Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835cc8cacb65721246f97e68fe845d5a8f04ac07e17e6017c73656b547806165
+oid sha256:ce4f4ba7ba9094dbb92cd519c1c22466954a5c9fa5daf0decd2c34d91bc353f9
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898e6f37cb7d0e4993992eddc75da89d80ffd798987bb15ffb25081060421ea9
+oid sha256:b20bc179b46c85c2f6cc7a092e0e7ce3ac0df3e41196e7c313be7a8dc8b390d3
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04474c64fc34f53d1b9c9b1bcee379925e4fc8de4f9074423188b4c3ac46e52c
+oid sha256:9c5d64ef5ff15211b07bb186d95342e13173abafc510cd1ffca0fd6b19a5938d
 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": 0.004232132465746178,
+  "epoch": 0.006348198698619267,
   "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": 11.4418,
       "step": 18
+    },
+    {
+      "epoch": 0.004443739089033487,
+      "grad_norm": 5.8854804039001465,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 9.2159,
+      "step": 21
+    },
+    {
+      "epoch": 0.005078558958895413,
+      "grad_norm": 4.918722152709961,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 9.2527,
+      "step": 24
+    },
+    {
+      "epoch": 0.005078558958895413,
+      "eval_loss": 2.3335814476013184,
+      "eval_runtime": 130.247,
+      "eval_samples_per_second": 15.279,
+      "eval_steps_per_second": 7.639,
+      "step": 24
+    },
+    {
+      "epoch": 0.00571337882875734,
+      "grad_norm": 6.152263641357422,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 9.319,
+      "step": 27
+    },
+    {
+      "epoch": 0.006348198698619267,
+      "grad_norm": 5.067956924438477,
+      "learning_rate": 0.0,
+      "loss": 8.7047,
+      "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": 5777796587520000.0,
+  "total_flos": 8738917338624000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null