Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4404b24076cc63d331e67d7ba3a7fe9520f7a0e8f6d4b52270bfbfafc9664489
+oid sha256:2832e178fbfc4fe2fb481e79a8d919fe407032c53cea12f332a1381234b6f1c4
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d619ba6794210f6129f2e991bb4cca6fb744cc687fb23c48cd2119fe42dacaae
+oid sha256:cbcd49ec20bf55444feca0578bd6f0012b99c1072af990df00376b5d58929f87
 size 281829907

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:417227e46f0a581722968d781d8ea2ba8688c7892e0d69749745f185230daf6a
+oid sha256:994855e9f3bb291ce54dbed25621bf0ab9b11111a5f95765ed4ae5933e96cbd7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f9c1a66b0f67830f363d7aa55a784bfca1310ea07876b83a0f2f54a5722f96
+oid sha256:2cea2e56a8bde12e649a1d7cae49ed9d38ef81a2916cebf53379e47210c432c6
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0666666666666667,
+  "epoch": 1.6,
   "eval_steps": 100,
-  "global_step": 80,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,70 @@
       "learning_rate": 0.0004110276028625994,
       "loss": 0.4856,
       "step": 80
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.1001599058508873,
+      "learning_rate": 0.00039568525901157527,
+      "loss": 0.4632,
+      "step": 85
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.09839078038930893,
+      "learning_rate": 0.0003794624062245813,
+      "loss": 0.5097,
+      "step": 90
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.102094367146492,
+      "learning_rate": 0.000362457094001909,
+      "loss": 0.4476,
+      "step": 95
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.11247370392084122,
+      "learning_rate": 0.00034477210096009486,
+      "loss": 0.4919,
+      "step": 100
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_loss": 0.506523609161377,
+      "eval_runtime": 45.0985,
+      "eval_samples_per_second": 0.377,
+      "eval_steps_per_second": 0.377,
+      "step": 100
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.10984684526920319,
+      "learning_rate": 0.00032651431364697186,
+      "loss": 0.3816,
+      "step": 105
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.10393229871988297,
+      "learning_rate": 0.0003077940805287425,
+      "loss": 0.4784,
+      "step": 110
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.11296918988227844,
+      "learning_rate": 0.00028872454505352117,
+      "loss": 0.4422,
+      "step": 115
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.10333701968193054,
+      "learning_rate": 0.0002694209618222516,
+      "loss": 0.4828,
+      "step": 120
     }
   ],
   "logging_steps": 5,
@@ -139,7 +203,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2644590082129920.0,
+  "total_flos": 3966885123194880.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null