Francesco0101
commited on
Commit
•
0637038
1
Parent(s):
9ba56da
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 498615900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77ebea82a9f3c4e22e3f17a10fe0983aceb8b905574bf779f0d1f4afcb2c2589
|
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:b69147daac578b55f7fb85920e4fed94f30a35f561e7324d1f02402b279bf900
|
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 sha256:6cf31f3315e0bfe25fcfad59fbf87799e20f6322db5e15fc401b772537e73d62
|
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 sha256:35fe87dbd6014deea326105569abe0f140270c203f324b3dec6bdad30aaebd26
|
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":
|
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": 46.969,
|
84 |
"eval_steps_per_second": 5.871,
|
85 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
}
|
87 |
],
|
88 |
"logging_steps": 500,
|
@@ -102,7 +121,7 @@
|
|
102 |
"attributes": {}
|
103 |
}
|
104 |
},
|
105 |
-
"total_flos":
|
106 |
"train_batch_size": 8,
|
107 |
"trial_name": null,
|
108 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6631765774552385,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-1250",
|
4 |
+
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1250,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
83 |
"eval_samples_per_second": 46.969,
|
84 |
"eval_steps_per_second": 5.871,
|
85 |
"step": 1000
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 5.0,
|
89 |
+
"grad_norm": 3.5804481506347656,
|
90 |
+
"learning_rate": 3.7500000000000003e-05,
|
91 |
+
"loss": 0.3592,
|
92 |
+
"step": 1250
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 5.0,
|
96 |
+
"eval_accuracy": 0.6765734265734266,
|
97 |
+
"eval_f1": 0.6631765774552385,
|
98 |
+
"eval_loss": 1.30519437789917,
|
99 |
+
"eval_precision": 0.6758934188659348,
|
100 |
+
"eval_recall": 0.6765734265734266,
|
101 |
+
"eval_runtime": 48.2801,
|
102 |
+
"eval_samples_per_second": 47.39,
|
103 |
+
"eval_steps_per_second": 5.924,
|
104 |
+
"step": 1250
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 500,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 2086004287219104.0,
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|