Commit
•
dbb9ce1
1
Parent(s):
7b3a087
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 sha256:515b87cf0a6a3172ae5c57e520f7d2104f42512194d4ce128b9412164367303b
|
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:c3883c680b06616a54d83f9d39716d483ff373243037f1e452335ed8a9e5c4a7
|
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:d00d1c63ddb24d4f81ac1488700230d892db68acd5821c3502fd0057c64003c1
|
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 sha256:33ab6338b810850df27c82b146a27ff4faf907486cbc0e08077af4440dd9d4fb
|
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": 88.066,
|
46 |
"eval_steps_per_second": 11.008,
|
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": 0.669233772837662,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-3000",
|
4 |
+
"epoch": 0.31789763696089857,
|
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": 88.066,
|
46 |
"eval_steps_per_second": 11.008,
|
47 |
"step": 2000
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.31789763696089857,
|
51 |
+
"grad_norm": 8.239383697509766,
|
52 |
+
"learning_rate": 9.733674230318526e-06,
|
53 |
+
"loss": 0.5349,
|
54 |
+
"step": 3000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.31789763696089857,
|
58 |
+
"eval_accuracy": 0.6914335664335665,
|
59 |
+
"eval_f1": 0.669233772837662,
|
60 |
+
"eval_loss": 0.8858013153076172,
|
61 |
+
"eval_precision": 0.6967032053774095,
|
62 |
+
"eval_recall": 0.6914335664335665,
|
63 |
+
"eval_runtime": 25.9486,
|
64 |
+
"eval_samples_per_second": 88.174,
|
65 |
+
"eval_steps_per_second": 11.022,
|
66 |
+
"step": 3000
|
67 |
}
|
68 |
],
|
69 |
"logging_steps": 1000,
|
|
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
+
"total_flos": 2912647822914960.0,
|
87 |
"train_batch_size": 8,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|