last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010267203983675146,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010267203983675146,
      "grad_norm": 0.2763766646385193,
      "learning_rate": 2e-05,
      "loss": 2.349,
      "step": 1
    },
    {
      "epoch": 0.00010267203983675146,
      "eval_loss": 2.121521472930908,
      "eval_runtime": 638.3943,
      "eval_samples_per_second": 6.424,
      "eval_steps_per_second": 3.213,
      "step": 1
    },
    {
      "epoch": 0.00020534407967350292,
      "grad_norm": 0.31695452332496643,
      "learning_rate": 4e-05,
      "loss": 2.2773,
      "step": 2
    },
    {
      "epoch": 0.0003080161195102544,
      "grad_norm": 0.3336767256259918,
      "learning_rate": 6e-05,
      "loss": 2.0207,
      "step": 3
    },
    {
      "epoch": 0.0003080161195102544,
      "eval_loss": 2.121673583984375,
      "eval_runtime": 639.8728,
      "eval_samples_per_second": 6.409,
      "eval_steps_per_second": 3.205,
      "step": 3
    },
    {
      "epoch": 0.00041068815934700584,
      "grad_norm": 0.31777092814445496,
      "learning_rate": 8e-05,
      "loss": 2.0824,
      "step": 4
    },
    {
      "epoch": 0.0005133601991837573,
      "grad_norm": 0.24618875980377197,
      "learning_rate": 0.0001,
      "loss": 2.2182,
      "step": 5
    },
    {
      "epoch": 0.0006160322390205088,
      "grad_norm": 0.2700459361076355,
      "learning_rate": 0.00012,
      "loss": 2.4521,
      "step": 6
    },
    {
      "epoch": 0.0006160322390205088,
      "eval_loss": 2.1164493560791016,
      "eval_runtime": 639.304,
      "eval_samples_per_second": 6.415,
      "eval_steps_per_second": 3.208,
      "step": 6
    },
    {
      "epoch": 0.0007187042788572602,
      "grad_norm": 0.35570693016052246,
      "learning_rate": 0.00014,
      "loss": 2.0329,
      "step": 7
    },
    {
      "epoch": 0.0008213763186940117,
      "grad_norm": 0.2799961566925049,
      "learning_rate": 0.00016,
      "loss": 2.1908,
      "step": 8
    },
    {
      "epoch": 0.0009240483585307631,
      "grad_norm": 0.37302330136299133,
      "learning_rate": 0.00018,
      "loss": 2.034,
      "step": 9
    },
    {
      "epoch": 0.0009240483585307631,
      "eval_loss": 2.0924861431121826,
      "eval_runtime": 639.2343,
      "eval_samples_per_second": 6.415,
      "eval_steps_per_second": 3.209,
      "step": 9
    },
    {
      "epoch": 0.0010267203983675146,
      "grad_norm": 0.2965444028377533,
      "learning_rate": 0.0002,
      "loss": 1.9257,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2058737544069120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}