Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053ee7b29d2412289e2d6bfe72f83395cf3c64acbb4ddfc21a3d87e98713d399
+oid sha256:696c2ddac33dbcd7b80e4291da7c8c125ce665e0284034fb7317a703d809a058
 size 474329096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a3012ffc4f603ebf0da9ae7388ceedd4aee52a916be608be0c96829c04c985
+oid sha256:b3768082765cf692fbab16c614a37a1edd4ccdf66ad058ec3fba40ba692790e4
 size 151500495

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2e998ffac771e9013035bcd833a2d91b2a5adf38fbc6439bf0771b153525115
+oid sha256:c9b990a594defede5a7e96cd94774813bcab48e4eef9fd509cc65a122207bfc2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.039085401602501464,
+  "epoch": 0.07817080320500293,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,6 +78,76 @@
       "learning_rate": 7.734375e-05,
       "loss": 3.4841968536376955,
       "step": 100
+    },
+    {
+      "epoch": 0.04299394176275161,
+      "grad_norm": 21.948543548583984,
+      "learning_rate": 8.515625e-05,
+      "loss": 3.5636287689208985,
+      "step": 110
+    },
+    {
+      "epoch": 0.04690248192300176,
+      "grad_norm": 5.58203125,
+      "learning_rate": 9.296875e-05,
+      "loss": 2.957254981994629,
+      "step": 120
+    },
+    {
+      "epoch": 0.0508110220832519,
+      "grad_norm": 2.311690330505371,
+      "learning_rate": 0.00010078125,
+      "loss": 2.8846551895141603,
+      "step": 130
+    },
+    {
+      "epoch": 0.05471956224350205,
+      "grad_norm": 3.563748598098755,
+      "learning_rate": 0.00010859375000000001,
+      "loss": 3.3207424163818358,
+      "step": 140
+    },
+    {
+      "epoch": 0.0586281024037522,
+      "grad_norm": 2.694491147994995,
+      "learning_rate": 0.00011640625,
+      "loss": 3.001876449584961,
+      "step": 150
+    },
+    {
+      "epoch": 0.06253664256400235,
+      "grad_norm": 4.056739807128906,
+      "learning_rate": 0.00012421875,
+      "loss": 3.2485610961914064,
+      "step": 160
+    },
+    {
+      "epoch": 0.0664451827242525,
+      "grad_norm": 4.93998908996582,
+      "learning_rate": 0.00013203125000000001,
+      "loss": 3.2433551788330077,
+      "step": 170
+    },
+    {
+      "epoch": 0.07035372288450263,
+      "grad_norm": 4.614671230316162,
+      "learning_rate": 0.00013984375,
+      "loss": 3.1572134017944338,
+      "step": 180
+    },
+    {
+      "epoch": 0.07426226304475278,
+      "grad_norm": 1.8324024677276611,
+      "learning_rate": 0.00014765625,
+      "loss": 2.9814380645751952,
+      "step": 190
+    },
+    {
+      "epoch": 0.07817080320500293,
+      "grad_norm": 2.2585086822509766,
+      "learning_rate": 0.00015546875,
+      "loss": 3.5383621215820313,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -97,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8452495269366784e+16,
+  "total_flos": 5.753012541967411e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null