Training in progress, epoch 2, checkpoint

last-checkpoint/README.md

@@ -204,11 +204,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 
-- PEFT 0.6.0
-## Training procedure
-
-
-### Framework versions
-
-
 - PEFT 0.6.0

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a6f7b8642257f9b4f1e86b5e790deb01fb08d21a35bc606d660880c474c957
+oid sha256:618d3d2ec5705a7944867cc0c68898df210a3c05c738f54b0205069540cf24d2
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da7ed3e024431b3bbcebe76249f0df3cb6045c3bfbed4ab79b945cce887a06fb
+oid sha256:625e28979140500e855f5b58095550ebd7658d74d8eade4471277421e86391a4
 size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47993ea280f151c8fcf3c46332c56341dd2d240bb3795a6056a9ef944063ec76
+oid sha256:7b471cb8860708101ce25d1e88b8a57bd85b52cc315d3ebab43324c4b3ab7aa7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac18e681aa029bb50d7d52c8e0c494629884770666cf83509333f41063885a3e
+oid sha256:c6a9178c341cb01ad3a57133d651ab638c27109b4e6d3df4f0b9fa185a8e9cb2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.9649720191955566,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-25511",
-  "epoch": 1.0,
+  "best_metric": 2.9141533374786377,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-51022",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 25511,
+  "global_step": 51022,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -332,13 +332,338 @@
       "eval_steps_per_second": 0.29,
       "eval_translation_length": 5805056,
       "step": 25511
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 7.978077848281594e-05,
+      "loss": 3.066,
+      "step": 26000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 7.977210552957941e-05,
+      "loss": 3.0837,
+      "step": 26500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 7.976326481636685e-05,
+      "loss": 3.0351,
+      "step": 27000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 7.975425638046865e-05,
+      "loss": 3.0893,
+      "step": 27500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 7.974508025988271e-05,
+      "loss": 3.1108,
+      "step": 28000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 7.973573649331417e-05,
+      "loss": 3.092,
+      "step": 28500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.972622512017531e-05,
+      "loss": 3.0614,
+      "step": 29000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.971654618058541e-05,
+      "loss": 3.0665,
+      "step": 29500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.970669971537055e-05,
+      "loss": 3.0267,
+      "step": 30000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.969668576606342e-05,
+      "loss": 3.0357,
+      "step": 30500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.968650437490315e-05,
+      "loss": 3.0802,
+      "step": 31000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.96761555848352e-05,
+      "loss": 3.02,
+      "step": 31500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 7.966563943951106e-05,
+      "loss": 3.019,
+      "step": 32000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 7.965495598328816e-05,
+      "loss": 2.963,
+      "step": 32500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 7.964410526122968e-05,
+      "loss": 3.0504,
+      "step": 33000
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 7.963308731910425e-05,
+      "loss": 3.0028,
+      "step": 33500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 7.962190220338592e-05,
+      "loss": 3.1032,
+      "step": 34000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 7.961054996125386e-05,
+      "loss": 3.1041,
+      "step": 34500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 7.959903064059219e-05,
+      "loss": 3.0636,
+      "step": 35000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 7.958734428998974e-05,
+      "loss": 3.0328,
+      "step": 35500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 7.95754909587399e-05,
+      "loss": 3.119,
+      "step": 36000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 7.95634706968404e-05,
+      "loss": 3.0262,
+      "step": 36500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 7.955128355499307e-05,
+      "loss": 2.9855,
+      "step": 37000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 7.953892958460368e-05,
+      "loss": 2.961,
+      "step": 37500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.95264088377816e-05,
+      "loss": 3.0219,
+      "step": 38000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.95137213673398e-05,
+      "loss": 3.0122,
+      "step": 38500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 7.950086722679437e-05,
+      "loss": 3.0509,
+      "step": 39000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 7.948784647036451e-05,
+      "loss": 3.0243,
+      "step": 39500
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 7.947465915297216e-05,
+      "loss": 3.0097,
+      "step": 40000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 7.946130533024182e-05,
+      "loss": 3.0304,
+      "step": 40500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 7.944778505850034e-05,
+      "loss": 3.0242,
+      "step": 41000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 7.943409839477667e-05,
+      "loss": 3.0768,
+      "step": 41500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 7.942024539680155e-05,
+      "loss": 3.002,
+      "step": 42000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 7.940622612300737e-05,
+      "loss": 3.051,
+      "step": 42500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 7.939204063252785e-05,
+      "loss": 2.9671,
+      "step": 43000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 7.937768898519784e-05,
+      "loss": 3.0447,
+      "step": 43500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.936317124155305e-05,
+      "loss": 3.0225,
+      "step": 44000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.934848746282973e-05,
+      "loss": 3.0529,
+      "step": 44500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.933363771096455e-05,
+      "loss": 2.9976,
+      "step": 45000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.931862204859424e-05,
+      "loss": 3.0628,
+      "step": 45500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.930344053905528e-05,
+      "loss": 3.052,
+      "step": 46000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.928809324638376e-05,
+      "loss": 3.0504,
+      "step": 46500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.927258023531509e-05,
+      "loss": 2.9963,
+      "step": 47000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 7.925690157128356e-05,
+      "loss": 2.977,
+      "step": 47500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 7.924105732042232e-05,
+      "loss": 2.9631,
+      "step": 48000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.922504754956285e-05,
+      "loss": 3.0761,
+      "step": 48500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.920887232623493e-05,
+      "loss": 3.0048,
+      "step": 49000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 7.919253171866611e-05,
+      "loss": 3.0274,
+      "step": 49500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 7.91760257957816e-05,
+      "loss": 3.0597,
+      "step": 50000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 7.915935462720387e-05,
+      "loss": 3.036,
+      "step": 50500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.914251828325245e-05,
+      "loss": 3.0542,
+      "step": 51000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.9141533374786377,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 5805056,
+      "eval_runtime": 9841.5587,
+      "eval_samples_per_second": 1.152,
+      "eval_steps_per_second": 0.288,
+      "eval_translation_length": 5805056,
+      "step": 51022
     }
   ],
   "logging_steps": 500,
   "max_steps": 765330,
   "num_train_epochs": 30,
   "save_steps": 1000,
-  "total_flos": 8.756537195747082e+17,
+  "total_flos": 1.7513074391494164e+18,
   "trial_name": null,
   "trial_params": null
 }