trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.43605359317905,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1218026796589525,
      "grad_norm": 0.567721962928772,
      "learning_rate": 5e-06,
      "loss": 1.6252,
      "step": 50
    },
    {
      "epoch": 0.243605359317905,
      "grad_norm": 0.7323570251464844,
      "learning_rate": 1e-05,
      "loss": 1.582,
      "step": 100
    },
    {
      "epoch": 0.3654080389768575,
      "grad_norm": 0.7963395118713379,
      "learning_rate": 1.5e-05,
      "loss": 1.4706,
      "step": 150
    },
    {
      "epoch": 0.48721071863581,
      "grad_norm": 0.6532277464866638,
      "learning_rate": 2e-05,
      "loss": 1.2949,
      "step": 200
    },
    {
      "epoch": 0.6090133982947625,
      "grad_norm": 0.7197393774986267,
      "learning_rate": 2.5e-05,
      "loss": 1.1536,
      "step": 250
    },
    {
      "epoch": 0.730816077953715,
      "grad_norm": 0.7984452247619629,
      "learning_rate": 3e-05,
      "loss": 1.0621,
      "step": 300
    },
    {
      "epoch": 0.8526187576126675,
      "grad_norm": 1.125217318534851,
      "learning_rate": 3.5e-05,
      "loss": 1.0322,
      "step": 350
    },
    {
      "epoch": 0.97442143727162,
      "grad_norm": 0.9447218179702759,
      "learning_rate": 4e-05,
      "loss": 1.0086,
      "step": 400
    },
    {
      "epoch": 1.0962241169305724,
      "grad_norm": 0.9581252932548523,
      "learning_rate": 4.5e-05,
      "loss": 0.9828,
      "step": 450
    },
    {
      "epoch": 1.218026796589525,
      "grad_norm": 1.0622270107269287,
      "learning_rate": 5e-05,
      "loss": 0.9694,
      "step": 500
    },
    {
      "epoch": 1.3398294762484775,
      "grad_norm": 1.1124155521392822,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.9658,
      "step": 550
    },
    {
      "epoch": 1.46163215590743,
      "grad_norm": 1.2832890748977661,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.9635,
      "step": 600
    },
    {
      "epoch": 1.5834348355663823,
      "grad_norm": 1.0713014602661133,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.9382,
      "step": 650
    },
    {
      "epoch": 1.705237515225335,
      "grad_norm": 1.0779744386672974,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.9457,
      "step": 700
    },
    {
      "epoch": 1.8270401948842876,
      "grad_norm": 1.0238535404205322,
      "learning_rate": 2.5e-05,
      "loss": 0.9462,
      "step": 750
    },
    {
      "epoch": 1.94884287454324,
      "grad_norm": 1.1264749765396118,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.9315,
      "step": 800
    },
    {
      "epoch": 2.0706455542021924,
      "grad_norm": 1.1411375999450684,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.9232,
      "step": 850
    },
    {
      "epoch": 2.192448233861145,
      "grad_norm": 1.1316472291946411,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.9232,
      "step": 900
    },
    {
      "epoch": 2.3142509135200973,
      "grad_norm": 1.1166857481002808,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.9241,
      "step": 950
    },
    {
      "epoch": 2.43605359317905,
      "grad_norm": 1.2450848817825317,
      "learning_rate": 0.0,
      "loss": 0.9213,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.241676072477491e+16,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}