Commit
•
55d4ce0
1
Parent(s):
a5cfdd6
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 +367 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_exact_match": 59.6310312204352,
|
| 4 |
+
"eval_f1": 76.36038789574842,
|
| 5 |
+
"eval_samples": 10624,
|
| 6 |
+
"train_loss": 1.452151380763232,
|
| 7 |
+
"train_runtime": 2009.9163,
|
| 8 |
+
"train_samples": 87747,
|
| 9 |
+
"train_samples_per_second": 87.314,
|
| 10 |
+
"train_steps_per_second": 5.458
|
| 11 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/albert-base-10-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": 10,
|
| 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": 2.0,
|
| 3 |
+
"eval_exact_match": 59.6310312204352,
|
| 4 |
+
"eval_f1": 76.36038789574842,
|
| 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:dc072037d60f5feaa123a4e78773744cc1becb43290b249d6b4c1a39f3e62b20
|
| 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-10-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": 2.0,
|
| 3 |
+
"train_loss": 1.452151380763232,
|
| 4 |
+
"train_runtime": 2009.9163,
|
| 5 |
+
"train_samples": 87747,
|
| 6 |
+
"train_samples_per_second": 87.314,
|
| 7 |
+
"train_steps_per_second": 5.458
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,367 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 76.36038789574842,
|
| 3 |
+
"best_model_checkpoint": "/home/jcanete/ft-data/all_results/tar/albeto_base_10/epochs_2_bs_16_lr_5e-5/checkpoint-10200",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 10970,
|
| 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": 45.53453169347209,
|
| 13 |
+
"eval_f1": 64.38889275299238,
|
| 14 |
+
"step": 300
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 4.774840474020055e-05,
|
| 19 |
+
"loss": 2.3938,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.11,
|
| 24 |
+
"eval_exact_match": 49.14853358561968,
|
| 25 |
+
"eval_f1": 67.53518688183068,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"eval_exact_match": 51.26773888363292,
|
| 31 |
+
"eval_f1": 69.15241192316618,
|
| 32 |
+
"step": 900
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.18,
|
| 36 |
+
"learning_rate": 4.546946216955333e-05,
|
| 37 |
+
"loss": 1.8676,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.22,
|
| 42 |
+
"eval_exact_match": 52.677388836329236,
|
| 43 |
+
"eval_f1": 71.264646480928,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27,
|
| 48 |
+
"learning_rate": 4.319051959890611e-05,
|
| 49 |
+
"loss": 1.7557,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"eval_exact_match": 52.8003784295175,
|
| 55 |
+
"eval_f1": 70.69843839338733,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.33,
|
| 60 |
+
"eval_exact_match": 53.841059602649004,
|
| 61 |
+
"eval_f1": 71.55219520099376,
|
| 62 |
+
"step": 1800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.36,
|
| 66 |
+
"learning_rate": 4.091157702825889e-05,
|
| 67 |
+
"loss": 1.7093,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.38,
|
| 72 |
+
"eval_exact_match": 54.08703878902554,
|
| 73 |
+
"eval_f1": 72.75312871370792,
|
| 74 |
+
"step": 2100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.44,
|
| 78 |
+
"eval_exact_match": 54.15326395458846,
|
| 79 |
+
"eval_f1": 72.25373492579445,
|
| 80 |
+
"step": 2400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.46,
|
| 84 |
+
"learning_rate": 3.863263445761167e-05,
|
| 85 |
+
"loss": 1.6266,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.49,
|
| 90 |
+
"eval_exact_match": 55.81835383159886,
|
| 91 |
+
"eval_f1": 73.13623090017391,
|
| 92 |
+
"step": 2700
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.55,
|
| 96 |
+
"learning_rate": 3.635369188696445e-05,
|
| 97 |
+
"loss": 1.6179,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.55,
|
| 102 |
+
"eval_exact_match": 56.017029328287606,
|
| 103 |
+
