End of training

README.md

@@ -0,0 +1,53 @@
+---
+base_model: Shivam098/opt-translation
+tags:
+- generated_from_trainer
+datasets:
+- opus100
+model-index:
+- name: opt-Translator
+  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. -->
+
+# opt-Translator
+
+This model is a fine-tuned version of [Shivam098/opt-translation](https://huggingface.co/Shivam098/opt-translation) on the opus100 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 300
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,218 @@
+{
+  "_name_or_path": "Shivam098/opt-translation",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": "model.decoder.layers",
+    "damp_percent": 0.1,
+    "dataset": "c4",
+    "desc_act": false,
+    "disable_exllama": true,
+    "group_size": 128,
+    "model_seqlen": 1024,
+    "module_name_preceding_first_block": [
+      "model.shared",
+      "model.encoder.embed_tokens",
+      "model.encoder.embed_positions",
+      "model.encoder.layers.0.self_attn.k_proj",
+      "model.encoder.layers.0.self_attn.v_proj",
+      "model.encoder.layers.0.self_attn.q_proj",
+      "model.encoder.layers.0.self_attn.out_proj",
+      "model.encoder.layers.0.self_attn",
+      "model.encoder.layers.0.self_attn_layer_norm",
+      "model.encoder.layers.0.activation_fn",
+      "model.encoder.layers.0.fc1",
+      "model.encoder.layers.0.fc2",
+      "model.encoder.layers.0.final_layer_norm",
+      "model.encoder.layers.0",
+      "model.encoder.layers.1.self_attn.k_proj",
+      "model.encoder.layers.1.self_attn.v_proj",
+      "model.encoder.layers.1.self_attn.q_proj",
+      "model.encoder.layers.1.self_attn.out_proj",
+      "model.encoder.layers.1.self_attn",
+      "model.encoder.layers.1.self_attn_layer_norm",
+      "model.encoder.layers.1.activation_fn",
+      "model.encoder.layers.1.fc1",
+      "model.encoder.layers.1.fc2",
+      "model.encoder.layers.1.final_layer_norm",
+      "model.encoder.layers.1",
+      "model.encoder.layers.2.self_attn.k_proj",
+      "model.encoder.layers.2.self_attn.v_proj",
+      "model.encoder.layers.2.self_attn.q_proj",
+      "model.encoder.layers.2.self_attn.out_proj",
+      "model.encoder.layers.2.self_attn",
+      "model.encoder.layers.2.self_attn_layer_norm",
+      "model.encoder.layers.2.activation_fn",
+      "model.encoder.layers.2.fc1",
+      "model.encoder.layers.2.fc2",
+      "model.encoder.layers.2.final_layer_norm",
+      "model.encoder.layers.2",
+      "model.encoder.layers.3.self_attn.k_proj",
+      "model.encoder.layers.3.self_attn.v_proj",
+      "model.encoder.layers.3.self_attn.q_proj",
+      "model.encoder.layers.3.self_attn.out_proj",
+      "model.encoder.layers.3.self_attn",
+      "model.encoder.layers.3.self_attn_layer_norm",
+      "model.encoder.layers.3.activation_fn",
+      "model.encoder.layers.3.fc1",
+      "model.encoder.layers.3.fc2",
+      "model.encoder.layers.3.final_layer_norm",
+      "model.encoder.layers.3",
+      "model.encoder.layers.4.self_attn.k_proj",
+      "model.encoder.layers.4.self_attn.v_proj",
+      "model.encoder.layers.4.self_attn.q_proj",
+      "model.encoder.layers.4.self_attn.out_proj",
+      "model.encoder.layers.4.self_attn",
+      "model.encoder.layers.4.self_attn_layer_norm",
+      "model.encoder.layers.4.activation_fn",
+      "model.encoder.layers.4.fc1",
+      "model.encoder.layers.4.fc2",
+      "model.encoder.layers.4.final_layer_norm",
+      "model.encoder.layers.4",
+      "model.encoder.layers.5.self_attn.k_proj",
+      "model.encoder.layers.5.self_attn.v_proj",
+      "model.encoder.layers.5.self_attn.q_proj",
+      "model.encoder.layers.5.self_attn.out_proj",
+      "model.encoder.layers.5.self_attn",
+      "model.encoder.layers.5.self_attn_layer_norm",
+      "model.encoder.layers.5.activation_fn",
+      "model.encoder.layers.5.fc1",
