Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1163343785c89c91ea8e1399fb7e8a2dac2d25c42551bdaf03dc0fc3f3f9d995
+oid sha256:902ef54f7502c36c82d928e0aefc9830d508586655cbc992b20c73b4ab8f825f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c30328429c5077f93e9f08148c21d414d0793373f221d4c29fe77f93cdcab64
+oid sha256:9840d4db068fa6c2bd912a4129186928fcca1157afa195a52f236726f57c1073
 size 43122580

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": 0.006874328678839957,
+  "epoch": 0.013748657357679914,
   "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": 14.792,
       "eval_steps_per_second": 7.396,
       "step": 2
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 7.876696586608887,
+      "learning_rate": 3e-05,
+      "loss": 10.7218,
+      "step": 3
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "grad_norm": 8.09037971496582,
+      "learning_rate": 4e-05,
+      "loss": 10.9274,
+      "step": 4
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "eval_loss": 10.605326652526855,
+      "eval_runtime": 26.0997,
+      "eval_samples_per_second": 18.774,
+      "eval_steps_per_second": 9.387,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2404433522589696.0,
+  "total_flos": 4762627938975744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null