Commit
•
9a8534c
1
Parent(s):
fea0de0
Training in progress, step 2000, 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 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c63ac2740529d45592199af761ef88351d8bf33a0ced6a1c7bfa51ae6a262e3e
|
3 |
size 267835644
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535733434
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44796c23481279b04feeb89690334c50fc7938f1076fc5c8d84157bb2cd2e390
|
3 |
size 535733434
|
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:d406d538cd09764f86141c5283b0697ea9959a1fda63bbb795129d06c6b2a1d8
|
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:d4841384879f1112c4a211310579ca4e33089f588151f1074a18f817f4e1294d
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "training_dir/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -26,6 +26,25 @@
|
|
26 |
"eval_samples_per_second": 85.857,
|
27 |
"eval_steps_per_second": 10.732,
|
28 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
],
|
31 |
"logging_steps": 1000,
|
@@ -45,7 +64,7 @@
|
|
45 |
"attributes": {}
|
46 |
}
|
47 |
},
|
48 |
-
"total_flos":
|
49 |
"train_batch_size": 8,
|
50 |
"trial_name": null,
|
51 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6366336108184594,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-2000",
|
4 |
+
"epoch": 0.2119317579739324,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
26 |
"eval_samples_per_second": 85.857,
|
27 |
"eval_steps_per_second": 10.732,
|
28 |
"step": 1000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.2119317579739324,
|
32 |
+
"grad_norm": 14.981549263000488,
|
33 |
+
"learning_rate": 9.840204538191116e-06,
|
34 |
+
"loss": 0.5828,
|
35 |
+
"step": 2000
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.2119317579739324,
|
39 |
+
"eval_accuracy": 0.6682692307692307,
|
40 |
+
"eval_f1": 0.6366336108184594,
|
41 |
+
"eval_loss": 0.9371851086616516,
|
42 |
+
"eval_precision": 0.6852715704153842,
|
43 |
+
"eval_recall": 0.6682692307692307,
|
44 |
+
"eval_runtime": 25.9805,
|
45 |
+
"eval_samples_per_second": 88.066,
|
46 |
+
"eval_steps_per_second": 11.008,
|
47 |
+
"step": 2000
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 1000,
|
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
+
"total_flos": 1940081745396960.0,
|
68 |
"train_batch_size": 8,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|