trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.891566265060241,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0963855421686747,
      "grad_norm": 0.5874277949333191,
      "learning_rate": 0.0001,
      "loss": 3.0129,
      "step": 10
    },
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 0.5504733920097351,
      "learning_rate": 0.0001,
      "loss": 1.3638,
      "step": 20
    },
    {
      "epoch": 0.2891566265060241,
      "grad_norm": 0.28183117508888245,
      "learning_rate": 0.0001,
      "loss": 0.5456,
      "step": 30
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 0.22062893211841583,
      "learning_rate": 0.0001,
      "loss": 0.4025,
      "step": 40
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 0.19783374667167664,
      "learning_rate": 0.0001,
      "loss": 0.3357,
      "step": 50
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 0.2082074135541916,
      "learning_rate": 0.0001,
      "loss": 0.3078,
      "step": 60
    },
    {
      "epoch": 0.6746987951807228,
      "grad_norm": 0.21820276975631714,
      "learning_rate": 0.0001,
      "loss": 0.287,
      "step": 70
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 0.18571995198726654,
      "learning_rate": 0.0001,
      "loss": 0.2769,
      "step": 80
    },
    {
      "epoch": 0.8674698795180723,
      "grad_norm": 0.1946105808019638,
      "learning_rate": 0.0001,
      "loss": 0.2721,
      "step": 90
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.16163858771324158,
      "learning_rate": 0.0001,
      "loss": 0.2676,
      "step": 100
    },
    {
      "epoch": 1.0602409638554218,
      "grad_norm": 0.1597064584493637,
      "learning_rate": 0.0001,
      "loss": 0.2644,
      "step": 110
    },
    {
      "epoch": 1.1566265060240963,
      "grad_norm": 0.16861063241958618,
      "learning_rate": 0.0001,
      "loss": 0.2635,
      "step": 120
    },
    {
      "epoch": 1.2530120481927711,
      "grad_norm": 0.1666216403245926,
      "learning_rate": 0.0001,
      "loss": 0.256,
      "step": 130
    },
    {
      "epoch": 1.3493975903614457,
      "grad_norm": 0.1696414053440094,
      "learning_rate": 0.0001,
      "loss": 0.2529,
      "step": 140
    },
    {
      "epoch": 1.4457831325301205,
      "grad_norm": 0.16793620586395264,
      "learning_rate": 0.0001,
      "loss": 0.2466,
      "step": 150
    },
    {
      "epoch": 1.5421686746987953,
      "grad_norm": 0.19180789589881897,
      "learning_rate": 0.0001,
      "loss": 0.2446,
      "step": 160
    },
    {
      "epoch": 1.6385542168674698,
      "grad_norm": 0.18770650029182434,
      "learning_rate": 0.0001,
      "loss": 0.2446,
      "step": 170
    },
    {
      "epoch": 1.7349397590361446,
      "grad_norm": 0.1509401947259903,
      "learning_rate": 0.0001,
      "loss": 0.2418,
      "step": 180
    },
    {
      "epoch": 1.8313253012048194,
      "grad_norm": 0.1551649123430252,
      "learning_rate": 0.0001,
      "loss": 0.2391,
      "step": 190
    },
    {
      "epoch": 1.927710843373494,
      "grad_norm": 0.17986978590488434,
      "learning_rate": 0.0001,
      "loss": 0.2344,
      "step": 200
    },
    {
      "epoch": 2.0240963855421685,
      "grad_norm": 0.20075887441635132,
      "learning_rate": 0.0001,
      "loss": 0.2304,
      "step": 210
    },
    {
      "epoch": 2.1204819277108435,
      "grad_norm": 0.14372113347053528,
      "learning_rate": 0.0001,
      "loss": 0.2313,
      "step": 220
    },
    {
      "epoch": 2.216867469879518,
      "grad_norm": 0.17301425337791443,
      "learning_rate": 0.0001,
      "loss": 0.2294,
      "step": 230
    },
    {
      "epoch": 2.3132530120481927,
      "grad_norm": 0.1603270024061203,
      "learning_rate": 0.0001,
      "loss": 0.2238,
      "step": 240
    },
    {
      "epoch": 2.4096385542168672,
      "grad_norm": 0.1819937825202942,
      "learning_rate": 0.0001,
      "loss": 0.2236,
      "step": 250
    },
    {
      "epoch": 2.5060240963855422,
      "grad_norm": 0.201055645942688,
      "learning_rate": 0.0001,
      "loss": 0.2184,
      "step": 260
    },
    {
      "epoch": 2.602409638554217,
      "grad_norm": 0.17147445678710938,
      "learning_rate": 0.0001,
      "loss": 0.2205,
      "step": 270
    },
    {
      "epoch": 2.6987951807228914,
      "grad_norm": 0.12793570756912231,
      "learning_rate": 0.0001,
      "loss": 0.2146,
      "step": 280
    },
    {
      "epoch": 2.7951807228915664,
      "grad_norm": 0.18070928752422333,
      "learning_rate": 0.0001,
      "loss": 0.2163,
      "step": 290
    },
    {
      "epoch": 2.891566265060241,
      "grad_norm": 0.1529516875743866,
      "learning_rate": 0.0001,
      "loss": 0.216,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 309,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.547183001305088e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}