End of training

README.md

@@ -0,0 +1,56 @@
+---
+license: cc-by-4.0
+base_model: allegro/plt5-base
+tags:
+- generated_from_trainer
+model-index:
+- name: plt5-base-finetuned-onet
+  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. -->
+
+# plt5-base-finetuned-onet
+
+This model is a fine-tuned version of [allegro/plt5-base](https://huggingface.co/allegro/plt5-base) on the None dataset.
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | P       | R       | F1     | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:------:|:-------:|
+| No log        | 1.0   | 250  | nan             | 62.1748 | 60.3819 | 61.226 | 18.44   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "allegro/plt5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 50048
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7a9b01f6ae198dc70e7f660236825951eae5c9567cd574664041ace3da00ce
+size 1100445544

runs/Jan04_13-53-08_bc7253dc3030/events.out.tfevents.1704376389.bc7253dc3030.297.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51fe2e863c52cc1782f665d5a61942e05b59f2cc4628181acc40fd194818ba54
+size 4704

runs/Jan04_13-53-56_bc7253dc3030/events.out.tfevents.1704376441.bc7253dc3030.297.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6922ada73cca67998a76c95d13af3077b7b61598f82c7e0a53fb422b512e2614
+size 9320

runs/Jan04_14-02-37_bc7253dc3030/events.out.tfevents.1704376963.bc7253dc3030.297.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d7ef2d8f749c2a3226f3f437716e1049e5fe6ae7bcb93288b19dda3d1e24e0
+size 4704

runs/Jan04_14-02-37_bc7253dc3030/events.out.tfevents.1704377306.bc7253dc3030.297.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55013cf009627bf572e9cc6b4be33f3288a76d216387bfc79510b867a00f0a9e
+size 4704

runs/Jan04_14-02-37_bc7253dc3030/events.out.tfevents.1704377646.bc7253dc3030.297.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec51974c8e443d672d962bd58459fe5b6fd58342d88cc38da7094785c593f01
+size 5516

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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:a200b4b9d7106b32ea2340e5cd27033a5c03ae5ece9241ab6e1f685b938800b9
+size 1124950

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1cbe460fa57b1fa7848411326e531ee02b673f179b30dc6250a8242a5b0de1
+size 4856