Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1f6a0c184501068692cfe479164043b41f2b48ea41d9208a7d56f38fd21a32
+oid sha256:b6d937f57ba11b7bcdb9a6cee873df5dcda663dbccec9abfd294fc2b5d02de03
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058d165754ad5a50f660c79304c902ad696b944bf511983efbbfdd09fdaa7612
+oid sha256:79c713da0a6959806649735859159ac564501130b65a955cf346fca1a45e0e2b
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab0bb58b755e27ce07d6a7ef69b601abc77d45c748b3994c8fbfe04f2a863734
+oid sha256:a7fdc456dcebcac50af4f55e1db580d067c7e757ee566f54540d35895e7fa369
 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": 0.0026431718061674008,
+  "epoch": 0.0052863436123348016,
   "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": 3.92,
       "eval_steps_per_second": 1.96,
       "step": 3
+    },
+    {
+      "epoch": 0.003524229074889868,
+      "grad_norm": 37.080467224121094,
+      "learning_rate": 8e-05,
+      "loss": 10.3349,
+      "step": 4
+    },
+    {
+      "epoch": 0.004405286343612335,
+      "grad_norm": 34.49464797973633,
+      "learning_rate": 0.0001,
+      "loss": 8.5361,
+      "step": 5
+    },
+    {
+      "epoch": 0.0052863436123348016,
+      "grad_norm": 32.58349609375,
+      "learning_rate": 0.00012,
+      "loss": 8.3812,
+      "step": 6
+    },
+    {
+      "epoch": 0.0052863436123348016,
+      "eval_loss": 7.188342094421387,
+      "eval_runtime": 121.9598,
+      "eval_samples_per_second": 3.919,
+      "eval_steps_per_second": 1.96,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1206357948628992.0,
+  "total_flos": 2412715897257984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null