Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca9de97e186b636a7aab469ea42cc3299e04e2cd7b95b7e090cbe514aa78ff5
+oid sha256:65093a3c85a5c05b20fa6abab827bd353692eab57db9c47c096fc191d8f5b94a
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd4e635c95b672009a050d508c24fe72980ea6982467d3d0fabd2dc3118c038
+oid sha256:fff51b00fdd47622bf2714e9b56c5d80e75fd10508891a8b08c0c5cb56a28b13
 size 136814

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": 0.009180628873077806,
+  "epoch": 0.013770943309616708,
   "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": 358.808,
       "eval_steps_per_second": 179.404,
       "step": 20
+    },
+    {
+      "epoch": 0.009639660316731696,
+      "grad_norm": 1.4532055854797363,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 44.1706,
+      "step": 21
+    },
+    {
+      "epoch": 0.011016754647693368,
+      "grad_norm": 1.2766399383544922,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 44.215,
+      "step": 24
+    },
+    {
+      "epoch": 0.011475786091347258,
+      "eval_loss": 11.048693656921387,
+      "eval_runtime": 2.7201,
+      "eval_samples_per_second": 337.49,
+      "eval_steps_per_second": 168.745,
+      "step": 25
+    },
+    {
+      "epoch": 0.012393848978655038,
+      "grad_norm": 1.5444846153259277,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 44.1775,
+      "step": 27
+    },
+    {
+      "epoch": 0.013770943309616708,
+      "grad_norm": 1.5085878372192383,
+      "learning_rate": 0.0,
+      "loss": 44.2091,
+      "step": 30
+    },
+    {
+      "epoch": 0.013770943309616708,
+      "eval_loss": 11.04821491241455,
+      "eval_runtime": 2.6777,
+      "eval_samples_per_second": 342.83,
+      "eval_steps_per_second": 171.415,
+      "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": 37434163200.0,
+  "total_flos": 56151244800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null