Delete trainer_state.json

trainer_state.json

@@ -1,304 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.3529411764705883,
-  "eval_steps": 100,
-  "global_step": 1800,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.13071895424836602,
-      "grad_norm": 2.612921714782715,
-      "learning_rate": 2.8515e-05,
-      "loss": 1.5786,
-      "step": 100
-    },
-    {
-      "epoch": 0.13071895424836602,
-      "eval_loss": 1.2468026876449585,
-      "eval_runtime": 49.2181,
-      "eval_samples_per_second": 55.224,
-      "eval_steps_per_second": 1.727,
-      "step": 100
-    },
-    {
-      "epoch": 0.26143790849673204,
-      "grad_norm": 2.842139482498169,
-      "learning_rate": 2.7015e-05,
-      "loss": 1.4427,
-      "step": 200
-    },
-    {
-      "epoch": 0.26143790849673204,
-      "eval_loss": 1.200204849243164,
-      "eval_runtime": 49.3689,
-      "eval_samples_per_second": 55.055,
-      "eval_steps_per_second": 1.722,
-      "step": 200
-    },
-    {
-      "epoch": 0.39215686274509803,
-      "grad_norm": 2.886702060699463,
-      "learning_rate": 2.5515000000000002e-05,
-      "loss": 1.4714,
-      "step": 300
-    },
-    {
-      "epoch": 0.39215686274509803,
-      "eval_loss": 1.173571228981018,
-      "eval_runtime": 49.4135,
-      "eval_samples_per_second": 55.005,
-      "eval_steps_per_second": 1.72,
-      "step": 300
-    },
-    {
-      "epoch": 0.5228758169934641,
-      "grad_norm": 2.9086837768554688,
-      "learning_rate": 2.4015e-05,
-      "loss": 1.3829,
-      "step": 400
-    },
-    {
-      "epoch": 0.5228758169934641,
-      "eval_loss": 1.1620103120803833,
-      "eval_runtime": 49.407,
-      "eval_samples_per_second": 55.012,
-      "eval_steps_per_second": 1.72,
-      "step": 400
-    },
-    {
-      "epoch": 0.6535947712418301,
-      "grad_norm": 2.680055856704712,
-      "learning_rate": 2.2515e-05,
-      "loss": 1.4034,
-      "step": 500
-    },
-    {
-      "epoch": 0.6535947712418301,
-      "eval_loss": 1.1487430334091187,
-      "eval_runtime": 49.4341,
-      "eval_samples_per_second": 54.982,
-      "eval_steps_per_second": 1.719,
-      "step": 500
-    },
-    {
-      "epoch": 0.7843137254901961,
-      "grad_norm": 2.7972700595855713,
-      "learning_rate": 2.1015e-05,
-      "loss": 1.3393,
-      "step": 600
-    },
-    {
-      "epoch": 0.7843137254901961,
-      "eval_loss": 1.1399074792861938,
-      "eval_runtime": 49.4463,
-      "eval_samples_per_second": 54.969,
-      "eval_steps_per_second": 1.719,
-      "step": 600
-    },
-    {
-      "epoch": 0.9150326797385621,
-      "grad_norm": 2.4504594802856445,
-      "learning_rate": 1.9515e-05,
-      "loss": 1.3386,
-      "step": 700
-    },
-    {
-      "epoch": 0.9150326797385621,
-      "eval_loss": 1.1321361064910889,
-      "eval_runtime": 49.4141,
-      "eval_samples_per_second": 55.004,
-      "eval_steps_per_second": 1.72,
-      "step": 700
-    },
-    {
-      "epoch": 1.0457516339869282,
-      "grad_norm": 2.388720989227295,
-      "learning_rate": 1.8015000000000003e-05,
-      "loss": 1.3639,
-      "step": 800
-    },
-    {
-      "epoch": 1.0457516339869282,
-      "eval_loss": 1.1278705596923828,
-      "eval_runtime": 49.4078,
-      "eval_samples_per_second": 55.012,
-      "eval_steps_per_second": 1.72,
-      "step": 800
-    },
-    {
-      "epoch": 1.1764705882352942,
-      "grad_norm": 2.8180274963378906,
-      "learning_rate": 1.6515e-05,
-      "loss": 1.2569,
-      "step": 900
-    },
-    {
-      "epoch": 1.1764705882352942,
-      "eval_loss": 1.12681245803833,
-      "eval_runtime": 49.4505,
-      "eval_samples_per_second": 54.964,
-      "eval_steps_per_second": 1.719,
-      "step": 900
-    },
-    {
-      "epoch": 1.3071895424836601,
