Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05166989685c4207c466b0c6109018ad9986af4b84dfe86b8f27c5e10ee7c78c
+oid sha256:4e1aa8459bb45b16501efac30df613e997231a0477b6ee680dd480726646ddc1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642480ea3b723f443904f39c92d36b9f4ad2ddf2a8e8e17dacab27f6fc8777e7
+oid sha256:6acf58c4de6e278bd61bda097fe4f19a5021fb1986e8a68871a6ebf5a375cd8a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bbba064701c6c5641a803b1cc6ad3663ec5a37b46a361f1a3f2ad360548d26
+oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
 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": 0.007677543186180422,
+  "epoch": 0.015355086372360844,
   "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": 15.246,
       "eval_steps_per_second": 7.64,
       "step": 2
+    },
+    {
+      "epoch": 0.011516314779270634,
+      "grad_norm": 4.6484246253967285,
+      "learning_rate": 3e-05,
+      "loss": 10.5576,
+      "step": 3
+    },
+    {
+      "epoch": 0.015355086372360844,
+      "grad_norm": 4.643052577972412,
+      "learning_rate": 4e-05,
+      "loss": 11.2563,
+      "step": 4
+    },
+    {
+      "epoch": 0.015355086372360844,
+      "eval_loss": 10.888284683227539,
+      "eval_runtime": 26.6909,
+      "eval_samples_per_second": 16.448,
+      "eval_steps_per_second": 8.243,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2959302797033472.0,
+  "total_flos": 5826127381659648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null