Training in progress, step 319, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41a884109ab682178b73a987753f7502434190aee444fb64c585a779e0054394
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37431220
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59f3d52f3297799e817157553f5eecf4bd11588f7463aabb282321c95bf83870
|
3 |
size 37431220
|
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 sha256:019693671adf444ecdcdad70744c387ce98652ccd4852947f91f3c50c1e73518
|
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": 0.
|
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,
|
@@ -2226,6 +2226,20 @@
|
|
2226 |
"learning_rate": 3.560606060606061e-05,
|
2227 |
"loss": 1.1711,
|
2228 |
"step": 317
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2229 |
}
|
2230 |
],
|
2231 |
"logging_steps": 1,
|
@@ -2245,7 +2259,7 @@
|
|
2245 |
"attributes": {}
|
2246 |
}
|
2247 |
},
|
2248 |
-
"total_flos": 3.
|
2249 |
"train_batch_size": 4,
|
2250 |
"trial_name": null,
|
2251 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8751714677640604,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 319,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2226 |
"learning_rate": 3.560606060606061e-05,
|
2227 |
"loss": 1.1711,
|
2228 |
"step": 317
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.8724279835390947,
|
2232 |
+
"grad_norm": 0.16212019324302673,
|
2233 |
+
"learning_rate": 3.484848484848485e-05,
|
2234 |
+
"loss": 1.1346,
|
2235 |
+
"step": 318
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.8751714677640604,
|
2239 |
+
"grad_norm": 0.16122637689113617,
|
2240 |
+
"learning_rate": 3.409090909090909e-05,
|
2241 |
+
"loss": 1.2463,
|
2242 |
+
"step": 319
|
2243 |
}
|
2244 |
],
|
2245 |
"logging_steps": 1,
|
|
|
2259 |
"attributes": {}
|
2260 |
}
|
2261 |
},
|
2262 |
+
"total_flos": 3.952768708551721e+17,
|
2263 |
"train_batch_size": 4,
|
2264 |
"trial_name": null,
|
2265 |
"trial_params": null
|