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:c08076ca3c7735b300728b9e7fa0aae79cf9e342bb6439df5d97f61404f6efdb
+oid sha256:c3465d2ac1a8ca5f49fee0d1e3a4251607d06746605a46664ad8b271a83ab7c1
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3567d45eb91c163c751004dfdf68d0b2ea641201553e1454fc29f1b50e6bf3
+oid sha256:a6907e632c6a08aeb4b7fe3f530899af645fa5d7dda00a8917a49b23d1ea89a3
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e24d535c5c1523f0486038b5930228f33566ca520ba04d10e88741a42965211
+oid sha256:a098dffa38fa9c01aae74eebd50d55d442f41711e114eb99ba341d13be3779bf
 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": 0.0025548494235620987,
+  "epoch": 0.0038322741353431482,
   "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": 4.3663,
       "step": 18
+    },
+    {
+      "epoch": 0.0026825918947402036,
+      "grad_norm": 9.319868087768555,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.7561,
+      "step": 21
+    },
+    {
+      "epoch": 0.0030658193082745188,
+      "grad_norm": 7.558574199676514,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.6226,
+      "step": 24
+    },
+    {
+      "epoch": 0.0030658193082745188,
+      "eval_loss": 0.8786661624908447,
+      "eval_runtime": 183.5815,
+      "eval_samples_per_second": 17.959,
+      "eval_steps_per_second": 8.982,
+      "step": 24
+    },
+    {
+      "epoch": 0.0034490467218088335,
+      "grad_norm": 27.973899841308594,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.2881,
+      "step": 27
+    },
+    {
+      "epoch": 0.0038322741353431482,
+      "grad_norm": 6.591433048248291,
+      "learning_rate": 0.0,
+      "loss": 3.661,
+      "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": 6534582019031040.0,
+  "total_flos": 9801873028546560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null