Training in progress, step 4650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c9ee81f1a5f2aca4877f804ddc266ce1515f0b8ab7e7e66f32085a4e0efdc70
+oid sha256:40f3328ee4a1abb22c7c87ff66605a87fc16d9c72dcaf84e33c9f372cf143309
 size 144748392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d58fabdcf76f95f479f5ab2cb8357256bcedcf60f4ed21b9e7a84d5c76fa7e
+oid sha256:d8420873b95a7015ac283b565db0edfa7bf6da6bb0b60d7d1c58f8831b13179c
 size 289690562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b6d57158a43317d364194a2d857459227019cc82d49b1f5a0e5ad95a7a48ef
+oid sha256:b015303c34afce45237ba1bac3daf679d9cae234ba16bc9876bc1e5e6c2369d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bf4acbbdf4243a5b30121f973d426853acaed3d0caa7d9deb065ee076e1e1d
+oid sha256:9612206721dab747b72325faca201c5b62b462fd9a44bcf14483ab477a2645b1
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8971238732337952,
-  "best_model_checkpoint": "./output/checkpoint-4500",
-  "epoch": 0.28680688336520077,
+  "best_metric": 0.8963962197303772,
+  "best_model_checkpoint": "./output/checkpoint-4650",
+  "epoch": 0.29636711281070743,
   "eval_steps": 150,
-  "global_step": 4500,
+  "global_step": 4650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3397,6 +3397,119 @@
       "eval_samples_per_second": 12.141,
       "eval_steps_per_second": 12.141,
       "step": 4500
+    },
+    {
+      "epoch": 0.2874442319949012,
+      "grad_norm": 0.6785925626754761,
+      "learning_rate": 3.0589677315529044e-06,
+      "loss": 0.8918,
+      "step": 4510
+    },
+    {
+      "epoch": 0.28808158062460165,
+      "grad_norm": 0.640612781047821,
+      "learning_rate": 2.9363630392945513e-06,
+      "loss": 0.8881,
+      "step": 4520
+    },
+    {
+      "epoch": 0.2887189292543021,
+      "grad_norm": 0.6500893831253052,
+      "learning_rate": 2.816206774856854e-06,
+      "loss": 0.9024,
+      "step": 4530
+    },
+    {
+      "epoch": 0.28935627788400253,
+      "grad_norm": 0.6150489449501038,
+      "learning_rate": 2.6985038773932046e-06,
+      "loss": 0.8976,
+      "step": 4540
+    },
+    {
+      "epoch": 0.289993626513703,
+      "grad_norm": 0.6642642021179199,
+      "learning_rate": 2.583259185208714e-06,
+      "loss": 0.9023,
+      "step": 4550
+    },
+    {
+      "epoch": 0.29063097514340347,
+      "grad_norm": 0.6468821167945862,
+      "learning_rate": 2.4704774355612943e-06,
+      "loss": 0.8929,
+      "step": 4560
+    },
+    {
+      "epoch": 0.2912683237731039,
+      "grad_norm": 0.6480686068534851,
+      "learning_rate": 2.3601632644669536e-06,
+      "loss": 0.8982,
+      "step": 4570
+    },
+    {
+      "epoch": 0.29190567240280435,
+      "grad_norm": 0.6992853879928589,
+      "learning_rate": 2.2523212065091723e-06,
+      "loss": 0.8626,
+      "step": 4580
+    },
+    {
+      "epoch": 0.2925430210325048,
+      "grad_norm": 0.7066597938537598,
+      "learning_rate": 2.1469556946525706e-06,
+      "loss": 0.8962,
+      "step": 4590
+    },
+    {
+      "epoch": 0.29318036966220523,
+      "grad_norm": 0.6244568228721619,
+      "learning_rate": 2.0440710600606595e-06,
+      "loss": 0.8887,
+      "step": 4600
+    },
+    {
+      "epoch": 0.29381771829190567,
+      "grad_norm": 0.6500007510185242,
+      "learning_rate": 1.9436715319177956e-06,
+      "loss": 0.8853,
+      "step": 4610
+    },
+    {
+      "epoch": 0.2944550669216061,
+      "grad_norm": 0.6446324586868286,
+      "learning_rate": 1.8457612372553348e-06,
+      "loss": 0.8889,
+      "step": 4620
+    },
+    {
+      "epoch": 0.29509241555130655,
+      "grad_norm": 0.6383276581764221,
+      "learning_rate": 1.75034420078201e-06,
+      "loss": 0.9005,
+      "step": 4630
+    },
+    {
+      "epoch": 0.295729764181007,
+      "grad_norm": 0.6221078038215637,
+      "learning_rate": 1.6574243447184597e-06,
+      "loss": 0.8846,
+      "step": 4640
+    },
+    {
+      "epoch": 0.29636711281070743,
+      "grad_norm": 0.6676984429359436,
+      "learning_rate": 1.567005488636024e-06,
+      "loss": 0.8919,
+      "step": 4650
+    },
+    {
+      "epoch": 0.29636711281070743,
+      "eval_loss": 0.8963962197303772,
+      "eval_runtime": 41.0446,
+      "eval_samples_per_second": 12.182,
+      "eval_steps_per_second": 12.182,
+      "step": 4650
     }
   ],
   "logging_steps": 10,
@@ -3416,7 +3529,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2559349120434176e+17,
+  "total_flos": 1.29777485070336e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null