Commit
·
616a93b
1
Parent(s):
b2b2f0d
Upload 7 files
Browse files- config.json +27 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +658 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.20.0.dev0",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ef99498453a2b5f14a1a057d288e79ac64a46e6e3a3dc077deccef485cd6ba
|
| 3 |
+
size 997696473
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8e0d22aa0718e69f4de1e9cdadb4e44a7bfc44b9072d4edacec255e1ded6c4e
|
| 3 |
+
size 498861675
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6793604ea0058af7e9bd95fab943108e031c394c4e622771198b6cc3ceac116a
|
| 3 |
+
size 17563
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e376b226761ba465a326f91cf97f11b9af7df499d4c2fc53007f8c8de02c4915
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,658 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 45.96219931271477,
|
| 5 |
+
"global_step": 53500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.43,
|
| 12 |
+
"learning_rate": 4.97852233676976e-05,
|
| 13 |
+
"loss": 2.4481,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.86,
|
| 18 |
+
"learning_rate": 4.957044673539519e-05,
|
| 19 |
+
"loss": 2.0258,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.29,
|
| 24 |
+
"learning_rate": 4.935567010309279e-05,
|
| 25 |
+
"loss": 1.8794,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.72,
|
| 30 |
+
"learning_rate": 4.9140893470790375e-05,
|
| 31 |
+
"loss": 1.8082,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.15,
|
| 36 |
+
"learning_rate": 4.892611683848797e-05,
|
| 37 |
+
"loss": 1.7553,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.58,
|
| 42 |
+
"learning_rate": 4.871134020618557e-05,
|
| 43 |
+
"loss": 1.6993,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.01,
|
| 48 |
+
"learning_rate": 4.849656357388316e-05,
|
| 49 |
+
"loss": 1.6629,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.44,
|
| 54 |
+
"learning_rate": 4.828178694158076e-05,
|
| 55 |
+
"loss": 1.6249,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.87,
|
| 60 |
+
"learning_rate": 4.806701030927835e-05,
|
| 61 |
+
"loss": 1.6062,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.3,
|
| 66 |
+
"learning_rate": 4.785223367697595e-05,
|
| 67 |
+
"loss": 1.5661,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.73,
|
| 72 |
+
"learning_rate": 4.763745704467354e-05,
|
| 73 |
+
"loss": 1.5406,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 5.15,
|
| 78 |
+
"learning_rate": 4.7422680412371134e-05,
|
| 79 |
+
"loss": 1.5285,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.58,
|
| 84 |
+
"learning_rate": 4.720790378006873e-05,
|
| 85 |
+
"loss": 1.5024,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 6.01,
|
| 90 |
+
"learning_rate": 4.6993127147766324e-05,
|
| 91 |
+
"loss": 1.4933,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.44,
|
| 96 |
+
"learning_rate": 4.677835051546392e-05,
|
| 97 |
+
"loss": 1.474,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.87,
|
| 102 |
+
"learning_rate": 4.656357388316151e-05,
|
| 103 |
+
"loss": 1.46,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.3,
|
| 108 |
+
"learning_rate": 4.634879725085911e-05,
|
| 109 |
+
"loss": 1.4409,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.73,
|
| 114 |
+
"learning_rate": 4.61340206185567e-05,
|
| 115 |
+
"loss": 1.4251,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 8.16,
|
| 120 |
+
"learning_rate": 4.5919243986254295e-05,
|
| 121 |
+
"loss": 1.4157,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 8.59,
|
| 126 |
+
"learning_rate": 4.570446735395189e-05,
|
| 127 |
+
"loss": 1.3975,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 9.02,
|
| 132 |
+
"learning_rate": 4.5489690721649484e-05,
|
| 133 |
+
"loss": 1.3924,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 9.45,
|
| 138 |
+
"learning_rate": 4.527491408934708e-05,
|
| 139 |
+
"loss": 1.3699,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 9.88,
|
| 144 |
+
"learning_rate": 4.5060137457044674e-05,
|
| 145 |
+
