last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012738853503184714,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014154281670205238,
      "grad_norm": 0.35979539155960083,
      "learning_rate": 2e-05,
      "loss": 6.0737,
      "step": 1
    },
    {
      "epoch": 0.0014154281670205238,
      "eval_loss": 1.550566554069519,
      "eval_runtime": 31.4921,
      "eval_samples_per_second": 9.463,
      "eval_steps_per_second": 4.731,
      "step": 1
    },
    {
      "epoch": 0.0028308563340410475,
      "grad_norm": 0.3379415273666382,
      "learning_rate": 4e-05,
      "loss": 5.9829,
      "step": 2
    },
    {
      "epoch": 0.004246284501061571,
      "grad_norm": 0.41088634729385376,
      "learning_rate": 6e-05,
      "loss": 5.6532,
      "step": 3
    },
    {
      "epoch": 0.004246284501061571,
      "eval_loss": 1.5500292778015137,
      "eval_runtime": 31.4992,
      "eval_samples_per_second": 9.461,
      "eval_steps_per_second": 4.73,
      "step": 3
    },
    {
      "epoch": 0.005661712668082095,
      "grad_norm": 0.3271850347518921,
      "learning_rate": 8e-05,
      "loss": 6.2798,
      "step": 4
    },
    {
      "epoch": 0.007077140835102618,
      "grad_norm": 0.4017261266708374,
      "learning_rate": 0.0001,
      "loss": 6.1845,
      "step": 5
    },
    {
      "epoch": 0.008492569002123142,
      "grad_norm": 0.4634651839733124,
      "learning_rate": 0.00012,
      "loss": 6.5431,
      "step": 6
    },
    {
      "epoch": 0.008492569002123142,
      "eval_loss": 1.5396825075149536,
      "eval_runtime": 31.5091,
      "eval_samples_per_second": 9.458,
      "eval_steps_per_second": 4.729,
      "step": 6
    },
    {
      "epoch": 0.009907997169143666,
      "grad_norm": 0.45960116386413574,
      "learning_rate": 0.00014,
      "loss": 5.9549,
      "step": 7
    },
    {
      "epoch": 0.01132342533616419,
      "grad_norm": 0.64166259765625,
      "learning_rate": 0.00016,
      "loss": 6.081,
      "step": 8
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.6194164752960205,
      "learning_rate": 0.00018,
      "loss": 6.0523,
      "step": 9
    },
    {
      "epoch": 0.012738853503184714,
      "eval_loss": 1.4865055084228516,
      "eval_runtime": 31.5385,
      "eval_samples_per_second": 9.449,
      "eval_steps_per_second": 4.724,
      "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": 5699203749642240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}