Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541de50e2e4bf2cd6d0d20a7b06199e726a64a8e256f54c2e7ef3e1e064e80fb
+oid sha256:fd9df1b35cbfb9c2227a4211d01eb6a5e1e875b7158056e946b26eace3630c6b
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9e6e80b376d888ff8f85bdab6153ac0183e1fd6675ffa971361492ff6d661f
+oid sha256:5c0d801a04a82e6e1ff1e8cd097d226490661dc17c2fc3516f9351843637f475
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d8aa60f663ec86834c8d99a6d6d6e46be2240b1212ecfed01f00afa9bdf3cf
+oid sha256:a3da36683a47a91a9ad772f7df43342ed45380cacff56c8d7dcb5142c555aaa0
 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": 0.004168113928447377,
+  "epoch": 0.008336227856894755,
   "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": 39.131,
       "eval_steps_per_second": 19.63,
       "step": 3
+    },
+    {
+      "epoch": 0.0055574852379298365,
+      "grad_norm": 0.7677498459815979,
+      "learning_rate": 8e-05,
+      "loss": 1.5734,
+      "step": 4
+    },
+    {
+      "epoch": 0.0069468565474122956,
+      "grad_norm": 0.7228012084960938,
+      "learning_rate": 0.0001,
+      "loss": 1.553,
+      "step": 5
+    },
+    {
+      "epoch": 0.008336227856894755,
+      "grad_norm": 0.7682281732559204,
+      "learning_rate": 0.00012,
+      "loss": 1.4623,
+      "step": 6
+    },
+    {
+      "epoch": 0.008336227856894755,
+      "eval_loss": 1.5117799043655396,
+      "eval_runtime": 7.8138,
+      "eval_samples_per_second": 38.777,
+      "eval_steps_per_second": 19.453,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 246014599495680.0,
+  "total_flos": 492029198991360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null