Upload 19 files
Browse files- latest +1 -1
- rng_state_0.pth +1 -1
- rng_state_1.pth +1 -1
- rng_state_2.pth +1 -1
- rng_state_3.pth +1 -1
- rng_state_4.pth +1 -1
- rng_state_5.pth +1 -1
- rng_state_6.pth +1 -1
- rng_state_7.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +344 -116
- training_args.bin +1 -1
latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step150
|
rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36d2a2034ebb05cb71c510897f2795b31164e50f17b270bc25d2be3ad9a17b22
|
| 3 |
size 15984
|
rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:060dfdb1c49102cbdc8868a6031e68787601b4ccd782f3fb9b137e20c1fd2c7a
|
| 3 |
size 15984
|
rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af01895cb66e616591f2e4baa8dcd8151530eab133c73571ccb31c74f35422ce
|
| 3 |
size 15984
|
rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:677921992b1e0cef3aee776f245975003d22f51d9bd6ed20f248ded1deb72fa9
|
| 3 |
size 15984
|
rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d69353c629541c690c5471f8ec05fdab2bfecf3d37afaa436bc45939da6db68f
|
| 3 |
size 15984
|
rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e40ba6668cc03c9162c68a933d164bf38ae2d196a9a6fec03ae615491201185
|
| 3 |
size 15984
|
rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:870968fea834e24b2e099cf3e4fe1e3fb8caf38d8f8e5b790d7d47386d4d05f5
|
| 3 |
size 15984
|
rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9e19618bee7c6ef43256fea25abe19bca88535eb1e7dc213cde8929ae4e8180
|
| 3 |
size 15984
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44a49855ec88358e7941539b062fd65978349a22019f83b36fff75496bcf2d6a
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,242 +1,470 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"learning_rate": 4.
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 4.
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 4.
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 4.
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 4.
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 4.
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 4.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 4.
|
| 56 |
-
"loss": 0.
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 4.
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 4.
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 4.
|
| 74 |
-
"loss": 0.
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 4.
|
| 80 |
-
"loss": 0.
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 4.
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 4.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate": 4.
|
| 98 |
-
"loss": 0.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"learning_rate": 4.
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"learning_rate": 4.
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
-
"learning_rate": 4.
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 1.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 1.
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss": 0.
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 1.
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 1.
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 1.
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 1.
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 1.
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 1.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 1.
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 1.
|
| 187 |
-
"learning_rate":
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 1.
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 74
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 232 |
}
|
| 233 |
],
|
| 234 |
"logging_steps": 2,
|
| 235 |
-
"max_steps":
|
| 236 |
"num_input_tokens_seen": 0,
|
| 237 |
-
"num_train_epochs":
|
| 238 |
"save_steps": 25,
|
| 239 |
-
"total_flos":
|
| 240 |
"train_batch_size": 2,
|
| 241 |
"trial_name": null,
|
