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:e5f7ec9d4fb9f48fb3c053761ce1a6e63f70fb6c0eb1d5a337fc922d03e0d32e
+oid sha256:a884df52d5d497f0cf99ab33bbb9939e2bfc7c572f77288c619db14b3807ea12
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2bff353fe17f01437031b04aacfd0d0e9c0acb9ecc5f701ffba577df69de92
+oid sha256:befb75f8f7c52ae837b85545c28d514e0bade4a0a4bf5eabe9463024129283f3
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee7312ed36813270d0c4465af92d1ab6dcd97ac3785a251ad8cca2bc53326fd
+oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0050526315789473685,
+  "epoch": 0.010105263157894737,
   "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": 97.38,
       "eval_steps_per_second": 48.69,
       "step": 3
+    },
+    {
+      "epoch": 0.006736842105263158,
+      "grad_norm": 36.44790267944336,
+      "learning_rate": 8e-05,
+      "loss": 10.008,
+      "step": 4
+    },
+    {
+      "epoch": 0.008421052631578947,
+      "grad_norm": 28.15861701965332,
+      "learning_rate": 0.0001,
+      "loss": 10.1501,
+      "step": 5
+    },
+    {
+      "epoch": 0.010105263157894737,
+      "grad_norm": 33.711490631103516,
+      "learning_rate": 0.00012,
+      "loss": 10.5486,
+      "step": 6
+    },
+    {
+      "epoch": 0.010105263157894737,
+      "eval_loss": 2.9084646701812744,
+      "eval_runtime": 2.5795,
+      "eval_samples_per_second": 96.916,
+      "eval_steps_per_second": 48.458,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26318569734144.0,
+  "total_flos": 52637139468288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null