trainer_state.json

{
  "best_global_step": 60,
  "best_metric": 1.0112364292144775,
  "best_model_checkpoint": "j05hr3d/peft-FT-3-Coder-30b-v2/checkpoint-60",
  "epoch": 2.0,
  "eval_steps": 30,
  "global_step": 66,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.3513231873512268,
      "learning_rate": 1.941544065183021e-05,
      "loss": 1.2806,
      "step": 10
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.9766170382499695,
      "learning_rate": 1.6715589548470187e-05,
      "loss": 1.5279,
      "step": 20
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.22962720692157745,
      "learning_rate": 1.242980179903264e-05,
      "loss": 1.0885,
      "step": 30
    },
    {
      "epoch": 0.9230769230769231,
      "eval_loss": 1.0279428958892822,
      "eval_runtime": 397.5727,
      "eval_samples_per_second": 0.07,
      "eval_steps_per_second": 0.035,
      "step": 30
    },
    {
      "epoch": 1.2153846153846155,
      "grad_norm": 0.21934713423252106,
      "learning_rate": 7.570198200967363e-06,
      "loss": 1.1829,
      "step": 40
    },
    {
      "epoch": 1.523076923076923,
      "grad_norm": 0.19970707595348358,
      "learning_rate": 3.284410451529816e-06,
      "loss": 1.4437,
      "step": 50
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.2555944323539734,
      "learning_rate": 5.845593481697931e-07,
      "loss": 1.0246,
      "step": 60
    },
    {
      "epoch": 1.830769230769231,
      "eval_loss": 1.0112364292144775,
      "eval_runtime": 405.21,
      "eval_samples_per_second": 0.069,
      "eval_steps_per_second": 0.035,
      "step": 60
    },
    {
      "epoch": 2.0,
      "step": 66,
      "total_flos": 3.9699322308132864e+17,
      "train_loss": 1.241963545481364,
      "train_runtime": 14535.1384,
      "train_samples_per_second": 0.036,
      "train_steps_per_second": 0.005,
      "train_tokens_per_second": 293.072
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0112364292144775,
      "eval_runtime": 408.8198,
      "eval_samples_per_second": 0.068,
      "eval_steps_per_second": 0.034,
      "step": 66
    }
  ],
  "logging_steps": 10,
  "max_steps": 66,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 30,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.9699322308132864e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}