Training in progress, step 9, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94412008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7228aad5cf88c91f72f6c4c8be9a1fd949a4e4a03f11e1253ed957a6d4bd69f1
|
| 3 |
size 94412008
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 48260756
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18faf23103458d173e46410706d233b2a8ffc5e6e0dc792de41f6295f5b1ab0d
|
| 3 |
size 48260756
|
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:bfb79989f0b6ef3fd37f867a5b814d6aca11d21de163825e3e0b00f3a404b965
|
| 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 sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
| 3 |
size 1064
|
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": 3,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -74,6 +74,35 @@
|
|
| 74 |
"eval_samples_per_second": 6.673,
|
| 75 |
"eval_steps_per_second": 3.337,
|
| 76 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
}
|
| 78 |
],
|
| 79 |
"logging_steps": 1,
|
|
@@ -93,7 +122,7 @@
|
|
| 93 |
"attributes": {}
|
| 94 |
}
|
| 95 |
},
|
| 96 |
-
"total_flos":
|
| 97 |
"train_batch_size": 2,
|
| 98 |
"trial_name": null,
|
| 99 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.0004557712028561662,
|
| 6 |
"eval_steps": 3,
|
| 7 |
+
"global_step": 9,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 74 |
"eval_samples_per_second": 6.673,
|
| 75 |
"eval_steps_per_second": 3.337,
|
| 76 |
"step": 6
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.0003544887133325737,
|
| 80 |
+
"grad_norm": 0.8589541912078857,
|
| 81 |
+
"learning_rate": 0.00012,
|
| 82 |
+
"loss": 3.0754,
|
| 83 |
+
"step": 7
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.00040512995809436996,
|
| 87 |
+
"grad_norm": 0.904832661151886,
|
| 88 |
+
"learning_rate": 0.00014,
|
| 89 |
+
"loss": 3.3662,
|
| 90 |
+
"step": 8
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.0004557712028561662,
|
| 94 |
+
"grad_norm": 0.8699621558189392,
|
| 95 |
+
"learning_rate": 0.00016,
|
| 96 |
+
"loss": 2.9704,
|
| 97 |
+
"step": 9
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.0004557712028561662,
|
| 101 |
+
"eval_loss": 2.990236520767212,
|
| 102 |
+
"eval_runtime": 1246.2607,
|
| 103 |
+
"eval_samples_per_second": 6.672,
|
| 104 |
+
"eval_steps_per_second": 3.336,
|
| 105 |
+
"step": 9
|
| 106 |
}
|
| 107 |
],
|
| 108 |
"logging_steps": 1,
|
|
|
|
| 122 |
"attributes": {}
|
| 123 |
}
|
| 124 |
},
|
| 125 |
+
"total_flos": 2567524822548480.0,
|
| 126 |
"train_batch_size": 2,
|
| 127 |
"trial_name": null,
|
| 128 |
"trial_params": null
|