Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7d8776a2aa6384b62e69bdee19492d98da39f772c8d887e53b38857a93395c
+oid sha256:6f848dad3c8dccd4344eb1f32c7525180d7f2bf72ab2e543f3698467ef0782d3
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2123b4b419fe290b51c91077f11c5cad5bd594b076c4d726b5724fdef4bd8d5c
+oid sha256:d58d4a43a1af627c6e2e9db47f41ff0d4f8b5e3ca18e93a37861e4b68874b3f8
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15927cbf30125a74729ed941cb9b28b37024b8135a90654ef97971d5317f1537
+oid sha256:f4d11953e47b9a3f639761fcfec1e07d8e68d91a69c42fe9592aa1d1f633d38f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
+oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004270082732852949,
+  "epoch": 0.008540165465705898,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 2.89,
       "eval_steps_per_second": 1.445,
       "step": 9
+    },
+    {
+      "epoch": 0.005693443643803932,
+      "grad_norm": 26.121597290039062,
+      "learning_rate": 0.00012,
+      "loss": 28.0893,
+      "step": 12
+    },
+    {
+      "epoch": 0.007116804554754915,
+      "grad_norm": 22.931711196899414,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 26.3657,
+      "step": 15
+    },
+    {
+      "epoch": 0.008540165465705898,
+      "grad_norm": 15.313858032226562,
+      "learning_rate": 0.00018,
+      "loss": 22.876,
+      "step": 18
+    },
+    {
+      "epoch": 0.008540165465705898,
+      "eval_loss": 0.7377527952194214,
+      "eval_runtime": 730.2515,
+      "eval_samples_per_second": 9.723,
+      "eval_steps_per_second": 4.861,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.766063703097344e+16,
+  "total_flos": 9.49925800134574e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null