feat: add tokenizer
Browse filesThis view is limited to 50 files because it contains too many changes. 聽
See raw diff
- checkpoint-1000/config.json +27 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +37 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +56 -0
- checkpoint-1000/trainer_state.json +363 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1000/vocab.txt +0 -0
- checkpoint-1500/config.json +27 -0
- checkpoint-1500/model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scaler.pt +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/special_tokens_map.json +37 -0
- checkpoint-1500/tokenizer.json +0 -0
- checkpoint-1500/tokenizer_config.json +56 -0
- checkpoint-1500/trainer_state.json +523 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-1500/vocab.txt +0 -0
- checkpoint-2000/config.json +27 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +37 -0
- checkpoint-2000/tokenizer.json +0 -0
- checkpoint-2000/tokenizer_config.json +56 -0
- checkpoint-2000/trainer_state.json +683 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2000/vocab.txt +0 -0
- checkpoint-2500/config.json +27 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scaler.pt +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +37 -0
- checkpoint-2500/tokenizer.json +0 -0
- checkpoint-2500/tokenizer_config.json +56 -0
- checkpoint-2500/trainer_state.json +843 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-2500/vocab.txt +0 -0
- checkpoint-3000/config.json +27 -0
- checkpoint-3000/model.safetensors +3 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForQuestionAnswering"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"language": "english",
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"name": "Bert",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.50.3",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf8991e05b422c14c8e2fc5cd3f72feb17bd3677b6f1389322d3fed4a8999b98
|
| 3 |
+
size 435596088
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4f8538c773a31efc17fab7c7d668c5e79c64ca7830d4516cd0480460f573545
|
| 3 |
+
size 871311930
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9eb0e8e8bc64936aefc31ee7af1a5d1912fdfb5b07d689677f79a6259ca2c757
|
| 3 |
+
size 14244
|
checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:595fac63b46180ff479afa6e7307045f9376a829986c66b1a84e9eba8d5f2706
|
| 3 |
+
size 988
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a63e8131bb66c9187759ce67cd24c6b46de8a1bef28b9d60900c3736a72e1e4
|
| 3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 700,
|
| 3 |
+
"best_metric": 79.0143805614001,
|
| 4 |
+
"best_model_checkpoint": "bert-soccer-qa/checkpoint-500",
|
| 5 |
+
"epoch": 0.15537600994406464,
|
| 6 |
+
"eval_steps": 100,
|
| 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": 0.007768800497203232,
|
| 14 |
+
"grad_norm": 9.272425651550293,
|
| 15 |
+
"learning_rate": 9.99925419515227e-06,
|
| 16 |
+
"loss": 1.1446,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015537600994406464,
|
| 21 |
+
"grad_norm": 12.237289428710938,
|
| 22 |
+
"learning_rate": 9.99847731510255e-06,
|
| 23 |
+
"loss": 0.9455,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.015537600994406464,
|
| 28 |
+
"eval_HasAns_exact": 69.85208252238225,
|
| 29 |
+
"eval_HasAns_f1": 77.13603651720207,
|
| 30 |
+
"eval_HasAns_total": 25690,
|
| 31 |
+
"eval_best_exact": 69.85208252238225,
|
| 32 |
+
"eval_best_exact_thresh": 0.0,
|
| 33 |
+
"eval_best_f1": 77.13603651720207,
|
| 34 |
+
"eval_best_f1_thresh": 0.0,
|
| 35 |
+
"eval_exact": 69.85208252238225,
|
| 36 |
+
"eval_f1": 77.13603651720207,
|
| 37 |
+
"eval_loss": 0.8127343058586121,
|
| 38 |
+
"eval_runtime": 202.0338,
|
| 39 |
+
"eval_samples_per_second": 127.157,
|
| 40 |
+
"eval_steps_per_second": 7.949,
|
| 41 |
+
"eval_total": 25690,
|
| 42 |
+
"step": 100
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.023306401491609695,
|
| 46 |
+
"grad_norm": 5.626998424530029,
|
| 47 |
+
"learning_rate": 9.997700435052828e-06,
|
| 48 |
+
"loss": 0.8129,
|
| 49 |
+
"step": 150
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.031075201988812928,
|
| 53 |
+
"grad_norm": 6.87526798248291,
|
| 54 |
+
"learning_rate": 9.996923555003108e-06,
|
| 55 |
+
"loss": 0.8743,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.031075201988812928,
|
| 60 |
+
"eval_HasAns_exact": 70.21409108602569,
|
| 61 |
+
"eval_HasAns_f1": 77.38207884007946,
|
| 62 |
+
"eval_HasAns_total": 25690,
|
| 63 |
+
"eval_best_exact": 70.21409108602569,
|
| 64 |
+
"eval_best_exact_thresh": 0.0,
|
| 65 |
+
"eval_best_f1": 77.38207884007946,
|
| 66 |
+
"eval_best_f1_thresh": 0.0,
|
| 67 |
+
"eval_exact": 70.21409108602569,
|
| 68 |
+
"eval_f1": 77.38207884007946,
|
| 69 |
+
"eval_loss": 0.7383215427398682,
|
| 70 |
+
"eval_runtime": 202.5157,
|
| 71 |
+
"eval_samples_per_second": 126.854,
|
| 72 |
+
"eval_steps_per_second": 7.93,
|
| 73 |
+
"eval_total": 25690,
|
| 74 |
+
"step": 200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.03884400248601616,
|
| 78 |
+
"grad_norm": 11.461019515991211,
|
| 79 |
+
"learning_rate": 9.996146674953388e-06,
|
| 80 |
+
"loss": 0.7825,
|
| 81 |
+
"step": 250
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04661280298321939,
|
| 85 |
+
"grad_norm": 9.630631446838379,
|
| 86 |
+
"learning_rate": 9.995369794903668e-06,
|
| 87 |
+
"loss": 0.7189,
|
| 88 |
+
"step": 300
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.04661280298321939,
|
| 92 |
+
"eval_HasAns_exact": 71.03931490852472,
|
| 93 |
+
"eval_HasAns_f1": 78.08897109574,
|
| 94 |
+
"eval_HasAns_total": 25690,
|
| 95 |
+
"eval_best_exact": 71.03931490852472,
|
| 96 |
+
"eval_best_exact_thresh": 0.0,
|
| 97 |
+
"eval_best_f1": 78.08897109574,
|
| 98 |
+
"eval_best_f1_thresh": 0.0,
|
| 99 |
+
"eval_exact": 71.03931490852472,
|
| 100 |
+
"eval_f1": 78.08897109574,
|
| 101 |
+
"eval_loss": 0.7194859981536865,
|
| 102 |
+
"eval_runtime": 202.3679,
|
| 103 |
+
"eval_samples_per_second": 126.947,
|
| 104 |
+
"eval_steps_per_second": 7.936,
|
| 105 |
+
"eval_total": 25690,
|
| 106 |
+
"step": 300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.054381603480422626,
|
| 110 |
+
"grad_norm": 11.377346992492676,
|
| 111 |
+
"learning_rate": 9.994592914853948e-06,
|
| 112 |
+
"loss": 0.7889,
|
| 113 |
+
"step": 350
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.062150403977625855,
|
| 117 |
+
"grad_norm": 7.450821399688721,
|
| 118 |
+
"learning_rate": 9.993816034804228e-06,
|
| 119 |
+
"loss": 0.7367,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.062150403977625855,
|
| 124 |
+
"eval_HasAns_exact": 71.08991825613079,
|
| 125 |
+
"eval_HasAns_f1": 78.00619214091435,
|
| 126 |
+
"eval_HasAns_total": 25690,
|
| 127 |
+
"eval_best_exact": 71.08991825613079,
|
| 128 |
+
"eval_best_exact_thresh": 0.0,
|
| 129 |
+
"eval_best_f1": 78.00619214091435,
|
| 130 |
+
"eval_best_f1_thresh": 0.0,
|
| 131 |
+
"eval_exact": 71.08991825613079,
|
| 132 |
+
"eval_f1": 78.00619214091435,
|
| 133 |
+
"eval_loss": 0.683600902557373,
|
| 134 |
+
"eval_runtime": 202.4728,
|
| 135 |
+
"eval_samples_per_second": 126.881,
|
| 136 |
+
"eval_steps_per_second": 7.932,
|
| 137 |
+
"eval_total": 25690,
|
| 138 |
+
"step": 400
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.06991920447482909,
|
| 142 |
+
"grad_norm": 14.92029857635498,
|
| 143 |
+
"learning_rate": 9.993039154754508e-06,
|
| 144 |
+
"loss": 0.7838,
|
| 145 |
+
"step": 450
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.07768800497203232,
|
| 149 |
+
"grad_norm": 9.030844688415527,
|
| 150 |
+
"learning_rate": 9.992262274704786e-06,
|
| 151 |
+
"loss": 0.6469,
|
| 152 |
+
"step": 500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.07768800497203232,
|
| 156 |
+
"eval_HasAns_exact": 71.42467886337096,
|
| 157 |
+
"eval_HasAns_f1": 78.23334576784337,
|
| 158 |
+
"eval_HasAns_total": 25690,
|
| 159 |
+
"eval_best_exact": 71.42467886337096,
|
| 160 |
+
"eval_best_exact_thresh": 0.0,
|
| 161 |
+
"eval_best_f1": 78.23334576784337,
|
| 162 |
+
"eval_best_f1_thresh": 0.0,
|
| 163 |
+
"eval_exact": 71.42467886337096,
|
| 164 |
+
"eval_f1": 78.23334576784337,
|
| 165 |
+
"eval_loss": 0.6646179556846619,
|
| 166 |
+
"eval_runtime": 202.6333,
|
| 167 |
+
"eval_samples_per_second": 126.781,
|
| 168 |
+
"eval_steps_per_second": 7.926,
|
| 169 |
+
"eval_total": 25690,
|
| 170 |
+
"step": 500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08545680546923555,
|
| 174 |
+
"grad_norm": 10.103166580200195,
|
| 175 |
+
"learning_rate": 9.991485394655066e-06,
|
| 176 |
+
"loss": 0.725,
|
| 177 |
+
"step": 550
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09322560596643878,
|
| 181 |
+
"grad_norm": 6.986274242401123,
|
| 182 |
+
"learning_rate": 9.990708514605346e-06,
|
| 183 |
+
"loss": 0.6657,
|
| 184 |
+
"step": 600
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.09322560596643878,
|
| 188 |
+
"eval_HasAns_exact": 70.2841572596341,
|
| 189 |
+
"eval_HasAns_f1": 77.1247889416155,
|
| 190 |
+
"eval_HasAns_total": 25690,
|
| 191 |
+
"eval_best_exact": 70.2841572596341,
|
| 192 |
+
"eval_best_exact_thresh": 0.0,
|
| 193 |
+
"eval_best_f1": 77.1247889416155,
|
| 194 |
+
"eval_best_f1_thresh": 0.0,
|
| 195 |
+
"eval_exact": 70.2841572596341,
|
| 196 |
+
"eval_f1": 77.1247889416155,
|
| 197 |
+
"eval_loss": 0.6492825150489807,
|
| 198 |
+
"eval_runtime": 203.3854,
|
| 199 |
+
"eval_samples_per_second": 126.312,
|
| 200 |
+
"eval_steps_per_second": 7.896,
|
| 201 |
+
"eval_total": 25690,
|
| 202 |
+
"step": 600
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.10099440646364201,
|
| 206 |
+
"grad_norm": 10.636602401733398,
|
| 207 |
+
"learning_rate": 9.989931634555626e-06,
|
| 208 |
+
"loss": 0.7337,
|
| 209 |
+
"step": 650
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.10876320696084525,
|
| 213 |
+
"grad_norm": 8.252824783325195,
|
| 214 |
+
"learning_rate": 9.989154754505906e-06,
|
| 215 |
+
"loss": 0.662,
|
| 216 |
+
"step": 700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.10876320696084525,
|
| 220 |
+
"eval_HasAns_exact": 72.22654729466718,
|
| 221 |
+
"eval_HasAns_f1": 79.0143805614001,
|
| 222 |
+
"eval_HasAns_total": 25690,
|
| 223 |
+
"eval_best_exact": 72.22654729466718,
|
| 224 |
+
"eval_best_exact_thresh": 0.0,
|
| 225 |
+
"eval_best_f1": 79.0143805614001,
|
| 226 |
+
"eval_best_f1_thresh": 0.0,
|
| 227 |
+
"eval_exact": 72.22654729466718,
|
| 228 |
+
"eval_f1": 79.0143805614001,
|
| 229 |
+
"eval_loss": 0.6340453028678894,
|
| 230 |
+
"eval_runtime": 202.8216,
|
| 231 |
+
"eval_samples_per_second": 126.663,
|
| 232 |
+
"eval_steps_per_second": 7.918,
|
| 233 |
+
"eval_total": 25690,
|
| 234 |
+
"step": 700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.11653200745804848,
|
| 238 |
+
"grad_norm": 8.463785171508789,
|
| 239 |
+
"learning_rate": 9.988377874456184e-06,
|
| 240 |
+
"loss": 0.7265,
|
| 241 |
+
"step": 750
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12430080795525171,
|
| 245 |
+
"grad_norm": 9.748174667358398,
|
| 246 |
+
"learning_rate": 9.987600994406464e-06,
|
| 247 |
+
"loss": 0.6969,
|
| 248 |
+
"step": 800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.12430080795525171,
|
| 252 |
+
"eval_HasAns_exact": 72.1292331646555,
|
| 253 |
+
"eval_HasAns_f1": 78.83892105701732,
|
| 254 |
+
"eval_HasAns_total": 25690,
|
| 255 |
+
"eval_best_exact": 72.1292331646555,
|
| 256 |
+
"eval_best_exact_thresh": 0.0,
|
| 257 |
+
"eval_best_f1": 78.83892105701732,
|
| 258 |
+
"eval_best_f1_thresh": 0.0,
