last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.042105263157894736,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 0.3747830092906952,
      "learning_rate": 2e-05,
      "loss": 2.0706,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 2.444136142730713,
      "eval_runtime": 2.0579,
      "eval_samples_per_second": 43.733,
      "eval_steps_per_second": 21.867,
      "step": 1
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 0.41439950466156006,
      "learning_rate": 4e-05,
      "loss": 2.3185,
      "step": 2
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.4124947190284729,
      "learning_rate": 6e-05,
      "loss": 2.2032,
      "step": 3
    },
    {
      "epoch": 0.014035087719298246,
      "eval_loss": 2.4437968730926514,
      "eval_runtime": 1.6288,
      "eval_samples_per_second": 55.257,
      "eval_steps_per_second": 27.628,
      "step": 3
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 0.38794511556625366,
      "learning_rate": 8e-05,
      "loss": 2.4269,
      "step": 4
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 0.3471144437789917,
      "learning_rate": 0.0001,
      "loss": 2.5172,
      "step": 5
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 0.5253433585166931,
      "learning_rate": 0.00012,
      "loss": 2.9958,
      "step": 6
    },
    {
      "epoch": 0.028070175438596492,
      "eval_loss": 2.440718412399292,
      "eval_runtime": 1.6486,
      "eval_samples_per_second": 54.59,
      "eval_steps_per_second": 27.295,
      "step": 6
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": 0.44060736894607544,
      "learning_rate": 0.00014,
      "loss": 2.4808,
      "step": 7
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 0.4031517207622528,
      "learning_rate": 0.00016,
      "loss": 2.4764,
      "step": 8
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.36345911026000977,
      "learning_rate": 0.00018,
      "loss": 2.2561,
      "step": 9
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 2.419855833053589,
      "eval_runtime": 1.6451,
      "eval_samples_per_second": 54.709,
      "eval_steps_per_second": 27.354,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 460425560850432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}