Commit
•
ac79f38
1
Parent(s):
623163f
Training in progress, epoch 5, 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:a6f13d3f381449f8d84b7ca05fb821a8b2c0861629beaa791e6c2b5fc00bbb5d
|
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 sha256:9765040586104af3a74cdbea9cc7074b0e48ef0d1226c3c15c17be1de83b9f59
|
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 sha256:675b9a4f8cd0e254dcba3b5459763afcac5d970080440d891cee0ad59e24dfb1
|
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 sha256:74a0adf096c9eebfe9a2fa6c4d4fa6dd5ed912c3085653d4e028c18b90b90dc0
|
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,
|
@@ -83,6 +83,25 @@
|
|
83 |
"eval_samples_per_second": 76.538,
|
84 |
"eval_steps_per_second": 9.567,
|
85 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
}
|
87 |
],
|
88 |
"logging_steps": 500,
|
@@ -102,7 +121,7 @@
|
|
102 |
"attributes": {}
|
103 |
}
|
104 |
},
|
105 |
-
"total_flos":
|
106 |
"train_batch_size": 16,
|
107 |
"trial_name": null,
|
108 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.6361710372570955,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-250",
|
4 |
+
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 625,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
83 |
"eval_samples_per_second": 76.538,
|
84 |
"eval_steps_per_second": 9.567,
|
85 |
"step": 500
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 5.0,
|
89 |
+
"grad_norm": 7.975765705108643,
|
90 |
+
"learning_rate": 5e-05,
|
91 |
+
"loss": 0.2239,
|
92 |
+
"step": 625
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 5.0,
|
96 |
+
"eval_accuracy": 0.6324300699300699,
|
97 |
+
"eval_f1": 0.6186338450685905,
|
98 |
+
"eval_loss": 1.4131898880004883,
|
99 |
+
"eval_precision": 0.657121853967928,
|
100 |
+
"eval_recall": 0.6324300699300699,
|
101 |
+
"eval_runtime": 29.8857,
|
102 |
+
"eval_samples_per_second": 76.558,
|
103 |
+
"eval_steps_per_second": 9.57,
|
104 |
+
"step": 625
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 500,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 1019396207880000.0,
|
125 |
"train_batch_size": 16,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|