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:d608b514d77c22f7a3abb19f1f80f7d9ae5689a07231e4fc08db79bb06ed75e3
+oid sha256:3d7473927a08af11d2835bcac04c37becbc5b8196da3a8950c56b2941400da0a
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ba0ca400e3dd7a07b47ab53166b1fd0f4972aa41831decad64edb77d5c13d6
+oid sha256:373d60bd968d84b58704d98f52a80e7de2d59d338fb9bf5cec8f34b2c53425b0
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0321889f8ed923edee52a6e35612417334c6f7ed0ea7cc3ae74075fefed31b2
+oid sha256:a9c1b2ac5be3cd8d07b30efc15d35a20ae097f6e09cfc422fd45d7ddd5f0c3b8
 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": 0.0053839423918164075,
+  "epoch": 0.00807591358772461,
   "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": 4.51,
       "step": 10
+    },
+    {
+      "epoch": 0.005922336630998048,
+      "grad_norm": 3.0932722091674805,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.3751,
+      "step": 11
+    },
+    {
+      "epoch": 0.006460730870179689,
+      "grad_norm": 2.336444854736328,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.2279,
+      "step": 12
+    },
+    {
+      "epoch": 0.006460730870179689,
+      "eval_loss": 4.283242225646973,
+      "eval_runtime": 185.6479,
+      "eval_samples_per_second": 8.43,
+      "eval_steps_per_second": 4.218,
+      "step": 12
+    },
+    {
+      "epoch": 0.00699912510936133,
+      "grad_norm": 2.7305572032928467,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.1567,
+      "step": 13
+    },
+    {
+      "epoch": 0.007537519348542971,
+      "grad_norm": 2.3469622135162354,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.1394,
+      "step": 14
+    },
+    {
+      "epoch": 0.00807591358772461,
+      "grad_norm": 2.188025712966919,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.1941,
+      "step": 15
+    },
+    {
+      "epoch": 0.00807591358772461,
+      "eval_loss": 4.151458740234375,
+      "eval_runtime": 186.8151,
+      "eval_samples_per_second": 8.377,
+      "eval_steps_per_second": 4.191,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -128,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.533788723085312e+16,
+  "total_flos": 2.300683084627968e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null