"loss": 1.3711,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 10.31,
|
| 150 |
+
"learning_rate": 4.484536082474227e-05,
|
| 151 |
+
"loss": 1.3514,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.74,
|
| 156 |
+
"learning_rate": 4.463058419243987e-05,
|
| 157 |
+
"loss": 1.3502,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 11.17,
|
| 162 |
+
"learning_rate": 4.4415807560137455e-05,
|
| 163 |
+
"loss": 1.3308,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 11.6,
|
| 168 |
+
"learning_rate": 4.4201030927835053e-05,
|
| 169 |
+
"loss": 1.3288,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 12.03,
|
| 174 |
+
"learning_rate": 4.3986254295532645e-05,
|
| 175 |
+
"loss": 1.3197,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 12.46,
|
| 180 |
+
"learning_rate": 4.377147766323024e-05,
|
| 181 |
+
"loss": 1.3022,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 12.89,
|
| 186 |
+
"learning_rate": 4.3556701030927835e-05,
|
| 187 |
+
"loss": 1.3039,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 13.32,
|
| 192 |
+
"learning_rate": 4.334192439862543e-05,
|
| 193 |
+
"loss": 1.2948,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 13.75,
|
| 198 |
+
"learning_rate": 4.312714776632303e-05,
|
| 199 |
+
"loss": 1.2842,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 14.18,
|
| 204 |
+
"learning_rate": 4.2912371134020616e-05,
|
| 205 |
+
"loss": 1.2804,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 14.6,
|
| 210 |
+
"learning_rate": 4.2697594501718214e-05,
|
| 211 |
+
"loss": 1.2646,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 15.03,
|
| 216 |
+
"learning_rate": 4.2482817869415805e-05,
|
| 217 |
+
"loss": 1.2672,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 15.46,
|
| 222 |
+
"learning_rate": 4.2268041237113404e-05,
|
| 223 |
+
"loss": 1.2501,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 15.89,
|
| 228 |
+
"learning_rate": 4.2053264604811e-05,
|
| 229 |
+
"loss": 1.2566,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 16.32,
|
| 234 |
+
"learning_rate": 4.1838487972508593e-05,
|
| 235 |
+
"loss": 1.2406,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 16.75,
|
| 240 |
+
"learning_rate": 4.162371134020619e-05,
|
| 241 |
+
"loss": 1.2383,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 17.18,
|
| 246 |
+
"learning_rate": 4.140893470790378e-05,
|
| 247 |
+
"loss": 1.2246,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 17.61,
|
| 252 |
+
"learning_rate": 4.1194158075601375e-05,
|
| 253 |
+
"loss": 1.2219,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 18.04,
|
| 258 |
+
"learning_rate": 4.097938144329897e-05,
|
| 259 |
+
"loss": 1.2174,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 18.47,
|
| 264 |
+
"learning_rate": 4.0764604810996564e-05,
|
| 265 |
+
"loss": 1.2089,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 18.9,
|
| 270 |
+
"learning_rate": 4.054982817869416e-05,
|
| 271 |
+
"loss": 1.2049,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 19.33,
|
| 276 |
+
"learning_rate": 4.0335051546391754e-05,
|
| 277 |
+
"loss": 1.2014,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 19.76,
|
| 282 |
+
"learning_rate": 4.012027491408935e-05,
|
| 283 |
+
"loss": 1.1965,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 20.19,
|
| 288 |
+
"learning_rate": 3.9905498281786944e-05,
|
| 289 |
+
"loss": 1.184,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 20.62,
|
| 294 |
+
"learning_rate": 3.9690721649484535e-05,
|
| 295 |
+
"loss": 1.178,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 21.05,
|
| 300 |
+
"learning_rate": 3.9475945017182134e-05,
|
| 301 |
+
"loss": 1.1801,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 21.48,
|
| 306 |
+
"learning_rate": 3.9261168384879725e-05,
|
| 307 |
+
"loss": 1.1661,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 21.91,
|
| 312 |
+
"learning_rate": 3.904639175257732e-05,
|
| 313 |
+
"loss": 1.1687,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 22.34,
|
| 318 |
+
"learning_rate": 3.8831615120274915e-05,
|
| 319 |
+
