Commit
•
ca8494a
1
Parent(s):
cdade97
adding model finetuned on tar
Browse files- all_results.json +11 -0
- config.json +33 -0
- eval_nbest_predictions.json +0 -0
- eval_predictions.json +0 -0
- eval_results.json +6 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
- train_results.json +8 -0
- trainer_state.json +541 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_exact_match": 52.980132450331126,
|
| 4 |
+
"eval_f1": 70.54026450257521,
|
| 5 |
+
"eval_samples": 10624,
|
| 6 |
+
"train_loss": 1.4580001696595593,
|
| 7 |
+
"train_runtime": 2422.3692,
|
| 8 |
+
"train_samples": 87747,
|
| 9 |
+
"train_samples_per_second": 108.671,
|
| 10 |
+
"train_steps_per_second": 6.793
|
| 11 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/albert-base-4-spanish",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AlbertForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout_prob": 0.1,
|
| 9 |
+
"down_scale_factor": 1,
|
| 10 |
+
"embedding_size": 128,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"gap_size": 0,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"inner_group_num": 1,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "albert",
|
| 22 |
+
"net_structure_type": 0,
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_groups": 1,
|
| 25 |
+
"num_hidden_layers": 4,
|
| 26 |
+
"num_memory_blocks": 0,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.25.1",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"vocab_size": 31000
|
| 33 |
+
}
|
eval_nbest_predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_exact_match": 52.980132450331126,
|
| 4 |
+
"eval_f1": 70.54026450257521,
|
| 5 |
+
"eval_samples": 10624
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:269614633709afae62be9590073d9b85ddac1de183e2baf2a9268af5bfeac98a
|
| 3 |
+
size 44903231
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"eos_token": "[SEP]",
|
| 6 |
+
"keep_accents": true,
|
| 7 |
+
"mask_token": {
|
| 8 |
+
"__type": "AddedToken",
|
| 9 |
+
"content": "[MASK]",
|
| 10 |
+
"lstrip": true,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"model_max_length": 512,
|
| 16 |
+
"name_or_path": "dccuchile/albert-base-4-spanish",
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"remove_space": true,
|
| 19 |
+
"sep_token": "[SEP]",
|
| 20 |
+
"special_tokens_map_file": null,
|
| 21 |
+
"tokenizer_class": "AlbertTokenizer",
|
| 22 |
+
"unk_token": "<unk>"
|
| 23 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.4580001696595593,
|
| 4 |
+
"train_runtime": 2422.3692,
|
| 5 |
+
"train_samples": 87747,
|
| 6 |
+
"train_samples_per_second": 108.671,
|
| 7 |
+
"train_steps_per_second": 6.793
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,541 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 70.54026450257521,
|
| 3 |
+
"best_model_checkpoint": "/home/jcanete/ft-data/all_results/tar/albeto_base_4/epochs_3_bs_16_lr_5e-5/checkpoint-9000",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 16455,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"eval_exact_match": 34.645222327341536,
|
| 13 |
+
"eval_f1": 52.13460975937906,
|
| 14 |
+
"step": 300
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 4.848678213309025e-05,
|
| 19 |
+
"loss": 2.8212,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.11,
|
| 24 |
+
"eval_exact_match": 40.38789025543993,
|
| 25 |
+
"eval_f1": 58.80108695949609,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"eval_exact_match": 44.1438032166509,
|
| 31 |
+
"eval_f1": 61.68021475413032,
|
| 32 |
+
"step": 900
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.18,
