last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013364517206815904,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013364517206815904,
      "grad_norm": 0.27126675844192505,
      "learning_rate": 2e-05,
      "loss": 10.8485,
      "step": 1
    },
    {
      "epoch": 0.0026729034413631807,
      "grad_norm": 0.23387199640274048,
      "learning_rate": 4e-05,
      "loss": 10.8212,
      "step": 2
    },
    {
      "epoch": 0.004009355162044771,
      "grad_norm": 0.2120688557624817,
      "learning_rate": 6e-05,
      "loss": 10.8479,
      "step": 3
    },
    {
      "epoch": 0.004009355162044771,
      "eval_loss": 10.839851379394531,
      "eval_runtime": 5.655,
      "eval_samples_per_second": 55.703,
      "eval_steps_per_second": 27.94,
      "step": 3
    },
    {
      "epoch": 0.0053458068827263614,
      "grad_norm": 0.23968082666397095,
      "learning_rate": 8e-05,
      "loss": 10.8387,
      "step": 4
    },
    {
      "epoch": 0.006682258603407952,
      "grad_norm": 0.23080295324325562,
      "learning_rate": 0.0001,
      "loss": 10.83,
      "step": 5
    },
    {
      "epoch": 0.008018710324089542,
      "grad_norm": 0.17982040345668793,
      "learning_rate": 0.00012,
      "loss": 10.8437,
      "step": 6
    },
    {
      "epoch": 0.008018710324089542,
      "eval_loss": 10.837489128112793,
      "eval_runtime": 5.0921,
      "eval_samples_per_second": 61.861,
      "eval_steps_per_second": 31.029,
      "step": 6
    },
    {
      "epoch": 0.009355162044771133,
      "grad_norm": 0.2414633184671402,
      "learning_rate": 0.00014,
      "loss": 10.8399,
      "step": 7
    },
    {
      "epoch": 0.010691613765452723,
      "grad_norm": 0.2134893238544464,
      "learning_rate": 0.00016,
      "loss": 10.8369,
      "step": 8
    },
    {
      "epoch": 0.012028065486134313,
      "grad_norm": 0.20277711749076843,
      "learning_rate": 0.00018,
      "loss": 10.8212,
      "step": 9
    },
    {
      "epoch": 0.012028065486134313,
      "eval_loss": 10.8336763381958,
      "eval_runtime": 5.0773,
      "eval_samples_per_second": 62.041,
      "eval_steps_per_second": 31.119,
      "step": 9
    },
    {
      "epoch": 0.013364517206815904,
      "grad_norm": 0.23867052793502808,
      "learning_rate": 0.0002,
      "loss": 10.8361,
      "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": 1620084129792.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}