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:a2457bf6a81faec52448359af72418769a440f8bda7355409d40d3419c24e767
+oid sha256:66ee07d4b1ba6340480d1487f04875bb810f623a46022020f8b8eb3b05d6b538
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29a0a0465d60f893a6bb380e220c0b792e0a373a096f3651ccc2548cb423061
+oid sha256:6cb3a55cdb7ed937b6452503c0c411a42521c276366fbe0b5a7e090b279b03c9
 size 13005114

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": 0.028193832599118944,
+  "epoch": 0.05638766519823789,
   "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": 127.292,
       "eval_steps_per_second": 63.646,
       "step": 2
+    },
+    {
+      "epoch": 0.04229074889867841,
+      "grad_norm": 143.23622131347656,
+      "learning_rate": 3e-05,
+      "loss": 126.6562,
+      "step": 3
+    },
+    {
+      "epoch": 0.05638766519823789,
+      "grad_norm": 145.47706604003906,
+      "learning_rate": 4e-05,
+      "loss": 121.875,
+      "step": 4
+    },
+    {
+      "epoch": 0.05638766519823789,
+      "eval_loss": 7.481770992279053,
+      "eval_runtime": 0.9623,
+      "eval_samples_per_second": 124.708,
+      "eval_steps_per_second": 62.354,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 238857895280640.0,
+  "total_flos": 477715790561280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null