Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5540b02c0c8b9718f4c8b163b89d2536d0a204a96872cc1813830ea2f5ff2def
+oid sha256:a393eecc8859798c86704ccd1740b6f825f3063101dfb84fb1c0e1bb44fc8bb9
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07da83974549f0bd472e89e0306438f6ba6224e07eeffab08f1bdd4c06240b0c
+oid sha256:c1597d5dd75462983a2c5a48479f862672dc9074eaa7c62526cd140d73656352
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67beb949b8d9f7d418f57ffcfa3af010c6a734200eee76f8fffbb6c1af5da698
+oid sha256:629924d74f807859938a2e0544d41b7fc7e7257734a23d6398e9f4c4c430a987
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fc781feaf7f256475a659aa4c1161b5c2bf2ab5d085f394f920fa586f35178
+oid sha256:28b503174003f93898a1090cb2b211d63af9d1104e10530d32ee248925b03f40
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.44,
+  "epoch": 0.48,
   "eval_steps": 1000,
-  "global_step": 22000,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1746,6 +1746,164 @@
       "eval_samples_per_second": 80.576,
       "eval_steps_per_second": 0.645,
       "step": 22000
+    },
+    {
+      "epoch": 0.442,
+      "grad_norm": 0.1659466177225113,
+      "learning_rate": 0.0012711062414645967,
+      "loss": 3.3785,
+      "step": 22100
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 0.15995340049266815,
+      "learning_rate": 0.0012647341726206296,
+      "loss": 3.389,
+      "step": 22200
+    },
+    {
+      "epoch": 0.446,
+      "grad_norm": 0.17644192278385162,
+      "learning_rate": 0.0012583505234463322,
+      "loss": 3.3787,
+      "step": 22300
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.170969158411026,
+      "learning_rate": 0.0012519555731831996,
+      "loss": 3.365,
+      "step": 22400
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.1832742989063263,
+      "learning_rate": 0.0012455496015670732,
+      "loss": 3.3835,
+      "step": 22500
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 0.16345185041427612,
+      "learning_rate": 0.001239132888815904,
+      "loss": 3.3824,
+      "step": 22600
+    },
+    {
+      "epoch": 0.454,
+      "grad_norm": 0.16044080257415771,
+      "learning_rate": 0.0012327057156174945,
+      "loss": 3.3691,
+      "step": 22700
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.1500287652015686,
+      "learning_rate": 0.0012262683631172222,
+      "loss": 3.3775,
+      "step": 22800
+    },
+    {
+      "epoch": 0.458,
+      "grad_norm": 0.1463031768798828,
+      "learning_rate": 0.0012198211129057393,
+      "loss": 3.377,
+      "step": 22900
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.15354429185390472,
+      "learning_rate": 0.0012133642470066562,
+      "loss": 3.3741,
+      "step": 23000
+    },
+    {
+      "epoch": 0.46,
+      "eval_accuracy": 0.3781017612524462,
+      "eval_loss": 3.3543314933776855,
+      "eval_runtime": 14.9495,
+      "eval_samples_per_second": 66.892,
+      "eval_steps_per_second": 0.535,
+      "step": 23000
+    },
+    {
+      "epoch": 0.462,
+      "grad_norm": 0.16891853511333466,
+      "learning_rate": 0.0012068980478642047,
+      "loss": 3.3573,
+      "step": 23100
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.15053242444992065,
+      "learning_rate": 0.0012004227983308828,
+      "loss": 3.3767,
+      "step": 23200
+    },
+    {
+      "epoch": 0.466,
+      "grad_norm": 0.13770438730716705,
+      "learning_rate": 0.001193938781655082,
+      "loss": 3.3735,
+      "step": 23300
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 0.16500090062618256,
+      "learning_rate": 0.0011874462814686975,
+      "loss": 3.3594,
+      "step": 23400
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.15050701797008514,
+      "learning_rate": 0.0011809455817747194,
+      "loss": 3.3736,
+      "step": 23500
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.14346493780612946,
+      "learning_rate": 0.0011744369669348122,
+      "loss": 3.3714,
+      "step": 23600
+    },
+    {
+      "epoch": 0.474,
+      "grad_norm": 0.15672604739665985,
+      "learning_rate": 0.0011679207216568738,
+      "loss": 3.3547,
+      "step": 23700
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 0.20898281037807465,
+      "learning_rate": 0.0011613971309825828,
+      "loss": 3.3603,
+      "step": 23800
+    },
+    {
+      "epoch": 0.478,
+      "grad_norm": 0.15672914683818817,
+      "learning_rate": 0.001154866480274928,
+      "loss": 3.363,
+      "step": 23900
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.15417250990867615,
+      "learning_rate": 0.0011483290552057285,
+      "loss": 3.3706,
+      "step": 24000
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.37883365949119374,
+      "eval_loss": 3.344762086868286,
+      "eval_runtime": 12.8887,
+      "eval_samples_per_second": 77.587,
+      "eval_steps_per_second": 0.621,
+      "step": 24000
     }
   ],
   "logging_steps": 100,