Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "pingusPongus",
+  "_name_or_path": "google/flan-t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -18,45 +18,16 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
-    }
-  },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 32128
 }

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d18f93b6416cb6de922b525ae2aefefd5555f3956bf539033033a8a0334866a
+size 3132668808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df5f5ee2b56d6c0f93fb801be312fc1bd48ab0eacd78bb34294fb243c2b7397a
-size 37990394
+oid sha256:e04dbe6cc517d74a5eb81747881c0161660f2668ab3564ad3304a3fd6f87af59
+size 6265677800

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbfd5efb5880d038e40ef818b6a478489100d8537842fb87344a0d7f88275ee0
+oid sha256:427e669d0ee683c4b12f0805ce85ad0ea605698ac777a13ff0e4e41b5b4ddf99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71d106c12a183d47d2349d6d228d20595c1cad95f8d19fec2a8622032de302f5
+oid sha256:3199f68c919ad9f15fb49df0b36624f234cba762e6bf2c59cdcbf6ebb2295917
 size 1064

last-checkpoint/trainer_state.json

@@ -1,379 +1,452 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8720549976018488,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 30000,
+  "global_step": 34567,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.01,
-      "learning_rate": 4e-05,
-      "loss": 4.4951,
+      "learning_rate": 0.0001,
+      "loss": 3.3228,
       "step": 500
     },
     {
       "epoch": 0.03,
-      "learning_rate": 8e-05,
-      "loss": 3.777,
+      "learning_rate": 9.999994258403258e-05,
+      "loss": 2.8639,
       "step": 1000
     },
     {
       "epoch": 0.04,
-      "learning_rate": 7.999831247941866e-05,
-      "loss": 3.6246,
+      "learning_rate": 9.99997703362622e-05,
+      "loss": 2.8198,
       "step": 1500
     },
     {
       "epoch": 0.06,
-      "learning_rate": 7.99932500600609e-05,
-      "loss": 3.5067,
+      "learning_rate": 9.999948325708443e-05,
+      "loss": 2.7858,
       "step": 2000
     },
     {
       "epoch": 0.07,
-      "learning_rate": 7.998481316907362e-05,
-      "loss": 3.4947,
+      "learning_rate": 9.999908134715859e-05,
+      "loss": 2.7422,
       "step": 2500
     },
     {
       "epoch": 0.09,
-      "learning_rate": 7.99730025183281e-05,
-      "loss": 3.4452,
+      "learning_rate": 9.999856460740773e-05,
+      "loss": 2.7274,
       "step": 3000
     },
     {
       "epoch": 0.1,
-      "learning_rate": 7.995781910436019e-05,
-      "loss": 3.3696,
+      "learning_rate": 9.99979330390186e-05,
+      "loss": 2.6958,
       "step": 3500
     },
     {
       "epoch": 0.12,
-      "learning_rate": 7.993926420828609e-05,
-      "loss": 3.4226,
+      "learning_rate": 9.999718664344171e-05,
+      "loss": 2.6617,
       "step": 4000
     },
     {
       "epoch": 0.13,
-      "learning_rate": 7.991733939569422e-05,
-      "loss": 3.3765,
+      "learning_rate": 9.999632542239125e-05,
+      "loss": 2.6747,
       "step": 4500
     },
     {
-      "epoch": 0.15,
-      "learning_rate": 7.989204651651322e-05,
-      "loss": 3.4237,
+      "epoch": 0.14,
+      "learning_rate": 9.999534937784512e-05,
+      "loss": 2.6564,
       "step": 5000
     },
     {
       "epoch": 0.16,
-      "learning_rate": 7.986338770485576e-05,
-      "loss": 3.3054,
+      "learning_rate": 9.999425851204496e-05,
+      "loss": 2.585,
       "step": 5500
     },
     {
       "epoch": 0.17,
-      "learning_rate": 7.983136537883862e-05,
-      "loss": 3.3544,
+      "learning_rate": 9.99930528274961e-05,
+      "loss": 2.6385,
       "step": 6000
     },
     {
       "epoch": 0.19,
-      "learning_rate": 7.97959822403785e-05,
-      "loss": 3.3659,
+      "learning_rate": 9.999173232696753e-05,
+      "loss": 2.6262,
