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:d3158e7c632ea3f7564a36c3c916e920c5f594b72fd79e87688e47ca97e1ae9b
+oid sha256:7112d09444dfb155cc0928035841032e71cbb909b0b09e65bf99fc2bf34269fe
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9b842d934dd2498b9e510b71379813bcb08908d72d821728d571c55f535d05
+oid sha256:01a9e9dc7c88d849dc0da1b108ef642dff5216a0b0148b39dc5fb2156b7f40d8
 size 325339796

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:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08784773060029283,
+  "epoch": 0.1171303074670571,
   "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": 15.576,
       "eval_steps_per_second": 1.947,
       "step": 15
+    },
+    {
+      "epoch": 0.1054172767203514,
+      "grad_norm": 18.735877990722656,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 4.3689,
+      "step": 18
+    },
+    {
+      "epoch": 0.1171303074670571,
+      "eval_loss": 0.8026209473609924,
+      "eval_runtime": 18.4677,
+      "eval_samples_per_second": 15.595,
+      "eval_steps_per_second": 1.949,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.995762988744704e+16,
+  "total_flos": 2.661017318326272e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null