Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f4b2413612ff9181690d2771b471f45308f449a468cb305ab3efcf8384a3b9
+oid sha256:999ca600cc7c85ea257be95a84c2783c3052a45b1a9059f1cf72a21318a87617
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9cfe9a64fbec8d8094ee9fd69f79f78eeb20dc238ec50f7a1ce5656099ec0d
+oid sha256:cc4dce7c1d26d91c7eb8ae44b560ec74b699f1fe037eec9125434af5f074cf93
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2ebc62e9336f8068d3625f8376b4f08343cd5fde08ca8c74f25b90076938b7
+oid sha256:ffc4c610dc3671cf5380eba0f4e453c928ccabb11af4f60dfa46b9b63fd7463b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00423998304006784,
+  "epoch": 0.006359974560101759,
   "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": 0.00013090169943749476,
       "loss": 7.1342,
       "step": 18
+    },
+    {
+      "epoch": 0.0044519821920712315,
+      "grad_norm": 1.1358927488327026,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.8089,
+      "step": 21
+    },
+    {
+      "epoch": 0.005087979648081407,
+      "grad_norm": 1.0122755765914917,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.5714,
+      "step": 24
+    },
+    {
+      "epoch": 0.005087979648081407,
+      "eval_loss": 1.7018647193908691,
+      "eval_runtime": 235.9213,
+      "eval_samples_per_second": 8.422,
+      "eval_steps_per_second": 4.213,
+      "step": 24
+    },
+    {
+      "epoch": 0.005723977104091583,
+      "grad_norm": 1.0656787157058716,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.6396,
+      "step": 27
+    },
+    {
+      "epoch": 0.006359974560101759,
+      "grad_norm": 1.0406821966171265,
+      "learning_rate": 0.0,
+      "loss": 6.6495,
+      "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": 2088258615902208.0,
+  "total_flos": 3109852758933504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null