Upload folder using huggingface_hub

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "/home/jupyter/src/en-to-lg/checkpoint-160/",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      64109
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 64109,
+  "decoder_vocab_size": 64110,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 64110,
+  "forced_eos_token_id": 0,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 64109,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 64110
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bad_words_ids": [
+    [
+      64109
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 64109,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 64109,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3db348ab863eb89642f354c5634023bc9b1fa29e55c7227ff317de1cdb47c99
+size 308136760

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57a716ef23a9b612610cdecf524815626ba5d82fd7d5bd2c0da50655df8a124
+size 615914106

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef2636bebde089f4f343f264b26b7356d0e27b1c8b1d1e34b12c70381a25b4f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc10121628abb0b56ef05082fb3fb477990eee89139a5e4ec6401699f3f56ffb
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64109": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "src_lang": "eng_Latn",
+  "target_lang": "mul",
+  "tgt_lang": "lug_Latn",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 3.8955132961273193,
+  "best_model_checkpoint": "en-to-lg-nllb/checkpoint-126",
+  "epoch": 4.984126984126984,
+  "eval_steps": 50,
+  "global_step": 157,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9841269841269841,
+      "eval_bleu": 4.9826,
+      "eval_gen_len": 21.0615,
+      "eval_loss": 4.006349086761475,
+      "eval_runtime": 25808.7824,
+      "eval_samples_per_second": 13.795,
+      "eval_steps_per_second": 0.862,
+      "step": 31
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 5.1662,
+      "eval_gen_len": 21.0337,
+      "eval_loss": 3.9251999855041504,
+      "eval_runtime": 24598.2105,
+      "eval_samples_per_second": 14.474,
+      "eval_steps_per_second": 0.905,
+      "step": 63
+    },
+    {
+      "epoch": 2.984126984126984,
+      "eval_bleu": 5.1982,
+      "eval_gen_len": 21.0079,
+      "eval_loss": 3.9015612602233887,
+      "eval_runtime": 24397.4743,
+      "eval_samples_per_second": 14.594,
+      "eval_steps_per_second": 0.912,
+      "step": 94
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 5.1957,
+      "eval_gen_len": 21.1682,
+      "eval_loss": 3.8955132961273193,
+      "eval_runtime": 24834.7491,
+      "eval_samples_per_second": 14.337,
+      "eval_steps_per_second": 0.896,
+      "step": 126
+    },
+    {
+      "epoch": 4.984126984126984,
+      "eval_bleu": 5.2696,
+      "eval_gen_len": 20.8579,
+      "eval_loss": 3.8994901180267334,
+      "eval_runtime": 24130.7665,
+      "eval_samples_per_second": 14.755,
+      "eval_steps_per_second": 0.922,
+      "step": 157
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 42631431192576.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3e8ed6d515ab0dd0706dbdef16311b1a9deb0c9391a5d486355035a5ef5af9
+size 5240