Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426d59d55bb27a8a6a00382846f994c7c4902a9b52c309cce7df371d473771a5
+oid sha256:9d1eecfce2ce5a475d07c9b8d9eb490cee69fc05e91981dadd1f816a6309af85
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f71a4243e7380b25f40cb28b87bebea9d32abb91b2feac7eb9a974beeee13c9
+oid sha256:3bb91d3aa2dba6985bbfda47e627d674a4cf84633222b447d5b948daf9f8c346
 size 111142

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d83bc6ecc84c3509bf103ec4cb38b3401780de11cf5ab7321afff4f6200d382
+oid sha256:5b79569914b66c8a8adae97b253e826ad354a54341d167ae1705fdfccf06f3e4
 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": 0.27856365614798695,
+  "epoch": 0.4178454842219804,
   "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": 179.537,
       "eval_steps_per_second": 90.694,
       "step": 16
+    },
+    {
+      "epoch": 0.2959738846572361,
+      "grad_norm": 0.05909638851881027,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.7599,
+      "step": 17
+    },
+    {
+      "epoch": 0.3133841131664853,
+      "grad_norm": 0.05829249694943428,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.762,
+      "step": 18
+    },
+    {
+      "epoch": 0.3307943416757345,
+      "grad_norm": 0.0558004230260849,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 11.7626,
+      "step": 19
+    },
+    {
+      "epoch": 0.3482045701849837,
+      "grad_norm": 0.05378162860870361,
+      "learning_rate": 5e-05,
+      "loss": 11.7597,
+      "step": 20
+    },
+    {
+      "epoch": 0.36561479869423286,
+      "grad_norm": 0.0506143718957901,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.7609,
+      "step": 21
+    },
+    {
+      "epoch": 0.383025027203482,
+      "grad_norm": 0.056044526398181915,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.7612,
+      "step": 22
+    },
+    {
+      "epoch": 0.40043525571273125,
+      "grad_norm": 0.059284962713718414,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 11.762,
+      "step": 23
+    },
+    {
+      "epoch": 0.4178454842219804,
+      "grad_norm": 0.06157379597425461,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.762,
+      "step": 24
+    },
+    {
+      "epoch": 0.4178454842219804,
+      "eval_loss": 11.762452125549316,
+      "eval_runtime": 0.5407,
+      "eval_samples_per_second": 179.407,
+      "eval_steps_per_second": 90.628,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26073605603328.0,
+  "total_flos": 39110408404992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null