last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029563932002956393,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009854644000985464,
      "eval_loss": 1.6932358741760254,
      "eval_runtime": 46.054,
      "eval_samples_per_second": 9.293,
      "eval_steps_per_second": 4.647,
      "step": 1
    },
    {
      "epoch": 0.0029563932002956393,
      "grad_norm": 2.935326337814331,
      "learning_rate": 4e-05,
      "loss": 1.6906,
      "step": 3
    },
    {
      "epoch": 0.004927322000492732,
      "eval_loss": 1.6801007986068726,
      "eval_runtime": 46.2223,
      "eval_samples_per_second": 9.26,
      "eval_steps_per_second": 4.63,
      "step": 5
    },
    {
      "epoch": 0.005912786400591279,
      "grad_norm": 1.5826900005340576,
      "learning_rate": 8e-05,
      "loss": 1.6815,
      "step": 6
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 1.0061872005462646,
      "learning_rate": 0.00012,
      "loss": 1.6003,
      "step": 9
    },
    {
      "epoch": 0.009854644000985464,
      "eval_loss": 1.6075009107589722,
      "eval_runtime": 46.1623,
      "eval_samples_per_second": 9.272,
      "eval_steps_per_second": 4.636,
      "step": 10
    },
    {
      "epoch": 0.011825572801182557,
      "grad_norm": 0.5639610886573792,
      "learning_rate": 0.00016,
      "loss": 1.6336,
      "step": 12
    },
    {
      "epoch": 0.014781966001478197,
      "grad_norm": 0.6469801664352417,
      "learning_rate": 0.0002,
      "loss": 1.5621,
      "step": 15
    },
    {
      "epoch": 0.014781966001478197,
      "eval_loss": 1.542202115058899,
      "eval_runtime": 46.2098,
      "eval_samples_per_second": 9.262,
      "eval_steps_per_second": 4.631,
      "step": 15
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 0.7007733583450317,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.4142,
      "step": 18
    },
    {
      "epoch": 0.01970928800197093,
      "eval_loss": 1.4901186227798462,
      "eval_runtime": 46.1925,
      "eval_samples_per_second": 9.266,
      "eval_steps_per_second": 4.633,
      "step": 20
    },
    {
      "epoch": 0.020694752402069475,
      "grad_norm": 0.7448059320449829,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.6253,
      "step": 21
    },
    {
      "epoch": 0.023651145602365115,
      "grad_norm": 0.6697611212730408,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.4523,
      "step": 24
    },
    {
      "epoch": 0.02463661000246366,
      "eval_loss": 1.4631699323654175,
      "eval_runtime": 46.1947,
      "eval_samples_per_second": 9.265,
      "eval_steps_per_second": 4.633,
      "step": 25
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": 0.6793627142906189,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.495,
      "step": 27
    },
    {
      "epoch": 0.029563932002956393,
      "grad_norm": 0.6140923500061035,
      "learning_rate": 0.0,
      "loss": 1.3848,
      "step": 30
    },
    {
      "epoch": 0.029563932002956393,
      "eval_loss": 1.456243872642517,
      "eval_runtime": 46.1815,
      "eval_samples_per_second": 9.268,
      "eval_steps_per_second": 4.634,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5551080370864128.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}