Commit
•
8f94b47
1
Parent(s):
c427fcf
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 sha256:97477183783427f4a0e6c4c64c89c2ff713711937ba50a0a7f0ebc2c0beb19eb
|
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 sha256:8e3b341e9e13369ba57399436690c86adca73b7a520cae93fbc7be3f277f55d6
|
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 sha256:04491054115f5fca09d38960caedd814323b1326ebd99907da9bf3fbd799e184
|
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 sha256:20335469f0ec66a4e6ceae2c6f0f5a5eb0bddc566fe7b367e2d26bc30cb02212
|
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,
|
@@ -121,6 +121,25 @@
|
|
121 |
"eval_samples_per_second": 87.806,
|
122 |
"eval_steps_per_second": 10.976,
|
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": 0.7023119335505582,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-7000",
|
4 |
+
"epoch": 0.7417611529087634,
|
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": 87.806,
|
122 |
"eval_steps_per_second": 10.976,
|
123 |
"step": 6000
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.7417611529087634,
|
127 |
+
"grad_norm": 2.134586811065674,
|
128 |
+
"learning_rate": 9.307552998828167e-06,
|
129 |
+
"loss": 0.4972,
|
130 |
+
"step": 7000
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.7417611529087634,
|
134 |
+
"eval_accuracy": 0.715472027972028,
|
135 |
+
"eval_f1": 0.7023119335505582,
|
136 |
+
"eval_loss": 0.8132364749908447,
|
137 |
+
"eval_precision": 0.7209094583908723,
|
138 |
+
"eval_recall": 0.715472027972028,
|
139 |
+
"eval_runtime": 26.036,
|
140 |
+
"eval_samples_per_second": 87.878,
|
141 |
+
"eval_steps_per_second": 10.985,
|
142 |
+
"step": 7000
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 1000,
|
|
|
159 |
"attributes": {}
|
160 |
}
|
161 |
},
|
162 |
+
"total_flos": 6790124661368112.0,
|
163 |
"train_batch_size": 8,
|
164 |
"trial_name": null,
|
165 |
"trial_params": null
|