checkpoint-156/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 156,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 95.26730346679688,
      "learning_rate": 0.0004180909090909091,
      "loss": 22.4465,
      "mean_token_accuracy": 0.08969678990542888,
      "num_tokens": 1310720.0,
      "step": 10
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 0.0,
      "learning_rate": 0.0005103526968014265,
      "loss": 0.8012,
      "mean_token_accuracy": 0.13804710581898688,
      "num_tokens": 2621440.0,
      "step": 20
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 0.0,
      "learning_rate": 0.0005077286477833616,
      "loss": 452.9577,
      "mean_token_accuracy": 0.05160275483503938,
      "num_tokens": 3932160.0,
      "step": 30
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 0.0,
      "learning_rate": 0.0005031081504278389,
      "loss": 470.5136,
      "mean_token_accuracy": 0.03822226445190609,
      "num_tokens": 5242880.0,
      "step": 40
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 26.303752899169922,
      "learning_rate": 0.0004965277770447238,
      "loss": 167.1384,
      "mean_token_accuracy": 0.057517293840646744,
      "num_tokens": 6553600.0,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_mean_token_accuracy": 0.13677339731378757,
      "eval_num_tokens": 6713344.0,
      "eval_runtime": 8.9806,
      "eval_samples_per_second": 41.089,
      "eval_steps_per_second": 5.233,
      "step": 52
    },
    {
      "epoch": 1.1542168674698796,
      "grad_norm": 28.755094528198242,
      "learning_rate": 0.00048803961281790017,
      "loss": 27.9726,
      "mean_token_accuracy": 0.03075966710531259,
      "num_tokens": 7761920.0,
      "step": 60
    },
    {
      "epoch": 1.346987951807229,
      "grad_norm": 0.9693858027458191,
      "learning_rate": 0.000477710843538941,
      "loss": 2.2869,
      "mean_token_accuracy": 0.10747051909565926,
      "num_tokens": 9072640.0,
      "step": 70
    },
    {
      "epoch": 1.5397590361445783,
      "grad_norm": 0.36548200249671936,
      "learning_rate": 0.0004656232238159615,
      "loss": 60.0031,
      "mean_token_accuracy": 0.10124717205762863,
      "num_tokens": 10383360.0,
      "step": 80
    },
    {
      "epoch": 1.7325301204819277,
      "grad_norm": 0.8749092817306519,
      "learning_rate": 0.0004518724299669051,
      "loss": 0.8994,
      "mean_token_accuracy": 0.1551567144691944,
      "num_tokens": 11694080.0,
      "step": 90
    },
    {
      "epoch": 1.9253012048192772,
      "grad_norm": 0.0,
      "learning_rate": 0.0004365673027192623,
      "loss": 2.2759,
      "mean_token_accuracy": 0.13096993789076805,
      "num_tokens": 13004800.0,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_loss": NaN,
      "eval_mean_token_accuracy": 0.14378934084100925,
      "eval_num_tokens": 13426688.0,
      "eval_runtime": 8.9689,
      "eval_samples_per_second": 41.142,
      "eval_steps_per_second": 5.24,
      "step": 104
    },
    {
      "epoch": 2.1156626506024097,
      "grad_norm": 0.6895984411239624,
      "learning_rate": 0.0004198289857104298,
      "loss": 0.2064,
      "mean_token_accuracy": 0.08719592305678356,
      "num_tokens": 14213120.0,
      "step": 110
    },
    {
      "epoch": 2.3084337349397592,
      "grad_norm": 0.7038294672966003,
      "learning_rate": 0.0004017899666076801,
      "loss": 1.3155,
      "mean_token_accuracy": 0.1053241491317749,
      "num_tokens": 15523840.0,
      "step": 120
    },
    {
      "epoch": 2.5012048192771084,
      "grad_norm": 27.594745635986328,
      "learning_rate": 0.0003825930284374996,
      "loss": 0.0836,
      "mean_token_accuracy": 0.07201291918754578,
      "num_tokens": 16834560.0,
      "step": 130
    },
    {
      "epoch": 2.693975903614458,
      "grad_norm": 0.0,
      "learning_rate": 0.00036239011942476655,
      "loss": 1.364,
      "mean_token_accuracy": 0.15817394778132438,
      "num_tokens": 18145280.0,
      "step": 140
    },
    {
      "epoch": 2.886746987951807,
      "grad_norm": 0.0,
      "learning_rate": 0.00034134115028725524,
      "loss": 3.5977,
      "mean_token_accuracy": 0.10589548945426941,
      "num_tokens": 19456000.0,
      "step": 150
    },
    {
      "epoch": 3.0,
      "eval_loss": NaN,
      "eval_mean_token_accuracy": 0.14411297884393245,
      "eval_num_tokens": 20140032.0,
      "eval_runtime": 8.9831,
      "eval_samples_per_second": 41.077,
      "eval_steps_per_second": 5.232,
      "step": 156
    }
  ],
  "logging_steps": 10,
  "max_steps": 364,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.85125687348822e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}