Training in progress, epoch 1, checkpoint

last-checkpoint/README.md

@@ -18,6 +18,7 @@ base_model: google/flan-t5-xl
 
 
 - **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
@@ -76,7 +77,7 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
 [More Information Needed]
 
@@ -107,7 +108,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Data Card if possible. -->
+<!-- This should link to a Dataset Card if possible. -->
 
 [More Information Needed]
 
@@ -204,4 +205,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 
-- PEFT 0.6.0
+- PEFT 0.6.2

last-checkpoint/adapter_config.json

@@ -16,8 +16,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
-    "v"
+    "v",
+    "q"
   ],
   "task_type": "SEQ_2_SEQ_LM"
 }

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b127cfb645d1c75f132a876553609b5374befd9def67d558e5974fa97067d21c
+oid sha256:4602760b59b06299e933de1cabee7a847e392fa5c40fee852f8918f5b35ad215
 size 37789864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:853fdc84d3fd43924101f3b600fbd9f7fc43eb8341b64b2118c78dce07ce9bc5
-size 1256
+oid sha256:3edb87d3ecd16a7429d7ac352d010d359f3a0dff217ec6098b81876c6ebff172
+size 2621690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bfea11a2e02465bb531791987f71426cd35b56e7ebc758216b34e89a76ca829
+oid sha256:d1da9aa18d7924a07f722f332077e6eae3d36694b90416e0a3981d3bfad8282e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2492f9b5d907d6544a13d4d0a642eb64eb32b5925504787877c14c24ec71c83
+oid sha256:9c264768290f9849fa6fa417060b5498e9d26e7c5d585205c9e94d1d4cf3a2be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,248 +1,518 @@
 {
-  "best_metric": 3.0692174434661865,
-  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-17782",
+  "best_metric": 3.1455512046813965,
+  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-40162",
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 17782,
+  "global_step": 40162,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
-      "learning_rate": 6e-05,
-      "loss": 3.2033,
+      "epoch": 0.01,
+      "learning_rate": 0.0001,
+      "loss": 4.5056,
       "step": 500
     },
     {
-      "epoch": 0.06,
-      "learning_rate": 5.9999869700884375e-05,
-      "loss": 3.1925,
+      "epoch": 0.02,
+      "learning_rate": 9.9999957472774e-05,
+      "loss": 3.8512,
       "step": 1000
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 5.999947880466937e-05,
-      "loss": 3.1596,
+      "epoch": 0.04,
+      "learning_rate": 9.999982989116833e-05,
+      "loss": 3.6498,
       "step": 1500
     },
     {
-      "epoch": 0.11,
-      "learning_rate": 5.999882731475053e-05,
-      "loss": 3.2032,
+      "epoch": 0.05,
+      "learning_rate": 9.999961725540003e-05,
+      "loss": 3.6328,
       "step": 2000
     },
     {
-      "epoch": 0.14,
-      "learning_rate": 5.99979152367871e-05,
-      "loss": 3.1379,
+      "epoch": 0.06,
+      "learning_rate": 9.999931956583082e-05,
+      "loss": 3.6162,
       "step": 2500
     },
     {
-      "epoch": 0.17,
-      "learning_rate": 5.999674257870195e-05,
-      "loss": 3.1821,
+      "epoch": 0.07,
+      "learning_rate": 9.999893682296706e-05,
+      "loss": 3.6415,
       "step": 3000
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 5.9995309350681496e-05,
-      "loss": 3.165,
+      "epoch": 0.09,
+      "learning_rate": 9.999846902745986e-05,
+      "loss": 3.6273,
       "step": 3500
     },
     {
-      "epoch": 0.22,
-      "learning_rate": 5.9993615565175614e-05,
-      "loss": 3.1682,
+      "epoch": 0.1,
+      "learning_rate": 9.999791618010498e-05,
+      "loss": 3.5555,
       "step": 4000
     },
     {
-      "epoch": 0.25,
-      "learning_rate": 5.999166123689758e-05,
-      "loss": 3.1234,
+      "epoch": 0.11,
+      "learning_rate": 9.999727828184285e-05,
+      "loss": 3.5176,
       "step": 4500
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 5.9989446382823863e-05,
-      "loss": 3.1389,
+      "epoch": 0.12,
+      "learning_rate": 9.99965553337586e-05,
