Training in progress, step 240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8184a10ca48807e22cc06e50ec6c504f76f4078fa26a373c09b1e614591a70dd
+oid sha256:55f63548d61d6c65a1654bc4bf0a1b62fc84fb53fb4d0f3eb1a55325d89267bb
 size 479769104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c59c970af91f75ad174c54b9036732a06ac597e37b07db4c76c33a0dbe1d9b
+oid sha256:df0b473c11c1b6b133d909acb6c86cf9a832deb9c2a2162cac061c32e7b84d08
 size 240728084

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef7d41b67bbb64d8f59b1b890b60e98c43be1a525871d9f2311fa3b7b48a618
+oid sha256:703f8b43f2697cc055bff9862430a4543fd4d2968318f68935d73a18b734e1eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014481890565557426,
+  "epoch": 0.015516311320240098,
   "eval_steps": 500,
-  "global_step": 224,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1575,6 +1575,118 @@
       "learning_rate": 9.999498966411415e-06,
       "loss": 1.3715,
       "step": 224
+    },
+    {
+      "epoch": 0.014546541862725092,
+      "grad_norm": 4.114704608917236,
+      "learning_rate": 9.999484338713096e-06,
+      "loss": 1.376,
+      "step": 225
+    },
+    {
+      "epoch": 0.01461119315989276,
+      "grad_norm": 4.159117221832275,
+      "learning_rate": 9.999469500558872e-06,
+      "loss": 1.3388,
+      "step": 226
+    },
+    {
+      "epoch": 0.014675844457060426,
+      "grad_norm": 4.336222171783447,
+      "learning_rate": 9.999454451949364e-06,
+      "loss": 1.3121,
+      "step": 227
+    },
+    {
+      "epoch": 0.014740495754228094,
+      "grad_norm": 3.4951186180114746,
+      "learning_rate": 9.999439192885212e-06,
+      "loss": 1.3861,
+      "step": 228
+    },
+    {
+      "epoch": 0.01480514705139576,
+      "grad_norm": 4.519493579864502,
+      "learning_rate": 9.999423723367056e-06,
+      "loss": 1.3151,
+      "step": 229
+    },
+    {
+      "epoch": 0.014869798348563428,
+      "grad_norm": 3.895230770111084,
+      "learning_rate": 9.999408043395546e-06,
+      "loss": 1.3877,
+      "step": 230
+    },
+    {
+      "epoch": 0.014934449645731094,
+      "grad_norm": 3.6650257110595703,
+      "learning_rate": 9.999392152971344e-06,
+      "loss": 1.3744,
+      "step": 231
+    },
+    {
+      "epoch": 0.014999100942898762,
+      "grad_norm": 4.416625022888184,
+      "learning_rate": 9.999376052095117e-06,
+      "loss": 1.2943,
+      "step": 232
+    },
+    {
+      "epoch": 0.01506375224006643,
+      "grad_norm": 4.903157711029053,
+      "learning_rate": 9.999359740767545e-06,
+      "loss": 1.3302,
+      "step": 233
+    },
+    {
+      "epoch": 0.015128403537234096,
+      "grad_norm": 4.176599502563477,
+      "learning_rate": 9.999343218989313e-06,
+      "loss": 1.3421,
+      "step": 234
+    },
+    {
+      "epoch": 0.015193054834401764,
+      "grad_norm": 4.2415876388549805,
+      "learning_rate": 9.999326486761114e-06,
+      "loss": 1.3693,
+      "step": 235
+    },
+    {
+      "epoch": 0.01525770613156943,
+      "grad_norm": 4.100305080413818,
+      "learning_rate": 9.999309544083657e-06,
+      "loss": 1.3251,
+      "step": 236
+    },
+    {
+      "epoch": 0.015322357428737098,
+      "grad_norm": 3.9971888065338135,
+      "learning_rate": 9.999292390957653e-06,
+      "loss": 1.4118,
+      "step": 237
+    },
+    {
+      "epoch": 0.015387008725904764,
+      "grad_norm": 4.218728065490723,
+      "learning_rate": 9.999275027383826e-06,
+      "loss": 1.371,
+      "step": 238
+    },
+    {
+      "epoch": 0.015451660023072432,
+      "grad_norm": 5.075481414794922,
+      "learning_rate": 9.999257453362903e-06,
+      "loss": 1.3753,
+      "step": 239
+    },
+    {
+      "epoch": 0.015516311320240098,
+      "grad_norm": 4.296051025390625,
+      "learning_rate": 9.999239668895627e-06,
+      "loss": 1.4116,
+      "step": 240
     }
   ],
   "logging_steps": 1,
@@ -1594,7 +1706,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.437989735806894e+17,
+  "total_flos": 1.536003023152988e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null