Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48db73ff0abb0aa0af33c84cca494a65adc7ce42afdce2acda24b28aafb869cf
+oid sha256:081efc5cffcc9771a1e0f355a6db4f175864cd96b85c62390f366e280fb2c83a
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37c8efcf1002b75067a2b07351c0feab70b5e71308258a9e9023a1da6b45f228
+oid sha256:6b6bb6df0e6c8c367ddc484cfe98bf8989f34cb197733bf320fa07a2f2d53ea4
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de830288606b38e6cfca5b625f3b4e9a64b2aee6f091f612490c0af98ad6b5b
+oid sha256:6f33eab43f94c54c28d44f815245195ca47f5bccffb6fd58d916729befff7f8a
 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": 0.004642794962567465,
+  "epoch": 0.006964192443851198,
   "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": 2.3763,
       "step": 18
+    },
+    {
+      "epoch": 0.004874934710695839,
+      "grad_norm": 2.4084312915802,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.3294,
+      "step": 21
+    },
+    {
+      "epoch": 0.005571353955080959,
+      "grad_norm": 3.027545690536499,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.6611,
+      "step": 24
+    },
+    {
+      "epoch": 0.005571353955080959,
+      "eval_loss": 2.306494951248169,
+      "eval_runtime": 62.409,
+      "eval_samples_per_second": 29.066,
+      "eval_steps_per_second": 14.533,
+      "step": 24
+    },
+    {
+      "epoch": 0.006267773199466079,
+      "grad_norm": 2.319289207458496,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.2589,
+      "step": 27
+    },
+    {
+      "epoch": 0.006964192443851198,
+      "grad_norm": 2.523486375808716,
+      "learning_rate": 0.0,
+      "loss": 2.2499,
+      "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": 967722569564160.0,
+  "total_flos": 1451583854346240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null