Training in progress, step 240, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee09aee714a0d8fcb8ef312ee4a4072b24468a833b9d6dafbebd60510fabfd1e
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20523679
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1cdb6e9cc6334a957b12d618a98551370f68b5bdec4911f762b5c5f985fa0ba
|
3 |
size 20523679
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4e085dbfb4360d0b1d1a70f41f8cc0d50c49411158b7692da0161b20fa6f644
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bffc51fe41100ceb6b5ccb0547daebfd4c07145e23781aecc9f04927874c1216
|
3 |
size 627
|
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": 60,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -46,13 +46,26 @@
|
|
46 |
"eval_samples_per_second": 1.913,
|
47 |
"eval_steps_per_second": 0.239,
|
48 |
"step": 180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 60,
|
52 |
"max_steps": 1011,
|
53 |
"num_train_epochs": 3,
|
54 |
"save_steps": 60,
|
55 |
-
"total_flos":
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7111111111111111,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 240,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
46 |
"eval_samples_per_second": 1.913,
|
47 |
"eval_steps_per_second": 0.239,
|
48 |
"step": 180
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.71,
|
52 |
+
"learning_rate": 0.0002,
|
53 |
+
"loss": 0.6116,
|
54 |
+
"step": 240
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.71,
|
58 |
+
"eval_runtime": 313.0801,
|
59 |
+
"eval_samples_per_second": 1.916,
|
60 |
+
"eval_steps_per_second": 0.24,
|
61 |
+
"step": 240
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 60,
|
65 |
"max_steps": 1011,
|
66 |
"num_train_epochs": 3,
|
67 |
"save_steps": 60,
|
68 |
+
"total_flos": 3.986425972260864e+16,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
71 |
}
|