Training in progress, step 20, 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 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb772073806250c1967b5d3476cb1fcaeec4fcc7c4627ac5a15a3968ad651dea
|
3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41119636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:511015aa2da6e82f21bcc30704fef822f736c2446f4b68bdb208c10db553c2da
|
3 |
size 41119636
|
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:ed2ebb658eb8fe3287ed926d1a645fde572791ea4407191c4bca3ef2e77e758f
|
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 sha256:098701d87daa8176da669f731787f8326702510e8abb54b18e920ededa301ec5
|
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,
|
@@ -23,6 +23,14 @@
|
|
23 |
"eval_samples_per_second": 7.379,
|
24 |
"eval_steps_per_second": 3.69,
|
25 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 40,
|
@@ -42,7 +50,7 @@
|
|
42 |
"attributes": {}
|
43 |
}
|
44 |
},
|
45 |
-
"total_flos":
|
46 |
"train_batch_size": 2,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007555901867724493,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
23 |
"eval_samples_per_second": 7.379,
|
24 |
"eval_steps_per_second": 3.69,
|
25 |
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.007555901867724493,
|
29 |
+
"eval_loss": 1.3265780210494995,
|
30 |
+
"eval_runtime": 599.8781,
|
31 |
+
"eval_samples_per_second": 7.432,
|
32 |
+
"eval_steps_per_second": 3.716,
|
33 |
+
"step": 20
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 40,
|
|
|
50 |
"attributes": {}
|
51 |
}
|
52 |
},
|
53 |
+
"total_flos": 1.31825833869312e+16,
|
54 |
"train_batch_size": 2,
|
55 |
"trial_name": null,
|
56 |
"trial_params": null
|