Training in progress, step 90, 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 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a770f3185b4bc959d9093b622efcb1c6a0649f574dd4cb2f803a7a0b0f5847e
|
3 |
size 966995080
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1925064044
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9404b3b8073985a0ad59571a09b36826009505c1e25c30b4a3bcaea415bb5aa
|
3 |
size 1925064044
|
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 sha256:5dfc9586ba42710aa4ce0391828f29de924e90b3b8e4b33ef6fb16e4e88e645f
|
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:df8acfe66f0561ea918b9d7da9a7d6ce9312bdfd8b3c3cd4af6fca3356e7db5c
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -19,6 +19,12 @@
|
|
19 |
"learning_rate": 9.200000000000001e-07,
|
20 |
"loss": 2.3577,
|
21 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 25,
|
@@ -26,7 +32,7 @@
|
|
26 |
"num_input_tokens_seen": 0,
|
27 |
"num_train_epochs": 3,
|
28 |
"save_steps": 10,
|
29 |
-
"total_flos":
|
30 |
"trial_name": null,
|
31 |
"trial_params": null
|
32 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04955947136563876,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 90,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
19 |
"learning_rate": 9.200000000000001e-07,
|
20 |
"loss": 2.3577,
|
21 |
"step": 50
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.04,
|
25 |
+
"learning_rate": 1.42e-06,
|
26 |
+
"loss": 1.7546,
|
27 |
+
"step": 75
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 25,
|
|
|
32 |
"num_input_tokens_seen": 0,
|
33 |
"num_train_epochs": 3,
|
34 |
"save_steps": 10,
|
35 |
+
"total_flos": 4.155629764608e+17,
|
36 |
"trial_name": null,
|
37 |
"trial_params": null
|
38 |
}
|