Training in progress, step 1000, 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 14708920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aff2942e086fee64e229a4e2a26064062a784e94d190c2b6770488551814df5f
|
3 |
size 14708920
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7601989
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3326d984fd9d9dbf90e3668982e4a493b4d0bc8c2a550626cf01b411a0383ec4
|
3 |
size 7601989
|
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:d9025cc4e0da6c63c9bfa2164c686a6228c0b57e1cfeed81ad3255941a7fe7b0
|
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 sha256:06f2ca6113578d7efef90342397e73138a7a92da90251edb146063c752147788
|
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": 1.
|
5 |
"eval_steps": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -59,13 +59,26 @@
|
|
59 |
"eval_samples_per_second": 2.228,
|
60 |
"eval_steps_per_second": 0.279,
|
61 |
"step": 800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 200,
|
65 |
"max_steps": 1593,
|
66 |
"num_train_epochs": 3,
|
67 |
"save_steps": 200,
|
68 |
-
"total_flos":
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
71 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.8820577164366374,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
59 |
"eval_samples_per_second": 2.228,
|
60 |
"eval_steps_per_second": 0.279,
|
61 |
"step": 800
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 1.88,
|
65 |
+
"learning_rate": 2e-05,
|
66 |
+
"loss": 0.6491,
|
67 |
+
"step": 1000
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 1.88,
|
71 |
+
"eval_runtime": 1014.137,
|
72 |
+
"eval_samples_per_second": 2.219,
|
73 |
+
"eval_steps_per_second": 0.278,
|
74 |
+
"step": 1000
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 200,
|
78 |
"max_steps": 1593,
|
79 |
"num_train_epochs": 3,
|
80 |
"save_steps": 200,
|
81 |
+
"total_flos": 2.2334346732679987e+17,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|