Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eeee4860240051d5da8058db7745ba5f6462e84938dc60a2e6aaa613defebbd
+oid sha256:8794c42f7aa23d99b63f86664a31bdcb87f7e76cc7776215442a328fc204917d
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ec3981b1a8e74efa5280af2fd85acc10341811b8602877bea226d978f688c8
+oid sha256:d3c639d8b67a1799045a61609c1fc5e8644dc68802e0c0a9c5e6141608d65717
 size 40131268

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4d7269bb9ae43f3a5821e97eb340225aae805bff1c8a28eaa0aeaa54b175be
+oid sha256:d85c5e3e589dfdf3eb8679de9d5cf33e0165cd6aeb13a8f2940235bf86350900
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008633093525179856,
+  "epoch": 0.017266187050359712,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 10.273,
       "eval_steps_per_second": 10.273,
       "step": 3
+    },
+    {
+      "epoch": 0.011510791366906475,
+      "grad_norm": Infinity,
+      "learning_rate": 6e-05,
+      "loss": 6.9544,
+      "step": 4
+    },
+    {
+      "epoch": 0.014388489208633094,
+      "grad_norm": 37.38779067993164,
+      "learning_rate": 8e-05,
+      "loss": 6.7915,
+      "step": 5
+    },
+    {
+      "epoch": 0.017266187050359712,
+      "grad_norm": 31.44697380065918,
+      "learning_rate": 0.0001,
+      "loss": 5.4368,
+      "step": 6
+    },
+    {
+      "epoch": 0.017266187050359712,
+      "eval_loss": 3.5580296516418457,
+      "eval_runtime": 7.235,
+      "eval_samples_per_second": 10.228,
+      "eval_steps_per_second": 10.228,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 590265207226368.0,
+  "total_flos": 1180530414452736.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null