|
| 259 |
+
"eval_exact": 72.1292331646555,
|
| 260 |
+
"eval_f1": 78.83892105701732,
|
| 261 |
+
"eval_loss": 0.6085864901542664,
|
| 262 |
+
"eval_runtime": 202.3194,
|
| 263 |
+
"eval_samples_per_second": 126.977,
|
| 264 |
+
"eval_steps_per_second": 7.938,
|
| 265 |
+
"eval_total": 25690,
|
| 266 |
+
"step": 800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.13206960845245494,
|
| 270 |
+
"grad_norm": 9.786517143249512,
|
| 271 |
+
"learning_rate": 9.986824114356744e-06,
|
| 272 |
+
"loss": 0.7111,
|
| 273 |
+
"step": 850
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.13983840894965818,
|
| 277 |
+
"grad_norm": 8.391840934753418,
|
| 278 |
+
"learning_rate": 9.986047234307024e-06,
|
| 279 |
+
"loss": 0.669,
|
| 280 |
+
"step": 900
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.13983840894965818,
|
| 284 |
+
"eval_HasAns_exact": 71.89567925262749,
|
| 285 |
+
"eval_HasAns_f1": 78.61371443349637,
|
| 286 |
+
"eval_HasAns_total": 25690,
|
| 287 |
+
"eval_best_exact": 71.89567925262749,
|
| 288 |
+
"eval_best_exact_thresh": 0.0,
|
| 289 |
+
"eval_best_f1": 78.61371443349637,
|
| 290 |
+
"eval_best_f1_thresh": 0.0,
|
| 291 |
+
"eval_exact": 71.89567925262749,
|
| 292 |
+
"eval_f1": 78.61371443349637,
|
| 293 |
+
"eval_loss": 0.5937665104866028,
|
| 294 |
+
"eval_runtime": 202.8476,
|
| 295 |
+
"eval_samples_per_second": 126.647,
|
| 296 |
+
"eval_steps_per_second": 7.917,
|
| 297 |
+
"eval_total": 25690,
|
| 298 |
+
"step": 900
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.1476072094468614,
|
| 302 |
+
"grad_norm": 11.602773666381836,
|
| 303 |
+
"learning_rate": 9.985270354257304e-06,
|
| 304 |
+
"loss": 0.7253,
|
| 305 |
+
"step": 950
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.15537600994406464,
|
| 309 |
+
"grad_norm": 9.150772094726562,
|
| 310 |
+
"learning_rate": 9.984493474207582e-06,
|
| 311 |
+
"loss": 0.6676,
|
| 312 |
+
"step": 1000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.15537600994406464,
|
| 316 |
+
"eval_HasAns_exact": 72.28493577267419,
|
| 317 |
+
"eval_HasAns_f1": 78.8876551339714,
|
| 318 |
+
"eval_HasAns_total": 25690,
|
| 319 |
+
"eval_best_exact": 72.28493577267419,
|
| 320 |
+
"eval_best_exact_thresh": 0.0,
|
| 321 |
+
"eval_best_f1": 78.8876551339714,
|
| 322 |
+
"eval_best_f1_thresh": 0.0,
|
| 323 |
+
"eval_exact": 72.28493577267419,
|
| 324 |
+
"eval_f1": 78.8876551339714,
|
| 325 |
+
"eval_loss": 0.5816648602485657,
|
| 326 |
+
"eval_runtime": 202.8184,
|
| 327 |
+
"eval_samples_per_second": 126.665,
|
| 328 |
+
"eval_steps_per_second": 7.918,
|
| 329 |
+
"eval_total": 25690,
|
| 330 |
+
"step": 1000
|
| 331 |
+
}
|
| 332 |
+
],
|
| 333 |
+
"logging_steps": 50,
|
| 334 |
+
"max_steps": 643600,
|
| 335 |
+
"num_input_tokens_seen": 0,
|
| 336 |
+
"num_train_epochs": 100,
|
| 337 |
+
"save_steps": 500,
|
| 338 |
+
"stateful_callbacks": {
|
| 339 |
+
"EarlyStoppingCallback": {
|
| 340 |
+
"args": {
|
| 341 |
+
"early_stopping_patience": 10,
|
| 342 |
+
"early_stopping_threshold": 0.0
|
| 343 |
+
},
|
| 344 |
+
"attributes": {
|
| 345 |
+
"early_stopping_patience_counter": 3
|
| 346 |
+
}
|
| 347 |
+
},
|
| 348 |
+
"TrainerControl": {
|
| 349 |
+
"args": {
|
| 350 |
+
"should_epoch_stop": false,
|
| 351 |
+
"should_evaluate": false,
|
| 352 |
+
"should_log": false,
|
| 353 |
+
"should_save": true,
|
| 354 |
+
"should_training_stop": false
|
| 355 |
+
},
|
| 356 |
+
"attributes": {}
|
| 357 |
+
}
|
| 358 |
+
},
|
| 359 |
+
"total_flos": 8361496215552000.0,
|
| 360 |
+
"train_batch_size": 16,
|
| 361 |
+
"trial_name": null,
|
| 362 |
+
"trial_params": null
|
| 363 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6670cd309bc79c4638de77be66649432fb3a049d09959fd300cbc983c7c7160d
|
| 3 |
+
size 5304
|
checkpoint-1000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForQuestionAnswering"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"language": "english",
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"name": "Bert",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.50.3",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b5e818a28c003e9d5e292e503ba6339f07e2e958436351bbc477e0529c9b4fc
|
| 3 |
+
size 435596088
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:769230f395510a338c8b7097d73cf1204d74261b21047d516f5174cc75b14eaf
|
| 3 |
+
size 871311930
|
checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba088525666769e1cf08d578b612b2c50f01fcf002579f70e2b63fb97fbe2652
|
| 3 |
+
size 14244
|
checkpoint-1500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0808910e967b8f15cb8cc606607565e13ec061ebffc9c741d03a50211415c905
|
| 3 |
+
size 988
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63aa3335b5a4100e7305fdfb065b15de8bd1e2aeacb68069ea089d83049885f9
|
| 3 |
+
size 1064
|
checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-1500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,523 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1500,
|
| 3 |
+
"best_metric": 79.36155045560372,
|
| 4 |
+
"best_model_checkpoint": "bert-soccer-qa/checkpoint-1500",
|
| 5 |
+
"epoch": 0.23306401491609696,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 1500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007768800497203232,
|
| 14 |
+
"grad_norm": 9.272425651550293,
|
| 15 |
+
"learning_rate": 9.99925419515227e-06,
|
| 16 |
+
"loss": 1.1446,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015537600994406464,
|
| 21 |
+
"grad_norm": 12.237289428710938,
|
| 22 |
+
"learning_rate": 9.99847731510255e-06,
|
| 23 |
+
"loss": 0.9455,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.015537600994406464,
|
| 28 |
+
"eval_HasAns_exact": 69.85208252238225,
|
| 29 |
+
"eval_HasAns_f1": 77.13603651720207,
|
| 30 |
+
"eval_HasAns_total": 25690,
|
| 31 |
+
"eval_best_exact": 69.85208252238225,
|
| 32 |
+
"eval_best_exact_thresh": 0.0,
|
| 33 |
+
"eval_best_f1": 77.13603651720207,
|
| 34 |
+
"eval_best_f1_thresh": 0.0,
|
| 35 |
+
"eval_exact": 69.85208252238225,
|
| 36 |
+
"eval_f1": 77.13603651720207,
|
| 37 |
+
"eval_loss": 0.8127343058586121,
|
| 38 |
+
"eval_runtime": 202.0338,
|
| 39 |
+
"eval_samples_per_second": 127.157,
|
| 40 |
+
"eval_steps_per_second": 7.949,
|
| 41 |
+
"eval_total": 25690,
|
| 42 |
+
"step": 100
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.023306401491609695,
|
| 46 |
+
"grad_norm": 5.626998424530029,
|
| 47 |
+
"learning_rate": 9.997700435052828e-06,
|
| 48 |
+
"loss": 0.8129,
|
| 49 |
+
"step": 150
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.031075201988812928,
|
| 53 |
+
"grad_norm": 6.87526798248291,
|
| 54 |
+
"learning_rate": 9.996923555003108e-06,
|
| 55 |
+
"loss": 0.8743,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.031075201988812928,
|
| 60 |
+
"eval_HasAns_exact": 70.21409108602569,
|
| 61 |
+
"eval_HasAns_f1": 77.38207884007946,
|
| 62 |
+
"eval_HasAns_total": 25690,
|
| 63 |
+
"eval_best_exact": 70.21409108602569,
|
| 64 |
+
"eval_best_exact_thresh": 0.0,
|
| 65 |
+
"eval_best_f1": 77.38207884007946,
|
| 66 |
+
"eval_best_f1_thresh": 0.0,
|
| 67 |
+
"eval_exact": 70.21409108602569,
|
| 68 |
+
"eval_f1": 77.38207884007946,
|
| 69 |
+
"eval_loss": 0.7383215427398682,
|
| 70 |
+
"eval_runtime": 202.5157,
|
| 71 |
+
"eval_samples_per_second": 126.854,
|
| 72 |
+
"eval_steps_per_second": 7.93,
|
| 73 |
+
"eval_total": 25690,
|
| 74 |
+
"step": 200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.03884400248601616,
|
| 78 |
+
"grad_norm": 11.461019515991211,
|
| 79 |
+
"learning_rate": 9.996146674953388e-06,
|
| 80 |
+
"loss": 0.7825,
|
| 81 |
+
"step": 250
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04661280298321939,
|
| 85 |
+
"grad_norm": 9.630631446838379,
|
| 86 |
+
"learning_rate": 9.995369794903668e-06,
|
| 87 |
+
"loss": 0.7189,
|
| 88 |
+
"step": 300
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.04661280298321939,
|
| 92 |
+
"eval_HasAns_exact": 71.03931490852472,
|
| 93 |
+
"eval_HasAns_f1": 78.08897109574,
|
| 94 |
+
"eval_HasAns_total": 25690,
|
| 95 |
+
"eval_best_exact": 71.03931490852472,
|
| 96 |
+
"eval_best_exact_thresh": 0.0,
|
| 97 |
+
"eval_best_f1": 78.08897109574,
|
| 98 |
+
"eval_best_f1_thresh": 0.0,
|
| 99 |
+
"eval_exact": 71.03931490852472,
|
| 100 |
+
"eval_f1": 78.08897109574,
|
| 101 |
+
"eval_loss": 0.7194859981536865,
|
| 102 |
+
"eval_runtime": 202.3679,
|
| 103 |
+
"eval_samples_per_second": 126.947,
|
| 104 |
+
"eval_steps_per_second": 7.936,
|
| 105 |
+
"eval_total": 25690,
|
| 106 |
+
"step": 300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.054381603480422626,
|
| 110 |
+
"grad_norm": 11.377346992492676,
|
| 111 |
+
"learning_rate": 9.994592914853948e-06,
|
| 112 |
+
"loss": 0.7889,
|
| 113 |
+
"step": 350
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.062150403977625855,
|
| 117 |
+
"grad_norm": 7.450821399688721,
|
| 118 |
+
"learning_rate": 9.993816034804228e-06,
|
| 119 |
+
"loss": 0.7367,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.062150403977625855,
|
| 124 |
+
"eval_HasAns_exact": 71.08991825613079,
|
| 125 |
+
"eval_HasAns_f1": 78.00619214091435,
|
| 126 |
+
"eval_HasAns_total": 25690,
|
| 127 |
+
"eval_best_exact": 71.08991825613079,
|
| 128 |
+
"eval_best_exact_thresh": 0.0,
|
| 129 |
+
"eval_best_f1": 78.00619214091435,
|
| 130 |
+
"eval_best_f1_thresh": 0.0,
|
| 131 |
+
"eval_exact": 71.08991825613079,
|
| 132 |
+
"eval_f1": 78.00619214091435,
|
| 133 |
+
"eval_loss": 0.683600902557373,
|
| 134 |
+
"eval_runtime": 202.4728,
|
| 135 |
+
"eval_samples_per_second": 126.881,
|
| 136 |
+
"eval_steps_per_second": 7.932,
|
| 137 |
+
"eval_total": 25690,
|
| 138 |
+
"step": 400
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.06991920447482909,
|
| 142 |
+
"grad_norm": 14.92029857635498,
|
| 143 |
+
"learning_rate": 9.993039154754508e-06,
|
| 144 |
+
"loss": 0.7838,
|
| 145 |
+
"step": 450
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.07768800497203232,
|
| 149 |
+
"grad_norm": 9.030844688415527,
|
| 150 |
+
"learning_rate": 9.992262274704786e-06,
|
| 151 |
+
"loss": 0.6469,
|
| 152 |
+
"step": 500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.07768800497203232,
|
| 156 |
+
"eval_HasAns_exact": 71.42467886337096,
|
| 157 |
+
"eval_HasAns_f1": 78.23334576784337,
|
| 158 |
+
"eval_HasAns_total": 25690,
|
| 159 |
+
"eval_best_exact": 71.42467886337096,
|
| 160 |
+
"eval_best_exact_thresh": 0.0,
|
| 161 |
+
"eval_best_f1": 78.23334576784337,
|
| 162 |
+
"eval_best_f1_thresh": 0.0,
|
| 163 |
+
"eval_exact": 71.42467886337096,
|
| 164 |
+
"eval_f1": 78.23334576784337,
|
| 165 |
+
"eval_loss": 0.6646179556846619,
|
| 166 |
+
"eval_runtime": 202.6333,
|
| 167 |
+
"eval_samples_per_second": 126.781,
|
| 168 |
+
"eval_steps_per_second": 7.926,
|
| 169 |
+
"eval_total": 25690,
|
| 170 |
+
"step": 500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08545680546923555,
|
| 174 |
+
"grad_norm": 10.103166580200195,
|
| 175 |
+
"learning_rate": 9.991485394655066e-06,
|
| 176 |
+
"loss": 0.725,
|
| 177 |
+
"step": 550
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09322560596643878,
|
| 181 |
+
"grad_norm": 6.986274242401123,
|
| 182 |
+
"learning_rate": 9.990708514605346e-06,
|
| 183 |
+
"loss": 0.6657,
|
| 184 |
+
"step": 600
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.09322560596643878,
|
| 188 |
+
"eval_HasAns_exact": 70.2841572596341,
|
| 189 |
+
"eval_HasAns_f1": 77.1247889416155,
|
| 190 |
+
"eval_HasAns_total": 25690,
|
| 191 |
+
"eval_best_exact": 70.2841572596341,
|
| 192 |
+
