last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009012617664730624,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003004205888243541,
      "eval_loss": 2.7872743606567383,
      "eval_runtime": 88.3464,
      "eval_samples_per_second": 11.908,
      "eval_steps_per_second": 5.954,
      "step": 1
    },
    {
      "epoch": 0.0009012617664730623,
      "grad_norm": 1.1402565240859985,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.7378,
      "step": 3
    },
    {
      "epoch": 0.0018025235329461246,
      "grad_norm": 2.1231765747070312,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.939,
      "step": 6
    },
    {
      "epoch": 0.002403364710594833,
      "eval_loss": 2.432232618331909,
      "eval_runtime": 88.9769,
      "eval_samples_per_second": 11.823,
      "eval_steps_per_second": 5.912,
      "step": 8
    },
    {
      "epoch": 0.0027037852994191867,
      "grad_norm": 1.5503355264663696,
      "learning_rate": 0.00027,
      "loss": 2.5135,
      "step": 9
    },
    {
      "epoch": 0.0036050470658922492,
      "grad_norm": 1.399559736251831,
      "learning_rate": 0.00029265847744427303,
      "loss": 2.3922,
      "step": 12
    },
    {
      "epoch": 0.004506308832365312,
      "grad_norm": 1.0500314235687256,
      "learning_rate": 0.00025606601717798207,
      "loss": 2.0311,
      "step": 15
    },
    {
      "epoch": 0.004806729421189666,
      "eval_loss": 2.156785011291504,
      "eval_runtime": 89.5225,
      "eval_samples_per_second": 11.751,
      "eval_steps_per_second": 5.876,
      "step": 16
    },
    {
      "epoch": 0.005407570598838373,
      "grad_norm": 1.1485878229141235,
      "learning_rate": 0.0001963525491562421,
      "loss": 2.1654,
      "step": 18
    },
    {
      "epoch": 0.006308832365311436,
      "grad_norm": 1.0800117254257202,
      "learning_rate": 0.00012653483024396533,
      "loss": 2.0277,
      "step": 21
    },
    {
      "epoch": 0.0072100941317844985,
      "grad_norm": 1.12771475315094,
      "learning_rate": 6.183221215612904e-05,
      "loss": 2.1248,
      "step": 24
    },
    {
      "epoch": 0.0072100941317844985,
      "eval_loss": 2.105942487716675,
      "eval_runtime": 89.1213,
      "eval_samples_per_second": 11.804,
      "eval_steps_per_second": 5.902,
      "step": 24
    },
    {
      "epoch": 0.008111355898257561,
      "grad_norm": 1.0826979875564575,
      "learning_rate": 1.634902137174483e-05,
      "loss": 2.0851,
      "step": 27
    },
    {
      "epoch": 0.009012617664730624,
      "grad_norm": 0.8876891136169434,
      "learning_rate": 0.0,
      "loss": 2.0737,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8346231940055040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}