trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 0.24846524000167847,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.2054,
      "step": 1
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 0.23854631185531616,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.1943,
      "step": 2
    },
    {
      "epoch": 0.19672131147540983,
      "grad_norm": 0.12206465750932693,
      "learning_rate": 2.4e-05,
      "loss": 0.1598,
      "step": 3
    },
    {
      "epoch": 0.26229508196721313,
      "grad_norm": 0.10146363824605942,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.1503,
      "step": 4
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.29939085245132446,
      "learning_rate": 4e-05,
      "loss": 0.1893,
      "step": 5
    },
    {
      "epoch": 0.39344262295081966,
      "grad_norm": 0.23336249589920044,
      "learning_rate": 3.9938346674662565e-05,
      "loss": 0.1819,
      "step": 6
    },
    {
      "epoch": 0.45901639344262296,
      "grad_norm": 0.0746205598115921,
      "learning_rate": 3.9753766811902756e-05,
      "loss": 0.1577,
      "step": 7
    },
    {
      "epoch": 0.5245901639344263,
      "grad_norm": 0.07674132287502289,
      "learning_rate": 3.9447398407953536e-05,
      "loss": 0.1482,
      "step": 8
    },
    {
      "epoch": 0.5901639344262295,
      "grad_norm": 0.055854540318250656,
      "learning_rate": 3.9021130325903076e-05,
      "loss": 0.135,
      "step": 9
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.04436395317316055,
      "learning_rate": 3.8477590650225735e-05,
      "loss": 0.1366,
      "step": 10
    },
    {
      "epoch": 0.7213114754098361,
      "grad_norm": 0.053606096655130386,
      "learning_rate": 3.782013048376736e-05,
      "loss": 0.128,
      "step": 11
    },
    {
      "epoch": 0.7868852459016393,
      "grad_norm": 0.036096639931201935,
      "learning_rate": 3.705280328708185e-05,
      "loss": 0.1205,
      "step": 12
    },
    {
      "epoch": 0.8524590163934426,
      "grad_norm": 0.032327715307474136,
      "learning_rate": 3.6180339887498953e-05,
      "loss": 0.1193,
      "step": 13
    },
    {
      "epoch": 0.9180327868852459,
      "grad_norm": 0.03768343850970268,
      "learning_rate": 3.520811931200063e-05,
      "loss": 0.123,
      "step": 14
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.03514982387423515,
      "learning_rate": 3.4142135623730954e-05,
      "loss": 0.125,
      "step": 15
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.03514982387423515,
      "learning_rate": 3.298896096660367e-05,
      "loss": 0.1023,
      "step": 16
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 45,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 31455266734080.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}