+      "loss": 3.4374,
       "step": 5000
     },
     {
-      "epoch": 0.31,
-      "learning_rate": 5.9986971022194026e-05,
-      "loss": 3.1197,
+      "epoch": 0.14,
+      "learning_rate": 9.999574733708204e-05,
+      "loss": 3.5565,
       "step": 5500
     },
     {
-      "epoch": 0.34,
-      "learning_rate": 5.998423517651056e-05,
-      "loss": 3.2251,
+      "epoch": 0.15,
+      "learning_rate": 9.999485429318763e-05,
+      "loss": 3.4639,
       "step": 6000
     },
     {
-      "epoch": 0.37,
-      "learning_rate": 5.998123886953869e-05,
-      "loss": 3.2011,
+      "epoch": 0.16,
+      "learning_rate": 9.99938762035945e-05,
+      "loss": 3.3833,
       "step": 6500
     },
     {
-      "epoch": 0.39,
-      "learning_rate": 5.9977982127306157e-05,
-      "loss": 3.1573,
+      "epoch": 0.17,
+      "learning_rate": 9.999281306996651e-05,
+      "loss": 3.4726,
       "step": 7000
     },
     {
-      "epoch": 0.42,
-      "learning_rate": 5.9974464978103e-05,
-      "loss": 3.1049,
+      "epoch": 0.19,
+      "learning_rate": 9.999166489411211e-05,
+      "loss": 3.4132,
       "step": 7500
     },
     {
-      "epoch": 0.45,
-      "learning_rate": 5.997068745248132e-05,
-      "loss": 3.1919,
+      "epoch": 0.2,
+      "learning_rate": 9.999043167798448e-05,
+      "loss": 3.3754,
       "step": 8000
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 5.996664958325499e-05,
-      "loss": 3.1192,
+      "epoch": 0.21,
+      "learning_rate": 9.99891134236814e-05,
+      "loss": 3.4333,
       "step": 8500
     },
     {
-      "epoch": 0.51,
-      "learning_rate": 5.99623514054994e-05,
-      "loss": 3.1393,
+      "epoch": 0.22,
+      "learning_rate": 9.998771013344535e-05,
+      "loss": 3.3313,
       "step": 9000
     },
     {
-      "epoch": 0.53,
-      "learning_rate": 5.995779295655114e-05,
-      "loss": 3.1306,
+      "epoch": 0.24,
+      "learning_rate": 9.998622180966344e-05,
+      "loss": 3.3758,
       "step": 9500
     },
     {
-      "epoch": 0.56,
-      "learning_rate": 5.995297427600766e-05,
-      "loss": 3.1719,
+      "epoch": 0.25,
+      "learning_rate": 9.998464845486746e-05,
+      "loss": 3.3814,
       "step": 10000
     },
     {
-      "epoch": 0.59,
-      "learning_rate": 5.994789540572695e-05,
-      "loss": 3.1197,
+      "epoch": 0.26,
+      "learning_rate": 9.998299007173383e-05,
+      "loss": 3.429,
       "step": 10500
     },
     {
-      "epoch": 0.62,
-      "learning_rate": 5.994255638982716e-05,
-      "loss": 3.1231,
+      "epoch": 0.27,
+      "learning_rate": 9.99812466630836e-05,
+      "loss": 3.4547,
       "step": 11000
     },
     {
-      "epoch": 0.65,
-      "learning_rate": 5.9936957274686233e-05,
-      "loss": 3.1585,
+      "epoch": 0.29,
+      "learning_rate": 9.997941823188243e-05,
+      "loss": 3.4204,
       "step": 11500
     },
     {
-      "epoch": 0.67,
-      "learning_rate": 5.9931098108941496e-05,
-      "loss": 3.2459,
+      "epoch": 0.3,
+      "learning_rate": 9.99775047812407e-05,
+      "loss": 3.3807,
       "step": 12000
     },
     {
-      "epoch": 0.7,
-      "learning_rate": 5.9924978943489196e-05,
-      "loss": 3.1119,
+      "epoch": 0.31,
+      "learning_rate": 9.997550631441332e-05,
+      "loss": 3.3749,
       "step": 12500
     },
     {
-      "epoch": 0.73,
-      "learning_rate": 5.991859983148415e-05,
-      "loss": 3.1499,
+      "epoch": 0.32,
+      "learning_rate": 9.997342283479989e-05,
+      "loss": 3.326,
       "step": 13000
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 5.9911960828339176e-05,
-      "loss": 3.2634,
+      "epoch": 0.34,
+      "learning_rate": 9.997125434594458e-05,
+      "loss": 3.3626,
       "step": 13500
     },
     {
-      "epoch": 0.79,
-      "learning_rate": 5.9905061991724704e-05,
-      "loss": 3.1048,
+      "epoch": 0.35,
+      "learning_rate": 9.996900085153617e-05,
+      "loss": 3.304,
       "step": 14000
