Training in progress, epoch 5, 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 sha256:8b83643423830ced90be75b5936a230435a4d7c41271ee6396b36ae21e3e9184
|
| 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 sha256:3634b7a801605ac075cba08fca5f6cee78d7e2616fbd4b23eb3d2563d852d5ba
|
| 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 sha256:81cdff37fcc9f2e7b67e49eacca7ee58d0849ebd84d0d18ed314d15b6d08b9bf
|
| 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:d769e3aa8f29c38c9f462b2e7e4c0d81c0096d2cc9fa67472ba538364ee3d794
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.6301519274711609,
|
| 3 |
"best_model_checkpoint": "./opt_trained3/checkpoint-60",
|
| 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,
|
|
@@ -39,6 +39,14 @@
|
|
| 39 |
"eval_samples_per_second": 50.127,
|
| 40 |
"eval_steps_per_second": 12.532,
|
| 41 |
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|
| 43 |
],
|
| 44 |
"logging_steps": 500,
|
|
@@ -58,7 +66,7 @@
|
|
| 58 |
"attributes": {}
|
| 59 |
}
|
| 60 |
},
|
| 61 |
-
"total_flos":
|
| 62 |
"train_batch_size": 24,
|
| 63 |
"trial_name": null,
|
| 64 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.6301519274711609,
|
| 3 |
"best_model_checkpoint": "./opt_trained3/checkpoint-60",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 75,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 39 |
"eval_samples_per_second": 50.127,
|
| 40 |
"eval_steps_per_second": 12.532,
|
| 41 |
"step": 60
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 5.0,
|
| 45 |
+
"eval_loss": 0.630576491355896,
|
| 46 |
+
"eval_runtime": 5.9904,
|
| 47 |
+
"eval_samples_per_second": 50.08,
|
| 48 |
+
"eval_steps_per_second": 12.52,
|
| 49 |
+
"step": 75
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"logging_steps": 500,
|
|
|
|
| 66 |
"attributes": {}
|
| 67 |
}
|
| 68 |
},
|
| 69 |
+
"total_flos": 2783028067200000.0,
|
| 70 |
"train_batch_size": 24,
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": null
|