Upload 13 files

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "/home/remote/dev/llm/Helsinki-NLP/opus-mt-mul-en-word-fine-tune-en-to-pt-1k/checkpoint-3000",
+  "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": [
+    [
+      64171
+    ]
+  ],
+  "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": 64171,
+  "decoder_vocab_size": 64172,
+  "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": 64172,
+  "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": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 64171,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 64172
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      64171
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 64171,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 64171,
+  "renormalize_logits": true,
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ed2e328c096ec3b1f47f79fef0466997e39effe33289490071f4b73b556219
+size 308263984

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa3fc6b0dd6023abcc258f854abeafa95c16a90982b8d810d5d987b586a4cbb
+size 616168058

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7935cbb9bea3460378dd8c4b97fc0d20141a7f1c1b714ff807c02613fca8d0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3773a90387bd38a747c1064d5d58598d64de07296ece860fcc65d3bafb34ff4f
+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 +1,39 @@
+{
+  "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
+    },
+    "64171": {
+      "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>",
+  "return_tensors": "pt",
+  "separate_vocabs": false,
+  "source_lang": "mul",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 105.0,
+  "eval_steps": 500,
+  "global_step": 16485,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.1847133757961785,
+      "grad_norm": 1.833742380142212,
+      "learning_rate": 1.9872611464968155e-05,
+      "loss": 0.3724,
+      "step": 500
+    },
+    {
+      "epoch": 6.369426751592357,
+      "grad_norm": 1.515284538269043,
+      "learning_rate": 1.9745222929936306e-05,
+      "loss": 0.0612,
+      "step": 1000
+    },
+    {
+      "epoch": 9.554140127388536,
+      "grad_norm": 1.5868924856185913,
+      "learning_rate": 1.961783439490446e-05,
+      "loss": 0.0493,
+      "step": 1500
+    },
+    {
+      "epoch": 12.738853503184714,
+      "grad_norm": 1.5748449563980103,
+      "learning_rate": 1.9490445859872614e-05,
+      "loss": 0.0446,
+      "step": 2000
+    },
+    {
+      "epoch": 15.923566878980893,
+      "grad_norm": 1.6215589046478271,
+      "learning_rate": 1.9363057324840767e-05,
+      "loss": 0.0405,
+      "step": 2500
+    },
+    {
+      "epoch": 19.10828025477707,
+      "grad_norm": 1.1221493482589722,
+      "learning_rate": 1.9235668789808918e-05,
+      "loss": 0.0366,
+      "step": 3000
+    },
+    {
+      "epoch": 22.29299363057325,
+      "grad_norm": 1.6376855373382568,
+      "learning_rate": 1.910828025477707e-05,
+      "loss": 0.0331,
+      "step": 3500
+    },
+    {
+      "epoch": 25.477707006369428,
+      "grad_norm": 1.000545859336853,
+      "learning_rate": 1.8980891719745225e-05,
+      "loss": 0.0293,
+      "step": 4000
+    },
+    {
+      "epoch": 28.662420382165607,
+      "grad_norm": 0.6820641756057739,
+      "learning_rate": 1.8853503184713376e-05,
+      "loss": 0.0256,
+      "step": 4500
+    },
+    {
+      "epoch": 31.847133757961785,
+      "grad_norm": 1.1707481145858765,
+      "learning_rate": 1.872611464968153e-05,
+      "loss": 0.0221,
+      "step": 5000
+    },
+    {
+      "epoch": 35.031847133757964,
+      "grad_norm": 1.4677773714065552,
+      "learning_rate": 1.8598726114649684e-05,
+      "loss": 0.0185,
+      "step": 5500
+    },
+    {
+      "epoch": 38.21656050955414,
+      "grad_norm": 1.6114100217819214,
+      "learning_rate": 1.8471337579617837e-05,
+      "loss": 0.0157,
+      "step": 6000
