genta-tech/genta-mix

.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 +1,57 @@
+---
+license: apache-2.0
+base_model: bigscience/mt0-base
+tags:
+- generated_from_trainer
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [bigscience/mt0-base](https://huggingface.co/bigscience/mt0-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: 1.41e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "bigscience/mt0-base",
+  "architectures": [
+    "MT5ForSequenceClassification"
+  ],
+  "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",
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fc5d27e2450878df7672831f9c9e55636c37305b7d8535a6e32d5c30c821f2
+size 1563663820

runs/Nov20_07-54-23_6ffc095b5239/events.out.tfevents.1700466964.6ffc095b5239

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1a2c89bb00a8bc4e3658fb3fcf93d2a8a973ac140ee61f72978e20dfc55fdb
+size 4445

runs/Nov20_07-58-24_6ffc095b5239/events.out.tfevents.1700467275.6ffc095b5239

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0758e8e594fc7493e10a59e8838f9eae62109e3ca7d8421540e96d493f82d10e
+size 4446

runs/Nov20_08-27-55_6ffc095b5239/events.out.tfevents.1700468933.6ffc095b5239

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204442f3b4fb21380bd504da4915013e1c84170065cdf7bfc458dd8d4f6e8ab8
+size 4446

runs/Nov20_08-44-14_6ffc095b5239/events.out.tfevents.1700469913.6ffc095b5239

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34136404da4d717b838ff49417814c495aae08732a7d7c4dc7b7a187bf7ad35
+size 4800

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e5c72a5ea09da48b2f316760b8bc5a445683ab9a5bc6b68db5d8db624ecceb
+size 16315213

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "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,
+  "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:d509c6a13c68d1f8bd0bd6337c19a23a7c4d0abaaec9b20aa22242f7cbbadf64
+size 4155