Upload training checkpoints and best model
Browse files- checkpoint-300/config.json +29 -0
- checkpoint-300/merges.txt +0 -0
- checkpoint-300/model.safetensors +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scaler.pt +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +51 -0
- checkpoint-300/tokenizer.json +0 -0
- checkpoint-300/tokenizer_config.json +58 -0
- checkpoint-300/trainer_state.json +292 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-300/vocab.json +0 -0
- checkpoint-400/config.json +29 -0
- checkpoint-400/merges.txt +0 -0
- checkpoint-400/model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scaler.pt +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +51 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/tokenizer_config.json +58 -0
- checkpoint-400/trainer_state.json +375 -0
- checkpoint-400/training_args.bin +3 -0
- checkpoint-400/vocab.json +0 -0
checkpoint-300/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 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": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 1026,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"transformers_version": "4.56.0",
|
| 26 |
+
"type_vocab_size": 10,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 51416
|
| 29 |
+
}
|
checkpoint-300/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5df94bb5664f24898bd1747b90ec5ec1a7894763877b50ed6f92ec343e887343
|
| 3 |
+
size 506505672
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67c687386e7f0bcc1b0cab97971038f78f405c6cbaa22b344603ad4b030d172e
|
| 3 |
+
size 1007622411
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92749dba80344f7fbb600490e0859bf95cfe3553899b6b40b587db34c59e5a78
|
| 3 |
+
size 14645
|
checkpoint-300/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fe30269f1e01bbd05ef9d9a336eb0d22d9ef083f38758adacac6c503a6978bc
|
| 3 |
+
size 1383
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a5ab476f3cf79210c1ebb124e0a4c75b4d8b4d0df459d9b662052991fff0c55
|
| 3 |
+
size 1977
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 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": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 300,
|
| 3 |
+
"best_metric": 0.8230100448030374,
|
| 4 |
+
"best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-300",
|
| 5 |
+
"epoch": 0.03670622782332069,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 300,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.001223540927444023,
|
| 14 |
+
"grad_norm": 0.1898110806941986,
|
| 15 |
+
"learning_rate": 3.6734693877551025e-07,
|
| 16 |
+
"loss": 0.4422,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.002447081854888046,
|
| 21 |
+
"grad_norm": 0.3350900411605835,
|
| 22 |
+
"learning_rate": 7.346938775510205e-07,
|
| 23 |
+
"loss": 0.4323,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.003670622782332069,
|
| 28 |
+
"grad_norm": 0.3723449110984802,
|
| 29 |
+
"learning_rate": 1.142857142857143e-06,
|
| 30 |
+
"loss": 0.4362,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.004894163709776092,
|
| 35 |
+
"grad_norm": 0.3299769461154938,
|
| 36 |
+
"learning_rate": 1.5510204081632654e-06,
|
| 37 |
+
"loss": 0.4191,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.006117704637220115,
|
| 42 |
+
"grad_norm": 0.26681044697761536,
|
| 43 |
+
"learning_rate": 1.9591836734693877e-06,
|
| 44 |
+
"loss": 0.4289,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.007341245564664138,