"eval_best_exact_thresh": 0.0,
|
| 193 |
+
"eval_best_f1": 77.1247889416155,
|
| 194 |
+
"eval_best_f1_thresh": 0.0,
|
| 195 |
+
"eval_exact": 70.2841572596341,
|
| 196 |
+
"eval_f1": 77.1247889416155,
|
| 197 |
+
"eval_loss": 0.6492825150489807,
|
| 198 |
+
"eval_runtime": 203.3854,
|
| 199 |
+
"eval_samples_per_second": 126.312,
|
| 200 |
+
"eval_steps_per_second": 7.896,
|
| 201 |
+
"eval_total": 25690,
|
| 202 |
+
"step": 600
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.10099440646364201,
|
| 206 |
+
"grad_norm": 10.636602401733398,
|
| 207 |
+
"learning_rate": 9.989931634555626e-06,
|
| 208 |
+
"loss": 0.7337,
|
| 209 |
+
"step": 650
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.10876320696084525,
|
| 213 |
+
"grad_norm": 8.252824783325195,
|
| 214 |
+
"learning_rate": 9.989154754505906e-06,
|
| 215 |
+
"loss": 0.662,
|
| 216 |
+
"step": 700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.10876320696084525,
|
| 220 |
+
"eval_HasAns_exact": 72.22654729466718,
|
| 221 |
+
"eval_HasAns_f1": 79.0143805614001,
|
| 222 |
+
"eval_HasAns_total": 25690,
|
| 223 |
+
"eval_best_exact": 72.22654729466718,
|
| 224 |
+
"eval_best_exact_thresh": 0.0,
|
| 225 |
+
"eval_best_f1": 79.0143805614001,
|
| 226 |
+
"eval_best_f1_thresh": 0.0,
|
| 227 |
+
"eval_exact": 72.22654729466718,
|
| 228 |
+
"eval_f1": 79.0143805614001,
|
| 229 |
+
"eval_loss": 0.6340453028678894,
|
| 230 |
+
"eval_runtime": 202.8216,
|
| 231 |
+
"eval_samples_per_second": 126.663,
|
| 232 |
+
"eval_steps_per_second": 7.918,
|
| 233 |
+
"eval_total": 25690,
|
| 234 |
+
"step": 700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.11653200745804848,
|
| 238 |
+
"grad_norm": 8.463785171508789,
|
| 239 |
+
"learning_rate": 9.988377874456184e-06,
|
| 240 |
+
"loss": 0.7265,
|
| 241 |
+
"step": 750
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12430080795525171,
|
| 245 |
+
"grad_norm": 9.748174667358398,
|
| 246 |
+
"learning_rate": 9.987600994406464e-06,
|
| 247 |
+
"loss": 0.6969,
|
| 248 |
+
"step": 800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.12430080795525171,
|
| 252 |
+
"eval_HasAns_exact": 72.1292331646555,
|
| 253 |
+
"eval_HasAns_f1": 78.83892105701732,
|
| 254 |
+
"eval_HasAns_total": 25690,
|
| 255 |
+
"eval_best_exact": 72.1292331646555,
|
| 256 |
+
"eval_best_exact_thresh": 0.0,
|
| 257 |
+
"eval_best_f1": 78.83892105701732,
|
| 258 |
+
"eval_best_f1_thresh": 0.0,
|
| 259 |
+
"eval_exact": 72.1292331646555,
|
| 260 |
+
"eval_f1": 78.83892105701732,
|
| 261 |
+
"eval_loss": 0.6085864901542664,
|
| 262 |
+
"eval_runtime": 202.3194,
|
| 263 |
+
"eval_samples_per_second": 126.977,
|
| 264 |
+
"eval_steps_per_second": 7.938,
|
| 265 |
+
"eval_total": 25690,
|
| 266 |
+
"step": 800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.13206960845245494,
|
| 270 |
+
"grad_norm": 9.786517143249512,
|
| 271 |
+
"learning_rate": 9.986824114356744e-06,
|
| 272 |
+
"loss": 0.7111,
|
| 273 |
+
"step": 850
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.13983840894965818,
|
| 277 |
+
"grad_norm": 8.391840934753418,
|
| 278 |
+
"learning_rate": 9.986047234307024e-06,
|
| 279 |
+
"loss": 0.669,
|
| 280 |
+
"step": 900
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.13983840894965818,
|
| 284 |
+
"eval_HasAns_exact": 71.89567925262749,
|
| 285 |
+
"eval_HasAns_f1": 78.61371443349637,
|
| 286 |
+
"eval_HasAns_total": 25690,
|
| 287 |
+
"eval_best_exact": 71.89567925262749,
|
| 288 |
+
"eval_best_exact_thresh": 0.0,
|
| 289 |
+
"eval_best_f1": 78.61371443349637,
|
| 290 |
+
"eval_best_f1_thresh": 0.0,
|
| 291 |
+
"eval_exact": 71.89567925262749,
|
| 292 |
+
"eval_f1": 78.61371443349637,
|
| 293 |
+
"eval_loss": 0.5937665104866028,
|
| 294 |
+
"eval_runtime": 202.8476,
|
| 295 |
+
"eval_samples_per_second": 126.647,
|
| 296 |
+
"eval_steps_per_second": 7.917,
|
| 297 |
+
"eval_total": 25690,
|
| 298 |
+
"step": 900
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.1476072094468614,
|
| 302 |
+
"grad_norm": 11.602773666381836,
|
| 303 |
+
"learning_rate": 9.985270354257304e-06,
|
| 304 |
+
"loss": 0.7253,
|
| 305 |
+
"step": 950
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.15537600994406464,
|
| 309 |
+
"grad_norm": 9.150772094726562,
|
| 310 |
+
"learning_rate": 9.984493474207582e-06,
|
| 311 |
+
"loss": 0.6676,
|
| 312 |
+
"step": 1000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.15537600994406464,
|
| 316 |
+
"eval_HasAns_exact": 72.28493577267419,
|
| 317 |
+
"eval_HasAns_f1": 78.8876551339714,
|
| 318 |
+
"eval_HasAns_total": 25690,
|
| 319 |
+
"eval_best_exact": 72.28493577267419,
|
| 320 |
+
"eval_best_exact_thresh": 0.0,
|
| 321 |
+
"eval_best_f1": 78.8876551339714,
|
| 322 |
+
"eval_best_f1_thresh": 0.0,
|
| 323 |
+
"eval_exact": 72.28493577267419,
|
| 324 |
+
"eval_f1": 78.8876551339714,
|
| 325 |
+
"eval_loss": 0.5816648602485657,
|
| 326 |
+
"eval_runtime": 202.8184,
|
| 327 |
+
"eval_samples_per_second": 126.665,
|
| 328 |
+
"eval_steps_per_second": 7.918,
|
| 329 |
+
"eval_total": 25690,
|
| 330 |
+
"step": 1000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.16314481044126786,
|
| 334 |
+
"grad_norm": 10.605375289916992,
|
| 335 |
+
"learning_rate": 9.983716594157864e-06,
|
| 336 |
+
"loss": 0.7131,
|
| 337 |
+
"step": 1050
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.1709136109384711,
|
| 341 |
+
"grad_norm": 13.075970649719238,
|
| 342 |
+
"learning_rate": 9.982939714108144e-06,
|
| 343 |
+
"loss": 0.6664,
|
| 344 |
+
"step": 1100
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.1709136109384711,
|
| 348 |
+
"eval_HasAns_exact": 71.95406773063449,
|
| 349 |
+
"eval_HasAns_f1": 78.6814885378308,
|
| 350 |
+
"eval_HasAns_total": 25690,
|
| 351 |
+
"eval_best_exact": 71.95406773063449,
|
| 352 |
+
"eval_best_exact_thresh": 0.0,
|
| 353 |
+
"eval_best_f1": 78.6814885378308,
|
| 354 |
+
"eval_best_f1_thresh": 0.0,
|
| 355 |
+
"eval_exact": 71.95406773063449,
|
| 356 |
+
"eval_f1": 78.6814885378308,
|
| 357 |
+
"eval_loss": 0.5695982575416565,
|
| 358 |
+
"eval_runtime": 202.5931,
|
| 359 |
+
"eval_samples_per_second": 126.806,
|
| 360 |
+
"eval_steps_per_second": 7.927,
|
| 361 |
+
"eval_total": 25690,
|
| 362 |
+
"step": 1100
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.17868241143567434,
|
| 366 |
+
"grad_norm": 12.333536148071289,
|
| 367 |
+
"learning_rate": 9.982162834058422e-06,
|
| 368 |
+
"loss": 0.6016,
|
| 369 |
+
"step": 1150
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.18645121193287756,
|
| 373 |
+
"grad_norm": 9.748809814453125,
|
| 374 |
+
"learning_rate": 9.981385954008702e-06,
|
| 375 |
+
"loss": 0.6006,
|
| 376 |
+
"step": 1200
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.18645121193287756,
|
| 380 |
+
"eval_HasAns_exact": 72.06305955624757,
|
| 381 |
+
"eval_HasAns_f1": 78.75337714295185,
|
| 382 |
+
"eval_HasAns_total": 25690,
|
| 383 |
+
"eval_best_exact": 72.06305955624757,
|
| 384 |
+
"eval_best_exact_thresh": 0.0,
|
| 385 |
+
"eval_best_f1": 78.75337714295185,
|
| 386 |
+
"eval_best_f1_thresh": 0.0,
|
| 387 |
+
"eval_exact": 72.06305955624757,
|
| 388 |
+
"eval_f1": 78.75337714295185,
|
| 389 |
+
"eval_loss": 0.5660755038261414,
|
| 390 |
+
"eval_runtime": 202.8834,
|
| 391 |
+
"eval_samples_per_second": 126.624,
|
| 392 |
+
"eval_steps_per_second": 7.916,
|
| 393 |
+
"eval_total": 25690,
|
| 394 |
+
"step": 1200
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1942200124300808,
|
| 398 |
+
"grad_norm": 9.964409828186035,
|
| 399 |
+
"learning_rate": 9.980609073958982e-06,
|
| 400 |
+
"loss": 0.6268,
|
| 401 |
+
"step": 1250
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.20198881292728402,
|
| 405 |
+
"grad_norm": 6.387030124664307,
|
| 406 |
+
"learning_rate": 9.979832193909262e-06,
|
| 407 |
+
"loss": 0.6111,
|
| 408 |
+
"step": 1300
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.20198881292728402,
|
| 412 |
+
"eval_HasAns_exact": 72.65862203191904,
|
| 413 |
+
"eval_HasAns_f1": 79.23512118883761,
|
| 414 |
+
"eval_HasAns_total": 25690,
|
| 415 |
+
"eval_best_exact": 72.65862203191904,
|
| 416 |
+
"eval_best_exact_thresh": 0.0,
|
| 417 |
+
"eval_best_f1": 79.23512118883761,
|
| 418 |
+
"eval_best_f1_thresh": 0.0,
|
| 419 |
+
"eval_exact": 72.65862203191904,
|
| 420 |
+
"eval_f1": 79.23512118883761,
|
| 421 |
+
"eval_loss": 0.5586764216423035,
|
| 422 |
+
"eval_runtime": 203.0862,
|
| 423 |
+
"eval_samples_per_second": 126.498,
|
| 424 |
+
"eval_steps_per_second": 7.908,
|
| 425 |
+
"eval_total": 25690,
|
| 426 |
+
"step": 1300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.20975761342448726,
|
| 430 |
+
"grad_norm": 9.103731155395508,
|
| 431 |
+
"learning_rate": 9.979055313859542e-06,
|
| 432 |
+
"loss": 0.566,
|
| 433 |
+
"step": 1350
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.2175264139216905,
|
| 437 |
+
"grad_norm": 13.135197639465332,
|
| 438 |
+
"learning_rate": 9.97827843380982e-06,
|
| 439 |
+
"loss": 0.5793,
|
| 440 |
+
"step": 1400
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.2175264139216905,
|
| 444 |
+
"eval_HasAns_exact": 72.39392759828728,
|
| 445 |
+
"eval_HasAns_f1": 79.00515970901382,
|
| 446 |
+
"eval_HasAns_total": 25690,
|
| 447 |
+
"eval_best_exact": 72.39392759828728,
|
| 448 |
+
"eval_best_exact_thresh": 0.0,
|
| 449 |
+
"eval_best_f1": 79.00515970901382,
|
| 450 |
+
"eval_best_f1_thresh": 0.0,
|
| 451 |
+
"eval_exact": 72.39392759828728,
|
| 452 |
+
"eval_f1": 79.00515970901382,
|
| 453 |
+
"eval_loss": 0.5600055456161499,
|
| 454 |
+
"eval_runtime": 202.5804,
|
| 455 |
+
"eval_samples_per_second": 126.814,
|
| 456 |
+
"eval_steps_per_second": 7.928,
|
| 457 |
+
"eval_total": 25690,
|
| 458 |
+
"step": 1400
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.22529521441889372,
|
| 462 |
+
"grad_norm": 9.040102005004883,
|
| 463 |
+
"learning_rate": 9.9775015537601e-06,
|
| 464 |
+
"loss": 0.6309,
|
| 465 |
+
"step": 1450
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.23306401491609696,
|
| 469 |
+
"grad_norm": 11.526878356933594,
|
| 470 |
+
"learning_rate": 9.97672467371038e-06,
|
| 471 |
+
"loss": 0.6064,
|
| 472 |
+
"step": 1500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.23306401491609696,
|
| 476 |
+
"eval_HasAns_exact": 72.74425846632931,
|
| 477 |
+
"eval_HasAns_f1": 79.36155045560372,
|
| 478 |
+
"eval_HasAns_total": 25690,
|
| 479 |
+
"eval_best_exact": 72.74425846632931,
|
| 480 |
+
"eval_best_exact_thresh": 0.0,
|
| 481 |
+
"eval_best_f1": 79.36155045560372,
|
| 482 |
+
"eval_best_f1_thresh": 0.0,
|
| 483 |
+
"eval_exact": 72.74425846632931,
|
| 484 |
+
"eval_f1": 79.36155045560372,
|
| 485 |
+
"eval_loss": 0.5500572323799133,
|
| 486 |
+
"eval_runtime": 202.9048,
|
| 487 |
+
"eval_samples_per_second": 126.611,
|
| 488 |
+
"eval_steps_per_second": 7.915,
|
| 489 |
+
"eval_total": 25690,
|
| 490 |
+
"step": 1500
|
| 491 |
+
}
|
| 492 |
+
],
|
| 493 |
+
"logging_steps": 50,
|
| 494 |
+
"max_steps": 643600,
|
| 495 |
+
"num_input_tokens_seen": 0,
|
| 496 |
+
"num_train_epochs": 100,
|
| 497 |
+
"save_steps": 500,
|
| 498 |
+
"stateful_callbacks": {
|
| 499 |
+
"EarlyStoppingCallback": {
|
| 500 |
+
"args": {
|
| 501 |
+
"early_stopping_patience": 10,
|
| 502 |
+
"early_stopping_threshold": 0.0
|
| 503 |
+
},
|
| 504 |
+
"attributes": {
|
| 505 |
+
"early_stopping_patience_counter": 0
|
| 506 |
+
}
|
| 507 |
+
},
|
| 508 |
+
"TrainerControl": {
|
| 509 |
+
"args": {
|
| 510 |
+
"should_epoch_stop": false,
|
| 511 |
+
"should_evaluate": false,
|
| 512 |
+
