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:b43635177605b74a69081652a2317e912b69595c88c8902696ca2035eaaff791
+oid sha256:7e8729d60d03c5d30a44b8c2cd2ea03dffa040e64a49a948253bbd4427a60ca4
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f5841ca7e59d67695536048a15ed85f4762ab51ada73624fc57111798a9f60
+oid sha256:0a184ce6655e626145e594fed1dfc2b3445b33f1852c48feab665da5f10e284e
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22cdbc90fe5ab190ddc8c8d596470e7106be9ee2374df85af28061b6a32f91c4
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 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": 0.21897810218978103,
+  "epoch": 0.291970802919708,
   "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": 185.133,
       "eval_steps_per_second": 24.148,
       "step": 15
+    },
+    {
+      "epoch": 0.26277372262773724,
+      "grad_norm": 0.3243257999420166,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9177,
+      "step": 18
+    },
+    {
+      "epoch": 0.291970802919708,
+      "eval_loss": 11.902644157409668,
+      "eval_runtime": 0.6071,
+      "eval_samples_per_second": 189.414,
+      "eval_steps_per_second": 24.706,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 72312422400.0,
+  "total_flos": 96416563200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null