checkpoint-100/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6666666666666665,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 41.758705139160156,
      "learning_rate": 4.9986614686909146e-05,
      "loss": 39.5171,
      "num_input_tokens_seen": 47056,
      "step": 5
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 35.72260665893555,
      "learning_rate": 4.994647308096509e-05,
      "loss": 3.2466,
      "num_input_tokens_seen": 93544,
      "step": 10
    },
    {
      "epoch": 0.25,
      "grad_norm": 40.3800163269043,
      "learning_rate": 4.987961816680492e-05,
      "loss": 3.3122,
      "num_input_tokens_seen": 141120,
      "step": 15
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 22.71551513671875,
      "learning_rate": 4.9786121534345265e-05,
      "loss": 3.0265,
      "num_input_tokens_seen": 188544,
      "step": 20
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 16.711044311523438,
      "learning_rate": 4.966608330212198e-05,
      "loss": 2.6989,
      "num_input_tokens_seen": 235128,
      "step": 25
    },
    {
      "epoch": 0.5,
      "grad_norm": 10.093056678771973,
      "learning_rate": 4.951963201008076e-05,
      "loss": 2.2284,
      "num_input_tokens_seen": 281904,
      "step": 30
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 12.554229736328125,
      "learning_rate": 4.934692448193334e-05,
      "loss": 2.2164,
      "num_input_tokens_seen": 330096,
      "step": 35
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 20.774412155151367,
      "learning_rate": 4.914814565722671e-05,
      "loss": 2.6854,
      "num_input_tokens_seen": 376824,
      "step": 40
    },
    {
      "epoch": 0.75,
      "grad_norm": 12.924601554870605,
      "learning_rate": 4.892350839330522e-05,
      "loss": 2.4108,
      "num_input_tokens_seen": 424048,
      "step": 45
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 23.568218231201172,
      "learning_rate": 4.867325323737765e-05,
      "loss": 2.419,
      "num_input_tokens_seen": 470432,
      "step": 50
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 29.64082908630371,
      "learning_rate": 4.839764816893315e-05,
      "loss": 2.3183,
      "num_input_tokens_seen": 517624,
      "step": 55
    },
    {
      "epoch": 1.0,
      "grad_norm": 17.5496883392334,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 1.9734,
      "num_input_tokens_seen": 564920,
      "step": 60
    },
    {
      "epoch": 1.0833333333333333,
      "grad_norm": 14.56460189819336,
      "learning_rate": 4.7771595623029394e-05,
      "loss": 1.8086,
      "num_input_tokens_seen": 611240,
      "step": 65
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 11.394974708557129,
      "learning_rate": 4.742181853831721e-05,
      "loss": 2.4591,
      "num_input_tokens_seen": 658904,
      "step": 70
    },
    {
      "epoch": 1.25,
      "grad_norm": 5.737662315368652,
      "learning_rate": 4.7048031608708876e-05,
      "loss": 1.7169,
      "num_input_tokens_seen": 706480,
      "step": 75
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 18.580102920532227,
      "learning_rate": 4.665063509461097e-05,
      "loss": 1.809,
      "num_input_tokens_seen": 752904,
      "step": 80
    },
    {
      "epoch": 1.4166666666666667,
      "grad_norm": 18.77831268310547,
      "learning_rate": 4.6230054538164474e-05,
      "loss": 2.3907,
      "num_input_tokens_seen": 800304,
      "step": 85
    },
    {
      "epoch": 1.5,
      "grad_norm": 7.019700527191162,
      "learning_rate": 4.5786740307563636e-05,
      "loss": 2.0662,
      "num_input_tokens_seen": 846792,
      "step": 90
    },
    {
      "epoch": 1.5833333333333335,
      "grad_norm": 12.335309028625488,
      "learning_rate": 4.5321167114790385e-05,
      "loss": 2.0185,
      "num_input_tokens_seen": 894552,
      "step": 95
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 8.229971885681152,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 1.9831,
      "num_input_tokens_seen": 941040,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 480,
  "num_input_tokens_seen": 941040,
  "num_train_epochs": 8,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4946796550409984e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}