Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a2c237308577c12f2bd60b99b56367cf64a37f14cfa7fa7ef21f746bed9ae5
+oid sha256:6516c0187a6701ed4ae04e236bc64e315c66fceaed1559555b196ebc309cddc5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d60163084377634719f48ce1c687bea1a36d675b36393419b3c36bded9c9ab
+oid sha256:144191a261cc9161f3923ed66bd267c561fe1103462219b5004ef6e43b20c350
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df7a7c548661260df026af22e850190c6e0e825fcd4f3951c3661d2bae55f7a
+oid sha256:4b0bb5f15c5d4d38191f8ad2d0c875ec20e57010578224dd08ee2c3baa59fa96
 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": 0.013691596782474755,
+  "epoch": 0.020537395173712135,
   "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": 0.6944,
       "step": 18
+    },
+    {
+      "epoch": 0.014376176621598494,
+      "grad_norm": 0.6650722026824951,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.6943,
+      "step": 21
+    },
+    {
+      "epoch": 0.016429916138969707,
+      "grad_norm": 0.8915995359420776,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.6703,
+      "step": 24
+    },
+    {
+      "epoch": 0.016429916138969707,
+      "eval_loss": 0.7271555066108704,
+      "eval_runtime": 53.6434,
+      "eval_samples_per_second": 11.465,
+      "eval_steps_per_second": 5.742,
+      "step": 24
+    },
+    {
+      "epoch": 0.01848365565634092,
+      "grad_norm": 0.6706926226615906,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.6565,
+      "step": 27
+    },
+    {
+      "epoch": 0.020537395173712135,
+      "grad_norm": 0.47476261854171753,
+      "learning_rate": 0.0,
+      "loss": 0.622,
+      "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": 7697080566939648.0,
+  "total_flos": 1.1499252895186944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null