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:e15be6654f891cd862c42fde2ce9de8c5cc147ee08789b27e047487065a267a2
+oid sha256:14f5c981156d6e93b33c4ca7a12817bf8dc5aebd07a0b4b4292e07629e4d63ef
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e4c837fe2094dec2a36e68d45c7e4b9a753205f5d205d0f8e14149bb68f18a
+oid sha256:3b552a32a3dd3976b9f9d7036ad6ac6430abda7057e44f21652439a7fe1eb71c
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f443aa61c0b62c8ce46a45f05c924349ef1098c9769a4e87bef2a843ccd40e1d
+oid sha256:049ef9d402621f8d67191fa7981b9705ec1748fcb4431765ca3a28fee3882315
 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": 8.221317877255724e-05,
+  "epoch": 0.0001644263575451145,
   "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": 29.393,
       "eval_steps_per_second": 14.698,
       "step": 3
+    },
+    {
+      "epoch": 0.00010961757169674298,
+      "grad_norm": 5.824885845184326,
+      "learning_rate": 8e-05,
+      "loss": 3.7096,
+      "step": 4
+    },
+    {
+      "epoch": 0.00013702196462092874,
+      "grad_norm": 5.463647365570068,
+      "learning_rate": 0.0001,
+      "loss": 3.6884,
+      "step": 5
+    },
+    {
+      "epoch": 0.0001644263575451145,
+      "grad_norm": 5.512495517730713,
+      "learning_rate": 0.00012,
+      "loss": 3.0868,
+      "step": 6
+    },
+    {
+      "epoch": 0.0001644263575451145,
+      "eval_loss": 2.885078191757202,
+      "eval_runtime": 522.6605,
+      "eval_samples_per_second": 29.398,
+      "eval_steps_per_second": 14.7,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 573327424880640.0,
+  "total_flos": 1146654849761280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null