Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252b097295c8cb658a95186584c8c191bbf681e89c901ff7fe67c5936bb25b00
+oid sha256:98e73bbb56ed33df02becfea3375596f6d64b44a1dbbf2432e64797751172d8e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ab08126725be321b919615ac92cfbe2e14395147018761831431bcaf5a7ee0
+oid sha256:1271ea4d6fa8467eced8f934f22c530c32f8468a964095e9dd5cc3ea3dcf8996
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab22ddf51bfbb0e52394ea82ce6def3703300cb6b77357d2a920d3ed8bca3047
+oid sha256:8532b81b442a52e7641152d52819f99f24bb427b98bc8d1a82e25a081ba985ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:964730355c317bebf1d8ccbe8c0becdecfcea59207dec1596c5fd980e1b6084d
+oid sha256:eee81c5e75673c3b9060a012dcd6537b28a2cc9b4464a9db8908848717dda896
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02206693637366679,
+  "epoch": 0.02942258183155572,
   "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": 11.03,
       "eval_steps_per_second": 1.387,
       "step": 15
+    },
+    {
+      "epoch": 0.026480323648400146,
+      "grad_norm": 1.6007380485534668,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 8.6175,
+      "step": 18
+    },
+    {
+      "epoch": 0.02942258183155572,
+      "eval_loss": 2.0439629554748535,
+      "eval_runtime": 103.8112,
+      "eval_samples_per_second": 11.03,
+      "eval_steps_per_second": 1.387,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.960393933062144e+16,
+  "total_flos": 2.613858577416192e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null