trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.998282770463652,
  "eval_steps": 6,
  "global_step": 109,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05495134516313681,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.2633,
      "step": 6
    },
    {
      "epoch": 0.10990269032627362,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.2511,
      "step": 12
    },
    {
      "epoch": 0.1648540354894104,
      "grad_norm": 0.5077374577522278,
      "learning_rate": 0.0016329931618554523,
      "loss": 1.2743,
      "step": 18
    },
    {
      "epoch": 0.21980538065254723,
      "grad_norm": 0.4308764338493347,
      "learning_rate": 0.001,
      "loss": 1.2678,
      "step": 24
    },
    {
      "epoch": 0.27475672581568406,
      "grad_norm": 0.3473643958568573,
      "learning_rate": 0.0007559289460184544,
      "loss": 0.9491,
      "step": 30
    },
    {
      "epoch": 0.3297080709788208,
      "grad_norm": 0.3959534466266632,
      "learning_rate": 0.0006324555320336759,
      "loss": 0.8782,
      "step": 36
    },
    {
      "epoch": 0.38465941614195764,
      "grad_norm": 0.3642798960208893,
      "learning_rate": 0.0005547001962252292,
      "loss": 0.8816,
      "step": 42
    },
    {
      "epoch": 0.43961076130509447,
      "grad_norm": 0.3345658481121063,
      "learning_rate": 0.0005,
      "loss": 0.8279,
      "step": 48
    },
    {
      "epoch": 0.49456210646823123,
      "grad_norm": 0.31645363569259644,
      "learning_rate": 0.0004588314677411235,
      "loss": 0.8249,
      "step": 54
    },
    {
      "epoch": 0.5495134516313681,
      "grad_norm": 0.29738476872444153,
      "learning_rate": 0.00042640143271122083,
      "loss": 0.8297,
      "step": 60
    },
    {
      "epoch": 0.6044647967945048,
      "grad_norm": 0.3066190183162689,
      "learning_rate": 0.0004,
      "loss": 0.815,
      "step": 66
    },
    {
      "epoch": 0.6594161419576416,
      "grad_norm": 0.3899874985218048,
      "learning_rate": 0.0003779644730092272,
      "loss": 0.8002,
      "step": 72
    },
    {
      "epoch": 0.7143674871207785,
      "grad_norm": 0.32948872447013855,
      "learning_rate": 0.00035921060405354985,
      "loss": 0.7834,
      "step": 78
    },
    {
      "epoch": 0.7693188322839153,
      "grad_norm": 0.3329070508480072,
      "learning_rate": 0.00034299717028501764,
      "loss": 0.7763,
      "step": 84
    },
    {
      "epoch": 0.8242701774470521,
      "grad_norm": 0.3928099274635315,
      "learning_rate": 0.0003287979746107146,
      "loss": 0.7737,
      "step": 90
    },
    {
      "epoch": 0.8792215226101889,
      "grad_norm": 0.262188583612442,
      "learning_rate": 0.00031622776601683794,
      "loss": 0.777,
      "step": 96
    },
    {
      "epoch": 0.9341728677733258,
      "grad_norm": 0.2854004502296448,
      "learning_rate": 0.00030499714066520935,
      "loss": 0.7828,
      "step": 102
    },
    {
      "epoch": 0.9891242129364625,
      "grad_norm": 0.2840617895126343,
      "learning_rate": 0.0002948839123097943,
      "loss": 0.7732,
      "step": 108
    },
    {
      "epoch": 0.998282770463652,
      "step": 109,
      "total_flos": 1.1070545524204503e+18,
      "train_loss": 0.9170126422829584,
      "train_runtime": 980.4859,
      "train_samples_per_second": 14.252,
      "train_steps_per_second": 0.111
    }
  ],
  "logging_steps": 6,
  "max_steps": 109,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1070545524204503e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}