Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a1a01dfb0640c4f39a48d06f5800b8cdb86fa1ca1fcecb74ef6c290f428512
+oid sha256:e2fd4e98fe846e9f240dc5f1669fcd727cf42b48417301b7c7882df2e304a620
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca14eefa7d7bf36d2545030dd33adb9e09d1a7dade937830a89aeaed1c9c2da
+oid sha256:b478559d602ddd1cd330929dfd7431549a458f5873167ae77dd27f105bfd782f
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288a16e6d9d8c06d39eaaf028ab7ce6ab9c130eeb62c3121161c9ecb57cfd771
+oid sha256:0202e01efe8f13fd7b2c8ee3c96f603708af0ebe0527513b8b210324c785c8c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008494973807164095,
+  "epoch": 0.01132663174288546,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 12.498,
       "eval_steps_per_second": 3.127,
       "step": 15
+    },
+    {
+      "epoch": 0.010193968568596914,
+      "grad_norm": 4.215411186218262,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 4.5758,
+      "step": 18
+    },
+    {
+      "epoch": 0.01132663174288546,
+      "eval_loss": 4.316648006439209,
+      "eval_runtime": 237.9369,
+      "eval_samples_per_second": 12.499,
+      "eval_steps_per_second": 3.127,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.262770368118784e+16,
+  "total_flos": 3.017027157491712e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null