Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd5c519a89d2c83b7066571454406a8d363db57c06cf2fbea1e01f5f6640fce
+oid sha256:1831e0075b7e225174ac540989359463710dd6e5952612baa87b434f559a5e27
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43884c404797bfa04597df84e91370eca0c9975f96bc78fd9a7a2c35cfbe60c
+oid sha256:ab284e395324a339b3f911b01806e07bf343a39cedc14db91a422b5145e8fc2c
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c900d4c6853d677a7868b2838751ed164390e83255a80643445dc284e68bad62
+oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
 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": 0.3007518796992481,
+  "epoch": 0.45112781954887216,
   "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": 302.811,
       "eval_steps_per_second": 151.406,
       "step": 100
+    },
+    {
+      "epoch": 0.3308270676691729,
+      "grad_norm": 0.10568591207265854,
+      "learning_rate": 0.0002,
+      "loss": 10.703,
+      "step": 110
+    },
+    {
+      "epoch": 0.3609022556390977,
+      "grad_norm": 0.10359843820333481,
+      "learning_rate": 0.0002,
+      "loss": 10.6997,
+      "step": 120
+    },
+    {
+      "epoch": 0.39097744360902253,
+      "grad_norm": 0.09477504342794418,
+      "learning_rate": 0.0002,
+      "loss": 10.7039,
+      "step": 130
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.10229877382516861,
+      "learning_rate": 0.0002,
+      "loss": 10.694,
+      "step": 140
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 0.13511568307876587,
+      "learning_rate": 0.0002,
+      "loss": 10.6899,
+      "step": 150
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "eval_loss": 10.677408218383789,
+      "eval_runtime": 0.4665,
+      "eval_samples_per_second": 300.117,
+      "eval_steps_per_second": 150.058,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 16405915238400.0,
+  "total_flos": 24608872857600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null