Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a42e55daa8cc1fee1f47d7d587c3012e68565df8e389493ecbb9f9e4b2154d
+oid sha256:63d1004c1ca522a17daf011a6c1c6f4c9146513ba91dba2220601d3e2924b110
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88098c94329ee387b9855d956d3b12e93c1b967523f1245fbec3e595556a3b3
+oid sha256:47b8c5f152e7ab513387c2dfc9aaa950fcb2ff6706070cd6b8ceca0761db1490
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6be1a01f43622ea2c9fefe62a5948187f60e2cc6073cda9324096d39270e1c
+oid sha256:3aa60f907bcefc96d1ee550fde6bc3108be15094e4e4a02313b3665f538037f7
 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": 0.06256517205422316,
+  "epoch": 0.09384775808133472,
   "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": 2.0277,
       "step": 18
+    },
+    {
+      "epoch": 0.06569343065693431,
+      "grad_norm": 0.7185098528862,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.9239,
+      "step": 21
+    },
+    {
+      "epoch": 0.07507820646506778,
+      "grad_norm": 0.76585453748703,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.9982,
+      "step": 24
+    },
+    {
+      "epoch": 0.07507820646506778,
+      "eval_loss": 2.0088443756103516,
+      "eval_runtime": 14.7377,
+      "eval_samples_per_second": 13.706,
+      "eval_steps_per_second": 6.853,
+      "step": 24
+    },
+    {
+      "epoch": 0.08446298227320125,
+      "grad_norm": 0.8107510805130005,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.0522,
+      "step": 27
+    },
+    {
+      "epoch": 0.09384775808133472,
+      "grad_norm": 0.7503340244293213,
+      "learning_rate": 0.0,
+      "loss": 1.9216,
+      "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": 3015894871572480.0,
+  "total_flos": 4574107221884928.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null