Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4e4f4f368e401b1dfb1c7711bc1d1011e8ad010d32e2b41f3c4ab3f6714cb6
+oid sha256:7456be62a4877d4fc6e72b5af80d3e09c3ddb2eb466a92ffb445d138b56f6aae
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6041879186e4d9b1b8c5c34bf8bb79bb5b785523b0192dae75e6db7446c5f9
+oid sha256:e0c0487157ccd2dabb3b0a76043034934814376ca83c19572478d65b65ce333b
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b52214f9bd9fd90e146416d19db727ff822d3ff4dfe457467cf1dd46cfde3948
+oid sha256:5da98638b5afea10e0de2f4fc87452ede8bc4b95ee5e48c3293a3388722f1e2e
 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": 0.0014119058964720001,
+  "epoch": 0.0021178588447080004,
   "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": 9.158,
       "step": 18
+    },
+    {
+      "epoch": 0.0014825011912956002,
+      "grad_norm": 1.2306267023086548,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 9.464,
+      "step": 21
+    },
+    {
+      "epoch": 0.0016942870757664001,
+      "grad_norm": 1.0889095067977905,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 9.4374,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016942870757664001,
+      "eval_loss": 2.303675889968872,
+      "eval_runtime": 669.5487,
+      "eval_samples_per_second": 8.909,
+      "eval_steps_per_second": 4.455,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019060729602372003,
+      "grad_norm": 0.9970927238464355,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 8.9337,
+      "step": 27
+    },
+    {
+      "epoch": 0.0021178588447080004,
+      "grad_norm": 1.0527116060256958,
+      "learning_rate": 0.0,
+      "loss": 9.2766,
+      "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": 1.26956599246848e+16,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null