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

lora_date_format_change_only/checkpoint-600/trainer_state.json

@@ -0,0 +1,317 @@
+{
+  "best_global_step": 600,
+  "best_metric": 2.7076871395111084,
+  "best_model_checkpoint": "/scratch/aditya.mishra/lma/models/lora_date_format_change_only/checkpoint-600",
+  "epoch": 24.0,
+  "eval_steps": 75,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.41712844371795654,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 7.5908,
+      "step": 20
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.4582262337207794,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 7.5603,
+      "step": 40
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.5395545959472656,
+      "learning_rate": 2.6222222222222226e-05,
+      "loss": 7.4736,
+      "step": 60
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 7.173784255981445,
+      "eval_runtime": 1.1224,
+      "eval_samples_per_second": 267.281,
+      "eval_steps_per_second": 11.582,
+      "step": 75
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.6233034729957581,
+      "learning_rate": 3.511111111111111e-05,
+      "loss": 7.2329,
+      "step": 80
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8371453881263733,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 6.7922,
+      "step": 100
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.0765700340270996,
+      "learning_rate": 5.2888888888888885e-05,
+      "loss": 5.9905,
+      "step": 120
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.7292976975440979,
+      "learning_rate": 6.177777777777779e-05,
+      "loss": 4.825,
+      "step": 140
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.036015033721924,
+      "eval_runtime": 0.4844,
+      "eval_samples_per_second": 619.368,
+      "eval_steps_per_second": 26.839,
+      "step": 150
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 0.4728981554508209,
+      "learning_rate": 7.066666666666667e-05,
+      "loss": 4.0399,
+      "step": 160
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 0.3667033016681671,
+      "learning_rate": 7.955555555555556e-05,
+      "loss": 3.702,
+      "step": 180
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.31484851241111755,
+      "learning_rate": 8.844444444444445e-05,
+      "loss": 3.5226,
+      "step": 200
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.3103426992893219,
+      "learning_rate": 9.733333333333335e-05,
+      "loss": 3.4057,
+      "step": 220
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.3390941619873047,
+      "eval_runtime": 0.9074,
+      "eval_samples_per_second": 330.621,
+      "eval_steps_per_second": 14.327,
+      "step": 225
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.3025698661804199,
+      "learning_rate": 0.00010622222222222222,
+      "loss": 3.3185,
+      "step": 240
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 0.3149551749229431,
+      "learning_rate": 0.00011511111111111112,
+      "loss": 3.2451,
+      "step": 260
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 0.2536594271659851,
+      "learning_rate": 0.000124,
+      "loss": 3.1997,
+      "step": 280
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.3023339509963989,
+      "learning_rate": 0.00013288888888888888,
+      "loss": 3.1636,
+      "step": 300
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 3.148141622543335,
+      "eval_runtime": 0.5347,
+      "eval_samples_per_second": 561.058,
+      "eval_steps_per_second": 24.313,
+      "step": 300
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 0.43101465702056885,
+      "learning_rate": 0.00014177777777777778,
+      "loss": 3.1314,
+      "step": 320
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 0.29925617575645447,
+      "learning_rate": 0.00015066666666666668,
+      "loss": 3.0871,
+      "step": 340
+    },
+    {
+      "epoch": 14.4,
+      "grad_norm": 0.47846999764442444,
+      "learning_rate": 0.00015955555555555558,
+      "loss": 3.0122,
+      "step": 360
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 2.9132258892059326,
+      "eval_runtime": 0.5886,
+      "eval_samples_per_second": 509.687,
+      "eval_steps_per_second": 22.086,
+      "step": 375
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 0.34506991505622864,
+      "learning_rate": 0.00016844444444444445,
+      "loss": 2.9266,
+      "step": 380
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.3448505401611328,
+      "learning_rate": 0.00017733333333333335,
+      "loss": 2.8583,
+      "step": 400
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.30222710967063904,
+      "learning_rate": 0.00018622222222222223,
+      "loss": 2.8068,
+      "step": 420
+    },
+    {
+      "epoch": 17.6,
+      "grad_norm": 0.21652688086032867,
+      "learning_rate": 0.0001951111111111111,
+      "loss": 2.7732,
+      "step": 440
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 2.7573180198669434,
+      "eval_runtime": 0.5558,
+      "eval_samples_per_second": 539.753,
+      "eval_steps_per_second": 23.389,
+      "step": 450
+    },
+    {
+      "epoch": 18.4,
+      "grad_norm": 0.3127593696117401,
+      "learning_rate": 0.00019999981118841182,
+      "loss": 2.7532,
+      "step": 460
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 0.20969198644161224,
+      "learning_rate": 0.00019999803962868136,
+      "loss": 2.7409,
+      "step": 480
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.31829535961151123,
+      "learning_rate": 0.00019999440330200995,
+      "loss": 2.7261,
+      "step": 500
+    },
+    {
+      "epoch": 20.8,
+      "grad_norm": 0.35474255681037903,
+      "learning_rate": 0.00019998890227620783,
+      "loss": 2.7161,
+      "step": 520
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 2.7177388668060303,
+      "eval_runtime": 0.5552,
+      "eval_samples_per_second": 540.333,
+      "eval_steps_per_second": 23.414,
+      "step": 525
+    },
+    {
+      "epoch": 21.6,
+      "grad_norm": 0.28053319454193115,
+      "learning_rate": 0.00019998153665385843,
+      "loss": 2.7098,
+      "step": 540
+    },
+    {
+      "epoch": 22.4,
+      "grad_norm": 0.2555520832538605,
+      "learning_rate": 0.00019997230657231612,
+      "loss": 2.7075,
+      "step": 560
+    },
+    {
+      "epoch": 23.2,
+      "grad_norm": 0.24908167123794556,
+      "learning_rate": 0.00019996121220370374,
+      "loss": 2.7005,
+      "step": 580
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.3387139141559601,
+      "learning_rate": 0.00019994825375490948,
+      "loss": 2.6979,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 2.7076871395111084,
+      "eval_runtime": 0.6226,
+      "eval_samples_per_second": 481.813,
+      "eval_steps_per_second": 20.879,
+      "step": 600
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 15000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 600,
+  "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": 769732222464000.0,
+  "train_batch_size": 96,
+  "trial_name": null,
+  "trial_params": null
+}