Jason Wu
commited on
Commit
•
2ca8142
1
Parent(s):
dda0885
init
Browse files- config.json +28 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +654 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/roberta-large-squad2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"language": "english",
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"name": "Roberta",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 24,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"transformers_version": "4.6.0.dev0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:798b0d269a9dc217c26732e4355362a7cbf1f3c9d509419ebe6023c6b1b618f5
|
| 3 |
+
size 1417344577
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "model_max_length": 512, "name_or_path": "deepset/roberta-large-squad2", "special_tokens_map_file": "../saved_models/farm_roberta-large-squad2/special_tokens_map.json"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,654 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.999350804660539,
|
| 5 |
+
"global_step": 4570,
|
| 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 |
+
"learning_rate": 1.5e-06,
|
| 13 |
+
"loss": 2.6965,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 3e-06,
|
| 19 |
+
"loss": 1.85,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"learning_rate": 4.5e-06,
|
| 25 |
+
"loss": 1.7546,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.22,
|
| 30 |
+
"learning_rate": 6e-06,
|
| 31 |
+
"loss": 1.6255,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.27,
|
| 36 |
+
"learning_rate": 7.5e-06,
|
| 37 |
+
"loss": 1.5579,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.33,
|
| 42 |
+
"learning_rate": 9e-06,
|
| 43 |
+
"loss": 1.5321,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.38,
|
| 48 |
+
"learning_rate": 1.05e-05,
|
| 49 |
+
"loss": 1.4919,
|
| 50 |
+
"step": 350
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.44,
|
| 54 |
+
"learning_rate": 1.2e-05,
|
| 55 |
+
"loss": 1.4036,
|
| 56 |
+
"step": 400
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.49,
|
| 60 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 61 |
+
"loss": 1.4189,
|
| 62 |
+
"step": 450
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.55,
|
| 66 |
+
"learning_rate": 1.5e-05,
|
| 67 |
+
"loss": 1.4814,
|
| 68 |
+
"step": 500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.6,
|
| 72 |
+
"learning_rate": 1.65e-05,
|
| 73 |
+
"loss": 1.5028,
|
| 74 |
+
"step": 550
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.66,
|
| 78 |
+
"learning_rate": 1.8e-05,
|
| 79 |
+
"loss": 1.4442,
|
| 80 |
+
"step": 600
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.71,
|
| 84 |
+
"learning_rate": 1.95e-05,
|
| 85 |
+
"loss": 1.4614,
|
| 86 |
+
"step": 650
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.77,
|
| 90 |
+
"learning_rate": 2.1e-05,
|
| 91 |
+
"loss": 1.3753,
|
| 92 |
+
"step": 700
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.82,
|
| 96 |
+
"learning_rate": 2.25e-05,
|
| 97 |
+
"loss": 1.3651,
|
| 98 |
+
"step": 750
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.87,
|
| 102 |
+
"learning_rate": 2.4e-05,
|
| 103 |
+
"loss": 1.4083,
|
| 104 |
+
"step": 800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.93,
|
| 108 |
+
"learning_rate": 2.55e-05,
|
| 109 |
+
"loss": 1.4364,
|
| 110 |
+
"step": 850
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.98,
|
| 114 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 115 |
+
"loss": 1.448,
|
| 116 |
+
"step": 900
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"HasAns_exact": 58.954531394989175,
|
| 120 |
+
"HasAns_f1": 74.09900890720559,
|
| 121 |
+
"HasAns_total": 3233,
|
| 122 |
+
"NoAns_exact": 71.16564417177914,
|
| 123 |
+
"NoAns_f1": 71.16564417177914,
|
| 124 |
+
"NoAns_total": 163,
|
| 125 |
+
"best_exact": 60.924617196702,
