Training in progress, step 70000
Browse files- config.json +2 -2
- model.safetensors +1 -1
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +553 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"EsmForMaskedLM"
|
| 5 |
],
|
|
@@ -23,7 +23,7 @@
|
|
| 23 |
"position_embedding_type": "rotary",
|
| 24 |
"token_dropout": true,
|
| 25 |
"torch_dtype": "float32",
|
| 26 |
-
"transformers_version": "4.
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_list": null,
|
| 29 |
"vocab_size": 33
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "mgh6/TCS_MLM",
|
| 3 |
"architectures": [
|
| 4 |
"EsmForMaskedLM"
|
| 5 |
],
|
|
|
|
| 23 |
"position_embedding_type": "rotary",
|
| 24 |
"token_dropout": true,
|
| 25 |
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.37.2",
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_list": null,
|
| 29 |
"vocab_size": 33
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 136000488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0ea43ef01adeb69e4ad577380ed31e90c1a5bd0f0619ee9b66bf3bd9e22fff5
|
| 3 |
size 136000488
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d7d8e2181fbd44c975aa71b4db7db47e5e346397a615f83767017f384dda543
|
| 3 |
+
size 268174417
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da25f32745f674c5f578c521f588f79917675eeaf6e0b8dcae003f3745222130
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01ea102be1ec9698bc4ca3c3c653aa98e113cf491e0d96462a950ea007d7260b
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,553 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.6665325513378,
|
| 5 |
+
"eval_steps": 5000,
|
| 6 |
+
"global_step": 70000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"learning_rate": 9.958730551772523e-05,
|
| 14 |
+
"loss": 1.4035,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.25,
|
| 19 |
+
"learning_rate": 9.917461103545046e-05,
|
| 20 |
+
"loss": 1.332,
|
| 21 |
+
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.37,
|
| 25 |
+
"learning_rate": 9.87619165531757e-05,
|
| 26 |
+
"loss": 1.2981,
|
| 27 |
+
"step": 3000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.5,
|
| 31 |
+
"learning_rate": 9.834922207090091e-05,
|
| 32 |
+
"loss": 1.272,
|
| 33 |
+
"step": 4000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.62,
|
| 37 |
+
"learning_rate": 9.793652758862615e-05,
|
| 38 |
+
"loss": 1.2501,
|
| 39 |
+
"step": 5000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.62,
|
| 43 |
+
"eval_loss": 1.1940463781356812,
|
| 44 |
+
"eval_runtime": 120.3265,
|
| 45 |
+
"eval_samples_per_second": 134.692,
|
| 46 |
+
"eval_steps_per_second": 16.838,
|
| 47 |
+
"step": 5000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.74,
|
| 51 |
+
"learning_rate": 9.752383310635137e-05,
|
| 52 |
+
"loss": 1.2328,
|
| 53 |
+
"step": 6000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.87,
|
| 57 |
+
"learning_rate": 9.71111386240766e-05,
|
| 58 |
+
"loss": 1.208,
|
| 59 |
+
"step": 7000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.99,
|
| 63 |
+
"learning_rate": 9.669844414180183e-05,
|
| 64 |
+
"loss": 1.1886,
|
| 65 |
+
"step": 8000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.11,
|
| 69 |
+
"learning_rate": 9.628574965952706e-05,
|
| 70 |
+
"loss": 1.182,
|
| 71 |
+
"step": 9000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.24,
|
| 75 |
+
"learning_rate": 9.587305517725228e-05,
|
| 76 |
+
"loss": 1.1761,
|
| 77 |
+
