MohamedAhmedAE
commited on
Commit
•
ff44d16
1
Parent(s):
88dd7d6
Training in progress, step 4000, 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:eb01ed2a8ec6b8d9ca441331f478bc184548ba2cd587732637da94911f94caa3
|
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 sha256:48b28c6356ac383f9524b669dda20f0fa6982eb51ae20cccd0122514477c4f52
|
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 sha256:3712761bc2feaa4dd59bbca7eb1e2751ef5fe3d141fa66ff9fb4561780df39c8
|
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 sha256:17c0443aeeda2543522ca2ca694a10a6e2b344c5716e020a89e9019e3511777c
|
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,
|
@@ -140,6 +140,13 @@
|
|
140 |
"learning_rate": 1.9999984311180655e-05,
|
141 |
"loss": 1.5804,
|
142 |
"step": 3800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 200,
|
@@ -147,7 +154,7 @@
|
|
147 |
"num_input_tokens_seen": 0,
|
148 |
"num_train_epochs": 5,
|
149 |
"save_steps": 200,
|
150 |
-
"total_flos":
|
151 |
"train_batch_size": 1,
|
152 |
"trial_name": null,
|
153 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.002974652244561034,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 4000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
140 |
"learning_rate": 1.9999984311180655e-05,
|
141 |
"loss": 1.5804,
|
142 |
"step": 3800
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.0,
|
146 |
+
"grad_norm": 5.269617557525635,
|
147 |
+
"learning_rate": 1.999998261213993e-05,
|
148 |
+
"loss": 1.6025,
|
149 |
+
"step": 4000
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 200,
|
|
|
154 |
"num_input_tokens_seen": 0,
|
155 |
"num_train_epochs": 5,
|
156 |
"save_steps": 200,
|
157 |
+
"total_flos": 5.2577140632576e+16,
|
158 |
"train_batch_size": 1,
|
159 |
"trial_name": null,
|
160 |
"trial_params": null
|