Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6219e8df1e72f271ee8b1e9011f6a157f7d093ce3f90f6d2e96e10fceea216
+oid sha256:3b489e7a8d9d0fa7628fbed15c1fc3077124bbdcea44d5a32220fdb9f614b7ab
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fb2b902b2642aa5b6430f96d77d5c8d626218316d4c23f0d355a5bfdca0ba9
+oid sha256:c32f4f8da53e2d25785ba231f38161a4f4dffd0c2f47b8fc9c1e4ab604b1de1f
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5e01f48167f2cf44d2d57c9cf12332c401974db0431167c8cc543fa9db0f82
+oid sha256:4edfda4456ffe1464fd3f2ab00db089363942d2f3ba0836f05c2b7e3e37ffea1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10075566750629723,
+  "epoch": 0.15113350125944586,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -109,6 +109,57 @@
       "learning_rate": 0.0002,
       "loss": 11.7817,
       "step": 10
+    },
+    {
+      "epoch": 0.11083123425692695,
+      "grad_norm": 0.11759434640407562,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 11.7652,
+      "step": 11
+    },
+    {
+      "epoch": 0.12090680100755667,
+      "grad_norm": 0.1497734636068344,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 11.7804,
+      "step": 12
+    },
+    {
+      "epoch": 0.12090680100755667,
+      "eval_loss": 11.773073196411133,
+      "eval_runtime": 1.4475,
+      "eval_samples_per_second": 58.032,
+      "eval_steps_per_second": 29.016,
+      "step": 12
+    },
+    {
+      "epoch": 0.1309823677581864,
+      "grad_norm": 0.12857705354690552,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 11.7778,
+      "step": 13
+    },
+    {
+      "epoch": 0.14105793450881612,
+      "grad_norm": 0.12967197597026825,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 11.774,
+      "step": 14
+    },
+    {
+      "epoch": 0.15113350125944586,
+      "grad_norm": 0.12622714042663574,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 11.7798,
+      "step": 15
+    },
+    {
+      "epoch": 0.15113350125944586,
+      "eval_loss": 11.771885871887207,
+      "eval_runtime": 1.4339,
+      "eval_samples_per_second": 58.582,
+      "eval_steps_per_second": 29.291,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -128,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4074000875520.0,
+  "total_flos": 6111001313280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null