last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0035945363048166786,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011981787682722263,
      "eval_loss": 10.837915420532227,
      "eval_runtime": 14.5061,
      "eval_samples_per_second": 242.311,
      "eval_steps_per_second": 121.19,
      "step": 1
    },
    {
      "epoch": 0.0003594536304816679,
      "grad_norm": 0.20624394714832306,
      "learning_rate": 6e-05,
      "loss": 10.8326,
      "step": 3
    },
    {
      "epoch": 0.0005990893841361131,
      "eval_loss": 10.836527824401855,
      "eval_runtime": 14.0891,
      "eval_samples_per_second": 249.483,
      "eval_steps_per_second": 124.777,
      "step": 5
    },
    {
      "epoch": 0.0007189072609633358,
      "grad_norm": 0.23632025718688965,
      "learning_rate": 0.00012,
      "loss": 10.8328,
      "step": 6
    },
    {
      "epoch": 0.0010783608914450035,
      "grad_norm": 0.2031337171792984,
      "learning_rate": 0.00018,
      "loss": 10.8302,
      "step": 9
    },
    {
      "epoch": 0.0011981787682722263,
      "eval_loss": 10.831363677978516,
      "eval_runtime": 14.1282,
      "eval_samples_per_second": 248.794,
      "eval_steps_per_second": 124.432,
      "step": 10
    },
    {
      "epoch": 0.0014378145219266715,
      "grad_norm": 0.23456250131130219,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.8349,
      "step": 12
    },
    {
      "epoch": 0.0017972681524083393,
      "grad_norm": 0.30499228835105896,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.8233,
      "step": 15
    },
    {
      "epoch": 0.0017972681524083393,
      "eval_loss": 10.823454856872559,
      "eval_runtime": 14.1306,
      "eval_samples_per_second": 248.752,
      "eval_steps_per_second": 124.411,
      "step": 15
    },
    {
      "epoch": 0.002156721782890007,
      "grad_norm": 0.22637830674648285,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.8181,
      "step": 18
    },
    {
      "epoch": 0.0023963575365444525,
      "eval_loss": 10.816689491271973,
      "eval_runtime": 14.0209,
      "eval_samples_per_second": 250.698,
      "eval_steps_per_second": 125.384,
      "step": 20
    },
    {
      "epoch": 0.0025161754133716753,
      "grad_norm": 0.25965455174446106,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.812,
      "step": 21
    },
    {
      "epoch": 0.002875629043853343,
      "grad_norm": 0.24722248315811157,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.8121,
      "step": 24
    },
    {
      "epoch": 0.0029954469206805653,
      "eval_loss": 10.813106536865234,
      "eval_runtime": 14.0562,
      "eval_samples_per_second": 250.067,
      "eval_steps_per_second": 125.069,
      "step": 25
    },
    {
      "epoch": 0.003235082674335011,
      "grad_norm": 0.2858768105506897,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.8136,
      "step": 27
    },
    {
      "epoch": 0.0035945363048166786,
      "grad_norm": 0.37482893466949463,
      "learning_rate": 0.0,
      "loss": 10.8134,
      "step": 30
    },
    {
      "epoch": 0.0035945363048166786,
      "eval_loss": 10.812426567077637,
      "eval_runtime": 14.0598,
      "eval_samples_per_second": 250.004,
      "eval_steps_per_second": 125.037,
      "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": 4950557982720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}