End of training

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: google/madlad400-3b-mt
+datasets:
+- generator
+metrics:
+- bleu
+model-index:
+- name: traduction_fon_french
+  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. -->
+
+# traduction_fon_french
+
+This model is a fine-tuned version of [google/madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.2698
+- Bleu: 0.217
+- Gen Len: 9.6092
+
+## 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: 0.0003
+- train_batch_size: 18
+- eval_batch_size: 18
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
+| 3.3025        | 1.0   | 2528  | 5.2043          | 0.2814 | 8.9524  |
+| 3.1868        | 2.0   | 5056  | 5.2746          | 0.1393 | 8.8278  |
+| 3.0907        | 3.0   | 7584  | 5.1989          | 0.2607 | 9.6087  |
+| 3.0409        | 4.0   | 10112 | 5.2698          | 0.217  | 9.6092  |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/madlad400-3b-mt",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8595b3871624ff2f5a98a0cf050f6ac464e37b6abc3e2705218b8616346f9967
+size 37803600

runs/Jun23_14-49-55_ea23d3ed3b0b/events.out.tfevents.1719155250.ea23d3ed3b0b.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d46a0e43fab839c3c6da38db880838defb1f22960ff1f51571e1433307efe3
+size 12003

runs/Jun23_14-49-55_ea23d3ed3b0b/events.out.tfevents.1719186271.ea23d3ed3b0b.24.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8adf91e0bd1e33562ce4703daaf30cf8277b344b048bb9eb30d1b068fa2a2881
+size 458

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "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:ef11ac9a22c7503492f56d48dce53be20e339b63605983e9f27d2cd0e0f3922c
+size 4427844

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "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": "</s>",
+      "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": false,
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "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 sha256:49e8e25b56c47e77837e46a4181b4e9d2056532fc3e3e0e63a6132b14cee8772
+size 5240