| 242 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.7267080745341614,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 4.998766400914329e-05,
|
| 14 |
+
"loss": 0.6951,
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 4.995066821070679e-05,
|
| 20 |
+
"loss": 0.5589,
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 4.9889049115077005e-05,
|
| 26 |
+
"loss": 0.5485,
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.2,
|
| 31 |
+
"learning_rate": 4.980286753286195e-05,
|
| 32 |
+
"loss": 0.5392,
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.25,
|
| 37 |
+
"learning_rate": 4.9692208514878444e-05,
|
| 38 |
+
"loss": 0.5347,
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.3,
|
| 43 |
+
"learning_rate": 4.9557181268217227e-05,
|
| 44 |
+
"loss": 0.5261,
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.35,
|
| 49 |
+
"learning_rate": 4.939791904846869e-05,
|
| 50 |
+
"loss": 0.5298,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"learning_rate": 4.9214579028215776e-05,
|
| 56 |
+
"loss": 0.536,
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.45,
|
| 61 |
+
"learning_rate": 4.900734214192358e-05,
|
| 62 |
+
"loss": 0.5012,
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.5,
|
| 67 |
+
"learning_rate": 4.877641290737884e-05,
|
| 68 |
+
"loss": 0.5342,
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.55,
|
| 73 |
+
"learning_rate": 4.852201922385564e-05,
|
| 74 |
+
"loss": 0.5324,
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.6,
|
| 79 |
+
"learning_rate": 4.8244412147206284e-05,
|
| 80 |
+
"loss": 0.4863,
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.65,
|
| 85 |
+
"learning_rate": 4.794386564209953e-05,
|
| 86 |
+
"loss": 0.4774,
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.7,
|
| 91 |
+
"learning_rate": 4.762067631165049e-05,
|
| 92 |
+
"loss": 0.4957,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.75,
|
| 97 |
+
"learning_rate": 4.72751631047092e-05,
|
| 98 |
+
"loss": 0.4531,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.8,
|
| 103 |
+
"learning_rate": 4.72751631047092e-05,
|
| 104 |
+
"loss": 0.5678,
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.84,
|
| 109 |
+
"learning_rate": 4.72751631047092e-05,
|
| 110 |
+
"loss": 0.5456,
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.89,
|
| 115 |
+
"learning_rate": 4.690766700109659e-05,
|
| 116 |
+
"loss": 0.541,
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.94,
|
| 121 |
+
"learning_rate": 4.65185506750986e-05,
|
| 122 |
+
"loss": 0.5035,
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.99,
|
| 127 |
+
"learning_rate": 4.610819813755038e-05,
|
| 128 |
+
"loss": 0.4901,
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 1.04,
|
| 133 |
+
"learning_rate": 4.567701435686404e-05,
|
| 134 |
+
"loss": 0.3193,
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 1.09,
|
| 139 |
+
"learning_rate": 4.522542485937369e-05,
|
| 140 |
+
"loss": 0.3019,
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 1.14,
|
| 145 |
+
"learning_rate": 4.4753875309392266e-05,
|
| 146 |
+
"loss": 0.2869,
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 1.19,
|
| 151 |
+
"learning_rate": 4.426283106939474e-05,
|
| 152 |
+
"loss": 0.2998,
|
| 153 |
"step": 48
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 1.24,
|
| 157 |
+
"learning_rate": 4.375277674076149e-05,
|
| 158 |
+
"loss": 0.2784,
|
| 159 |
"step": 50
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 1.29,
|
| 163 |
+
"learning_rate": 4.3224215685535294e-05,
|
| 164 |
+
"loss": 0.3551,
|
| 165 |
"step": 52
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 1.34,
|
| 169 |
+
"learning_rate": 4.267766952966369e-05,
|
| 170 |
+
"loss": 0.3224,
|
| 171 |
"step": 54
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 1.39,
|
| 175 |
+
"learning_rate": 4.211367764821722e-05,
|
| 176 |
+
"loss": 0.2901,
|
| 177 |
"step": 56
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 1.44,
|
| 181 |
+
