Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5da7b80a8e4f67ea44fe4ca7c5e90734b8f6babd4122e07ab7ab0ef6091249
+oid sha256:2767e1a9696d3fc22d045d15b5be281656eafc9c5e7a1f72b729cae1e8e681c9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a2618ba96c1c76f87ce4bb59587c7b1bff56663475f050645aba90427ca9e7
+oid sha256:30c5060550e6f184b17b91286b39a72e6dc03b925bda255bd2d080d5cf953d4a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d2430a504f31c9b7fd3120e51e379d0900588466ffc423d40adc7cb940aa491
+oid sha256:375821e39d2967b7ee28fa23c79e88e8d298ace5c697b299efe87ae74b6d7087
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07450845119006554,
+  "epoch": 0.0869265263884098,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 7.139,
       "eval_steps_per_second": 0.895,
       "step": 54
+    },
+    {
+      "epoch": 0.07864780958951363,
+      "grad_norm": 3.4419732093811035,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.6105,
+      "step": 57
+    },
+    {
+      "epoch": 0.08278716798896171,
+      "grad_norm": 3.259693145751953,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.6081,
+      "step": 60
+    },
+    {
+      "epoch": 0.0869265263884098,
+      "grad_norm": 3.1575546264648438,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 0.6062,
+      "step": 63
+    },
+    {
+      "epoch": 0.0869265263884098,
+      "eval_loss": 0.16651968657970428,
+      "eval_runtime": 171.0519,
+      "eval_samples_per_second": 7.138,
+      "eval_steps_per_second": 0.894,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.518759717151703e+17,
+  "total_flos": 1.771886336676987e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null