last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008531149359097404,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.531149359097404e-05,
      "grad_norm": 0.8437489867210388,
      "learning_rate": 2e-05,
      "loss": 2.7629,
      "step": 1
    },
    {
      "epoch": 8.531149359097404e-05,
      "eval_loss": 3.126101493835449,
      "eval_runtime": 186.972,
      "eval_samples_per_second": 26.4,
      "eval_steps_per_second": 13.2,
      "step": 1
    },
    {
      "epoch": 0.00017062298718194808,
      "grad_norm": 0.9115301370620728,
      "learning_rate": 4e-05,
      "loss": 3.0406,
      "step": 2
    },
    {
      "epoch": 0.00025593448077292216,
      "grad_norm": 0.7873786091804504,
      "learning_rate": 6e-05,
      "loss": 3.1436,
      "step": 3
    },
    {
      "epoch": 0.00025593448077292216,
      "eval_loss": 3.122842788696289,
      "eval_runtime": 185.5301,
      "eval_samples_per_second": 26.605,
      "eval_steps_per_second": 13.302,
      "step": 3
    },
    {
      "epoch": 0.00034124597436389616,
      "grad_norm": 0.8051307201385498,
      "learning_rate": 8e-05,
      "loss": 2.9916,
      "step": 4
    },
    {
      "epoch": 0.0004265574679548702,
      "grad_norm": 0.902753472328186,
      "learning_rate": 0.0001,
      "loss": 3.1378,
      "step": 5
    },
    {
      "epoch": 0.0005118689615458443,
      "grad_norm": 0.9318247437477112,
      "learning_rate": 0.00012,
      "loss": 2.9882,
      "step": 6
    },
    {
      "epoch": 0.0005118689615458443,
      "eval_loss": 3.082014799118042,
      "eval_runtime": 185.7657,
      "eval_samples_per_second": 26.571,
      "eval_steps_per_second": 13.286,
      "step": 6
    },
    {
      "epoch": 0.0005971804551368183,
      "grad_norm": 1.095488429069519,
      "learning_rate": 0.00014,
      "loss": 2.7722,
      "step": 7
    },
    {
      "epoch": 0.0006824919487277923,
      "grad_norm": 1.1569803953170776,
      "learning_rate": 0.00016,
      "loss": 2.585,
      "step": 8
    },
    {
      "epoch": 0.0007678034423187664,
      "grad_norm": 1.3624595403671265,
      "learning_rate": 0.00018,
      "loss": 3.2317,
      "step": 9
    },
    {
      "epoch": 0.0007678034423187664,
      "eval_loss": 2.8597023487091064,
      "eval_runtime": 185.5701,
      "eval_samples_per_second": 26.599,
      "eval_steps_per_second": 13.3,
      "step": 9
    },
    {
      "epoch": 0.0008531149359097404,
      "grad_norm": 1.5147428512573242,
      "learning_rate": 0.0002,
      "loss": 2.7923,
      "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": 2059778654208000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}