last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003446229250828052,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.8291436120311695e-05,
      "grad_norm": 5.167859077453613,
      "learning_rate": 2e-05,
      "loss": 4.2271,
      "step": 1
    },
    {
      "epoch": 3.8291436120311695e-05,
      "eval_loss": 2.2706639766693115,
      "eval_runtime": 1008.1823,
      "eval_samples_per_second": 5.453,
      "eval_steps_per_second": 2.727,
      "step": 1
    },
    {
      "epoch": 7.658287224062339e-05,
      "grad_norm": 1.0517507791519165,
      "learning_rate": 4e-05,
      "loss": 1.9998,
      "step": 2
    },
    {
      "epoch": 0.00011487430836093508,
      "grad_norm": 0.8671896457672119,
      "learning_rate": 6e-05,
      "loss": 1.4522,
      "step": 3
    },
    {
      "epoch": 0.00011487430836093508,
      "eval_loss": 2.257763147354126,
      "eval_runtime": 1008.5431,
      "eval_samples_per_second": 5.451,
      "eval_steps_per_second": 2.726,
      "step": 3
    },
    {
      "epoch": 0.00015316574448124678,
      "grad_norm": 3.5897583961486816,
      "learning_rate": 8e-05,
      "loss": 3.2432,
      "step": 4
    },
    {
      "epoch": 0.00019145718060155847,
      "grad_norm": 1.8159574270248413,
      "learning_rate": 0.0001,
      "loss": 3.0641,
      "step": 5
    },
    {
      "epoch": 0.00022974861672187016,
      "grad_norm": 0.7535229325294495,
      "learning_rate": 0.00012,
      "loss": 1.82,
      "step": 6
    },
    {
      "epoch": 0.00022974861672187016,
      "eval_loss": 2.150543451309204,
      "eval_runtime": 1008.4579,
      "eval_samples_per_second": 5.452,
      "eval_steps_per_second": 2.726,
      "step": 6
    },
    {
      "epoch": 0.00026804005284218184,
      "grad_norm": 1.0133801698684692,
      "learning_rate": 0.00014,
      "loss": 2.3383,
      "step": 7
    },
    {
      "epoch": 0.00030633148896249356,
      "grad_norm": 1.2487194538116455,
      "learning_rate": 0.00016,
      "loss": 1.2447,
      "step": 8
    },
    {
      "epoch": 0.0003446229250828052,
      "grad_norm": 0.8460904359817505,
      "learning_rate": 0.00018,
      "loss": 1.3048,
      "step": 9
    },
    {
      "epoch": 0.0003446229250828052,
      "eval_loss": 1.9420808553695679,
      "eval_runtime": 1008.6015,
      "eval_samples_per_second": 5.451,
      "eval_steps_per_second": 2.726,
      "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": 5881123817127936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}