Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71b091e0a662ec4a1e35479c0a41efbe22813cc18bd6b2b564caf946071b430
+oid sha256:a6f0111be9a8c907ca40016bd9b78bc69fb711439764cfe20eae85a248504b48
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca1e84f335e7a41c291732509c20818b042b6f86e21b6d547934767ae4a08e7
+oid sha256:28ae19fa8b99403bbeb4ef3f55d75c5bd05ddda6bc56edaa66dc94375286e20b
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015873015873015872,
+  "epoch": 0.023809523809523808,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 338.866,
       "eval_steps_per_second": 169.433,
       "step": 6
+    },
+    {
+      "epoch": 0.018518518518518517,
+      "grad_norm": 0.22394391894340515,
+      "learning_rate": 0.00014,
+      "loss": 10.8425,
+      "step": 7
+    },
+    {
+      "epoch": 0.021164021164021163,
+      "grad_norm": 0.2672518789768219,
+      "learning_rate": 0.00016,
+      "loss": 10.8437,
+      "step": 8
+    },
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 0.22409218549728394,
+      "learning_rate": 0.00018,
+      "loss": 10.8279,
+      "step": 9
+    },
+    {
+      "epoch": 0.023809523809523808,
+      "eval_loss": 10.839607238769531,
+      "eval_runtime": 0.467,
+      "eval_samples_per_second": 342.601,
+      "eval_steps_per_second": 171.301,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 820295761920.0,
+  "total_flos": 1168921460736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null