Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f582474f4a585678c483ac9fff1f2efcec06042b0a0c19e1e1cd7fec71027e
+oid sha256:4c9dde00fd9b6aa3ff6678aa586d75db410b36135ac641658826ef8660fecd71
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:994cf1b5b32fbf07cc830c8ccc63aaaf1e553017f8c351309d8100ebe998867a
+oid sha256:12b52d07c06872f3b63c0b99309969c50d6cbc84a1a7f07b74f3d90ddf8980fe
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
+oid sha256:2b4f63aec6d8b3291c19fe2b4497f750eeddd6b87b84886cefc94a6bfc39de55
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
+oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013392857142857142,
+  "epoch": 0.020089285714285716,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 13.979,
       "eval_steps_per_second": 1.747,
       "step": 18
+    },
+    {
+      "epoch": 0.015625,
+      "grad_norm": 6.13102912902832,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 6.0363,
+      "step": 21
+    },
+    {
+      "epoch": 0.017857142857142856,
+      "grad_norm": 5.863094329833984,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 5.4919,
+      "step": 24
+    },
+    {
+      "epoch": 0.020089285714285716,
+      "grad_norm": 7.331254959106445,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 5.5447,
+      "step": 27
+    },
+    {
+      "epoch": 0.020089285714285716,
+      "eval_loss": 5.072122573852539,
+      "eval_runtime": 162.0067,
+      "eval_samples_per_second": 13.975,
+      "eval_steps_per_second": 1.747,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.670794220817613e+16,
+  "total_flos": 4.006191331226419e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null