Commit
•
7835177
1
Parent(s):
2496567
Training in progress, step 8400, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68399e5c313a915751634cf5ffae9ace9416e38938d0103a268d1d11dce06274
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4548ac75442441bb1d5da3687ffb1363df171933d0e50d8f215a23de567a8a6b
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d48374e1e6b1447bbeee1d70f64941ccb28e15e76b5206f65f89b25b037eb922
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:877cbfb7de479f62248634d105d7b3cf3fb2397e07f0e8b78265a455155762d7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -294,6 +294,13 @@
|
|
294 |
"learning_rate": 1.999992679444808e-05,
|
295 |
"loss": 1.5118,
|
296 |
"step": 8200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
297 |
}
|
298 |
],
|
299 |
"logging_steps": 200,
|
@@ -301,7 +308,7 @@
|
|
301 |
"num_input_tokens_seen": 0,
|
302 |
"num_train_epochs": 5,
|
303 |
"save_steps": 200,
|
304 |
-
"total_flos": 1.
|
305 |
"train_batch_size": 1,
|
306 |
"trial_name": null,
|
307 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006246769713578172,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 8400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
294 |
"learning_rate": 1.999992679444808e-05,
|
295 |
"loss": 1.5118,
|
296 |
"step": 8200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.01,
|
300 |
+
"grad_norm": 4.383536338806152,
|
301 |
+
"learning_rate": 1.9999923174987494e-05,
|
302 |
+
"loss": 1.5533,
|
303 |
+
"step": 8400
|
304 |
}
|
305 |
],
|
306 |
"logging_steps": 200,
|
|
|
308 |
"num_input_tokens_seen": 0,
|
309 |
"num_train_epochs": 5,
|
310 |
"save_steps": 200,
|
311 |
+
"total_flos": 1.0986977552390554e+17,
|
312 |
"train_batch_size": 1,
|
313 |
"trial_name": null,
|
314 |
"trial_params": null
|