|
| 49 |
+
"grad_norm": 0.30233338475227356,
|
| 50 |
+
"learning_rate": 2.3673469387755103e-06,
|
| 51 |
+
"loss": 0.4083,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.008564786492108161,
|
| 56 |
+
"grad_norm": 0.31031334400177,
|
| 57 |
+
"learning_rate": 2.775510204081633e-06,
|
| 58 |
+
"loss": 0.404,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.009788327419552184,
|
| 63 |
+
"grad_norm": 0.2552475035190582,
|
| 64 |
+
"learning_rate": 3.183673469387755e-06,
|
| 65 |
+
"loss": 0.3889,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.011011868346996207,
|
| 70 |
+
"grad_norm": 0.3131052553653717,
|
| 71 |
+
"learning_rate": 3.5918367346938777e-06,
|
| 72 |
+
"loss": 0.3813,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.01223540927444023,
|
| 77 |
+
"grad_norm": 0.3377229571342468,
|
| 78 |
+
"learning_rate": 4.000000000000001e-06,
|
| 79 |
+
"loss": 0.3727,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.01223540927444023,
|
| 84 |
+
"eval_accuracy": 0.6961,
|
| 85 |
+
"eval_f1_weighted": 0.6955947095331424,
|
| 86 |
+
"eval_loss": 0.15026023983955383,
|
| 87 |
+
"eval_macro_f1": 0.6959280508399847,
|
| 88 |
+
"eval_precision": 0.7019396279846728,
|
| 89 |
+
"eval_recall": 0.6961,
|
| 90 |
+
"eval_runtime": 789.7648,
|
| 91 |
+
"eval_samples_per_second": 126.62,
|
| 92 |
+
"eval_steps_per_second": 0.99,
|
| 93 |
+
"step": 100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.013458950201884253,
|
| 97 |
+
"grad_norm": 0.3366774618625641,
|
| 98 |
+
"learning_rate": 4.408163265306123e-06,
|
| 99 |
+
"loss": 0.3671,
|
| 100 |
+
"step": 110
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.014682491129328276,
|
| 104 |
+
"grad_norm": 0.33491575717926025,
|
| 105 |
+
"learning_rate": 4.816326530612245e-06,
|
| 106 |
+
"loss": 0.3498,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0159060320567723,
|
| 111 |
+
"grad_norm": 0.4119006097316742,
|
| 112 |
+
"learning_rate": 5.2244897959183684e-06,
|
| 113 |
+
"loss": 0.3409,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.017129572984216322,
|
| 118 |
+
"grad_norm": 0.2964725196361542,
|
| 119 |
+
"learning_rate": 5.63265306122449e-06,
|
| 120 |
+
"loss": 0.3433,
|
| 121 |
+
"step": 140
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.018353113911660345,
|
| 125 |
+
"grad_norm": 0.3075334429740906,
|
| 126 |
+
"learning_rate": 6.040816326530613e-06,
|
| 127 |
+
"loss": 0.3298,
|
| 128 |
+
"step": 150
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.019576654839104368,
|
| 132 |
+
"grad_norm": 0.33718687295913696,
|
| 133 |
+
"learning_rate": 6.4489795918367345e-06,
|
| 134 |
+
"loss": 0.3297,
|
| 135 |
+
"step": 160
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.02080019576654839,
|
| 139 |
+
"grad_norm": 0.2809618413448334,
|
| 140 |
+
"learning_rate": 6.857142857142858e-06,
|
| 141 |
+
"loss": 0.3275,
|
| 142 |
+
"step": 170
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.022023736693992414,
|
| 146 |
+
"grad_norm": 0.37805014848709106,
|
| 147 |
+
"learning_rate": 7.2653061224489805e-06,
|
| 148 |
+
"loss": 0.3201,
|
| 149 |
+
"step": 180
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.023247277621436437,
|
| 153 |
+
"grad_norm": 0.2940429151058197,
|
| 154 |
+
"learning_rate": 7.673469387755102e-06,
|
| 155 |
+
"loss": 0.3042,
|
| 156 |
+
"step": 190
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.02447081854888046,
|
| 160 |
+
"grad_norm": 0.3286060690879822,
