last-checkpoint/trainer_state.json

{
  "best_metric": 0.8222852349281311,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.007895775759968417,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002631925253322806,
      "eval_loss": 1.2169289588928223,
      "eval_runtime": 458.4085,
      "eval_samples_per_second": 6.981,
      "eval_steps_per_second": 1.745,
      "step": 1
    },
    {
      "epoch": 0.0007895775759968417,
      "grad_norm": 3.563742160797119,
      "learning_rate": 0.00012,
      "loss": 3.8291,
      "step": 3
    },
    {
      "epoch": 0.0013159626266614028,
      "eval_loss": 1.008426547050476,
      "eval_runtime": 462.8779,
      "eval_samples_per_second": 6.913,
      "eval_steps_per_second": 1.728,
      "step": 5
    },
    {
      "epoch": 0.0015791551519936833,
      "grad_norm": 2.7800955772399902,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.4193,
      "step": 6
    },
    {
      "epoch": 0.002368732727990525,
      "grad_norm": 1.959545373916626,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.1617,
      "step": 9
    },
    {
      "epoch": 0.0026319252533228057,
      "eval_loss": 0.8942686319351196,
      "eval_runtime": 459.4632,
      "eval_samples_per_second": 6.965,
      "eval_steps_per_second": 1.741,
      "step": 10
    },
    {
      "epoch": 0.0031583103039873666,
      "grad_norm": 1.8942865133285522,
      "learning_rate": 0.000163742398974869,
      "loss": 3.2126,
      "step": 12
    },
    {
      "epoch": 0.0039478878799842085,
      "grad_norm": 2.632387638092041,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.1678,
      "step": 15
    },
    {
      "epoch": 0.0039478878799842085,
      "eval_loss": 0.8524987697601318,
      "eval_runtime": 459.1579,
      "eval_samples_per_second": 6.969,
      "eval_steps_per_second": 1.742,
      "step": 15
    },
    {
      "epoch": 0.00473746545598105,
      "grad_norm": 1.9677852392196655,
      "learning_rate": 9.372094804706867e-05,
      "loss": 3.2285,
      "step": 18
    },
    {
      "epoch": 0.005263850506645611,
      "eval_loss": 0.8367408514022827,
      "eval_runtime": 461.6482,
      "eval_samples_per_second": 6.932,
      "eval_steps_per_second": 1.733,
      "step": 20
    },
    {
      "epoch": 0.005527043031977891,
      "grad_norm": 2.336571455001831,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 3.2396,
      "step": 21
    },
    {
      "epoch": 0.006316620607974733,
      "grad_norm": 1.9358288049697876,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 3.3153,
      "step": 24
    },
    {
      "epoch": 0.006579813133307014,
      "eval_loss": 0.824735701084137,
      "eval_runtime": 460.9414,
      "eval_samples_per_second": 6.942,
      "eval_steps_per_second": 1.736,
      "step": 25
    },
    {
      "epoch": 0.007106198183971575,
      "grad_norm": 2.247568130493164,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.4157,
      "step": 27
    },
    {
      "epoch": 0.007895775759968417,
      "grad_norm": 2.3092644214630127,
      "learning_rate": 0.0,
      "loss": 3.5174,
      "step": 30
    },
    {
      "epoch": 0.007895775759968417,
      "eval_loss": 0.8222852349281311,
      "eval_runtime": 462.7305,
      "eval_samples_per_second": 6.915,
      "eval_steps_per_second": 1.729,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.162123208445133e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}