|
| 36 |
+
"learning_rate": 4.6967487085992104e-05,
|
| 37 |
+
"loss": 2.147,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.22,
|
| 42 |
+
"eval_exact_match": 45.08041627246925,
|
| 43 |
+
"eval_f1": 63.22958368722072,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27,
|
| 48 |
+
"learning_rate": 4.544819203889396e-05,
|
| 49 |
+
"loss": 2.0333,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"eval_exact_match": 46.09271523178808,
|
| 55 |
+
"eval_f1": 63.34953738572746,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.33,
|
| 60 |
+
"eval_exact_match": 47.13339640491959,
|
| 61 |
+
"eval_f1": 64.76366505969077,
|
| 62 |
+
"step": 1800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.36,
|
| 66 |
+
"learning_rate": 4.392889699179581e-05,
|
| 67 |
+
"loss": 1.9667,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.38,
|
| 72 |
+
"eval_exact_match": 47.4077578051088,
|
| 73 |
+
"eval_f1": 65.80706119842145,
|
| 74 |
+
"step": 2100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.44,
|
| 78 |
+
"eval_exact_match": 48.55250709555345,
|
| 79 |
+
"eval_f1": 66.49751567340297,
|
| 80 |
+
"step": 2400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.46,
|
| 84 |
+
"learning_rate": 4.2409601944697666e-05,
|
| 85 |
+
"loss": 1.8743,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.49,
|
| 90 |
+
"eval_exact_match": 48.84578997161778,
|
| 91 |
+
"eval_f1": 66.76044504218349,
|
| 92 |
+
"step": 2700
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.55,
|
| 96 |
+
"learning_rate": 4.089030689759952e-05,
|
| 97 |
+
"loss": 1.8655,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.55,
|
| 102 |
+
"eval_exact_match": 49.55534531693472,
|
| 103 |
+
"eval_f1": 67.55609852983001,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.6,
|
| 108 |
+
"eval_exact_match": 49.45127719962157,
|
| 109 |
+
"eval_f1": 67.28955811469469,
|
| 110 |
+
"step": 3300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.64,
|
| 114 |
+
"learning_rate": 3.9371011850501374e-05,
|
| 115 |
+
"loss": 1.8223,
|
| 116 |
+
"step": 3500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.66,
|
| 120 |
+
"eval_exact_match": 50.08514664143803,
|
| 121 |
+
"eval_f1": 68.11294509259712,
|
| 122 |
+
"step": 3600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.71,
|
| 126 |
+
"eval_exact_match": 50.38789025543993,
|
| 127 |
+
"eval_f1": 68.15488930053279,
|
| 128 |
+
"step": 3900
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.73,
|
| 132 |
+
"learning_rate": 3.785171680340323e-05,
|
| 133 |
+
"loss": 1.7684,
|
| 134 |
+
"step": 4000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.77,
|
| 138 |
+
"eval_exact_match": 51.05960264900662,
|
| 139 |
+
"eval_f1": 69.07576620387981,
|
| 140 |
+
"step": 4200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.82,
|
| 144 |
+
"learning_rate": 3.6335460346399276e-05,
|
| 145 |
+
"loss": 1.7677,
|
| 146 |
+
"step": 4500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.82,
|
| 150 |
+
"eval_exact_match": 51.561021759697255,
|
| 151 |
+
"eval_f1": 69.20806146876814,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.88,
|
| 156 |
+
"eval_exact_match": 51.61778618732261,
|
| 157 |
+
"eval_f1": 69.20269381359182,
|
| 158 |
+
"step": 4800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.91,
|
| 162 |
+
"learning_rate": 3.481616529930112e-05,
|
| 163 |
+
"loss": 1.7566,
|
| 164 |
+
"step": 5000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.93,
|
| 168 |
+
"eval_exact_match": 51.68401135288553,
|
| 169 |
+
"eval_f1": 69.22415299954444,
|
| 170 |
+
