trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5923566878980893,
  "eval_steps": 7000,
  "global_step": 56000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19904458598726116,
      "grad_norm": 0.2248842865228653,
      "learning_rate": 9.947398350867217e-06,
      "loss": 0.0083,
      "step": 7000
    },
    {
      "epoch": 0.19904458598726116,
      "eval_loss": 0.002906730631366372,
      "eval_runtime": 281.988,
      "eval_samples_per_second": 249.429,
      "eval_steps_per_second": 31.179,
      "step": 7000
    },
    {
      "epoch": 0.3980891719745223,
      "grad_norm": 0.0002081295824609697,
      "learning_rate": 8.900350699819912e-06,
      "loss": 0.0026,
      "step": 14000
    },
    {
      "epoch": 0.3980891719745223,
      "eval_loss": 0.0018650980200618505,
      "eval_runtime": 284.0569,
      "eval_samples_per_second": 247.612,
      "eval_steps_per_second": 30.952,
      "step": 14000
    },
    {
      "epoch": 0.5971337579617835,
      "grad_norm": 0.010839835740625858,
      "learning_rate": 7.795014375533159e-06,
      "loss": 0.0015,
      "step": 21000
    },
    {
      "epoch": 0.5971337579617835,
      "eval_loss": 0.001360387192107737,
      "eval_runtime": 285.5315,
      "eval_samples_per_second": 246.334,
      "eval_steps_per_second": 30.792,
      "step": 21000
    },
    {
      "epoch": 0.7961783439490446,
      "grad_norm": 0.00013278079859446734,
      "learning_rate": 6.689836024138259e-06,
      "loss": 0.0013,
      "step": 28000
    },
    {
      "epoch": 0.7961783439490446,
      "eval_loss": 0.0011233221739530563,
      "eval_runtime": 285.4742,
      "eval_samples_per_second": 246.383,
      "eval_steps_per_second": 30.798,
      "step": 28000
    },
    {
      "epoch": 0.9952229299363057,
      "grad_norm": 0.00014249606465455145,
      "learning_rate": 5.5841837540678024e-06,
      "loss": 0.0013,
      "step": 35000
    },
    {
      "epoch": 0.9952229299363057,
      "eval_loss": 0.0010357595747336745,
      "eval_runtime": 286.0827,
      "eval_samples_per_second": 245.859,
      "eval_steps_per_second": 30.732,
      "step": 35000
    },
    {
      "epoch": 1.194267515923567,
      "grad_norm": 0.0002924288564827293,
      "learning_rate": 4.478689456889198e-06,
      "loss": 0.0008,
      "step": 42000
    },
    {
      "epoch": 1.194267515923567,
      "eval_loss": 0.0010089210700243711,
      "eval_runtime": 282.9155,
      "eval_samples_per_second": 248.611,
      "eval_steps_per_second": 31.076,
      "step": 42000
    },
    {
      "epoch": 1.393312101910828,
      "grad_norm": 0.00017198333807755262,
      "learning_rate": 3.3733531326024454e-06,
      "loss": 0.0005,
      "step": 49000
    },
    {
      "epoch": 1.393312101910828,
      "eval_loss": 0.0009262111852876842,
      "eval_runtime": 285.6294,
      "eval_samples_per_second": 246.249,
      "eval_steps_per_second": 30.781,
      "step": 49000
    },
    {
      "epoch": 1.5923566878980893,
      "grad_norm": 2.850917553587351e-05,
      "learning_rate": 2.2678588354238415e-06,
      "loss": 0.0003,
      "step": 56000
    },
    {
      "epoch": 1.5923566878980893,
      "eval_loss": 0.0008692654664628208,
      "eval_runtime": 281.4473,
      "eval_samples_per_second": 249.908,
      "eval_steps_per_second": 31.239,
      "step": 56000
    }
  ],
  "logging_steps": 7000,
  "max_steps": 70336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}