Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d40be18a8c875493d91c7a97e19cb65fe8f2a8891b8459a63eedd1d4bd4e22
+oid sha256:83a6bdd327156f3b6ed0ff8d5c7d720e1cc862b44a2b9dbec235fc9af08313a1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1b8393fad2a08dde839578e2e29c4a4c94c1b86554c0a32ede5771f4b83376
+oid sha256:0f8faada37eeb7a95ff5315aba1fa40d53bffaac7ec8484ae60128520ef351bf
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a056a23a2b694850733aa8969819c8c578fa33328554e51a9e924a49fd0982
+oid sha256:63606c73c93c05d27e7758139a39e39228c390bd2d751703d97059d8f583fa7f
 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": 0.0011246063877642825,
+  "epoch": 0.0016869095816464238,
   "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": 1.0765,
       "step": 18
+    },
+    {
+      "epoch": 0.0011808367071524967,
+      "grad_norm": 0.5732019543647766,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.9584,
+      "step": 21
+    },
+    {
+      "epoch": 0.001349527665317139,
+      "grad_norm": 0.5618394613265991,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.0454,
+      "step": 24
+    },
+    {
+      "epoch": 0.001349527665317139,
+      "eval_loss": 1.0413671731948853,
+      "eval_runtime": 430.964,
+      "eval_samples_per_second": 17.375,
+      "eval_steps_per_second": 8.688,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015182186234817814,
+      "grad_norm": 0.6845934987068176,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.9827,
+      "step": 27
+    },
+    {
+      "epoch": 0.0016869095816464238,
+      "grad_norm": 0.6820257902145386,
+      "learning_rate": 0.0,
+      "loss": 1.0895,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null