Francesco0101
commited on
Commit
•
a4739e9
1
Parent(s):
0ed8a9f
Training in progress, step 3000, 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:d16848521b5f211c51bd2b253bdc28aaf9a346fbc5fd4aec9c15cb5825f28615
|
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 sha256:30a419bb2d2294db4015ccf4f984a71493d06deda8043d661fc666e34e19d15d
|
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:cd680bce7049a97dfbda7e74506101a3130ce0e3b97bfb0721afdcd06344a009
|
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:fce293a85c3a6d15ea092b89fa1d71f8b33619837f3a63ea3c7e7e335811845b
|
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,
|
@@ -45,6 +45,25 @@
|
|
45 |
"eval_samples_per_second": 76.707,
|
46 |
"eval_steps_per_second": 9.588,
|
47 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 1000,
|
@@ -64,7 +83,7 @@
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
-
"total_flos":
|
68 |
"train_batch_size": 8,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6892053083671648,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-3000",
|
4 |
+
"epoch": 0.46977763858440336,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 3000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 76.707,
|
46 |
"eval_steps_per_second": 9.588,
|
47 |
"step": 2000
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.46977763858440336,
|
51 |
+
"grad_norm": 2.5105936527252197,
|
52 |
+
"learning_rate": 9.605429292929293e-06,
|
53 |
+
"loss": 0.4747,
|
54 |
+
"step": 3000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.46977763858440336,
|
58 |
+
"eval_accuracy": 0.7076048951048951,
|
59 |
+
"eval_f1": 0.6892053083671648,
|
60 |
+
"eval_loss": 0.8822671175003052,
|
61 |
+
"eval_precision": 0.7144457563342712,
|
62 |
+
"eval_recall": 0.7076048951048951,
|
63 |
+
"eval_runtime": 29.6497,
|
64 |
+
"eval_samples_per_second": 77.168,
|
65 |
+
"eval_steps_per_second": 9.646,
|
66 |
+
"step": 3000
|
67 |
}
|
68 |
],
|
69 |
"logging_steps": 1000,
|
|
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
+
"total_flos": 3022521140484288.0,
|
87 |
"train_batch_size": 8,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|