last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007174373139146967,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.174373139146967e-05,
      "grad_norm": 4.656033992767334,
      "learning_rate": 2e-05,
      "loss": 2.9154,
      "step": 1
    },
    {
      "epoch": 0.00014348746278293933,
      "grad_norm": 5.37037467956543,
      "learning_rate": 4e-05,
      "loss": 3.3874,
      "step": 2
    },
    {
      "epoch": 0.000215231194174409,
      "grad_norm": 4.452802658081055,
      "learning_rate": 6e-05,
      "loss": 2.8531,
      "step": 3
    },
    {
      "epoch": 0.000215231194174409,
      "eval_loss": 0.771416962146759,
      "eval_runtime": 420.5838,
      "eval_samples_per_second": 13.954,
      "eval_steps_per_second": 6.978,
      "step": 3
    },
    {
      "epoch": 0.00028697492556587867,
      "grad_norm": 5.913466930389404,
      "learning_rate": 8e-05,
      "loss": 3.3287,
      "step": 4
    },
    {
      "epoch": 0.00035871865695734833,
      "grad_norm": 4.9988694190979,
      "learning_rate": 0.0001,
      "loss": 2.7558,
      "step": 5
    },
    {
      "epoch": 0.000430462388348818,
      "grad_norm": 5.8590779304504395,
      "learning_rate": 0.00012,
      "loss": 2.48,
      "step": 6
    },
    {
      "epoch": 0.000430462388348818,
      "eval_loss": 0.5436943173408508,
      "eval_runtime": 486.3101,
      "eval_samples_per_second": 12.068,
      "eval_steps_per_second": 6.035,
      "step": 6
    },
    {
      "epoch": 0.0005022061197402877,
      "grad_norm": 4.613923072814941,
      "learning_rate": 0.00014,
      "loss": 2.1972,
      "step": 7
    },
    {
      "epoch": 0.0005739498511317573,
      "grad_norm": 5.623652935028076,
      "learning_rate": 0.00016,
      "loss": 1.9682,
      "step": 8
    },
    {
      "epoch": 0.0006456935825232271,
      "grad_norm": 5.242792129516602,
      "learning_rate": 0.00018,
      "loss": 1.7976,
      "step": 9
    },
    {
      "epoch": 0.0006456935825232271,
      "eval_loss": 0.4103832244873047,
      "eval_runtime": 420.6357,
      "eval_samples_per_second": 13.953,
      "eval_steps_per_second": 6.978,
      "step": 9
    },
    {
      "epoch": 0.0007174373139146967,
      "grad_norm": 4.515064716339111,
      "learning_rate": 0.0002,
      "loss": 1.3864,
      "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": 3506885760122880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}