Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8373c5e4c8ca9133fbe3ff268192eb46706f3a841ef92d81816a0577e1744f3
+oid sha256:55e64cd9429c3e3e5761c51f818f35c75ecd1232057c81228740dea4aa744c7d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a134857514fb9dfe5e2f59d16b28f578292d717fe3548b42257a0cb8f318fcf
+oid sha256:2cb57304bbdb393557583e9ea391f4cfe629785a56d8b7f467320faeb6a4decb
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5607b27ad36e8b8b6a123386b38e0716be53aa03eb9581fdcae093ba333e0d68
+oid sha256:b63c8755f60283d61d8f5e9b05b9fc3d8c48b7abe96f514359bc54f46be9cceb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
+oid sha256:470670603e8fdc5330cdb9a9152c4fd9c3d8c5a74dd26bffbbb0d869d097eafa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05383580080753701,
+  "epoch": 0.06460296096904442,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,42 @@
       "eval_samples_per_second": 7.667,
       "eval_steps_per_second": 7.667,
       "step": 20
+    },
+    {
+      "epoch": 0.05652759084791386,
+      "grad_norm": 1.8083579540252686,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 0.3447,
+      "step": 21
+    },
+    {
+      "epoch": 0.059219380888290714,
+      "grad_norm": 1.2060580253601074,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.1974,
+      "step": 22
+    },
+    {
+      "epoch": 0.06191117092866756,
+      "grad_norm": 0.7741371989250183,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 0.1914,
+      "step": 23
+    },
+    {
+      "epoch": 0.06460296096904442,
+      "grad_norm": 1.2901431322097778,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.2147,
+      "step": 24
+    },
+    {
+      "epoch": 0.06460296096904442,
+      "eval_loss": 0.28900590538978577,
+      "eval_runtime": 10.1131,
+      "eval_samples_per_second": 7.812,
+      "eval_steps_per_second": 7.812,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -214,7 +250,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8068024208719872.0,
+  "total_flos": 9830006507175936.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null