"eval_f1": 73.68563507466432,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.6,
|
| 108 |
+
"eval_exact_match": 57.03878902554399,
|
| 109 |
+
"eval_f1": 73.81599366386958,
|
| 110 |
+
"step": 3300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.64,
|
| 114 |
+
"learning_rate": 3.4074749316317225e-05,
|
| 115 |
+
"loss": 1.5863,
|
| 116 |
+
"step": 3500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.66,
|
| 120 |
+
"eval_exact_match": 56.9441816461684,
|
| 121 |
+
"eval_f1": 74.03932269687274,
|
| 122 |
+
"step": 3600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.71,
|
| 126 |
+
"eval_exact_match": 57.11447492904446,
|
| 127 |
+
"eval_f1": 74.25288243781013,
|
| 128 |
+
"step": 3900
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.73,
|
| 132 |
+
"learning_rate": 3.1795806745670006e-05,
|
| 133 |
+
"loss": 1.5291,
|
| 134 |
+
"step": 4000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.77,
|
| 138 |
+
"eval_exact_match": 57.63481551561022,
|
| 139 |
+
"eval_f1": 74.89927170312892,
|
| 140 |
+
"step": 4200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.82,
|
| 144 |
+
"learning_rate": 2.951686417502279e-05,
|
| 145 |
+
"loss": 1.5386,
|
| 146 |
+
"step": 4500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.82,
|
| 150 |
+
"eval_exact_match": 57.95648060548723,
|
| 151 |
+
"eval_f1": 74.61884384474561,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.88,
|
| 156 |
+
"eval_exact_match": 58.02270577105014,
|
| 157 |
+
"eval_f1": 75.32600315809357,
|
| 158 |
+
"step": 4800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.91,
|
| 162 |
+
"learning_rate": 2.723792160437557e-05,
|
| 163 |
+
"loss": 1.5132,
|
| 164 |
+
"step": 5000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.93,
|
| 168 |
+
"eval_exact_match": 58.306527909176914,
|
| 169 |
+
"eval_f1": 74.89942757720935,
|
| 170 |
+
"step": 5100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.98,
|
| 174 |
+
"eval_exact_match": 58.64711447492905,
|
| 175 |
+
"eval_f1": 75.59723967213186,
|
| 176 |
+
"step": 5400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.0,
|
| 180 |
+
"learning_rate": 2.4958979033728353e-05,
|
| 181 |
+
"loss": 1.4682,
|
| 182 |
+
"step": 5500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.04,
|
| 186 |
+
"eval_exact_match": 59.15799432355724,
|
| 187 |
+
"eval_f1": 75.83737312760167,
|
| 188 |
+
"step": 5700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.09,
|
| 192 |
+
"learning_rate": 2.268003646308113e-05,
|
| 193 |
+
"loss": 1.2319,
|
| 194 |
+
"step": 6000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.09,
|
| 198 |
+
"eval_exact_match": 58.609271523178805,
|
| 199 |
+
"eval_f1": 75.81477740927686,
|
| 200 |
+
"step": 6000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.15,
|
| 204 |
+
"eval_exact_match": 58.59035004730369,
|
| 205 |
+
"eval_f1": 75.43205542917899,
|
| 206 |
+
"step": 6300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.19,
|
| 210 |
+
"learning_rate": 2.040109389243391e-05,
|
| 211 |
+
"loss": 1.2259,
|
| 212 |
+
"step": 6500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2,
|
| 216 |
+
"eval_exact_match": 58.77010406811731,
|
| 217 |
+
"eval_f1": 75.82376993425314,
|
| 218 |
+
"step": 6600
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.26,
|
| 222 |
+
"eval_exact_match": 58.24976348155156,
|
| 223 |
+
"eval_f1": 75.0320889415698,
|
| 224 |
+
"step": 6900
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.28,
|
| 228 |
+
"learning_rate": 1.8122151321786692e-05,
|
| 229 |
+
"loss": 1.2123,
|
| 230 |
+
"step": 7000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.31,
|
| 234 |
+
"eval_exact_match": 58.98770104068117,
|
| 235 |
+
"eval_f1": 76.02527498333018,
|
| 236 |
+
"step": 7200
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.37,
|
| 240 |
+
