Commit
•
477bc2f
1
Parent(s):
8644b11
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": 58.80794701986755,
|
| 4 |
+
"eval_f1": 75.75802081436439,
|
| 5 |
+
"eval_samples": 10624,
|
| 6 |
+
"train_loss": 1.4681447838476385,
|
| 7 |
+
"train_runtime": 1862.4153,
|
| 8 |
+
"train_samples": 87747,
|
| 9 |
+
"train_samples_per_second": 94.229,
|
| 10 |
+
"train_steps_per_second": 5.89
|
| 11 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/albert-base-8-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": 8,
|
| 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": 58.80794701986755,
|
| 4 |
+
"eval_f1": 75.75802081436439,
|
| 5 |
+
"eval_samples": 10624
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33eddf243de5dd5c6a61d6526d80b55477e096958d95b59dc925fd2e2db133d3
|
| 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-8-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": 1.4681447838476385,
|
| 4 |
+
"train_runtime": 1862.4153,
|
| 5 |
+
"train_samples": 87747,
|
| 6 |
+
"train_samples_per_second": 94.229,
|
| 7 |
+
"train_steps_per_second": 5.89
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,367 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 75.75802081436439,
|
| 3 |
+
"best_model_checkpoint": "/home/jcanete/ft-data/all_results/tar/albeto_base_8/epochs_2_bs_16_lr_5e-5/checkpoint-10500",
|
| 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": 43.973509933774835,
|
| 13 |
+
"eval_f1": 62.94849738783248,
|
| 14 |
+
"step": 300
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.09,
|
| 18 |
+
"learning_rate": 4.773473108477667e-05,
|
| 19 |
+
"loss": 2.4433,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.11,
|
| 24 |
+
"eval_exact_match": 47.682119205298015,
|
| 25 |
+
"eval_f1": 66.74232170504494,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"eval_exact_match": 49.84862819299905,
|
| 31 |
+
"eval_f1": 67.82623236742938,
|
| 32 |
+
"step": 900
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.18,
|
| 36 |
+
"learning_rate": 4.545578851412944e-05,
|
| 37 |
+
"loss": 1.8951,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.22,
|
| 42 |
+
"eval_exact_match": 51.7123935666982,
|
| 43 |
+
"eval_f1": 70.35883323184615,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27,
|
| 48 |
+
"learning_rate": 4.3176845943482223e-05,
|
| 49 |
+
"loss": 1.7818,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"eval_exact_match": 52.69631031220435,
|
| 55 |
+
"eval_f1": 70.10225551135818,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.33,
|
| 60 |
+
"eval_exact_match": 52.93282876064333,
|
| 61 |
+
"eval_f1": 70.57743501701938,
|
| 62 |
+
"step": 1800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.36,
|
| 66 |
+
"learning_rate": 4.0897903372835004e-05,
|
| 67 |
+
"loss": 1.7351,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.38,
|
| 72 |
+
"eval_exact_match": 53.822138126773886,
|
| 73 |
+
"eval_f1": 72.2913967717095,
|
| 74 |
+
"step": 2100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.44,
|
| 78 |
+
"eval_exact_match": 54.15326395458846,
|
| 79 |
+
"eval_f1": 71.8960686504451,
|
| 80 |
+
"step": 2400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.46,
|
| 84 |
+
"learning_rate": 3.8618960802187785e-05,
|
| 85 |
+
"loss": 1.6499,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.49,
|
| 90 |
+
"eval_exact_match": 54.91012298959319,
|
| 91 |
+
"eval_f1": 72.36339758418018,
|
| 92 |
+
"step": 2700
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.55,
|
| 96 |
+
"learning_rate": 3.6340018231540566e-05,
|
| 97 |
+
"loss": 1.6346,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.55,
|
| 102 |
+
"eval_exact_match": 55.2317880794702,
|
| 103 |
+
