Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fcd40c6cd4bfaae156f30e69e10c1aac099df2aaf29d1896c16e278a1e78d89
+oid sha256:b9bb98103ff94a94cebd4450bbabfd594cfd6252227c249044e58db6ba5860b1
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0335cc0c9131099ae075a5df0c1f2abf2133d4c380c3c012d9412999d70caf1e
+oid sha256:46f083d3618c447f6a58b857b0caefcecefa586d5ae63a36ae33a2e2c8ecb604
 size 27002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
+oid sha256:eed7443db706351be6dd27431c0a74aab9cc8fb80aac1c56005e8e16b28688cb
 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": 0.007209805335255948,
+  "epoch": 0.010814708002883922,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 68.942,
       "eval_steps_per_second": 34.5,
       "step": 20
+    },
+    {
+      "epoch": 0.007570295602018745,
+      "grad_norm": 1.9149787476635538e-05,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 46.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.008651766402307137,
+      "grad_norm": 2.979295823024586e-05,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 46.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.009012256669069935,
+      "eval_loss": 11.5,
+      "eval_runtime": 16.6576,
+      "eval_samples_per_second": 70.178,
+      "eval_steps_per_second": 35.119,
+      "step": 25
+    },
+    {
+      "epoch": 0.00973323720259553,
+      "grad_norm": 1.7904030755744316e-05,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 46.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.010814708002883922,
+      "grad_norm": 2.0520408725133166e-05,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.010814708002883922,
+      "eval_loss": 11.5,
+      "eval_runtime": 16.9066,
+      "eval_samples_per_second": 69.145,
+      "eval_steps_per_second": 34.602,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1236778745856.0,
+  "total_flos": 1954908340224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null