Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb24c1a5ce2dcbd2a174e0afb01b78a95bb3e1e7994d70c9fcc09492977657b
+oid sha256:69b2ad2f0bede0d854d1bdd8dfa37e1e582ba2a1d68ba6e4c92ee53b9929329e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a5569b098692f9b20d3704c89790271a570c4ddfa4638dee910768b6fbd603a
+oid sha256:388a59562894bd1ed1cad1f074d9ce0d68e221b2f34fef6e55a82c8554494313
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1992109d976de42b482bc8a451a56f55fae3f8b1181688e040d434f8eee78156
+oid sha256:48e7e67f60697ef750d984765ede1a16d11367caa01be162071daf6ac56a114e
 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": 0.006359300476947536,
+  "epoch": 0.009538950715421303,
   "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": 14.4,
       "eval_steps_per_second": 7.2,
       "step": 6
+    },
+    {
+      "epoch": 0.007419183889772125,
+      "grad_norm": 0.9638036489486694,
+      "learning_rate": 0.00014,
+      "loss": 6.2643,
+      "step": 7
+    },
+    {
+      "epoch": 0.008479067302596715,
+      "grad_norm": 1.229278326034546,
+      "learning_rate": 0.00016,
+      "loss": 6.0166,
+      "step": 8
+    },
+    {
+      "epoch": 0.009538950715421303,
+      "grad_norm": 1.4966942071914673,
+      "learning_rate": 0.00018,
+      "loss": 5.9872,
+      "step": 9
+    },
+    {
+      "epoch": 0.009538950715421303,
+      "eval_loss": 1.4243505001068115,
+      "eval_runtime": 27.6135,
+      "eval_samples_per_second": 14.413,
+      "eval_steps_per_second": 7.207,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1954499090448384.0,
+  "total_flos": 2931748635672576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null