Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f68593585389116dfc8ce91a485d5769155cdadae6d4db18429ead3c62f2f1
+oid sha256:5b74a8c06eee10b2281dfc0d14330904994300394d5b5c90b922e2b369e0a7d8
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da48a8019d62f323887db1bce770ac0e29160123c856ae3eea8a4c94e7857e77
+oid sha256:d1e5058271dd295bb6b9ac8d2f10cfe47ada29c1d6fbc0a3c3faaf7344e20e45
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
+oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.045146726862302484,
+  "epoch": 0.056433408577878104,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 530.083,
       "eval_steps_per_second": 66.704,
       "step": 20
+    },
+    {
+      "epoch": 0.04740406320541761,
+      "grad_norm": 0.481340229511261,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 10.3482,
+      "step": 21
+    },
+    {
+      "epoch": 0.05417607223476298,
+      "grad_norm": 0.6495785713195801,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 10.3488,
+      "step": 24
+    },
+    {
+      "epoch": 0.056433408577878104,
+      "eval_loss": 10.337669372558594,
+      "eval_runtime": 1.3982,
+      "eval_samples_per_second": 534.277,
+      "eval_steps_per_second": 67.232,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2231013212160.0,
+  "total_flos": 2788766515200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null