last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008484162895927601,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.21934866905212402,
      "learning_rate": 0.0002,
      "loss": 2.1352,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.37619397044181824,
      "learning_rate": 0.0002,
      "loss": 2.3002,
      "step": 2
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.43210744857788086,
      "learning_rate": 0.0002,
      "loss": 2.041,
      "step": 3
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.4717111885547638,
      "learning_rate": 0.0002,
      "loss": 1.839,
      "step": 4
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.6455919146537781,
      "learning_rate": 0.0002,
      "loss": 1.5939,
      "step": 5
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.2801408767700195,
      "learning_rate": 0.0002,
      "loss": 1.327,
      "step": 6
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.9770981669425964,
      "learning_rate": 0.0002,
      "loss": 1.1536,
      "step": 7
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.177263617515564,
      "learning_rate": 0.0002,
      "loss": 0.9881,
      "step": 8
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.6201061606407166,
      "learning_rate": 0.0002,
      "loss": 0.8609,
      "step": 9
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.45395827293396,
      "learning_rate": 0.0002,
      "loss": 0.8477,
      "step": 10
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.0724296569824219,
      "learning_rate": 0.0002,
      "loss": 0.7573,
      "step": 11
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.9028312563896179,
      "learning_rate": 0.0002,
      "loss": 0.7258,
      "step": 12
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.8523911237716675,
      "learning_rate": 0.0002,
      "loss": 0.7513,
      "step": 13
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.6326367855072021,
      "learning_rate": 0.0002,
      "loss": 0.7186,
      "step": 14
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.39301833510398865,
      "learning_rate": 0.0002,
      "loss": 0.706,
      "step": 15
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.5725602507591248,
      "learning_rate": 0.0002,
      "loss": 0.6406,
      "step": 16
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.6625002026557922,
      "learning_rate": 0.0002,
      "loss": 0.6349,
      "step": 17
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.19412539899349213,
      "learning_rate": 0.0002,
      "loss": 0.6134,
      "step": 18
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.34864893555641174,
      "learning_rate": 0.0002,
      "loss": 0.6381,
      "step": 19
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.30731046199798584,
      "learning_rate": 0.0002,
      "loss": 0.6553,
      "step": 20
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.1636987179517746,
      "learning_rate": 0.0002,
      "loss": 0.5984,
      "step": 21
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.1931622475385666,
      "learning_rate": 0.0002,
      "loss": 0.5821,
      "step": 22
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.32078325748443604,
      "learning_rate": 0.0002,
      "loss": 0.586,
      "step": 23
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.17550581693649292,
      "learning_rate": 0.0002,
      "loss": 0.5315,
      "step": 24
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.22394584119319916,
      "learning_rate": 0.0002,
      "loss": 0.5415,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 2946,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 6828259445391360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}