|
| 126 |
+
"best_exact_thresh": 0.0,
|
| 127 |
+
"best_f1": 75.3421954643685,
|
| 128 |
+
"best_f1_thresh": 0.0,
|
| 129 |
+
"epoch": 1.0,
|
| 130 |
+
"exact": 59.540636042402824,
|
| 131 |
+
"f1": 73.9582143100694,
|
| 132 |
+
"step": 914,
|
| 133 |
+
"total": 3396
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.04,
|
| 137 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 138 |
+
"loss": 1.3679,
|
| 139 |
+
"step": 950
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.09,
|
| 143 |
+
"learning_rate": 3e-05,
|
| 144 |
+
"loss": 1.2567,
|
| 145 |
+
"step": 1000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.15,
|
| 149 |
+
"learning_rate": 2.957983193277311e-05,
|
| 150 |
+
"loss": 1.2319,
|
| 151 |
+
"step": 1050
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.2,
|
| 155 |
+
"learning_rate": 2.9159663865546218e-05,
|
| 156 |
+
"loss": 1.2453,
|
| 157 |
+
"step": 1100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.26,
|
| 161 |
+
"learning_rate": 2.8739495798319328e-05,
|
| 162 |
+
"loss": 1.3484,
|
| 163 |
+
"step": 1150
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.31,
|
| 167 |
+
"learning_rate": 2.831932773109244e-05,
|
| 168 |
+
"loss": 1.2464,
|
| 169 |
+
"step": 1200
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.37,
|
| 173 |
+
"learning_rate": 2.789915966386555e-05,
|
| 174 |
+
"loss": 1.2314,
|
| 175 |
+
"step": 1250
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.42,
|
| 179 |
+
"learning_rate": 2.7478991596638655e-05,
|
| 180 |
+
"loss": 1.3351,
|
| 181 |
+
"step": 1300
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.48,
|
| 185 |
+
"learning_rate": 2.7058823529411766e-05,
|
| 186 |
+
"loss": 1.2563,
|
| 187 |
+
"step": 1350
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.53,
|
| 191 |
+
"learning_rate": 2.6638655462184873e-05,
|
| 192 |
+
"loss": 1.3376,
|
| 193 |
+
"step": 1400
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.59,
|
| 197 |
+
"learning_rate": 2.6218487394957983e-05,
|
| 198 |
+
"loss": 1.2481,
|
| 199 |
+
"step": 1450
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.64,
|
| 203 |
+
"learning_rate": 2.5798319327731093e-05,
|
| 204 |
+
"loss": 1.1875,
|
| 205 |
+
"step": 1500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.7,
|
| 209 |
+
"learning_rate": 2.5378151260504203e-05,
|
| 210 |
+
"loss": 1.2709,
|
| 211 |
+
"step": 1550
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.75,
|
| 215 |
+
"learning_rate": 2.4957983193277314e-05,
|
| 216 |
+
"loss": 1.1849,
|
| 217 |
+
"step": 1600
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.8,
|
| 221 |
+
"learning_rate": 2.453781512605042e-05,
|
| 222 |
+
"loss": 1.2105,
|
| 223 |
+
"step": 1650
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.86,
|
| 227 |
+
"learning_rate": 2.411764705882353e-05,
|
| 228 |
+
"loss": 1.2137,
|
| 229 |
+
"step": 1700
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.91,
|
| 233 |
+
"learning_rate": 2.3697478991596638e-05,
|
| 234 |
+
"loss": 1.2807,
|
| 235 |
+
"step": 1750
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.97,
|
| 239 |
+
"learning_rate": 2.3277310924369748e-05,
|
| 240 |
+
"loss": 1.2816,
|
| 241 |
+
"step": 1800
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"HasAns_exact": 61.58366841942468,
|
| 245 |
+
"HasAns_f1": 76.76180559350382,
|
| 246 |
+
"HasAns_total": 3233,
|
| 247 |
+
"NoAns_exact": 54.60122699386503,
|
| 248 |
+
"NoAns_f1": 54.60122699386503,
|
| 249 |
+
"NoAns_total": 163,
|
| 250 |
+
"best_exact": 63.42756183745583,
|
| 251 |
+
"best_exact_thresh": 0.0,
|
| 252 |
+
"best_f1": 77.87718418250819,
|
| 253 |
+
"best_f1_thresh": 0.0,
|
| 254 |
+
"epoch": 2.0,
|
| 255 |
+
"exact": 61.24852767962309,
|
| 256 |
+
"f1": 75.69815002467547,
|
| 257 |
+
"step": 1828,
|
| 258 |
+
"total": 3396
