Training in progress, step 3800, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 250422888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2aa35fce984e735a636c36b30ee78b534cdcaa8b7905695fa2d3645f4adecce5
|
| 3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 127492797
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1138fa94dec685dccd75130188b34f9d8efa384d0ecf180da905b6189c7e22ee
|
| 3 |
size 127492797
|
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 sha256:9b15ae2201ca03d06a838d717bba4d10584392cecaec5065453d73b67b36d95c
|
| 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 sha256:3961d2f201ce99426ee113655da78d8214f6ef72fc082855daa3c565989888c2
|
| 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":
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -241,13 +241,26 @@
|
|
| 241 |
"eval_samples_per_second": 7.925,
|
| 242 |
"eval_steps_per_second": 0.517,
|
| 243 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 244 |
}
|
| 245 |
],
|
| 246 |
"logging_steps": 200,
|
| 247 |
"max_steps": 3936,
|
| 248 |
"num_train_epochs": 12,
|
| 249 |
"save_steps": 200,
|
| 250 |
-
"total_flos": 1.
|
| 251 |
"trial_name": null,
|
| 252 |
"trial_params": null
|
| 253 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.585365853658537,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 3800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 241 |
"eval_samples_per_second": 7.925,
|
| 242 |
"eval_steps_per_second": 0.517,
|
| 243 |
"step": 3600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 11.59,
|
| 247 |
+
"learning_rate": 0.0002,
|
| 248 |
+
"loss": 0.026,
|
| 249 |
+
"step": 3800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 11.59,
|
| 253 |
+
"eval_runtime": 34.8416,
|
| 254 |
+
"eval_samples_per_second": 7.922,
|
| 255 |
+
"eval_steps_per_second": 0.517,
|
| 256 |
+
"step": 3800
|
| 257 |
}
|
| 258 |
],
|
| 259 |
"logging_steps": 200,
|
| 260 |
"max_steps": 3936,
|
| 261 |
"num_train_epochs": 12,
|
| 262 |
"save_steps": 200,
|
| 263 |
+
"total_flos": 1.2241559754375168e+18,
|
| 264 |
"trial_name": null,
|
| 265 |
"trial_params": null
|
| 266 |
}
|