|
| 161 |
+
"learning_rate": 8.081632653061225e-06,
|
| 162 |
+
"loss": 0.3071,
|
| 163 |
+
"step": 200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.02447081854888046,
|
| 167 |
+
"eval_accuracy": 0.77807,
|
| 168 |
+
"eval_f1_weighted": 0.7781129395311969,
|
| 169 |
+
"eval_loss": 0.12153773754835129,
|
| 170 |
+
"eval_macro_f1": 0.7780651598452646,
|
| 171 |
+
"eval_precision": 0.7808306361972198,
|
| 172 |
+
"eval_recall": 0.77807,
|
| 173 |
+
"eval_runtime": 792.7157,
|
| 174 |
+
"eval_samples_per_second": 126.149,
|
| 175 |
+
"eval_steps_per_second": 0.986,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.025694359476324483,
|
| 180 |
+
"grad_norm": 0.33857154846191406,
|
| 181 |
+
"learning_rate": 8.489795918367347e-06,
|
| 182 |
+
"loss": 0.2964,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.026917900403768506,
|
| 187 |
+
"grad_norm": 0.2752092182636261,
|
| 188 |
+
"learning_rate": 8.89795918367347e-06,
|
| 189 |
+
"loss": 0.3,
|
| 190 |
+
"step": 220
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.02814144133121253,
|
| 194 |
+
"grad_norm": 0.4952544569969177,
|
| 195 |
+
"learning_rate": 9.306122448979593e-06,
|
| 196 |
+
"loss": 0.294,
|
| 197 |
+
"step": 230
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.029364982258656552,
|
| 201 |
+
"grad_norm": 0.37926042079925537,
|
| 202 |
+
"learning_rate": 9.714285714285715e-06,
|
| 203 |
+
"loss": 0.2964,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.030588523186100575,
|
| 208 |
+
"grad_norm": 0.3222455680370331,
|
| 209 |
+
"learning_rate": 1.0122448979591836e-05,
|
| 210 |
+
"loss": 0.283,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.0318120641135446,
|
| 215 |
+
"grad_norm": 0.2930658459663391,
|
| 216 |
+
"learning_rate": 1.053061224489796e-05,
|
| 217 |
+
"loss": 0.2793,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.03303560504098862,
|
| 222 |
+
"grad_norm": 0.4313414692878723,
|
| 223 |
+
"learning_rate": 1.0938775510204083e-05,
|
| 224 |
+
"loss": 0.2728,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.034259145968432644,
|
| 229 |
+
"grad_norm": 0.37351569533348083,
|
| 230 |
+
"learning_rate": 1.1346938775510206e-05,
|
| 231 |
+
"loss": 0.2752,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.035482686895876664,
|
| 236 |
+
"grad_norm": 0.22772285342216492,
|
| 237 |
+
"learning_rate": 1.1755102040816328e-05,
|
| 238 |
+
"loss": 0.274,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.03670622782332069,
|
| 243 |
+
"grad_norm": 0.15888753533363342,
|
| 244 |
+
"learning_rate": 1.2163265306122449e-05,
|
| 245 |
+
"loss": 0.264,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.03670622782332069,
|
| 250 |
+
"eval_accuracy": 0.82326,
|
| 251 |
+
"eval_f1_weighted": 0.8227034206790359,
|
| 252 |
+
"eval_loss": 0.10234300792217255,
|
| 253 |
+
"eval_macro_f1": 0.8230100448030374,
|
| 254 |
+
"eval_precision": 0.8338333810964687,
|
| 255 |
+
"eval_recall": 0.82326,
|
| 256 |
+
"eval_runtime": 789.0168,
|
| 257 |
+
"eval_samples_per_second": 126.74,
|
| 258 |
+
"eval_steps_per_second": 0.991,
|
| 259 |
+
"step": 300
|
| 260 |
+
}
|
| 261 |
+
],
|
| 262 |
+
"logging_steps": 10,
|
| 263 |
+
"max_steps": 8173,
|
| 264 |
+
"num_input_tokens_seen": 0,
|
| 265 |
+
"num_train_epochs": 1,
|
| 266 |
+
"save_steps": 100,
|
| 267 |
+
"stateful_callbacks": {
|
| 268 |
+
"EarlyStoppingCallback": {
|
| 269 |
+
"args": {
|
| 270 |
+
"early_stopping_patience": 3,
