Training in progress, step 80, 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 847599616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffded77dbe5849f717ceec3a8e05e32f2accc34f67a38414e5a8628ec6482874
|
| 3 |
size 847599616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1386414411
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b81aec63631cf3d99093746f160b7b04db79c246f3e802e4cdcf3b2e337e823
|
| 3 |
size 1386414411
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6427194f9035b62d203772b7f8860b70a156c72e5e2aa512f0b705b44137fbf4
|
| 3 |
size 14917
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e00fe96875163560113675800aca8f3ff0896df20c4b9639585c87e713e56c8
|
| 3 |
size 14917
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cdffd4f448e38d1e13d54e0da12d65b4a70306f7569df188f294ba615d9017e
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 5,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -134,6 +134,24 @@
|
|
| 134 |
"eval_samples_per_second": 13.964,
|
| 135 |
"eval_steps_per_second": 6.982,
|
| 136 |
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137 |
}
|
| 138 |
],
|
| 139 |
"logging_steps": 100,
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.08,
|
| 6 |
"eval_steps": 5,
|
| 7 |
+
"global_step": 80,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 134 |
"eval_samples_per_second": 13.964,
|
| 135 |
"eval_steps_per_second": 6.982,
|
| 136 |
"step": 70
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.075,
|
| 140 |
+
"eval_accuracy": 0.07566666666666666,
|
| 141 |
+
"eval_loss": 17.033140182495117,
|
| 142 |
+
"eval_runtime": 39.2943,
|
| 143 |
+
"eval_samples_per_second": 12.725,
|
| 144 |
+
"eval_steps_per_second": 6.362,
|
| 145 |
+
"step": 75
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.08,
|
| 149 |
+
"eval_accuracy": 0.07093333333333333,
|
| 150 |
+
"eval_loss": 16.976137161254883,
|
| 151 |
+
"eval_runtime": 35.688,
|
| 152 |
+
"eval_samples_per_second": 14.01,
|
| 153 |
+
"eval_steps_per_second": 7.005,
|
| 154 |
+
"step": 80
|
| 155 |
}
|
| 156 |
],
|
| 157 |
"logging_steps": 100,
|