Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9224e147cad687cbac23fdc886c7eaa7ffbf6f40134d81dbecb7f832c600cae5
+oid sha256:9020ca88dd75335997088149ce3cc825a094a46014efad01de76fc806a0635b4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c254c307b22234da81d7a4c25c6f3eaa662751a95e0c6c62dbfafefb3ca4d2
+oid sha256:6a421f0fe2f28b1563186a1744fd317208ff2ac685133523338e1056ebe073c2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a2f7061246ead644ffa263f882843bd233440575c110dc83dd08da7e675eaf
+oid sha256:1066ebe8c65713c645a47aa66174e4f843f5e351a5c6bb60ef9d363d28511f16
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d82a50e00eb8b3463ddd39187c4a757c5ec4e2aa43cce2e0729eee8edc48ef
+oid sha256:a63b864e0edbc8975992341f990ee2ae3b358499049688aeb089fcb545e500be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20196353436185133,
+  "epoch": 0.40392706872370265,
   "eval_steps": 27,
-  "global_step": 27,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 14.819,
       "eval_steps_per_second": 7.409,
       "step": 27
+    },
+    {
+      "epoch": 0.2992052360916316,
+      "grad_norm": 59.90390396118164,
+      "learning_rate": 1e-05,
+      "loss": 75.3596,
+      "step": 40
+    },
+    {
+      "epoch": 0.40392706872370265,
+      "eval_loss": 3.6523022651672363,
+      "eval_runtime": 14.9676,
+      "eval_samples_per_second": 15.099,
+      "eval_steps_per_second": 7.55,
+      "step": 54
     }
   ],
   "logging_steps": 40,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.892883368824013e+16,
+  "total_flos": 3.785766737648026e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null