Training in progress, step 2200, 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:d2fe1a1edf619615cc34ff5e5ffe70593069471f207bf5e73938a378938486d7
|
| 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 sha256:9e8419ad27007f810b0b00ce14ef24ef11b9d2f4062c7026c3f9c293933876fb
|
| 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 sha256:83e6c6f7fee46c7f98dc914278c7b6be6afe219268e94d50c2ba7305931bbd9f
|
| 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 sha256:1cffbe7340a8b03bb6ff6b8dfa99ecb1c7dbb489612e657266462c1dbb23cd7a
|
| 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": 4.
|
| 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,
|
|
@@ -186,6 +186,13 @@
|
|
| 186 |
"learning_rate": 8.6e-05,
|
| 187 |
"loss": 1.2963,
|
| 188 |
"step": 2100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 189 |
}
|
| 190 |
],
|
| 191 |
"logging_steps": 100,
|
|
@@ -205,7 +212,7 @@
|
|
| 205 |
"attributes": {}
|
| 206 |
}
|
| 207 |
},
|
| 208 |
-
"total_flos": 3.
|
| 209 |
"train_batch_size": 8,
|
| 210 |
"trial_name": null,
|
| 211 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.399312607405093,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 186 |
"learning_rate": 8.6e-05,
|
| 187 |
"loss": 1.2963,
|
| 188 |
"step": 2100
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.399312607405093,
|
| 192 |
+
"grad_norm": 0.15457451343536377,
|
| 193 |
+
"learning_rate": 8.533333333333334e-05,
|
| 194 |
+
"loss": 1.294,
|
| 195 |
+
"step": 2200
|
| 196 |
}
|
| 197 |
],
|
| 198 |
"logging_steps": 100,
|
|
|
|
| 212 |
"attributes": {}
|
| 213 |
}
|
| 214 |
},
|
| 215 |
+
"total_flos": 3.433612738658566e+18,
|
| 216 |
"train_batch_size": 8,
|
| 217 |
"trial_name": null,
|
| 218 |
"trial_params": null
|