+      "model.encoder.layers.5.fc2",
+      "model.encoder.layers.5.final_layer_norm",
+      "model.encoder.layers.5",
+      "model.encoder.layers.6.self_attn.k_proj",
+      "model.encoder.layers.6.self_attn.v_proj",
+      "model.encoder.layers.6.self_attn.q_proj",
+      "model.encoder.layers.6.self_attn.out_proj",
+      "model.encoder.layers.6.self_attn",
+      "model.encoder.layers.6.self_attn_layer_norm",
+      "model.encoder.layers.6.activation_fn",
+      "model.encoder.layers.6.fc1",
+      "model.encoder.layers.6.fc2",
+      "model.encoder.layers.6.final_layer_norm",
+      "model.encoder.layers.6",
+      "model.encoder.layers.7.self_attn.k_proj",
+      "model.encoder.layers.7.self_attn.v_proj",
+      "model.encoder.layers.7.self_attn.q_proj",
+      "model.encoder.layers.7.self_attn.out_proj",
+      "model.encoder.layers.7.self_attn",
+      "model.encoder.layers.7.self_attn_layer_norm",
+      "model.encoder.layers.7.activation_fn",
+      "model.encoder.layers.7.fc1",
+      "model.encoder.layers.7.fc2",
+      "model.encoder.layers.7.final_layer_norm",
+      "model.encoder.layers.7",
+      "model.encoder.layers.8.self_attn.k_proj",
+      "model.encoder.layers.8.self_attn.v_proj",
+      "model.encoder.layers.8.self_attn.q_proj",
+      "model.encoder.layers.8.self_attn.out_proj",
+      "model.encoder.layers.8.self_attn",
+      "model.encoder.layers.8.self_attn_layer_norm",
+      "model.encoder.layers.8.activation_fn",
+      "model.encoder.layers.8.fc1",
+      "model.encoder.layers.8.fc2",
+      "model.encoder.layers.8.final_layer_norm",
+      "model.encoder.layers.8",
+      "model.encoder.layers.9.self_attn.k_proj",
+      "model.encoder.layers.9.self_attn.v_proj",
+      "model.encoder.layers.9.self_attn.q_proj",
+      "model.encoder.layers.9.self_attn.out_proj",
+      "model.encoder.layers.9.self_attn",
+      "model.encoder.layers.9.self_attn_layer_norm",
+      "model.encoder.layers.9.activation_fn",
+      "model.encoder.layers.9.fc1",
+      "model.encoder.layers.9.fc2",
+      "model.encoder.layers.9.final_layer_norm",
+      "model.encoder.layers.9",
+      "model.encoder.layers.10.self_attn.k_proj",
+      "model.encoder.layers.10.self_attn.v_proj",
+      "model.encoder.layers.10.self_attn.q_proj",
+      "model.encoder.layers.10.self_attn.out_proj",
+      "model.encoder.layers.10.self_attn",
+      "model.encoder.layers.10.self_attn_layer_norm",
+      "model.encoder.layers.10.activation_fn",
+      "model.encoder.layers.10.fc1",
+      "model.encoder.layers.10.fc2",
+      "model.encoder.layers.10.final_layer_norm",
+      "model.encoder.layers.10",
+      "model.encoder.layers.11.self_attn.k_proj",
+      "model.encoder.layers.11.self_attn.v_proj",
+      "model.encoder.layers.11.self_attn.q_proj",
+      "model.encoder.layers.11.self_attn.out_proj",
+      "model.encoder.layers.11.self_attn",
+      "model.encoder.layers.11.self_attn_layer_norm",
+      "model.encoder.layers.11.activation_fn",
+      "model.encoder.layers.11.fc1",
+      "model.encoder.layers.11.fc2",
+      "model.encoder.layers.11.final_layer_norm",
+      "model.encoder.layers.11",
+      "model.encoder.layers",
+      "model.encoder.layernorm_embedding",
+      "model.encoder.layer_norm",
+      "model.encoder",
+      "model.decoder.embed_tokens",
+      "model.decoder.embed_positions"
+    ],
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": true
+  },
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250054
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 200,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84875a3830a144e79616e806032fd39e1ceb56e4f731efc07693d74011dadc5d
+size 925140285

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098050078b86e9e2f24c87d8529331a2c16f85d801b54f544323bb998597e9c2
+size 4155