last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01955458989679522,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021727322107550242,
      "grad_norm": 38.05088424682617,
      "learning_rate": 2e-05,
      "loss": 26.2925,
      "step": 1
    },
    {
      "epoch": 0.0021727322107550242,
      "eval_loss": 6.362123489379883,
      "eval_runtime": 30.1256,
      "eval_samples_per_second": 6.44,
      "eval_steps_per_second": 3.22,
      "step": 1
    },
    {
      "epoch": 0.0043454644215100485,
      "grad_norm": 33.849876403808594,
      "learning_rate": 4e-05,
      "loss": 23.3629,
      "step": 2
    },
    {
      "epoch": 0.006518196632265073,
      "grad_norm": 46.13959503173828,
      "learning_rate": 6e-05,
      "loss": 31.472,
      "step": 3
    },
    {
      "epoch": 0.006518196632265073,
      "eval_loss": 6.058818817138672,
      "eval_runtime": 32.8322,
      "eval_samples_per_second": 5.909,
      "eval_steps_per_second": 2.954,
      "step": 3
    },
    {
      "epoch": 0.008690928843020097,
      "grad_norm": 34.175010681152344,
      "learning_rate": 8e-05,
      "loss": 22.6822,
      "step": 4
    },
    {
      "epoch": 0.010863661053775122,
      "grad_norm": 27.02315330505371,
      "learning_rate": 0.0001,
      "loss": 19.7116,
      "step": 5
    },
    {
      "epoch": 0.013036393264530146,
      "grad_norm": 32.253116607666016,
      "learning_rate": 0.00012,
      "loss": 24.4795,
      "step": 6
    },
    {
      "epoch": 0.013036393264530146,
      "eval_loss": 4.786070346832275,
      "eval_runtime": 33.4731,
      "eval_samples_per_second": 5.796,
      "eval_steps_per_second": 2.898,
      "step": 6
    },
    {
      "epoch": 0.015209125475285171,
      "grad_norm": 29.270177841186523,
      "learning_rate": 0.00014,
      "loss": 19.651,
      "step": 7
    },
    {
      "epoch": 0.017381857686040194,
      "grad_norm": 26.47623634338379,
      "learning_rate": 0.00016,
      "loss": 18.795,
      "step": 8
    },
    {
      "epoch": 0.01955458989679522,
      "grad_norm": 28.52800941467285,
      "learning_rate": 0.00018,
      "loss": 17.5999,
      "step": 9
    },
    {
      "epoch": 0.01955458989679522,
      "eval_loss": 3.6607913970947266,
      "eval_runtime": 33.3485,
      "eval_samples_per_second": 5.817,
      "eval_steps_per_second": 2.909,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1622867083001856.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}