checkpoint-1600/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14670150827488196,
  "eval_steps": 200,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "eval_bertscore": 0.7401605248451233,
      "eval_loss": 1.9530484676361084,
      "eval_rouge1": 0.6562857460474375,
      "eval_rouge2": 0.3640670727106235,
      "eval_rougeL": 0.5655212336424695,
      "eval_rougeLsum": 0.6414840198810386,
      "eval_runtime": 21.7196,
      "eval_samples_per_second": 1.381,
      "eval_steps_per_second": 0.691,
      "step": 200
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.25105270743370056,
      "learning_rate": 0.00019771674842969145,
      "loss": 1.7353,
      "step": 250
    },
    {
      "epoch": 0.04,
      "eval_bertscore": 0.7432050108909607,
      "eval_loss": 1.9583823680877686,
      "eval_rouge1": 0.6554226269617707,
      "eval_rouge2": 0.36661086995296877,
      "eval_rougeL": 0.5637448790342183,
      "eval_rougeLsum": 0.6419796784912521,
      "eval_runtime": 21.9623,
      "eval_samples_per_second": 1.366,
      "eval_steps_per_second": 0.683,
      "step": 400
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.26550447940826416,
      "learning_rate": 0.00019542432717436156,
      "loss": 1.7786,
      "step": 500
    },
    {
      "epoch": 0.06,
      "eval_bertscore": 0.7469045519828796,
      "eval_loss": 1.9245686531066895,
      "eval_rouge1": 0.6662431635890791,
      "eval_rouge2": 0.3735263724826765,
      "eval_rougeL": 0.5755071616151013,
      "eval_rougeLsum": 0.6538383087686117,
      "eval_runtime": 21.5302,
      "eval_samples_per_second": 1.393,
      "eval_steps_per_second": 0.697,
      "step": 600
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.1538015753030777,
      "learning_rate": 0.0001931319059190317,
      "loss": 1.8851,
      "step": 750
    },
    {
      "epoch": 0.07,
      "eval_bertscore": 0.7442477941513062,
      "eval_loss": 1.9187489748001099,
      "eval_rouge1": 0.6606221897489035,
      "eval_rouge2": 0.368654563659435,
      "eval_rougeL": 0.5731546210408094,
      "eval_rougeLsum": 0.6470590823125606,
      "eval_runtime": 21.9831,
      "eval_samples_per_second": 1.365,
      "eval_steps_per_second": 0.682,
      "step": 800
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.1681252270936966,
      "learning_rate": 0.0001908394846637018,
      "loss": 1.8919,
      "step": 1000
    },
    {
      "epoch": 0.09,
      "eval_bertscore": 0.7458053231239319,
      "eval_loss": 1.9159075021743774,
      "eval_rouge1": 0.6621259186456026,
      "eval_rouge2": 0.372024043683234,
      "eval_rougeL": 0.5743354509339939,
      "eval_rougeLsum": 0.6491550893780276,
      "eval_runtime": 21.7159,
      "eval_samples_per_second": 1.381,
      "eval_steps_per_second": 0.691,
      "step": 1000
    },
    {
      "epoch": 0.11,
      "eval_bertscore": 0.7468854784965515,
      "eval_loss": 1.9140182733535767,
      "eval_rouge1": 0.6626581781149132,
      "eval_rouge2": 0.37318557504782157,
      "eval_rougeL": 0.5759264203594217,
      "eval_rougeLsum": 0.6490702446275723,
      "eval_runtime": 21.6486,
      "eval_samples_per_second": 1.386,
      "eval_steps_per_second": 0.693,
      "step": 1200
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.1552441120147705,
      "learning_rate": 0.00018854706340837193,
      "loss": 1.9052,
      "step": 1250
    },
    {
      "epoch": 0.13,
      "eval_bertscore": 0.7475314736366272,
      "eval_loss": 1.913794755935669,
      "eval_rouge1": 0.6648687174353192,
      "eval_rouge2": 0.3760379232448734,
      "eval_rougeL": 0.5784915488164926,
      "eval_rougeLsum": 0.6513864520108938,
      "eval_runtime": 21.664,
      "eval_samples_per_second": 1.385,
      "eval_steps_per_second": 0.692,
      "step": 1400
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.14638397097587585,
      "learning_rate": 0.00018625464215304204,
      "loss": 1.8843,
      "step": 1500
    },
    {
      "epoch": 0.15,
      "eval_bertscore": 0.747238039970398,
      "eval_loss": 1.9117029905319214,
      "eval_rouge1": 0.6638085237198453,
      "eval_rouge2": 0.3742779818055127,
      "eval_rougeL": 0.5754209460423059,
      "eval_rougeLsum": 0.6506476155592722,
      "eval_runtime": 21.9308,
      "eval_samples_per_second": 1.368,
      "eval_steps_per_second": 0.684,
      "step": 1600
    }
  ],
  "logging_steps": 250,
  "max_steps": 21812,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 800,
  "total_flos": 1.07858507071488e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}