"learning_rate": 1.5847766636280767e-05,
|
| 241 |
+
"loss": 1.1885,
|
| 242 |
+
"step": 7500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.37,
|
| 246 |
+
"eval_exact_match": 58.9120151371807,
|
| 247 |
+
"eval_f1": 76.0439212810425,
|
| 248 |
+
"step": 7500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.42,
|
| 252 |
+
"eval_exact_match": 58.826868495742666,
|
| 253 |
+
"eval_f1": 75.94488358894192,
|
| 254 |
+
"step": 7800
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.46,
|
| 258 |
+
"learning_rate": 1.3568824065633548e-05,
|
| 259 |
+
"loss": 1.2468,
|
| 260 |
+
"step": 8000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.48,
|
| 264 |
+
"eval_exact_match": 59.3282876064333,
|
| 265 |
+
"eval_f1": 76.00751273155576,
|
| 266 |
+
"step": 8100
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.53,
|
| 270 |
+
"eval_exact_match": 58.99716177861873,
|
| 271 |
+
"eval_f1": 75.85711081597596,
|
| 272 |
+
"step": 8400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.55,
|
| 276 |
+
"learning_rate": 1.1289881494986327e-05,
|
| 277 |
+
"loss": 1.2093,
|
| 278 |
+
"step": 8500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.59,
|
| 282 |
+
"eval_exact_match": 59.04446546830653,
|
| 283 |
+
"eval_f1": 75.83015637646359,
|
| 284 |
+
"step": 8700
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.64,
|
| 288 |
+
"learning_rate": 9.010938924339108e-06,
|
| 289 |
+
"loss": 1.2199,
|
| 290 |
+
"step": 9000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.64,
|
| 294 |
+
"eval_exact_match": 59.10122989593188,
|
| 295 |
+
"eval_f1": 76.0261318966032,
|
| 296 |
+
"step": 9000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.7,
|
| 300 |
+
"eval_exact_match": 59.0728476821192,
|
| 301 |
+
"eval_f1": 76.13920824424939,
|
| 302 |
+
"step": 9300
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.73,
|
| 306 |
+
"learning_rate": 6.731996353691887e-06,
|
| 307 |
+
"loss": 1.2102,
|
| 308 |
+
"step": 9500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.75,
|
| 312 |
+
"eval_exact_match": 59.0728476821192,
|
| 313 |
+
"eval_f1": 76.09156663606447,
|
| 314 |
+
"step": 9600
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.8,
|
| 318 |
+
"eval_exact_match": 59.47965941343425,
|
| 319 |
+
"eval_f1": 76.2619678916128,
|
| 320 |
+
"step": 9900
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.82,
|
| 324 |
+
"learning_rate": 4.453053783044668e-06,
|
| 325 |
+
"loss": 1.1986,
|
| 326 |
+
"step": 10000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.86,
|
| 330 |
+
"eval_exact_match": 59.6310312204352,
|
| 331 |
+
"eval_f1": 76.36038789574842,
|
| 332 |
+
"step": 10200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.91,
|
| 336 |
+
"learning_rate": 2.174111212397448e-06,
|
| 337 |
+
"loss": 1.2024,
|
| 338 |
+
"step": 10500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.91,
|
| 342 |
+
"eval_exact_match": 59.39451277199622,
|
| 343 |
+
"eval_f1": 76.24512822926708,
|
| 344 |
+
"step": 10500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.97,
|
| 348 |
+
"eval_exact_match": 59.593188268684955,
|
| 349 |
+
"eval_f1": 76.29176107833557,
|
| 350 |
+
"step": 10800
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.0,
|
| 354 |
+
"step": 10970,
|
| 355 |
+
"total_flos": 2544773915225664.0,
|
| 356 |
+
"train_loss": 1.452151380763232,
|
| 357 |
+
"train_runtime": 2009.9163,
|
| 358 |
+
"train_samples_per_second": 87.314,
|
| 359 |
+
"train_steps_per_second": 5.458
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"max_steps": 10970,
|
| 363 |
+
"num_train_epochs": 2,
|
| 364 |
+
"total_flos": 2544773915225664.0,
|
| 365 |
+
"trial_name": null,
|
| 366 |
+
"trial_params": null
|
| 367 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f1aca32c97fd106b2614462fee0df8a8f3f291faa44dc14d52196e29c437c0d
|
| 3 |
+
size 3515
|