Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2623f9de2f4d411cb3fd1c5cf19e539bcace7c307fb13c3fda9936f8029eeb45
+oid sha256:44e6180c9e3fad77bbdc23daab88876db6fee51fc4043fcebce753c776f681b8
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae4af5fb2c933eebbacecbc9db62d6298a570f2f7449dd2f1aa6bf40210d9a6
+oid sha256:f02f2d6a78a64a80012383151160898e19e925b67963454f9f88a61b4195fd80
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a42bdd74ff13352881db8dcbb79f1b26943e4f61cd30f3d264203c6f8095da
+oid sha256:34de7513ace4771b70a9755d6eef3d62eb22e1822eec9b095622e5916d8422fc
 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": 0.01794168950909544,
+  "epoch": 0.02093197109394468,
   "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": 22.894,
       "eval_steps_per_second": 2.863,
       "step": 54
+    },
+    {
+      "epoch": 0.01893845003737852,
+      "grad_norm": 5.4833221435546875,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 6.6639,
+      "step": 57
+    },
+    {
+      "epoch": 0.0199352105656616,
+      "grad_norm": 6.972083568572998,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 6.7846,
+      "step": 60
+    },
+    {
+      "epoch": 0.02093197109394468,
+      "grad_norm": 38.77021789550781,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 6.4933,
+      "step": 63
+    },
+    {
+      "epoch": 0.02093197109394468,
+      "eval_loss": 1.5598267316818237,
+      "eval_runtime": 221.2927,
+      "eval_samples_per_second": 22.906,
+      "eval_steps_per_second": 2.865,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4505059178053632.0,
+  "total_flos": 5248318099685376.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null