Training in progress, epoch 3, 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 sha256:86227795b6af17362e082b5722ee5cfb433b5919f11fd53e9aa7790b768bccad
|
| 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 sha256:95103f0401a062a7f1baf4ee902ce4a0f311a0d7e3ab20ab02ed88f6cac0685a
|
| 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 sha256:98ff1569a40368a50ec7371f3deb5220c08b4970d5020eba50f3e7a49dafe402
|
| 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 sha256:5b7d0d8b02c2af9cef5dcb3886b2f77dd2aa54420e9dd39691b6b24767e637b2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "./opt_trained/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,
|
|
@@ -23,6 +23,14 @@
|
|
| 23 |
"eval_samples_per_second": 37.278,
|
| 24 |
"eval_steps_per_second": 9.32,
|
| 25 |
"step": 44
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"logging_steps": 500,
|
|
@@ -42,7 +50,7 @@
|
|
| 42 |
"attributes": {}
|
| 43 |
}
|
| 44 |
},
|
| 45 |
-
"total_flos":
|
| 46 |
"train_batch_size": 16,
|
| 47 |
"trial_name": null,
|
| 48 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3922361135482788,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-66",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 66,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 23 |
"eval_samples_per_second": 37.278,
|
| 24 |
"eval_steps_per_second": 9.32,
|
| 25 |
"step": 44
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 3.0,
|
| 29 |
+
"eval_loss": 1.3922361135482788,
|
| 30 |
+
"eval_runtime": 8.0491,
|
| 31 |
+
"eval_samples_per_second": 37.271,
|
| 32 |
+
"eval_steps_per_second": 9.318,
|
| 33 |
+
"step": 66
|
| 34 |
}
|
| 35 |
],
|
| 36 |
"logging_steps": 500,
|
|
|
|
| 50 |
"attributes": {}
|
| 51 |
}
|
| 52 |
},
|
| 53 |
+
"total_flos": 2128260344832000.0,
|
| 54 |
"train_batch_size": 16,
|
| 55 |
"trial_name": null,
|
| 56 |
"trial_params": null
|