Commit
•
e27a3ab
1
Parent(s):
46cd56f
initial commit
Browse files- config.json +26 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +412 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/contriever-msmarco",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.24.0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7206601b158dec537c1ebc4702a4a60a7f0c14ad608bf1e9e764dfbd9e90952a
|
| 3 |
+
size 876232773
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:733a6b093af04ecc1130d139bc4733d93a4c1b6d40259cec60e54068106f8530
|
| 3 |
+
size 438130617
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab069ab297d5023e8ee458ebd851a2441664b8f0346558e28c9422537069a19f
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:491f8b1926da3df271a92bdfe7e82197fb62436994975756ea186b0f23d80fd0
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:859f677806381a2caf81f1a7276cec79089b81dde7c6ef2448f0400829515c45
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.473081588745117,
|
| 3 |
+
"best_model_checkpoint": "domain-adapted-contriever/checkpoint-1440",
|
| 4 |
+
"epoch": 48.0,
|
| 5 |
+
"global_step": 1440,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_loss": 10.873493194580078,
|
| 13 |
+
"eval_runtime": 0.0467,
|
| 14 |
+
"eval_samples_per_second": 449.222,
|
| 15 |
+
"eval_steps_per_second": 64.175,
|
| 16 |
+
"step": 30
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0,
|
| 20 |
+
"eval_loss": 9.2319917678833,
|
| 21 |
+
"eval_runtime": 0.0465,
|
| 22 |
+
"eval_samples_per_second": 451.748,
|
| 23 |
+
"eval_steps_per_second": 64.535,
|
| 24 |
+
"step": 60
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 3.0,
|
| 28 |
+
"eval_loss": 7.761892318725586,
|
| 29 |
+
"eval_runtime": 0.0466,
|
| 30 |
+
"eval_samples_per_second": 450.664,
|
| 31 |
+
"eval_steps_per_second": 64.381,
|
| 32 |
+
"step": 90
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 4.0,
|
| 36 |
+
"eval_loss": 7.499742031097412,
|
| 37 |
+
"eval_runtime": 0.0467,
|
| 38 |
+
"eval_samples_per_second": 449.436,
|
| 39 |
+
"eval_steps_per_second": 64.205,
|
| 40 |
+
"step": 120
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 5.0,
|
| 44 |
+
"eval_loss": 6.862554550170898,
|
| 45 |
+
"eval_runtime": 0.0466,
|
| 46 |
+
"eval_samples_per_second": 450.876,
|
| 47 |
+
"eval_steps_per_second": 64.411,
|
| 48 |
+
"step": 150
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 6.0,
|
| 52 |
+
"eval_loss": 6.674304962158203,
|
| 53 |
+
"eval_runtime": 0.0466,
|
| 54 |
+
"eval_samples_per_second": 450.913,
|
| 55 |
+
"eval_steps_per_second": 64.416,
|
| 56 |
+
"step": 180
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 7.0,
|
| 60 |
+
"eval_loss": 6.445440292358398,
|
| 61 |
+
"eval_runtime": 0.0466,
|
| 62 |
+
"eval_samples_per_second": 450.283,
|
| 63 |
+
"eval_steps_per_second": 64.326,
|
| 64 |
+
"step": 210
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 8.0,
|
| 68 |
+
"eval_loss": 6.35595178604126,
|
| 69 |
+
"eval_runtime": 0.0468,
|
| 70 |
+
"eval_samples_per_second": 448.943,
|
| 71 |
+
"eval_steps_per_second": 64.135,
|
| 72 |
+
"step": 240
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 9.0,
|
| 76 |
+
"eval_loss": 6.049570083618164,
|
| 77 |
+
"eval_runtime": 0.0468,
|
| 78 |
+
"eval_samples_per_second": 448.913,
|
| 79 |
+
"eval_steps_per_second": 64.13,
|
| 80 |
+
"step": 270
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 10.0,
|
| 84 |
+
"eval_loss": 5.842072486877441,
|
| 85 |
+
"eval_runtime": 0.0468,
|
| 86 |
+