-      "grad_norm": 2.588479518890381,
-      "learning_rate": 1.5015e-05,
-      "loss": 1.2463,
-      "step": 1000
-    },
-    {
-      "epoch": 1.3071895424836601,
-      "eval_loss": 1.1237956285476685,
-      "eval_runtime": 49.44,
-      "eval_samples_per_second": 54.976,
-      "eval_steps_per_second": 1.719,
-      "step": 1000
-    },
-    {
-      "epoch": 1.4379084967320261,
-      "grad_norm": 2.7836344242095947,
-      "learning_rate": 1.3515e-05,
-      "loss": 1.1957,
-      "step": 1100
-    },
-    {
-      "epoch": 1.4379084967320261,
-      "eval_loss": 1.1178600788116455,
-      "eval_runtime": 49.4187,
-      "eval_samples_per_second": 54.999,
-      "eval_steps_per_second": 1.72,
-      "step": 1100
-    },
-    {
-      "epoch": 1.5686274509803921,
-      "grad_norm": 3.272765874862671,
-      "learning_rate": 1.2015000000000001e-05,
-      "loss": 1.2142,
-      "step": 1200
-    },
-    {
-      "epoch": 1.5686274509803921,
-      "eval_loss": 1.116894006729126,
-      "eval_runtime": 49.4336,
-      "eval_samples_per_second": 54.983,
-      "eval_steps_per_second": 1.719,
-      "step": 1200
-    },
-    {
-      "epoch": 1.6993464052287581,
-      "grad_norm": 2.6856162548065186,
-      "learning_rate": 1.0515e-05,
-      "loss": 1.2177,
-      "step": 1300
-    },
-    {
-      "epoch": 1.6993464052287581,
-      "eval_loss": 1.1120049953460693,
-      "eval_runtime": 49.446,
-      "eval_samples_per_second": 54.969,
-      "eval_steps_per_second": 1.719,
-      "step": 1300
-    },
-    {
-      "epoch": 1.8300653594771243,
-      "grad_norm": 2.9578452110290527,
-      "learning_rate": 9.015e-06,
-      "loss": 1.2407,
-      "step": 1400
-    },
-    {
-      "epoch": 1.8300653594771243,
-      "eval_loss": 1.1107261180877686,
-      "eval_runtime": 49.4097,
-      "eval_samples_per_second": 55.009,
-      "eval_steps_per_second": 1.72,
-      "step": 1400
-    },
-    {
-      "epoch": 1.9607843137254903,
-      "grad_norm": 2.797602653503418,
-      "learning_rate": 7.515e-06,
-      "loss": 1.2679,
-      "step": 1500
-    },
-    {
-      "epoch": 1.9607843137254903,
-      "eval_loss": 1.1109682321548462,
-      "eval_runtime": 49.422,
-      "eval_samples_per_second": 54.996,
-      "eval_steps_per_second": 1.72,
-      "step": 1500
-    },
-    {
-      "epoch": 2.0915032679738563,
-      "grad_norm": 2.613773822784424,
-      "learning_rate": 6.015000000000001e-06,
-      "loss": 1.1959,
-      "step": 1600
-    },
-    {
-      "epoch": 2.0915032679738563,
-      "eval_loss": 1.108609914779663,
-      "eval_runtime": 49.0734,
-      "eval_samples_per_second": 55.386,
-      "eval_steps_per_second": 1.732,
-      "step": 1600
-    },
-    {
-      "epoch": 2.2222222222222223,
-      "grad_norm": 2.685255765914917,
-      "learning_rate": 4.515e-06,
-      "loss": 1.1868,
-      "step": 1700
-    },
-    {
-      "epoch": 2.2222222222222223,
-      "eval_loss": 1.1089801788330078,
-      "eval_runtime": 49.4346,
-      "eval_samples_per_second": 54.982,
-      "eval_steps_per_second": 1.719,
-      "step": 1700
-    },
-    {
-      "epoch": 2.3529411764705883,
-      "grad_norm": 2.5635337829589844,
-      "learning_rate": 3.0150000000000004e-06,
-      "loss": 1.1443,
-      "step": 1800
-    },
-    {
-      "epoch": 2.3529411764705883,
-      "eval_loss": 1.1081539392471313,
-      "eval_runtime": 49.3845,
-      "eval_samples_per_second": 55.038,
-      "eval_steps_per_second": 1.721,
-      "step": 1800
-    }
-  ],
-  "logging_steps": 100,
-  "max_steps": 2000,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 100,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 3.504309077016576e+16,
-  "train_batch_size": 32,
-  "trial_name": null,
-  "trial_params": null
-}