Training in progress, step 1500, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 160285149
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d3eb374ac2b1d9eeef085cfee67b2d12a1bbf0c0243df87240a21eb4e66ca8a
|
| 3 |
size 160285149
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17809451b43231344ce0c8cd2e95f6abbd68c7c8935a1e1037fc822911e98eb0
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5702e3359ca8686596887944139c71f5ceb56f3d468613b0807fcb6841ba09c
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -189,13 +189,26 @@
|
|
| 189 |
"eval_samples_per_second": 1.902,
|
| 190 |
"eval_steps_per_second": 0.238,
|
| 191 |
"step": 1400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 192 |
}
|
| 193 |
],
|
| 194 |
"logging_steps": 100,
|
| 195 |
"max_steps": 2025,
|
| 196 |
"num_train_epochs": 3,
|
| 197 |
"save_steps": 100,
|
| 198 |
-
"total_flos":
|
| 199 |
"trial_name": null,
|
| 200 |
"trial_params": null
|
| 201 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.2222222222222223,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 189 |
"eval_samples_per_second": 1.902,
|
| 190 |
"eval_steps_per_second": 0.238,
|
| 191 |
"step": 1400
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.22,
|
| 195 |
+
"learning_rate": 0.0,
|
| 196 |
+
"loss": 8.4733,
|
| 197 |
+
"step": 1500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 2.22,
|
| 201 |
+
"eval_runtime": 787.7569,
|
| 202 |
+
"eval_samples_per_second": 1.904,
|
| 203 |
+
"eval_steps_per_second": 0.239,
|
| 204 |
+
"step": 1500
|
| 205 |
}
|
| 206 |
],
|
| 207 |
"logging_steps": 100,
|
| 208 |
"max_steps": 2025,
|
| 209 |
"num_train_epochs": 3,
|
| 210 |
"save_steps": 100,
|
| 211 |
+
"total_flos": 3.1236059824128e+17,
|
| 212 |
"trial_name": null,
|
| 213 |
"trial_params": null
|
| 214 |
}
|