Commit
•
3336f0d
1
Parent(s):
9d18ca3
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 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:172a879e54f0613ed34fc2ebe311f2f27a68a3f88d233f7000673e5598a77685
|
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 sha256:0385300931157697e4a915b5ce3364c3ef452b5cc6f19883fa9a9bcbdfdaf3b4
|
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 sha256:10b2cbbcfce68a465b5dc9649714636223f26c4334afe4a2b30c904f877d83a7
|
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 sha256:2410c1bb6e04ddda81f1a5814723f61652cb286cac246e7b64a7b46322f8b053
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.6361710372570955,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-250",
|
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": 76.721,
|
46 |
"eval_steps_per_second": 9.59,
|
47 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 500,
|
@@ -64,7 +83,7 @@
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
-
"total_flos":
|
68 |
"train_batch_size": 16,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.6361710372570955,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-250",
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 375,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 76.721,
|
46 |
"eval_steps_per_second": 9.59,
|
47 |
"step": 250
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 3.0,
|
51 |
+
"grad_norm": 7.845700263977051,
|
52 |
+
"learning_rate": 7.500000000000001e-05,
|
53 |
+
"loss": 0.3732,
|
54 |
+
"step": 375
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.0,
|
58 |
+
"eval_accuracy": 0.603583916083916,
|
59 |
+
"eval_f1": 0.565369682305176,
|
60 |
+
"eval_loss": 1.3425886631011963,
|
61 |
+
"eval_precision": 0.6364003210803549,
|
62 |
+
"eval_recall": 0.603583916083916,
|
63 |
+
"eval_runtime": 29.9297,
|
64 |
+
"eval_samples_per_second": 76.446,
|
65 |
+
"eval_steps_per_second": 9.556,
|
66 |
+
"step": 375
|
67 |
}
|
68 |
],
|
69 |
"logging_steps": 500,
|
|
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
+
"total_flos": 611637724728000.0,
|
87 |
"train_batch_size": 16,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|