"eval_samples_per_second": 448.648,
|
| 87 |
+
"eval_steps_per_second": 64.093,
|
| 88 |
+
"step": 300
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 11.0,
|
| 92 |
+
"eval_loss": 6.05306339263916,
|
| 93 |
+
"eval_runtime": 0.0467,
|
| 94 |
+
"eval_samples_per_second": 449.222,
|
| 95 |
+
"eval_steps_per_second": 64.175,
|
| 96 |
+
"step": 330
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 12.0,
|
| 100 |
+
"eval_loss": 5.601278781890869,
|
| 101 |
+
"eval_runtime": 0.0474,
|
| 102 |
+
"eval_samples_per_second": 443.192,
|
| 103 |
+
"eval_steps_per_second": 63.313,
|
| 104 |
+
"step": 360
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 13.0,
|
| 108 |
+
"eval_loss": 5.842929363250732,
|
| 109 |
+
"eval_runtime": 0.048,
|
| 110 |
+
"eval_samples_per_second": 437.952,
|
| 111 |
+
"eval_steps_per_second": 62.565,
|
| 112 |
+
"step": 390
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 14.0,
|
| 116 |
+
"eval_loss": 5.403830528259277,
|
| 117 |
+
"eval_runtime": 0.0476,
|
| 118 |
+
"eval_samples_per_second": 440.999,
|
| 119 |
+
"eval_steps_per_second": 63.0,
|
| 120 |
+
"step": 420
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 15.0,
|
| 124 |
+
"eval_loss": 5.1446332931518555,
|
| 125 |
+
"eval_runtime": 0.0469,
|
| 126 |
+
"eval_samples_per_second": 448.066,
|
| 127 |
+
"eval_steps_per_second": 64.009,
|
| 128 |
+
"step": 450
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 16.0,
|
| 132 |
+
"eval_loss": 4.861954689025879,
|
| 133 |
+
"eval_runtime": 0.0478,
|
| 134 |
+
"eval_samples_per_second": 439.045,
|
| 135 |
+
"eval_steps_per_second": 62.721,
|
| 136 |
+
"step": 480
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 16.67,
|
| 140 |
+
"learning_rate": 1.9840000000000003e-05,
|
| 141 |
+
"loss": 6.8332,
|
| 142 |
+
"step": 500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 17.0,
|
| 146 |
+
"eval_loss": 5.051825046539307,
|
| 147 |
+
"eval_runtime": 0.0484,
|
| 148 |
+
"eval_samples_per_second": 433.592,
|
| 149 |
+
"eval_steps_per_second": 61.942,
|
| 150 |
+
"step": 510
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 18.0,
|
| 154 |
+
"eval_loss": 4.834855556488037,
|
| 155 |
+
"eval_runtime": 0.0475,
|
| 156 |
+
"eval_samples_per_second": 442.506,
|
| 157 |
+
"eval_steps_per_second": 63.215,
|
| 158 |
+
"step": 540
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 19.0,
|
| 162 |
+
"eval_loss": 4.873433589935303,
|
| 163 |
+
"eval_runtime": 0.0478,
|
| 164 |
+
"eval_samples_per_second": 439.758,
|
| 165 |
+
"eval_steps_per_second": 62.823,
|
| 166 |
+
"step": 570
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 20.0,
|
| 170 |
+
"eval_loss": 4.606621265411377,
|
| 171 |
+
"eval_runtime": 0.0471,
|
| 172 |
+
"eval_samples_per_second": 445.719,
|
| 173 |
+
"eval_steps_per_second": 63.674,
|
| 174 |
+
"step": 600
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 21.0,
|
| 178 |
+
"eval_loss": 4.420989513397217,
|
| 179 |
+
"eval_runtime": 0.0469,
|
| 180 |
+
"eval_samples_per_second": 447.929,
|
| 181 |
+
"eval_steps_per_second": 63.99,
|
| 182 |
+
"step": 630
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 22.0,
|
| 186 |
+
"eval_loss": 4.37644100189209,
|
| 187 |
+
"eval_runtime": 0.0472,
|
| 188 |
+
"eval_samples_per_second": 445.111,
|
| 189 |
+
"eval_steps_per_second": 63.587,
|
| 190 |
+
"step": 660
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 23.0,
|
| 194 |
+
"eval_loss": 4.4230475425720215,
|
| 195 |
+
"eval_runtime": 0.0469,
|
| 196 |
+
"eval_samples_per_second": 447.941,
