Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5380c87b8a1992262417a07584f7e2ad84f4c2f88005d931c232bf8ae2edd651
+oid sha256:30c52112c96ec25f31baf587e4ea477ab4159bb1c63abe90bcc28c81ca010247
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d345cb2206543c9c855d8cd93c9763b056b3b514641a19501f256c2c6ec77df7
+oid sha256:1f7e9850bee199260d6d224038c95a23455b03a11ddd77fdb4a243a7fb5a4fa4
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c4ef51004bd7cb63819242ee70337c219b896f88e964689c3e3e6e457044c6
+oid sha256:52385b94ea56e4debf05c2da14392180d553361a3ff764d1b252b9267d0e1fa2
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833776bf99a0597a4bf38df86be38e8ac151736eba1d084c9cbb84cab1caf4e9
+oid sha256:43ab2089bb2cb7b873a77ac8e24a3b3b2416ededca3811b6bb0922f61bea4c99
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.24,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -798,6 +798,164 @@
       "eval_samples_per_second": 56.058,
       "eval_steps_per_second": 0.448,
       "step": 10000
+    },
+    {
+      "epoch": 0.202,
+      "grad_norm": 0.13834109902381897,
+      "learning_rate": 0.0018763385407335963,
+      "loss": 3.5627,
+      "step": 10100
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 0.15819378197193146,
+      "learning_rate": 0.001873133519711602,
+      "loss": 3.5634,
+      "step": 10200
+    },
+    {
+      "epoch": 0.206,
+      "grad_norm": 0.1618553251028061,
+      "learning_rate": 0.0018698903050008956,
+      "loss": 3.5768,
+      "step": 10300
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.14207501709461212,
+      "learning_rate": 0.0018666090384701947,
+      "loss": 3.5676,
+      "step": 10400
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.13513191044330597,
+      "learning_rate": 0.001863289863652727,
+      "loss": 3.5653,
+      "step": 10500
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 0.12555710971355438,
+      "learning_rate": 0.0018599329257399516,
+      "loss": 3.5577,
+      "step": 10600
+    },
+    {
+      "epoch": 0.214,
+      "grad_norm": 0.129461869597435,
+      "learning_rate": 0.0018565383715752083,
+      "loss": 3.576,
+      "step": 10700
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.11782678216695786,
+      "learning_rate": 0.0018531063496472927,
+      "loss": 3.5695,
+      "step": 10800
+    },
+    {
+      "epoch": 0.218,
+      "grad_norm": 0.1391923427581787,
+      "learning_rate": 0.0018496370100839622,
+      "loss": 3.5478,
+      "step": 10900
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.15454861521720886,
+      "learning_rate": 0.0018461305046453683,
+      "loss": 3.56,
+      "step": 11000
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.3610430528375734,
+      "eval_loss": 3.5181522369384766,
+      "eval_runtime": 12.5872,
+      "eval_samples_per_second": 79.446,
+      "eval_steps_per_second": 0.636,
+      "step": 11000
+    },
+    {
+      "epoch": 0.222,
+      "grad_norm": 0.14800433814525604,
+      "learning_rate": 0.0018425869867174187,
+      "loss": 3.5559,
+      "step": 11100
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.16677607595920563,
+      "learning_rate": 0.0018390066113050665,
+      "loss": 3.5393,
+      "step": 11200
+    },
+    {
+      "epoch": 0.226,
+      "grad_norm": 0.17119687795639038,
+      "learning_rate": 0.0018353895350255317,
+      "loss": 3.5503,
+      "step": 11300
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.16998586058616638,
+      "learning_rate": 0.0018317359161014477,
+      "loss": 3.5546,
+      "step": 11400
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.16900590062141418,
+      "learning_rate": 0.001828045914353943,
+      "loss": 3.5485,
+      "step": 11500
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.13857169449329376,
+      "learning_rate": 0.0018243196911956476,
+      "loss": 3.5357,
+      "step": 11600
+    },
+    {
+      "epoch": 0.234,
+      "grad_norm": 0.134566068649292,
+      "learning_rate": 0.0018205574096236336,
+      "loss": 3.5478,
+      "step": 11700
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 0.13580797612667084,
+      "learning_rate": 0.0018167592342122857,
+      "loss": 3.5452,
+      "step": 11800
+    },
+    {
+      "epoch": 0.238,
+      "grad_norm": 0.16239416599273682,
+      "learning_rate": 0.0018129253311061002,
+      "loss": 3.5256,
+      "step": 11900
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.16310077905654907,
+      "learning_rate": 0.0018090558680124193,
+      "loss": 3.5331,
+      "step": 12000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.3630156555772994,
+      "eval_loss": 3.4982736110687256,
+      "eval_runtime": 12.3123,
+      "eval_samples_per_second": 81.22,
+      "eval_steps_per_second": 0.65,
+      "step": 12000
     }
   ],
   "logging_steps": 100,