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:c86266da51badc4b5e664ae557c2ee452ce2b4efb7a8933743c545229e1d9b3d
+oid sha256:1f3d51275c5d9bb0d43047f680b5d2db1e27823491857e24698f5550397124e6
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af7e79b34efd1c51fac8a459363e0be1fd290be0e80709eb999eda77ddccfa7
+oid sha256:58a13787a56cae20b69e4c87686bfa1d843ba6a8ad91756580bc7bc0ab3b2716
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 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": 0.00010597430123195125,
+  "epoch": 0.0002119486024639025,
   "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": 237.029,
       "eval_steps_per_second": 118.514,
       "step": 3
+    },
+    {
+      "epoch": 0.00014129906830926835,
+      "grad_norm": 0.250560462474823,
+      "learning_rate": 8e-05,
+      "loss": 10.8422,
+      "step": 4
+    },
+    {
+      "epoch": 0.00017662383538658542,
+      "grad_norm": 0.14231401681900024,
+      "learning_rate": 0.0001,
+      "loss": 10.8284,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002119486024639025,
+      "grad_norm": 0.14842887222766876,
+      "learning_rate": 0.00012,
+      "loss": 10.8331,
+      "step": 6
+    },
+    {
+      "epoch": 0.0002119486024639025,
+      "eval_loss": 10.839518547058105,
+      "eval_runtime": 67.283,
+      "eval_samples_per_second": 177.162,
+      "eval_steps_per_second": 88.581,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 246088728576.0,
+  "total_flos": 492177457152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null