trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.876543209876543,
  "eval_steps": 500,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7054673721340388,
      "grad_norm": 0.16109323501586914,
      "learning_rate": 0.0002,
      "loss": 1.6978,
      "step": 100
    },
    {
      "epoch": 1.4109347442680775,
      "grad_norm": 0.1664305478334427,
      "learning_rate": 0.0002,
      "loss": 1.4728,
      "step": 200
    },
    {
      "epoch": 2.1164021164021163,
      "grad_norm": 0.19294697046279907,
      "learning_rate": 0.0002,
      "loss": 1.4337,
      "step": 300
    },
    {
      "epoch": 2.821869488536155,
      "grad_norm": 0.20536458492279053,
      "learning_rate": 0.0002,
      "loss": 1.3806,
      "step": 400
    },
    {
      "epoch": 3.527336860670194,
      "grad_norm": 0.21814219653606415,
      "learning_rate": 0.0002,
      "loss": 1.3472,
      "step": 500
    },
    {
      "epoch": 4.232804232804233,
      "grad_norm": 0.2931879162788391,
      "learning_rate": 0.0002,
      "loss": 1.3009,
      "step": 600
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.2566097676753998,
      "learning_rate": 0.0002,
      "loss": 1.3227,
      "step": 700
    },
    {
      "epoch": 5.64373897707231,
      "grad_norm": 0.3220715820789337,
      "learning_rate": 0.0002,
      "loss": 1.2369,
      "step": 800
    },
    {
      "epoch": 6.349206349206349,
      "grad_norm": 0.3416915237903595,
      "learning_rate": 0.0002,
      "loss": 1.1785,
      "step": 900
    },
    {
      "epoch": 7.054673721340388,
      "grad_norm": 0.3860929310321808,
      "learning_rate": 0.0002,
      "loss": 1.1151,
      "step": 1000
    },
    {
      "epoch": 7.760141093474427,
      "grad_norm": 0.5656395554542542,
      "learning_rate": 0.0002,
      "loss": 1.033,
      "step": 1100
    },
    {
      "epoch": 8.465608465608465,
      "grad_norm": 0.690337598323822,
      "learning_rate": 0.0002,
      "loss": 0.981,
      "step": 1200
    },
    {
      "epoch": 9.171075837742505,
      "grad_norm": 0.8267166614532471,
      "learning_rate": 0.0002,
      "loss": 0.9868,
      "step": 1300
    },
    {
      "epoch": 9.876543209876543,
      "grad_norm": 0.5811594128608704,
      "learning_rate": 0.0002,
      "loss": 0.9134,
      "step": 1400
    }
  ],
  "logging_steps": 100,
  "max_steps": 1410,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "total_flos": 1.604382181037015e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}