Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65bb239781bfc8ca6941c6181fb311d42df41989d824e2e2c4d4090efc9e5600
+oid sha256:f69e9ad809e02b190cf733436990a68040e6761cb0b66f585226f2f156366c59
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7baff0ebf99579de6e9adccc0d9c61495ef075a2857116212ab874f4a2d0aa08
+oid sha256:551f5ddcd567e9fcdea1e5f8a456a61f4421bb56816507e3ca96ba41ec32f7c3
 size 239766722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b835124e9438a67b4922362546d9917dd2ad1ecf9964a45797b5ccba615a520
+oid sha256:4f29e05bcbde75ce27a9713f89d1d62332544e44f262dd85c2f7f43afaa9c494
 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": 0.000644361035488184,
+  "epoch": 0.0009665415532322761,
   "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": 1.0285,
       "step": 18
+    },
+    {
+      "epoch": 0.0006765790872625933,
+      "grad_norm": 0.6982560753822327,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.9894,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007732332425858208,
+      "grad_norm": 0.5578031539916992,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.906,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007732332425858208,
+      "eval_loss": 0.925150454044342,
+      "eval_runtime": 950.9141,
+      "eval_samples_per_second": 13.744,
+      "eval_steps_per_second": 6.872,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008698873979090484,
+      "grad_norm": 0.4861893653869629,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.9067,
+      "step": 27
+    },
+    {
+      "epoch": 0.0009665415532322761,
+      "grad_norm": 0.6888020634651184,
+      "learning_rate": 0.0,
+      "loss": 0.9166,
+      "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": 2757139491717120.0,
+  "total_flos": 4135709237575680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null