Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967af943b35171535a1c1831423fdcda5e1e13b08bd86f4f263a565521c5b511
+oid sha256:fa17b6750abed3869b7c55b698a8c86aa214ebbe45fd1c4d8bdeb6837f989b33
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42f013731e67a772a759009545e15767f582f3215fdc0102548b076a4aa5ecf
+oid sha256:b682ce08bc14065df5c5af2d4180bf77611d765940aaf8eb829113453e8dce77
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b663b5eda4d0da2dcb843509e2c21a870da154750c8ea7d398f43a7e0cf8632
+oid sha256:27e83968c2d0fcbd9ce3decdbd850180096a3c3813ec3f1e2e7fbcdcb1b335e3
 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": 0.000487685930260912,
+  "epoch": 0.000975371860521824,
   "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": 37.431,
       "eval_steps_per_second": 18.723,
       "step": 3
+    },
+    {
+      "epoch": 0.0006502479070145493,
+      "grad_norm": 1.5695548057556152,
+      "learning_rate": 8e-05,
+      "loss": 8.7696,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008128098837681866,
+      "grad_norm": 1.080654501914978,
+      "learning_rate": 0.0001,
+      "loss": 7.2986,
+      "step": 5
+    },
+    {
+      "epoch": 0.000975371860521824,
+      "grad_norm": 1.2302272319793701,
+      "learning_rate": 0.00012,
+      "loss": 7.6666,
+      "step": 6
+    },
+    {
+      "epoch": 0.000975371860521824,
+      "eval_loss": 2.0656354427337646,
+      "eval_runtime": 69.4387,
+      "eval_samples_per_second": 37.313,
+      "eval_steps_per_second": 18.664,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 489743409217536.0,
+  "total_flos": 979486818435072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null