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:a9638ab5a52f88ebd80032bb8f3263d6b4c81329d4fc18b6c09010428f1cb87d
+oid sha256:6ecbe66bb90005c2da530c4dedfe8bdc57ea610b8d5d4fa9e160f7700dd1dd3e
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4adce36d56d6ca4cab7255d215a6ac2722f78872fbc18add544cbd4c9f9f92fb
+oid sha256:7ff712cd5f541f1626ae44243d65c7c4c7dd32c66ea21b72930170b2fbad7d59
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bf42e7f87caba383b22782e2b7179fde7a6de33b2b24b2c9d2794c015512971
+oid sha256:48eb1b0095c15f46650a9d2ec96e31c26714b620c5be9cc03b1f8120e84563f7
 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": 0.01498855041287905,
+  "epoch": 0.01748664214835889,
   "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": 9.192,
       "eval_steps_per_second": 1.15,
       "step": 54
+    },
+    {
+      "epoch": 0.015821247658039,
+      "grad_norm": 0.17183250188827515,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.3577,
+      "step": 57
+    },
+    {
+      "epoch": 0.016653944903198947,
+      "grad_norm": 0.18601562082767487,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.3407,
+      "step": 60
+    },
+    {
+      "epoch": 0.01748664214835889,
+      "grad_norm": 0.17450034618377686,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 0.3614,
+      "step": 63
+    },
+    {
+      "epoch": 0.01748664214835889,
+      "eval_loss": 0.35599005222320557,
+      "eval_runtime": 659.9247,
+      "eval_samples_per_second": 9.195,
+      "eval_steps_per_second": 1.15,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1673946178558362e+17,
+  "total_flos": 1.3771062258538906e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null