Deploy mBART Yemba translation model

.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 +1,49 @@
+---
+language:
+- fr
+- mul  
+language_bcp47:
+- fr
+- yemba
+license: apache-2.0  
+base_model: facebook/mbart-large-50
+tags:
+- translation
+- mbart
+- yemba
+- african-languages
+- low-resource-languages
+pipeline_tag: translation
+---
+
+# mBART Yemba Translation Model
+
+Ce modèle est un fine-tuning de mBART pour la traduction entre le français et le yemba.
+
+## Utilisation
+
+Voici comment utiliser le modèle:
+
+from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
+
+# Charger le modèle et le tokenizer
+model = MBartForConditionalGeneration.from_pretrained("Dims002/mbart-yemba-translator")
+tokenizer = MBart50TokenizerFast.from_pretrained("Dims002/mbart-yemba-translator")
+
+# Exemple de traduction
+def translate_text(text, src_lang="fr_XX", tgt_lang="yemba"):
+    tokenizer.src_lang = src_lang
+    encoded = tokenizer(text, return_tensors="pt")
+    generated_tokens = model.generate(**encoded)
+    return tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
+
+## Détails du modèle
+
+- **Modèle de base**: facebook/mbart-large-50
+- **Langues**: Français ↔ Yemba  
+- **Checkpoint**: 20000
+
+## Langues supportées
+
+- **Français** (fr): Langue source principale
+- **Yemba**: Langue cible (langue bantoue du Cameroun)

config.json

@@ -0,0 +1,57 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "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": null,
+  "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": null,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "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": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10048899e0ebb9985c5b84af35d4b16275d57a419d5b1657a735b0bcedde5a5
+size 2444578688

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e478347f42b0b9c090cb01c428c09a22ed6f56701e7e412146a43607c156c2
+size 4887473903

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dcf59ca816e53587eb4eca1649f47c957fc98c7803ee70559cc740df9ca4a0b
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265959433d40a86dc9b378fa56293d719e24b10778e4ed5c0f95bbb43a0a03e7
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e111882faa53a8ec61ad5f6b886695ae6756ef1d6ed3158f51fc7161a9c510c6
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,69 @@
+{
+  "additional_special_tokens": [
+    "ar_AR",
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN",
+    "af_ZA",
+    "az_AZ",
+    "bn_IN",
+    "fa_IR",
+    "he_IL",
+    "hr_HR",
+    "id_ID",
+    "ka_GE",
+    "km_KH",
+    "mk_MK",
+    "ml_IN",
+    "mn_MN",
+    "mr_IN",
+    "pl_PL",
+    "ps_AF",
+    "pt_XX",
+    "sv_SE",
+    "sw_KE",
+    "ta_IN",
+    "te_IN",
+    "th_TH",
+    "tl_XX",
+    "uk_UA",
+    "ur_PK",
+    "xh_ZA",
+    "gl_ES",
+    "sl_SI"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d967c5b869fb40df2df523bdc86a7e46888783e349ba81e7883b35f44a8c7ac0
+size 17110186

