Training in progress, step 1400, 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 sha256:8927683e0409ef21ad2b9bc8cc13c6800cfb5590a23142ced607e08869d074fb
|
| 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:d3219639986ad86e4811f92ac562e0c772d743df77fd611625fcebdb38339be0
|
| 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 sha256:1f2115101af4d4b5e45b0940e0c622ad77b0a5d2f224127198cef7127193e2f8
|
| 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:ca19c73ed66fbba4990e15bea507703b1f5228216fc2abeb22d8d074d1228662
|
| 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": 2.
|
| 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,
|
|
@@ -114,6 +114,13 @@
|
|
| 114 |
"learning_rate": 9.133333333333334e-05,
|
| 115 |
"loss": 1.3161,
|
| 116 |
"step": 1300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
}
|
| 118 |
],
|
| 119 |
"logging_steps": 100,
|
|
@@ -133,7 +140,7 @@
|
|
| 133 |
"attributes": {}
|
| 134 |
}
|
| 135 |
},
|
| 136 |
-
"total_flos": 2.
|
| 137 |
"train_batch_size": 8,
|
| 138 |
"trial_name": null,
|
| 139 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.7995625683486955,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 114 |
"learning_rate": 9.133333333333334e-05,
|
| 115 |
"loss": 1.3161,
|
| 116 |
"step": 1300
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.7995625683486955,
|
| 120 |
+
"grad_norm": 0.13487331569194794,
|
| 121 |
+
"learning_rate": 9.066666666666667e-05,
|
| 122 |
+
"loss": 1.3047,
|
| 123 |
+
"step": 1400
|
| 124 |
}
|
| 125 |
],
|
| 126 |
"logging_steps": 100,
|
|
|
|
| 140 |
"attributes": {}
|
| 141 |
}
|
| 142 |
},
|
| 143 |
+
"total_flos": 2.185031282893783e+18,
|
| 144 |
"train_batch_size": 8,
|
| 145 |
"trial_name": null,
|
| 146 |
"trial_params": null
|