|
| 271 |
+
"early_stopping_threshold": 0.0
|
| 272 |
+
},
|
| 273 |
+
"attributes": {
|
| 274 |
+
"early_stopping_patience_counter": 0
|
| 275 |
+
}
|
| 276 |
+
},
|
| 277 |
+
"TrainerControl": {
|
| 278 |
+
"args": {
|
| 279 |
+
"should_epoch_stop": false,
|
| 280 |
+
"should_evaluate": false,
|
| 281 |
+
"should_log": false,
|
| 282 |
+
"should_save": true,
|
| 283 |
+
"should_training_stop": false
|
| 284 |
+
},
|
| 285 |
+
"attributes": {}
|
| 286 |
+
}
|
| 287 |
+
},
|
| 288 |
+
"total_flos": 5092372552089600.0,
|
| 289 |
+
"train_batch_size": 64,
|
| 290 |
+
"trial_name": null,
|
| 291 |
+
"trial_params": null
|
| 292 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35d071116340aee07c195df38edc9c8a987c20a84c3af618845dff316a63c31a
|
| 3 |
+
size 5841
|
checkpoint-300/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 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": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 1026,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"transformers_version": "4.56.0",
|
| 26 |
+
"type_vocab_size": 10,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 51416
|
| 29 |
+
}
|
checkpoint-400/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dd1ca26fa229c9545670ecf9e66be143b5e587e21443286e1fc268bd145046a
|
| 3 |
+
size 506505672
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d82bb9793c8d840a9948fe203133398c8ec366eb90d59c0eae5af63cf790fe2b
|
| 3 |
+
size 1007622411
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e08560613aca9da0f5194640c31cde75488bad269a31eb6a9b271573a61cff20
|
| 3 |
+
size 14645
|
checkpoint-400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94c541eb6ef896f3e760a51d1437355e15c9e0b1b5365bcda1fa18a405d0bb55
|
| 3 |
+
size 1383
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7eda7ec867288da79c71f9fc41a7c2af734e71bb221a093021bd48a0eb65b1f
|
| 3 |
+
size 1977
|
checkpoint-400/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 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/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 |
+
"4": {
|
| 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": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 400,
|
| 3 |
+
"best_metric": 0.8451923512067675,
|
| 4 |
+
"best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-400",
|
| 5 |
+
"epoch": 0.04894163709776092,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.001223540927444023,
|
| 14 |
+
"grad_norm": 0.1898110806941986,
|
| 15 |
+
"learning_rate": 3.6734693877551025e-07,
|
| 16 |
+
"loss": 0.4422,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.002447081854888046,
|
| 21 |
+
"grad_norm": 0.3350900411605835,
|
| 22 |
+
"learning_rate": 7.346938775510205e-07,
|
| 23 |
+
"loss": 0.4323,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.003670622782332069,
|
| 28 |
+
"grad_norm": 0.3723449110984802,
|
| 29 |
+
"learning_rate": 1.142857142857143e-06,
|
| 30 |
+
"loss": 0.4362,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.004894163709776092,
|
| 35 |
+
"grad_norm": 0.3299769461154938,
|
| 36 |
+
"learning_rate": 1.5510204081632654e-06,
|
| 37 |
+
"loss": 0.4191,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.006117704637220115,
|
| 42 |
+
"grad_norm": 0.26681044697761536,
|
| 43 |
+
"learning_rate": 1.9591836734693877e-06,
|
| 44 |
+
"loss": 0.4289,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.007341245564664138,
|
| 49 |
+
"grad_norm": 0.30233338475227356,