"should_log": false,
|
| 513 |
+
"should_save": true,
|
| 514 |
+
"should_training_stop": false
|
| 515 |
+
},
|
| 516 |
+
"attributes": {}
|
| 517 |
+
}
|
| 518 |
+
},
|
| 519 |
+
"total_flos": 1.2542244323328e+16,
|
| 520 |
+
"train_batch_size": 16,
|
| 521 |
+
"trial_name": null,
|
| 522 |
+
"trial_params": null
|
| 523 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6670cd309bc79c4638de77be66649432fb3a049d09959fd300cbc983c7c7160d
|
| 3 |
+
size 5304
|
checkpoint-1500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForQuestionAnswering"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"language": "english",
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"name": "Bert",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.50.3",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab6e779400893356b64fd6c6878843a02872e859352b7ea9771af23ef27e5dec
|
| 3 |
+
size 435596088
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:794a28f346fb8d4167151f7684b737964ac1ec3c38428a462137bbee9f32d6a9
|
| 3 |
+
size 871311930
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c739be83fa1f3a50eced1baaf28a6293b7420251b4834aa76b330fef386f8a43
|
| 3 |
+
size 14244
|
checkpoint-2000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82e70d8e700c15b370a15146b2fea86ef770d6a5dad45912e9295eff40cd0193
|
| 3 |
+
size 988
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:828b5dd5761979bb2a6ab76639bf89d01ac2bc7d013d9600252487ed2a1577d2
|
| 3 |
+
size 1064
|
checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-2000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,683 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1500,
|
| 3 |
+
"best_metric": 79.36155045560372,
|
| 4 |
+
"best_model_checkpoint": "bert-soccer-qa/checkpoint-1500",
|
| 5 |
+
"epoch": 0.3107520198881293,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 2000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007768800497203232,
|
| 14 |
+
"grad_norm": 9.272425651550293,
|
| 15 |
+
"learning_rate": 9.99925419515227e-06,
|
| 16 |
+
"loss": 1.1446,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015537600994406464,
|
| 21 |
+
"grad_norm": 12.237289428710938,
|
| 22 |
+
"learning_rate": 9.99847731510255e-06,
|
| 23 |
+
"loss": 0.9455,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.015537600994406464,
|
| 28 |
+
"eval_HasAns_exact": 69.85208252238225,
|
| 29 |
+
"eval_HasAns_f1": 77.13603651720207,
|
| 30 |
+
"eval_HasAns_total": 25690,
|
| 31 |
+
"eval_best_exact": 69.85208252238225,
|
| 32 |
+
"eval_best_exact_thresh": 0.0,
|
| 33 |
+
"eval_best_f1": 77.13603651720207,
|
| 34 |
+
"eval_best_f1_thresh": 0.0,
|
| 35 |
+
"eval_exact": 69.85208252238225,
|
| 36 |
+
"eval_f1": 77.13603651720207,
|
| 37 |
+
"eval_loss": 0.8127343058586121,
|
| 38 |
+
"eval_runtime": 202.0338,
|
| 39 |
+
"eval_samples_per_second": 127.157,
|
| 40 |
+
"eval_steps_per_second": 7.949,
|
| 41 |
+
"eval_total": 25690,
|
| 42 |
+
"step": 100
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.023306401491609695,
|
| 46 |
+
"grad_norm": 5.626998424530029,
|
| 47 |
+
"learning_rate": 9.997700435052828e-06,
|
| 48 |
+
"loss": 0.8129,
|
| 49 |
+
"step": 150
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.031075201988812928,
|
| 53 |
+
"grad_norm": 6.87526798248291,
|
| 54 |
+
"learning_rate": 9.996923555003108e-06,
|
| 55 |
+
"loss": 0.8743,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.031075201988812928,
|
| 60 |
+
"eval_HasAns_exact": 70.21409108602569,
|
| 61 |
+
"eval_HasAns_f1": 77.38207884007946,
|
| 62 |
+
"eval_HasAns_total": 25690,
|
| 63 |
+
"eval_best_exact": 70.21409108602569,
|
| 64 |
+
"eval_best_exact_thresh": 0.0,
|
| 65 |
+
"eval_best_f1": 77.38207884007946,
|
| 66 |
+
"eval_best_f1_thresh": 0.0,
|
| 67 |
+
"eval_exact": 70.21409108602569,
|
| 68 |
+
"eval_f1": 77.38207884007946,
|
| 69 |
+
"eval_loss": 0.7383215427398682,
|
| 70 |
+
"eval_runtime": 202.5157,
|
| 71 |
+
"eval_samples_per_second": 126.854,
|
| 72 |
+
"eval_steps_per_second": 7.93,
|
| 73 |
+
"eval_total": 25690,
|
| 74 |
+
"step": 200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.03884400248601616,
|
| 78 |
+
"grad_norm": 11.461019515991211,
|
| 79 |
+
"learning_rate": 9.996146674953388e-06,
|
| 80 |
+
"loss": 0.7825,
|
| 81 |
+
"step": 250
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04661280298321939,
|
| 85 |
+
"grad_norm": 9.630631446838379,
|
| 86 |
+
"learning_rate": 9.995369794903668e-06,
|
| 87 |
+
"loss": 0.7189,
|
| 88 |
+
"step": 300
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.04661280298321939,
|
| 92 |
+
"eval_HasAns_exact": 71.03931490852472,
|
| 93 |
+
"eval_HasAns_f1": 78.08897109574,
|
| 94 |
+
"eval_HasAns_total": 25690,
|
| 95 |
+
"eval_best_exact": 71.03931490852472,
|
| 96 |
+
"eval_best_exact_thresh": 0.0,
|
| 97 |
+
"eval_best_f1": 78.08897109574,
|
| 98 |
+
"eval_best_f1_thresh": 0.0,
|
| 99 |
+
"eval_exact": 71.03931490852472,
|
| 100 |
+
"eval_f1": 78.08897109574,
|
| 101 |
+
"eval_loss": 0.7194859981536865,
|
| 102 |
+
"eval_runtime": 202.3679,
|
| 103 |
+
"eval_samples_per_second": 126.947,
|
| 104 |
+
"eval_steps_per_second": 7.936,
|
| 105 |
+
"eval_total": 25690,
|
| 106 |
+
"step": 300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.054381603480422626,
|
| 110 |
+
"grad_norm": 11.377346992492676,
|
| 111 |
+
"learning_rate": 9.994592914853948e-06,
|
| 112 |
+
"loss": 0.7889,
|
| 113 |
+
"step": 350
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.062150403977625855,
|
| 117 |
+
"grad_norm": 7.450821399688721,
|
| 118 |
+
"learning_rate": 9.993816034804228e-06,
|
| 119 |
+
"loss": 0.7367,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.062150403977625855,
|
| 124 |
+
"eval_HasAns_exact": 71.08991825613079,
|
| 125 |
+
"eval_HasAns_f1": 78.00619214091435,
|
| 126 |
+
"eval_HasAns_total": 25690,
|
| 127 |
+
"eval_best_exact": 71.08991825613079,
|
| 128 |
+
"eval_best_exact_thresh": 0.0,
|
| 129 |
+
"eval_best_f1": 78.00619214091435,
|
| 130 |
+
"eval_best_f1_thresh": 0.0,
|
| 131 |
+
"eval_exact": 71.08991825613079,
|
| 132 |
+
"eval_f1": 78.00619214091435,
|
| 133 |
+
"eval_loss": 0.683600902557373,
|
| 134 |
+
"eval_runtime": 202.4728,
|
| 135 |
+
"eval_samples_per_second": 126.881,
|
| 136 |
+
"eval_steps_per_second": 7.932,
|
| 137 |
+
"eval_total": 25690,
|
| 138 |
+
"step": 400
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.06991920447482909,
|
| 142 |
+
"grad_norm": 14.92029857635498,
|
| 143 |
+
"learning_rate": 9.993039154754508e-06,
|
| 144 |
+
"loss": 0.7838,
|
| 145 |
+
"step": 450
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.07768800497203232,
|
| 149 |
+
"grad_norm": 9.030844688415527,
|
| 150 |
+
"learning_rate": 9.992262274704786e-06,
|
| 151 |
+
"loss": 0.6469,
|
| 152 |
+
"step": 500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.07768800497203232,
|
| 156 |
+
"eval_HasAns_exact": 71.42467886337096,
|
| 157 |
+
"eval_HasAns_f1": 78.23334576784337,
|
| 158 |
+
"eval_HasAns_total": 25690,
|
| 159 |
+
"eval_best_exact": 71.42467886337096,
|
| 160 |
+
"eval_best_exact_thresh": 0.0,
|
| 161 |
+
"eval_best_f1": 78.23334576784337,
|
| 162 |
+
"eval_best_f1_thresh": 0.0,
|
| 163 |
+
"eval_exact": 71.42467886337096,
|
| 164 |
+
"eval_f1": 78.23334576784337,
|
| 165 |
+
"eval_loss": 0.6646179556846619,
|
| 166 |
+
"eval_runtime": 202.6333,
|
| 167 |
+
"eval_samples_per_second": 126.781,
|
| 168 |
+
"eval_steps_per_second": 7.926,
|
| 169 |
+
"eval_total": 25690,
|
| 170 |
+
"step": 500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08545680546923555,
|
| 174 |
+
"grad_norm": 10.103166580200195,
|
| 175 |
+
"learning_rate": 9.991485394655066e-06,
|
| 176 |
+
"loss": 0.725,
|
| 177 |
+
"step": 550
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09322560596643878,
|
| 181 |
+
"grad_norm": 6.986274242401123,
|
| 182 |
+
"learning_rate": 9.990708514605346e-06,
|
| 183 |
+
"loss": 0.6657,
|
| 184 |
+
"step": 600
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.09322560596643878,
|
| 188 |
+
"eval_HasAns_exact": 70.2841572596341,
|
| 189 |
+
"eval_HasAns_f1": 77.1247889416155,
|
| 190 |
+
"eval_HasAns_total": 25690,
|
| 191 |
+
"eval_best_exact": 70.2841572596341,
|
| 192 |
+
"eval_best_exact_thresh": 0.0,
|
| 193 |
+
"eval_best_f1": 77.1247889416155,
|
| 194 |
+
"eval_best_f1_thresh": 0.0,
|
| 195 |
+
"eval_exact": 70.2841572596341,
|
| 196 |
+
"eval_f1": 77.1247889416155,
|
| 197 |
+
"eval_loss": 0.6492825150489807,
|
| 198 |
+
"eval_runtime": 203.3854,
|
| 199 |
+
"eval_samples_per_second": 126.312,
|
| 200 |
+
"eval_steps_per_second": 7.896,
|
| 201 |
+
"eval_total": 25690,
|
| 202 |
+
"step": 600
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.10099440646364201,
|
| 206 |
+
"grad_norm": 10.636602401733398,
|
| 207 |
+
"learning_rate": 9.989931634555626e-06,
|
| 208 |
+
"loss": 0.7337,
|
| 209 |
+
"step": 650
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.10876320696084525,
|
| 213 |
+
"grad_norm": 8.252824783325195,
|
| 214 |
+
"learning_rate": 9.989154754505906e-06,
|
| 215 |
+
"loss": 0.662,
|
| 216 |
+
"step": 700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.10876320696084525,
|
| 220 |
+
"eval_HasAns_exact": 72.22654729466718,
|
| 221 |
+
"eval_HasAns_f1": 79.0143805614001,
|
| 222 |
+
"eval_HasAns_total": 25690,
|
| 223 |
+
"eval_best_exact": 72.22654729466718,
|
| 224 |
+
"eval_best_exact_thresh": 0.0,
|
| 225 |
+
"eval_best_f1": 79.0143805614001,
|
| 226 |
+
"eval_best_f1_thresh": 0.0,
|
| 227 |
+
"eval_exact": 72.22654729466718,
|
| 228 |
+
"eval_f1": 79.0143805614001,
|
| 229 |
+
"eval_loss": 0.6340453028678894,
|
| 230 |
+
"eval_runtime": 202.8216,
|
| 231 |
+
"eval_samples_per_second": 126.663,
|
| 232 |
+
"eval_steps_per_second": 7.918,
|
| 233 |
+
"eval_total": 25690,
|
| 234 |
+
"step": 700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.11653200745804848,
|
| 238 |
+
"grad_norm": 8.463785171508789,
|
| 239 |
+
"learning_rate": 9.988377874456184e-06,
|
| 240 |
+
"loss": 0.7265,
|
| 241 |
+
"step": 750
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12430080795525171,
|
| 245 |
+
"grad_norm": 9.748174667358398,
|
| 246 |
+
"learning_rate": 9.987600994406464e-06,
|
| 247 |
+
"loss": 0.6969,
|
| 248 |
+
"step": 800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.12430080795525171,
|
| 252 |
+
"eval_HasAns_exact": 72.1292331646555,
|
| 253 |
+
"eval_HasAns_f1": 78.83892105701732,
|
| 254 |
+
"eval_HasAns_total": 25690,
|
| 255 |
+
"eval_best_exact": 72.1292331646555,
|
| 256 |
+
"eval_best_exact_thresh": 0.0,
|
| 257 |
+
"eval_best_f1": 78.83892105701732,
|
| 258 |
+
"eval_best_f1_thresh": 0.0,
|
| 259 |
+
"eval_exact": 72.1292331646555,
|
| 260 |
+
"eval_f1": 78.83892105701732,
|
| 261 |
+
"eval_loss": 0.6085864901542664,
|
| 262 |
+
"eval_runtime": 202.3194,
|
| 263 |
+
"eval_samples_per_second": 126.977,
|
| 264 |
+
"eval_steps_per_second": 7.938,
|
| 265 |
+
"eval_total": 25690,
|
| 266 |
+
"step": 800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.13206960845245494,
|
| 270 |
+
"grad_norm": 9.786517143249512,
|
| 271 |
+
"learning_rate": 9.986824114356744e-06,
|
| 272 |
+
"loss": 0.7111,
|
| 273 |
+
"step": 850
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.13983840894965818,
|
| 277 |
+
"grad_norm": 8.391840934753418,
|
| 278 |
+
"learning_rate": 9.986047234307024e-06,
|
| 279 |
+
"loss": 0.669,
|
| 280 |
+
"step": 900
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.13983840894965818,
|
| 284 |
+
"eval_HasAns_exact": 71.89567925262749,