       "step": 6500
     },
     {
       "epoch": 0.2,
-      "learning_rate": 7.97572412749641e-05,
-      "loss": 3.3426,
+      "learning_rate": 9.999029701349196e-05,
+      "loss": 2.6055,
       "step": 7000
     },
     {
       "epoch": 0.22,
-      "learning_rate": 7.971514575140424e-05,
-      "loss": 3.3332,
+      "learning_rate": 9.998874689036583e-05,
+      "loss": 2.5917,
       "step": 7500
     },
     {
       "epoch": 0.23,
-      "learning_rate": 7.966969922155206e-05,
-      "loss": 3.3163,
+      "learning_rate": 9.998708196114922e-05,
+      "loss": 2.6162,
       "step": 8000
     },
     {
       "epoch": 0.25,
-      "learning_rate": 7.962090552000528e-05,
-      "loss": 3.3127,
+      "learning_rate": 9.99853022296658e-05,
+      "loss": 2.6188,
       "step": 8500
     },
     {
       "epoch": 0.26,
-      "learning_rate": 7.956876876378266e-05,
-      "loss": 3.3187,
+      "learning_rate": 9.998340770000302e-05,
+      "loss": 2.5671,
       "step": 9000
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 7.951329335197668e-05,
-      "loss": 3.3195,
+      "epoch": 0.27,
+      "learning_rate": 9.998139837651193e-05,
+      "loss": 2.5897,
       "step": 9500
     },
     {
       "epoch": 0.29,
-      "learning_rate": 7.94544839653823e-05,
-      "loss": 3.2599,
+      "learning_rate": 9.997927426380721e-05,
+      "loss": 2.5414,
       "step": 10000
     },
     {
-      "epoch": 0.31,
-      "learning_rate": 7.939234556610201e-05,
-      "loss": 3.3353,
+      "epoch": 0.3,
+      "learning_rate": 9.997703536676718e-05,
+      "loss": 2.5139,
       "step": 10500
     },
     {
       "epoch": 0.32,
-      "learning_rate": 7.932688339712721e-05,
-      "loss": 3.1893,
+      "learning_rate": 9.997468169053379e-05,
+      "loss": 2.5904,
       "step": 11000
     },
     {
       "epoch": 0.33,
-      "learning_rate": 7.925810298189578e-05,
-      "loss": 3.2074,
+      "learning_rate": 9.997221324051255e-05,
+      "loss": 2.6288,
       "step": 11500
     },
     {
       "epoch": 0.35,
-      "learning_rate": 7.918601012382602e-05,
-      "loss": 3.2427,
+      "learning_rate": 9.996963002237263e-05,
+      "loss": 2.598,
       "step": 12000
     },
     {
       "epoch": 0.36,
-      "learning_rate": 7.911061090582703e-05,
-      "loss": 3.3292,
+      "learning_rate": 9.996693204204674e-05,
+      "loss": 2.5276,
       "step": 12500
     },
     {
       "epoch": 0.38,
-      "learning_rate": 7.90319116897854e-05,
-      "loss": 3.2498,
+      "learning_rate": 9.996411930573117e-05,
+      "loss": 2.5817,
       "step": 13000
     },
     {
       "epoch": 0.39,
-      "learning_rate": 7.89499191160285e-05,
-      "loss": 3.2745,
+      "learning_rate": 9.996119181988575e-05,
+      "loss": 2.5316,
       "step": 13500
     },
     {
       "epoch": 0.41,
-      "learning_rate": 7.88646401027641e-05,
-      "loss": 3.2645,
+      "learning_rate": 9.995814959123386e-05,
+      "loss": 2.4692,
       "step": 14000
     },
     {
       "epoch": 0.42,
-      "learning_rate": 7.87760818454967e-05,
-      "loss": 3.2276,
+      "learning_rate": 9.995499262676243e-05,
+      "loss": 2.5464,
       "step": 14500
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 7.868425181642037e-05,
-      "loss": 3.235,
+      "epoch": 0.43,
+      "learning_rate": 9.99517209337218e-05,
+      "loss": 2.5222,
       "step": 15000
     },
     {
       "epoch": 0.45,
-      "learning_rate": 7.858915776378836e-05,
-      "loss": 3.1867,
+      "learning_rate": 9.994833451962592e-05,
+      "loss": 2.5304,
       "step": 15500
     },
     {
-      "epoch": 0.47,
-      "learning_rate": 7.849080771125918e-05,
-      "loss": 3.1661,
+      "epoch": 0.46,
+      "learning_rate": 9.994483339225213e-05,