"step": 10000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.24,
|
| 81 |
+
"eval_loss": 1.1365982294082642,
|
| 82 |
+
"eval_runtime": 124.7536,
|
| 83 |
+
"eval_samples_per_second": 129.912,
|
| 84 |
+
"eval_steps_per_second": 16.24,
|
| 85 |
+
"step": 10000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.36,
|
| 89 |
+
"learning_rate": 9.546036069497752e-05,
|
| 90 |
+
"loss": 1.1594,
|
| 91 |
+
"step": 11000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.49,
|
| 95 |
+
"learning_rate": 9.504766621270275e-05,
|
| 96 |
+
"loss": 1.1449,
|
| 97 |
+
"step": 12000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.61,
|
| 101 |
+
"learning_rate": 9.463497173042796e-05,
|
| 102 |
+
"loss": 1.1387,
|
| 103 |
+
"step": 13000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.73,
|
| 107 |
+
"learning_rate": 9.422227724815321e-05,
|
| 108 |
+
"loss": 1.1318,
|
| 109 |
+
"step": 14000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.86,
|
| 113 |
+
"learning_rate": 9.380958276587842e-05,
|
| 114 |
+
"loss": 1.1222,
|
| 115 |
+
"step": 15000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.86,
|
| 119 |
+
"eval_loss": 1.103798270225525,
|
| 120 |
+
"eval_runtime": 119.9985,
|
| 121 |
+
"eval_samples_per_second": 135.06,
|
| 122 |
+
"eval_steps_per_second": 16.884,
|
| 123 |
+
"step": 15000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.98,
|
| 127 |
+
"learning_rate": 9.339688828360365e-05,
|
| 128 |
+
"loss": 1.1164,
|
| 129 |
+
"step": 16000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.1,
|
| 133 |
+
"learning_rate": 9.298419380132888e-05,
|
| 134 |
+
"loss": 1.1073,
|
| 135 |
+
"step": 17000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.23,
|
| 139 |
+
"learning_rate": 9.257149931905411e-05,
|
| 140 |
+
"loss": 1.1026,
|
| 141 |
+
"step": 18000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.35,
|
| 145 |
+
"learning_rate": 9.215880483677933e-05,
|
| 146 |
+
"loss": 1.0957,
|
| 147 |
+
"step": 19000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.48,
|
| 151 |
+
"learning_rate": 9.174611035450457e-05,
|
| 152 |
+
"loss": 1.0859,
|
| 153 |
+
"step": 20000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.48,
|
| 157 |
+
"eval_loss": 1.0691076517105103,
|
| 158 |
+
"eval_runtime": 120.0736,
|
| 159 |
+
"eval_samples_per_second": 134.976,
|
| 160 |
+
"eval_steps_per_second": 16.873,
|
| 161 |
+
"step": 20000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.6,
|
| 165 |
+
"learning_rate": 9.133341587222979e-05,
|
| 166 |
+
"loss": 1.0856,
|
| 167 |
+
"step": 21000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.72,
|
| 171 |
+
"learning_rate": 9.092072138995502e-05,
|
| 172 |
+
"loss": 1.0769,
|
| 173 |
+
"step": 22000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.85,
|
| 177 |
+
"learning_rate": 9.050802690768025e-05,
|
| 178 |
+
"loss": 1.0768,
|
| 179 |
+
"step": 23000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.97,
|
| 183 |
+
"learning_rate": 9.009533242540548e-05,
|
| 184 |
+
"loss": 1.0671,
|
| 185 |
+
"step": 24000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.09,
|
| 189 |
+
"learning_rate": 8.968263794313071e-05,
|
| 190 |
+
"loss": 1.0703,
|
| 191 |
+
"step": 25000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.09,
|
| 195 |
+
"eval_loss": 1.0342341661453247,
|
| 196 |
+
"eval_runtime": 142.3338,
|
| 197 |
+
"eval_samples_per_second": 113.866,
|
| 198 |
+
"eval_steps_per_second": 14.234,
|