"step": 5100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.98,
|
| 174 |
+
"eval_exact_match": 51.82592242194891,
|
| 175 |
+
"eval_f1": 69.68048492944583,
|
| 176 |
+
"step": 5400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.0,
|
| 180 |
+
"learning_rate": 3.329990884229718e-05,
|
| 181 |
+
"loss": 1.6976,
|
| 182 |
+
"step": 5500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.04,
|
| 186 |
+
"eval_exact_match": 51.84484389782403,
|
| 187 |
+
"eval_f1": 69.61844469538968,
|
| 188 |
+
"step": 5700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.09,
|
| 192 |
+
"learning_rate": 3.1780613795199024e-05,
|
| 193 |
+
"loss": 1.3996,
|
| 194 |
+
"step": 6000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.09,
|
| 198 |
+
"eval_exact_match": 51.79754020813623,
|
| 199 |
+
"eval_f1": 69.51904893791095,
|
| 200 |
+
"step": 6000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.15,
|
| 204 |
+
"eval_exact_match": 51.72185430463576,
|
| 205 |
+
"eval_f1": 69.18971361078592,
|
| 206 |
+
"step": 6300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.19,
|
| 210 |
+
"learning_rate": 3.0261318748100882e-05,
|
| 211 |
+
"loss": 1.3947,
|
| 212 |
+
"step": 6500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2,
|
| 216 |
+
"eval_exact_match": 51.82592242194891,
|
| 217 |
+
"eval_f1": 69.9010405722466,
|
| 218 |
+
"step": 6600
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.26,
|
| 222 |
+
"eval_exact_match": 51.74077578051088,
|
| 223 |
+
"eval_f1": 69.21425877541581,
|
| 224 |
+
"step": 6900
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.28,
|
| 228 |
+
"learning_rate": 2.8742023701002736e-05,
|
| 229 |
+
"loss": 1.3898,
|
| 230 |
+
"step": 7000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.31,
|
| 234 |
+
"eval_exact_match": 52.64900662251656,
|
| 235 |
+
"eval_f1": 70.03047551437781,
|
| 236 |
+
"step": 7200
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.37,
|
| 240 |
+
"learning_rate": 2.722272865390459e-05,
|
| 241 |
+
"loss": 1.3861,
|
| 242 |
+
"step": 7500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.37,
|
| 246 |
+
"eval_exact_match": 52.232734153263955,
|
| 247 |
+
"eval_f1": 69.84348950849247,
|
| 248 |
+
"step": 7500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.42,
|
| 252 |
+
"eval_exact_match": 52.05298013245033,
|
| 253 |
+
"eval_f1": 69.85616305536696,
|
| 254 |
+
"step": 7800
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.46,
|
| 258 |
+
"learning_rate": 2.5703433606806444e-05,
|
| 259 |
+
"loss": 1.4272,
|
| 260 |
+
"step": 8000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.48,
|
| 264 |
+
"eval_exact_match": 52.42194891201514,
|
| 265 |
+
"eval_f1": 70.12191052992236,
|
| 266 |
+
"step": 8100
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.53,
|
| 270 |
+
"eval_exact_match": 52.327341532639544,
|
| 271 |
+
"eval_f1": 70.1945849880174,
|
| 272 |
+
"step": 8400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.55,
|
| 276 |
+
"learning_rate": 2.4184138559708297e-05,
|
| 277 |
+
"loss": 1.387,
|
| 278 |
+
"step": 8500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.59,
|
| 282 |
+
"eval_exact_match": 52.73415326395459,
|
| 283 |
+
"eval_f1": 70.53063216515172,
|
| 284 |
+
"step": 8700
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.64,
|
| 288 |
+
"learning_rate": 2.266484351261015e-05,
|
| 289 |
+
"loss": 1.4181,
|
| 290 |
+
"step": 9000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.64,
|
| 294 |
+
"eval_exact_match": 52.980132450331126,
|
| 295 |
+
"eval_f1": 70.54026450257521,
|
| 296 |
+
