Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37e233968841f50c7c99d698169bb752a8b7227429925c0556b12883334fbcd6
+oid sha256:edbbdcc2c6ee84ce47d03fe97f6f91395a4a830bc85e197a21726d36312cb8da
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa9e322fe0948e46586bef85a6561c3df7bc47ff5ce06a596b9af99bc9ce523
+oid sha256:0d1b12b75be11b6f2a453dca326f0e24e7177db26fe4a37771c80bf37c98f8b1
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022068965517241378,
+  "epoch": 0.044137931034482755,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 36.061,
       "eval_steps_per_second": 18.148,
       "step": 2
+    },
+    {
+      "epoch": 0.03310344827586207,
+      "grad_norm": 2.8996269702911377,
+      "learning_rate": 3e-05,
+      "loss": 13.6811,
+      "step": 3
+    },
+    {
+      "epoch": 0.044137931034482755,
+      "grad_norm": 3.0916175842285156,
+      "learning_rate": 4e-05,
+      "loss": 14.1368,
+      "step": 4
+    },
+    {
+      "epoch": 0.044137931034482755,
+      "eval_loss": 13.764532089233398,
+      "eval_runtime": 4.2543,
+      "eval_samples_per_second": 35.963,
+      "eval_steps_per_second": 18.099,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1786201947242496.0,
+  "total_flos": 3528837993332736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null