Training in progress, step 2346, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20491829e0be4b1b4e8e0e277797b9bf1c8ad29983a72101f2fc3f64084fa5b8
+oid sha256:58d08d5813f649ca268303a2d3d99723f498db322c7d97abdf986fed38188910
 size 121537408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:310a9f3c78b1bf175abf83bdf7f5bcbe5a72b117dc5643746a9e552cbaf5b1dc
+oid sha256:a8dcd9d4924db1f69d93c9f0ada617d4c4853ffa26038e01ebda80e0697d084c
 size 61998229

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d835d6083fdb1e5238226cd4cbca157d080c178a650e6d8ecd9ca4cd32b543
+oid sha256:5a7002ad532a6b218e3f05e223230c40b581cc4789ffa87baff71e356b3f6c34
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.55808,
+  "epoch": 3.0,
   "eval_steps": 200,
-  "global_step": 2000,
+  "global_step": 2346,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,48 @@
       "learning_rate": 7.724844167408728e-06,
       "loss": 1.2202,
       "step": 2000
+    },
+    {
+      "epoch": 2.62208,
+      "grad_norm": 3.409816026687622,
+      "learning_rate": 6.6117542297417635e-06,
+      "loss": 1.2307,
+      "step": 2050
+    },
+    {
+      "epoch": 2.68608,
+      "grad_norm": 3.0260939598083496,
+      "learning_rate": 5.4986642920748e-06,
+      "loss": 1.2336,
+      "step": 2100
+    },
+    {
+      "epoch": 2.75008,
+      "grad_norm": 3.358412742614746,
+      "learning_rate": 4.385574354407836e-06,
+      "loss": 1.2232,
+      "step": 2150
+    },
+    {
+      "epoch": 2.81408,
+      "grad_norm": 3.677654981613159,
+      "learning_rate": 3.272484416740873e-06,
+      "loss": 1.2217,
+      "step": 2200
+    },
+    {
+      "epoch": 2.8780799999999997,
+      "grad_norm": 3.050172805786133,
+      "learning_rate": 2.1593944790739096e-06,
+      "loss": 1.2259,
+      "step": 2250
+    },
+    {
+      "epoch": 2.94208,
+      "grad_norm": 3.531214475631714,
+      "learning_rate": 1.0463045414069457e-06,
+      "loss": 1.2241,
+      "step": 2300
     }
   ],
   "logging_steps": 50,
@@ -302,12 +344,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.3883581752743936e+16,
+  "total_flos": 2.796613146217267e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null