checkpoint-1192/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.987034713508992,
  "eval_steps": 500,
  "global_step": 1192,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1672940192388122,
      "grad_norm": 0.03940200433135033,
      "learning_rate": 0.0001917785234899329,
      "loss": 0.388,
      "step": 50
    },
    {
      "epoch": 0.3345880384776244,
      "grad_norm": 0.03866202384233475,
      "learning_rate": 0.00018338926174496644,
      "loss": 0.3472,
      "step": 100
    },
    {
      "epoch": 0.5018820577164367,
      "grad_norm": 0.040275849401950836,
      "learning_rate": 0.000175,
      "loss": 0.3506,
      "step": 150
    },
    {
      "epoch": 0.6691760769552488,
      "grad_norm": 0.03893669694662094,
      "learning_rate": 0.00016661073825503358,
      "loss": 0.3398,
      "step": 200
    },
    {
      "epoch": 0.8364700961940611,
      "grad_norm": 0.03782316669821739,
      "learning_rate": 0.0001582214765100671,
      "loss": 0.3371,
      "step": 250
    },
    {
      "epoch": 1.0033458803847763,
      "grad_norm": 0.03445591777563095,
      "learning_rate": 0.00014983221476510067,
      "loss": 0.3301,
      "step": 300
    },
    {
      "epoch": 1.1706398996235885,
      "grad_norm": 0.042704977095127106,
      "learning_rate": 0.00014144295302013425,
      "loss": 0.317,
      "step": 350
    },
    {
      "epoch": 1.3379339188624007,
      "grad_norm": 0.04385839030146599,
      "learning_rate": 0.0001330536912751678,
      "loss": 0.3148,
      "step": 400
    },
    {
      "epoch": 1.5052279381012128,
      "grad_norm": 0.04302438348531723,
      "learning_rate": 0.00012466442953020134,
      "loss": 0.3159,
      "step": 450
    },
    {
      "epoch": 1.6725219573400252,
      "grad_norm": 0.05040173605084419,
      "learning_rate": 0.0001162751677852349,
      "loss": 0.3271,
      "step": 500
    },
    {
      "epoch": 1.8398159765788373,
      "grad_norm": 0.05767366662621498,
      "learning_rate": 0.00010788590604026847,
      "loss": 0.3133,
      "step": 550
    },
    {
      "epoch": 2.0066917607695527,
      "grad_norm": 0.04548301920294762,
      "learning_rate": 9.949664429530202e-05,
      "loss": 0.315,
      "step": 600
    },
    {
      "epoch": 2.1739857800083646,
      "grad_norm": 0.05534046143293381,
      "learning_rate": 9.110738255033557e-05,
      "loss": 0.3001,
      "step": 650
    },
    {
      "epoch": 2.341279799247177,
      "grad_norm": 0.054814413189888,
      "learning_rate": 8.271812080536914e-05,
      "loss": 0.2985,
      "step": 700
    },
    {
      "epoch": 2.5085738184859894,
      "grad_norm": 0.0619826577603817,
      "learning_rate": 7.432885906040269e-05,
      "loss": 0.2939,
      "step": 750
    },
    {
      "epoch": 2.6758678377248013,
      "grad_norm": 0.06426603347063065,
      "learning_rate": 6.593959731543624e-05,
      "loss": 0.2968,
      "step": 800
    },
    {
      "epoch": 2.8431618569636137,
      "grad_norm": 0.05984446406364441,
      "learning_rate": 5.7550335570469805e-05,
      "loss": 0.3063,
      "step": 850
    },
    {
      "epoch": 3.010037641154329,
      "grad_norm": 0.06274156272411346,
      "learning_rate": 4.9161073825503354e-05,
      "loss": 0.3021,
      "step": 900
    },
    {
      "epoch": 3.1773316603931407,
      "grad_norm": 0.08778294175863266,
      "learning_rate": 4.077181208053692e-05,
      "loss": 0.2803,
      "step": 950
    },
    {
      "epoch": 3.344625679631953,
      "grad_norm": 0.07436411827802658,
      "learning_rate": 3.238255033557047e-05,
      "loss": 0.2835,
      "step": 1000
    },
    {
      "epoch": 3.5119196988707655,
      "grad_norm": 0.05694897472858429,
      "learning_rate": 2.3993288590604026e-05,
      "loss": 0.2859,
      "step": 1050
    },
    {
      "epoch": 3.6792137181095774,
      "grad_norm": 0.0587756410241127,
      "learning_rate": 1.5604026845637585e-05,
      "loss": 0.2863,
      "step": 1100
    },
    {
      "epoch": 3.84650773734839,
      "grad_norm": 0.0690668448805809,
      "learning_rate": 7.214765100671142e-06,
      "loss": 0.2954,
      "step": 1150
    }
  ],
  "logging_steps": 50,
  "max_steps": 1192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.779324622389903e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}