checkpoint-3000/trainer_state.json

{
  "best_metric": 1.1920161247253418,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e6l56-l/checkpoint-3000",
  "epoch": 0.552689756816507,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09211495946941783,
      "grad_norm": 0.49671515822410583,
      "learning_rate": 4.923237533775486e-06,
      "loss": 0.2159,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.4818799495697021,
      "eval_runtime": 72.2844,
      "eval_samples_per_second": 16.698,
      "eval_steps_per_second": 2.089,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 0.0015633106231689453,
      "learning_rate": 4.846475067550971e-06,
      "loss": 0.2648,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 1.4225908517837524,
      "eval_runtime": 73.6999,
      "eval_samples_per_second": 16.377,
      "eval_steps_per_second": 2.049,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 0.047471947968006134,
      "learning_rate": 4.769712601326456e-06,
      "loss": 0.328,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 1.412400245666504,
      "eval_runtime": 74.9915,
      "eval_samples_per_second": 16.095,
      "eval_steps_per_second": 2.014,
      "step": 1500
    },
    {
      "epoch": 0.36845983787767134,
      "grad_norm": 3.9284778208248383e-10,
      "learning_rate": 4.692950135101941e-06,
      "loss": 0.1813,
      "step": 2000
    },
    {
      "epoch": 0.36845983787767134,
      "eval_loss": 1.2844351530075073,
      "eval_runtime": 74.7649,
      "eval_samples_per_second": 16.144,
      "eval_steps_per_second": 2.02,
      "step": 2000
    },
    {
      "epoch": 0.46057479734708917,
      "grad_norm": 514.6055297851562,
      "learning_rate": 4.616187668877426e-06,
      "loss": 0.4836,
      "step": 2500
    },
    {
      "epoch": 0.46057479734708917,
      "eval_loss": 1.301351547241211,
      "eval_runtime": 74.7994,
      "eval_samples_per_second": 16.136,
      "eval_steps_per_second": 2.019,
      "step": 2500
    },
    {
      "epoch": 0.552689756816507,
      "grad_norm": 127.98405456542969,
      "learning_rate": 4.5394252026529115e-06,
      "loss": 0.2803,
      "step": 3000
    },
    {
      "epoch": 0.552689756816507,
      "eval_loss": 1.1920161247253418,
      "eval_runtime": 75.5447,
      "eval_samples_per_second": 15.977,
      "eval_steps_per_second": 1.999,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 32568,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1079994570482520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}