legacy

config.json

@@ -1,15 +1,15 @@
 {
-  "_name_or_path": "/home/ubuntu/Pythonprojects/kcbert2/models/t5/checkpoint-13000",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
   "d_model": 768,
   "decoder_start_token_id": 0,
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
+  "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
   "layer_norm_epsilon": 1e-06,
@@ -18,10 +18,40 @@
   "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,
+  "output_past": true,
   "pad_token_id": 0,
   "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: "
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.16.2",
   "use_cache": true,
-  "vocab_size": 64128
+  "vocab_size": 32128
 }

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccbf67abf7b7df2654ca82e81966f4e1221e13a63d031a443f301e8ecdaceb7b
-size 1980001437
+oid sha256:6e7250ce1ab70dc1a9fd526bb4d5d8eb5222e08cdf5b654e319428c72c219d89
+size 1783379133

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6abf405ac68e47b566017e60d64f372f68c57bceb04bf0e7b87195e74315658
-size 990044879
+oid sha256:3e23f9bb16399dbb6299333937b7d2eeb28058c49c33ee3ff3a2e4f28f9930cb
+size 891730879

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c1c8707660f293cf247bc55f30db15ce41969c38eb328ae554545164b41802
+oid sha256:13d5b1bae4964fb2f4d01538a124e8fa3d09ef60275a74b9b04e9572c2256028
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a3d40f34928ebeb55fd517c0a57bdac49979a9803d4310aa6fffee0ec04b497
+oid sha256:06cbc2ad564cf4cd4ae1683a2a75297d61e4bb88322c20b1f9c2c3540e65749c
 size 623