|
| 50 |
+
"learning_rate": 2.3673469387755103e-06,
|
| 51 |
+
"loss": 0.4083,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.008564786492108161,
|
| 56 |
+
"grad_norm": 0.31031334400177,
|
| 57 |
+
"learning_rate": 2.775510204081633e-06,
|
| 58 |
+
"loss": 0.404,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.009788327419552184,
|
| 63 |
+
"grad_norm": 0.2552475035190582,
|
| 64 |
+
"learning_rate": 3.183673469387755e-06,
|
| 65 |
+
"loss": 0.3889,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.011011868346996207,
|
| 70 |
+
"grad_norm": 0.3131052553653717,
|
| 71 |
+
"learning_rate": 3.5918367346938777e-06,
|
| 72 |
+
"loss": 0.3813,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.01223540927444023,
|
| 77 |
+
"grad_norm": 0.3377229571342468,
|
| 78 |
+
"learning_rate": 4.000000000000001e-06,
|
| 79 |
+
"loss": 0.3727,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.01223540927444023,
|
| 84 |
+
"eval_accuracy": 0.6961,
|
| 85 |
+
"eval_f1_weighted": 0.6955947095331424,
|
| 86 |
+
"eval_loss": 0.15026023983955383,
|
| 87 |
+
"eval_macro_f1": 0.6959280508399847,
|
| 88 |
+
"eval_precision": 0.7019396279846728,
|
| 89 |
+
"eval_recall": 0.6961,
|
| 90 |
+
"eval_runtime": 789.7648,
|
| 91 |
+
"eval_samples_per_second": 126.62,
|
| 92 |
+
"eval_steps_per_second": 0.99,
|
| 93 |
+
"step": 100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.013458950201884253,
|
| 97 |
+
"grad_norm": 0.3366774618625641,
|
| 98 |
+
"learning_rate": 4.408163265306123e-06,
|
| 99 |
+
"loss": 0.3671,
|
| 100 |
+
"step": 110
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.014682491129328276,
|
| 104 |
+
"grad_norm": 0.33491575717926025,
|
| 105 |
+
"learning_rate": 4.816326530612245e-06,
|
| 106 |
+
"loss": 0.3498,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.0159060320567723,
|
| 111 |
+
"grad_norm": 0.4119006097316742,
|
| 112 |
+
"learning_rate": 5.2244897959183684e-06,
|
| 113 |
+
"loss": 0.3409,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.017129572984216322,
|
| 118 |
+
"grad_norm": 0.2964725196361542,
|
| 119 |
+
"learning_rate": 5.63265306122449e-06,
|
| 120 |
+
"loss": 0.3433,
|
| 121 |
+
"step": 140
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.018353113911660345,
|
| 125 |
+
"grad_norm": 0.3075334429740906,
|
| 126 |
+
"learning_rate": 6.040816326530613e-06,
|
| 127 |
+
"loss": 0.3298,
|
| 128 |
+
"step": 150
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.019576654839104368,
|
| 132 |
+
"grad_norm": 0.33718687295913696,
|
| 133 |
+
"learning_rate": 6.4489795918367345e-06,
|
| 134 |
+
"loss": 0.3297,
|
| 135 |
+
"step": 160
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.02080019576654839,
|
| 139 |
+
"grad_norm": 0.2809618413448334,
|
| 140 |
+
"learning_rate": 6.857142857142858e-06,
|
| 141 |
+
"loss": 0.3275,
|
| 142 |
+
"step": 170
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.022023736693992414,
|
| 146 |
+
"grad_norm": 0.37805014848709106,
|
| 147 |
+
"learning_rate": 7.2653061224489805e-06,
|
| 148 |
+
"loss": 0.3201,
|
| 149 |
+
"step": 180
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.023247277621436437,
|
| 153 |
+
"grad_norm": 0.2940429151058197,
|
| 154 |
+
"learning_rate": 7.673469387755102e-06,
|
| 155 |
+
"loss": 0.3042,
|
| 156 |
+
"step": 190
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.02447081854888046,
|
| 160 |
+
"grad_norm": 0.3286060690879822,
|
| 161 |
+
