initial

README.md

@@ -1,3 +1,54 @@
 ---
+language:
+- br
+- fr
 license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: m2m100_br_fr
+  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. -->
+
+# m2m100_br_fr
+
+This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on an unknown 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.23.1
+- Pytorch 1.12.1+cu116
+- Datasets 2.6.1
+- Tokenizers 0.13.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.4955534830489579,
+    "train_runtime": 15709.331,
+    "train_samples": 48907,
+    "train_samples_per_second": 9.34,
+    "train_steps_per_second": 1.168
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "facebook/m2m100_418M",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "M2M100ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.05,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.05,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 128028,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "m2m_100",
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 128112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e6ca2e2048c0abf133d1ea4f986221f7744da591536e2c96c4aa7c8ad290d8e
+size 1935792071

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
+size 2423393

special_tokens_map.json

@@ -0,0 +1,109 @@
+{
+  "additional_special_tokens": [
+    "__af__",
+    "__am__",
+    "__ar__",
+    "__ast__",
+    "__az__",
+    "__ba__",
+    "__be__",
+    "__bg__",
+    "__bn__",
+    "__br__",
+    "__bs__",
+    "__ca__",
+    "__ceb__",
+    "__cs__",
+    "__cy__",
+    "__da__",
+    "__de__",
+    "__el__",
+    "__en__",
+    "__es__",
+    "__et__",
+    "__fa__",
+    "__ff__",
+    "__fi__",
+    "__fr__",
+    "__fy__",
+    "__ga__",
+    "__gd__",
+    "__gl__",
+    "__gu__",
+    "__ha__",
+    "__he__",
+    "__hi__",
+    "__hr__",
+    "__ht__",
+    "__hu__",
+    "__hy__",
+    "__id__",
+    "__ig__",
+    "__ilo__",
+    "__is__",
+    "__it__",
+    "__ja__",
+    "__jv__",
+    "__ka__",
+    "__kk__",
+    "__km__",
+    "__kn__",
+    "__ko__",
+    "__lb__",
+    "__lg__",
+    "__ln__",
+    "__lo__",
+    "__lt__",
+    "__lv__",
+    "__mg__",
+    "__mk__",
+    "__ml__",
+    "__mn__",
+    "__mr__",
+    "__ms__",
+    "__my__",
+    "__ne__",
+    "__nl__",
+    "__no__",
+    "__ns__",
+    "__oc__",
+    "__or__",
+    "__pa__",
+    "__pl__",
+    "__ps__",
+    "__pt__",
+    "__ro__",
+    "__ru__",
+    "__sd__",
+    "__si__",
+    "__sk__",
+    "__sl__",
+    "__so__",
+    "__sq__",
+    "__sr__",
+    "__ss__",
+    "__su__",
+    "__sv__",
+    "__sw__",
+    "__ta__",
+    "__th__",
+    "__tl__",
+    "__tn__",
+    "__tr__",
+    "__uk__",
+    "__ur__",
+    "__uz__",
+    "__vi__",
+    "__wo__",
+    "__xh__",
+    "__yi__",
+    "__yo__",
+    "__zh__",
+    "__zu__"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,119 @@
+{
+  "additional_special_tokens": [
+    "__af__",
+    "__am__",
+    "__ar__",
+    "__ast__",
+    "__az__",
+    "__ba__",
+    "__be__",
+    "__bg__",
+    "__bn__",
+    "__br__",
+    "__bs__",
+    "__ca__",
+    "__ceb__",
+    "__cs__",
+    "__cy__",
+    "__da__",
+    "__de__",
+    "__el__",
+    "__en__",
+    "__es__",
+    "__et__",
+    "__fa__",
+    "__ff__",
+    "__fi__",
+    "__fr__",
+    "__fy__",
+    "__ga__",
+    "__gd__",
+    "__gl__",
+    "__gu__",
+    "__ha__",
+    "__he__",
+    "__hi__",
+    "__hr__",
+    "__ht__",
+    "__hu__",
+    "__hy__",
+    "__id__",
+    "__ig__",
+    "__ilo__",
+    "__is__",
+    "__it__",
+    "__ja__",
+    "__jv__",
+    "__ka__",
+    "__kk__",
+    "__km__",
+    "__kn__",
+    "__ko__",
+    "__lb__",
+    "__lg__",
+    "__ln__",
+    "__lo__",
+    "__lt__",
+    "__lv__",
+    "__mg__",
+    "__mk__",
+    "__ml__",
+    "__mn__",
+    "__mr__",
+    "__ms__",
+    "__my__",
+    "__ne__",
+    "__nl__",
+    "__no__",
+    "__ns__",
+    "__oc__",
+    "__or__",
+    "__pa__",
+    "__pl__",
+    "__ps__",
+    "__pt__",
+    "__ro__",
+    "__ru__",
+    "__sd__",
+    "__si__",
+    "__sk__",
+    "__sl__",
+    "__so__",
+    "__sq__",
+    "__sr__",
+    "__ss__",
+    "__su__",
+    "__sv__",
+    "__sw__",
+    "__ta__",
+    "__th__",
+    "__tl__",
+    "__tn__",
+    "__tr__",
+    "__uk__",
+    "__ur__",
+    "__uz__",
+    "__vi__",
+    "__wo__",
+    "__xh__",
+    "__yi__",
+    "__yo__",
+    "__zh__",
+    "__zu__"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "language_codes": "m2m100",
+  "model_max_length": 1024,
+  "name_or_path": "facebook/m2m100_418M",
+  "num_madeup_words": 8,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json",
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "M2M100Tokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.4955534830489579,
+    "train_runtime": 15709.331,
+    "train_samples": 48907,
+    "train_samples_per_second": 9.34,
+    "train_steps_per_second": 1.168
+}

