last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007665772326561901,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007665772326561902,
      "grad_norm": 2.21907639503479,
      "learning_rate": 2e-05,
      "loss": 3.9583,
      "step": 1
    },
    {
      "epoch": 0.0007665772326561902,
      "eval_loss": 0.9905641674995422,
      "eval_runtime": 16.517,
      "eval_samples_per_second": 33.299,
      "eval_steps_per_second": 16.65,
      "step": 1
    },
    {
      "epoch": 0.0015331544653123803,
      "grad_norm": 1.9840973615646362,
      "learning_rate": 4e-05,
      "loss": 3.9198,
      "step": 2
    },
    {
      "epoch": 0.0022997316979685703,
      "grad_norm": 2.0610175132751465,
      "learning_rate": 6e-05,
      "loss": 3.8546,
      "step": 3
    },
    {
      "epoch": 0.0022997316979685703,
      "eval_loss": 0.9854159355163574,
      "eval_runtime": 16.4134,
      "eval_samples_per_second": 33.509,
      "eval_steps_per_second": 16.755,
      "step": 3
    },
    {
      "epoch": 0.0030663089306247606,
      "grad_norm": 2.0427134037017822,
      "learning_rate": 8e-05,
      "loss": 3.7017,
      "step": 4
    },
    {
      "epoch": 0.0038328861632809506,
      "grad_norm": 2.6414690017700195,
      "learning_rate": 0.0001,
      "loss": 4.1406,
      "step": 5
    },
    {
      "epoch": 0.0045994633959371405,
      "grad_norm": 2.220031261444092,
      "learning_rate": 0.00012,
      "loss": 3.3839,
      "step": 6
    },
    {
      "epoch": 0.0045994633959371405,
      "eval_loss": 0.935398280620575,
      "eval_runtime": 16.7375,
      "eval_samples_per_second": 32.86,
      "eval_steps_per_second": 16.43,
      "step": 6
    },
    {
      "epoch": 0.005366040628593331,
      "grad_norm": 2.7698333263397217,
      "learning_rate": 0.00014,
      "loss": 4.302,
      "step": 7
    },
    {
      "epoch": 0.006132617861249521,
      "grad_norm": 3.5623602867126465,
      "learning_rate": 0.00016,
      "loss": 3.4733,
      "step": 8
    },
    {
      "epoch": 0.006899195093905711,
      "grad_norm": 2.596081256866455,
      "learning_rate": 0.00018,
      "loss": 3.3853,
      "step": 9
    },
    {
      "epoch": 0.006899195093905711,
      "eval_loss": 0.7518635988235474,
      "eval_runtime": 16.5706,
      "eval_samples_per_second": 33.191,
      "eval_steps_per_second": 16.596,
      "step": 9
    },
    {
      "epoch": 0.007665772326561901,
      "grad_norm": 2.2372212409973145,
      "learning_rate": 0.0002,
      "loss": 2.4515,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 917953377730560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}