Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7d31f42c36ca2b6182f3fd3a20dc693ef3c4df8b2c564631d180b20ef3e5f3
+oid sha256:df7f56e2543984d2cfd48e15af93db3d274508ebeba028290b8b8857927fe8d7
 size 1195453784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01763ab0852eae3c912e9d050160c9525aa0b964c547afc7af8485243bf49dc0
+oid sha256:3b1b332a5c0ad454bd31619ce08dfcb9703883011895912ea16f530e750af660
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adf0e0fad701e76d66d9ca7e7e7bb2833a45c43ddf9224441b9068ca8a415c6c
+oid sha256:d74b05f2720b311440022765a28fc8006a7374957aaca6aca1b5e6bc5db4cbaa
 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": 0.028985507246376812,
+  "epoch": 0.03864734299516908,
   "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": 7.473,
       "eval_steps_per_second": 0.934,
       "step": 15
+    },
+    {
+      "epoch": 0.034782608695652174,
+      "grad_norm": 0.4921862483024597,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.1103,
+      "step": 18
+    },
+    {
+      "epoch": 0.03864734299516908,
+      "eval_loss": 0.11116211861371994,
+      "eval_runtime": 116.7218,
+      "eval_samples_per_second": 7.471,
+      "eval_steps_per_second": 0.934,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.792146857879142e+16,
+  "total_flos": 5.151595731458458e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null