"step": 9000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.7,
|
| 300 |
+
"eval_exact_match": 52.327341532639544,
|
| 301 |
+
"eval_f1": 70.03067034409061,
|
| 302 |
+
"step": 9300
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.73,
|
| 306 |
+
"learning_rate": 2.1145548465512002e-05,
|
| 307 |
+
"loss": 1.3941,
|
| 308 |
+
"step": 9500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.75,
|
| 312 |
+
"eval_exact_match": 52.75307473982971,
|
| 313 |
+
"eval_f1": 70.53593438103856,
|
| 314 |
+
"step": 9600
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.8,
|
| 318 |
+
"eval_exact_match": 52.37464522232734,
|
| 319 |
+
"eval_f1": 69.9459164585827,
|
| 320 |
+
"step": 9900
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.82,
|
| 324 |
+
"learning_rate": 1.9629292008508053e-05,
|
| 325 |
+
"loss": 1.4019,
|
| 326 |
+
"step": 10000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.86,
|
| 330 |
+
"eval_exact_match": 52.544938505203405,
|
| 331 |
+
"eval_f1": 70.19906201457854,
|
| 332 |
+
"step": 10200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.91,
|
| 336 |
+
"learning_rate": 1.8109996961409907e-05,
|
| 337 |
+
"loss": 1.4031,
|
| 338 |
+
"step": 10500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.91,
|
| 342 |
+
"eval_exact_match": 52.61116367076632,
|
| 343 |
+
"eval_f1": 70.3522720546097,
|
| 344 |
+
"step": 10500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.97,
|
| 348 |
+
"eval_exact_match": 53.02743614001892,
|
| 349 |
+
"eval_f1": 70.4807280516286,
|
| 350 |
+
"step": 10800
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.01,
|
| 354 |
+
"learning_rate": 1.659070191431176e-05,
|
| 355 |
+
"loss": 1.3625,
|
| 356 |
+
"step": 11000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.02,
|
| 360 |
+
"eval_exact_match": 51.88268684957427,
|
| 361 |
+
"eval_f1": 69.74458138686404,
|
| 362 |
+
"step": 11100
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.08,
|
| 366 |
+
"eval_exact_match": 51.66508987701041,
|
| 367 |
+
"eval_f1": 69.55251413256356,
|
| 368 |
+
"step": 11400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.1,
|
| 372 |
+
"learning_rate": 1.5071406867213613e-05,
|
| 373 |
+
"loss": 1.0261,
|
| 374 |
+
"step": 11500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.13,
|
| 378 |
+
"eval_exact_match": 51.12582781456954,
|
| 379 |
+
"eval_f1": 69.45293644822506,
|
| 380 |
+
"step": 11700
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.19,
|
| 384 |
+
"learning_rate": 1.3555150410209664e-05,
|
| 385 |
+
"loss": 0.9969,
|
| 386 |
+
"step": 12000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.19,
|
| 390 |
+
"eval_exact_match": 51.84484389782403,
|
| 391 |
+
"eval_f1": 69.82132514934786,
|
| 392 |
+
"step": 12000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.24,
|
| 396 |
+
"eval_exact_match": 51.106906338694415,
|
| 397 |
+
"eval_f1": 69.26705027187695,
|
| 398 |
+
"step": 12300
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.28,
|
| 402 |
+
"learning_rate": 1.2035855363111518e-05,
|
| 403 |
+
"loss": 1.0186,
|
| 404 |
+
"step": 12500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.3,
|
| 408 |
+
"eval_exact_match": 51.59886471144749,
|
| 409 |
+
"eval_f1": 69.76823383346489,
|
| 410 |
+
"step": 12600
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.35,
|
| 414 |
+
"eval_exact_match": 51.45695364238411,
|
| 415 |
+
"eval_f1": 69.76810827781901,
|
| 416 |
+
"step": 12900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.37,
|
| 420 |
+
"learning_rate": 1.051656031601337e-05,
|
| 421 |
+
"loss": 1.0272,
|
| 422 |
+
