last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4468085106382977,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05673758865248227,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.05673758865248227,
      "eval_loss": NaN,
      "eval_runtime": 5.3644,
      "eval_samples_per_second": 2.796,
      "eval_steps_per_second": 1.491,
      "step": 1
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": NaN,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": NaN,
      "learning_rate": 9.96210254835968e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": NaN,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": NaN,
      "learning_rate": 9.848984680175049e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": NaN,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": NaN,
      "learning_rate": 9.662361147021779e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": NaN,
      "learning_rate": 9.542326359097619e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": NaN,
      "learning_rate": 9.405060971428923e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.624113475177305,
      "grad_norm": NaN,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": NaN,
      "learning_rate": 9.08098456178111e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.7375886524822695,
      "grad_norm": NaN,
      "learning_rate": 8.895402872628352e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.7943262411347518,
      "grad_norm": NaN,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": NaN,
      "learning_rate": 8.480669729814635e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.9078014184397163,
      "grad_norm": NaN,
      "learning_rate": 8.25309150102121e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.9645390070921985,
      "grad_norm": NaN,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.049645390070922,
      "grad_norm": NaN,
      "learning_rate": 7.76182486480253e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.1063829787234043,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.1631205673758864,
      "grad_norm": NaN,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.2198581560283688,
      "grad_norm": NaN,
      "learning_rate": 6.948929366463396e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": NaN,
      "learning_rate": 6.661773997398298e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": NaN,
      "learning_rate": 6.368314950360415e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.3900709219858156,
      "grad_norm": NaN,
      "learning_rate": 6.069665416032487e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.4468085106382977,
      "grad_norm": NaN,
      "learning_rate": 5.7669582743934284e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.4468085106382977,
      "eval_loss": NaN,
      "eval_runtime": 5.0452,
      "eval_samples_per_second": 2.973,
      "eval_steps_per_second": 1.586,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 53,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.746225840128e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}