trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1764705882352942,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 6.380861282348633,
      "learning_rate": 4e-05,
      "loss": 1.2336,
      "step": 1
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 6.581923961639404,
      "learning_rate": 8e-05,
      "loss": 1.2422,
      "step": 2
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 3.7366814613342285,
      "learning_rate": 0.00012,
      "loss": 1.232,
      "step": 3
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 2.0385751724243164,
      "learning_rate": 0.00016,
      "loss": 0.9913,
      "step": 4
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 3.706179141998291,
      "learning_rate": 0.0002,
      "loss": 0.7839,
      "step": 5
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 2.4191720485687256,
      "learning_rate": 0.00016,
      "loss": 0.6118,
      "step": 6
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 5.164414882659912,
      "learning_rate": 0.00012,
      "loss": 0.4166,
      "step": 7
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.263913869857788,
      "learning_rate": 8e-05,
      "loss": 0.2625,
      "step": 8
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 6.900355339050293,
      "learning_rate": 4e-05,
      "loss": 0.2826,
      "step": 9
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.510345697402954,
      "learning_rate": 0.0,
      "loss": 0.2053,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1128473317238784.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}