Training in progress, step 4800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f3328ee4a1abb22c7c87ff66605a87fc16d9c72dcaf84e33c9f372cf143309
+oid sha256:7603902b76dfb153996cd58830ff2244b1c85eb06a0dbd52e2c83aa4db919240
 size 144748392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8420873b95a7015ac283b565db0edfa7bf6da6bb0b60d7d1c58f8831b13179c
+oid sha256:5a7049d10ee3c694bd2470145a49ede9bec92ae46b8a0cfd24b342730ad05e3c
 size 289690562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b015303c34afce45237ba1bac3daf679d9cae234ba16bc9876bc1e5e6c2369d3
+oid sha256:84e8894b47240b5e938409bdde12ef850338a078ac443b39608ef1f61c6d50e9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9612206721dab747b72325faca201c5b62b462fd9a44bcf14483ab477a2645b1
+oid sha256:741e5a74b4b8a7e18ee94356eb03e28c998d3e32cf81a6bc98c8f2bfb8fb01d7
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8963962197303772,
-  "best_model_checkpoint": "./output/checkpoint-4650",
-  "epoch": 0.29636711281070743,
+  "best_metric": 0.8962866067886353,
+  "best_model_checkpoint": "./output/checkpoint-4800",
+  "epoch": 0.30592734225621415,
   "eval_steps": 150,
-  "global_step": 4650,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3510,6 +3510,119 @@
       "eval_samples_per_second": 12.182,
       "eval_steps_per_second": 12.182,
       "step": 4650
+    },
+    {
+      "epoch": 0.29700446144040793,
+      "grad_norm": 0.6811459064483643,
+      "learning_rate": 1.4790913492997438e-06,
+      "loss": 0.8875,
+      "step": 4660
+    },
+    {
+      "epoch": 0.29764181007010837,
+      "grad_norm": 0.6501142382621765,
+      "learning_rate": 1.3936855405155408e-06,
+      "loss": 0.8959,
+      "step": 4670
+    },
+    {
+      "epoch": 0.2982791586998088,
+      "grad_norm": 0.6603941321372986,
+      "learning_rate": 1.3107915729816954e-06,
+      "loss": 0.887,
+      "step": 4680
+    },
+    {
+      "epoch": 0.29891650732950925,
+      "grad_norm": 0.6620382070541382,
+      "learning_rate": 1.230412854144547e-06,
+      "loss": 0.8847,
+      "step": 4690
+    },
+    {
+      "epoch": 0.2995538559592097,
+      "grad_norm": 0.6567186117172241,
+      "learning_rate": 1.15255268805841e-06,
+      "loss": 0.8955,
+      "step": 4700
+    },
+    {
+      "epoch": 0.30019120458891013,
+      "grad_norm": 0.6121493577957153,
+      "learning_rate": 1.0772142752497604e-06,
+      "loss": 0.8988,
+      "step": 4710
+    },
+    {
+      "epoch": 0.3008285532186106,
+      "grad_norm": 0.6948884129524231,
+      "learning_rate": 1.004400712585646e-06,
+      "loss": 0.9086,
+      "step": 4720
+    },
+    {
+      "epoch": 0.301465901848311,
+      "grad_norm": 0.6520769000053406,
+      "learning_rate": 9.341149931464537e-07,
+      "loss": 0.8802,
+      "step": 4730
+    },
+    {
+      "epoch": 0.30210325047801145,
+      "grad_norm": 0.6592210531234741,
+      "learning_rate": 8.663600061028162e-07,
+      "loss": 0.9139,
+      "step": 4740
+    },
+    {
+      "epoch": 0.3027405991077119,
+      "grad_norm": 0.6573534607887268,
+      "learning_rate": 8.011385365968641e-07,
+      "loss": 0.9039,
+      "step": 4750
+    },
+    {
+      "epoch": 0.3033779477374124,
+      "grad_norm": 0.6443983316421509,
+      "learning_rate": 7.384532656277698e-07,
+      "loss": 0.8939,
+      "step": 4760
+    },
+    {
+      "epoch": 0.30401529636711283,
+      "grad_norm": 0.6723068952560425,
+      "learning_rate": 6.783067699414891e-07,
+      "loss": 0.8871,
+      "step": 4770
+    },
+    {
+      "epoch": 0.30465264499681327,
+      "grad_norm": 0.6483265161514282,
+      "learning_rate": 6.207015219248866e-07,
+      "loss": 0.8888,
+      "step": 4780
+    },
+    {
+      "epoch": 0.3052899936265137,
+      "grad_norm": 0.6345191597938538,
+      "learning_rate": 5.656398895040813e-07,
+      "loss": 0.8899,
+      "step": 4790
+    },
+    {
+      "epoch": 0.30592734225621415,
+      "grad_norm": 0.6864520907402039,
+      "learning_rate": 5.131241360471217e-07,
+      "loss": 0.8845,
+      "step": 4800
+    },
+    {
+      "epoch": 0.30592734225621415,
+      "eval_loss": 0.8962866067886353,
+      "eval_runtime": 44.5297,
+      "eval_samples_per_second": 11.228,
+      "eval_steps_per_second": 11.228,
+      "step": 4800
     }
   ],
   "logging_steps": 10,
@@ -3529,7 +3642,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.29777485070336e+17,
+  "total_flos": 1.3399278300168192e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null