Training in progress, step 600, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1636004224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c56bfdeb81809f419aa484cec539363ae0b419e40db38c037c709b38c7deb05
|
| 3 |
size 1636004224
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2667211
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d35814f7dc97f1df236a0d1629a47b14255f9648b37166f383d0d4e6aaa50c7
|
| 3 |
size 2667211
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb7fde5111803012042c93a73aa191336bb6e10b3ad44f6bd1d94fc7008a22b6
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57e8133166841d0f76ada9c480c98275cc56e4fa980fc766a81c78f6f8ca609d
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -120,6 +120,62 @@
|
|
| 120 |
"learning_rate": 5.383928571428571e-05,
|
| 121 |
"loss": 3.9649624633789062,
|
| 122 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
}
|
| 124 |
],
|
| 125 |
"logging_steps": 25,
|
|
@@ -134,12 +190,12 @@
|
|
| 134 |
"should_evaluate": false,
|
| 135 |
"should_log": false,
|
| 136 |
"should_save": true,
|
| 137 |
-
"should_training_stop":
|
| 138 |
},
|
| 139 |
"attributes": {}
|
| 140 |
}
|
| 141 |
},
|
| 142 |
-
"total_flos":
|
| 143 |
"train_batch_size": 4,
|
| 144 |
"trial_name": null,
|
| 145 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0409381663113004,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 120 |
"learning_rate": 5.383928571428571e-05,
|
| 121 |
"loss": 3.9649624633789062,
|
| 122 |
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.446908315565032,
|
| 126 |
+
"grad_norm": 0.45619258284568787,
|
| 127 |
+
"learning_rate": 4.7142857142857136e-05,
|
| 128 |
+
"loss": 3.946517028808594,
|
| 129 |
+
"step": 425
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.5321961620469082,
|
| 133 |
+
"grad_norm": 0.45738720893859863,
|
| 134 |
+
"learning_rate": 4.044642857142857e-05,
|
| 135 |
+
"loss": 3.9221026611328127,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.6174840085287845,
|
| 140 |
+
"grad_norm": 0.4545121192932129,
|
| 141 |
+
"learning_rate": 3.375e-05,
|
| 142 |
+
"loss": 3.907404479980469,
|
| 143 |
+
"step": 475
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.702771855010661,
|
| 147 |
+
"grad_norm": 0.458916574716568,
|
| 148 |
+
"learning_rate": 2.7053571428571426e-05,
|
| 149 |
+
"loss": 3.874950256347656,
|
| 150 |
+
"step": 500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.7880597014925375,
|
| 154 |
+
"grad_norm": 0.48818081617355347,
|
| 155 |
+
"learning_rate": 2.0357142857142855e-05,
|
| 156 |
+
"loss": 3.8785760498046873,
|
| 157 |
+
"step": 525
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.8733475479744137,
|
| 161 |
+
"grad_norm": 0.4515751898288727,
|
| 162 |
+
"learning_rate": 1.3660714285714284e-05,
|
| 163 |
+
"loss": 3.8657327270507813,
|
| 164 |
+
"step": 550
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.95863539445629,
|
| 168 |
+
"grad_norm": 0.45125558972358704,
|
| 169 |
+
"learning_rate": 6.9642857142857136e-06,
|
| 170 |
+
"loss": 3.8602328491210938,
|
| 171 |
+
"step": 575
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.0409381663113004,
|
| 175 |
+
"grad_norm": 0.4686155915260315,
|
| 176 |
+
"learning_rate": 2.6785714285714284e-07,
|
| 177 |
+
"loss": 3.7586907958984375,
|
| 178 |
+
"step": 600
|
| 179 |
}
|
| 180 |
],
|
| 181 |
"logging_steps": 25,
|
|
|
|
| 190 |
"should_evaluate": false,
|
| 191 |
"should_log": false,
|
| 192 |
"should_save": true,
|
| 193 |
+
"should_training_stop": true
|
| 194 |
},
|
| 195 |
"attributes": {}
|
| 196 |
}
|
| 197 |
},
|
| 198 |
+
"total_flos": 7.896972537470362e+16,
|
| 199 |
"train_batch_size": 4,
|
| 200 |
"trial_name": null,
|
| 201 |
"trial_params": null
|