Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732ac2e788a562daf3be0c1048dff85b6b85940947d7cbbeeb6804eef14397f3
+oid sha256:77a3d262929a48dc20b612a92082dfa395858a28053977da4fe954d03ef6db18
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb66384576ee212c250beaa561c3784493d57f62985870903a7d8c452dcaad8
+oid sha256:b1bf8180eff8cef94027594309319a9d73be150019e18c2629fb5d2780b676bc
 size 264440954

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a105955d745909363bccb3708cf208b8b2a4904b9be8151e1819366a9c06d818
+oid sha256:9c8ba5accb44246d730288ff07b57497fe5f3b5025d74d3cadb3f0b656179292
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003305238803503553,
+  "epoch": 0.00495785820525533,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 7.5361,
       "step": 18
+    },
+    {
+      "epoch": 0.0034705007436787306,
+      "grad_norm": 5.870885848999023,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 7.3992,
+      "step": 21
+    },
+    {
+      "epoch": 0.0039662865642042635,
+      "grad_norm": 5.5092949867248535,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.8797,
+      "step": 24
+    },
+    {
+      "epoch": 0.0039662865642042635,
+      "eval_loss": 1.7399580478668213,
+      "eval_runtime": 333.8116,
+      "eval_samples_per_second": 7.633,
+      "eval_steps_per_second": 3.817,
+      "step": 24
+    },
+    {
+      "epoch": 0.004462072384729797,
+      "grad_norm": 6.92725944519043,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 7.2091,
+      "step": 27
+    },
+    {
+      "epoch": 0.00495785820525533,
+      "grad_norm": 6.732820987701416,
+      "learning_rate": 0.0,
+      "loss": 6.9546,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5777796587520000.0,
+  "total_flos": 8738917338624000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null