Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2cb53ce4097ebb1fc7562064683c252c3d9869d99a6bbdf3a2bab404f670f2
+oid sha256:2c0e0bcd5d88a3500231ff55b4f0ae557a84604ca8c798fc9265f3b46f0448d6
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70be69df5bf6f98001193ad48e3be216ee54a8b7d29475c032de96a6f9ac5361
+oid sha256:5277051a519761231b9a075d5fba93dfc965af3536520aebf560a1b7763031b4
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1355c639766d3952c3be512dc3398093c55d179396a88b0f2916aee9460092db
+oid sha256:891a60711995466ede70ee8fe95ed9d1d8e59808b0ae6ea01a40ca4ead79ea82
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03602355386214063,
+  "epoch": 0.07204710772428126,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 41.091,
       "eval_steps_per_second": 5.138,
       "step": 10
+    },
+    {
+      "epoch": 0.05542085209560097,
+      "grad_norm": 1.2649078369140625,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.8277,
+      "step": 20
+    },
+    {
+      "epoch": 0.05542085209560097,
+      "eval_loss": 2.6205527782440186,
+      "eval_runtime": 59.2126,
+      "eval_samples_per_second": 41.055,
+      "eval_steps_per_second": 5.134,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0257258327834624e+16,
+  "total_flos": 2.0309883073069056e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null