+      "loss": 2.6063,
       "step": 16000
     },
     {
       "epoch": 0.48,
-      "learning_rate": 7.838920995721975e-05,
-      "loss": 3.2233,
+      "learning_rate": 9.994121755964129e-05,
+      "loss": 2.5286,
       "step": 16500
     },
     {
       "epoch": 0.49,
-      "learning_rate": 7.828437307408509e-05,
-      "loss": 3.1632,
+      "learning_rate": 9.993748703009764e-05,
+      "loss": 2.5273,
       "step": 17000
     },
     {
       "epoch": 0.51,
-      "learning_rate": 7.81763059075751e-05,
-      "loss": 3.2981,
+      "learning_rate": 9.993364181218885e-05,
+      "loss": 2.4868,
       "step": 17500
     },
     {
       "epoch": 0.52,
-      "learning_rate": 7.806501757596819e-05,
-      "loss": 3.2572,
+      "learning_rate": 9.992968191474601e-05,
+      "loss": 2.435,
       "step": 18000
     },
     {
       "epoch": 0.54,
-      "learning_rate": 7.795051746933185e-05,
-      "loss": 3.1959,
+      "learning_rate": 9.992560734686357e-05,
+      "loss": 2.484,
       "step": 18500
     },
     {
       "epoch": 0.55,
-      "learning_rate": 7.783281524873039e-05,
-      "loss": 3.2433,
+      "learning_rate": 9.992141811789933e-05,
+      "loss": 2.5301,
       "step": 19000
     },
     {
-      "epoch": 0.57,
-      "learning_rate": 7.771192084540983e-05,
-      "loss": 3.1956,
+      "epoch": 0.56,
+      "learning_rate": 9.991711423747445e-05,
+      "loss": 2.4857,
       "step": 19500
     },
     {
       "epoch": 0.58,
-      "learning_rate": 7.75878444599598e-05,
-      "loss": 3.2134,
+      "learning_rate": 9.991269571547339e-05,
+      "loss": 2.4958,
       "step": 20000
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 7.746059656145306e-05,
-      "loss": 3.1633,
+      "epoch": 0.59,
+      "learning_rate": 9.99081625620439e-05,
+      "loss": 2.4757,
       "step": 20500
     },
     {
       "epoch": 0.61,
-      "learning_rate": 7.733018788656199e-05,
-      "loss": 3.2601,
+      "learning_rate": 9.990351478759696e-05,
+      "loss": 2.544,
       "step": 21000
     },
     {
       "epoch": 0.62,
-      "learning_rate": 7.71966294386527e-05,
-      "loss": 3.173,
+      "learning_rate": 9.989875240280689e-05,
+      "loss": 2.4796,
       "step": 21500
     },
     {
       "epoch": 0.64,
-      "learning_rate": 7.70599324868567e-05,
-      "loss": 3.2264,
+      "learning_rate": 9.989387541861111e-05,
+      "loss": 2.4968,
       "step": 22000
     },
     {
       "epoch": 0.65,
-      "learning_rate": 7.692010856511996e-05,
-      "loss": 3.1828,
+      "learning_rate": 9.988888384621031e-05,
+      "loss": 2.4426,
       "step": 22500
     },
     {
       "epoch": 0.67,
-      "learning_rate": 7.677716947122976e-05,
-      "loss": 3.1522,
+      "learning_rate": 9.988377769706834e-05,
+      "loss": 2.4471,
       "step": 23000
     },
     {
       "epoch": 0.68,
-      "learning_rate": 7.663112726581924e-05,
-      "loss": 3.2148,
+      "learning_rate": 9.987855698291218e-05,
+      "loss": 2.5022,
       "step": 23500
     },
     {
-      "epoch": 0.7,
-      "learning_rate": 7.648199427134978e-05,
-      "loss": 3.1741,
+      "epoch": 0.69,
+      "learning_rate": 9.98732217157319e-05,
+      "loss": 2.5202,
       "step": 24000
     },
     {
       "epoch": 0.71,
-      "learning_rate": 7.632978307107125e-05,
-      "loss": 3.2386,
+      "learning_rate": 9.98677719077807e-05,
+      "loss": 2.5562,
       "step": 24500
     },
     {
-      "epoch": 0.73,
-      "learning_rate": 7.617450650796032e-05,
-      "loss": 3.1865,
+      "epoch": 0.72,
+      "learning_rate": 9.986220757157482e-05,
+      "loss": 2.4888,
       "step": 25000
     },
     {
       "epoch": 0.74,
-      "learning_rate": 7.601617768363678e-05,
