End of training

.gitattributes

@@ -33,3 +33,4 @@ 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

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: bigscience/mt0-small
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mt-0-small-multilanguage-query-extraction
+  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. -->
+
+# mt-0-small-multilanguage-query-extraction
+
+This model is a fine-tuned version of [bigscience/mt0-small](https://huggingface.co/bigscience/mt0-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0037
+- Rouge1: 90.139
+- Rouge2: 88.3647
+- Rougel: 90.1385
+- Rougelsum: 90.1396
+- Gen Len: 19.0
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 0.0046        | 1.0   | 17500 | 0.0040          | 90.1388 | 88.3642 | 90.1382 | 90.1395   | 19.0    |
+| 0.0041        | 2.0   | 35000 | 0.0038          | 90.139  | 88.3647 | 90.1385 | 90.1396   | 19.0    |
+| 0.0039        | 3.0   | 52500 | 0.0037          | 90.139  | 88.3647 | 90.1385 | 90.1396   | 19.0    |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/mt0-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 250100
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.1"
+}

logs/events.out.tfevents.1715223447.cfd70a6b34ef.1925.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880d5ad40a31058318af707ca7065abec16d896b74750c3de9068104906190af
+size 5075

logs/events.out.tfevents.1715223471.cfd70a6b34ef.1925.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152636d6f856a832adb7b81c29f8555b718665419a15f1cde232dc5f83b2d3fc
+size 5075

logs/events.out.tfevents.1715223511.cfd70a6b34ef.1925.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ac08ee69d3358b6e6cbbf76f99489bf8fae97c9c1207f8ee57af53f2609d6e
+size 5073

logs/events.out.tfevents.1715223815.cfd70a6b34ef.1925.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef63b9c225618dbf4651736f6dad5628235278f89d4bf46c8fdb1f1a6dd3dfc
+size 5075

logs/events.out.tfevents.1715223956.cfd70a6b34ef.1925.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e41ce41577e0e238e3482031f887bf1d1cf9386397ff2cbefdc9e7ed00f42e
+size 5073

logs/events.out.tfevents.1715224140.cfd70a6b34ef.1925.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d568c8595315aac8d02160d80ae2b39eefb9e90e81b139cd0ba096ba390babbb
+size 5073

logs/events.out.tfevents.1715224268.cfd70a6b34ef.1925.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c087f0f9cdabf890a8d3ebe244b19c5b0dc76c29bf03cbfff1902fd68dd4ad70
+size 29485

logs/events.out.tfevents.1715253803.cfd70a6b34ef.1925.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebeb8cedb563744164d154d82d9523b6ddc2931883c8d71a065e5bbeb2e8fb84
+size 623

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7c881f67958f8dc0179da54977efc61d33683a2594aab74487d2b3829afabd
+size 1200680360

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:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eee34a459d686dbb9e550c0c02c91b6bc2db7363f2eea5d3a248a147909dbac
+size 16315807

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "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
+    },
+    "596": {
+      "content": "{",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1354": {
+      "content": "}",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "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 sha256:2e20108de9a4863eba3508ef9cfd0d2106371b6493b702f574d50ab3a1fef418
+size 5240