Francesco0101
commited on
Commit
•
4573433
1
Parent(s):
cb5db12
Training in progress, step 7000, 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 sha256:9d4ac88371dde2f60ef6d4d9a01421dcfb0401b145ab3b0e03ce04e6b56129bc
|
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 sha256:6efa1ee1d27102be4345d533482e0ff32e75d8628ff01fdf0f47a76e13e4f878
|
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 sha256:6be12ed77222a22ba6dde61423d5318d408cb16924190445d77fc24710d55cab
|
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 sha256:6f98331ffce66771671e51650bbdb66863679a792bd33c519c623f2e0832464e
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7293047058493298,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-5000",
|
4 |
-
"epoch":
|
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,
|
@@ -121,6 +121,25 @@
|
|
121 |
"eval_samples_per_second": 76.727,
|
122 |
"eval_steps_per_second": 9.591,
|
123 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
124 |
}
|
125 |
],
|
126 |
"logging_steps": 1000,
|
@@ -140,7 +159,7 @@
|
|
140 |
"attributes": {}
|
141 |
}
|
142 |
},
|
143 |
-
"total_flos":
|
144 |
"train_batch_size": 8,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.7293047058493298,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-5000",
|
4 |
+
"epoch": 1.096147823363608,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 7000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
121 |
"eval_samples_per_second": 76.727,
|
122 |
"eval_steps_per_second": 9.591,
|
123 |
"step": 6000
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.096147823363608,
|
127 |
+
"grad_norm": 4.596695899963379,
|
128 |
+
"learning_rate": 8.974116161616161e-06,
|
129 |
+
"loss": 0.3993,
|
130 |
+
"step": 7000
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.096147823363608,
|
134 |
+
"eval_accuracy": 0.7198426573426573,
|
135 |
+
"eval_f1": 0.7041969146725503,
|
136 |
+
"eval_loss": 1.0100624561309814,
|
137 |
+
"eval_precision": 0.7315013162404153,
|
138 |
+
"eval_recall": 0.7198426573426573,
|
139 |
+
"eval_runtime": 29.6299,
|
140 |
+
"eval_samples_per_second": 77.219,
|
141 |
+
"eval_steps_per_second": 9.652,
|
142 |
+
"step": 7000
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 1000,
|
|
|
159 |
"attributes": {}
|
160 |
}
|
161 |
},
|
162 |
+
"total_flos": 7049920113516348.0,
|
163 |
"train_batch_size": 8,
|
164 |
"trial_name": null,
|
165 |
"trial_params": null
|