Training in progress, step 1400, 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 19669752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37a52e5b67af8b2cc65ab1c1577d5ecccf74a0ddbc9f2f2066049a126d8e409f
|
3 |
size 19669752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39356997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eb0ed09e9a75c4d71f9d8635514ccf20c879abbc6d629a82153441c3a512b63
|
3 |
size 39356997
|
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 sha256:4bea0b80d96d23f3f961d11718afa3bd11f3aaf4fdfcb59d7ee8fe5190f75ff3
|
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:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 1.
|
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,
|
@@ -189,6 +189,20 @@
|
|
189 |
"eval_samples_per_second": 2.45,
|
190 |
"eval_steps_per_second": 0.307,
|
191 |
"step": 1300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 100,
|
@@ -196,7 +210,7 @@
|
|
196 |
"num_input_tokens_seen": 0,
|
197 |
"num_train_epochs": 5,
|
198 |
"save_steps": 100,
|
199 |
-
"total_flos": 3.
|
200 |
"trial_name": null,
|
201 |
"trial_params": null
|
202 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9653750658035278,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1400",
|
4 |
+
"epoch": 1.8666666666666667,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
189 |
"eval_samples_per_second": 2.45,
|
190 |
"eval_steps_per_second": 0.307,
|
191 |
"step": 1300
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.87,
|
195 |
+
"learning_rate": 0.0002,
|
196 |
+
"loss": 0.7971,
|
197 |
+
"step": 1400
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.87,
|
201 |
+
"eval_loss": 0.9653750658035278,
|
202 |
+
"eval_runtime": 777.1907,
|
203 |
+
"eval_samples_per_second": 2.483,
|
204 |
+
"eval_steps_per_second": 0.311,
|
205 |
+
"step": 1400
|
206 |
}
|
207 |
],
|
208 |
"logging_steps": 100,
|
|
|
210 |
"num_input_tokens_seen": 0,
|
211 |
"num_train_epochs": 5,
|
212 |
"save_steps": 100,
|
213 |
+
"total_flos": 3.627481660202189e+17,
|
214 |
"trial_name": null,
|
215 |
"trial_params": null
|
216 |
}
|