 477 |
+
"learning_rate": 2.8547045018135274e-06,
|
| 478 |
+
"loss": 0.695,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.04352,
|
| 483 |
+
"grad_norm": 1.966036319732666,
|
| 484 |
+
"learning_rate": 2.897375720076808e-06,
|
| 485 |
+
"loss": 0.6833,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.04416,
|
| 490 |
+
"grad_norm": 1.0460131168365479,
|
| 491 |
+
"learning_rate": 2.9400469383400897e-06,
|
| 492 |
+
"loss": 0.6802,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.0448,
|
| 497 |
+
"grad_norm": 1.2445200681686401,
|
| 498 |
+
"learning_rate": 2.9827181566033713e-06,
|
| 499 |
+
"loss": 0.6883,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.04544,
|
| 504 |
+
"grad_norm": 1.1759636402130127,
|
| 505 |
+
"learning_rate": 3.025389374866653e-06,
|
| 506 |
+
"loss": 0.682,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.04608,
|
| 511 |
+
"grad_norm": 1.2478561401367188,
|
| 512 |
+
"learning_rate": 3.068060593129934e-06,
|
| 513 |
+
"loss": 0.6802,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.04672,
|
| 518 |
+
"grad_norm": 0.8945108652114868,
|
| 519 |
+
"learning_rate": 3.1107318113932156e-06,
|
| 520 |
+
"loss": 0.6873,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.04736,
|
| 525 |
+
"grad_norm": 1.6810317039489746,
|
| 526 |
+
"learning_rate": 3.153403029656497e-06,
|
| 527 |
+
"loss": 0.6828,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.048,
|
| 532 |
+
"grad_norm": 2.882283926010132,
|
| 533 |
+
"learning_rate": 3.1960742479197783e-06,
|
| 534 |
+
"loss": 0.6797,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.04864,
|
| 539 |
+
"grad_norm": 1.575766921043396,
|
| 540 |
+
"learning_rate": 3.23874546618306e-06,
|
| 541 |
+
"loss": 0.6826,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.04928,
|
| 546 |
+
"grad_norm": 1.8044737577438354,
|
| 547 |
+
"learning_rate": 3.2814166844463415e-06,
|
| 548 |
+
"loss": 0.6837,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.04992,
|
| 553 |
+
"grad_norm": 1.4755513668060303,
|
| 554 |
+
"learning_rate": 3.324087902709623e-06,
|
| 555 |
+
"loss": 0.6815,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.05056,
|
| 560 |
+
"grad_norm": 2.0735654830932617,
|
| 561 |
+
"learning_rate": 3.3667591209729038e-06,
|
| 562 |
+
"loss": 0.6773,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.0512,
|
| 567 |
+
"grad_norm": 0.9823655486106873,
|
| 568 |
+
"learning_rate": 3.4094303392361854e-06,
|
| 569 |
+
"loss": 0.6689,
|
| 570 |
+
"step": 800
|
| 571 |
+
}
|
| 572 |
+
],
|
| 573 |
+
"logging_steps": 10,
|
| 574 |
+
"max_steps": 46875,
|
| 575 |
+
"num_input_tokens_seen": 0,
|
| 576 |
+
"num_train_epochs": 3,
|
| 577 |
+
"save_steps": 200,
|
| 578 |
+
"stateful_callbacks": {
|
| 579 |
+
"EarlyStoppingCallback": {
|
| 580 |
+
"args": {
|
| 581 |
+
"early_stopping_patience": 3,
|
| 582 |
+
"early_stopping_threshold": 0.0
|
| 583 |
+
},
|
| 584 |
+
"attributes": {
|
| 585 |
+
"early_stopping_patience_counter": 0
|
| 586 |
+
}
|
| 587 |
+
},
|
| 588 |
+
"TrainerControl": {
|
| 589 |
+
"args": {
|
| 590 |
+
"should_epoch_stop": false,
|
| 591 |
+
"should_evaluate": false,
|
| 592 |
+
"should_log": false,
|
| 593 |
+
"should_save": true,
|
| 594 |
+
"should_training_stop": false
|
| 595 |
+
},
|
| 596 |
+
"attributes": {}
|
| 597 |
+
}
|
| 598 |
+
},
|
| 599 |
+
"total_flos": 6731943018000000.0,
|
| 600 |
+
"train_batch_size": 32,
|
| 601 |
+
"trial_name": null,
|
| 602 |
+
"trial_params": null
|
| 603 |
+
}
|
graphcodebert-rdrop/checkpoint-800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7cd390fef915efa37cfafbe6f2d5d365158faf1073058ef1c9ea09cda16a6a5
|
| 3 |
+
size 5841
|