Training in progress, step 600, 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:afb7ef1ec82241fd009b0e3fba2bb9ab103b17a1db82970ea238901a8ac4812e
|
| 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:f42dc44073a48dac19f32e76f64eb608346ac531bb737ea8e05ae9762b3d7bf8
|
| 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 sha256:96c115c7c9e612e3051941839195c9a04f1487acc5d657beb82249cc8517ab93
|
| 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 sha256:3e6544bc2a8c1702c364c1a0f85d998607374f0fe5fac06edca83a199f838d44
|
| 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,
|
|
@@ -50,6 +50,13 @@
|
|
| 50 |
"eval_samples_per_second": 19.87,
|
| 51 |
"eval_steps_per_second": 2.485,
|
| 52 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
}
|
| 54 |
],
|
| 55 |
"logging_steps": 100,
|
|
@@ -69,7 +76,7 @@
|
|
| 69 |
"attributes": {}
|
| 70 |
}
|
| 71 |
},
|
| 72 |
-
"total_flos":
|
| 73 |
"train_batch_size": 8,
|
| 74 |
"trial_name": null,
|
| 75 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.199812529292298,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 50 |
"eval_samples_per_second": 19.87,
|
| 51 |
"eval_steps_per_second": 2.485,
|
| 52 |
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.199812529292298,
|
| 56 |
+
"grad_norm": 0.10176929831504822,
|
| 57 |
+
"learning_rate": 9.6e-05,
|
| 58 |
+
"loss": 1.3505,
|
| 59 |
+
"step": 600
|
| 60 |
}
|
| 61 |
],
|
| 62 |
"logging_steps": 100,
|
|
|
|
| 76 |
"attributes": {}
|
| 77 |
}
|
| 78 |
},
|
| 79 |
+
"total_flos": 9.364406702587249e+17,
|
| 80 |
"train_batch_size": 8,
|
| 81 |
"trial_name": null,
|
| 82 |
"trial_params": null
|