Training in progress, epoch 19, 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 500979600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cdf60bec8938bf8d01f9352daf0851b5dad78e224da43b05d955e0449cccb10
|
| 3 |
size 500979600
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1002078330
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8b491c69d0eb9b9cce5623f6f3f486053bd6dbaaca080e25f9837d580a38611
|
| 3 |
size 1002078330
|
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 sha256:7469601ab0b6ecac6e0c9a0483b33f4854b14bcced5f194b9b3d8698af746545
|
| 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 sha256:14ba909328244934e8ba18b57a5ebb47aa31d2a59052769489230ebb52ad3b28
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9877104163169861,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-3216",
|
| 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,
|
|
@@ -200,6 +200,14 @@
|
|
| 200 |
"eval_samples_per_second": 37.175,
|
| 201 |
"eval_steps_per_second": 9.294,
|
| 202 |
"step": 3618
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
}
|
| 204 |
],
|
| 205 |
"logging_steps": 500,
|
|
@@ -219,7 +227,7 @@
|
|
| 219 |
"attributes": {}
|
| 220 |
}
|
| 221 |
},
|
| 222 |
-
"total_flos": 1.
|
| 223 |
"train_batch_size": 16,
|
| 224 |
"trial_name": null,
|
| 225 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.9877104163169861,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-3216",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3819,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 200 |
"eval_samples_per_second": 37.175,
|
| 201 |
"eval_steps_per_second": 9.294,
|
| 202 |
"step": 3618
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 19.0,
|
| 206 |
+
"eval_loss": 0.9973178505897522,
|
| 207 |
+
"eval_runtime": 77.4812,
|
| 208 |
+
"eval_samples_per_second": 36.861,
|
| 209 |
+
"eval_steps_per_second": 9.215,
|
| 210 |
+
"step": 3819
|
| 211 |
}
|
| 212 |
],
|
| 213 |
"logging_steps": 500,
|
|
|
|
| 227 |
"attributes": {}
|
| 228 |
}
|
| 229 |
},
|
| 230 |
+
"total_flos": 1.2856067083008e+17,
|
| 231 |
"train_batch_size": 16,
|
| 232 |
"trial_name": null,
|
| 233 |
"trial_params": null
|