"loss": 1.1636,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 22.77,
|
| 324 |
+
"learning_rate": 3.861683848797251e-05,
|
| 325 |
+
"loss": 1.1578,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 23.2,
|
| 330 |
+
"learning_rate": 3.8402061855670104e-05,
|
| 331 |
+
"loss": 1.1456,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 23.63,
|
| 336 |
+
"learning_rate": 3.8187285223367696e-05,
|
| 337 |
+
"loss": 1.148,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 24.05,
|
| 342 |
+
"learning_rate": 3.7972508591065294e-05,
|
| 343 |
+
"loss": 1.1458,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 24.48,
|
| 348 |
+
"learning_rate": 3.7757731958762886e-05,
|
| 349 |
+
"loss": 1.1348,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 24.91,
|
| 354 |
+
"learning_rate": 3.7542955326460484e-05,
|
| 355 |
+
"loss": 1.1359,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 25.34,
|
| 360 |
+
"learning_rate": 3.7328178694158075e-05,
|
| 361 |
+
"loss": 1.1266,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 25.77,
|
| 366 |
+
"learning_rate": 3.7113402061855674e-05,
|
| 367 |
+
"loss": 1.1193,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 26.2,
|
| 372 |
+
"learning_rate": 3.689862542955327e-05,
|
| 373 |
+
"loss": 1.1201,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 26.63,
|
| 378 |
+
"learning_rate": 3.6683848797250856e-05,
|
| 379 |
+
"loss": 1.1177,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 27.06,
|
| 384 |
+
"learning_rate": 3.6469072164948455e-05,
|
| 385 |
+
"loss": 1.1102,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 27.49,
|
| 390 |
+
"learning_rate": 3.6254295532646046e-05,
|
| 391 |
+
"loss": 1.1038,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 27.92,
|
| 396 |
+
"learning_rate": 3.6039518900343644e-05,
|
| 397 |
+
"loss": 1.1086,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 28.35,
|
| 402 |
+
"learning_rate": 3.5824742268041236e-05,
|
| 403 |
+
"loss": 1.0972,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 28.78,
|
| 408 |
+
"learning_rate": 3.5609965635738834e-05,
|
| 409 |
+
"loss": 1.1021,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 29.21,
|
| 414 |
+
"learning_rate": 3.539518900343643e-05,
|
| 415 |
+
"loss": 1.0974,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 29.64,
|
| 420 |
+
"learning_rate": 3.5180412371134024e-05,
|
| 421 |
+
"loss": 1.0839,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 30.07,
|
| 426 |
+
"learning_rate": 3.4965635738831615e-05,
|
| 427 |
+
"loss": 1.0918,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 30.5,
|
| 432 |
+
"learning_rate": 3.475085910652921e-05,
|
| 433 |
+
"loss": 1.0809,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 30.93,
|
| 438 |
+
"learning_rate": 3.4536082474226805e-05,
|
| 439 |
+
"loss": 1.0789,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 31.36,
|
| 444 |
+
"learning_rate": 3.43213058419244e-05,
|
| 445 |
+
"loss": 1.0741,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 31.79,
|
| 450 |
+
"learning_rate": 3.4106529209621995e-05,
|
| 451 |
+
"loss": 1.0701,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 32.22,
|
| 456 |
+
"learning_rate": 3.389175257731959e-05,
|
| 457 |
+
"loss": 1.0648,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 32.65,
|
| 462 |
+
"learning_rate": 3.3676975945017185e-05,
|
| 463 |
+
"loss": 1.0627,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 33.08,
|
| 468 |
+
"learning_rate": 3.3462199312714776e-05,
|
| 469 |
+
"loss": 1.0659,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 33.51,
|
| 474 |
+
"learning_rate": 3.3247422680412374e-05,
|
| 475 |
+
"loss": 1.05,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 33.93,
|
| 480 |
+
"learning_rate": 3.3032646048109966e-05,
|
| 481 |
+
"loss": 1.0496,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 34.36,
|
| 486 |
+
"learning_rate": 3.2817869415807564e-05,
|
| 487 |
+
"loss": 1.0472,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 34.79,
|
| 492 |
+
"learning_rate": 3.2603092783505155e-05,
|
| 493 |
+
