Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71c9b9fee951d621701bc991372c9c5b2a9c820d9b7e979938b859df0005f4b
+oid sha256:17b0e26409add284040bfb6519212fa66546ffc66a3aa5d979a1343d1f1d8877
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae2b7b02d8e90c63111ff174c3dabc90698a17dcd854aaf6e3a7f31b34675a35
+oid sha256:8889293fec09b2fe74498d01572c3ce26b61db84338a9cdbed6cfa42cb25b38d
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb762df0bcde1a278e4cfee9529f100080d2053b9f907e04587f9a17f96f840e
+oid sha256:a49c5843763fc46ee1da521e469762370035a34eaade0c5483dded6460bc0d21
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010296010296010296,
+  "epoch": 0.02059202059202059,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 7.3149,
       "step": 9
+    },
+    {
+      "epoch": 0.012355212355212355,
+      "grad_norm": 1.8765102624893188,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.4621,
+      "step": 12
+    },
+    {
+      "epoch": 0.015444015444015444,
+      "grad_norm": 2.23150634765625,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.2479,
+      "step": 15
+    },
+    {
+      "epoch": 0.016473616473616472,
+      "eval_loss": 5.598282337188721,
+      "eval_runtime": 31.4187,
+      "eval_samples_per_second": 13.018,
+      "eval_steps_per_second": 6.525,
+      "step": 16
+    },
+    {
+      "epoch": 0.018532818532818532,
+      "grad_norm": 1.7026886940002441,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.5097,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3495193466634240.0,
+  "total_flos": 7077766769934336.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null