Force add model files

checkpoint-23985/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:da681d00471785472c51b663fa5dfc09d86055e11281b2f9ca1d89f44cc450e2
-size 207734077

checkpoint-23985/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:44b8d226f925403ae3da29607377591d51678f6b810b38292a8988d53c35c49d
-size 14244

checkpoint-23985/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ddb29c7c2b214d417422c344dc6f897586016be65d4e0e163c3818c7e263f168
-size 1064

checkpoint-23985/trainer_state.json

@@ -1,180 +0,0 @@
-{
-  "best_metric": 0.718079007713154,
-  "best_model_checkpoint": "./checkpoints/checkpoint-23985",
-  "epoch": 5.0,
-  "eval_steps": 500,
-  "global_step": 23985,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.26,
-      "learning_rate": 2.5e-05,
-      "loss": 2.119,
-      "step": 1250
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 1.75e-05,
-      "loss": 1.2117,
-      "step": 2500
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 1.75e-05,
-      "loss": 1.0565,
-      "step": 3750
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.6968938920158433,
-      "eval_loss": 0.930023193359375,
-      "eval_runtime": 327.1586,
-      "eval_samples_per_second": 117.301,
-      "eval_steps_per_second": 3.668,
-      "step": 4797
-    },
-    {
-      "epoch": 1.04,
-      "learning_rate": 1.2249999999999998e-05,
-      "loss": 0.9975,
-      "step": 5000
-    },
-    {
-      "epoch": 1.3,
-      "learning_rate": 1.2249999999999998e-05,
-      "loss": 0.9029,
-      "step": 6250
-    },
-    {
-      "epoch": 1.56,
-      "learning_rate": 8.574999999999998e-06,
-      "loss": 0.8903,
-      "step": 7500
-    },
-    {
-      "epoch": 1.82,
-      "learning_rate": 8.574999999999998e-06,
-      "loss": 0.874,
-      "step": 8750
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.7115905774442359,
-      "eval_loss": 0.8782150745391846,
-      "eval_runtime": 300.3321,
-      "eval_samples_per_second": 127.779,
-      "eval_steps_per_second": 3.996,
-      "step": 9594
-    },
-    {
-      "epoch": 2.08,
-      "learning_rate": 6.002499999999999e-06,
-      "loss": 0.8538,
-      "step": 10000
-    },
-    {
-      "epoch": 2.35,
-      "learning_rate": 6.002499999999999e-06,
-      "loss": 0.8203,
-      "step": 11250
-    },
-    {
-      "epoch": 2.61,
-      "learning_rate": 4.201749999999999e-06,
-      "loss": 0.8195,
-      "step": 12500
-    },
-    {
-      "epoch": 2.87,
-      "learning_rate": 4.201749999999999e-06,
-      "loss": 0.8116,
-      "step": 13750
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.7145611840733792,
-      "eval_loss": 0.8623952865600586,
-      "eval_runtime": 300.1975,
-      "eval_samples_per_second": 127.836,
-      "eval_steps_per_second": 3.997,
-      "step": 14391
-    },
-    {
-      "epoch": 3.13,
-      "learning_rate": 2.941224999999999e-06,
-      "loss": 0.7909,
-      "step": 15000
-    },
-    {
-      "epoch": 3.39,
-      "learning_rate": 2.941224999999999e-06,
-      "loss": 0.7914,
-      "step": 16250
-    },
-    {
-      "epoch": 3.65,
-      "learning_rate": 2.058857499999999e-06,
-      "loss": 0.7926,
-      "step": 17500
-    },
-    {
-      "epoch": 3.91,
-      "learning_rate": 2.058857499999999e-06,
-      "loss": 0.7839,
-      "step": 18750
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.7179226599958307,
-      "eval_loss": 0.8576174378395081,
-      "eval_runtime": 300.1549,
-      "eval_samples_per_second": 127.854,
-      "eval_steps_per_second": 3.998,
-      "step": 19188
-    },
-    {
-      "epoch": 4.17,
-      "learning_rate": 1.4412002499999993e-06,
-      "loss": 0.7696,
-      "step": 20000
-    },
-    {
-      "epoch": 4.43,
-      "learning_rate": 1.4412002499999993e-06,
-      "loss": 0.7667,
-      "step": 21250
-    },
-    {
-      "epoch": 4.69,
-      "learning_rate": 1.0088401749999995e-06,
-      "loss": 0.7701,
-      "step": 22500
-    },
-    {
-      "epoch": 4.95,
-      "learning_rate": 1.0088401749999995e-06,
-      "loss": 0.7726,
-      "step": 23750
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.718079007713154,
-      "eval_loss": 0.8557529449462891,
-      "eval_runtime": 300.2736,
-      "eval_samples_per_second": 127.803,
-      "eval_steps_per_second": 3.996,
-      "step": 23985
-    }
-  ],
-  "logging_steps": 1250,
-  "max_steps": 23985,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
-  "save_steps": 500,
-  "total_flos": 0.0,
-  "train_batch_size": 32,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-23985/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:351ee58f715ddbda098b9c7aa4f73852ef8355fd01d77a909cbdf33db04aedc4
-size 4664