"learning_rate": 4.1532796633091296e-05,
|
| 182 |
+
"loss": 0.2776,
|
| 183 |
"step": 58
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 1.49,
|
| 187 |
+
"learning_rate": 4.093559974371725e-05,
|
| 188 |
+
"loss": 0.2993,
|
| 189 |
"step": 60
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 1.54,
|
| 193 |
+
"learning_rate": 4.0322676341324415e-05,
|
| 194 |
+
"loss": 0.2978,
|
| 195 |
"step": 62
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 1.59,
|
| 199 |
+
"learning_rate": 3.969463130731183e-05,
|
| 200 |
+
"loss": 0.2895,
|
| 201 |
"step": 64
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 1.64,
|
| 205 |
+
"learning_rate": 3.905208444630327e-05,
|
| 206 |
+
"loss": 0.3016,
|
| 207 |
"step": 66
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 1.69,
|
| 211 |
+
"learning_rate": 3.8395669874474915e-05,
|
| 212 |
+
"loss": 0.2613,
|
| 213 |
"step": 68
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 1.74,
|
| 217 |
+
"learning_rate": 3.7726035393759285e-05,
|
| 218 |
+
"loss": 0.2993,
|
| 219 |
"step": 70
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 1.79,
|
| 223 |
+
"learning_rate": 3.704384185254288e-05,
|
| 224 |
+
"loss": 0.2853,
|
| 225 |
"step": 72
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 1.84,
|
| 229 |
+
"learning_rate": 3.634976249348867e-05,
|
| 230 |
+
"loss": 0.2578,
|
| 231 |
"step": 74
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.89,
|
| 235 |
+
"learning_rate": 3.564448228912682e-05,
|
| 236 |
+
"loss": 0.2845,
|
| 237 |
+
"step": 76
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.94,
|
| 241 |
+
"learning_rate": 3.4928697265869515e-05,
|
| 242 |
+
"loss": 0.2931,
|
| 243 |
+
"step": 78
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.99,
|
| 247 |
+
"learning_rate": 3.4203113817116957e-05,
|
| 248 |
+
"loss": 0.3093,
|
| 249 |
+
"step": 80
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.04,
|
| 253 |
+
"learning_rate": 3.346844800613229e-05,
|
| 254 |
+
"loss": 0.1741,
|
| 255 |
+
"step": 82
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.09,
|
| 259 |
+
"learning_rate": 3.272542485937369e-05,
|
| 260 |
+
"loss": 0.1583,
|
| 261 |
+
"step": 84
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.14,
|
| 265 |
+
"learning_rate": 3.1974777650980735e-05,
|
| 266 |
+
"loss": 0.135,
|
| 267 |
+
"step": 86
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.19,
|
| 271 |
+
"learning_rate": 3.121724717912138e-05,
|
| 272 |
+
"loss": 0.1423,
|
| 273 |
+
"step": 88
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.24,
|
| 277 |
+
"learning_rate": 3.045358103491357e-05,
|
| 278 |
+
"loss": 0.1372,
|
| 279 |
+
"step": 90
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.29,
|
| 283 |
+
"learning_rate": 2.9684532864643122e-05,
|
| 284 |
+
"loss": 0.1249,
|
| 285 |
+
"step": 92
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.34,
|
| 289 |
+
"learning_rate": 2.8910861626005776e-05,
|
| 290 |
+
"loss": 0.1222,
|
| 291 |
+
"step": 94
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.39,
|
| 295 |
+
"learning_rate": 2.8133330839107608e-05,
|
| 296 |
+
"loss": 0.1607,
|
| 297 |
+
"step": 96
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.43,
|
| 301 |
+
"learning_rate": 2.7352707832962865e-05,
|
| 302 |
+
"loss": 0.1427,
|
| 303 |
+
"step": 98
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.48,
|
| 307 |
+
"learning_rate": 2.656976298823284e-05,
|
| 308 |
+
"loss": 0.12,
|
| 309 |
+
"step": 100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.53,
|
| 313 |
+
"learning_rate": 2.578526897695321e-05,
|
| 314 |
+
"loss": 0.1309,
|
| 315 |
+
"step": 102
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.58,
|
| 319 |
+
"learning_rate": 2.5e-05,
|
| 320 |
+
"loss": 0.1332,
|
| 321 |
+
"step": 104
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.63,
|
| 325 |
+
"learning_rate": 2.4214731023046793e-05,
|
| 326 |
+
"loss": 0.1256,
|
| 327 |
+
"step": 106
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.68,
