last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0425531914893617,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00425531914893617,
      "grad_norm": 1.4950554370880127,
      "learning_rate": 2e-05,
      "loss": 1.5465,
      "step": 1
    },
    {
      "epoch": 0.00425531914893617,
      "eval_loss": 1.6495660543441772,
      "eval_runtime": 2.9741,
      "eval_samples_per_second": 33.287,
      "eval_steps_per_second": 16.812,
      "step": 1
    },
    {
      "epoch": 0.00851063829787234,
      "grad_norm": 1.658284068107605,
      "learning_rate": 4e-05,
      "loss": 1.6,
      "step": 2
    },
    {
      "epoch": 0.01276595744680851,
      "grad_norm": 1.444246768951416,
      "learning_rate": 6e-05,
      "loss": 1.6347,
      "step": 3
    },
    {
      "epoch": 0.01276595744680851,
      "eval_loss": 1.6359561681747437,
      "eval_runtime": 2.9683,
      "eval_samples_per_second": 33.352,
      "eval_steps_per_second": 16.844,
      "step": 3
    },
    {
      "epoch": 0.01702127659574468,
      "grad_norm": 1.73983895778656,
      "learning_rate": 8e-05,
      "loss": 1.6332,
      "step": 4
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 1.4625120162963867,
      "learning_rate": 0.0001,
      "loss": 1.3766,
      "step": 5
    },
    {
      "epoch": 0.02553191489361702,
      "grad_norm": 1.3686795234680176,
      "learning_rate": 0.00012,
      "loss": 1.554,
      "step": 6
    },
    {
      "epoch": 0.02553191489361702,
      "eval_loss": 1.4791361093521118,
      "eval_runtime": 3.0201,
      "eval_samples_per_second": 32.78,
      "eval_steps_per_second": 16.556,
      "step": 6
    },
    {
      "epoch": 0.029787234042553193,
      "grad_norm": 1.4011821746826172,
      "learning_rate": 0.00014,
      "loss": 1.3207,
      "step": 7
    },
    {
      "epoch": 0.03404255319148936,
      "grad_norm": 1.3235112428665161,
      "learning_rate": 0.00016,
      "loss": 1.3556,
      "step": 8
    },
    {
      "epoch": 0.03829787234042553,
      "grad_norm": 1.2235034704208374,
      "learning_rate": 0.00018,
      "loss": 1.2754,
      "step": 9
    },
    {
      "epoch": 0.03829787234042553,
      "eval_loss": 1.299785852432251,
      "eval_runtime": 3.0493,
      "eval_samples_per_second": 32.466,
      "eval_steps_per_second": 16.397,
      "step": 9
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 1.6802290678024292,
      "learning_rate": 0.0002,
      "loss": 1.4407,
      "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": 500097330708480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}