Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2997a4024dfdc97b8b4149e0db00eeccff5d122e74d84c9877509219f98af7
+oid sha256:617cbbd5238090c49c0f53a22695f4890b40c37a489f0afe6c81dab20746c69a
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5514aafb3c2b44765b5a4b12e85bc0743ab1397babfcf4432bcb103b76f7758e
+oid sha256:24b82ca455703bdaaafded95476a2e8a4ded1f3ec1e37c0aa04ce78589e10f18
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
+oid sha256:e9c762e745e6b10819fd8afb33b4a1b715c756c7b22945b0044c81ebcb593a7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
+oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15763546798029557,
+  "epoch": 0.23645320197044334,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 5.829,
       "eval_steps_per_second": 2.932,
       "step": 16
+    },
+    {
+      "epoch": 0.16748768472906403,
+      "grad_norm": 0.44595250487327576,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.5655,
+      "step": 17
+    },
+    {
+      "epoch": 0.17733990147783252,
+      "grad_norm": 0.3530769646167755,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.3349,
+      "step": 18
+    },
+    {
+      "epoch": 0.18719211822660098,
+      "grad_norm": 0.3304716944694519,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.4219,
+      "step": 19
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 0.32741332054138184,
+      "learning_rate": 5e-05,
+      "loss": 0.5405,
+      "step": 20
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.32143503427505493,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.5708,
+      "step": 21
+    },
+    {
+      "epoch": 0.21674876847290642,
+      "grad_norm": 0.369148850440979,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8169,
+      "step": 22
+    },
+    {
+      "epoch": 0.22660098522167488,
+      "grad_norm": 0.27789416909217834,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.3423,
+      "step": 23
+    },
+    {
+      "epoch": 0.23645320197044334,
+      "grad_norm": 0.32239577174186707,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.4614,
+      "step": 24
+    },
+    {
+      "epoch": 0.23645320197044334,
+      "eval_loss": 0.6010122895240784,
+      "eval_runtime": 29.4041,
+      "eval_samples_per_second": 5.816,
+      "eval_steps_per_second": 2.925,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.947695274583654e+16,
+  "total_flos": 1.3421542911875482e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null