Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b3e4d838d64d822062530c84d8a79c52481413b5f253e7f55a72e7e586efc71
+oid sha256:1bd01f8b907643808cd540a2f68fe07fe9c6ac25f82979164e95b2760bd540bb
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d6704889f8a5bb5ca1509bab591e93d0e08b6f61fce85e0df8525bda730c93
+oid sha256:57ed9b9c3aa841750fe9153bd4c930f2470bdcbab7a2c0eb5124fae0fa857a7c
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
+oid sha256:ca99bebeea385ce2c1d4db38b17f7a71d082f2093a6dc4945fbf7655d2c5b44a
 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": 0.027294438758103036,
+  "epoch": 0.04094165813715456,
   "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": 44.0678,
       "step": 18
+    },
+    {
+      "epoch": 0.028659160696008188,
+      "grad_norm": 2.2774696350097656,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 43.9817,
+      "step": 21
+    },
+    {
+      "epoch": 0.032753326509723645,
+      "grad_norm": 2.248439073562622,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 43.9821,
+      "step": 24
+    },
+    {
+      "epoch": 0.032753326509723645,
+      "eval_loss": 10.980461120605469,
+      "eval_runtime": 1.1906,
+      "eval_samples_per_second": 259.526,
+      "eval_steps_per_second": 130.183,
+      "step": 24
+    },
+    {
+      "epoch": 0.0368474923234391,
+      "grad_norm": 2.1170878410339355,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 43.8709,
+      "step": 27
+    },
+    {
+      "epoch": 0.04094165813715456,
+      "grad_norm": 2.1071853637695312,
+      "learning_rate": 0.0,
+      "loss": 43.9185,
+      "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": 415991070720.0,
+  "total_flos": 623986606080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null