Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fde73d5f5784458ee5326a8012a9f044446d272f00a35fcf6605f6abfdf1045
+oid sha256:660e259502605e834dd8abbd515a95cf791c90b835cd8619af34ae2871638746
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d47ad4f1de884126a79db1358e1135a8e3d09423ce74f2bd7e2332875d61810
+oid sha256:f893ac69d7d1f10d39868874c3b9562ac71e9c3dd7da29564ebf79fb717f4bb0
 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": 0.00018974731981910754,
+  "epoch": 0.0003794946396382151,
   "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": 29.405,
       "eval_steps_per_second": 14.702,
       "step": 3
+    },
+    {
+      "epoch": 0.00025299642642547676,
+      "grad_norm": 16.72240447998047,
+      "learning_rate": 8e-05,
+      "loss": 8.9993,
+      "step": 4
+    },
+    {
+      "epoch": 0.0003162455330318459,
+      "grad_norm": 12.045751571655273,
+      "learning_rate": 0.0001,
+      "loss": 8.7741,
+      "step": 5
+    },
+    {
+      "epoch": 0.0003794946396382151,
+      "grad_norm": 17.086132049560547,
+      "learning_rate": 0.00012,
+      "loss": 9.3432,
+      "step": 6
+    },
+    {
+      "epoch": 0.0003794946396382151,
+      "eval_loss": 7.4766669273376465,
+      "eval_runtime": 226.3391,
+      "eval_samples_per_second": 29.416,
+      "eval_steps_per_second": 14.708,
+      "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