Training in progress, step 1500, 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 6304192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a9ea19a14ed11592de0c6e2dcae9ced556eddf3c0b0b13211afc010d0f5b9d7
|
3 |
size 6304192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12639429
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d998e0791bba6243f188e62cbf6a59b367f43d52b8d76fc2a22133120e6a110a
|
3 |
size 12639429
|
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:f409da3dcc8d395470a77e66ec88ee64f503054e416b434d299f2eda08c45ccd
|
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:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.250588297843933,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-1400",
|
4 |
-
"epoch":
|
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,
|
@@ -203,6 +203,20 @@
|
|
203 |
"eval_samples_per_second": 15.321,
|
204 |
"eval_steps_per_second": 1.921,
|
205 |
"step": 1400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
}
|
207 |
],
|
208 |
"logging_steps": 100,
|
@@ -210,7 +224,7 @@
|
|
210 |
"num_input_tokens_seen": 0,
|
211 |
"num_train_epochs": 3,
|
212 |
"save_steps": 100,
|
213 |
-
"total_flos":
|
214 |
"trial_name": null,
|
215 |
"trial_params": null
|
216 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.250588297843933,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-1400",
|
4 |
+
"epoch": 2.0,
|
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,
|
|
|
203 |
"eval_samples_per_second": 15.321,
|
204 |
"eval_steps_per_second": 1.921,
|
205 |
"step": 1400
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.0,
|
209 |
+
"learning_rate": 0.0002,
|
210 |
+
"loss": 1.0783,
|
211 |
+
"step": 1500
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 2.0,
|
215 |
+
"eval_loss": 1.2534571886062622,
|
216 |
+
"eval_runtime": 126.2955,
|
217 |
+
"eval_samples_per_second": 15.282,
|
218 |
+
"eval_steps_per_second": 1.916,
|
219 |
+
"step": 1500
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 100,
|
|
|
224 |
"num_input_tokens_seen": 0,
|
225 |
"num_train_epochs": 3,
|
226 |
"save_steps": 100,
|
227 |
+
"total_flos": 5.317568138938368e+16,
|
228 |
"trial_name": null,
|
229 |
"trial_params": null
|
230 |
}
|