Training in progress, step 8000, 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 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75c5b2419640fe13669a068fb7e26254322466c5d858313ef02de53677581c9d
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89674eaeda206b838ac99ca2ee9263c40a01135163edaa0624d151c7c84fd452
|
3 |
size 484163514
|
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:cd79f2fefbaefbe9088e7c79a1da25f013e6ccd3483f5ddbddeb65ac105c1771
|
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 sha256:1f56c5e55013c47d62968ace7dd778a0c079a8e2b4cfdd3b2ddaacc49c8a8e75
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -107,13 +107,19 @@
|
|
107 |
"learning_rate": 0.0007698588090853285,
|
108 |
"loss": 0.5623,
|
109 |
"step": 7500
|
|
|
|
|
|
|
|
|
|
|
|
|
110 |
}
|
111 |
],
|
112 |
"logging_steps": 500,
|
113 |
"max_steps": 32580,
|
114 |
"num_train_epochs": 5,
|
115 |
"save_steps": 500,
|
116 |
-
"total_flos":
|
117 |
"trial_name": null,
|
118 |
"trial_params": null
|
119 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2277470841006752,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 8000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
107 |
"learning_rate": 0.0007698588090853285,
|
108 |
"loss": 0.5623,
|
109 |
"step": 7500
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 1.23,
|
113 |
+
"learning_rate": 0.0007545119705340699,
|
114 |
+
"loss": 0.5669,
|
115 |
+
"step": 8000
|
116 |
}
|
117 |
],
|
118 |
"logging_steps": 500,
|
119 |
"max_steps": 32580,
|
120 |
"num_train_epochs": 5,
|
121 |
"save_steps": 500,
|
122 |
+
"total_flos": 4240465882251264.0,
|
123 |
"trial_name": null,
|
124 |
"trial_params": null
|
125 |
}
|