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 80013120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a0a2aeb1099e63ab80c55443c4f92b7e81fcb6ce28e2842f970f02128753398
|
| 3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41119636
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f7d790aec22356fdde96a6d781e6b420cfa882a2a207ff201faefca07ebab84
|
| 3 |
size 41119636
|
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 sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
|
| 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
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 3,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -65,6 +65,35 @@
|
|
| 65 |
"eval_samples_per_second": 22.988,
|
| 66 |
"eval_steps_per_second": 11.494,
|
| 67 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
}
|
| 69 |
],
|
| 70 |
"logging_steps": 1,
|
|
@@ -84,7 +113,7 @@
|
|
| 84 |
"attributes": {}
|
| 85 |
}
|
| 86 |
},
|
| 87 |
-
"total_flos":
|
| 88 |
"train_batch_size": 2,
|
| 89 |
"trial_name": null,
|
| 90 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.03515625,
|
| 5 |
"eval_steps": 3,
|
| 6 |
+
"global_step": 9,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 65 |
"eval_samples_per_second": 22.988,
|
| 66 |
"eval_steps_per_second": 11.494,
|
| 67 |
"step": 6
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.02734375,
|
| 71 |
+
"grad_norm": 0.8043889999389648,
|
| 72 |
+
"learning_rate": 0.00014,
|
| 73 |
+
"loss": 2.0573,
|
| 74 |
+
"step": 7
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.03125,
|
| 78 |
+
"grad_norm": 0.6341584324836731,
|
| 79 |
+
"learning_rate": 0.00016,
|
| 80 |
+
"loss": 1.9364,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.03515625,
|
| 85 |
+
"grad_norm": 0.8237600922584534,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 2.6282,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.03515625,
|
| 92 |
+
"eval_loss": 2.232496976852417,
|
| 93 |
+
"eval_runtime": 5.3978,
|
| 94 |
+
"eval_samples_per_second": 20.008,
|
| 95 |
+
"eval_steps_per_second": 10.004,
|
| 96 |
+
"step": 9
|
| 97 |
}
|
| 98 |
],
|
| 99 |
"logging_steps": 1,
|
|
|
|
| 113 |
"attributes": {}
|
| 114 |
}
|
| 115 |
},
|
| 116 |
+
"total_flos": 1465874317836288.0,
|
| 117 |
"train_batch_size": 2,
|
| 118 |
"trial_name": null,
|
| 119 |
"trial_params": null
|