Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06ec767616027800b719342c256c7f9fbbd2a5e5098d73be6fbcb5f5288c4a4
+oid sha256:fa657dd5df7b5aea8a8ea71a2c4db77b2a2238203f10eff4f53d8a84dfb63529
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfcca2ff976a9ae0b114d4cf204d45ca4a07b60ae3ae4f2c7cea6e415d872dba
+oid sha256:f01f5b64a7cc9d77d0803208e3aaeb7b4add9e15d53a519b3c60efc20b1b40fa
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3977c89ae562c7d96889fff99b3c3083286a7fbebfcc1f61d64eabe6090de2
+oid sha256:b3e5dbc325562c890f65b04c44ff9ae3a4aaec245e3f64053f21254bb31be760
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00023734646650447992,
+  "epoch": 0.00047469293300895983,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 2.7989,
       "step": 9
+    },
+    {
+      "epoch": 0.0002848157598053759,
+      "grad_norm": 4.004361629486084,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.2768,
+      "step": 12
+    },
+    {
+      "epoch": 0.00035601969975671986,
+      "grad_norm": 2.4428646564483643,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.4227,
+      "step": 15
+    },
+    {
+      "epoch": 0.00037975434640716787,
+      "eval_loss": 0.48976579308509827,
+      "eval_runtime": 1875.0182,
+      "eval_samples_per_second": 9.461,
+      "eval_steps_per_second": 4.731,
+      "step": 16
+    },
+    {
+      "epoch": 0.0004272236397080638,
+      "grad_norm": 1.8519223928451538,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.8599,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6416060349677568.0,
+  "total_flos": 1.3007903174688768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null