     },
     {
-      "epoch": 0.82,
-      "learning_rate": 5.9897903381568234e-05,
-      "loss": 3.1717,
+      "epoch": 0.36,
+      "learning_rate": 9.996666235540808e-05,
+      "loss": 3.3671,
       "step": 14500
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 5.989048506005378e-05,
-      "loss": 3.317,
+      "epoch": 0.37,
+      "learning_rate": 9.996423886153828e-05,
+      "loss": 3.3667,
       "step": 15000
     },
     {
-      "epoch": 0.87,
-      "learning_rate": 5.98828070916214e-05,
-      "loss": 3.1535,
+      "epoch": 0.39,
+      "learning_rate": 9.996173037404934e-05,
+      "loss": 3.321,
       "step": 15500
     },
     {
-      "epoch": 0.9,
-      "learning_rate": 5.9874869542966605e-05,
-      "loss": 3.0698,
+      "epoch": 0.4,
+      "learning_rate": 9.995913689720844e-05,
+      "loss": 3.2639,
       "step": 16000
     },
     {
-      "epoch": 0.93,
-      "learning_rate": 5.986667248303975e-05,
-      "loss": 3.1798,
+      "epoch": 0.41,
+      "learning_rate": 9.995645843542732e-05,
+      "loss": 3.3529,
       "step": 16500
     },
     {
-      "epoch": 0.96,
-      "learning_rate": 5.985821598304549e-05,
-      "loss": 3.0956,
+      "epoch": 0.42,
+      "learning_rate": 9.995369499326228e-05,
+      "loss": 3.2607,
       "step": 17000
     },
     {
-      "epoch": 0.98,
-      "learning_rate": 5.984950011644212e-05,
-      "loss": 3.1267,
+      "epoch": 0.44,
+      "learning_rate": 9.995084657541416e-05,
+      "loss": 3.2858,
       "step": 17500
     },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.994791318672838e-05,
+      "loss": 3.3516,
+      "step": 18000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.994489483219492e-05,
+      "loss": 3.2944,
+      "step": 18500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.994179151694824e-05,
+      "loss": 3.278,
+      "step": 19000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.993860324626737e-05,
+      "loss": 3.2557,
+      "step": 19500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.993533002557585e-05,
+      "loss": 3.366,
+      "step": 20000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.99319718604417e-05,
+      "loss": 3.2581,
+      "step": 20500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.992852875657746e-05,
+      "loss": 3.3302,
+      "step": 21000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.992500071984017e-05,
+      "loss": 3.334,
+      "step": 21500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.992138775623132e-05,
+      "loss": 3.3146,
+      "step": 22000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.991768987189688e-05,
+      "loss": 3.3315,
+      "step": 22500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.991390707312733e-05,
+      "loss": 3.3853,
+      "step": 23000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.991003936635747e-05,
+      "loss": 3.3447,
+      "step": 23500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.990608675816668e-05,
+      "loss": 3.1906,
+      "step": 24000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.990204925527867e-05,
+      "loss": 3.3639,
+      "step": 24500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.989792686456158e-05,
+      "loss": 3.2723,
+      "step": 25000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.989371959302797e-05,
+      "loss": 3.2156,
+      "step": 25500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.988942744783481e-05,
+      "loss": 3.3264,
+      "step": 26000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.988505043628337e-05,
+      "loss": 3.2336,
+      "step": 26500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.98805885658194e-05,
+      "loss": 3.2806,
+      "step": 27000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.98760418440329e-05,
+      "loss": 3.3251,
+      "step": 27500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.987141027865825e-05,
+      "loss": 3.2188,
