last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004120596112904333,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001373532037634778,
      "eval_loss": 10.835843086242676,
      "eval_runtime": 12.9786,
      "eval_samples_per_second": 236.236,
      "eval_steps_per_second": 118.118,
      "step": 1
    },
    {
      "epoch": 0.00041205961129043336,
      "grad_norm": 0.1319541186094284,
      "learning_rate": 4e-05,
      "loss": 10.835,
      "step": 3
    },
    {
      "epoch": 0.000686766018817389,
      "eval_loss": 10.835081100463867,
      "eval_runtime": 12.9356,
      "eval_samples_per_second": 237.021,
      "eval_steps_per_second": 118.51,
      "step": 5
    },
    {
      "epoch": 0.0008241192225808667,
      "grad_norm": 0.38596540689468384,
      "learning_rate": 8e-05,
      "loss": 10.8278,
      "step": 6
    },
    {
      "epoch": 0.0012361788338713,
      "grad_norm": 0.16341632604599,
      "learning_rate": 0.00012,
      "loss": 10.8326,
      "step": 9
    },
    {
      "epoch": 0.001373532037634778,
      "eval_loss": 10.832352638244629,
      "eval_runtime": 12.9359,
      "eval_samples_per_second": 237.014,
      "eval_steps_per_second": 118.507,
      "step": 10
    },
    {
      "epoch": 0.0016482384451617334,
      "grad_norm": 0.17010462284088135,
      "learning_rate": 0.00016,
      "loss": 10.8328,
      "step": 12
    },
    {
      "epoch": 0.0020602980564521666,
      "grad_norm": 0.17308123409748077,
      "learning_rate": 0.0002,
      "loss": 10.8282,
      "step": 15
    },
    {
      "epoch": 0.0020602980564521666,
      "eval_loss": 10.826925277709961,
      "eval_runtime": 12.9638,
      "eval_samples_per_second": 236.505,
      "eval_steps_per_second": 118.252,
      "step": 15
    },
    {
      "epoch": 0.0024723576677426,
      "grad_norm": 0.19254495203495026,
      "learning_rate": 0.00018090169943749476,
      "loss": 10.8235,
      "step": 18
    },
    {
      "epoch": 0.002747064075269556,
      "eval_loss": 10.819356918334961,
      "eval_runtime": 13.0087,
      "eval_samples_per_second": 235.689,
      "eval_steps_per_second": 117.844,
      "step": 20
    },
    {
      "epoch": 0.0028844172790330335,
      "grad_norm": 0.1905592381954193,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.8209,
      "step": 21
    },
    {
      "epoch": 0.003296476890323467,
      "grad_norm": 0.18835890293121338,
      "learning_rate": 6.909830056250527e-05,
      "loss": 10.8132,
      "step": 24
    },
    {
      "epoch": 0.0034338300940869445,
      "eval_loss": 10.814057350158691,
      "eval_runtime": 12.884,
      "eval_samples_per_second": 237.969,
      "eval_steps_per_second": 118.984,
      "step": 25
    },
    {
      "epoch": 0.0037085365016139003,
      "grad_norm": 0.28516891598701477,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 10.8092,
      "step": 27
    },
    {
      "epoch": 0.004120596112904333,
      "grad_norm": 0.23441976308822632,
      "learning_rate": 0.0,
      "loss": 10.8112,
      "step": 30
    },
    {
      "epoch": 0.004120596112904333,
      "eval_loss": 10.812871932983398,
      "eval_runtime": 12.8772,
      "eval_samples_per_second": 238.096,
      "eval_steps_per_second": 119.048,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6188197478400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}