Training in progress, step 1800, 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 12595704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:232b1f56f6ebf344f5c012b7b3e9af10382c003ca7cd01523fe1aaba0c988ec7
|
3 |
size 12595704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25222341
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aef14976ac039f712ae953d0ffd5bca65180c1336d98f5b5fb0d60faf6ff01c
|
3 |
size 25222341
|
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:b0ed68540abf53877f31d72dfb49b5e75b15e4cc70f9158d4c016264864ea60a
|
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:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.0762122869491577,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-1700",
|
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,
|
@@ -245,6 +245,20 @@
|
|
245 |
"eval_samples_per_second": 9.412,
|
246 |
"eval_steps_per_second": 1.18,
|
247 |
"step": 1700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
248 |
}
|
249 |
],
|
250 |
"logging_steps": 100,
|
@@ -252,7 +266,7 @@
|
|
252 |
"num_input_tokens_seen": 0,
|
253 |
"num_train_epochs": 3,
|
254 |
"save_steps": 100,
|
255 |
-
"total_flos": 2.
|
256 |
"trial_name": null,
|
257 |
"trial_params": null
|
258 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.0762122869491577,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-1700",
|
4 |
+
"epoch": 2.4,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
245 |
"eval_samples_per_second": 9.412,
|
246 |
"eval_steps_per_second": 1.18,
|
247 |
"step": 1700
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.4,
|
251 |
+
"learning_rate": 0.0002,
|
252 |
+
"loss": 0.9245,
|
253 |
+
"step": 1800
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 2.4,
|
257 |
+
"eval_loss": 1.077301263809204,
|
258 |
+
"eval_runtime": 356.8145,
|
259 |
+
"eval_samples_per_second": 5.409,
|
260 |
+
"eval_steps_per_second": 0.678,
|
261 |
+
"step": 1800
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 100,
|
|
|
266 |
"num_input_tokens_seen": 0,
|
267 |
"num_train_epochs": 3,
|
268 |
"save_steps": 100,
|
269 |
+
"total_flos": 2.545114966391931e+17,
|
270 |
"trial_name": null,
|
271 |
"trial_params": null
|
272 |
}
|