|
| 331 |
+
"learning_rate": 2.3430237011767167e-05,
|
| 332 |
+
"loss": 0.1258,
|
| 333 |
+
"step": 108
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.73,
|
| 337 |
+
"learning_rate": 2.2647292167037144e-05,
|
| 338 |
+
"loss": 0.1498,
|
| 339 |
+
"step": 110
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.78,
|
| 343 |
+
"learning_rate": 2.186666916089239e-05,
|
| 344 |
+
"loss": 0.1417,
|
| 345 |
+
"step": 112
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.83,
|
| 349 |
+
"learning_rate": 2.1089138373994223e-05,
|
| 350 |
+
"loss": 0.1287,
|
| 351 |
+
"step": 114
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.88,
|
| 355 |
+
"learning_rate": 2.031546713535688e-05,
|
| 356 |
+
"loss": 0.1152,
|
| 357 |
+
"step": 116
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.93,
|
| 361 |
+
"learning_rate": 1.9546418965086442e-05,
|
| 362 |
+
"loss": 0.1352,
|
| 363 |
+
"step": 118
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.98,
|
| 367 |
+
"learning_rate": 1.8782752820878634e-05,
|
| 368 |
+
"loss": 0.1149,
|
| 369 |
+
"step": 120
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.03,
|
| 373 |
+
"learning_rate": 1.802522234901927e-05,
|
| 374 |
+
"loss": 0.0871,
|
| 375 |
+
"step": 122
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.08,
|
| 379 |
+
"learning_rate": 1.7274575140626318e-05,
|
| 380 |
+
"loss": 0.0679,
|
| 381 |
+
"step": 124
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.13,
|
| 385 |
+
"learning_rate": 1.6531551993867717e-05,
|
| 386 |
+
"loss": 0.0616,
|
| 387 |
+
"step": 126
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.18,
|
| 391 |
+
"learning_rate": 1.5796886182883053e-05,
|
| 392 |
+
"loss": 0.0677,
|
| 393 |
+
"step": 128
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.23,
|
| 397 |
+
"learning_rate": 1.5071302734130489e-05,
|
| 398 |
+
"loss": 0.0636,
|
| 399 |
+
"step": 130
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.28,
|
| 403 |
+
"learning_rate": 1.4355517710873184e-05,
|
| 404 |
+
"loss": 0.0612,
|
| 405 |
+
"step": 132
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.33,
|
| 409 |
+
"learning_rate": 1.3650237506511331e-05,
|
| 410 |
+
"loss": 0.0574,
|
| 411 |
+
"step": 134
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.38,
|
| 415 |
+
"learning_rate": 1.2956158147457115e-05,
|
| 416 |
+
"loss": 0.0467,
|
| 417 |
+
"step": 136
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.43,
|
| 421 |
+
"learning_rate": 1.2273964606240718e-05,
|
| 422 |
+
"loss": 0.0611,
|
| 423 |
+
"step": 138
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.48,
|
| 427 |
+
"learning_rate": 1.1604330125525079e-05,
|
| 428 |
+
"loss": 0.0655,
|
| 429 |
+
"step": 140
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.53,
|
| 433 |
+
"learning_rate": 1.0947915553696742e-05,
|
| 434 |
+
"loss": 0.069,
|
| 435 |
+
"step": 142
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.58,
|
| 439 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 440 |
+
"loss": 0.0573,
|
| 441 |
+
"step": 144
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.63,
|
| 445 |
+
"learning_rate": 9.677323658675594e-06,
|
| 446 |
+
"loss": 0.047,
|
| 447 |
+
"step": 146
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.68,
|
| 451 |
+
"learning_rate": 9.064400256282757e-06,
|
| 452 |
+
"loss": 0.0443,
|
| 453 |
+
"step": 148
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.73,
|
| 457 |
+
"learning_rate": 8.467203366908707e-06,
|
| 458 |
+
"loss": 0.0595,
|
| 459 |
+
"step": 150
|
| 460 |
}
|
| 461 |
],
|
| 462 |
"logging_steps": 2,
|
| 463 |
+
"max_steps": 200,
|
| 464 |
"num_input_tokens_seen": 0,
|
| 465 |
+
"num_train_epochs": 5,
|
| 466 |
"save_steps": 25,
|
| 467 |
+
"total_flos": 2.021958544038822e+18,
|
| 468 |
"train_batch_size": 2,
|
| 469 |
"trial_name": null,
|
| 470 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e415afc0b50add77b8846469d4cfb306165074885c031319c567f8683ac3f319
|
| 3 |
size 6136
|