MohamedAhmedAE
commited on
Commit
•
e25e93a
1
Parent(s):
ecce33c
Training in progress, step 3400, 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 sha256:88adee23a7e35b2cf4aebcd8c81faec7b932abea1a3d19cf7a8d36adbdbc169d
|
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 sha256:73c08ba3cc41f312df74a4897f9862543590396f79d1f28fccf1aaa0e2d0a62e
|
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 sha256:8533a46f2820d296dd8dd66497b3038b4c8cd3388b495350dff5037c2a4c3482
|
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 sha256:715607d045c48cb60eaa3afa895318c1f98eb549c11762cb3cadd29ed207b42b
|
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,
|
@@ -119,6 +119,13 @@
|
|
119 |
"learning_rate": 1.9999988884312347e-05,
|
120 |
"loss": 1.6221,
|
121 |
"step": 3200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
}
|
123 |
],
|
124 |
"logging_steps": 200,
|
@@ -126,7 +133,7 @@
|
|
126 |
"num_input_tokens_seen": 0,
|
127 |
"num_train_epochs": 5,
|
128 |
"save_steps": 200,
|
129 |
-
"total_flos": 4.
|
130 |
"train_batch_size": 1,
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0025284544078768793,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 3400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
119 |
"learning_rate": 1.9999988884312347e-05,
|
120 |
"loss": 1.6221,
|
121 |
"step": 3200
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.0,
|
125 |
+
"grad_norm": 2.5657193660736084,
|
126 |
+
"learning_rate": 1.9999987447266877e-05,
|
127 |
+
"loss": 1.5533,
|
128 |
+
"step": 3400
|
129 |
}
|
130 |
],
|
131 |
"logging_steps": 200,
|
|
|
133 |
"num_input_tokens_seen": 0,
|
134 |
"num_train_epochs": 5,
|
135 |
"save_steps": 200,
|
136 |
+
"total_flos": 4.438400445092659e+16,
|
137 |
"train_batch_size": 1,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|