Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590a4917af92b594576d1810b5086608d6c4026cab4966c13b30786e7c8e7b9e
+oid sha256:c0335c6813b301c3b864907d00587eb6d699944df71348f257cb71caecf4df88
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d62d8a7b4d9488248370990f3a5cbdce14849c7cb5e00a2e52b85e0d0072b5e
+oid sha256:f368c87329c93e3ff140f6c93b504044e95345f5052c76c8554cdb85d8b79a04
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8c6fc31ac199e6c243ffe062905a7862052130540b4f8afa1589a29fe97b6d
+oid sha256:8cbc589a06e2970f3d1e1f484146819e64848b461fbefd953e917f429a552096
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0028394974089586142,
+  "epoch": 0.004259246113437922,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 146.921,
       "eval_steps_per_second": 73.51,
       "step": 10
+    },
+    {
+      "epoch": 0.0031234471498544757,
+      "grad_norm": 1.0151692628860474,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 44.2977,
+      "step": 11
+    },
+    {
+      "epoch": 0.0034073968907503372,
+      "grad_norm": 1.013784646987915,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 44.3243,
+      "step": 12
+    },
+    {
+      "epoch": 0.0036913466316461988,
+      "grad_norm": 1.0569106340408325,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 44.2707,
+      "step": 13
+    },
+    {
+      "epoch": 0.00397529637254206,
+      "grad_norm": 3.530860185623169,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 44.2178,
+      "step": 14
+    },
+    {
+      "epoch": 0.004259246113437922,
+      "grad_norm": 1.0001676082611084,
+      "learning_rate": 0.0001,
+      "loss": 44.278,
+      "step": 15
+    },
+    {
+      "epoch": 0.004259246113437922,
+      "eval_loss": 11.058786392211914,
+      "eval_runtime": 9.9005,
+      "eval_samples_per_second": 149.79,
+      "eval_steps_per_second": 74.946,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 39305871360.0,
+  "total_flos": 63638077440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null