tokenizer_config.json

@@ -0,0 +1,528 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "ar_AR",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "cs_CZ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "de_DE",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250004": {
+      "content": "en_XX",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250005": {
+      "content": "es_XX",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250006": {
+      "content": "et_EE",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250007": {
+      "content": "fi_FI",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250008": {
+      "content": "fr_XX",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250009": {
+      "content": "gu_IN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250010": {
+      "content": "hi_IN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250011": {
+      "content": "it_IT",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250012": {
+      "content": "ja_XX",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250013": {
+      "content": "kk_KZ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250014": {
+      "content": "ko_KR",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250015": {
+      "content": "lt_LT",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250016": {
+      "content": "lv_LV",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250017": {
+      "content": "my_MM",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250018": {
+      "content": "ne_NP",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250019": {
+      "content": "nl_XX",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250020": {
+      "content": "ro_RO",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250021": {
+      "content": "ru_RU",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250022": {
+      "content": "si_LK",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250023": {
+      "content": "tr_TR",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250024": {
+      "content": "vi_VN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250025": {
+      "content": "zh_CN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250026": {
+      "content": "af_ZA",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250027": {
+      "content": "az_AZ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250028": {
+      "content": "bn_IN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250029": {
+      "content": "fa_IR",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250030": {
+      "content": "he_IL",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250031": {
+      "content": "hr_HR",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250032": {
+      "content": "id_ID",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250033": {
+      "content": "ka_GE",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250034": {
+      "content": "km_KH",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250035": {
+      "content": "mk_MK",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250036": {
+      "content": "ml_IN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250037": {
+      "content": "mn_MN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250038": {
+      "content": "mr_IN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250039": {
+      "content": "pl_PL",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250040": {
+      "content": "ps_AF",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250041": {
+      "content": "pt_XX",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250042": {
+      "content": "sv_SE",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250043": {
+      "content": "sw_KE",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250044": {
+      "content": "ta_IN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250045": {
+      "content": "te_IN",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250046": {
+      "content": "th_TH",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250047": {
+      "content": "tl_XX",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250048": {
+      "content": "uk_UA",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250049": {
+      "content": "ur_PK",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250050": {
+      "content": "xh_ZA",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250051": {
+      "content": "gl_ES",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250052": {
+      "content": "sl_SI",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250053": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "ar_AR",
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN",
+    "af_ZA",
+    "az_AZ",
+    "bn_IN",
+    "fa_IR",
+    "he_IL",
+    "hr_HR",
+    "id_ID",
+    "ka_GE",
+    "km_KH",
+    "mk_MK",
+    "ml_IN",
+    "mn_MN",
+    "mr_IN",
+    "pl_PL",
+    "ps_AF",
+    "pt_XX",
+    "sv_SE",
+    "sw_KE",
+    "ta_IN",
+    "te_IN",
+    "th_TH",
+    "tl_XX",
+    "uk_UA",
+    "ur_PK",
+    "xh_ZA",
+    "gl_ES",
+    "sl_SI"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": "fr_XX",
+  "tgt_lang": "xh_ZA",
+  "tokenizer_class": "MBart50Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.980039920159681,
+  "eval_steps": 500,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.249500998003992,
+      "grad_norm": 2.452378511428833,
+      "learning_rate": 4.876746506986028e-05,
+      "loss": 2.1274,
+      "step": 500
+    },
+    {
+      "epoch": 0.499001996007984,
+      "grad_norm": 10.962518692016602,
+      "learning_rate": 4.751996007984032e-05,
+      "loss": 1.3207,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7485029940119761,
+      "grad_norm": 2.4429094791412354,
+      "learning_rate": 4.627245508982036e-05,
+      "loss": 1.138,
+      "step": 1500
+    },
+    {
+      "epoch": 0.998003992015968,
+      "grad_norm": 2.2755186557769775,
+      "learning_rate": 4.50249500998004e-05,
+      "loss": 1.0141,
+      "step": 2000
+    },
+    {
+      "epoch": 1.24750499001996,
+      "grad_norm": 1.8802367448806763,
+      "learning_rate": 4.377744510978044e-05,
+      "loss": 0.8877,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4970059880239521,
+      "grad_norm": 3.98767352104187,
+      "learning_rate": 4.252994011976048e-05,