+    },
+    {
+      "epoch": 41.40127388535032,
+      "grad_norm": 1.0237997770309448,
+      "learning_rate": 1.8343949044585988e-05,
+      "loss": 0.013,
+      "step": 6500
+    },
+    {
+      "epoch": 44.5859872611465,
+      "grad_norm": 0.8055925965309143,
+      "learning_rate": 1.821656050955414e-05,
+      "loss": 0.0112,
+      "step": 7000
+    },
+    {
+      "epoch": 47.77070063694268,
+      "grad_norm": 0.8719159364700317,
+      "learning_rate": 1.8089171974522295e-05,
+      "loss": 0.0095,
+      "step": 7500
+    },
+    {
+      "epoch": 50.955414012738856,
+      "grad_norm": 1.6024932861328125,
+      "learning_rate": 1.796178343949045e-05,
+      "loss": 0.0083,
+      "step": 8000
+    },
+    {
+      "epoch": 54.140127388535035,
+      "grad_norm": 0.6275691986083984,
+      "learning_rate": 1.78343949044586e-05,
+      "loss": 0.0076,
+      "step": 8500
+    },
+    {
+      "epoch": 57.32484076433121,
+      "grad_norm": 0.7005597949028015,
+      "learning_rate": 1.7707006369426754e-05,
+      "loss": 0.0065,
+      "step": 9000
+    },
+    {
+      "epoch": 60.50955414012739,
+      "grad_norm": 0.30579155683517456,
+      "learning_rate": 1.7579617834394907e-05,
+      "loss": 0.0063,
+      "step": 9500
+    },
+    {
+      "epoch": 63.69426751592356,
+      "grad_norm": 0.4344225227832794,
+      "learning_rate": 1.7452229299363058e-05,
+      "loss": 0.0059,
+      "step": 10000
+    },
+    {
+      "epoch": 66.87898089171975,
+      "grad_norm": 1.7709016799926758,
+      "learning_rate": 1.732484076433121e-05,
+      "loss": 0.0053,
+      "step": 10500
+    },
+    {
+      "epoch": 70.06369426751593,
+      "grad_norm": 0.622224748134613,
+      "learning_rate": 1.7197452229299365e-05,
+      "loss": 0.005,
+      "step": 11000
+    },
+    {
+      "epoch": 73.2484076433121,
+      "grad_norm": 0.564902126789093,
+      "learning_rate": 1.707006369426752e-05,
+      "loss": 0.0049,
+      "step": 11500
+    },
+    {
+      "epoch": 76.43312101910828,
+      "grad_norm": 0.5126436352729797,
+      "learning_rate": 1.694267515923567e-05,
+      "loss": 0.0045,
+      "step": 12000
+    },
+    {
+      "epoch": 79.61783439490446,
+      "grad_norm": 1.7633012533187866,
+      "learning_rate": 1.6815286624203824e-05,
+      "loss": 0.0041,
+      "step": 12500
+    },
+    {
+      "epoch": 82.80254777070064,
+      "grad_norm": 0.7407333850860596,
+      "learning_rate": 1.6687898089171977e-05,
+      "loss": 0.004,
+      "step": 13000
+    },
+    {
+      "epoch": 85.98726114649682,
+      "grad_norm": 0.5011927485466003,
+      "learning_rate": 1.6560509554140128e-05,
+      "loss": 0.0043,
+      "step": 13500
+    },
+    {
+      "epoch": 89.171974522293,
+      "grad_norm": 0.5946338176727295,
+      "learning_rate": 1.643312101910828e-05,
+      "loss": 0.0039,
+      "step": 14000
+    },
+    {
+      "epoch": 92.35668789808918,
+      "grad_norm": 0.3282039761543274,
+      "learning_rate": 1.6305732484076436e-05,
+      "loss": 0.0035,
+      "step": 14500
+    },
+    {
+      "epoch": 95.54140127388536,
+      "grad_norm": 0.0594528391957283,
+      "learning_rate": 1.617834394904459e-05,
+      "loss": 0.0037,
+      "step": 15000
+    },
+    {
+      "epoch": 98.72611464968153,
+      "grad_norm": 0.032949354499578476,
+      "learning_rate": 1.605095541401274e-05,
+      "loss": 0.0034,
+      "step": 15500
+    },
+    {
+      "epoch": 101.91082802547771,
+      "grad_norm": 1.0133298635482788,
+      "learning_rate": 1.5923566878980894e-05,
+      "loss": 0.0035,
+      "step": 16000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 78500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 500,
+  "save_steps": 500,
+  "total_flos": 2594375342751744.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66a168af0b8d4f85fcd5fd68d6ebbe38351e1d4f9788945f2a758af99c2097c
+size 5368