Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c19f52762fb89e249f24d1131f876b3ca0b2f2b7d030a981f6c6068fe812962
+oid sha256:dd22062d3c6141b257ed2c228b8eb8df697119355d46843e8f85df2882f1681d
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e209bb2fb484b48d25796544c30929809e236b1f610796c58ba48eeb68a027d4
+oid sha256:6140004b5cd23d82fe86cf4ec52b32c2c5588fc1ac72664e3f4ae3ed7d3eabd3
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bde9187c36bf5ca555d4af62901c73b296315ca3bff4e85e7b53c52c7f64dd1
+oid sha256:f613803e28dc72ed88806f6bbbdd07320170a9c2baa206b6c6824190260aa13d
 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": 0.0003544575249117179,
+  "epoch": 0.0005316862873675769,
   "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": 1.6869,
       "step": 18
+    },
+    {
+      "epoch": 0.00037218040115730383,
+      "grad_norm": 0.7580921649932861,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.6636,
+      "step": 21
+    },
+    {
+      "epoch": 0.0004253490298940615,
+      "grad_norm": 0.5212671756744385,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.5364,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004253490298940615,
+      "eval_loss": 1.564977765083313,
+      "eval_runtime": 2005.6696,
+      "eval_samples_per_second": 11.845,
+      "eval_steps_per_second": 5.923,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004785176586308192,
+      "grad_norm": 0.7111144065856934,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.5786,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005316862873675769,
+      "grad_norm": 0.7312278747558594,
+      "learning_rate": 0.0,
+      "loss": 1.5883,
+      "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": 6693577933455360.0,
+  "total_flos": 1.016432204709888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null