trainer_state.json

@@ -0,0 +1,241 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 18342,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.863700795987351e-05,
+      "loss": 2.8121,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7274015919747035e-05,
+      "loss": 2.3962,
+      "step": 1000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.5911023879620545e-05,
+      "loss": 2.2275,
+      "step": 1500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.454803183949406e-05,
+      "loss": 2.1283,
+      "step": 2000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.318503979936757e-05,
+      "loss": 2.0421,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.182204775924109e-05,
+      "loss": 1.9646,
+      "step": 3000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.0459055719114605e-05,
+      "loss": 1.9383,
+      "step": 3500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.9096063678988114e-05,
+      "loss": 1.8862,
+      "step": 4000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.773307163886163e-05,
+      "loss": 1.8524,
+      "step": 4500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.637007959873515e-05,
+      "loss": 1.8164,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.500708755860866e-05,
+      "loss": 1.7536,
+      "step": 5500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.3644095518482174e-05,
+      "loss": 1.7631,
+      "step": 6000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.228110347835569e-05,
+      "loss": 1.4821,
+      "step": 6500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.09181114382292e-05,
+      "loss": 1.4501,
+      "step": 7000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2.9555119398102717e-05,
+      "loss": 1.4364,
+      "step": 7500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.8192127357976233e-05,
+      "loss": 1.4028,
+      "step": 8000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.6829135317849746e-05,
+      "loss": 1.3865,
+      "step": 8500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.546614327772326e-05,
+      "loss": 1.4069,
+      "step": 9000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.4103151237596773e-05,
+      "loss": 1.3883,
+      "step": 9500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.2740159197470286e-05,
+      "loss": 1.3654,
+      "step": 10000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.1377167157343802e-05,
+      "loss": 1.3411,
+      "step": 10500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.0014175117217316e-05,
+      "loss": 1.3359,
+      "step": 11000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8651183077090832e-05,
+      "loss": 1.379,
+      "step": 11500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.7288191036964345e-05,
+      "loss": 1.3316,
+      "step": 12000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.592519899683786e-05,
+      "loss": 1.2242,
+      "step": 12500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.4562206956711375e-05,
+      "loss": 1.0537,
+      "step": 13000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.3199214916584887e-05,
+      "loss": 1.0697,
+      "step": 13500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.1836222876458403e-05,
+      "loss": 1.0704,
+      "step": 14000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.0473230836331916e-05,
+      "loss": 1.0918,
+      "step": 14500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 9.110238796205431e-06,
+      "loss": 1.0878,
+      "step": 15000
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.747246756078944e-06,
+      "loss": 1.0506,
+      "step": 15500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.384254715952459e-06,
+      "loss": 1.0557,
+      "step": 16000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.021262675825973e-06,
+      "loss": 1.0325,
+      "step": 16500
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 3.658270635699488e-06,
+      "loss": 1.0784,
+      "step": 17000
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.295278595573002e-06,
+      "loss": 1.0239,
+      "step": 17500
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 9.322865554465163e-07,
+      "loss": 1.0211,
+      "step": 18000
+    },
+    {
+      "epoch": 3.0,
+      "step": 18342,
+      "total_flos": 2.148457555862323e+16,
+      "train_loss": 1.4955534830489579,
+      "train_runtime": 15709.331,
+      "train_samples_per_second": 9.34,
+      "train_steps_per_second": 1.168
+    }
+  ],
+  "max_steps": 18342,
+  "num_train_epochs": 3,
+  "total_flos": 2.148457555862323e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906c9235c8bf75589426402d4a87903317a704f12dd138c3607b781101161aea
+size 3503