Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4437ce85d5f4dd7860b7fe313ccfbd02e844876c773baee770cca74b160097
+oid sha256:002af32a590093290e0a9c7729b92a84afdc00e85030308f849817d0b9c1650a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab4bac7074f27fb0ec6239535117f53aca668e6f21632890372345bd9e26628
+oid sha256:d26c640d748af893d72dae69a12269eee1396b9138b5268c9efd67369847392a
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5095323b290578a89328d8247b6223badac2013fbf499b9514ebea4b896d297
+oid sha256:6806389118ec16be45f91f2597dc80c85380e866e2552fc0b165cbd873f66c65
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008335648791330926,
+  "epoch": 0.0012503473186996387,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 16.335,
       "eval_steps_per_second": 8.17,
       "step": 6
+    },
+    {
+      "epoch": 0.000972492358988608,
+      "grad_norm": 0.7191041111946106,
+      "learning_rate": 0.00014,
+      "loss": 4.1163,
+      "step": 7
+    },
+    {
+      "epoch": 0.0011114198388441233,
+      "grad_norm": 1.3875627517700195,
+      "learning_rate": 0.00016,
+      "loss": 5.7162,
+      "step": 8
+    },
+    {
+      "epoch": 0.0012503473186996387,
+      "grad_norm": 0.97846519947052,
+      "learning_rate": 0.00018,
+      "loss": 5.0321,
+      "step": 9
+    },
+    {
+      "epoch": 0.0012503473186996387,
+      "eval_loss": 1.1586050987243652,
+      "eval_runtime": 185.5947,
+      "eval_samples_per_second": 16.331,
+      "eval_steps_per_second": 8.168,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1913780359397376.0,
+  "total_flos": 2809592442519552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null