|
| 285 |
+
"eval_HasAns_f1": 78.61371443349637,
|
| 286 |
+
"eval_HasAns_total": 25690,
|
| 287 |
+
"eval_best_exact": 71.89567925262749,
|
| 288 |
+
"eval_best_exact_thresh": 0.0,
|
| 289 |
+
"eval_best_f1": 78.61371443349637,
|
| 290 |
+
"eval_best_f1_thresh": 0.0,
|
| 291 |
+
"eval_exact": 71.89567925262749,
|
| 292 |
+
"eval_f1": 78.61371443349637,
|
| 293 |
+
"eval_loss": 0.5937665104866028,
|
| 294 |
+
"eval_runtime": 202.8476,
|
| 295 |
+
"eval_samples_per_second": 126.647,
|
| 296 |
+
"eval_steps_per_second": 7.917,
|
| 297 |
+
"eval_total": 25690,
|
| 298 |
+
"step": 900
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.1476072094468614,
|
| 302 |
+
"grad_norm": 11.602773666381836,
|
| 303 |
+
"learning_rate": 9.985270354257304e-06,
|
| 304 |
+
"loss": 0.7253,
|
| 305 |
+
"step": 950
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.15537600994406464,
|
| 309 |
+
"grad_norm": 9.150772094726562,
|
| 310 |
+
"learning_rate": 9.984493474207582e-06,
|
| 311 |
+
"loss": 0.6676,
|
| 312 |
+
"step": 1000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.15537600994406464,
|
| 316 |
+
"eval_HasAns_exact": 72.28493577267419,
|
| 317 |
+
"eval_HasAns_f1": 78.8876551339714,
|
| 318 |
+
"eval_HasAns_total": 25690,
|
| 319 |
+
"eval_best_exact": 72.28493577267419,
|
| 320 |
+
"eval_best_exact_thresh": 0.0,
|
| 321 |
+
"eval_best_f1": 78.8876551339714,
|
| 322 |
+
"eval_best_f1_thresh": 0.0,
|
| 323 |
+
"eval_exact": 72.28493577267419,
|
| 324 |
+
"eval_f1": 78.8876551339714,
|
| 325 |
+
"eval_loss": 0.5816648602485657,
|
| 326 |
+
"eval_runtime": 202.8184,
|
| 327 |
+
"eval_samples_per_second": 126.665,
|
| 328 |
+
"eval_steps_per_second": 7.918,
|
| 329 |
+
"eval_total": 25690,
|
| 330 |
+
"step": 1000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.16314481044126786,
|
| 334 |
+
"grad_norm": 10.605375289916992,
|
| 335 |
+
"learning_rate": 9.983716594157864e-06,
|
| 336 |
+
"loss": 0.7131,
|
| 337 |
+
"step": 1050
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.1709136109384711,
|
| 341 |
+
"grad_norm": 13.075970649719238,
|
| 342 |
+
"learning_rate": 9.982939714108144e-06,
|
| 343 |
+
"loss": 0.6664,
|
| 344 |
+
"step": 1100
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.1709136109384711,
|
| 348 |
+
"eval_HasAns_exact": 71.95406773063449,
|
| 349 |
+
"eval_HasAns_f1": 78.6814885378308,
|
| 350 |
+
"eval_HasAns_total": 25690,
|
| 351 |
+
"eval_best_exact": 71.95406773063449,
|
| 352 |
+
"eval_best_exact_thresh": 0.0,
|
| 353 |
+
"eval_best_f1": 78.6814885378308,
|
| 354 |
+
"eval_best_f1_thresh": 0.0,
|
| 355 |
+
"eval_exact": 71.95406773063449,
|
| 356 |
+
"eval_f1": 78.6814885378308,
|
| 357 |
+
"eval_loss": 0.5695982575416565,
|
| 358 |
+
"eval_runtime": 202.5931,
|
| 359 |
+
"eval_samples_per_second": 126.806,
|
| 360 |
+
"eval_steps_per_second": 7.927,
|
| 361 |
+
"eval_total": 25690,
|
| 362 |
+
"step": 1100
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.17868241143567434,
|
| 366 |
+
"grad_norm": 12.333536148071289,
|
| 367 |
+
"learning_rate": 9.982162834058422e-06,
|
| 368 |
+
"loss": 0.6016,
|
| 369 |
+
"step": 1150
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.18645121193287756,
|
| 373 |
+
"grad_norm": 9.748809814453125,
|
| 374 |
+
"learning_rate": 9.981385954008702e-06,
|
| 375 |
+
"loss": 0.6006,
|
| 376 |
+
"step": 1200
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.18645121193287756,
|
| 380 |
+
"eval_HasAns_exact": 72.06305955624757,
|
| 381 |
+
"eval_HasAns_f1": 78.75337714295185,
|
| 382 |
+
"eval_HasAns_total": 25690,
|
| 383 |
+
"eval_best_exact": 72.06305955624757,
|
| 384 |
+
"eval_best_exact_thresh": 0.0,
|
| 385 |
+
"eval_best_f1": 78.75337714295185,
|
| 386 |
+
"eval_best_f1_thresh": 0.0,
|
| 387 |
+
"eval_exact": 72.06305955624757,
|
| 388 |
+
"eval_f1": 78.75337714295185,
|
| 389 |
+
"eval_loss": 0.5660755038261414,
|
| 390 |
+
"eval_runtime": 202.8834,
|
| 391 |
+
"eval_samples_per_second": 126.624,
|
| 392 |
+
"eval_steps_per_second": 7.916,
|
| 393 |
+
"eval_total": 25690,
|
| 394 |
+
"step": 1200
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1942200124300808,
|
| 398 |
+
"grad_norm": 9.964409828186035,
|
| 399 |
+
"learning_rate": 9.980609073958982e-06,
|
| 400 |
+
"loss": 0.6268,
|
| 401 |
+
"step": 1250
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.20198881292728402,
|
| 405 |
+
"grad_norm": 6.387030124664307,
|
| 406 |
+
"learning_rate": 9.979832193909262e-06,
|
| 407 |
+
"loss": 0.6111,
|
| 408 |
+
"step": 1300
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.20198881292728402,
|
| 412 |
+
"eval_HasAns_exact": 72.65862203191904,
|
| 413 |
+
"eval_HasAns_f1": 79.23512118883761,
|
| 414 |
+
"eval_HasAns_total": 25690,
|
| 415 |
+
"eval_best_exact": 72.65862203191904,
|
| 416 |
+
"eval_best_exact_thresh": 0.0,
|
| 417 |
+
"eval_best_f1": 79.23512118883761,
|
| 418 |
+
"eval_best_f1_thresh": 0.0,
|
| 419 |
+
"eval_exact": 72.65862203191904,
|
| 420 |
+
"eval_f1": 79.23512118883761,
|
| 421 |
+
"eval_loss": 0.5586764216423035,
|
| 422 |
+
"eval_runtime": 203.0862,
|
| 423 |
+
"eval_samples_per_second": 126.498,
|
| 424 |
+
"eval_steps_per_second": 7.908,
|
| 425 |
+
"eval_total": 25690,
|
| 426 |
+
"step": 1300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.20975761342448726,
|
| 430 |
+
"grad_norm": 9.103731155395508,
|
| 431 |
+
"learning_rate": 9.979055313859542e-06,
|
| 432 |
+
"loss": 0.566,
|
| 433 |
+
"step": 1350
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.2175264139216905,
|
| 437 |
+
"grad_norm": 13.135197639465332,
|
| 438 |
+
"learning_rate": 9.97827843380982e-06,
|
| 439 |
+
"loss": 0.5793,
|
| 440 |
+
"step": 1400
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.2175264139216905,
|
| 444 |
+
"eval_HasAns_exact": 72.39392759828728,
|
| 445 |
+
"eval_HasAns_f1": 79.00515970901382,
|
| 446 |
+
"eval_HasAns_total": 25690,
|
| 447 |
+
"eval_best_exact": 72.39392759828728,
|
| 448 |
+
"eval_best_exact_thresh": 0.0,
|
| 449 |
+
"eval_best_f1": 79.00515970901382,
|
| 450 |
+
"eval_best_f1_thresh": 0.0,
|
| 451 |
+
"eval_exact": 72.39392759828728,
|
| 452 |
+
"eval_f1": 79.00515970901382,
|
| 453 |
+
"eval_loss": 0.5600055456161499,
|
| 454 |
+
"eval_runtime": 202.5804,
|
| 455 |
+
"eval_samples_per_second": 126.814,
|
| 456 |
+
"eval_steps_per_second": 7.928,
|
| 457 |
+
"eval_total": 25690,
|
| 458 |
+
"step": 1400
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.22529521441889372,
|
| 462 |
+
"grad_norm": 9.040102005004883,
|
| 463 |
+
"learning_rate": 9.9775015537601e-06,
|
| 464 |
+
"loss": 0.6309,
|
| 465 |
+
"step": 1450
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.23306401491609696,
|
| 469 |
+
"grad_norm": 11.526878356933594,
|
| 470 |
+
"learning_rate": 9.97672467371038e-06,
|
| 471 |
+
"loss": 0.6064,
|
| 472 |
+
"step": 1500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.23306401491609696,
|
| 476 |
+
"eval_HasAns_exact": 72.74425846632931,
|
| 477 |
+
"eval_HasAns_f1": 79.36155045560372,
|
| 478 |
+
"eval_HasAns_total": 25690,
|
| 479 |
+
"eval_best_exact": 72.74425846632931,
|
| 480 |
+
"eval_best_exact_thresh": 0.0,
|
| 481 |
+
"eval_best_f1": 79.36155045560372,
|
| 482 |
+
"eval_best_f1_thresh": 0.0,
|
| 483 |
+
"eval_exact": 72.74425846632931,
|
| 484 |
+
"eval_f1": 79.36155045560372,
|
| 485 |
+
"eval_loss": 0.5500572323799133,
|
| 486 |
+
"eval_runtime": 202.9048,
|
| 487 |
+
"eval_samples_per_second": 126.611,
|
| 488 |
+
"eval_steps_per_second": 7.915,
|
| 489 |
+
"eval_total": 25690,
|
| 490 |
+
"step": 1500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.24083281541330018,
|
| 494 |
+
"grad_norm": 4.359344482421875,
|
| 495 |
+
"learning_rate": 9.97594779366066e-06,
|
| 496 |
+
"loss": 0.6823,
|
| 497 |
+
"step": 1550
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.24860161591050342,
|
| 501 |
+
"grad_norm": 9.813569068908691,
|
| 502 |
+
"learning_rate": 9.97517091361094e-06,
|
| 503 |
+
"loss": 0.6314,
|
| 504 |
+
"step": 1600
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.24860161591050342,
|
| 508 |
+
"eval_HasAns_exact": 72.27715064227326,
|
| 509 |
+
"eval_HasAns_f1": 78.8175772466993,
|
| 510 |
+
"eval_HasAns_total": 25690,
|
| 511 |
+
"eval_best_exact": 72.27715064227326,
|
| 512 |
+
"eval_best_exact_thresh": 0.0,
|
| 513 |
+
"eval_best_f1": 78.8175772466993,
|
| 514 |
+
"eval_best_f1_thresh": 0.0,
|
| 515 |
+
"eval_exact": 72.27715064227326,
|
| 516 |
+
"eval_f1": 78.8175772466993,
|
| 517 |
+
"eval_loss": 0.5353918075561523,
|
| 518 |
+
"eval_runtime": 202.6516,
|
| 519 |
+
"eval_samples_per_second": 126.769,
|
| 520 |
+
"eval_steps_per_second": 7.925,
|
| 521 |
+
"eval_total": 25690,
|
| 522 |
+
"step": 1600
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.25637041640770664,
|
| 526 |
+
"grad_norm": 7.802361965179443,
|
| 527 |
+
"learning_rate": 9.974394033561218e-06,
|
| 528 |
+
"loss": 0.6026,
|
| 529 |
+
"step": 1650
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.2641392169049099,
|
| 533 |
+
"grad_norm": 15.137731552124023,
|
| 534 |
+
"learning_rate": 9.973617153511498e-06,
|
| 535 |
+
"loss": 0.6741,
|
| 536 |
+
"step": 1700
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.2641392169049099,
|
| 540 |
+
"eval_HasAns_exact": 72.1058777734527,
|
| 541 |
+
"eval_HasAns_f1": 78.67773271200794,
|
| 542 |
+
"eval_HasAns_total": 25690,
|
| 543 |
+
"eval_best_exact": 72.1058777734527,
|
| 544 |
+
"eval_best_exact_thresh": 0.0,
|
| 545 |
+
"eval_best_f1": 78.67773271200794,
|
| 546 |
+
"eval_best_f1_thresh": 0.0,
|
| 547 |
+
"eval_exact": 72.1058777734527,
|
| 548 |
+
"eval_f1": 78.67773271200794,
|
| 549 |
+
"eval_loss": 0.5329614877700806,
|
| 550 |
+
"eval_runtime": 202.7192,
|
| 551 |
+
"eval_samples_per_second": 126.727,
|
| 552 |
+
"eval_steps_per_second": 7.922,
|
| 553 |
+
"eval_total": 25690,
|
| 554 |
+
"step": 1700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.2719080174021131,
|
| 558 |
+
"grad_norm": 11.30902099609375,
|
| 559 |
+
"learning_rate": 9.972840273461778e-06,
|
| 560 |
+
"loss": 0.6069,
|
| 561 |
+
"step": 1750
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.27967681789931637,
|
| 565 |
+
"grad_norm": 9.311911582946777,
|
| 566 |
+
"learning_rate": 9.972063393412058e-06,
|
| 567 |
+
"loss": 0.5912,
|
| 568 |
+
"step": 1800
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.27967681789931637,
|
| 572 |
+
"eval_HasAns_exact": 72.24990268586998,
|
| 573 |
+
"eval_HasAns_f1": 78.7891482246884,
|
| 574 |
+
"eval_HasAns_total": 25690,
|
| 575 |
+
"eval_best_exact": 72.24990268586998,
|
| 576 |
+
"eval_best_exact_thresh": 0.0,
|
| 577 |
+
"eval_best_f1": 78.7891482246884,
|
| 578 |
+
"eval_best_f1_thresh": 0.0,
|
| 579 |
+
"eval_exact": 72.24990268586998,
|
| 580 |
+
"eval_f1": 78.7891482246884,
|
| 581 |
+
"eval_loss": 0.5291240811347961,
|
| 582 |
+
"eval_runtime": 202.8091,
|
| 583 |
+
"eval_samples_per_second": 126.671,
|
| 584 |
+
"eval_steps_per_second": 7.919,
|
| 585 |
+
"eval_total": 25690,
|
| 586 |
+
"step": 1800
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.28744561839651955,
|
| 590 |
+
"grad_norm": 9.725021362304688,
|
| 591 |
+
"learning_rate": 9.971286513362338e-06,
|
| 592 |
+
"loss": 0.5943,
|
| 593 |
+
"step": 1850
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.2952144188937228,
|
| 597 |
+
"grad_norm": 8.321113586425781,
|
| 598 |
+
"learning_rate": 9.970509633312618e-06,
|
| 599 |
+
"loss": 0.584,
|
| 600 |
+
"step": 1900
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.2952144188937228,
