Upload lora_string_concatenation_wo_quotes/checkpoint-600/trainer_state.json with huggingface_hub

lora_string_concatenation_wo_quotes/checkpoint-600/trainer_state.json

@@ -0,0 +1,317 @@
+{
+  "best_global_step": 600,
+  "best_metric": 4.4137349128723145,
+  "best_model_checkpoint": "/scratch/aditya.mishra/lma/models/lora_string_concatenation_wo_quotes/checkpoint-600",
+  "epoch": 12.0,
+  "eval_steps": 75,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.37128207087516785,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 8.5401,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3776383101940155,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 8.4959,
+      "step": 40
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.47413960099220276,
+      "learning_rate": 2.6222222222222226e-05,
+      "loss": 8.3922,
+      "step": 60
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 8.143651962280273,
+      "eval_runtime": 2.2083,
+      "eval_samples_per_second": 271.699,
+      "eval_steps_per_second": 11.321,
+      "step": 75
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5524934530258179,
+      "learning_rate": 3.511111111111111e-05,
+      "loss": 8.2383,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5713401436805725,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 7.9506,
+      "step": 100
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.5087965726852417,
+      "learning_rate": 5.2888888888888885e-05,
+      "loss": 7.4394,
+      "step": 120
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.4845825433731079,
+      "learning_rate": 6.177777777777779e-05,
+      "loss": 7.0443,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.57938814163208,
+      "eval_runtime": 1.025,
+      "eval_samples_per_second": 585.341,
+      "eval_steps_per_second": 24.389,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.5707466006278992,
+      "learning_rate": 7.066666666666667e-05,
+      "loss": 6.6202,
+      "step": 160
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.5126263499259949,
+      "learning_rate": 7.955555555555556e-05,
+      "loss": 6.0175,
+      "step": 180
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.4099263548851013,
+      "learning_rate": 8.844444444444445e-05,
+      "loss": 5.6502,
+      "step": 200
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.4085135757923126,
+      "learning_rate": 9.733333333333335e-05,
+      "loss": 5.287,
+      "step": 220
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 5.131898403167725,
+      "eval_runtime": 1.0269,
+      "eval_samples_per_second": 584.29,
+      "eval_steps_per_second": 24.345,
+      "step": 225
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.4942854046821594,
+      "learning_rate": 0.00010622222222222222,
+      "loss": 5.0822,
+      "step": 240
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.4563262462615967,
+      "learning_rate": 0.00011511111111111112,
+      "loss": 4.9342,
+      "step": 260
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.5420230627059937,
+      "learning_rate": 0.000124,
+      "loss": 4.7651,
+      "step": 280
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.49297860264778137,
+      "learning_rate": 0.00013288888888888888,
+      "loss": 4.6992,
+      "step": 300
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.683771133422852,
+      "eval_runtime": 0.9657,
+      "eval_samples_per_second": 621.3,
+      "eval_steps_per_second": 25.888,
+      "step": 300
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.7895792722702026,
+      "learning_rate": 0.00014177777777777778,
+      "loss": 4.6258,
+      "step": 320
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.6426990032196045,
+      "learning_rate": 0.00015066666666666668,
+      "loss": 4.618,
+      "step": 340
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 0.5119326710700989,
+      "learning_rate": 0.00015955555555555558,
+      "loss": 4.5176,
+      "step": 360
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 4.5526123046875,
+      "eval_runtime": 0.968,
+      "eval_samples_per_second": 619.817,
+      "eval_steps_per_second": 25.826,
+      "step": 375
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 0.6145326495170593,
+      "learning_rate": 0.00016844444444444445,
+      "loss": 4.5587,
+      "step": 380
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5165311098098755,
+      "learning_rate": 0.00017733333333333335,
+      "loss": 4.498,
+      "step": 400
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 0.47469064593315125,
+      "learning_rate": 0.00018622222222222223,
+      "loss": 4.477,
+      "step": 420
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.4975617527961731,
+      "learning_rate": 0.0001951111111111111,
+      "loss": 4.4525,
+      "step": 440
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 4.477118015289307,
+      "eval_runtime": 1.0421,
+      "eval_samples_per_second": 575.755,
+      "eval_steps_per_second": 23.99,
+      "step": 450
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 0.6947550177574158,
+      "learning_rate": 0.00019999981118841182,
+      "loss": 4.4424,
+      "step": 460
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.5004560947418213,
+      "learning_rate": 0.00019999803962868136,
+      "loss": 4.4289,
+      "step": 480
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.49431946873664856,
+      "learning_rate": 0.00019999440330200995,
+      "loss": 4.4218,
+      "step": 500
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 0.5850865840911865,
+      "learning_rate": 0.00019998890227620783,
+      "loss": 4.3983,
+      "step": 520
+    },
+    {
+      "epoch": 10.5,
+      "eval_loss": 4.434837341308594,
+      "eval_runtime": 1.0583,
+      "eval_samples_per_second": 566.945,
+      "eval_steps_per_second": 23.623,
+      "step": 525
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.5564137101173401,
+      "learning_rate": 0.00019998153665385843,
+      "loss": 4.3908,
+      "step": 540
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 0.5610532164573669,
+      "learning_rate": 0.00019997230657231612,
+      "loss": 4.3757,
+      "step": 560
+    },
+    {
+      "epoch": 11.6,
+      "grad_norm": 0.5854133367538452,
+      "learning_rate": 0.00019996121220370374,
+      "loss": 4.3477,
+      "step": 580
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.46152743697166443,
+      "learning_rate": 0.00019994825375490948,
+      "loss": 4.37,
+      "step": 600
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 4.4137349128723145,
+      "eval_runtime": 1.0425,
+      "eval_samples_per_second": 575.524,
+      "eval_steps_per_second": 23.98,
+      "step": 600
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 15000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 300,
+  "save_steps": 150,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 964173275182080.0,
+  "train_batch_size": 96,
+  "trial_name": null,
+  "trial_params": null
+}