Delete checkpoints-v3.0-discrete-conditional

checkpoints-v3.0-discrete-conditional/checkpoint-1792/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8b3ad70db4ed69d93fd168409c9fb8df7d893bf06aebd8d9a1546cf4bd671646
-size 24272320

checkpoints-v3.0-discrete-conditional/checkpoint-1792/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:83207f207113cf981c258c88cca169fae259919129e37cd73de6fbfe322cbec4
-size 519947

checkpoints-v3.0-discrete-conditional/checkpoint-1792/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:33195186be30d1f265b097129519b2867d0c3a6cba0ca5c3fe920aa11e1cd406
-size 14645

checkpoints-v3.0-discrete-conditional/checkpoint-1792/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c53cf553f6434449959e590b32ad22ac0c6e07ffae962a4164d31ea3a75d345e
-size 1383

checkpoints-v3.0-discrete-conditional/checkpoint-1792/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:970abb983a5a0197c365bc7fdfdc8155569e58b62f56513c3b9d937587189b2d
-size 1465

checkpoints-v3.0-discrete-conditional/checkpoint-1792/trainer_state.json

@@ -1,251 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.8849382716049383,
-  "eval_steps": 256,
-  "global_step": 1792,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.06320987654320988,
-      "grad_norm": 0.23306457698345184,
-      "learning_rate": 0.000248046875,
-      "loss": 0.39816710352897644,
-      "step": 128
-    },
-    {
-      "epoch": 0.12641975308641976,
-      "grad_norm": 0.22459745407104492,
-      "learning_rate": 0.000498046875,
-      "loss": 0.40399056673049927,
-      "step": 256
-    },
-    {
-      "epoch": 0.12641975308641976,
-      "eval_cos_loss": 0.10607527632538866,
-      "eval_loss": 0.3911797745925624,
-      "eval_mse_loss": 0.38057224779594234,
-      "step": 256
-    },
-    {
-      "epoch": 0.12641975308641976,
-      "eval_cos_loss": 0.10607527632538866,
-      "eval_loss": 0.3911797745925624,
-      "eval_mse_loss": 0.38057224779594234,
-      "eval_runtime": 3.9087,
-      "eval_samples_per_second": 669.78,
-      "eval_steps_per_second": 10.489,
-      "step": 256
-    },
-    {
-      "epoch": 0.18962962962962962,
-      "grad_norm": 1.4832631349563599,
-      "learning_rate": 0.000748046875,
-      "loss": 0.40022405982017517,
-      "step": 384
-    },
-    {
-      "epoch": 0.2528395061728395,
-      "grad_norm": 0.28019025921821594,
-      "learning_rate": 0.000998046875,
-      "loss": 0.40096139907836914,
-      "step": 512
-    },
-    {
-      "epoch": 0.2528395061728395,
-      "eval_cos_loss": 0.1108138523087269,
-      "eval_loss": 0.4095045269989386,
-      "eval_mse_loss": 0.39842314473012597,
-      "step": 512
-    },
-    {
-      "epoch": 0.2528395061728395,
-      "eval_cos_loss": 0.1108138523087269,
-      "eval_loss": 0.4095045269989386,
-      "eval_mse_loss": 0.39842314473012597,
-      "eval_runtime": 3.9424,
-      "eval_samples_per_second": 664.061,
-      "eval_steps_per_second": 10.4,
-      "step": 512
-    },
-    {
-      "epoch": 0.3160493827160494,
-      "grad_norm": 0.2588430345058441,
-      "learning_rate": 0.0009827157247249464,
-      "loss": 0.39848989248275757,
-      "step": 640
-    },
-    {
-      "epoch": 0.37925925925925924,
-      "grad_norm": 0.22329679131507874,
-      "learning_rate": 0.0009315344337660421,
-      "loss": 0.3891080319881439,
-      "step": 768
-    },
-    {
-      "epoch": 0.37925925925925924,
-      "eval_cos_loss": 0.10478089422714419,
-      "eval_loss": 0.38925740195483693,
-      "eval_mse_loss": 0.37877931173254803,
-      "step": 768
-    },
-    {
-      "epoch": 0.37925925925925924,
-      "eval_cos_loss": 0.10478089422714419,
-      "eval_loss": 0.38925740195483693,
-      "eval_mse_loss": 0.37877931173254803,
-      "eval_runtime": 3.9118,
-      "eval_samples_per_second": 669.26,
-      "eval_steps_per_second": 10.481,
-      "step": 768
-    },
-    {
-      "epoch": 0.44246913580246916,
-      "grad_norm": 0.20011205971240997,
