Commit
•
f84238a
1
Parent(s):
b699fd6
Training in progress, epoch 3, 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:f4520baad3f6b69630065cdafd5c5b37d97d73083631718eb2d3f930865f247b
|
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 sha256:6852a54b62e1d649e6a859cd34725af91411a6e5cb31c94b824235999d27ae02
|
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 sha256:694f423926ac4340014289d665fb41e7c4dde468bc19fcd2c2b612fc44bafec6
|
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 sha256:877229026b55d004235a151c979fd49f2e0a0f7eab8421f7dbe46ed565dd74f6
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.57190397933845,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-500",
|
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,
|
@@ -45,6 +45,25 @@
|
|
45 |
"eval_samples_per_second": 47.104,
|
46 |
"eval_steps_per_second": 5.888,
|
47 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 500,
|
@@ -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": 0.57190397933845,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-500",
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 750,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 47.104,
|
46 |
"eval_steps_per_second": 5.888,
|
47 |
"step": 500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.0,
|
51 |
+
"grad_norm": 17.603412628173828,
|
52 |
+
"learning_rate": 5.25e-05,
|
53 |
+
"loss": 0.5728,
|
54 |
+
"step": 750
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.5878496503496503,
|
59 |
+
"eval_f1": 0.5621748822370558,
|
60 |
+
"eval_loss": 1.6389495134353638,
|
61 |
+
"eval_precision": 0.6276473886381739,
|
62 |
+
"eval_recall": 0.5878496503496503,
|
63 |
+
"eval_runtime": 48.841,
|
64 |
+
"eval_samples_per_second": 46.846,
|
65 |
+
"eval_steps_per_second": 5.856,
|
66 |
+
"step": 750
|
67 |
}
|
68 |
],
|
69 |
"logging_steps": 500,
|
|
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
+
"total_flos": 1251671639603616.0,
|
87 |
"train_batch_size": 8,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|