|
| 197 |
+
"eval_steps_per_second": 63.992,
|
| 198 |
+
"step": 690
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 24.0,
|
| 202 |
+
"eval_loss": 4.332743167877197,
|
| 203 |
+
"eval_runtime": 0.0471,
|
| 204 |
+
"eval_samples_per_second": 445.731,
|
| 205 |
+
"eval_steps_per_second": 63.676,
|
| 206 |
+
"step": 720
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 25.0,
|
| 210 |
+
"eval_loss": 4.291798114776611,
|
| 211 |
+
"eval_runtime": 0.0471,
|
| 212 |
+
"eval_samples_per_second": 445.429,
|
| 213 |
+
"eval_steps_per_second": 63.633,
|
| 214 |
+
"step": 750
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 26.0,
|
| 218 |
+
"eval_loss": 4.197042942047119,
|
| 219 |
+
"eval_runtime": 0.0471,
|
| 220 |
+
"eval_samples_per_second": 445.494,
|
| 221 |
+
"eval_steps_per_second": 63.642,
|
| 222 |
+
"step": 780
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 27.0,
|
| 226 |
+
"eval_loss": 4.085911273956299,
|
| 227 |
+
"eval_runtime": 0.047,
|
| 228 |
+
"eval_samples_per_second": 446.664,
|
| 229 |
+
"eval_steps_per_second": 63.809,
|
| 230 |
+
"step": 810
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 28.0,
|
| 234 |
+
"eval_loss": 4.071910858154297,
|
| 235 |
+
"eval_runtime": 0.0471,
|
| 236 |
+
"eval_samples_per_second": 445.733,
|
| 237 |
+
"eval_steps_per_second": 63.676,
|
| 238 |
+
"step": 840
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 29.0,
|
| 242 |
+
"eval_loss": 4.150127410888672,
|
| 243 |
+
"eval_runtime": 0.0471,
|
| 244 |
+
"eval_samples_per_second": 446.266,
|
| 245 |
+
"eval_steps_per_second": 63.752,
|
| 246 |
+
"step": 870
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 30.0,
|
| 250 |
+
"eval_loss": 3.875171184539795,
|
| 251 |
+
"eval_runtime": 0.0469,
|
| 252 |
+
"eval_samples_per_second": 447.781,
|
| 253 |
+
"eval_steps_per_second": 63.969,
|
| 254 |
+
"step": 900
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 31.0,
|
| 258 |
+
"eval_loss": 3.8007264137268066,
|
| 259 |
+
"eval_runtime": 0.047,
|
| 260 |
+
"eval_samples_per_second": 447.009,
|
| 261 |
+
"eval_steps_per_second": 63.858,
|
| 262 |
+
"step": 930
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 32.0,
|
| 266 |
+
"eval_loss": 3.7663497924804688,
|
| 267 |
+
"eval_runtime": 0.047,
|
| 268 |
+
"eval_samples_per_second": 447.099,
|
| 269 |
+
"eval_steps_per_second": 63.871,
|
| 270 |
+
"step": 960
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 33.0,
|
| 274 |
+
"eval_loss": 4.154388427734375,
|
| 275 |
+
"eval_runtime": 0.0471,
|
| 276 |
+
"eval_samples_per_second": 445.803,
|
| 277 |
+
"eval_steps_per_second": 63.686,
|
| 278 |
+
"step": 990
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 33.33,
|
| 282 |
+
"learning_rate": 1.008e-05,
|
| 283 |
+
"loss": 4.123,
|
| 284 |
+
"step": 1000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 34.0,
|
| 288 |
+
"eval_loss": 3.6973140239715576,
|
| 289 |
+
"eval_runtime": 0.0469,
|
| 290 |
+
"eval_samples_per_second": 448.23,
|
| 291 |
+
"eval_steps_per_second": 64.033,
|
| 292 |
+
"step": 1020
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 35.0,
|
| 296 |
+
"eval_loss": 4.152168273925781,
|
| 297 |
+
"eval_runtime": 0.0469,
|
| 298 |
+
"eval_samples_per_second": 448.137,
|
| 299 |
+
"eval_steps_per_second": 64.02,
|
| 300 |
+
"step": 1050
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 36.0,
|
| 304 |
+
"eval_loss": 3.746863603591919,
|
| 305 |
+
"eval_runtime": 0.0473,
|
| 306 |
+
"eval_samples_per_second": 443.569,
|
| 307 |