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.02,
|
| 262 |
+
"learning_rate": 2.2857142857142858e-05,
|
| 263 |
+
"loss": 1.0327,
|
| 264 |
+
"step": 1850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.08,
|
| 268 |
+
"learning_rate": 2.2436974789915968e-05,
|
| 269 |
+
"loss": 0.896,
|
| 270 |
+
"step": 1900
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.13,
|
| 274 |
+
"learning_rate": 2.2016806722689075e-05,
|
| 275 |
+
"loss": 0.9569,
|
| 276 |
+
"step": 1950
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.19,
|
| 280 |
+
"learning_rate": 2.1596638655462185e-05,
|
| 281 |
+
"loss": 0.8276,
|
| 282 |
+
"step": 2000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.24,
|
| 286 |
+
"learning_rate": 2.1176470588235296e-05,
|
| 287 |
+
"loss": 0.9038,
|
| 288 |
+
"step": 2050
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.3,
|
| 292 |
+
"learning_rate": 2.0756302521008403e-05,
|
| 293 |
+
"loss": 0.9296,
|
| 294 |
+
"step": 2100
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.35,
|
| 298 |
+
"learning_rate": 2.0336134453781513e-05,
|
| 299 |
+
"loss": 0.868,
|
| 300 |
+
"step": 2150
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.41,
|
| 304 |
+
"learning_rate": 1.9915966386554623e-05,
|
| 305 |
+
"loss": 0.884,
|
| 306 |
+
"step": 2200
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.46,
|
| 310 |
+
"learning_rate": 1.9495798319327733e-05,
|
| 311 |
+
"loss": 0.8594,
|
| 312 |
+
"step": 2250
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.52,
|
| 316 |
+
"learning_rate": 1.907563025210084e-05,
|
| 317 |
+
"loss": 0.8973,
|
| 318 |
+
"step": 2300
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.57,
|
| 322 |
+
"learning_rate": 1.865546218487395e-05,
|
| 323 |
+
"loss": 0.9248,
|
| 324 |
+
"step": 2350
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.63,
|
| 328 |
+
"learning_rate": 1.8235294117647057e-05,
|
| 329 |
+
"loss": 0.8629,
|
| 330 |
+
"step": 2400
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.68,
|
| 334 |
+
"learning_rate": 1.7815126050420167e-05,
|
| 335 |
+
"loss": 0.9535,
|
| 336 |
+
"step": 2450
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.73,
|
| 340 |
+
"learning_rate": 1.7394957983193278e-05,
|
| 341 |
+
"loss": 0.9778,
|
| 342 |
+
"step": 2500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.79,
|
| 346 |
+
"learning_rate": 1.6974789915966388e-05,
|
| 347 |
+
"loss": 0.8858,
|
| 348 |
+
"step": 2550
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.84,
|
| 352 |
+
"learning_rate": 1.6554621848739498e-05,
|
| 353 |
+
"loss": 0.8855,
|
| 354 |
+
"step": 2600
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.9,
|
| 358 |
+
"learning_rate": 1.6134453781512605e-05,
|
| 359 |
+
"loss": 0.9669,
|
| 360 |
+
"step": 2650
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.95,
|
| 364 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 365 |
+
"loss": 0.8746,
|
| 366 |
+
"step": 2700
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"HasAns_exact": 60.81039282400248,
|
| 370 |
+
"HasAns_f1": 76.48517908547677,
|
| 371 |
+
"HasAns_total": 3233,
|
| 372 |
+
"NoAns_exact": 57.668711656441715,
|
| 373 |
+
"NoAns_f1": 57.668711656441715,
|
| 374 |
+
"NoAns_total": 163,
|
| 375 |
+
"best_exact": 62.69140164899882,
|
| 376 |
+
"best_exact_thresh": 0.0,
|
| 377 |
+
"best_f1": 77.61383509521386,
|
| 378 |
+
"best_f1_thresh": 0.0,
|
| 379 |
+
"epoch": 3.0,
|
| 380 |
+
"exact": 60.65959952885748,
|
| 381 |
+
"f1": 75.58203297507256,
|
| 382 |
+
"step": 2742,
|
| 383 |
+
"total": 3396
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.01,
|
| 387 |
+
"learning_rate": 1.5294117647058822e-05,
|
| 388 |
+
"loss": 0.8392,
|
| 389 |
+
"step": 2750
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.06,
|
| 393 |
+
"learning_rate": 1.4873949579831934e-05,
|
