Training in progress, step 1100, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5baf66bae1adec7859725810856fb91dfb90b10cb6980c2fa5e436efb391e97
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb0eee2bdfb72dac54bf2bc429692deafb96a6a3278081912cb4dde6c531b1d6
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:771e87a1245ca1f22964da009cccc2a3a35adf3747accc2fcc10904014ae27e0
|
| 3 |
size 15006
|
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 sha256:7bfd5a65b7c927b952f142193830fdcbec814c41f796c10eda7a277995ef8805
|
| 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":
|
| 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,
|
|
@@ -93,6 +93,13 @@
|
|
| 93 |
"eval_samples_per_second": 19.883,
|
| 94 |
"eval_steps_per_second": 2.486,
|
| 95 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
}
|
| 97 |
],
|
| 98 |
"logging_steps": 100,
|
|
@@ -112,7 +119,7 @@
|
|
| 112 |
"attributes": {}
|
| 113 |
}
|
| 114 |
},
|
| 115 |
-
"total_flos": 1.
|
| 116 |
"train_batch_size": 8,
|
| 117 |
"trial_name": null,
|
| 118 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.1996563037025463,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 93 |
"eval_samples_per_second": 19.883,
|
| 94 |
"eval_steps_per_second": 2.486,
|
| 95 |
"step": 1000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.1996563037025463,
|
| 99 |
+
"grad_norm": 0.1258271187543869,
|
| 100 |
+
"learning_rate": 9.266666666666666e-05,
|
| 101 |
+
"loss": 1.3204,
|
| 102 |
+
"step": 1100
|
| 103 |
}
|
| 104 |
],
|
| 105 |
"logging_steps": 100,
|
|
|
|
| 119 |
"attributes": {}
|
| 120 |
}
|
| 121 |
},
|
| 122 |
+
"total_flos": 1.716806369329283e+18,
|
| 123 |
"train_batch_size": 8,
|
| 124 |
"trial_name": null,
|
| 125 |
"trial_params": null
|