MohamedAhmedAE
commited on
Commit
•
1b1b6f4
1
Parent(s):
ffc2d10
Training in progress, step 5600, 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:a30737d4c22b4b26e4123c801ceb26aa4e876b6d95f0b62cad4d768ed46f2ce6
|
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 sha256:1c4b879409f22641359b928d1e77271642a5b4639b676ff813e6ec4fed297a16
|
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 sha256:12a1c117c19e73bcd669e165d231b727aab93d182a0e0acc0ec7506cb4907381
|
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:daecd8e9a7fb8ab89776f0aa83b998d3983e03adcf54b58e801c6e6de09593a8
|
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,
|
@@ -196,6 +196,13 @@
|
|
196 |
"learning_rate": 1.9999968297103373e-05,
|
197 |
"loss": 1.5909,
|
198 |
"step": 5400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
199 |
}
|
200 |
],
|
201 |
"logging_steps": 200,
|
@@ -203,7 +210,7 @@
|
|
203 |
"num_input_tokens_seen": 0,
|
204 |
"num_train_epochs": 5,
|
205 |
"save_steps": 200,
|
206 |
-
"total_flos": 7.
|
207 |
"train_batch_size": 1,
|
208 |
"trial_name": null,
|
209 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004164513142385448,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 5600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
196 |
"learning_rate": 1.9999968297103373e-05,
|
197 |
"loss": 1.5909,
|
198 |
"step": 5400
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.0,
|
202 |
+
"grad_norm": 4.743027210235596,
|
203 |
+
"learning_rate": 1.999996590028264e-05,
|
204 |
+
"loss": 1.5651,
|
205 |
+
"step": 5600
|
206 |
}
|
207 |
],
|
208 |
"logging_steps": 200,
|
|
|
210 |
"num_input_tokens_seen": 0,
|
211 |
"num_train_epochs": 5,
|
212 |
"save_steps": 200,
|
213 |
+
"total_flos": 7.351449119465472e+16,
|
214 |
"train_batch_size": 1,
|
215 |
"trial_name": null,
|
216 |
"trial_params": null
|