End of training

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,115 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: pretrain_2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# pretrain_2
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5716
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 48
+- eval_batch_size: 48
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 96
+- total_eval_batch_size: 96
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 200
+
+### Training results
+
+| Training Loss | Epoch | Step    | Validation Loss |
+|:-------------:|:-----:|:-------:|:---------------:|
+| 0.7609        | 1.0   | 24286   | 0.6893          |
+| 0.7239        | 2.0   | 48572   | 0.6476          |
+| 0.7056        | 3.0   | 72858   | 0.6279          |
+| 0.6961        | 4.0   | 97144   | 0.6242          |
+| 0.6838        | 5.0   | 121430  | 0.6123          |
+| 0.6742        | 6.0   | 145716  | 0.6111          |
+| 0.6762        | 7.0   | 170002  | 0.6064          |
+| 0.6722        | 8.0   | 194288  | 0.6052          |
+| 0.6603        | 9.0   | 218574  | 0.6043          |
+| 0.6522        | 10.0  | 242860  | 0.6005          |
+| 0.654         | 11.0  | 267146  | 0.6022          |
+| 0.6422        | 12.0  | 291432  | 0.5964          |
+| 0.6495        | 13.0  | 315718  | 0.5967          |
+| 0.655         | 14.0  | 340004  | 0.5961          |
+| 0.651         | 15.0  | 364290  | 0.5925          |
+| 0.6458        | 16.0  | 388576  | 0.5922          |
+| 0.6441        | 17.0  | 412862  | 0.5901          |
+| 0.6477        | 18.0  | 437148  | 0.5871          |
+| 0.6382        | 19.0  | 461434  | 0.5896          |
+| 0.6426        | 20.0  | 485720  | 0.5878          |
+| 0.6369        | 21.0  | 510006  | 0.5873          |
+| 0.6298        | 22.0  | 534292  | 0.5844          |
+| 0.6388        | 23.0  | 558578  | 0.5863          |
+| 0.6389        | 24.0  | 582864  | 0.5826          |
+| 0.6394        | 25.0  | 607150  | 0.5861          |
+| 0.6295        | 26.0  | 631436  | 0.5848          |
+| 0.6365        | 27.0  | 655722  | 0.5815          |
+| 0.6347        | 28.0  | 680008  | 0.5836          |
+| 0.6384        | 29.0  | 704294  | 0.5870          |
+| 0.6381        | 30.0  | 728580  | 0.5816          |
+| 0.6306        | 31.0  | 752866  | 0.5813          |
+| 0.6385        | 32.0  | 777152  | 0.5838          |
+| 0.6338        | 33.0  | 801438  | 0.5808          |
+| 0.6331        | 34.0  | 825724  | 0.5806          |
+| 0.6235        | 35.0  | 850010  | 0.5825          |
+| 0.6329        | 36.0  | 874296  | 0.5825          |
+| 0.6338        | 37.0  | 898582  | 0.5810          |
+| 0.6257        | 38.0  | 922868  | 0.5803          |
+| 0.6268        | 39.0  | 947154  | 0.5810          |
+| 0.6371        | 40.0  | 971440  | 0.5759          |
+| 0.6272        | 41.0  | 995726  | 0.5775          |
+| 0.6276        | 42.0  | 1020012 | 0.5771          |
+| 0.635         | 43.0  | 1044298 | 0.5757          |
+| 0.6314        | 44.0  | 1068584 | 0.5753          |
+| 0.6279        | 45.0  | 1092870 | 0.5760          |
+| 0.6186        | 46.0  | 1117156 | 0.5756          |
+| 0.6214        | 47.0  | 1141442 | 0.5763          |
+| 0.6257        | 48.0  | 1165728 | 0.5776          |
+| 0.6272        | 49.0  | 1190014 | 0.5746          |
+| 0.6291        | 50.0  | 1214300 | 0.5734          |
+| 0.6311        | 51.0  | 1238586 | 0.5715          |
+| 0.6279        | 52.0  | 1262872 | 0.5776          |
+| 0.6372        | 53.0  | 1287158 | 0.5725          |
+| 0.6155        | 54.0  | 1311444 | 0.5782          |
+| 0.6241        | 55.0  | 1335730 | 0.5748          |
+| 0.6187        | 56.0  | 1360016 | 0.5716          |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.6.0.dev20241022+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "/home/bly/GitHub/results/AKK-SUX-ELX_T5Small/pretrain_1/checkpoint-1165728",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "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: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 107957
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a7701f690fbf9576ad8c50d1b8b500fbf4d71c37d75daa059fb64015537b2f
+size 397339688

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a611ced5fb5dda72f545f09f7abf4ed995e20509752de0f44b27c62fd46d339
+size 16373572

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40fdc141ebbef8299bfa7bb145df657a19d3ffe27c1736fca370bb842328d08
+size 13213579

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbff06547b5bd5a4e070df651c4efb073bcafcd94551527968a8c8810a25f5af
+size 5432