Training in progress, step 26000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a393eecc8859798c86704ccd1740b6f825f3063101dfb84fb1c0e1bb44fc8bb9
+oid sha256:e8fe178b2c865524971da242eead5a0a0fec5b3cb218040e9e466496006f5885
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1597d5dd75462983a2c5a48479f862672dc9074eaa7c62526cd140d73656352
+oid sha256:0bcee50e95784bd04fda383abb23615395a0ad72d918cfafb72b7cef0032329d
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629924d74f807859938a2e0544d41b7fc7e7257734a23d6398e9f4c4c430a987
+oid sha256:b061322e6ec670b87a8f9896d884fe5261ed4165781876f01308a3b5eff45c4a
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b503174003f93898a1090cb2b211d63af9d1104e10530d32ee248925b03f40
+oid sha256:891e10d00e5e712dd3d3f62daa558798b38eee3e75855dd02223a9bfb9d6ca61
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.48,
+  "epoch": 0.52,
   "eval_steps": 1000,
-  "global_step": 24000,
+  "global_step": 26000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1904,6 +1904,164 @@
       "eval_samples_per_second": 77.587,
       "eval_steps_per_second": 0.621,
       "step": 24000
+    },
+    {
+      "epoch": 0.482,
+      "grad_norm": 0.17039372026920319,
+      "learning_rate": 0.0011417851417431346,
+      "loss": 3.3587,
+      "step": 24100
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 0.16372039914131165,
+      "learning_rate": 0.0011352350261391204,
+      "loss": 3.3488,
+      "step": 24200
+    },
+    {
+      "epoch": 0.486,
+      "grad_norm": 0.15907979011535645,
+      "learning_rate": 0.0011286789949169628,
+      "loss": 3.3638,
+      "step": 24300
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.15641772747039795,
+      "learning_rate": 0.001122117334858705,
+      "loss": 3.3627,
+      "step": 24400
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.17920181155204773,
+      "learning_rate": 0.0011155503329926151,
+      "loss": 3.3278,
+      "step": 24500
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 0.16552342474460602,
+      "learning_rate": 0.001108978276580629,
+      "loss": 3.3653,
+      "step": 24600
+    },
+    {
+      "epoch": 0.494,
+      "grad_norm": 0.17901502549648285,
+      "learning_rate": 0.001102401453105785,
+      "loss": 3.3626,
+      "step": 24700
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.17022928595542908,
+      "learning_rate": 0.001095820150259647,
+      "loss": 3.3391,
+      "step": 24800
+    },
+    {
+      "epoch": 0.498,
+      "grad_norm": 0.1806282252073288,
+      "learning_rate": 0.0010892346559297226,
+      "loss": 3.3476,
+      "step": 24900
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.16578249633312225,
+      "learning_rate": 0.0010826452581868676,
+      "loss": 3.3586,
+      "step": 25000
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.38070841487279844,
+      "eval_loss": 3.3385705947875977,
+      "eval_runtime": 17.5524,
+      "eval_samples_per_second": 56.972,
+      "eval_steps_per_second": 0.456,
+      "step": 25000
+    },
+    {
+      "epoch": 0.502,
+      "grad_norm": 0.14317767322063446,
+      "learning_rate": 0.001076052245272686,
+      "loss": 3.3494,
+      "step": 25100
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.18083012104034424,
+      "learning_rate": 0.0010694559055869205,
+      "loss": 3.3425,
+      "step": 25200
+    },
+    {
+      "epoch": 0.506,
+      "grad_norm": 0.1475485861301422,
+      "learning_rate": 0.0010628565276748394,
+      "loss": 3.3346,
+      "step": 25300
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 0.19806760549545288,
+      "learning_rate": 0.0010562544002146108,
+      "loss": 3.359,
+      "step": 25400
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.1636313647031784,
+      "learning_rate": 0.0010496498120046778,
+      "loss": 3.351,
+      "step": 25500
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.14796622097492218,
+      "learning_rate": 0.0010430430519511244,
+      "loss": 3.3308,
+      "step": 25600
+    },
+    {
+      "epoch": 0.514,
+      "grad_norm": 0.15158209204673767,
+      "learning_rate": 0.001036434409055039,
+      "loss": 3.3462,
+      "step": 25700
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 0.1509816199541092,
+      "learning_rate": 0.0010298241723998701,
+      "loss": 3.3612,
+      "step": 25800
+    },
+    {
+      "epoch": 0.518,
+      "grad_norm": 0.2039985954761505,
+      "learning_rate": 0.001023212631138783,
+      "loss": 3.3233,
+      "step": 25900
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.15846829116344452,
+      "learning_rate": 0.001016600074482012,
+      "loss": 3.3338,
+      "step": 26000
+    },
+    {
+      "epoch": 0.52,
+      "eval_accuracy": 0.381559686888454,
+      "eval_loss": 3.330564498901367,
+      "eval_runtime": 11.5688,
+      "eval_samples_per_second": 86.439,
+      "eval_steps_per_second": 0.692,
+      "step": 26000
     }
   ],
   "logging_steps": 100,