| 199 |
+
"step": 25000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.22,
|
| 203 |
+
"learning_rate": 8.926994346085594e-05,
|
| 204 |
+
"loss": 1.0535,
|
| 205 |
+
"step": 26000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 3.34,
|
| 209 |
+
"learning_rate": 8.885724897858117e-05,
|
| 210 |
+
"loss": 1.0537,
|
| 211 |
+
"step": 27000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.47,
|
| 215 |
+
"learning_rate": 8.844455449630638e-05,
|
| 216 |
+
"loss": 1.0502,
|
| 217 |
+
"step": 28000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 3.59,
|
| 221 |
+
"learning_rate": 8.803186001403163e-05,
|
| 222 |
+
"loss": 1.0401,
|
| 223 |
+
"step": 29000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 3.71,
|
| 227 |
+
"learning_rate": 8.761916553175684e-05,
|
| 228 |
+
"loss": 1.0461,
|
| 229 |
+
"step": 30000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 3.71,
|
| 233 |
+
"eval_loss": 1.0171171426773071,
|
| 234 |
+
"eval_runtime": 155.2187,
|
| 235 |
+
"eval_samples_per_second": 104.414,
|
| 236 |
+
"eval_steps_per_second": 13.053,
|
| 237 |
+
"step": 30000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 3.84,
|
| 241 |
+
"learning_rate": 8.720647104948207e-05,
|
| 242 |
+
"loss": 1.0362,
|
| 243 |
+
"step": 31000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.96,
|
| 247 |
+
"learning_rate": 8.67937765672073e-05,
|
| 248 |
+
"loss": 1.0332,
|
| 249 |
+
"step": 32000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.09,
|
| 253 |
+
"learning_rate": 8.638108208493253e-05,
|
| 254 |
+
"loss": 1.0293,
|
| 255 |
+
"step": 33000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.21,
|
| 259 |
+
"learning_rate": 8.596838760265775e-05,
|
| 260 |
+
"loss": 1.0286,
|
| 261 |
+
"step": 34000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.33,
|
| 265 |
+
"learning_rate": 8.555569312038299e-05,
|
| 266 |
+
"loss": 1.025,
|
| 267 |
+
"step": 35000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.33,
|
| 271 |
+
"eval_loss": 0.9936763048171997,
|
| 272 |
+
"eval_runtime": 119.72,
|
| 273 |
+
"eval_samples_per_second": 135.374,
|
| 274 |
+
"eval_steps_per_second": 16.923,
|
| 275 |
+
"step": 35000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 4.46,
|
| 279 |
+
"learning_rate": 8.514299863810822e-05,
|
| 280 |
+
"loss": 1.0184,
|
| 281 |
+
"step": 36000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 4.58,
|
| 285 |
+
"learning_rate": 8.473030415583344e-05,
|
| 286 |
+
"loss": 1.0136,
|
| 287 |
+
"step": 37000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 4.7,
|
| 291 |
+
"learning_rate": 8.431760967355867e-05,
|
| 292 |
+
"loss": 1.0103,
|
| 293 |
+
"step": 38000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 4.83,
|
| 297 |
+
"learning_rate": 8.39049151912839e-05,
|
| 298 |
+
"loss": 1.0081,
|
| 299 |
+
"step": 39000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 4.95,
|
| 303 |
+
"learning_rate": 8.349222070900913e-05,
|
| 304 |
+
"loss": 1.0063,
|
| 305 |
+
"step": 40000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.95,
|
| 309 |
+
"eval_loss": 0.9914126396179199,
|
| 310 |
+
"eval_runtime": 176.7148,
|
| 311 |
+
"eval_samples_per_second": 91.713,
|
| 312 |
+
"eval_steps_per_second": 11.465,
|
| 313 |
+
"step": 40000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 5.08,
|
| 317 |
+
"learning_rate": 8.307952622673436e-05,
|
| 318 |
+
"loss": 1.003,
|
| 319 |
+
