last-checkpoint/trainer_state.json

{
  "best_metric": 3.461520195007324,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.014124293785310734,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047080979284369113,
      "eval_loss": 4.516218185424805,
      "eval_runtime": 189.8885,
      "eval_samples_per_second": 4.713,
      "eval_steps_per_second": 2.359,
      "step": 1
    },
    {
      "epoch": 0.0014124293785310734,
      "grad_norm": 1.3684500455856323,
      "learning_rate": 0.00012,
      "loss": 3.3336,
      "step": 3
    },
    {
      "epoch": 0.0023540489642184556,
      "eval_loss": 4.260828018188477,
      "eval_runtime": 211.2846,
      "eval_samples_per_second": 4.236,
      "eval_steps_per_second": 2.12,
      "step": 5
    },
    {
      "epoch": 0.002824858757062147,
      "grad_norm": 1.5670804977416992,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.6155,
      "step": 6
    },
    {
      "epoch": 0.00423728813559322,
      "grad_norm": 1.5346250534057617,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.4086,
      "step": 9
    },
    {
      "epoch": 0.004708097928436911,
      "eval_loss": 3.814056396484375,
      "eval_runtime": 210.3214,
      "eval_samples_per_second": 4.255,
      "eval_steps_per_second": 2.13,
      "step": 10
    },
    {
      "epoch": 0.005649717514124294,
      "grad_norm": 1.583258867263794,
      "learning_rate": 0.000163742398974869,
      "loss": 3.4178,
      "step": 12
    },
    {
      "epoch": 0.007062146892655367,
      "grad_norm": 1.6109554767608643,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.2549,
      "step": 15
    },
    {
      "epoch": 0.007062146892655367,
      "eval_loss": 3.5871899127960205,
      "eval_runtime": 209.6126,
      "eval_samples_per_second": 4.27,
      "eval_steps_per_second": 2.137,
      "step": 15
    },
    {
      "epoch": 0.00847457627118644,
      "grad_norm": 1.8463785648345947,
      "learning_rate": 9.372094804706867e-05,
      "loss": 3.4706,
      "step": 18
    },
    {
      "epoch": 0.009416195856873822,
      "eval_loss": 3.4954330921173096,
      "eval_runtime": 208.9877,
      "eval_samples_per_second": 4.283,
      "eval_steps_per_second": 2.144,
      "step": 20
    },
    {
      "epoch": 0.009887005649717515,
      "grad_norm": 2.2122228145599365,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 3.4689,
      "step": 21
    },
    {
      "epoch": 0.011299435028248588,
      "grad_norm": 2.0522589683532715,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 3.3605,
      "step": 24
    },
    {
      "epoch": 0.011770244821092278,
      "eval_loss": 3.4695844650268555,
      "eval_runtime": 209.3727,
      "eval_samples_per_second": 4.275,
      "eval_steps_per_second": 2.14,
      "step": 25
    },
    {
      "epoch": 0.012711864406779662,
      "grad_norm": 2.119175910949707,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.6951,
      "step": 27
    },
    {
      "epoch": 0.014124293785310734,
      "grad_norm": 2.415921211242676,
      "learning_rate": 0.0,
      "loss": 3.4002,
      "step": 30
    },
    {
      "epoch": 0.014124293785310734,
      "eval_loss": 3.461520195007324,
      "eval_runtime": 209.0434,
      "eval_samples_per_second": 4.281,
      "eval_steps_per_second": 2.143,
      "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": 1.2819192562581504e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}