last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032059845044082286,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00035622050048980317,
      "grad_norm": 0.9710186719894409,
      "learning_rate": 2e-05,
      "loss": 1.2377,
      "step": 1
    },
    {
      "epoch": 0.00035622050048980317,
      "eval_loss": 2.328693151473999,
      "eval_runtime": 33.1988,
      "eval_samples_per_second": 35.604,
      "eval_steps_per_second": 17.802,
      "step": 1
    },
    {
      "epoch": 0.0007124410009796063,
      "grad_norm": 0.877776563167572,
      "learning_rate": 4e-05,
      "loss": 1.5089,
      "step": 2
    },
    {
      "epoch": 0.0010686615014694097,
      "grad_norm": 1.2864619493484497,
      "learning_rate": 6e-05,
      "loss": 1.5115,
      "step": 3
    },
    {
      "epoch": 0.0010686615014694097,
      "eval_loss": 2.317746162414551,
      "eval_runtime": 33.2835,
      "eval_samples_per_second": 35.513,
      "eval_steps_per_second": 17.757,
      "step": 3
    },
    {
      "epoch": 0.0014248820019592127,
      "grad_norm": 1.4197344779968262,
      "learning_rate": 8e-05,
      "loss": 1.5582,
      "step": 4
    },
    {
      "epoch": 0.0017811025024490159,
      "grad_norm": 0.8563295006752014,
      "learning_rate": 0.0001,
      "loss": 0.9642,
      "step": 5
    },
    {
      "epoch": 0.0021373230029388193,
      "grad_norm": 0.9468586444854736,
      "learning_rate": 0.00012,
      "loss": 1.2557,
      "step": 6
    },
    {
      "epoch": 0.0021373230029388193,
      "eval_loss": 2.194425582885742,
      "eval_runtime": 33.2939,
      "eval_samples_per_second": 35.502,
      "eval_steps_per_second": 17.751,
      "step": 6
    },
    {
      "epoch": 0.002493543503428622,
      "grad_norm": 0.8728165030479431,
      "learning_rate": 0.00014,
      "loss": 1.3749,
      "step": 7
    },
    {
      "epoch": 0.0028497640039184253,
      "grad_norm": 0.936583399772644,
      "learning_rate": 0.00016,
      "loss": 1.4407,
      "step": 8
    },
    {
      "epoch": 0.0032059845044082286,
      "grad_norm": 0.7932253479957581,
      "learning_rate": 0.00018,
      "loss": 1.2949,
      "step": 9
    },
    {
      "epoch": 0.0032059845044082286,
      "eval_loss": 1.9489015340805054,
      "eval_runtime": 33.2862,
      "eval_samples_per_second": 35.51,
      "eval_steps_per_second": 17.755,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 525102197243904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}