Training in progress, step 1500, 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 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2096d6e418ab1a1fb1b6796af4b00ad742a59e45ae534c974216cfd6e3853f6
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:507d69cf2fc1aa770844e27408801f5ee31930cc2ccc6fa03d7678397b0587d3
|
3 |
size 1783272762
|
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 sha256:20294402676b8b8232d3be0cb80a9ffb92a161c28d7847bfbca2a9db648b436d
|
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:a5fdd8c32e3cbbf0e963fa8e34156237191e0de6ae8bcbd3bcbef97429ddf0e5
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -21,6 +21,13 @@
|
|
21 |
"learning_rate": 1.7127230857800806e-05,
|
22 |
"loss": 0.4945,
|
23 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 500,
|
@@ -40,7 +47,7 @@
|
|
40 |
"attributes": {}
|
41 |
}
|
42 |
},
|
43 |
-
"total_flos":
|
44 |
"train_batch_size": 4,
|
45 |
"trial_name": null,
|
46 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6476683937823834,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
21 |
"learning_rate": 1.7127230857800806e-05,
|
22 |
"loss": 0.4945,
|
23 |
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6476683937823834,
|
27 |
+
"grad_norm": 0.49951252341270447,
|
28 |
+
"learning_rate": 1.568796776050662e-05,
|
29 |
+
"loss": 0.4456,
|
30 |
+
"step": 1500
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 500,
|
|
|
47 |
"attributes": {}
|
48 |
}
|
49 |
},
|
50 |
+
"total_flos": 3653747343360000.0,
|
51 |
"train_batch_size": 4,
|
52 |
"trial_name": null,
|
53 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2d71d788b491a41c54d3b024285748be4a2e443d732e96343f48dd9941e304a
|
3 |
size 5432
|