+
"eval_steps_per_second": 63.367,
|
| 308 |
+
"step": 1080
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 37.0,
|
| 312 |
+
"eval_loss": 3.8012099266052246,
|
| 313 |
+
"eval_runtime": 0.0471,
|
| 314 |
+
"eval_samples_per_second": 446.105,
|
| 315 |
+
"eval_steps_per_second": 63.729,
|
| 316 |
+
"step": 1110
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 38.0,
|
| 320 |
+
"eval_loss": 3.714829683303833,
|
| 321 |
+
"eval_runtime": 0.0469,
|
| 322 |
+
"eval_samples_per_second": 447.308,
|
| 323 |
+
"eval_steps_per_second": 63.901,
|
| 324 |
+
"step": 1140
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 39.0,
|
| 328 |
+
"eval_loss": 3.4752964973449707,
|
| 329 |
+
"eval_runtime": 0.047,
|
| 330 |
+
"eval_samples_per_second": 447.127,
|
| 331 |
+
"eval_steps_per_second": 63.875,
|
| 332 |
+
"step": 1170
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 40.0,
|
| 336 |
+
"eval_loss": 3.982607126235962,
|
| 337 |
+
"eval_runtime": 0.0469,
|
| 338 |
+
"eval_samples_per_second": 447.311,
|
| 339 |
+
"eval_steps_per_second": 63.902,
|
| 340 |
+
"step": 1200
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 41.0,
|
| 344 |
+
"eval_loss": 3.850808620452881,
|
| 345 |
+
"eval_runtime": 0.0469,
|
| 346 |
+
"eval_samples_per_second": 447.856,
|
| 347 |
+
"eval_steps_per_second": 63.979,
|
| 348 |
+
"step": 1230
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 42.0,
|
| 352 |
+
"eval_loss": 4.094546794891357,
|
| 353 |
+
"eval_runtime": 0.0469,
|
| 354 |
+
"eval_samples_per_second": 448.002,
|
| 355 |
+
"eval_steps_per_second": 64.0,
|
| 356 |
+
"step": 1260
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 43.0,
|
| 360 |
+
"eval_loss": 3.4853432178497314,
|
| 361 |
+
"eval_runtime": 0.047,
|
| 362 |
+
"eval_samples_per_second": 446.474,
|
| 363 |
+
"eval_steps_per_second": 63.782,
|
| 364 |
+
"step": 1290
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 44.0,
|
| 368 |
+
"eval_loss": 3.5112228393554688,
|
| 369 |
+
"eval_runtime": 0.0471,
|
| 370 |
+
"eval_samples_per_second": 446.02,
|
| 371 |
+
"eval_steps_per_second": 63.717,
|
| 372 |
+
"step": 1320
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 45.0,
|
| 376 |
+
"eval_loss": 3.7965281009674072,
|
| 377 |
+
"eval_runtime": 0.047,
|
| 378 |
+
"eval_samples_per_second": 446.759,
|
| 379 |
+
"eval_steps_per_second": 63.823,
|
| 380 |
+
"step": 1350
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 46.0,
|
| 384 |
+
"eval_loss": 3.6154186725616455,
|
| 385 |
+
"eval_runtime": 0.0469,
|
| 386 |
+
"eval_samples_per_second": 448.15,
|
| 387 |
+
"eval_steps_per_second": 64.021,
|
| 388 |
+
"step": 1380
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 47.0,
|
| 392 |
+
"eval_loss": 3.5226211547851562,
|
| 393 |
+
"eval_runtime": 0.0468,
|
| 394 |
+
"eval_samples_per_second": 448.964,
|
| 395 |
+
"eval_steps_per_second": 64.138,
|
| 396 |
+
"step": 1410
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 48.0,
|
| 400 |
+
"eval_loss": 3.473081588745117,
|
| 401 |
+
"eval_runtime": 0.0469,
|
| 402 |
+
"eval_samples_per_second": 447.779,
|
| 403 |
+
"eval_steps_per_second": 63.968,
|
| 404 |
+
"step": 1440
|
| 405 |
+
}
|
| 406 |
+
],
|
| 407 |
+
"max_steps": 1500,
|
| 408 |
+
"num_train_epochs": 50,
|
| 409 |
+
"total_flos": 739079114342400.0,
|
| 410 |
+
"trial_name": null,
|
| 411 |
+
"trial_params": null
|
| 412 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40dd68ea8f0b8bcd1331fdf1a55d77b8fc58037adb61d94d3c7ae8746fa19a47
|
| 3 |
+
size 3451
|