-      "learning_rate": 0.0008500491898731988,
-      "loss": 0.3931492567062378,
-      "step": 896
-    },
-    {
-      "epoch": 0.505679012345679,
-      "grad_norm": 0.1937173455953598,
-      "learning_rate": 0.0007439821899385376,
-      "loss": 0.391335129737854,
-      "step": 1024
-    },
-    {
-      "epoch": 0.505679012345679,
-      "eval_cos_loss": 0.10188191693003584,
-      "eval_loss": 0.3795151790467704,
-      "eval_mse_loss": 0.3693269865541923,
-      "step": 1024
-    },
-    {
-      "epoch": 0.505679012345679,
-      "eval_cos_loss": 0.10188191693003584,
-      "eval_loss": 0.3795151790467704,
-      "eval_mse_loss": 0.3693269865541923,
-      "eval_runtime": 3.8456,
-      "eval_samples_per_second": 680.77,
-      "eval_steps_per_second": 10.661,
-      "step": 1024
-    },
-    {
-      "epoch": 0.5688888888888889,
-      "grad_norm": 0.17722535133361816,
-      "learning_rate": 0.0006207818531897271,
-      "loss": 0.3856668770313263,
-      "step": 1152
-    },
-    {
-      "epoch": 0.6320987654320988,
-      "grad_norm": 0.20393630862236023,
-      "learning_rate": 0.0004890997654891032,
-      "loss": 0.37992340326309204,
-      "step": 1280
-    },
-    {
-      "epoch": 0.6320987654320988,
-      "eval_cos_loss": 0.10752386781500607,
-      "eval_loss": 0.3945070817703154,
-      "eval_mse_loss": 0.3837546953340856,
-      "step": 1280
-    },
-    {
-      "epoch": 0.6320987654320988,
-      "eval_cos_loss": 0.10752386781500607,
-      "eval_loss": 0.3945070817703154,
-      "eval_mse_loss": 0.3837546953340856,
-      "eval_runtime": 3.9318,
-      "eval_samples_per_second": 665.855,
-      "eval_steps_per_second": 10.428,
-      "step": 1280
-    },
-    {
-      "epoch": 0.6953086419753086,
-      "grad_norm": 0.22595147788524628,
-      "learning_rate": 0.00035818313279679524,
-      "loss": 0.3873279094696045,
-      "step": 1408
-    },
-    {
-      "epoch": 0.7585185185185185,
-      "grad_norm": 0.2019820213317871,
-      "learning_rate": 0.00023722540797531234,
-      "loss": 0.37948113679885864,
-      "step": 1536
-    },
-    {
-      "epoch": 0.7585185185185185,
-      "eval_cos_loss": 0.1014540351745559,
-      "eval_loss": 0.37390955628418343,
-      "eval_mse_loss": 0.36376415229425196,
-      "step": 1536
-    },
-    {
-      "epoch": 0.7585185185185185,
-      "eval_cos_loss": 0.1014540351745559,
-      "eval_loss": 0.37390955628418343,
-      "eval_mse_loss": 0.36376415229425196,
-      "eval_runtime": 3.9553,
-      "eval_samples_per_second": 661.902,
-      "eval_steps_per_second": 10.366,
-      "step": 1536
-    },
-    {
-      "epoch": 0.8217283950617283,
-      "grad_norm": 0.20358595252037048,
-      "learning_rate": 0.00013472069233656453,
-      "loss": 0.3810204267501831,
-      "step": 1664
-    },
-    {
-      "epoch": 0.8849382716049383,
-      "grad_norm": 0.2263447791337967,
-      "learning_rate": 5.786724825584927e-05,
-      "loss": 0.3751329481601715,
-      "step": 1792
-    },
-    {
-      "epoch": 0.8849382716049383,
-      "eval_cos_loss": 0.09955191503210765,
-      "eval_loss": 0.3695452562192591,
-      "eval_mse_loss": 0.35959006446163827,
-      "step": 1792
-    },
-    {
-      "epoch": 0.8849382716049383,
-      "eval_cos_loss": 0.09955191503210765,
-      "eval_loss": 0.3695452562192591,
-      "eval_mse_loss": 0.35959006446163827,
-      "eval_runtime": 3.8784,
-      "eval_samples_per_second": 675.023,
-      "eval_steps_per_second": 10.571,
-      "step": 1792
-    }
-  ],
-  "logging_steps": 128,
-  "max_steps": 2025,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 256,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 0.0,
-  "train_batch_size": 64,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoints-v3.0-discrete-conditional/checkpoint-1792/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c0839bffbc58eb6068cc228e4d756dbb22a9adf723766e40a7bc2a03aca92630
-size 5137