trainer_state.json

@@ -1,102 +1,146 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.256382865078518,
-  "global_step": 18000,
+  "epoch": 14.838626976214215,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.31175968050956726,
-      "eval_runtime": 257.9912,
-      "eval_samples_per_second": 96.484,
-      "eval_steps_per_second": 24.121,
-      "step": 1755
+      "eval_loss": 0.9184420704841614,
+      "eval_runtime": 226.0895,
+      "eval_samples_per_second": 110.098,
+      "eval_steps_per_second": 27.524,
+      "step": 438
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.29588261246681213,
-      "eval_runtime": 263.3642,
-      "eval_samples_per_second": 94.516,
-      "eval_steps_per_second": 23.629,
-      "step": 3510
+      "eval_loss": 0.8269533514976501,
+      "eval_runtime": 222.6047,
+      "eval_samples_per_second": 111.822,
+      "eval_steps_per_second": 27.955,
+      "step": 876
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.28089064359664917,
-      "eval_runtime": 249.235,
-      "eval_samples_per_second": 99.874,
-      "eval_steps_per_second": 24.968,
-      "step": 5265
+      "eval_loss": 0.7799285054206848,
+      "eval_runtime": 267.0428,
+      "eval_samples_per_second": 93.214,
+      "eval_steps_per_second": 23.303,
+      "step": 1314
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.2724970579147339,
-      "eval_runtime": 252.6189,
-      "eval_samples_per_second": 98.536,
-      "eval_steps_per_second": 24.634,
-      "step": 7020
+      "eval_loss": 0.7528017163276672,
+      "eval_runtime": 225.2214,
+      "eval_samples_per_second": 110.522,
+      "eval_steps_per_second": 27.631,
+      "step": 1752
     },
     {
-      "epoch": 5.0,
-      "eval_loss": 0.2664159834384918,
-      "eval_runtime": 256.3161,
-      "eval_samples_per_second": 97.114,
-      "eval_steps_per_second": 24.279,
-      "step": 8775
+      "epoch": 4.57,
+      "learning_rate": 6.9558599695586e-05,
+      "loss": 0.9432,
+      "step": 2000
     },
     {
-      "epoch": 5.7,
-      "learning_rate": 5.251661918328585e-05,
-      "loss": 0.2909,
-      "step": 10000
+      "epoch": 5.0,
+      "eval_loss": 0.7184237241744995,
+      "eval_runtime": 225.9905,
+      "eval_samples_per_second": 110.146,
+      "eval_steps_per_second": 27.537,
+      "step": 2190
     },
     {
       "epoch": 6.0,
-      "eval_loss": 0.26015016436576843,
-      "eval_runtime": 251.5124,
-      "eval_samples_per_second": 98.969,
-      "eval_steps_per_second": 24.742,
-      "step": 10530
+      "eval_loss": 0.6917603611946106,
+      "eval_runtime": 229.2094,
+      "eval_samples_per_second": 108.599,
+      "eval_steps_per_second": 27.15,
+      "step": 2628
     },
     {
       "epoch": 7.0,
-      "eval_loss": 0.2540057301521301,
-      "eval_runtime": 257.1925,
-      "eval_samples_per_second": 96.784,
-      "eval_steps_per_second": 24.196,
-      "step": 12285
+      "eval_loss": 0.6674416065216064,
+      "eval_runtime": 228.8661,
+      "eval_samples_per_second": 108.762,
+      "eval_steps_per_second": 27.191,
+      "step": 3066
     },
     {
       "epoch": 8.0,
-      "eval_loss": 0.25006118416786194,
-      "eval_runtime": 249.8553,
-      "eval_samples_per_second": 99.626,
-      "eval_steps_per_second": 24.906,
-      "step": 14040
+      "eval_loss": 0.6534304022789001,
+      "eval_runtime": 238.4381,
+      "eval_samples_per_second": 104.396,
+      "eval_steps_per_second": 26.099,
+      "step": 3504
     },
     {
       "epoch": 9.0,
-      "eval_loss": 0.2474370002746582,
-      "eval_runtime": 250.2934,
-      "eval_samples_per_second": 99.451,
-      "eval_steps_per_second": 24.863,
-      "step": 15795
+      "eval_loss": 0.6406867504119873,
+      "eval_runtime": 235.4552,
+      "eval_samples_per_second": 105.719,
+      "eval_steps_per_second": 26.43,
+      "step": 3942
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 3.9117199391171995e-05,
+      "loss": 0.6607,
+      "step": 4000
     },
     {
       "epoch": 10.0,
-      "eval_loss": 0.24529701471328735,
-      "eval_runtime": 250.3126,
-      "eval_samples_per_second": 99.444,
-      "eval_steps_per_second": 24.861,
-      "step": 17550
+      "eval_loss": 0.6275271773338318,
+      "eval_runtime": 231.6414,
+      "eval_samples_per_second": 107.459,
+      "eval_steps_per_second": 26.865,
+      "step": 4380
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.6164868474006653,
+      "eval_runtime": 229.8159,
+      "eval_samples_per_second": 108.313,
+      "eval_steps_per_second": 27.078,
+      "step": 4818
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.610621452331543,
+      "eval_runtime": 234.5136,
+      "eval_samples_per_second": 106.143,
+      "eval_steps_per_second": 26.536,
+      "step": 5256
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.6076993942260742,
+      "eval_runtime": 221.8665,
+      "eval_samples_per_second": 112.194,
+      "eval_steps_per_second": 28.048,
+      "step": 5694
+    },
+    {
+      "epoch": 13.7,
+      "learning_rate": 8.675799086757991e-06,
+      "loss": 0.5624,
+      "step": 6000
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.6030386686325073,
+      "eval_runtime": 225.3038,
+      "eval_samples_per_second": 110.482,
+      "eval_steps_per_second": 27.62,
+      "step": 6132
     }
   ],
-  "max_steps": 21060,
-  "num_train_epochs": 12,
-  "total_flos": 3.507947600412672e+17,
+  "max_steps": 6570,
+  "num_train_epochs": 15,
+  "total_flos": 5.075204254610227e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b6631495f079f844c7ee6ed1052b675e4ee35710297e803762c3749d54d0ca
+oid sha256:92440562452781ca3f73efd16bc795762158e4972a2597602a92148285739f94
 size 2991