Training in progress, step 800, 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:ca5e23c465228e2b947fff5c9e13ca8a54c2b22dc69f94042cacc4bc4f4f0534
|
| 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:b1a0ec82ac04b4d9ccc96de767aae12fe7a52e37224939fd9e1f89a7025538e2
|
| 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 sha256:28ac6d6f63baafad9d2ceaf3fa4ec8c598a9cbcf87a4705844a1b79a5682c033
|
| 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 sha256:7e64c3ed8e79844386b92c479a002b11c813cfc5e611c42a50454b3e0c8c9d9b
|
| 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": 1.
|
| 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,
|
|
@@ -64,6 +64,13 @@
|
|
| 64 |
"learning_rate": 9.533333333333334e-05,
|
| 65 |
"loss": 1.3431,
|
| 66 |
"step": 700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
}
|
| 68 |
],
|
| 69 |
"logging_steps": 100,
|
|
@@ -83,7 +90,7 @@
|
|
| 83 |
"attributes": {}
|
| 84 |
}
|
| 85 |
},
|
| 86 |
-
"total_flos": 1.
|
| 87 |
"train_batch_size": 8,
|
| 88 |
"trial_name": null,
|
| 89 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.5997500390563975,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 64 |
"learning_rate": 9.533333333333334e-05,
|
| 65 |
"loss": 1.3431,
|
| 66 |
"step": 700
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.5997500390563975,
|
| 70 |
+
"grad_norm": 0.11078939586877823,
|
| 71 |
+
"learning_rate": 9.466666666666667e-05,
|
| 72 |
+
"loss": 1.3325,
|
| 73 |
+
"step": 800
|
| 74 |
}
|
| 75 |
],
|
| 76 |
"logging_steps": 100,
|
|
|
|
| 90 |
"attributes": {}
|
| 91 |
}
|
| 92 |
},
|
| 93 |
+
"total_flos": 1.2485906126350582e+18,
|
| 94 |
"train_batch_size": 8,
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": null
|