+      "loss": 0.8705,
+      "step": 3000
+    },
+    {
+      "epoch": 1.746506986027944,
+      "grad_norm": 1.9973433017730713,
+      "learning_rate": 4.128243512974052e-05,
+      "loss": 0.826,
+      "step": 3500
+    },
+    {
+      "epoch": 1.996007984031936,
+      "grad_norm": 2.2026467323303223,
+      "learning_rate": 4.003493013972056e-05,
+      "loss": 0.8115,
+      "step": 4000
+    },
+    {
+      "epoch": 2.245508982035928,
+      "grad_norm": 2.212198257446289,
+      "learning_rate": 3.87874251497006e-05,
+      "loss": 0.6751,
+      "step": 4500
+    },
+    {
+      "epoch": 2.49500998003992,
+      "grad_norm": 1.5753542184829712,
+      "learning_rate": 3.754241516966068e-05,
+      "loss": 0.6747,
+      "step": 5000
+    },
+    {
+      "epoch": 2.744510978043912,
+      "grad_norm": 2.395479202270508,
+      "learning_rate": 3.629491017964072e-05,
+      "loss": 0.6646,
+      "step": 5500
+    },
+    {
+      "epoch": 2.9940119760479043,
+      "grad_norm": 2.577756643295288,
+      "learning_rate": 3.504740518962076e-05,
+      "loss": 0.66,
+      "step": 6000
+    },
+    {
+      "epoch": 3.243512974051896,
+      "grad_norm": 2.7224512100219727,
+      "learning_rate": 3.3799900199600795e-05,
+      "loss": 0.5135,
+      "step": 6500
+    },
+    {
+      "epoch": 3.493013972055888,
+      "grad_norm": 2.3300223350524902,
+      "learning_rate": 3.255239520958084e-05,
+      "loss": 0.5112,
+      "step": 7000
+    },
+    {
+      "epoch": 3.7425149700598803,
+      "grad_norm": 2.3015055656433105,
+      "learning_rate": 3.130489021956088e-05,
+      "loss": 0.5119,
+      "step": 7500
+    },
+    {
+      "epoch": 3.992015968063872,
+      "grad_norm": 2.4661030769348145,
+      "learning_rate": 3.0057385229540918e-05,
+      "loss": 0.5107,
+      "step": 8000
+    },
+    {
+      "epoch": 4.241516966067865,
+      "grad_norm": 2.5810928344726562,
+      "learning_rate": 2.880988023952096e-05,
+      "loss": 0.3741,
+      "step": 8500
+    },
+    {
+      "epoch": 4.491017964071856,
+      "grad_norm": 1.8933159112930298,
+      "learning_rate": 2.7562375249501e-05,
+      "loss": 0.3756,
+      "step": 9000
+    },
+    {
+      "epoch": 4.740518962075848,
+      "grad_norm": 2.711456775665283,
+      "learning_rate": 2.6314870259481038e-05,
+      "loss": 0.3745,
+      "step": 9500
+    },
+    {
+      "epoch": 4.99001996007984,
+      "grad_norm": 2.8451802730560303,
+      "learning_rate": 2.506736526946108e-05,
+      "loss": 0.3743,
+      "step": 10000
+    },
+    {
+      "epoch": 5.2395209580838324,
+      "grad_norm": 2.1212046146392822,
+      "learning_rate": 2.381986027944112e-05,
+      "loss": 0.2603,
+      "step": 10500
+    },
+    {
+      "epoch": 5.489021956087824,
+      "grad_norm": 2.1375863552093506,
+      "learning_rate": 2.257235528942116e-05,
+      "loss": 0.2567,
+      "step": 11000
+    },
+    {
+      "epoch": 5.738522954091817,
+      "grad_norm": 3.2050704956054688,
+      "learning_rate": 2.1324850299401196e-05,
+      "loss": 0.2596,
+      "step": 11500
+    },
+    {
+      "epoch": 5.9880239520958085,
+      "grad_norm": 1.9162492752075195,
+      "learning_rate": 2.007734530938124e-05,
+      "loss": 0.2692,
+      "step": 12000
+    },
+    {
+      "epoch": 6.2375249500998,
+      "grad_norm": 1.6697739362716675,
+      "learning_rate": 1.8829840319361277e-05,
+      "loss": 0.1711,
+      "step": 12500
+    },
+    {
+      "epoch": 6.487025948103792,
+      "grad_norm": 2.253767728805542,
+      "learning_rate": 1.758233532934132e-05,
+      "loss": 0.1705,
+      "step": 13000
+    },
+    {
+      "epoch": 6.736526946107785,
+      "grad_norm": 1.5864336490631104,
+      "learning_rate": 1.6337325349301397e-05,
+      "loss": 0.1735,
+      "step": 13500
+    },
+    {
+      "epoch": 6.986027944111776,
+      "grad_norm": 2.6011617183685303,
+      "learning_rate": 1.5089820359281437e-05,
+      "loss": 0.1785,
+      "step": 14000
+    },
+    {
+      "epoch": 7.235528942115769,
+      "grad_norm": 1.8357607126235962,
+      "learning_rate": 1.3842315369261476e-05,
+      "loss": 0.1101,
+      "step": 14500
+    },
+    {
+      "epoch": 7.485029940119761,
+      "grad_norm": 2.048788547515869,
+      "learning_rate": 1.2594810379241517e-05,
+      "loss": 0.1152,
+      "step": 15000
+    },
+    {
+      "epoch": 7.734530938123752,
+      "grad_norm": 2.7625575065612793,
+      "learning_rate": 1.1347305389221557e-05,
+      "loss": 0.1126,
+      "step": 15500
+    },
+    {
+      "epoch": 7.984031936127744,
+      "grad_norm": 2.9754233360290527,
+      "learning_rate": 1.0099800399201598e-05,
+      "loss": 0.1116,
+      "step": 16000
+    },
+    {
+      "epoch": 8.233532934131736,
+      "grad_norm": 2.279146909713745,
+      "learning_rate": 8.852295409181637e-06,
+      "loss": 0.0743,
+      "step": 16500
+    },
+    {
+      "epoch": 8.48303393213573,
+      "grad_norm": 2.4354634284973145,
+      "learning_rate": 7.604790419161677e-06,
+      "loss": 0.074,
+      "step": 17000
+    },
+    {
+      "epoch": 8.732534930139721,
+      "grad_norm": 2.9256038665771484,
+      "learning_rate": 6.357285429141717e-06,
+      "loss": 0.0722,
+      "step": 17500
+    },
+    {
+      "epoch": 8.982035928143713,
+      "grad_norm": 1.8734424114227295,
+      "learning_rate": 5.109780439121756e-06,
+      "loss": 0.0703,
+      "step": 18000
+    },
+    {
+      "epoch": 9.231536926147704,
+      "grad_norm": 2.1415419578552246,
+      "learning_rate": 3.862275449101797e-06,
+      "loss": 0.0503,
+      "step": 18500
+    },
+    {
+      "epoch": 9.481037924151696,
+      "grad_norm": 2.486562490463257,
+      "learning_rate": 2.6172654690618765e-06,
+      "loss": 0.0497,
+      "step": 19000
+    },
+    {
+      "epoch": 9.730538922155688,
+      "grad_norm": 1.6438294649124146,
+      "learning_rate": 1.3697604790419162e-06,
+      "loss": 0.0467,
+      "step": 19500
+    },
+    {
+      "epoch": 9.980039920159681,
+      "grad_norm": 2.3399159908294678,
+      "learning_rate": 1.222554890219561e-07,
+      "loss": 0.0457,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 20040,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.167129767936e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d042c9477f7b6640ea1b10bd8e98613e428dbf4d8529e16a0a9ebff454a8a876
+size 5432