|
| 604 |
+
"eval_HasAns_exact": 72.56909303230829,
|
| 605 |
+
"eval_HasAns_f1": 79.12955371544794,
|
| 606 |
+
"eval_HasAns_total": 25690,
|
| 607 |
+
"eval_best_exact": 72.56909303230829,
|
| 608 |
+
"eval_best_exact_thresh": 0.0,
|
| 609 |
+
"eval_best_f1": 79.12955371544794,
|
| 610 |
+
"eval_best_f1_thresh": 0.0,
|
| 611 |
+
"eval_exact": 72.56909303230829,
|
| 612 |
+
"eval_f1": 79.12955371544794,
|
| 613 |
+
"eval_loss": 0.5198299288749695,
|
| 614 |
+
"eval_runtime": 202.5651,
|
| 615 |
+
"eval_samples_per_second": 126.823,
|
| 616 |
+
"eval_steps_per_second": 7.928,
|
| 617 |
+
"eval_total": 25690,
|
| 618 |
+
"step": 1900
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.30298321939092604,
|
| 622 |
+
"grad_norm": 11.973769187927246,
|
| 623 |
+
"learning_rate": 9.969732753262898e-06,
|
| 624 |
+
"loss": 0.5895,
|
| 625 |
+
"step": 1950
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.3107520198881293,
|
| 629 |
+
"grad_norm": 9.40645980834961,
|
| 630 |
+
"learning_rate": 9.968955873213176e-06,
|
| 631 |
+
"loss": 0.64,
|
| 632 |
+
"step": 2000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.3107520198881293,
|
| 636 |
+
"eval_HasAns_exact": 72.79096924873491,
|
| 637 |
+
"eval_HasAns_f1": 79.28733698122942,
|
| 638 |
+
"eval_HasAns_total": 25690,
|
| 639 |
+
"eval_best_exact": 72.79096924873491,
|
| 640 |
+
"eval_best_exact_thresh": 0.0,
|
| 641 |
+
"eval_best_f1": 79.28733698122942,
|
| 642 |
+
"eval_best_f1_thresh": 0.0,
|
| 643 |
+
"eval_exact": 72.79096924873491,
|
| 644 |
+
"eval_f1": 79.28733698122942,
|
| 645 |
+
"eval_loss": 0.5117060542106628,
|
| 646 |
+
"eval_runtime": 203.1079,
|
| 647 |
+
"eval_samples_per_second": 126.485,
|
| 648 |
+
"eval_steps_per_second": 7.907,
|
| 649 |
+
"eval_total": 25690,
|
| 650 |
+
"step": 2000
|
| 651 |
+
}
|
| 652 |
+
],
|
| 653 |
+
"logging_steps": 50,
|
| 654 |
+
"max_steps": 643600,
|
| 655 |
+
"num_input_tokens_seen": 0,
|
| 656 |
+
"num_train_epochs": 100,
|
| 657 |
+
"save_steps": 500,
|
| 658 |
+
"stateful_callbacks": {
|
| 659 |
+
"EarlyStoppingCallback": {
|
| 660 |
+
"args": {
|
| 661 |
+
"early_stopping_patience": 10,
|
| 662 |
+
"early_stopping_threshold": 0.0
|
| 663 |
+
},
|
| 664 |
+
"attributes": {
|
| 665 |
+
"early_stopping_patience_counter": 5
|
| 666 |
+
}
|
| 667 |
+
},
|
| 668 |
+
"TrainerControl": {
|
| 669 |
+
"args": {
|
| 670 |
+
"should_epoch_stop": false,
|
| 671 |
+
"should_evaluate": false,
|
| 672 |
+
"should_log": false,
|
| 673 |
+
"should_save": true,
|
| 674 |
+
"should_training_stop": false
|
| 675 |
+
},
|
| 676 |
+
"attributes": {}
|
| 677 |
+
}
|
| 678 |
+
},
|
| 679 |
+
"total_flos": 1.6722992431104e+16,
|
| 680 |
+
"train_batch_size": 16,
|
| 681 |
+
"trial_name": null,
|
| 682 |
+
"trial_params": null
|
| 683 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6670cd309bc79c4638de77be66649432fb3a049d09959fd300cbc983c7c7160d
|
| 3 |
+
size 5304
|
checkpoint-2000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForQuestionAnswering"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"language": "english",
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"name": "Bert",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.50.3",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b5ac3b298f089970fd5faa229f4e624022da482e3ed94e91fd321c508c86ed
|
| 3 |
+
size 435596088
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daf4067887ac289ee1cb25161d18e7a9b07789033905e88e16b492c53d559a46
|
| 3 |
+
size 871311930
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aac6ce6758a41be9c411ebc19f7bc46befaf0c549f6a057a6116e3dce102cc27
|
| 3 |
+
size 14244
|
checkpoint-2500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c42f07c52d5e58052c8ab9dd9e6ca80449cf9199ddded4d95cf9bf3e369b2da7
|
| 3 |
+
size 988
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8007a77b9380d5b0e9793dad6d7cce01a2173bd308ed9eec6014186473ea217a
|
| 3 |
+
size 1064
|
checkpoint-2500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2500,
|
| 3 |
+
"best_metric": 79.95807844595133,
|
| 4 |
+
"best_model_checkpoint": "bert-soccer-qa/checkpoint-2500",
|
| 5 |
+
"epoch": 0.3884400248601616,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007768800497203232,
|
| 14 |
+
"grad_norm": 9.272425651550293,
|
| 15 |
+
"learning_rate": 9.99925419515227e-06,
|
| 16 |
+
"loss": 1.1446,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015537600994406464,
|
| 21 |
+
"grad_norm": 12.237289428710938,
|
| 22 |
+
"learning_rate": 9.99847731510255e-06,
|
| 23 |
+
"loss": 0.9455,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.015537600994406464,
|
| 28 |
+
"eval_HasAns_exact": 69.85208252238225,
|
| 29 |
+
"eval_HasAns_f1": 77.13603651720207,
|
| 30 |
+
"eval_HasAns_total": 25690,
|
| 31 |
+
"eval_best_exact": 69.85208252238225,
|
| 32 |
+
"eval_best_exact_thresh": 0.0,
|
| 33 |
+
"eval_best_f1": 77.13603651720207,
|
| 34 |
+
"eval_best_f1_thresh": 0.0,
|
| 35 |
+
"eval_exact": 69.85208252238225,
|
| 36 |
+
"eval_f1": 77.13603651720207,
|
| 37 |
+
"eval_loss": 0.8127343058586121,
|
| 38 |
+
"eval_runtime": 202.0338,
|
| 39 |
+
"eval_samples_per_second": 127.157,
|
| 40 |
+
"eval_steps_per_second": 7.949,
|
| 41 |
+
"eval_total": 25690,
|
| 42 |
+
"step": 100
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.023306401491609695,
|
| 46 |
+
"grad_norm": 5.626998424530029,
|
| 47 |
+
"learning_rate": 9.997700435052828e-06,
|
| 48 |
+
"loss": 0.8129,
|
| 49 |
+
"step": 150
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.031075201988812928,
|
| 53 |
+
"grad_norm": 6.87526798248291,
|
| 54 |
+
"learning_rate": 9.996923555003108e-06,
|
| 55 |
+
"loss": 0.8743,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.031075201988812928,
|
| 60 |
+
"eval_HasAns_exact": 70.21409108602569,
|
| 61 |
+
"eval_HasAns_f1": 77.38207884007946,
|
| 62 |
+
"eval_HasAns_total": 25690,
|
| 63 |
+
"eval_best_exact": 70.21409108602569,
|
| 64 |
+
"eval_best_exact_thresh": 0.0,
|
| 65 |
+
"eval_best_f1": 77.38207884007946,
|
| 66 |
+
"eval_best_f1_thresh": 0.0,
|
| 67 |
+
"eval_exact": 70.21409108602569,
|
| 68 |
+
"eval_f1": 77.38207884007946,
|
| 69 |
+
"eval_loss": 0.7383215427398682,
|
| 70 |
+
"eval_runtime": 202.5157,
|
| 71 |
+
"eval_samples_per_second": 126.854,
|
| 72 |
+
"eval_steps_per_second": 7.93,
|
| 73 |
+
"eval_total": 25690,
|
| 74 |
+
"step": 200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.03884400248601616,
|
| 78 |
+
"grad_norm": 11.461019515991211,
|
| 79 |
+
"learning_rate": 9.996146674953388e-06,
|
| 80 |
+
"loss": 0.7825,
|
| 81 |
+
"step": 250
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04661280298321939,
|
| 85 |
+
"grad_norm": 9.630631446838379,
|
| 86 |
+
"learning_rate": 9.995369794903668e-06,
|
| 87 |
+
"loss": 0.7189,
|
| 88 |
+
"step": 300
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.04661280298321939,
|
| 92 |
+
"eval_HasAns_exact": 71.03931490852472,
|
| 93 |
+
"eval_HasAns_f1": 78.08897109574,
|
| 94 |
+
"eval_HasAns_total": 25690,
|
| 95 |
+
"eval_best_exact": 71.03931490852472,
|
| 96 |
+
"eval_best_exact_thresh": 0.0,
|
| 97 |
+
"eval_best_f1": 78.08897109574,
|
| 98 |
+
"eval_best_f1_thresh": 0.0,
|
| 99 |
+
"eval_exact": 71.03931490852472,
|
| 100 |
+
"eval_f1": 78.08897109574,
|
| 101 |
+
"eval_loss": 0.7194859981536865,
|
| 102 |
+
"eval_runtime": 202.3679,
|
| 103 |
+
"eval_samples_per_second": 126.947,
|
| 104 |
+
"eval_steps_per_second": 7.936,
|
| 105 |
+
"eval_total": 25690,
|
| 106 |
+
"step": 300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.054381603480422626,
|
| 110 |
+
"grad_norm": 11.377346992492676,
|
| 111 |
+
"learning_rate": 9.994592914853948e-06,
|
| 112 |
+
"loss": 0.7889,
|
| 113 |
+
"step": 350
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.062150403977625855,
|
| 117 |
+
"grad_norm": 7.450821399688721,
|
| 118 |
+
"learning_rate": 9.993816034804228e-06,
|
| 119 |
+
"loss": 0.7367,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.062150403977625855,
|
| 124 |
+
"eval_HasAns_exact": 71.08991825613079,
|
| 125 |
+
"eval_HasAns_f1": 78.00619214091435,
|
| 126 |
+
"eval_HasAns_total": 25690,
|
| 127 |
+
"eval_best_exact": 71.08991825613079,
|
| 128 |
+
"eval_best_exact_thresh": 0.0,
|
| 129 |
+
"eval_best_f1": 78.00619214091435,
|
| 130 |
+
"eval_best_f1_thresh": 0.0,
|
| 131 |
+
"eval_exact": 71.08991825613079,
|
| 132 |
+
"eval_f1": 78.00619214091435,
|
| 133 |
+
"eval_loss": 0.683600902557373,
|
| 134 |
+
"eval_runtime": 202.4728,
|
| 135 |
+
"eval_samples_per_second": 126.881,
|
| 136 |
+
"eval_steps_per_second": 7.932,
|
| 137 |
+
"eval_total": 25690,
|
| 138 |
+
"step": 400
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.06991920447482909,
|
| 142 |
+
"grad_norm": 14.92029857635498,
|
| 143 |
+
"learning_rate": 9.993039154754508e-06,
|
| 144 |
+
"loss": 0.7838,
|
| 145 |
+
"step": 450
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.07768800497203232,
|
| 149 |
+
"grad_norm": 9.030844688415527,
|
| 150 |
+
"learning_rate": 9.992262274704786e-06,
|
| 151 |
+
"loss": 0.6469,
|
| 152 |
+
"step": 500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.07768800497203232,
|
| 156 |
+
"eval_HasAns_exact": 71.42467886337096,
|
| 157 |
+
"eval_HasAns_f1": 78.23334576784337,
|
| 158 |
+
"eval_HasAns_total": 25690,
|
| 159 |
+
"eval_best_exact": 71.42467886337096,
|
| 160 |
+
"eval_best_exact_thresh": 0.0,
|
| 161 |
+
"eval_best_f1": 78.23334576784337,
|
| 162 |
+
"eval_best_f1_thresh": 0.0,
|
| 163 |
+
"eval_exact": 71.42467886337096,
|
| 164 |
+
"eval_f1": 78.23334576784337,
|
| 165 |
+
"eval_loss": 0.6646179556846619,
|
| 166 |
+
"eval_runtime": 202.6333,
|
| 167 |
+
"eval_samples_per_second": 126.781,
|
| 168 |
+
"eval_steps_per_second": 7.926,
|
| 169 |
+
"eval_total": 25690,
|
| 170 |
+
"step": 500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.08545680546923555,
|
| 174 |
+
"grad_norm": 10.103166580200195,
|
| 175 |
+
"learning_rate": 9.991485394655066e-06,
|
| 176 |
+
"loss": 0.725,
|
| 177 |
+
"step": 550
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09322560596643878,
|
| 181 |
+
"grad_norm": 6.986274242401123,
|
| 182 |
+
"learning_rate": 9.990708514605346e-06,
|
| 183 |
+
"loss": 0.6657,
|
| 184 |
+
"step": 600
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.09322560596643878,
|
| 188 |
+
"eval_HasAns_exact": 70.2841572596341,
|
| 189 |
+
"eval_HasAns_f1": 77.1247889416155,
|
| 190 |
+
"eval_HasAns_total": 25690,
|
| 191 |
+
"eval_best_exact": 70.2841572596341,
|
| 192 |
+
"eval_best_exact_thresh": 0.0,
|
| 193 |
+
"eval_best_f1": 77.1247889416155,
|
| 194 |
+
"eval_best_f1_thresh": 0.0,
|
| 195 |
+
"eval_exact": 70.2841572596341,
|
| 196 |
+
"eval_f1": 77.1247889416155,
|
| 197 |
+
"eval_loss": 0.6492825150489807,
|
| 198 |
+
"eval_runtime": 203.3854,
|
| 199 |
+
"eval_samples_per_second": 126.312,
|
| 200 |
+
"eval_steps_per_second": 7.896,
|
| 201 |
+
"eval_total": 25690,
|
| 202 |
+
"step": 600
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.10099440646364201,
|
| 206 |
+
"grad_norm": 10.636602401733398,
|
| 207 |
+
"learning_rate": 9.989931634555626e-06,
|
| 208 |
+
"loss": 0.7337,
|
| 209 |
+
"step": 650
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.10876320696084525,
|
| 213 |
+
"grad_norm": 8.252824783325195,
|
| 214 |
+
"learning_rate": 9.989154754505906e-06,
|
| 215 |
+
"loss": 0.662,
|
| 216 |
+
"step": 700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.10876320696084525,
|
| 220 |
+
"eval_HasAns_exact": 72.22654729466718,