| 394 |
+
"loss": 0.6246,
|
| 395 |
+
"step": 2800
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.12,
|
| 399 |
+
"learning_rate": 1.4453781512605043e-05,
|
| 400 |
+
"loss": 0.6114,
|
| 401 |
+
"step": 2850
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.17,
|
| 405 |
+
"learning_rate": 1.4033613445378151e-05,
|
| 406 |
+
"loss": 0.6607,
|
| 407 |
+
"step": 2900
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.23,
|
| 411 |
+
"learning_rate": 1.3613445378151261e-05,
|
| 412 |
+
"loss": 0.6362,
|
| 413 |
+
"step": 2950
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.28,
|
| 417 |
+
"learning_rate": 1.319327731092437e-05,
|
| 418 |
+
"loss": 0.6954,
|
| 419 |
+
"step": 3000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.34,
|
| 423 |
+
"learning_rate": 1.2773109243697479e-05,
|
| 424 |
+
"loss": 0.5845,
|
| 425 |
+
"step": 3050
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.39,
|
| 429 |
+
"learning_rate": 1.2352941176470587e-05,
|
| 430 |
+
"loss": 0.6107,
|
| 431 |
+
"step": 3100
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.45,
|
| 435 |
+
"learning_rate": 1.1932773109243697e-05,
|
| 436 |
+
"loss": 0.5863,
|
| 437 |
+
"step": 3150
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.5,
|
| 441 |
+
"learning_rate": 1.1512605042016808e-05,
|
| 442 |
+
"loss": 0.6415,
|
| 443 |
+
"step": 3200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.56,
|
| 447 |
+
"learning_rate": 1.1092436974789916e-05,
|
| 448 |
+
"loss": 0.6494,
|
| 449 |
+
"step": 3250
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.61,
|
| 453 |
+
"learning_rate": 1.0672268907563026e-05,
|
| 454 |
+
"loss": 0.6521,
|
| 455 |
+
"step": 3300
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.66,
|
| 459 |
+
"learning_rate": 1.0252100840336135e-05,
|
| 460 |
+
"loss": 0.6182,
|
| 461 |
+
"step": 3350
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.72,
|
| 465 |
+
"learning_rate": 9.831932773109244e-06,
|
| 466 |
+
"loss": 0.6293,
|
| 467 |
+
"step": 3400
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.77,
|
| 471 |
+
"learning_rate": 9.411764705882354e-06,
|
| 472 |
+
"loss": 0.5783,
|
| 473 |
+
"step": 3450
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.83,
|
| 477 |
+
"learning_rate": 8.991596638655462e-06,
|
| 478 |
+
"loss": 0.5962,
|
| 479 |
+
"step": 3500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 3.88,
|
| 483 |
+
"learning_rate": 8.571428571428571e-06,
|
| 484 |
+
"loss": 0.6096,
|
| 485 |
+
"step": 3550
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.94,
|
| 489 |
+
"learning_rate": 8.15126050420168e-06,
|
| 490 |
+
"loss": 0.6828,
|
| 491 |
+
"step": 3600
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.99,
|
| 495 |
+
"learning_rate": 7.73109243697479e-06,
|
| 496 |
+
"loss": 0.6435,
|
| 497 |
+
"step": 3650
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"HasAns_exact": 61.24342715743891,
|
| 501 |
+
"HasAns_f1": 76.51996301360617,
|
| 502 |
+
"HasAns_total": 3233,
|
| 503 |
+
"NoAns_exact": 60.736196319018404,
|
| 504 |
+
"NoAns_f1": 60.736196319018404,
|
| 505 |
+
"NoAns_total": 163,
|
| 506 |
+
"best_exact": 63.10365135453475,
|
| 507 |
+
"best_exact_thresh": 0.0,
|
| 508 |
+
"best_f1": 77.64694947673401,
|
| 509 |
+
"best_f1_thresh": 0.0,
|
| 510 |
+
"epoch": 4.0,
|
| 511 |
+
"exact": 61.21908127208481,
|
| 512 |
+
"f1": 75.76237939428408,
|
| 513 |
+
"step": 3656,
|
| 514 |
+
"total": 3396
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 4.05,
|
| 518 |
+
"learning_rate": 7.310924369747899e-06,
|
| 519 |
+
"loss": 0.4823,
|
| 520 |
+
"step": 3700
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 4.1,
|
| 524 |
+
"learning_rate": 6.8907563025210085e-06,
|
| 525 |
+
"loss": 0.4437,
|
| 526 |
+
"step": 3750
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 4.16,