"step": 41000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 5.2,
|
| 323 |
+
"learning_rate": 8.266683174445959e-05,
|
| 324 |
+
"loss": 0.9947,
|
| 325 |
+
"step": 42000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 5.32,
|
| 329 |
+
"learning_rate": 8.22541372621848e-05,
|
| 330 |
+
"loss": 0.999,
|
| 331 |
+
"step": 43000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 5.45,
|
| 335 |
+
"learning_rate": 8.184144277991003e-05,
|
| 336 |
+
"loss": 0.9987,
|
| 337 |
+
"step": 44000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 5.57,
|
| 341 |
+
"learning_rate": 8.142874829763526e-05,
|
| 342 |
+
"loss": 0.988,
|
| 343 |
+
"step": 45000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 5.57,
|
| 347 |
+
"eval_loss": 0.9876496195793152,
|
| 348 |
+
"eval_runtime": 149.4553,
|
| 349 |
+
"eval_samples_per_second": 108.44,
|
| 350 |
+
"eval_steps_per_second": 13.556,
|
| 351 |
+
"step": 45000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 5.69,
|
| 355 |
+
"learning_rate": 8.101605381536049e-05,
|
| 356 |
+
"loss": 0.9899,
|
| 357 |
+
"step": 46000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 5.82,
|
| 361 |
+
"learning_rate": 8.060335933308572e-05,
|
| 362 |
+
"loss": 0.9876,
|
| 363 |
+
"step": 47000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 5.94,
|
| 367 |
+
"learning_rate": 8.019066485081095e-05,
|
| 368 |
+
"loss": 0.9889,
|
| 369 |
+
"step": 48000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 6.07,
|
| 373 |
+
"learning_rate": 7.977797036853618e-05,
|
| 374 |
+
"loss": 0.9807,
|
| 375 |
+
"step": 49000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 6.19,
|
| 379 |
+
"learning_rate": 7.93652758862614e-05,
|
| 380 |
+
"loss": 0.971,
|
| 381 |
+
"step": 50000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 6.19,
|
| 385 |
+
"eval_loss": 0.9691153764724731,
|
| 386 |
+
"eval_runtime": 155.3931,
|
| 387 |
+
"eval_samples_per_second": 104.297,
|
| 388 |
+
"eval_steps_per_second": 13.038,
|
| 389 |
+
"step": 50000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 6.31,
|
| 393 |
+
"learning_rate": 7.895258140398664e-05,
|
| 394 |
+
"loss": 0.9796,
|
| 395 |
+
"step": 51000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 6.44,
|
| 399 |
+
"learning_rate": 7.853988692171186e-05,
|
| 400 |
+
"loss": 0.9784,
|
| 401 |
+
"step": 52000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 6.56,
|
| 405 |
+
"learning_rate": 7.812719243943709e-05,
|
| 406 |
+
"loss": 0.9682,
|
| 407 |
+
"step": 53000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 6.69,
|
| 411 |
+
"learning_rate": 7.771449795716232e-05,
|
| 412 |
+
"loss": 0.9609,
|
| 413 |
+
"step": 54000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 6.81,
|
| 417 |
+
"learning_rate": 7.730180347488755e-05,
|
| 418 |
+
"loss": 0.9704,
|
| 419 |
+
"step": 55000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 6.81,
|
| 423 |
+
"eval_loss": 0.9535136222839355,
|
| 424 |
+
"eval_runtime": 160.7447,
|
| 425 |
+
"eval_samples_per_second": 100.824,
|
| 426 |
+
"eval_steps_per_second": 12.604,
|
| 427 |
+
"step": 55000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 6.93,
|
| 431 |
+
"learning_rate": 7.688910899261278e-05,
|
| 432 |
+
"loss": 0.965,
|
| 433 |
+
"step": 56000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 7.06,
|
| 437 |
+
"learning_rate": 7.6476414510338e-05,
|
| 438 |
+
"loss": 0.9574,
|
| 439 |
+
"step": 57000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 7.18,
