Training in progress, epoch 9, 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:e506e8b711532ffbf8d019c3dbaa09eaed27feabeff7810d601ccc9a23cfc2d9
|
| 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 sha256:9d0f82e522d7c9c2307fe7e6bb081646b7b91b63b1d6c1d5da80eb96ef27b786
|
| 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 sha256:1812b24c4a0709c5ca3bbda05f6cbbac6be8f60609bcdd27c69d338fb9bf850d
|
| 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 sha256:2cf80e67dccb6aa983f190eabd4c5ec21d2397299a1f9709fdac00fd53b8aace
|
| 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,
|
|
@@ -71,6 +71,14 @@
|
|
| 71 |
"eval_samples_per_second": 37.177,
|
| 72 |
"eval_steps_per_second": 9.294,
|
| 73 |
"step": 176
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
}
|
| 75 |
],
|
| 76 |
"logging_steps": 500,
|
|
@@ -90,7 +98,7 @@
|
|
| 90 |
"attributes": {}
|
| 91 |
}
|
| 92 |
},
|
| 93 |
-
"total_flos":
|
| 94 |
"train_batch_size": 16,
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3414418697357178,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-198",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 198,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 71 |
"eval_samples_per_second": 37.177,
|
| 72 |
"eval_steps_per_second": 9.294,
|
| 73 |
"step": 176
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 9.0,
|
| 77 |
+
"eval_loss": 1.3414418697357178,
|
| 78 |
+
"eval_runtime": 8.0548,
|
| 79 |
+
"eval_samples_per_second": 37.245,
|
| 80 |
+
"eval_steps_per_second": 9.311,
|
| 81 |
+
"step": 198
|
| 82 |
}
|
| 83 |
],
|
| 84 |
"logging_steps": 500,
|
|
|
|
| 98 |
"attributes": {}
|
| 99 |
}
|
| 100 |
},
|
| 101 |
+
"total_flos": 6384781034496000.0,
|
| 102 |
"train_batch_size": 16,
|
| 103 |
"trial_name": null,
|
| 104 |
"trial_params": null
|