"step": 13000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.41,
|
| 426 |
+
"eval_exact_match": 51.35288552507095,
|
| 427 |
+
"eval_f1": 69.64753731877455,
|
| 428 |
+
"step": 13200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.46,
|
| 432 |
+
"learning_rate": 8.997265268915224e-06,
|
| 433 |
+
"loss": 1.0469,
|
| 434 |
+
"step": 13500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.46,
|
| 438 |
+
"eval_exact_match": 51.324503311258276,
|
| 439 |
+
"eval_f1": 69.46890832651873,
|
| 440 |
+
"step": 13500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.52,
|
| 444 |
+
"eval_exact_match": 51.343424787133394,
|
| 445 |
+
"eval_f1": 69.28540200400431,
|
| 446 |
+
"step": 13800
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.55,
|
| 450 |
+
"learning_rate": 7.4810088119112735e-06,
|
| 451 |
+
"loss": 1.0324,
|
| 452 |
+
"step": 14000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.57,
|
| 456 |
+
"eval_exact_match": 51.27719962157048,
|
| 457 |
+
"eval_f1": 69.21410385147476,
|
| 458 |
+
"step": 14100
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.63,
|
| 462 |
+
"eval_exact_match": 51.400189214758754,
|
| 463 |
+
"eval_f1": 69.48987451431931,
|
| 464 |
+
"step": 14400
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.64,
|
| 468 |
+
"learning_rate": 5.964752354907324e-06,
|
| 469 |
+
"loss": 1.026,
|
| 470 |
+
"step": 14500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.68,
|
| 474 |
+
"eval_exact_match": 51.14474929044466,
|
| 475 |
+
"eval_f1": 69.48096843416343,
|
| 476 |
+
"step": 14700
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.73,
|
| 480 |
+
"learning_rate": 4.445457307809177e-06,
|
| 481 |
+
"loss": 1.0191,
|
| 482 |
+
"step": 15000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.73,
|
| 486 |
+
"eval_exact_match": 51.333964049195835,
|
| 487 |
+
"eval_f1": 69.47772191155812,
|
| 488 |
+
"step": 15000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.79,
|
| 492 |
+
"eval_exact_match": 51.68401135288553,
|
| 493 |
+
"eval_f1": 69.54969415984502,
|
| 494 |
+
"step": 15300
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.83,
|
| 498 |
+
"learning_rate": 2.9261622607110303e-06,
|
| 499 |
+
"loss": 0.9864,
|
| 500 |
+
"step": 15500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.84,
|
| 504 |
+
"eval_exact_match": 51.37180700094607,
|
| 505 |
+
"eval_f1": 69.56621150352814,
|
| 506 |
+
"step": 15600
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.9,
|
| 510 |
+
"eval_exact_match": 51.561021759697255,
|
| 511 |
+
"eval_f1": 69.58651422829355,
|
| 512 |
+
"step": 15900
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.92,
|
| 516 |
+
"learning_rate": 1.4068672136128838e-06,
|
| 517 |
+
"loss": 1.0319,
|
| 518 |
+
"step": 16000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.95,
|
| 522 |
+
"eval_exact_match": 51.627246925260174,
|
| 523 |
+
"eval_f1": 69.53955054930253,
|
| 524 |
+
"step": 16200
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.0,
|
| 528 |
+
"step": 16455,
|
| 529 |
+
"total_flos": 3819871314614016.0,
|
| 530 |
+
"train_loss": 1.4580001696595593,
|
| 531 |
+
"train_runtime": 2422.3692,
|
| 532 |
+
"train_samples_per_second": 108.671,
|
| 533 |
+
"train_steps_per_second": 6.793
|
| 534 |
+
}
|
| 535 |
+
],
|
| 536 |
+
"max_steps": 16455,
|
| 537 |
+
"num_train_epochs": 3,
|
| 538 |
+
"total_flos": 3819871314614016.0,
|
| 539 |
+
"trial_name": null,
|
| 540 |
+
"trial_params": null
|
| 541 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f17d3e63798f297e20956487052fa5641ce9c7b1016f0bb521630f6a338e148f
|
| 3 |
+
size 3515
|