Training in progress, step 5500, 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 sha256:4276fed1397b0954e680466cea0d481a57ba70180922712a76d50d5e20fe99e1
|
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 sha256:9a608bdfb5b1ad4d3a40b4584028b29e5ea5ad8c9d7bfb2b815d85d5126f4b2b
|
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 sha256:923547af05cdd3afc057dbec6a47ce6d9a810c418671b3571637a299d286d7be
|
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 sha256:9241eff24b3925a44e89d3db66c6446b322e7c397558e0282e0355814c8466fd
|
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,
|
@@ -67,13 +67,19 @@
|
|
67 |
"learning_rate": 0.0008465623081645181,
|
68 |
"loss": 0.6151,
|
69 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 500,
|
73 |
"max_steps": 32580,
|
74 |
"num_train_epochs": 5,
|
75 |
"save_steps": 500,
|
76 |
-
"total_flos":
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
79 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8440761203192142,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
67 |
"learning_rate": 0.0008465623081645181,
|
68 |
"loss": 0.6151,
|
69 |
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.84,
|
73 |
+
"learning_rate": 0.0008312154696132597,
|
74 |
+
"loss": 0.611,
|
75 |
+
"step": 5500
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 500,
|
79 |
"max_steps": 32580,
|
80 |
"num_train_epochs": 5,
|
81 |
"save_steps": 500,
|
82 |
+
"total_flos": 2914518023798784.0,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
85 |
}
|