"eval_f1": 72.83417554949612,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.6,
|
| 108 |
+
"eval_exact_match": 56.67928098391675,
|
| 109 |
+
"eval_f1": 73.351425055483,
|
| 110 |
+
"step": 3300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.64,
|
| 114 |
+
"learning_rate": 3.406107566089335e-05,
|
| 115 |
+
"loss": 1.6113,
|
| 116 |
+
"step": 3500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.66,
|
| 120 |
+
"eval_exact_match": 56.20624408703879,
|
| 121 |
+
"eval_f1": 73.5623207381341,
|
| 122 |
+
"step": 3600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.71,
|
| 126 |
+
"eval_exact_match": 56.51844843897824,
|
| 127 |
+
"eval_f1": 73.8479893696103,
|
| 128 |
+
"step": 3900
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.73,
|
| 132 |
+
"learning_rate": 3.178213309024613e-05,
|
| 133 |
+
"loss": 1.5583,
|
| 134 |
+
"step": 4000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.77,
|
| 138 |
+
"eval_exact_match": 57.11447492904446,
|
| 139 |
+
"eval_f1": 74.4610534306545,
|
| 140 |
+
"step": 4200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.82,
|
| 144 |
+
"learning_rate": 2.9503190519598906e-05,
|
| 145 |
+
"loss": 1.5623,
|
| 146 |
+
"step": 4500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.82,
|
| 150 |
+
"eval_exact_match": 57.60643330179754,
|
| 151 |
+
"eval_f1": 74.50261751014862,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.88,
|
| 156 |
+
"eval_exact_match": 57.228003784295176,
|
| 157 |
+
"eval_f1": 74.4736305671364,
|
| 158 |
+
"step": 4800
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.91,
|
| 162 |
+
"learning_rate": 2.722880583409298e-05,
|
| 163 |
+
"loss": 1.5367,
|
| 164 |
+
"step": 5000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.93,
|
| 168 |
+
"eval_exact_match": 57.29422894985809,
|
| 169 |
+
"eval_f1": 74.42957742124376,
|
| 170 |
+
"step": 5100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.98,
|
| 174 |
+
"eval_exact_match": 57.93755912961211,
|
| 175 |
+
"eval_f1": 75.26960240667054,
|
| 176 |
+
"step": 5400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.0,
|
| 180 |
+
"learning_rate": 2.4949863263445765e-05,
|
| 181 |
+
"loss": 1.4926,
|
| 182 |
+
"step": 5500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.04,
|
| 186 |
+
"eval_exact_match": 58.438978240302745,
|
| 187 |
+
"eval_f1": 75.16537064693637,
|
| 188 |
+
"step": 5700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.09,
|
| 192 |
+
"learning_rate": 2.2670920692798542e-05,
|
| 193 |
+
"loss": 1.238,
|
| 194 |
+
"step": 6000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.09,
|
| 198 |
+
"eval_exact_match": 57.994323557237465,
|
| 199 |
+
"eval_f1": 75.09801725717467,
|
| 200 |
+
"step": 6000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.15,
|
| 204 |
+
"eval_exact_match": 58.306527909176914,
|
| 205 |
+
"eval_f1": 75.10273058477487,
|
| 206 |
+
"step": 6300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.19,
|
| 210 |
+
"learning_rate": 2.0391978122151323e-05,
|
| 211 |
+
"loss": 1.2301,
|
| 212 |
+
"step": 6500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2,
|
| 216 |
+
"eval_exact_match": 57.6631977294229,
|
| 217 |
+
"eval_f1": 75.16465753346614,
|
| 218 |
+
"step": 6600
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.26,
|
| 222 |
+
"eval_exact_match": 57.83349101229896,
|
| 223 |
+
"eval_f1": 74.40142589790919,
|
| 224 |
+
"step": 6900
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.28,
|
| 228 |
+
"learning_rate": 1.8113035551504104e-05,
|
| 229 |
+
"loss": 1.2176,
|
| 230 |
+
"step": 7000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.31,
|
| 234 |
+
"eval_exact_match": 58.39167455061495,
|
| 235 |
+
"eval_f1": 75.34980345320106,
|
| 236 |