"loss": 1.0439,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 35.22,
|
| 498 |
+
"learning_rate": 3.2388316151202754e-05,
|
| 499 |
+
"loss": 1.0453,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 35.65,
|
| 504 |
+
"learning_rate": 3.2173539518900345e-05,
|
| 505 |
+
"loss": 1.0418,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 36.08,
|
| 510 |
+
"learning_rate": 3.1958762886597937e-05,
|
| 511 |
+
"loss": 1.0342,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 36.51,
|
| 516 |
+
"learning_rate": 3.1743986254295535e-05,
|
| 517 |
+
"loss": 1.0258,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 36.94,
|
| 522 |
+
"learning_rate": 3.1529209621993126e-05,
|
| 523 |
+
"loss": 1.0319,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 37.37,
|
| 528 |
+
"learning_rate": 3.1314432989690725e-05,
|
| 529 |
+
"loss": 1.0238,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 37.8,
|
| 534 |
+
"learning_rate": 3.1099656357388316e-05,
|
| 535 |
+
"loss": 1.0274,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 38.23,
|
| 540 |
+
"learning_rate": 3.0884879725085914e-05,
|
| 541 |
+
"loss": 1.0233,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 38.66,
|
| 546 |
+
"learning_rate": 3.0670103092783506e-05,
|
| 547 |
+
"loss": 1.0209,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 39.09,
|
| 552 |
+
"learning_rate": 3.0455326460481097e-05,
|
| 553 |
+
"loss": 1.0164,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 39.52,
|
| 558 |
+
"learning_rate": 3.0240549828178692e-05,
|
| 559 |
+
"loss": 1.0027,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 39.95,
|
| 564 |
+
"learning_rate": 3.002577319587629e-05,
|
| 565 |
+
"loss": 1.0168,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 40.38,
|
| 570 |
+
"learning_rate": 2.9810996563573885e-05,
|
| 571 |
+
"loss": 1.0003,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 40.81,
|
| 576 |
+
"learning_rate": 2.959621993127148e-05,
|
| 577 |
+
"loss": 1.0067,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 41.24,
|
| 582 |
+
"learning_rate": 2.9381443298969075e-05,
|
| 583 |
+
"loss": 0.9941,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 41.67,
|
| 588 |
+
"learning_rate": 2.916666666666667e-05,
|
| 589 |
+
"loss": 1.0014,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 42.1,
|
| 594 |
+
"learning_rate": 2.8951890034364265e-05,
|
| 595 |
+
"loss": 0.9963,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 42.53,
|
| 600 |
+
"learning_rate": 2.8737113402061856e-05,
|
| 601 |
+
"loss": 0.9899,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 42.96,
|
| 606 |
+
"learning_rate": 2.852233676975945e-05,
|
| 607 |
+
"loss": 0.9882,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 43.38,
|
| 612 |
+
"learning_rate": 2.8307560137457046e-05,
|
| 613 |
+
"loss": 0.9832,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 43.81,
|
| 618 |
+
"learning_rate": 2.809278350515464e-05,
|
| 619 |
+
"loss": 0.9817,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 44.24,
|
| 624 |
+
"learning_rate": 2.7878006872852236e-05,
|
| 625 |
+
"loss": 0.9816,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 44.67,
|
| 630 |
+
"learning_rate": 2.766323024054983e-05,
|
| 631 |
+
"loss": 0.9795,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 45.1,
|
| 636 |
+
"learning_rate": 2.7448453608247425e-05,
|
| 637 |
+
"loss": 0.9737,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 45.53,
|
| 642 |
+
"learning_rate": 2.7233676975945017e-05,
|
| 643 |
+
"loss": 0.9693,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 45.96,
|
| 648 |
+
"learning_rate": 2.701890034364261e-05,
|
| 649 |
+
"loss": 0.9735,
|
| 650 |
+
"step": 53500
|
| 651 |
+
}
|
| 652 |
+
],
|
| 653 |
+
"max_steps": 116400,
|
| 654 |
+
"num_train_epochs": 100,
|
| 655 |
+
"total_flos": 4.504557638270131e+17,
|
| 656 |
+
"trial_name": null,
|
| 657 |
+
"trial_params": null
|
| 658 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcd1e3c8a373a807431a192a7b311d63547ff531f9d69479c69e0718e1360044
|
| 3 |
+
size 3311
|