MohamedAhmedAE
commited on
Commit
•
6d13786
1
Parent(s):
2f9060f
Training in progress, step 13700, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1716360444
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e371f5504566f00a547c6bf5dc76271ea0ad06d762d643694654527dc3346840
|
3 |
size 1716360444
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3433062021
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16e466d2ee4c48404eed81b17e1872461c9a51ce80d03b824705ab4d31a12f3d
|
3 |
size 3433062021
|
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:cc5d802f36cedde4a662f27d6a60aa6a1c9ef6ec948baf9bbe72cb2ba9b0eb3d
|
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:a2ecaf274f2d11ebe93c1edafaab1e1809e0fd9e148dbce8088ae8dd2ca43011
|
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": 1.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1063,6 +1063,13 @@
|
|
1063 |
"learning_rate": 3.755265096622077e-05,
|
1064 |
"loss": 1.3863,
|
1065 |
"step": 13600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1066 |
}
|
1067 |
],
|
1068 |
"logging_steps": 100,
|
@@ -1082,7 +1089,7 @@
|
|
1082 |
"attributes": {}
|
1083 |
}
|
1084 |
},
|
1085 |
-
"total_flos": 3.
|
1086 |
"train_batch_size": 4,
|
1087 |
"trial_name": null,
|
1088 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.675431087195793,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 13700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1063 |
"learning_rate": 3.755265096622077e-05,
|
1064 |
"loss": 1.3863,
|
1065 |
"step": 13600
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 1.675431087195793,
|
1069 |
+
"grad_norm": 0.00034479121677577496,
|
1070 |
+
"learning_rate": 3.7386132941443e-05,
|
1071 |
+
"loss": 1.3863,
|
1072 |
+
"step": 13700
|
1073 |
}
|
1074 |
],
|
1075 |
"logging_steps": 100,
|
|
|
1089 |
"attributes": {}
|
1090 |
}
|
1091 |
},
|
1092 |
+
"total_flos": 3.2783681485824e+16,
|
1093 |
"train_batch_size": 4,
|
1094 |
"trial_name": null,
|
1095 |
"trial_params": null
|