+
"step": 7200
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.37,
|
| 240 |
+
"learning_rate": 1.583409298085688e-05,
|
| 241 |
+
"loss": 1.2076,
|
| 242 |
+
"step": 7500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.37,
|
| 246 |
+
"eval_exact_match": 58.35383159886471,
|
| 247 |
+
"eval_f1": 75.31554814626054,
|
| 248 |
+
"step": 7500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.42,
|
| 252 |
+
"eval_exact_match": 58.00378429517502,
|
| 253 |
+
"eval_f1": 75.15654833167893,
|
| 254 |
+
"step": 7800
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.46,
|
| 258 |
+
"learning_rate": 1.3555150410209664e-05,
|
| 259 |
+
"loss": 1.2522,
|
| 260 |
+
"step": 8000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.48,
|
| 264 |
+
"eval_exact_match": 58.42005676442763,
|
| 265 |
+
"eval_f1": 75.42667424347809,
|
| 266 |
+
"step": 8100
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.53,
|
| 270 |
+
"eval_exact_match": 58.533585619678334,
|
| 271 |
+
"eval_f1": 75.482174465219,
|
| 272 |
+
"step": 8400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.55,
|
| 276 |
+
"learning_rate": 1.1276207839562443e-05,
|
| 277 |
+
"loss": 1.2069,
|
| 278 |
+
"step": 8500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.59,
|
| 282 |
+
"eval_exact_match": 58.438978240302745,
|
| 283 |
+
"eval_f1": 75.37247235785051,
|
| 284 |
+
"step": 8700
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.64,
|
| 288 |
+
"learning_rate": 9.001823154056518e-06,
|
| 289 |
+
"loss": 1.2185,
|
| 290 |
+
"step": 9000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.64,
|
| 294 |
+
"eval_exact_match": 58.80794701986755,
|
| 295 |
+
"eval_f1": 75.55945320105242,
|
| 296 |
+
"step": 9000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.7,
|
| 300 |
+
"eval_exact_match": 58.63765373699149,
|
| 301 |
+
"eval_f1": 75.48349982961263,
|
| 302 |
+
"step": 9300
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.73,
|
| 306 |
+
"learning_rate": 6.722880583409298e-06,
|
| 307 |
+
"loss": 1.2221,
|
| 308 |
+
"step": 9500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.75,
|
| 312 |
+
"eval_exact_match": 58.7038789025544,
|
| 313 |
+
"eval_f1": 75.52334202995019,
|
| 314 |
+
"step": 9600
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.8,
|
| 318 |
+
"eval_exact_match": 58.87417218543046,
|
| 319 |
+
"eval_f1": 75.59476406337527,
|
| 320 |
+
"step": 9900
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.82,
|
| 324 |
+
"learning_rate": 4.443938012762078e-06,
|
| 325 |
+
"loss": 1.1926,
|
| 326 |
+
"step": 10000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.86,
|
| 330 |
+
"eval_exact_match": 58.883632923368026,
|
| 331 |
+
"eval_f1": 75.53002560032212,
|
| 332 |
+
"step": 10200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.91,
|
| 336 |
+
"learning_rate": 2.169553327256153e-06,
|
| 337 |
+
"loss": 1.216,
|
| 338 |
+
"step": 10500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.91,
|
| 342 |
+
"eval_exact_match": 58.80794701986755,
|
| 343 |
+
"eval_f1": 75.75802081436439,
|
| 344 |
+
"step": 10500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.97,
|
| 348 |
+
"eval_exact_match": 58.836329233680225,
|
| 349 |
+
"eval_f1": 75.61405946041744,
|
| 350 |
+
"step": 10800
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.0,
|
| 354 |
+
"step": 10970,
|
| 355 |
+
"total_flos": 2544773915225664.0,
|
| 356 |
+
"train_loss": 1.4681447838476385,
|
| 357 |
+
"train_runtime": 1862.4153,
|
| 358 |
+
"train_samples_per_second": 94.229,
|
| 359 |
+
"train_steps_per_second": 5.89
|
| 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 sha256:09075a1310d0698d2c495719b361db8d61fa47355bbd28e136e257c1dde53a1a
|
| 3 |
+
size 3515
|