Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5918f923e94a1c71c1343bdcf10beeef3df1b930ad244fba32fd7f174ba907d
+oid sha256:13ffc792f3d259993d089983addf06408c5d4168bb80ae4e93d9e27c88ac2002
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3efa0ed49bd9be95076d7069e5e9edf45f6b79f66e0033c9a85e8f6d1f88f0b2
+oid sha256:7a67906f8c7c9a7e76b55b46a0195852521231f190af25c50db78e7a42712a24
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536f3bf5d8d9a338dc3c13d4a9497341d1858e9170a623670fdf984c7300d07b
+oid sha256:38fd2ee53c77ea2f7dbd66aca15b5e373033905c0f24009f095167575b44f3c3
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feac55dc4e1aa4e2fb9533ef48c19881a76f1225ae029d1ded10aa6105f9d143
+oid sha256:6633e86d4c67f74dfdd7f692c12dadf065f71b50d638c022301ad30cc5a4b374
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05fb06c8f2309f7e205252b1a3311f0b9687d7493c125c7e1233cf078e7b73e
+oid sha256:4fda8308b847684d2c9f3c998b6decc82d851c5d48d991f8092b8612e3e1813b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3333333333333333,
+  "epoch": 0.5,
   "eval_steps": 200,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -193,6 +193,94 @@
       "eval_samples_per_second": 63.185,
       "eval_steps_per_second": 2.022,
       "step": 1000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 869790.875,
+      "learning_rate": 7.739353226541009e-05,
+      "loss": 78.3315,
+      "step": 1050
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 131137.71875,
+      "learning_rate": 7.504771636387163e-05,
+      "loss": 79.5684,
+      "step": 1100
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 188537.671875,
+      "learning_rate": 7.262583137097018e-05,
+      "loss": 79.0903,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 38120.7890625,
+      "learning_rate": 7.013523247183e-05,
+      "loss": 79.5616,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.2313888600523758,
+      "eval_loss": 4.960353374481201,
+      "eval_runtime": 7.869,
+      "eval_samples_per_second": 63.54,
+      "eval_steps_per_second": 2.033,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 178847.84375,
+      "learning_rate": 6.758348353345014e-05,
+      "loss": 78.9412,
+      "step": 1250
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 72944.7734375,
+      "learning_rate": 6.497833413348909e-05,
+      "loss": 78.9907,
+      "step": 1300
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 82608.953125,
+      "learning_rate": 6.232769602505203e-05,
+      "loss": 78.8287,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 321814.40625,
+      "learning_rate": 5.963961910895676e-05,
+      "loss": 79.5967,
+      "step": 1400
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "eval_accuracy": 0.22584767922654594,
+      "eval_loss": 5.036545753479004,
+      "eval_runtime": 8.0524,
+      "eval_samples_per_second": 62.094,
+      "eval_steps_per_second": 1.987,
+      "step": 1400
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 27832.90625,
+      "learning_rate": 5.692226698644938e-05,
+      "loss": 80.2996,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 165018.953125,
+      "learning_rate": 5.418389216661579e-05,
+      "loss": 82.4446,
+      "step": 1500
     }
   ],
   "logging_steps": 50,