trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 2,
  "global_step": 23,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08695652173913043,
      "eval_loss": 0.6561041474342346,
      "eval_runtime": 1.4011,
      "eval_samples_per_second": 3.569,
      "eval_steps_per_second": 2.141,
      "step": 2
    },
    {
      "epoch": 0.17391304347826086,
      "eval_loss": 0.6379454731941223,
      "eval_runtime": 1.397,
      "eval_samples_per_second": 3.579,
      "eval_steps_per_second": 2.147,
      "step": 4
    },
    {
      "epoch": 0.2608695652173913,
      "eval_loss": 0.6212631464004517,
      "eval_runtime": 1.3983,
      "eval_samples_per_second": 3.576,
      "eval_steps_per_second": 2.146,
      "step": 6
    },
    {
      "epoch": 0.34782608695652173,
      "eval_loss": 0.6109676957130432,
      "eval_runtime": 1.396,
      "eval_samples_per_second": 3.582,
      "eval_steps_per_second": 2.149,
      "step": 8
    },
    {
      "epoch": 0.43478260869565216,
      "eval_loss": 0.5979903340339661,
      "eval_runtime": 1.3966,
      "eval_samples_per_second": 3.58,
      "eval_steps_per_second": 2.148,
      "step": 10
    },
    {
      "epoch": 0.5217391304347826,
      "eval_loss": 0.5886225700378418,
      "eval_runtime": 1.3975,
      "eval_samples_per_second": 3.578,
      "eval_steps_per_second": 2.147,
      "step": 12
    },
    {
      "epoch": 0.6086956521739131,
      "eval_loss": 0.5854005813598633,
      "eval_runtime": 1.3966,
      "eval_samples_per_second": 3.58,
      "eval_steps_per_second": 2.148,
      "step": 14
    },
    {
      "epoch": 0.6956521739130435,
      "eval_loss": 0.5828047394752502,
      "eval_runtime": 1.3966,
      "eval_samples_per_second": 3.58,
      "eval_steps_per_second": 2.148,
      "step": 16
    },
    {
      "epoch": 0.782608695652174,
      "eval_loss": 0.5814995169639587,
      "eval_runtime": 1.3995,
      "eval_samples_per_second": 3.573,
      "eval_steps_per_second": 2.144,
      "step": 18
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 0.5805516839027405,
      "eval_runtime": 1.3962,
      "eval_samples_per_second": 3.581,
      "eval_steps_per_second": 2.149,
      "step": 20
    },
    {
      "epoch": 0.9565217391304348,
      "eval_loss": 0.5803565382957458,
      "eval_runtime": 1.3957,
      "eval_samples_per_second": 3.582,
      "eval_steps_per_second": 2.149,
      "step": 22
    },
    {
      "epoch": 1.0,
      "step": 23,
      "total_flos": 331406114816.0,
      "train_loss": 0.629167598226796,
      "train_runtime": 86.9566,
      "train_samples_per_second": 0.517,
      "train_steps_per_second": 0.264
    }
  ],
  "logging_steps": 100,
  "max_steps": 23,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 331406114816.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}