last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0018077461924345822,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018077461924345822,
      "grad_norm": 1.018807053565979,
      "learning_rate": 2e-05,
      "loss": 1.5798,
      "step": 1
    },
    {
      "epoch": 0.00018077461924345822,
      "eval_loss": 1.5171396732330322,
      "eval_runtime": 709.8023,
      "eval_samples_per_second": 3.283,
      "eval_steps_per_second": 1.641,
      "step": 1
    },
    {
      "epoch": 0.00036154923848691643,
      "grad_norm": 0.6265318393707275,
      "learning_rate": 4e-05,
      "loss": 1.2996,
      "step": 2
    },
    {
      "epoch": 0.0005423238577303746,
      "grad_norm": 1.7181572914123535,
      "learning_rate": 6e-05,
      "loss": 1.8461,
      "step": 3
    },
    {
      "epoch": 0.0005423238577303746,
      "eval_loss": 1.513336420059204,
      "eval_runtime": 709.6894,
      "eval_samples_per_second": 3.283,
      "eval_steps_per_second": 1.642,
      "step": 3
    },
    {
      "epoch": 0.0007230984769738329,
      "grad_norm": 0.6023378968238831,
      "learning_rate": 8e-05,
      "loss": 1.4002,
      "step": 4
    },
    {
      "epoch": 0.0009038730962172911,
      "grad_norm": 0.5950872898101807,
      "learning_rate": 0.0001,
      "loss": 1.4489,
      "step": 5
    },
    {
      "epoch": 0.0010846477154607492,
      "grad_norm": 0.629414975643158,
      "learning_rate": 0.00012,
      "loss": 1.2502,
      "step": 6
    },
    {
      "epoch": 0.0010846477154607492,
      "eval_loss": 1.4722851514816284,
      "eval_runtime": 708.6755,
      "eval_samples_per_second": 3.288,
      "eval_steps_per_second": 1.644,
      "step": 6
    },
    {
      "epoch": 0.0012654223347042075,
      "grad_norm": 1.3326071500778198,
      "learning_rate": 0.00014,
      "loss": 1.8625,
      "step": 7
    },
    {
      "epoch": 0.0014461969539476657,
      "grad_norm": 0.6978418827056885,
      "learning_rate": 0.00016,
      "loss": 1.0635,
      "step": 8
    },
    {
      "epoch": 0.001626971573191124,
      "grad_norm": 1.8490407466888428,
      "learning_rate": 0.00018,
      "loss": 1.5742,
      "step": 9
    },
    {
      "epoch": 0.001626971573191124,
      "eval_loss": 1.3525186777114868,
      "eval_runtime": 708.6847,
      "eval_samples_per_second": 3.288,
      "eval_steps_per_second": 1.644,
      "step": 9
    },
    {
      "epoch": 0.0018077461924345822,
      "grad_norm": 2.7478888034820557,
      "learning_rate": 0.0002,
      "loss": 2.1121,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5589685858467840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}