|
| 530 |
+
"learning_rate": 6.470588235294118e-06,
|
| 531 |
+
"loss": 0.4424,
|
| 532 |
+
"step": 3800
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 4.21,
|
| 536 |
+
"learning_rate": 6.050420168067227e-06,
|
| 537 |
+
"loss": 0.4736,
|
| 538 |
+
"step": 3850
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 4.27,
|
| 542 |
+
"learning_rate": 5.630252100840336e-06,
|
| 543 |
+
"loss": 0.4747,
|
| 544 |
+
"step": 3900
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 4.32,
|
| 548 |
+
"learning_rate": 5.210084033613445e-06,
|
| 549 |
+
"loss": 0.4094,
|
| 550 |
+
"step": 3950
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 4.38,
|
| 554 |
+
"learning_rate": 4.789915966386555e-06,
|
| 555 |
+
"loss": 0.4644,
|
| 556 |
+
"step": 4000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 4.43,
|
| 560 |
+
"learning_rate": 4.369747899159664e-06,
|
| 561 |
+
"loss": 0.4356,
|
| 562 |
+
"step": 4050
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 4.49,
|
| 566 |
+
"learning_rate": 3.9495798319327735e-06,
|
| 567 |
+
"loss": 0.4324,
|
| 568 |
+
"step": 4100
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 4.54,
|
| 572 |
+
"learning_rate": 3.5294117647058825e-06,
|
| 573 |
+
"loss": 0.4429,
|
| 574 |
+
"step": 4150
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 4.59,
|
| 578 |
+
"learning_rate": 3.109243697478992e-06,
|
| 579 |
+
"loss": 0.4524,
|
| 580 |
+
"step": 4200
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 4.65,
|
| 584 |
+
"learning_rate": 2.689075630252101e-06,
|
| 585 |
+
"loss": 0.4388,
|
| 586 |
+
"step": 4250
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 4.7,
|
| 590 |
+
"learning_rate": 2.26890756302521e-06,
|
| 591 |
+
"loss": 0.4409,
|
| 592 |
+
"step": 4300
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 4.76,
|
| 596 |
+
"learning_rate": 1.8487394957983194e-06,
|
| 597 |
+
"loss": 0.4438,
|
| 598 |
+
"step": 4350
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 4.81,
|
| 602 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 603 |
+
"loss": 0.3694,
|
| 604 |
+
"step": 4400
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.87,
|
| 608 |
+
"learning_rate": 1.0084033613445378e-06,
|
| 609 |
+
"loss": 0.4524,
|
| 610 |
+
"step": 4450
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 4.92,
|
| 614 |
+
"learning_rate": 5.882352941176471e-07,
|
| 615 |
+
"loss": 0.4175,
|
| 616 |
+
"step": 4500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 4.98,
|
| 620 |
+
"learning_rate": 1.680672268907563e-07,
|
| 621 |
+
"loss": 0.4197,
|
| 622 |
+
"step": 4550
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"HasAns_exact": 61.11970306217136,
|
| 626 |
+
"HasAns_f1": 76.44576049759735,
|
| 627 |
+
"HasAns_total": 3233,
|
| 628 |
+
"NoAns_exact": 65.03067484662577,
|
| 629 |
+
"NoAns_f1": 65.03067484662577,
|
| 630 |
+
"NoAns_total": 163,
|
| 631 |
+
"best_exact": 62.985865724381625,
|
| 632 |
+
"best_exact_thresh": 0.0,
|
| 633 |
+
"best_f1": 77.5763085066938,
|
| 634 |
+
"best_f1_thresh": 0.0,
|
| 635 |
+
"epoch": 5.0,
|
| 636 |
+
"exact": 61.30742049469965,
|
| 637 |
+
"f1": 75.89786327701185,
|
| 638 |
+
"step": 4570,
|
| 639 |
+
"total": 3396
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 5.0,
|
| 643 |
+
"step": 4570,
|
| 644 |
+
"total_flos": 1.5925721822134272e+17,
|
| 645 |
+
"train_runtime": 26138.3161,
|
| 646 |
+
"train_samples_per_second": 0.175
|
| 647 |
+
}
|
| 648 |
+
],
|
| 649 |
+
"max_steps": 4570,
|
| 650 |
+
"num_train_epochs": 5,
|
| 651 |
+
"total_flos": 1.5925721822134272e+17,
|
| 652 |
+
"trial_name": null,
|
| 653 |
+
"trial_params": null
|
| 654 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8c2f2f6a47b73e0ccc4d9345a2f5c35680fb66190d1ad69eea09d24aa3cc53b
|
| 3 |
+
size 2479
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|