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:d7be764c65a4a4d4b8911eee2e956ab6f20d145714f83b453ec529c863235ded
+oid sha256:56620057c026e5aaa9b59a390e5b711b313a564e639a41bcb3fb80d7526a25f0
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef5d1000c49387fcdeda0a71cd720b83e2b30313c50526700b7ae8772cce067
+oid sha256:50fc5aded924fb9027edd6cdbd1893e5295121c5567506f834b5a808fa779b9b
 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": 0.00019560858721697882,
+  "epoch": 0.00039121717443395764,
   "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": 35.962,
       "eval_steps_per_second": 17.981,
       "step": 3
+    },
+    {
+      "epoch": 0.00026081144962263844,
+      "grad_norm": 3.0716772079467773,
+      "learning_rate": 8e-05,
+      "loss": 12.9326,
+      "step": 4
+    },
+    {
+      "epoch": 0.00032601431202829807,
+      "grad_norm": 2.6990952491760254,
+      "learning_rate": 0.0001,
+      "loss": 11.8885,
+      "step": 5
+    },
+    {
+      "epoch": 0.00039121717443395764,
+      "grad_norm": 3.010658025741577,
+      "learning_rate": 0.00012,
+      "loss": 12.3449,
+      "step": 6
+    },
+    {
+      "epoch": 0.00039121717443395764,
+      "eval_loss": 3.029665231704712,
+      "eval_runtime": 179.8671,
+      "eval_samples_per_second": 35.904,
+      "eval_steps_per_second": 17.952,
+      "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