Delete checkpoints

checkpoints/checkpoint-64/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3bc3e42a9b64e2588302c65f922098dc164e9533637b0366d543059cffc4d46e
-size 14851088

checkpoints/checkpoint-64/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20eb77acf0aad2036561ff4a6a2f7ea60e5460cd7315622fe018edf6af9477fa
-size 29695994

checkpoints/checkpoint-64/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4ed2e591b77a8475236224c0177524db10370f13296177433e7087f6779de2cd
-size 14244

checkpoints/checkpoint-64/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:79bdcda359cedf04bc9f65fce5ca61248f4a235c6e9c8a45682aa2dfc095ac0f
-size 1064

checkpoints/checkpoint-64/trainer_state.json

@@ -1,161 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 25.6,
-  "eval_steps": 8,
-  "global_step": 64,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 3.2,
-      "grad_norm": 2.572068691253662,
-      "learning_rate": 6.153846153846155e-05,
-      "loss": 1.4317,
-      "step": 8
-    },
-    {
-      "epoch": 3.2,
-      "eval_accuracy": 0.6066666666666667,
-      "eval_loss": 1.3396244049072266,
-      "eval_runtime": 4.4787,
-      "eval_samples_per_second": 33.492,
-      "eval_steps_per_second": 0.67,
-      "step": 8
-    },
-    {
-      "epoch": 6.4,
-      "grad_norm": 14.756144523620605,
-      "learning_rate": 9.91486549841951e-05,
-      "loss": 1.3743,
-      "step": 16
-    },
-    {
-      "epoch": 6.4,
-      "eval_accuracy": 0.6,
-      "eval_loss": 1.4254791736602783,
-      "eval_runtime": 4.2212,
-      "eval_samples_per_second": 35.535,
-      "eval_steps_per_second": 0.711,
-      "step": 16
-    },
-    {
-      "epoch": 9.6,
-      "grad_norm": 6.530676364898682,
-      "learning_rate": 8.895402872628352e-05,
-      "loss": 1.3977,
-      "step": 24
-    },
-    {
-      "epoch": 9.6,
-      "eval_accuracy": 0.6466666666666666,
-      "eval_loss": 1.3245296478271484,
-      "eval_runtime": 4.2384,
-      "eval_samples_per_second": 35.391,
-      "eval_steps_per_second": 0.708,
-      "step": 24
-    },
-    {
-      "epoch": 12.8,
-      "grad_norm": 14.631135940551758,
-      "learning_rate": 6.948929366463396e-05,
-      "loss": 1.3629,
-      "step": 32
-    },
-    {
-      "epoch": 12.8,
-      "eval_accuracy": 0.64,
-      "eval_loss": 1.290442943572998,
-      "eval_runtime": 5.0282,
-      "eval_samples_per_second": 29.832,
-      "eval_steps_per_second": 0.597,
-      "step": 32
-    },
-    {
-      "epoch": 16.0,
-      "grad_norm": 4.518190383911133,
-      "learning_rate": 4.5386582026834906e-05,
-      "loss": 1.3515,
-      "step": 40
-    },
-    {
-      "epoch": 16.0,
-      "eval_accuracy": 0.6266666666666667,
-      "eval_loss": 1.3534621000289917,
-      "eval_runtime": 6.0978,
-      "eval_samples_per_second": 24.599,
-      "eval_steps_per_second": 0.492,
-      "step": 40
-    },
-    {
-      "epoch": 19.2,
-      "grad_norm": 10.279590606689453,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 1.3871,
-      "step": 48
-    },
-    {
-      "epoch": 19.2,
-      "eval_accuracy": 0.5933333333333334,
-      "eval_loss": 1.3667320013046265,
-      "eval_runtime": 6.4398,
-      "eval_samples_per_second": 23.293,
-      "eval_steps_per_second": 0.466,
-      "step": 48
-    },
-    {
-      "epoch": 22.4,
-      "grad_norm": 5.7001872062683105,
-      "learning_rate": 7.489143213519301e-06,
-      "loss": 1.3224,
-      "step": 56
-    },
-    {
-      "epoch": 22.4,
-      "eval_accuracy": 0.6066666666666667,
-      "eval_loss": 1.3154500722885132,
-      "eval_runtime": 4.7475,
-      "eval_samples_per_second": 31.595,
-      "eval_steps_per_second": 0.632,
-      "step": 56
-    },
-    {
-      "epoch": 25.6,
-      "grad_norm": 8.32728385925293,
-      "learning_rate": 9.483356314779479e-08,
-      "loss": 1.328,
-      "step": 64
-    },
-    {
-      "epoch": 25.6,
-      "eval_accuracy": 0.6333333333333333,
-      "eval_loss": 1.2921510934829712,
-      "eval_runtime": 4.2106,
-      "eval_samples_per_second": 35.625,
-      "eval_steps_per_second": 0.712,
-      "step": 64
-    }
-  ],
-  "logging_steps": 8,
-  "max_steps": 64,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 32,
-  "save_steps": 8,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 0.0,
-  "train_batch_size": 64,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoints/checkpoint-64/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:07709a6f9df64331b59c24c1eeaafbea2a2d582622d433b37f7ed72b3574b7fc
-size 5112