del

checkpoint-500/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a6667ff94425aaa5ff75b2c159cce162423e7457f7587b00b8c1458d7319baa1
-size 33629893

checkpoint-500/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:27212d4a658166f71418ec7f9fa368839a86a429c6c352fba4ddd290ce7dbf80
-size 7023334881

checkpoint-500/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a0494f897755c11a1d6ee778ed960dce2c788754092bb0e157e9abaa41b7bb52
-size 14575

checkpoint-500/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:27deb6c1317f6d7dfdc532a327d645b3a9c3eba897c490955f7d425ab9b976cc
-size 557

checkpoint-500/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c999bca8f6d41d0b9498c44dc90b53e9466f2a1b56b41ac4e393b0bdc4fc967f
-size 627

checkpoint-500/trainer_state.json

@@ -1,166 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 8.088978766430738,
-  "global_step": 500,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.32,
-      "learning_rate": 1.9803278688524592e-05,
-      "loss": 1.9325,
-      "step": 20
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 1.9595628415300548e-05,
-      "loss": 1.7877,
-      "step": 40
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 1.937704918032787e-05,
-      "loss": 1.6385,
-      "step": 60
-    },
-    {
-      "epoch": 1.29,
-      "learning_rate": 1.9158469945355195e-05,
-      "loss": 1.5616,
-      "step": 80
-    },
-    {
-      "epoch": 1.62,
-      "learning_rate": 1.8939890710382515e-05,
-      "loss": 1.4152,
-      "step": 100
-    },
-    {
-      "epoch": 1.94,
-      "learning_rate": 1.873224043715847e-05,
-      "loss": 1.3212,
-      "step": 120
-    },
-    {
-      "epoch": 2.26,
-      "learning_rate": 1.8513661202185794e-05,
-      "loss": 1.2661,
-      "step": 140
-    },
-    {
-      "epoch": 2.59,
-      "learning_rate": 1.8295081967213114e-05,
-      "loss": 1.1635,
-      "step": 160
-    },
-    {
-      "epoch": 2.91,
-      "learning_rate": 1.807650273224044e-05,
-      "loss": 1.083,
-      "step": 180
-    },
-    {
-      "epoch": 3.24,
-      "learning_rate": 1.785792349726776e-05,
-      "loss": 1.0087,
-      "step": 200
-    },
-    {
-      "epoch": 3.56,
-      "learning_rate": 1.7639344262295085e-05,
-      "loss": 0.9656,
-      "step": 220
-    },
-    {
-      "epoch": 3.88,
-      "learning_rate": 1.7420765027322405e-05,
-      "loss": 0.9752,
-      "step": 240
-    },
-    {
-      "epoch": 4.21,
-      "learning_rate": 1.720218579234973e-05,
-      "loss": 0.9144,
-      "step": 260
-    },
-    {
-      "epoch": 4.53,
-      "learning_rate": 1.6983606557377052e-05,
-      "loss": 0.8767,
-      "step": 280
-    },
-    {
-      "epoch": 4.85,
-      "learning_rate": 1.6765027322404372e-05,
-      "loss": 0.8613,
-      "step": 300
-    },
-    {
-      "epoch": 5.18,
-      "learning_rate": 1.6546448087431696e-05,
-      "loss": 0.8689,
-      "step": 320
-    },
-    {
-      "epoch": 5.5,
-      "learning_rate": 1.6327868852459016e-05,
-      "loss": 0.778,
-      "step": 340
-    },
-    {
-      "epoch": 5.82,
-      "learning_rate": 1.6109289617486343e-05,
-      "loss": 0.7594,
-      "step": 360
-    },
-    {
-      "epoch": 6.15,
-      "learning_rate": 1.5890710382513663e-05,
-      "loss": 0.756,
-      "step": 380
-    },
-    {
-      "epoch": 6.47,
-      "learning_rate": 1.5672131147540986e-05,
-      "loss": 0.7412,
-      "step": 400
-    },
-    {
-      "epoch": 6.79,
-      "learning_rate": 1.5453551912568306e-05,
-      "loss": 0.6841,
-      "step": 420
-    },
-    {
-      "epoch": 7.12,
-      "learning_rate": 1.523497267759563e-05,
-      "loss": 0.6709,
-      "step": 440
-    },
-    {
-      "epoch": 7.44,
-      "learning_rate": 1.5016393442622952e-05,
-      "loss": 0.6456,
-      "step": 460
-    },
-    {
-      "epoch": 7.77,
-      "learning_rate": 1.4797814207650274e-05,
-      "loss": 0.6366,
-      "step": 480
-    },
-    {
-      "epoch": 8.09,
-      "learning_rate": 1.4579234972677595e-05,
-      "loss": 0.6762,
-      "step": 500
-    }
-  ],
-  "max_steps": 1830,
-  "num_train_epochs": 30,
-  "total_flos": 1.2995638935552e+18,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-500/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:90a8a3ab7979c24c11ed2e8e59bda7617c174ede7f48976d8989449ea69f3fbc
-size 3899