-      "loss": 3.2224,
+      "learning_rate": 9.985652871989352e-05,
+      "loss": 2.5049,
       "step": 25500
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 7.58548099572581e-05,
-      "loss": 3.1192,
+      "epoch": 0.75,
+      "learning_rate": 9.98507353657791e-05,
+      "loss": 2.4664,
       "step": 26000
     },
     {
       "epoch": 0.77,
-      "learning_rate": 7.569041694439229e-05,
-      "loss": 3.1802,
+      "learning_rate": 9.984482752253677e-05,
+      "loss": 2.4528,
       "step": 26500
     },
     {
       "epoch": 0.78,
-      "learning_rate": 7.552301251586894e-05,
-      "loss": 3.1781,
+      "learning_rate": 9.98388052037347e-05,
+      "loss": 2.4577,
       "step": 27000
     },
     {
       "epoch": 0.8,
-      "learning_rate": 7.5352610796609e-05,
-      "loss": 3.1921,
+      "learning_rate": 9.983266842320402e-05,
+      "loss": 2.4889,
       "step": 27500
     },
     {
       "epoch": 0.81,
-      "learning_rate": 7.517922616443289e-05,
-      "loss": 3.1896,
+      "learning_rate": 9.982641719503866e-05,
+      "loss": 2.4272,
       "step": 28000
     },
     {
-      "epoch": 0.83,
-      "learning_rate": 7.500287324884736e-05,
-      "loss": 3.1911,
+      "epoch": 0.82,
+      "learning_rate": 9.982005153359547e-05,
+      "loss": 2.4783,
       "step": 28500
     },
     {
       "epoch": 0.84,
-      "learning_rate": 7.482356692981116e-05,
-      "loss": 3.1367,
+      "learning_rate": 9.981357145349406e-05,
+      "loss": 2.4795,
       "step": 29000
     },
     {
-      "epoch": 0.86,
-      "learning_rate": 7.464132233647945e-05,
-      "loss": 3.1416,
+      "epoch": 0.85,
+      "learning_rate": 9.98069769696168e-05,
+      "loss": 2.4807,
       "step": 29500
     },
     {
       "epoch": 0.87,
-      "learning_rate": 7.445615484592736e-05,
-      "loss": 3.1682,
+      "learning_rate": 9.980026809710888e-05,
+      "loss": 2.4951,
       "step": 30000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.979344485137813e-05,
+      "loss": 2.5137,
+      "step": 30500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 9.978650724809511e-05,
+      "loss": 2.5249,
+      "step": 31000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.977945530319297e-05,
+      "loss": 2.4092,
+      "step": 31500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 9.977228903286746e-05,
+      "loss": 2.4978,
+      "step": 32000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 9.976500845357694e-05,
+      "loss": 2.4361,
+      "step": 32500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.975761358204227e-05,
+      "loss": 2.4774,
+      "step": 33000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.975010443524679e-05,
+      "loss": 2.4662,
+      "step": 33500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.974248103043629e-05,
+      "loss": 2.4252,
+      "step": 34000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.973474338511898e-05,
+      "loss": 2.4689,
+      "step": 34500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.3501155376434326,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 1966592,
+      "eval_runtime": 3383.1867,
+      "eval_samples_per_second": 1.135,
+      "eval_steps_per_second": 1.135,
+      "eval_translation_length": 1966592,
+      "step": 34567
     }
   ],
   "logging_steps": 500,
-  "max_steps": 172005,
-  "num_train_epochs": 5,
-  "save_steps": 5000,
-  "total_flos": 1.02801736728576e+18,
+  "max_steps": 1037010,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 7.966891375696282e+16,
   "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:ac93b83e20cb3266b0249c2b9cb223a898cd7a840eb97f009fc035d490eabb4d
+oid sha256:f7c8666ad1a059ed7265a7f4363a6ee3ab5fbfde75b0f7af29bc8baac32797e7
 size 4728