MohamedAhmedAE
commited on
Commit
•
279aa21
1
Parent(s):
380a81b
Training in progress, step 7000, 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 sha256:2dbf43604912a67d12a82c3ddf5f1b939d015de908422b4c0f8e4699d02fcc4a
|
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 sha256:59c7c6053c0bd928ed9df145ce525bc50185508e88d636fcc91edf4745bcac0f
|
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:b74ab7e4f70a25c27af953fcf81e51d62ef1f062e1f6941b002637b31fbb04d6
|
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 sha256:8e3e4f4d223c89d87dca50ebf348e1e323fc70dc0e5de01dc749be545d0332b2
|
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,
|
@@ -245,6 +245,13 @@
|
|
245 |
"learning_rate": 1.999994968539587e-05,
|
246 |
"loss": 1.5443,
|
247 |
"step": 6800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
248 |
}
|
249 |
],
|
250 |
"logging_steps": 200,
|
@@ -252,7 +259,7 @@
|
|
252 |
"num_input_tokens_seen": 0,
|
253 |
"num_train_epochs": 5,
|
254 |
"save_steps": 200,
|
255 |
-
"total_flos":
|
256 |
"train_batch_size": 1,
|
257 |
"trial_name": null,
|
258 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00520564142798181,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 7000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
245 |
"learning_rate": 1.999994968539587e-05,
|
246 |
"loss": 1.5443,
|
247 |
"step": 6800
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.01,
|
251 |
+
"grad_norm": 3.8644936084747314,
|
252 |
+
"learning_rate": 1.9999946677254565e-05,
|
253 |
+
"loss": 1.5163,
|
254 |
+
"step": 7000
|
255 |
}
|
256 |
],
|
257 |
"logging_steps": 200,
|
|
|
259 |
"num_input_tokens_seen": 0,
|
260 |
"num_train_epochs": 5,
|
261 |
"save_steps": 200,
|
262 |
+
"total_flos": 9.194353461650227e+16,
|
263 |
"train_batch_size": 1,
|
264 |
"trial_name": null,
|
265 |
"trial_params": null
|