|
| 443 |
+
"learning_rate": 7.606372002806322e-05,
|
| 444 |
+
"loss": 0.9565,
|
| 445 |
+
"step": 58000
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 7.3,
|
| 449 |
+
"learning_rate": 7.565102554578845e-05,
|
| 450 |
+
"loss": 0.9514,
|
| 451 |
+
"step": 59000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 7.43,
|
| 455 |
+
"learning_rate": 7.52383310635137e-05,
|
| 456 |
+
"loss": 0.951,
|
| 457 |
+
"step": 60000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 7.43,
|
| 461 |
+
"eval_loss": 0.9359220266342163,
|
| 462 |
+
"eval_runtime": 124.2464,
|
| 463 |
+
"eval_samples_per_second": 130.442,
|
| 464 |
+
"eval_steps_per_second": 16.306,
|
| 465 |
+
"step": 60000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 7.55,
|
| 469 |
+
"learning_rate": 7.482563658123891e-05,
|
| 470 |
+
"loss": 0.9477,
|
| 471 |
+
"step": 61000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 7.68,
|
| 475 |
+
"learning_rate": 7.441294209896414e-05,
|
| 476 |
+
"loss": 0.9581,
|
| 477 |
+
"step": 62000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 7.8,
|
| 481 |
+
"learning_rate": 7.400024761668937e-05,
|
| 482 |
+
"loss": 0.948,
|
| 483 |
+
"step": 63000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 7.92,
|
| 487 |
+
"learning_rate": 7.35875531344146e-05,
|
| 488 |
+
"loss": 0.9439,
|
| 489 |
+
"step": 64000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 8.05,
|
| 493 |
+
"learning_rate": 7.317485865213982e-05,
|
| 494 |
+
"loss": 0.9447,
|
| 495 |
+
"step": 65000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 8.05,
|
| 499 |
+
"eval_loss": 0.9360346794128418,
|
| 500 |
+
"eval_runtime": 160.0152,
|
| 501 |
+
"eval_samples_per_second": 101.284,
|
| 502 |
+
"eval_steps_per_second": 12.661,
|
| 503 |
+
"step": 65000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 8.17,
|
| 507 |
+
"learning_rate": 7.276216416986506e-05,
|
| 508 |
+
"loss": 0.9377,
|
| 509 |
+
"step": 66000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 8.29,
|
| 513 |
+
"learning_rate": 7.234946968759027e-05,
|
| 514 |
+
"loss": 0.9455,
|
| 515 |
+
"step": 67000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 8.42,
|
| 519 |
+
"learning_rate": 7.19367752053155e-05,
|
| 520 |
+
"loss": 0.9332,
|
| 521 |
+
"step": 68000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 8.54,
|
| 525 |
+
"learning_rate": 7.152408072304073e-05,
|
| 526 |
+
"loss": 0.9374,
|
| 527 |
+
"step": 69000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 8.67,
|
| 531 |
+
"learning_rate": 7.111138624076596e-05,
|
| 532 |
+
"loss": 0.9512,
|
| 533 |
+
"step": 70000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 8.67,
|
| 537 |
+
"eval_loss": 0.930946946144104,
|
| 538 |
+
"eval_runtime": 132.6824,
|
| 539 |
+
"eval_samples_per_second": 122.149,
|
| 540 |
+
"eval_steps_per_second": 15.27,
|
| 541 |
+
"step": 70000
|
| 542 |
+
}
|
| 543 |
+
],
|
| 544 |
+
"logging_steps": 1000,
|
| 545 |
+
"max_steps": 242310,
|
| 546 |
+
"num_input_tokens_seen": 0,
|
| 547 |
+
"num_train_epochs": 30,
|
| 548 |
+
"save_steps": 500,
|
| 549 |
+
"total_flos": 3.5013441751675136e+17,
|
| 550 |
+
"train_batch_size": 8,
|
| 551 |
+
"trial_name": null,
|
| 552 |
+
"trial_params": null
|
| 553 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4207
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16c7088a420614f10c4caeee3a98e60e4ba453f05edd647671fd07146b95e23d
|
| 3 |
size 4207
|