Francesco0101
commited on
Commit
•
380118f
1
Parent(s):
e774ab9
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 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e4966a7329d4b462aa103e2a1c5c9d956c1ca5d874264adfccce09cfb98eedf
|
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:e9649d1cd6546ae71420a5f729429484f882aec73618ff7c94ab57c73ebb6e55
|
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:a9fe601a3134d3c8c35dec249b894bf1731c41640749a2e794f0e2b5b0425d77
|
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:a1c1654640bb39861446cad5a11b2015812421c6a3c7bda32abed762ad21cb63
|
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": 89.561,
|
27 |
"eval_steps_per_second": 11.195,
|
28 |
"step": 125
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
],
|
31 |
"logging_steps": 500,
|
@@ -45,7 +64,7 @@
|
|
45 |
"attributes": {}
|
46 |
}
|
47 |
},
|
48 |
-
"total_flos":
|
49 |
"train_batch_size": 16,
|
50 |
"trial_name": null,
|
51 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6361710372570955,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-250",
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 250,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
26 |
"eval_samples_per_second": 89.561,
|
27 |
"eval_steps_per_second": 11.195,
|
28 |
"step": 125
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"grad_norm": 4.521803855895996,
|
33 |
+
"learning_rate": 5e-05,
|
34 |
+
"loss": 0.5748,
|
35 |
+
"step": 250
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.6407342657342657,
|
40 |
+
"eval_f1": 0.6361710372570955,
|
41 |
+
"eval_loss": 0.8366930484771729,
|
42 |
+
"eval_precision": 0.6428210794762689,
|
43 |
+
"eval_recall": 0.6407342657342657,
|
44 |
+
"eval_runtime": 27.5523,
|
45 |
+
"eval_samples_per_second": 83.042,
|
46 |
+
"eval_steps_per_second": 10.38,
|
47 |
+
"step": 250
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 500,
|
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
+
"total_flos": 407758483152000.0,
|
68 |
"train_batch_size": 16,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|