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:edd5e7fe1eb5008ef56eee0e0dc6e39fe3ceaea184a785d3df9e951575566d84
+oid sha256:7f7ae285be134647831790785448de58bcd4ded6b9cc2d5771c0500d7eef8404
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086226b2d838f61d62271a0836e73ca08e5b2a7d1a79b50902f69ef96af9664f
+oid sha256:ef268ad9fec28b4bb9636f28e26b4060e8bfdc6662476f89bab1268f5c6abcdd
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410be6df0646013ba0f713fe94ab31bb189826dffd97de94439dfb15d4469389
+oid sha256:a404e8017e5eb30c09159968627e0b9dfb05483324555b8a1e1d92d9cf71c2f7
 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": 0.6722689075630253,
+  "epoch": 1.0168067226890756,
   "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": 3.0599,
       "step": 18
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 29.74368667602539,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.8724,
+      "step": 21
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": 23.864553451538086,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.6777,
+      "step": 24
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "eval_loss": 0.6330844163894653,
+      "eval_runtime": 0.2706,
+      "eval_samples_per_second": 48.05,
+      "eval_steps_per_second": 25.873,
+      "step": 24
+    },
+    {
+      "epoch": 0.907563025210084,
+      "grad_norm": 26.351696014404297,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.5018,
+      "step": 27
+    },
+    {
+      "epoch": 1.0168067226890756,
+      "grad_norm": 19.887985229492188,
+      "learning_rate": 0.0,
+      "loss": 2.4856,
+      "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": 354006639575040.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null