last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004519263360072308,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00045192633600723084,
      "grad_norm": 0.03470371663570404,
      "learning_rate": 2e-05,
      "loss": 11.9474,
      "step": 1
    },
    {
      "epoch": 0.0009038526720144617,
      "grad_norm": 0.04096892103552818,
      "learning_rate": 4e-05,
      "loss": 11.9484,
      "step": 2
    },
    {
      "epoch": 0.0013557790080216926,
      "grad_norm": 0.04570753499865532,
      "learning_rate": 6e-05,
      "loss": 11.9458,
      "step": 3
    },
    {
      "epoch": 0.0013557790080216926,
      "eval_loss": 11.947966575622559,
      "eval_runtime": 49.1383,
      "eval_samples_per_second": 18.967,
      "eval_steps_per_second": 9.483,
      "step": 3
    },
    {
      "epoch": 0.0018077053440289234,
      "grad_norm": 0.04630984365940094,
      "learning_rate": 8e-05,
      "loss": 11.9486,
      "step": 4
    },
    {
      "epoch": 0.002259631680036154,
      "grad_norm": 0.04539979621767998,
      "learning_rate": 0.0001,
      "loss": 11.9474,
      "step": 5
    },
    {
      "epoch": 0.002711558016043385,
      "grad_norm": 0.04202263057231903,
      "learning_rate": 0.00012,
      "loss": 11.9499,
      "step": 6
    },
    {
      "epoch": 0.002711558016043385,
      "eval_loss": 11.947790145874023,
      "eval_runtime": 49.1438,
      "eval_samples_per_second": 18.965,
      "eval_steps_per_second": 9.482,
      "step": 6
    },
    {
      "epoch": 0.003163484352050616,
      "grad_norm": 0.04382634907960892,
      "learning_rate": 0.00014,
      "loss": 11.9479,
      "step": 7
    },
    {
      "epoch": 0.0036154106880578467,
      "grad_norm": 0.0340876542031765,
      "learning_rate": 0.00016,
      "loss": 11.9464,
      "step": 8
    },
    {
      "epoch": 0.004067337024065077,
      "grad_norm": 0.0457964763045311,
      "learning_rate": 0.00018,
      "loss": 11.9488,
      "step": 9
    },
    {
      "epoch": 0.004067337024065077,
      "eval_loss": 11.947565078735352,
      "eval_runtime": 49.0401,
      "eval_samples_per_second": 19.005,
      "eval_steps_per_second": 9.502,
      "step": 9
    },
    {
      "epoch": 0.004519263360072308,
      "grad_norm": 0.0413544699549675,
      "learning_rate": 0.0002,
      "loss": 11.9455,
      "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": 2067824640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}