Training in progress, step 39, 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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e2beec9e70f3e6e5b8be8e0d47d6c08bb36e5de9ca665720a59ad98b4916fba
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 64219860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3ab7b37c4ea93da4a86681b6b3eab3cfca629de7038d1ad66bb1dbda73c2d8
|
3 |
size 64219860
|
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 sha256:89ec80c42722702637d7b76af048c5e8229c9a8ba738c0d6bedd3cdb2a5529ce
|
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 sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -45,6 +45,21 @@
|
|
45 |
"eval_samples_per_second": 16.659,
|
46 |
"eval_steps_per_second": 8.35,
|
47 |
"step": 26
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 10,
|
@@ -64,7 +79,7 @@
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
-
"total_flos":
|
68 |
"train_batch_size": 2,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04097714736012608,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 16.659,
|
46 |
"eval_steps_per_second": 8.35,
|
47 |
"step": 26
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.03152088258471237,
|
51 |
+
"grad_norm": 0.1156439557671547,
|
52 |
+
"learning_rate": 8.263518223330697e-05,
|
53 |
+
"loss": 0.115,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.04097714736012608,
|
58 |
+
"eval_loss": 0.10069109499454498,
|
59 |
+
"eval_runtime": 24.1029,
|
60 |
+
"eval_samples_per_second": 16.637,
|
61 |
+
"eval_steps_per_second": 8.339,
|
62 |
+
"step": 39
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 10,
|
|
|
79 |
"attributes": {}
|
80 |
}
|
81 |
},
|
82 |
+
"total_flos": 1.456454498254848e+16,
|
83 |
"train_batch_size": 2,
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|