|
| 221 |
+
"eval_HasAns_f1": 79.0143805614001,
|
| 222 |
+
"eval_HasAns_total": 25690,
|
| 223 |
+
"eval_best_exact": 72.22654729466718,
|
| 224 |
+
"eval_best_exact_thresh": 0.0,
|
| 225 |
+
"eval_best_f1": 79.0143805614001,
|
| 226 |
+
"eval_best_f1_thresh": 0.0,
|
| 227 |
+
"eval_exact": 72.22654729466718,
|
| 228 |
+
"eval_f1": 79.0143805614001,
|
| 229 |
+
"eval_loss": 0.6340453028678894,
|
| 230 |
+
"eval_runtime": 202.8216,
|
| 231 |
+
"eval_samples_per_second": 126.663,
|
| 232 |
+
"eval_steps_per_second": 7.918,
|
| 233 |
+
"eval_total": 25690,
|
| 234 |
+
"step": 700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.11653200745804848,
|
| 238 |
+
"grad_norm": 8.463785171508789,
|
| 239 |
+
"learning_rate": 9.988377874456184e-06,
|
| 240 |
+
"loss": 0.7265,
|
| 241 |
+
"step": 750
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12430080795525171,
|
| 245 |
+
"grad_norm": 9.748174667358398,
|
| 246 |
+
"learning_rate": 9.987600994406464e-06,
|
| 247 |
+
"loss": 0.6969,
|
| 248 |
+
"step": 800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.12430080795525171,
|
| 252 |
+
"eval_HasAns_exact": 72.1292331646555,
|
| 253 |
+
"eval_HasAns_f1": 78.83892105701732,
|
| 254 |
+
"eval_HasAns_total": 25690,
|
| 255 |
+
"eval_best_exact": 72.1292331646555,
|
| 256 |
+
"eval_best_exact_thresh": 0.0,
|
| 257 |
+
"eval_best_f1": 78.83892105701732,
|
| 258 |
+
"eval_best_f1_thresh": 0.0,
|
| 259 |
+
"eval_exact": 72.1292331646555,
|
| 260 |
+
"eval_f1": 78.83892105701732,
|
| 261 |
+
"eval_loss": 0.6085864901542664,
|
| 262 |
+
"eval_runtime": 202.3194,
|
| 263 |
+
"eval_samples_per_second": 126.977,
|
| 264 |
+
"eval_steps_per_second": 7.938,
|
| 265 |
+
"eval_total": 25690,
|
| 266 |
+
"step": 800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.13206960845245494,
|
| 270 |
+
"grad_norm": 9.786517143249512,
|
| 271 |
+
"learning_rate": 9.986824114356744e-06,
|
| 272 |
+
"loss": 0.7111,
|
| 273 |
+
"step": 850
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.13983840894965818,
|
| 277 |
+
"grad_norm": 8.391840934753418,
|
| 278 |
+
"learning_rate": 9.986047234307024e-06,
|
| 279 |
+
"loss": 0.669,
|
| 280 |
+
"step": 900
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.13983840894965818,
|
| 284 |
+
"eval_HasAns_exact": 71.89567925262749,
|
| 285 |
+
"eval_HasAns_f1": 78.61371443349637,
|
| 286 |
+
"eval_HasAns_total": 25690,
|
| 287 |
+
"eval_best_exact": 71.89567925262749,
|
| 288 |
+
"eval_best_exact_thresh": 0.0,
|
| 289 |
+
"eval_best_f1": 78.61371443349637,
|
| 290 |
+
"eval_best_f1_thresh": 0.0,
|
| 291 |
+
"eval_exact": 71.89567925262749,
|
| 292 |
+
"eval_f1": 78.61371443349637,
|
| 293 |
+
"eval_loss": 0.5937665104866028,
|
| 294 |
+
"eval_runtime": 202.8476,
|
| 295 |
+
"eval_samples_per_second": 126.647,
|
| 296 |
+
"eval_steps_per_second": 7.917,
|
| 297 |
+
"eval_total": 25690,
|
| 298 |
+
"step": 900
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.1476072094468614,
|
| 302 |
+
"grad_norm": 11.602773666381836,
|
| 303 |
+
"learning_rate": 9.985270354257304e-06,
|
| 304 |
+
"loss": 0.7253,
|
| 305 |
+
"step": 950
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.15537600994406464,
|
| 309 |
+
"grad_norm": 9.150772094726562,
|
| 310 |
+
"learning_rate": 9.984493474207582e-06,
|
| 311 |
+
"loss": 0.6676,
|
| 312 |
+
"step": 1000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.15537600994406464,
|
| 316 |
+
"eval_HasAns_exact": 72.28493577267419,
|
| 317 |
+
"eval_HasAns_f1": 78.8876551339714,
|
| 318 |
+
"eval_HasAns_total": 25690,
|
| 319 |
+
"eval_best_exact": 72.28493577267419,
|
| 320 |
+
"eval_best_exact_thresh": 0.0,
|
| 321 |
+
"eval_best_f1": 78.8876551339714,
|
| 322 |
+
"eval_best_f1_thresh": 0.0,
|
| 323 |
+
"eval_exact": 72.28493577267419,
|
| 324 |
+
"eval_f1": 78.8876551339714,
|
| 325 |
+
"eval_loss": 0.5816648602485657,
|
| 326 |
+
"eval_runtime": 202.8184,
|
| 327 |
+
"eval_samples_per_second": 126.665,
|
| 328 |
+
"eval_steps_per_second": 7.918,
|
| 329 |
+
"eval_total": 25690,
|
| 330 |
+
"step": 1000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.16314481044126786,
|
| 334 |
+
"grad_norm": 10.605375289916992,
|
| 335 |
+
"learning_rate": 9.983716594157864e-06,
|
| 336 |
+
"loss": 0.7131,
|
| 337 |
+
"step": 1050
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.1709136109384711,
|
| 341 |
+
"grad_norm": 13.075970649719238,
|
| 342 |
+
"learning_rate": 9.982939714108144e-06,
|
| 343 |
+
"loss": 0.6664,
|
| 344 |
+
"step": 1100
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.1709136109384711,
|
| 348 |
+
"eval_HasAns_exact": 71.95406773063449,
|
| 349 |
+
"eval_HasAns_f1": 78.6814885378308,
|
| 350 |
+
"eval_HasAns_total": 25690,
|
| 351 |
+
"eval_best_exact": 71.95406773063449,
|
| 352 |
+
"eval_best_exact_thresh": 0.0,
|
| 353 |
+
"eval_best_f1": 78.6814885378308,
|
| 354 |
+
"eval_best_f1_thresh": 0.0,
|
| 355 |
+
"eval_exact": 71.95406773063449,
|
| 356 |
+
"eval_f1": 78.6814885378308,
|
| 357 |
+
"eval_loss": 0.5695982575416565,
|
| 358 |
+
"eval_runtime": 202.5931,
|
| 359 |
+
"eval_samples_per_second": 126.806,
|
| 360 |
+
"eval_steps_per_second": 7.927,
|
| 361 |
+
"eval_total": 25690,
|
| 362 |
+
"step": 1100
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.17868241143567434,
|
| 366 |
+
"grad_norm": 12.333536148071289,
|
| 367 |
+
"learning_rate": 9.982162834058422e-06,
|
| 368 |
+
"loss": 0.6016,
|
| 369 |
+
"step": 1150
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.18645121193287756,
|
| 373 |
+
"grad_norm": 9.748809814453125,
|
| 374 |
+
"learning_rate": 9.981385954008702e-06,
|
| 375 |
+
"loss": 0.6006,
|
| 376 |
+
"step": 1200
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.18645121193287756,
|
| 380 |
+
"eval_HasAns_exact": 72.06305955624757,
|
| 381 |
+
"eval_HasAns_f1": 78.75337714295185,
|
| 382 |
+
"eval_HasAns_total": 25690,
|
| 383 |
+
"eval_best_exact": 72.06305955624757,
|
| 384 |
+
"eval_best_exact_thresh": 0.0,
|
| 385 |
+
"eval_best_f1": 78.75337714295185,
|
| 386 |
+
"eval_best_f1_thresh": 0.0,
|
| 387 |
+
"eval_exact": 72.06305955624757,
|
| 388 |
+
"eval_f1": 78.75337714295185,
|
| 389 |
+
"eval_loss": 0.5660755038261414,
|
| 390 |
+
"eval_runtime": 202.8834,
|
| 391 |
+
"eval_samples_per_second": 126.624,
|
| 392 |
+
"eval_steps_per_second": 7.916,
|
| 393 |
+
"eval_total": 25690,
|
| 394 |
+
"step": 1200
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.1942200124300808,
|
| 398 |
+
"grad_norm": 9.964409828186035,
|
| 399 |
+
"learning_rate": 9.980609073958982e-06,
|
| 400 |
+
"loss": 0.6268,
|
| 401 |
+
"step": 1250
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.20198881292728402,
|
| 405 |
+
"grad_norm": 6.387030124664307,
|
| 406 |
+
"learning_rate": 9.979832193909262e-06,
|
| 407 |
+
"loss": 0.6111,
|
| 408 |
+
"step": 1300
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.20198881292728402,
|
| 412 |
+
"eval_HasAns_exact": 72.65862203191904,
|
| 413 |
+
"eval_HasAns_f1": 79.23512118883761,
|
| 414 |
+
"eval_HasAns_total": 25690,
|
| 415 |
+
"eval_best_exact": 72.65862203191904,
|
| 416 |
+
"eval_best_exact_thresh": 0.0,
|
| 417 |
+
"eval_best_f1": 79.23512118883761,
|
| 418 |
+
"eval_best_f1_thresh": 0.0,
|
| 419 |
+
"eval_exact": 72.65862203191904,
|
| 420 |
+
"eval_f1": 79.23512118883761,
|
| 421 |
+
"eval_loss": 0.5586764216423035,
|
| 422 |
+
"eval_runtime": 203.0862,
|
| 423 |
+
"eval_samples_per_second": 126.498,
|
| 424 |
+
"eval_steps_per_second": 7.908,
|
| 425 |
+
"eval_total": 25690,
|
| 426 |
+
"step": 1300
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.20975761342448726,
|
| 430 |
+
"grad_norm": 9.103731155395508,
|
| 431 |
+
"learning_rate": 9.979055313859542e-06,
|
| 432 |
+
"loss": 0.566,
|
| 433 |
+
"step": 1350
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 0.2175264139216905,
|
| 437 |
+
"grad_norm": 13.135197639465332,
|
| 438 |
+
"learning_rate": 9.97827843380982e-06,
|
| 439 |
+
"loss": 0.5793,
|
| 440 |
+
"step": 1400
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.2175264139216905,
|
| 444 |
+
"eval_HasAns_exact": 72.39392759828728,
|
| 445 |
+
"eval_HasAns_f1": 79.00515970901382,
|
| 446 |
+
"eval_HasAns_total": 25690,
|
| 447 |
+
"eval_best_exact": 72.39392759828728,
|
| 448 |
+
"eval_best_exact_thresh": 0.0,
|
| 449 |
+
"eval_best_f1": 79.00515970901382,
|
| 450 |
+
"eval_best_f1_thresh": 0.0,
|
| 451 |
+
"eval_exact": 72.39392759828728,
|
| 452 |
+
"eval_f1": 79.00515970901382,
|
| 453 |
+
"eval_loss": 0.5600055456161499,
|
| 454 |
+
"eval_runtime": 202.5804,
|
| 455 |
+
"eval_samples_per_second": 126.814,
|
| 456 |
+
"eval_steps_per_second": 7.928,
|
| 457 |
+
"eval_total": 25690,
|
| 458 |
+
"step": 1400
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.22529521441889372,
|
| 462 |
+
"grad_norm": 9.040102005004883,
|
| 463 |
+
"learning_rate": 9.9775015537601e-06,
|
| 464 |
+
"loss": 0.6309,
|
| 465 |
+
"step": 1450
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.23306401491609696,
|
| 469 |
+
"grad_norm": 11.526878356933594,
|
| 470 |
+
"learning_rate": 9.97672467371038e-06,
|
| 471 |
+
"loss": 0.6064,
|
| 472 |
+
"step": 1500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.23306401491609696,
|
| 476 |
+
"eval_HasAns_exact": 72.74425846632931,
|
| 477 |
+
"eval_HasAns_f1": 79.36155045560372,
|
| 478 |
+
"eval_HasAns_total": 25690,
|
| 479 |
+
"eval_best_exact": 72.74425846632931,
|
| 480 |
+
"eval_best_exact_thresh": 0.0,
|
| 481 |
+
"eval_best_f1": 79.36155045560372,
|
| 482 |
+
"eval_best_f1_thresh": 0.0,
|
| 483 |
+
"eval_exact": 72.74425846632931,
|
| 484 |
+
"eval_f1": 79.36155045560372,
|
| 485 |
+
"eval_loss": 0.5500572323799133,
|
| 486 |
+
"eval_runtime": 202.9048,
|
| 487 |
+
"eval_samples_per_second": 126.611,
|
| 488 |
+
"eval_steps_per_second": 7.915,
|
| 489 |
+
"eval_total": 25690,
|
| 490 |
+
"step": 1500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.24083281541330018,
|
| 494 |
+
"grad_norm": 4.359344482421875,
|
| 495 |
+
"learning_rate": 9.97594779366066e-06,
|
| 496 |
+
"loss": 0.6823,
|
| 497 |
+
"step": 1550
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.24860161591050342,
|
| 501 |
+
"grad_norm": 9.813569068908691,
|
| 502 |
+
"learning_rate": 9.97517091361094e-06,
|
| 503 |
+
"loss": 0.6314,
|
| 504 |
+
"step": 1600
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.24860161591050342,
|
| 508 |
+
"eval_HasAns_exact": 72.27715064227326,
|
| 509 |
+
"eval_HasAns_f1": 78.8175772466993,
|
| 510 |
+
"eval_HasAns_total": 25690,
|
| 511 |
+
"eval_best_exact": 72.27715064227326,
|
| 512 |
+
"eval_best_exact_thresh": 0.0,
|
| 513 |
+
"eval_best_f1": 78.8175772466993,
|
| 514 |
+
"eval_best_f1_thresh": 0.0,
|
| 515 |
+
"eval_exact": 72.27715064227326,
|
| 516 |
+
"eval_f1": 78.8175772466993,
|
| 517 |
+
"eval_loss": 0.5353918075561523,
|
| 518 |
+
"eval_runtime": 202.6516,
|
| 519 |
+
"eval_samples_per_second": 126.769,
|
| 520 |
+
"eval_steps_per_second": 7.925,
|
| 521 |
+
"eval_total": 25690,
|
| 522 |
+
"step": 1600
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.25637041640770664,
|
| 526 |
+
"grad_norm": 7.802361965179443,
|
| 527 |
+
"learning_rate": 9.974394033561218e-06,
|
| 528 |
+
"loss": 0.6026,
|
| 529 |
+
"step": 1650
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.2641392169049099,
|
| 533 |
+
"grad_norm": 15.137731552124023,
|
| 534 |
+
"learning_rate": 9.973617153511498e-06,
|
| 535 |
+
"loss": 0.6741,
|
| 536 |
+
"step": 1700
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.2641392169049099,
