Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59cc6aa6a1d3c2c636598b79936bc6380eab8235a86268ff9f990f524c0c5ad1
+oid sha256:9e2d045eaab4029183eab70110d8da3a86dc6cb5209c5cc347ea121d1a936c72
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c028f7601118b2bd8c47eb538c6b33defba5fa1b70a0d65daf1b941292a3526
+oid sha256:7863d2269a7112a9c0b5bd7ef8ce9ab88c2821d0aec17ba71898ede04a66525b
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ee9f6de2b9ee624ff80b759246f40d41488a67fe89de42af5ec5b550940b44
+oid sha256:c759f42a01f02ae1bf6251843b485f7d03c067e185dac44a3f25dadcdf3ce264
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016351892731583682,
+  "epoch": 0.02452783909737552,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 62.696,
       "eval_steps_per_second": 31.36,
       "step": 100
+    },
+    {
+      "epoch": 0.01798708200474205,
+      "grad_norm": 0.9787514805793762,
+      "learning_rate": 0.0002,
+      "loss": 1.6154,
+      "step": 110
+    },
+    {
+      "epoch": 0.019622271277900418,
+      "grad_norm": 1.1637746095657349,
+      "learning_rate": 0.0002,
+      "loss": 1.7687,
+      "step": 120
+    },
+    {
+      "epoch": 0.021257460551058784,
+      "grad_norm": 1.1354658603668213,
+      "learning_rate": 0.0002,
+      "loss": 1.6996,
+      "step": 130
+    },
+    {
+      "epoch": 0.022892649824217154,
+      "grad_norm": 0.9611806869506836,
+      "learning_rate": 0.0002,
+      "loss": 1.7219,
+      "step": 140
+    },
+    {
+      "epoch": 0.02452783909737552,
+      "grad_norm": 1.4163100719451904,
+      "learning_rate": 0.0002,
+      "loss": 1.6983,
+      "step": 150
+    },
+    {
+      "epoch": 0.02452783909737552,
+      "eval_loss": 1.7236453294754028,
+      "eval_runtime": 40.9926,
+      "eval_samples_per_second": 62.816,
+      "eval_steps_per_second": 31.42,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 890381638041600.0,
+  "total_flos": 1335572457062400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null