"learning_rate": 8.081632653061225e-06,
|
| 162 |
+
"loss": 0.3071,
|
| 163 |
+
"step": 200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.02447081854888046,
|
| 167 |
+
"eval_accuracy": 0.77807,
|
| 168 |
+
"eval_f1_weighted": 0.7781129395311969,
|
| 169 |
+
"eval_loss": 0.12153773754835129,
|
| 170 |
+
"eval_macro_f1": 0.7780651598452646,
|
| 171 |
+
"eval_precision": 0.7808306361972198,
|
| 172 |
+
"eval_recall": 0.77807,
|
| 173 |
+
"eval_runtime": 792.7157,
|
| 174 |
+
"eval_samples_per_second": 126.149,
|
| 175 |
+
"eval_steps_per_second": 0.986,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.025694359476324483,
|
| 180 |
+
"grad_norm": 0.33857154846191406,
|
| 181 |
+
"learning_rate": 8.489795918367347e-06,
|
| 182 |
+
"loss": 0.2964,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.026917900403768506,
|
| 187 |
+
"grad_norm": 0.2752092182636261,
|
| 188 |
+
"learning_rate": 8.89795918367347e-06,
|
| 189 |
+
"loss": 0.3,
|
| 190 |
+
"step": 220
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.02814144133121253,
|
| 194 |
+
"grad_norm": 0.4952544569969177,
|
| 195 |
+
"learning_rate": 9.306122448979593e-06,
|
| 196 |
+
"loss": 0.294,
|
| 197 |
+
"step": 230
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.029364982258656552,
|
| 201 |
+
"grad_norm": 0.37926042079925537,
|
| 202 |
+
"learning_rate": 9.714285714285715e-06,
|
| 203 |
+
"loss": 0.2964,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.030588523186100575,
|
| 208 |
+
"grad_norm": 0.3222455680370331,
|
| 209 |
+
"learning_rate": 1.0122448979591836e-05,
|
| 210 |
+
"loss": 0.283,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.0318120641135446,
|
| 215 |
+
"grad_norm": 0.2930658459663391,
|
| 216 |
+
"learning_rate": 1.053061224489796e-05,
|
| 217 |
+
"loss": 0.2793,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.03303560504098862,
|
| 222 |
+
"grad_norm": 0.4313414692878723,
|
| 223 |
+
"learning_rate": 1.0938775510204083e-05,
|
| 224 |
+
"loss": 0.2728,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.034259145968432644,
|
| 229 |
+
"grad_norm": 0.37351569533348083,
|
| 230 |
+
"learning_rate": 1.1346938775510206e-05,
|
| 231 |
+
"loss": 0.2752,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.035482686895876664,
|
| 236 |
+
"grad_norm": 0.22772285342216492,
|
| 237 |
+
"learning_rate": 1.1755102040816328e-05,
|
| 238 |
+
"loss": 0.274,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.03670622782332069,
|
| 243 |
+
"grad_norm": 0.15888753533363342,
|
| 244 |
+
"learning_rate": 1.2163265306122449e-05,
|
| 245 |
+
"loss": 0.264,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.03670622782332069,
|
| 250 |
+
"eval_accuracy": 0.82326,
|
| 251 |
+
"eval_f1_weighted": 0.8227034206790359,
|
| 252 |
+
"eval_loss": 0.10234300792217255,
|
| 253 |
+
"eval_macro_f1": 0.8230100448030374,
|
| 254 |
+
"eval_precision": 0.8338333810964687,
|
| 255 |
+
"eval_recall": 0.82326,
|
| 256 |
+
"eval_runtime": 789.0168,
|
| 257 |
+
"eval_samples_per_second": 126.74,
|
| 258 |
+
"eval_steps_per_second": 0.991,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.03792976875076471,
|
| 263 |
+
"grad_norm": 0.23560188710689545,
|
| 264 |
+
"learning_rate": 1.2571428571428572e-05,
|
| 265 |
+
"loss": 0.2753,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.039153309678208736,
|
| 270 |
+
"grad_norm": 0.18699614703655243,
|
| 271 |
+
"learning_rate": 1.2979591836734696e-05,
|
| 272 |
+
