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:d03debe1566ae1a06ed67cf9b1c7f498e6b4801ede69701a7ec7e6f411c4ea9d
+oid sha256:1371ecb6d32929f20cfdc17b80b405ba5a32115346d140c6708390270d0b56a8
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69cdc6ce45ed10da77d4e57c95a37aaa4672ccfa39e2a2167f07349e7ebddcd7
+oid sha256:c1dce1e0bcc55dd0e9162029ed9d6f81cf08e063d17d5079eaba957ebd704180
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b84eb34ea082513a9a6a2e5a22b6ad7d836ade6132ea78751d6466e21585b7
+oid sha256:295480827c70f9cd2cc957f5b4871246e7a40e8362f8bcbf2ee121f8124e0e12
 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": 0.0004081549356135589,
+  "epoch": 0.0008163098712271178,
   "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": 1.7096,
       "step": 9
+    },
+    {
+      "epoch": 0.0004897859227362707,
+      "grad_norm": 1.2086544036865234,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.8291,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006122324034203384,
+      "grad_norm": 1.120302438735962,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.7406,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006530478969816942,
+      "eval_loss": 1.7136527299880981,
+      "eval_runtime": 667.6475,
+      "eval_samples_per_second": 15.451,
+      "eval_steps_per_second": 7.726,
+      "step": 16
+    },
+    {
+      "epoch": 0.000734678884104406,
+      "grad_norm": 1.010192632675171,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.6754,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3834471807713280.0,
+  "total_flos": 7668943615426560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null