Training in progress, step 2100, 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:a277212c1266c93791fcd850e5f7ad1d24a6d7701f96e72adfea1ab6a1c701cd
|
| 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 sha256:5890385b64ffe3337a220f02ef3d6cfb8d512fa94cc5e1b99749da6a9a0a1191
|
| 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:b840b1ecb7a27f230e317e12ba0d507dd215ea11309e6506953aa344639e44eb
|
| 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:a644a764635707761eea11250a1f5f821c6b4adfb6adf0c5be9d17ee8b961f55
|
| 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,
|
|
@@ -179,6 +179,13 @@
|
|
| 179 |
"eval_samples_per_second": 19.891,
|
| 180 |
"eval_steps_per_second": 2.487,
|
| 181 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
}
|
| 183 |
],
|
| 184 |
"logging_steps": 100,
|
|
@@ -198,7 +205,7 @@
|
|
| 198 |
"attributes": {}
|
| 199 |
}
|
| 200 |
},
|
| 201 |
-
"total_flos": 3.
|
| 202 |
"train_batch_size": 8,
|
| 203 |
"trial_name": null,
|
| 204 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.199343852523043,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 179 |
"eval_samples_per_second": 19.891,
|
| 180 |
"eval_steps_per_second": 2.487,
|
| 181 |
"step": 2000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 4.199343852523043,
|
| 185 |
+
"grad_norm": 0.14762505888938904,
|
| 186 |
+
"learning_rate": 8.6e-05,
|
| 187 |
+
"loss": 1.2963,
|
| 188 |
+
"step": 2100
|
| 189 |
}
|
| 190 |
],
|
| 191 |
"logging_steps": 100,
|
|
|
|
| 205 |
"attributes": {}
|
| 206 |
}
|
| 207 |
},
|
| 208 |
+
"total_flos": 3.2775377674703995e+18,
|
| 209 |
"train_batch_size": 8,
|
| 210 |
"trial_name": null,
|
| 211 |
"trial_params": null
|