Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc1620164eeb66146f025792e6bfc933c768c945469cff7ce137734aa3aa9e9
+oid sha256:f9ab71f6aabfbf8c6ff6bde370de03471039f6bc9a6893fb6e94f79e7c749b8b
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1304d430d98e376a3e021659d88c8af85bdad05b9b3d526d92d81492c42d94b
+oid sha256:629cdfbe44cf8ff7b378e1a89fcb51a5335e410f4a32f3b82a4d211b3f41d71f
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a8fbdd40f7edc9d5266c41a92e911a33f810a381088729bf4c84d9fe8f8cfae
+oid sha256:446f86ec2d710de4e25bb65aa3702d3d6d34aaf5102619f692e1fb433a8cb9a7
 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": 0.05542725173210162,
+  "epoch": 0.08314087759815242,
   "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": 35.282,
       "eval_steps_per_second": 17.641,
       "step": 6
+    },
+    {
+      "epoch": 0.06466512702078522,
+      "grad_norm": 2.756948709487915,
+      "learning_rate": 0.00014,
+      "loss": 3.0057,
+      "step": 7
+    },
+    {
+      "epoch": 0.07390300230946882,
+      "grad_norm": 2.8316171169281006,
+      "learning_rate": 0.00016,
+      "loss": 3.4052,
+      "step": 8
+    },
+    {
+      "epoch": 0.08314087759815242,
+      "grad_norm": 2.612847089767456,
+      "learning_rate": 0.00018,
+      "loss": 3.1095,
+      "step": 9
+    },
+    {
+      "epoch": 0.08314087759815242,
+      "eval_loss": 3.4868814945220947,
+      "eval_runtime": 1.2684,
+      "eval_samples_per_second": 36.267,
+      "eval_steps_per_second": 18.134,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 312560831692800.0,
+  "total_flos": 462590030905344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null