Commit
•
301a809
1
Parent(s):
60612bf
Training in progress, epoch 2, 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 498615900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:610aeb0cae11943ac229dd161a4cba3f7ac2c6c4a5228df85ee96f46ce3f6a37
|
3 |
size 498615900
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 997351674
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:081d184c3a09c40305064c7b7db7573966885c1810f831eac5b01bd70f2e2757
|
3 |
size 997351674
|
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 sha256:1a06e53d3b8db8cc45595ffd5e46327d27c2e05c52ebbf3fbc6aae1a160aa1f9
|
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:f071afedb6f79dad7634efb3c11b5cadc1617244cc1febacfa77506e4d908406
|
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":
|
5 |
"eval_steps": 500,
|
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": 46.914,
|
27 |
"eval_steps_per_second": 5.864,
|
28 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
],
|
31 |
"logging_steps": 500,
|
@@ -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": 0.57190397933845,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-500",
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
26 |
"eval_samples_per_second": 46.914,
|
27 |
"eval_steps_per_second": 5.864,
|
28 |
"step": 250
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"grad_norm": 8.063375473022461,
|
33 |
+
"learning_rate": 6e-05,
|
34 |
+
"loss": 0.6685,
|
35 |
+
"step": 500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.6062062937062938,
|
40 |
+
"eval_f1": 0.57190397933845,
|
41 |
+
"eval_loss": 0.8881105780601501,
|
42 |
+
"eval_precision": 0.5980584671844231,
|
43 |
+
"eval_recall": 0.6062062937062938,
|
44 |
+
"eval_runtime": 48.5739,
|
45 |
+
"eval_samples_per_second": 47.104,
|
46 |
+
"eval_steps_per_second": 5.888,
|
47 |
+
"step": 500
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 500,
|
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
+
"total_flos": 834505315795872.0,
|
68 |
"train_batch_size": 8,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|