+      "step": 28000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.986669387757414e-05,
+      "loss": 3.2981,
+      "step": 28500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.986189264880364e-05,
+      "loss": 3.3023,
+      "step": 29000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.985700660051403e-05,
+      "loss": 3.3271,
+      "step": 29500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 9.985203574101691e-05,
+      "loss": 3.2955,
+      "step": 30000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 9.984698007876816e-05,
+      "loss": 3.3756,
+      "step": 30500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 9.984183962236792e-05,
+      "loss": 3.2936,
+      "step": 31000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.983661438056056e-05,
+      "loss": 3.3248,
+      "step": 31500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.983130436223469e-05,
+      "loss": 3.2569,
+      "step": 32000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.98259095764231e-05,
+      "loss": 3.3616,
+      "step": 32500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.982043003230282e-05,
+      "loss": 3.2892,
+      "step": 33000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.981486573919504e-05,
+      "loss": 3.2331,
+      "step": 33500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.98092167065651e-05,
+      "loss": 3.3242,
+      "step": 34000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.980348294402255e-05,
+      "loss": 3.3123,
+      "step": 34500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.9797664461321e-05,
+      "loss": 3.2869,
+      "step": 35000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.979176126835821e-05,
+      "loss": 3.2566,
+      "step": 35500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.978577337517603e-05,
+      "loss": 3.3036,
+      "step": 36000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.977970079196041e-05,
+      "loss": 3.299,
+      "step": 36500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.977354352904136e-05,
+      "loss": 3.31,
+      "step": 37000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.976730159689292e-05,
+      "loss": 3.2459,
+      "step": 37500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.976097500613318e-05,
+      "loss": 3.3162,
+      "step": 38000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.975456376752424e-05,
+      "loss": 3.3056,
+      "step": 38500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.974806789197216e-05,
+      "loss": 3.2404,
+      "step": 39000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.974148739052703e-05,
+      "loss": 3.2376,
+      "step": 39500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.973482227438287e-05,
+      "loss": 3.356,
+      "step": 40000
+    },
     {
       "epoch": 1.0,
       "eval_bleu": 1.0,
       "eval_brevity_penalty": 1.0,
       "eval_length_ratio": 1.0,
-      "eval_loss": 3.0692174434661865,
+      "eval_loss": 3.1455512046813965,
       "eval_precisions": [
         1.0,
         1.0,
         1.0,
         1.0
       ],
-      "eval_reference_length": 2023424,
-      "eval_runtime": 3477.4176,
-      "eval_samples_per_second": 1.136,
-      "eval_steps_per_second": 0.568,
-      "eval_translation_length": 2023424,
-      "step": 17782
+      "eval_reference_length": 4569600,
+      "eval_runtime": 8741.384,
+      "eval_samples_per_second": 1.021,
+      "eval_steps_per_second": 0.511,
+      "eval_translation_length": 4569600,
+      "step": 40162
     }
   ],
   "logging_steps": 500,
-  "max_steps": 533460,
+  "max_steps": 1204860,
   "num_train_epochs": 30,
   "save_steps": 1000,
-  "total_flos": 3.0517701759310234e+17,
+  "total_flos": 6.892848961321697e+17,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d95e82f3766efe05da841f4af2236c57541bc9acc301ad4339595e386ca971
+oid sha256:b62efb5e27cf22233e7e3d90ba4b9b06ff50053e55dc9f07a3ad40dc5b14b43a
 size 4728