trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9884169884169884,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06177606177606178,
      "grad_norm": 0.11829973012208939,
      "learning_rate": 2e-05,
      "loss": 1.9082,
      "step": 1
    },
    {
      "epoch": 0.12355212355212356,
      "grad_norm": 0.12353809177875519,
      "learning_rate": 4e-05,
      "loss": 1.902,
      "step": 2
    },
    {
      "epoch": 0.18532818532818532,
      "grad_norm": 0.11157257109880447,
      "learning_rate": 6e-05,
      "loss": 1.9608,
      "step": 3
    },
    {
      "epoch": 0.2471042471042471,
      "grad_norm": 0.13446162641048431,
      "learning_rate": 8e-05,
      "loss": 1.8379,
      "step": 4
    },
    {
      "epoch": 0.3088803088803089,
      "grad_norm": 0.12090934813022614,
      "learning_rate": 0.0001,
      "loss": 1.9759,
      "step": 5
    },
    {
      "epoch": 0.37065637065637064,
      "grad_norm": 0.1425676792860031,
      "learning_rate": 0.00012,
      "loss": 1.8112,
      "step": 6
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.09401809424161911,
      "learning_rate": 0.00014,
      "loss": 1.844,
      "step": 7
    },
    {
      "epoch": 0.4942084942084942,
      "grad_norm": 0.10318582504987717,
      "learning_rate": 0.00016,
      "loss": 1.8519,
      "step": 8
    },
    {
      "epoch": 0.555984555984556,
      "grad_norm": 0.17398066818714142,
      "learning_rate": 0.00018,
      "loss": 1.8401,
      "step": 9
    },
    {
      "epoch": 0.6177606177606177,
      "grad_norm": 0.14428512752056122,
      "learning_rate": 0.0002,
      "loss": 1.8799,
      "step": 10
    },
    {
      "epoch": 0.6795366795366795,
      "grad_norm": 0.0983770415186882,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.8504,
      "step": 11
    },
    {
      "epoch": 0.7413127413127413,
      "grad_norm": 0.0758327767252922,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.9038,
      "step": 12
    },
    {
      "epoch": 0.803088803088803,
      "grad_norm": 0.0723545029759407,
      "learning_rate": 0.0001,
      "loss": 1.8041,
      "step": 13
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.07799698412418365,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.8519,
      "step": 14
    },
    {
      "epoch": 0.9266409266409267,
      "grad_norm": 0.08120666444301605,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.8206,
      "step": 15
    },
    {
      "epoch": 0.9884169884169884,
      "grad_norm": 0.06756243109703064,
      "learning_rate": 0.0,
      "loss": 1.8063,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.087445439987057e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}