|
| 540 |
+
"eval_HasAns_exact": 72.1058777734527,
|
| 541 |
+
"eval_HasAns_f1": 78.67773271200794,
|
| 542 |
+
"eval_HasAns_total": 25690,
|
| 543 |
+
"eval_best_exact": 72.1058777734527,
|
| 544 |
+
"eval_best_exact_thresh": 0.0,
|
| 545 |
+
"eval_best_f1": 78.67773271200794,
|
| 546 |
+
"eval_best_f1_thresh": 0.0,
|
| 547 |
+
"eval_exact": 72.1058777734527,
|
| 548 |
+
"eval_f1": 78.67773271200794,
|
| 549 |
+
"eval_loss": 0.5329614877700806,
|
| 550 |
+
"eval_runtime": 202.7192,
|
| 551 |
+
"eval_samples_per_second": 126.727,
|
| 552 |
+
"eval_steps_per_second": 7.922,
|
| 553 |
+
"eval_total": 25690,
|
| 554 |
+
"step": 1700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.2719080174021131,
|
| 558 |
+
"grad_norm": 11.30902099609375,
|
| 559 |
+
"learning_rate": 9.972840273461778e-06,
|
| 560 |
+
"loss": 0.6069,
|
| 561 |
+
"step": 1750
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.27967681789931637,
|
| 565 |
+
"grad_norm": 9.311911582946777,
|
| 566 |
+
"learning_rate": 9.972063393412058e-06,
|
| 567 |
+
"loss": 0.5912,
|
| 568 |
+
"step": 1800
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.27967681789931637,
|
| 572 |
+
"eval_HasAns_exact": 72.24990268586998,
|
| 573 |
+
"eval_HasAns_f1": 78.7891482246884,
|
| 574 |
+
"eval_HasAns_total": 25690,
|
| 575 |
+
"eval_best_exact": 72.24990268586998,
|
| 576 |
+
"eval_best_exact_thresh": 0.0,
|
| 577 |
+
"eval_best_f1": 78.7891482246884,
|
| 578 |
+
"eval_best_f1_thresh": 0.0,
|
| 579 |
+
"eval_exact": 72.24990268586998,
|
| 580 |
+
"eval_f1": 78.7891482246884,
|
| 581 |
+
"eval_loss": 0.5291240811347961,
|
| 582 |
+
"eval_runtime": 202.8091,
|
| 583 |
+
"eval_samples_per_second": 126.671,
|
| 584 |
+
"eval_steps_per_second": 7.919,
|
| 585 |
+
"eval_total": 25690,
|
| 586 |
+
"step": 1800
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.28744561839651955,
|
| 590 |
+
"grad_norm": 9.725021362304688,
|
| 591 |
+
"learning_rate": 9.971286513362338e-06,
|
| 592 |
+
"loss": 0.5943,
|
| 593 |
+
"step": 1850
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.2952144188937228,
|
| 597 |
+
"grad_norm": 8.321113586425781,
|
| 598 |
+
"learning_rate": 9.970509633312618e-06,
|
| 599 |
+
"loss": 0.584,
|
| 600 |
+
"step": 1900
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.2952144188937228,
|
| 604 |
+
"eval_HasAns_exact": 72.56909303230829,
|
| 605 |
+
"eval_HasAns_f1": 79.12955371544794,
|
| 606 |
+
"eval_HasAns_total": 25690,
|
| 607 |
+
"eval_best_exact": 72.56909303230829,
|
| 608 |
+
"eval_best_exact_thresh": 0.0,
|
| 609 |
+
"eval_best_f1": 79.12955371544794,
|
| 610 |
+
"eval_best_f1_thresh": 0.0,
|
| 611 |
+
"eval_exact": 72.56909303230829,
|
| 612 |
+
"eval_f1": 79.12955371544794,
|
| 613 |
+
"eval_loss": 0.5198299288749695,
|
| 614 |
+
"eval_runtime": 202.5651,
|
| 615 |
+
"eval_samples_per_second": 126.823,
|
| 616 |
+
"eval_steps_per_second": 7.928,
|
| 617 |
+
"eval_total": 25690,
|
| 618 |
+
"step": 1900
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.30298321939092604,
|
| 622 |
+
"grad_norm": 11.973769187927246,
|
| 623 |
+
"learning_rate": 9.969732753262898e-06,
|
| 624 |
+
"loss": 0.5895,
|
| 625 |
+
"step": 1950
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.3107520198881293,
|
| 629 |
+
"grad_norm": 9.40645980834961,
|
| 630 |
+
"learning_rate": 9.968955873213176e-06,
|
| 631 |
+
"loss": 0.64,
|
| 632 |
+
"step": 2000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.3107520198881293,
|
| 636 |
+
"eval_HasAns_exact": 72.79096924873491,
|
| 637 |
+
"eval_HasAns_f1": 79.28733698122942,
|
| 638 |
+
"eval_HasAns_total": 25690,
|
| 639 |
+
"eval_best_exact": 72.79096924873491,
|
| 640 |
+
"eval_best_exact_thresh": 0.0,
|
| 641 |
+
"eval_best_f1": 79.28733698122942,
|
| 642 |
+
"eval_best_f1_thresh": 0.0,
|
| 643 |
+
"eval_exact": 72.79096924873491,
|
| 644 |
+
"eval_f1": 79.28733698122942,
|
| 645 |
+
"eval_loss": 0.5117060542106628,
|
| 646 |
+
"eval_runtime": 203.1079,
|
| 647 |
+
"eval_samples_per_second": 126.485,
|
| 648 |
+
"eval_steps_per_second": 7.907,
|
| 649 |
+
"eval_total": 25690,
|
| 650 |
+
"step": 2000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.3185208203853325,
|
| 654 |
+
"grad_norm": 14.14991569519043,
|
| 655 |
+
"learning_rate": 9.968178993163456e-06,
|
| 656 |
+
"loss": 0.5559,
|
| 657 |
+
"step": 2050
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.3262896208825357,
|
| 661 |
+
"grad_norm": 10.641693115234375,
|
| 662 |
+
"learning_rate": 9.967402113113736e-06,
|
| 663 |
+
"loss": 0.5361,
|
| 664 |
+
"step": 2100
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.3262896208825357,
|
| 668 |
+
"eval_HasAns_exact": 73.13351498637603,
|
| 669 |
+
"eval_HasAns_f1": 79.60268173326928,
|
| 670 |
+
"eval_HasAns_total": 25690,
|
| 671 |
+
"eval_best_exact": 73.13351498637603,
|
| 672 |
+
"eval_best_exact_thresh": 0.0,
|
| 673 |
+
"eval_best_f1": 79.60268173326928,
|
| 674 |
+
"eval_best_f1_thresh": 0.0,
|
| 675 |
+
"eval_exact": 73.13351498637603,
|
| 676 |
+
"eval_f1": 79.60268173326928,
|
| 677 |
+
"eval_loss": 0.5079160928726196,
|
| 678 |
+
"eval_runtime": 202.7995,
|
| 679 |
+
"eval_samples_per_second": 126.677,
|
| 680 |
+
"eval_steps_per_second": 7.919,
|
| 681 |
+
"eval_total": 25690,
|
| 682 |
+
"step": 2100
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.33405842137973896,
|
| 686 |
+
"grad_norm": 10.088223457336426,
|
| 687 |
+
"learning_rate": 9.966625233064016e-06,
|
| 688 |
+
"loss": 0.6151,
|
| 689 |
+
"step": 2150
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.3418272218769422,
|
| 693 |
+
"grad_norm": 10.863611221313477,
|
| 694 |
+
"learning_rate": 9.965848353014296e-06,
|
| 695 |
+
"loss": 0.5935,
|
| 696 |
+
"step": 2200
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.3418272218769422,
|
| 700 |
+
"eval_HasAns_exact": 72.9349941611522,
|
| 701 |
+
"eval_HasAns_f1": 79.49240914807372,
|
| 702 |
+
"eval_HasAns_total": 25690,
|
| 703 |
+
"eval_best_exact": 72.9349941611522,
|
| 704 |
+
"eval_best_exact_thresh": 0.0,
|
| 705 |
+
"eval_best_f1": 79.49240914807372,
|
| 706 |
+
"eval_best_f1_thresh": 0.0,
|
| 707 |
+
"eval_exact": 72.9349941611522,
|
| 708 |
+
"eval_f1": 79.49240914807372,
|
| 709 |
+
"eval_loss": 0.5025383234024048,
|
| 710 |
+
"eval_runtime": 203.3956,
|
| 711 |
+
"eval_samples_per_second": 126.306,
|
| 712 |
+
"eval_steps_per_second": 7.896,
|
| 713 |
+
"eval_total": 25690,
|
| 714 |
+
"step": 2200
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.34959602237414544,
|
| 718 |
+
"grad_norm": 12.565064430236816,
|
| 719 |
+
"learning_rate": 9.965071472964574e-06,
|
| 720 |
+
"loss": 0.5667,
|
| 721 |
+
"step": 2250
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.3573648228713487,
|
| 725 |
+
"grad_norm": 5.066905975341797,
|
| 726 |
+
"learning_rate": 9.964294592914854e-06,
|
| 727 |
+
"loss": 0.5198,
|
| 728 |
+
"step": 2300
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.3573648228713487,
|
| 732 |
+
"eval_HasAns_exact": 72.6975476839237,
|
| 733 |
+
"eval_HasAns_f1": 79.25327470362464,
|
| 734 |
+
"eval_HasAns_total": 25690,
|
| 735 |
+
"eval_best_exact": 72.6975476839237,
|
| 736 |
+
"eval_best_exact_thresh": 0.0,
|
| 737 |
+
"eval_best_f1": 79.25327470362464,
|
| 738 |
+
"eval_best_f1_thresh": 0.0,
|
| 739 |
+
"eval_exact": 72.6975476839237,
|
| 740 |
+
"eval_f1": 79.25327470362464,
|
| 741 |
+
"eval_loss": 0.4996239244937897,
|
| 742 |
+
"eval_runtime": 204.0149,
|
| 743 |
+
"eval_samples_per_second": 125.922,
|
| 744 |
+
"eval_steps_per_second": 7.872,
|
| 745 |
+
"eval_total": 25690,
|
| 746 |
+
"step": 2300
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.3651336233685519,
|
| 750 |
+
"grad_norm": 10.777655601501465,
|
| 751 |
+
"learning_rate": 9.963517712865134e-06,
|
| 752 |
+
"loss": 0.4983,
|
| 753 |
+
"step": 2350
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.3729024238657551,
|
| 757 |
+
"grad_norm": 6.770049095153809,
|
| 758 |
+
"learning_rate": 9.962740832815414e-06,
|
| 759 |
+
"loss": 0.5474,
|
| 760 |
+
"step": 2400
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.3729024238657551,
|
| 764 |
+
"eval_HasAns_exact": 73.29700272479565,
|
| 765 |
+
"eval_HasAns_f1": 79.7561576366954,
|
| 766 |
+
"eval_HasAns_total": 25690,
|
| 767 |
+
"eval_best_exact": 73.29700272479565,
|
| 768 |
+
"eval_best_exact_thresh": 0.0,
|
| 769 |
+
"eval_best_f1": 79.7561576366954,
|
| 770 |
+
"eval_best_f1_thresh": 0.0,
|
| 771 |
+
"eval_exact": 73.29700272479565,
|
| 772 |
+
"eval_f1": 79.7561576366954,
|
| 773 |
+
"eval_loss": 0.4912045896053314,
|
| 774 |
+
"eval_runtime": 202.5387,
|
| 775 |
+
"eval_samples_per_second": 126.84,
|
| 776 |
+
"eval_steps_per_second": 7.929,
|
| 777 |
+
"eval_total": 25690,
|
| 778 |
+
"step": 2400
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.38067122436295836,
|
| 782 |
+
"grad_norm": 11.886155128479004,
|
| 783 |
+
"learning_rate": 9.961963952765694e-06,
|
| 784 |
+
"loss": 0.5038,
|
| 785 |
+
"step": 2450
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.3884400248601616,
|
| 789 |
+
"grad_norm": 15.60519027709961,
|
| 790 |
+
"learning_rate": 9.961187072715973e-06,
|
| 791 |
+
"loss": 0.5655,
|
| 792 |
+
"step": 2500
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.3884400248601616,
|
| 796 |
+
"eval_HasAns_exact": 73.46049046321527,
|
| 797 |
+
"eval_HasAns_f1": 79.95807844595133,
|
| 798 |
+
"eval_HasAns_total": 25690,
|
| 799 |
+
"eval_best_exact": 73.46049046321527,
|
| 800 |
+
"eval_best_exact_thresh": 0.0,
|
| 801 |
+
"eval_best_f1": 79.95807844595133,
|
| 802 |
+
"eval_best_f1_thresh": 0.0,
|
| 803 |
+
"eval_exact": 73.46049046321527,
|
| 804 |
+
"eval_f1": 79.95807844595133,
|
| 805 |
+
"eval_loss": 0.48474493622779846,
|
| 806 |
+
"eval_runtime": 202.6752,
|
| 807 |
+
"eval_samples_per_second": 126.755,
|
| 808 |
+
"eval_steps_per_second": 7.924,
|
| 809 |
+
"eval_total": 25690,
|
| 810 |
+
"step": 2500
|
| 811 |
+
}
|
| 812 |
+
],
|
| 813 |
+
"logging_steps": 50,
|
| 814 |
+
"max_steps": 643600,
|
| 815 |
+
"num_input_tokens_seen": 0,
|
| 816 |
+
"num_train_epochs": 100,
|
| 817 |
+
"save_steps": 500,
|
| 818 |
+
"stateful_callbacks": {
|
| 819 |
+
"EarlyStoppingCallback": {
|
| 820 |
+
"args": {
|
| 821 |
+
"early_stopping_patience": 10,
|
| 822 |
+
"early_stopping_threshold": 0.0
|
| 823 |
+
},
|
| 824 |
+
"attributes": {
|
| 825 |
+
"early_stopping_patience_counter": 0
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"TrainerControl": {
|
| 829 |
+
"args": {
|
| 830 |
+
"should_epoch_stop": false,
|
| 831 |
+
"should_evaluate": false,
|
| 832 |
+
"should_log": false,
|
| 833 |
+
"should_save": true,
|
| 834 |
+
"should_training_stop": false
|
| 835 |
+
},
|
| 836 |
+
"attributes": {}
|
| 837 |
+
}
|
| 838 |
+
},
|
| 839 |
+
"total_flos": 2.090374053888e+16,
|
| 840 |
+
"train_batch_size": 16,
|
| 841 |
+
"trial_name": null,
|
| 842 |
+
"trial_params": null
|
| 843 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6670cd309bc79c4638de77be66649432fb3a049d09959fd300cbc983c7c7160d
|
| 3 |
+
size 5304
|
checkpoint-2500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForQuestionAnswering"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"language": "english",
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"name": "Bert",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.50.3",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11d9f01f2fbc8837fbfff5ff3be61c2957266444df3282cd389ac793a2ad3306
|
| 3 |
+
size 435596088
|