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:e2fd4e98fe846e9f240dc5f1669fcd727cf42b48417301b7c7882df2e304a620
+oid sha256:b49222358c631c4efd5f6a67247e0afafaeb43f20659e563aed41c3cbc50037d
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b478559d602ddd1cd330929dfd7431549a458f5873167ae77dd27f105bfd782f
+oid sha256:35f048fd69e27e14c22b14407a413bd9583e33183fcb9bec3670c09f9d86ef70
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0202e01efe8f13fd7b2c8ee3c96f603708af0ebe0527513b8b210324c785c8c3
+oid sha256:847e6adafbce1ce406fa778b8b6d2b9c0edf688a485355f7d2d7c87ce66c4fa0
 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": 0.01132663174288546,
+  "epoch": 0.014158289678606824,
   "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": 12.499,
       "eval_steps_per_second": 3.127,
       "step": 20
+    },
+    {
+      "epoch": 0.011892963330029732,
+      "grad_norm": 3.9418630599975586,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 4.3036,
+      "step": 21
+    },
+    {
+      "epoch": 0.01359195809146255,
+      "grad_norm": 3.5897490978240967,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 4.2336,
+      "step": 24
+    },
+    {
+      "epoch": 0.014158289678606824,
+      "eval_loss": 4.144935131072998,
+      "eval_runtime": 237.9531,
+      "eval_samples_per_second": 12.498,
+      "eval_steps_per_second": 3.127,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.017027157491712e+16,
+  "total_flos": 3.77128394686464e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null