"loss": 0.2565,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.040376850605652756,
|
| 277 |
+
"grad_norm": 0.24035991728305817,
|
| 278 |
+
"learning_rate": 1.3387755102040818e-05,
|
| 279 |
+
"loss": 0.2716,
|
| 280 |
+
"step": 330
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.04160039153309678,
|
| 284 |
+
"grad_norm": 0.15309660136699677,
|
| 285 |
+
"learning_rate": 1.3795918367346941e-05,
|
| 286 |
+
"loss": 0.2515,
|
| 287 |
+
"step": 340
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.0428239324605408,
|
| 291 |
+
"grad_norm": 0.3382055461406708,
|
| 292 |
+
"learning_rate": 1.4204081632653062e-05,
|
| 293 |
+
"loss": 0.2597,
|
| 294 |
+
"step": 350
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.04404747338798483,
|
| 298 |
+
"grad_norm": 0.24439455568790436,
|
| 299 |
+
"learning_rate": 1.4612244897959185e-05,
|
| 300 |
+
"loss": 0.247,
|
| 301 |
+
"step": 360
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.04527101431542885,
|
| 305 |
+
"grad_norm": 0.26233720779418945,
|
| 306 |
+
"learning_rate": 1.5020408163265307e-05,
|
| 307 |
+
"loss": 0.2431,
|
| 308 |
+
"step": 370
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.046494555242872875,
|
| 312 |
+
"grad_norm": 0.20477451384067535,
|
| 313 |
+
"learning_rate": 1.5387755102040818e-05,
|
| 314 |
+
"loss": 0.2538,
|
| 315 |
+
"step": 380
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.047718096170316894,
|
| 319 |
+
"grad_norm": 0.2765439748764038,
|
| 320 |
+
"learning_rate": 1.5795918367346942e-05,
|
| 321 |
+
"loss": 0.2404,
|
| 322 |
+
"step": 390
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.04894163709776092,
|
| 326 |
+
"grad_norm": 0.13196279108524323,
|
| 327 |
+
"learning_rate": 1.6204081632653063e-05,
|
| 328 |
+
"loss": 0.2393,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.04894163709776092,
|
| 333 |
+
"eval_accuracy": 0.84563,
|
| 334 |
+
"eval_f1_weighted": 0.8448128964509274,
|
| 335 |
+
"eval_loss": 0.09028046578168869,
|
| 336 |
+
"eval_macro_f1": 0.8451923512067675,
|
| 337 |
+
"eval_precision": 0.861024732271907,
|
| 338 |
+
"eval_recall": 0.84563,
|
| 339 |
+
"eval_runtime": 787.6067,
|
| 340 |
+
"eval_samples_per_second": 126.967,
|
| 341 |
+
"eval_steps_per_second": 0.993,
|
| 342 |
+
"step": 400
|
| 343 |
+
}
|
| 344 |
+
],
|
| 345 |
+
"logging_steps": 10,
|
| 346 |
+
"max_steps": 8173,
|
| 347 |
+
"num_input_tokens_seen": 0,
|
| 348 |
+
"num_train_epochs": 1,
|
| 349 |
+
"save_steps": 100,
|
| 350 |
+
"stateful_callbacks": {
|
| 351 |
+
"EarlyStoppingCallback": {
|
| 352 |
+
"args": {
|
| 353 |
+
"early_stopping_patience": 3,
|
| 354 |
+
"early_stopping_threshold": 0.0
|
| 355 |
+
},
|
| 356 |
+
"attributes": {
|
| 357 |
+
"early_stopping_patience_counter": 0
|
| 358 |
+
}
|
| 359 |
+
},
|
| 360 |
+
"TrainerControl": {
|
| 361 |
+
"args": {
|
| 362 |
+
"should_epoch_stop": false,
|
| 363 |
+
"should_evaluate": false,
|
| 364 |
+
"should_log": false,
|
| 365 |
+
"should_save": true,
|
| 366 |
+
"should_training_stop": false
|
| 367 |
+
},
|
| 368 |
+
"attributes": {}
|
| 369 |
+
}
|
| 370 |
+
},
|
| 371 |
+
"total_flos": 6789830069452800.0,
|
| 372 |
+
"train_batch_size": 64,
|
| 373 |
+
"trial_name": null,
|
| 374 |
+
"trial_params": null
|
| 375 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6ab3d3f08d9426eb9807e9630113e3f0e0c4e53931f1d94a0019c3b5e996465
|
| 3 |
+
size 5841
|
checkpoint-400/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|