Upload initial model

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "opus-mt-fi-fi-finetuned-fi-to-rg/checkpoint-9000",
+  "_num_labels": 3,
+  "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": [
+    [
+      33006
+    ]
+  ],
+  "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": 33006,
+  "decoder_vocab_size": 33007,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "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": 33006,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 33007
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      33006
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 33006,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 33006,
+  "renormalize_logits": true,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70407919dbf934382deb1d0c6c1421f28f67d71b87290138b35d2cbcc60d6c42
+size 244313404

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:babcedfaa308860d141e6ec8d931022f8dbc63340ef0b36949d40e0223f3ea6e
+size 488516218

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b651ed337497ccc790f6c9d45dd8062f79869dd55c27d7638335585f82290f7d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f172f931dd0e5c99920641ee2eafa5e22c4ab913eb4a09480a80cecf7634db
+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 +1,38 @@
+{
+  "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
+    },
+    "33006": {
+      "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": "fi",
+  "sp_model_kwargs": {},
+  "target_lang": "fi",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.911894273127754,
+  "eval_steps": 500,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.7246696035242295e-05,
+      "loss": 2.9573,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 17.2961,
+      "eval_gen_len": 53.6889,
+      "eval_loss": 2.6540744304656982,
+      "eval_runtime": 49.9025,
+      "eval_samples_per_second": 4.509,
+      "eval_steps_per_second": 0.581,
+      "step": 908
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.449339207048459e-05,
+      "loss": 2.927,
+      "step": 1000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.1740088105726874e-05,
+      "loss": 2.7809,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 19.3527,
+      "eval_gen_len": 42.6667,
+      "eval_loss": 2.5852272510528564,
+      "eval_runtime": 37.69,
+      "eval_samples_per_second": 5.97,
+      "eval_steps_per_second": 0.769,
+      "step": 1816
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.898678414096916e-05,
+      "loss": 2.7165,
+      "step": 2000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.623348017621145e-05,
+      "loss": 2.6527,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 18.53,
+      "eval_gen_len": 44.8044,
+      "eval_loss": 2.521505355834961,
+      "eval_runtime": 44.997,
+      "eval_samples_per_second": 5.0,
+      "eval_steps_per_second": 0.644,
+      "step": 2724
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.3480176211453745e-05,
+      "loss": 2.5517,
+      "step": 3000
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 3.072687224669604e-05,
+      "loss": 2.5069,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 21.0151,
+      "eval_gen_len": 39.6889,
+      "eval_loss": 2.480680227279663,
+      "eval_runtime": 35.165,
+      "eval_samples_per_second": 6.398,
+      "eval_steps_per_second": 0.825,
+      "step": 3632
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 2.7973568281938327e-05,
+      "loss": 2.4257,
+      "step": 4000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 2.522026431718062e-05,
+      "loss": 2.3976,
+      "step": 4500
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 21.4466,
+      "eval_gen_len": 39.8667,
+      "eval_loss": 2.4499943256378174,
+      "eval_runtime": 31.2343,
+      "eval_samples_per_second": 7.204,
+      "eval_steps_per_second": 0.928,
+      "step": 4540
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 2.246696035242291e-05,
+      "loss": 2.3175,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 20.5303,
+      "eval_gen_len": 42.0044,
+      "eval_loss": 2.4212148189544678,
+      "eval_runtime": 35.5561,
+      "eval_samples_per_second": 6.328,
+      "eval_steps_per_second": 0.816,
+      "step": 5448
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 1.97136563876652e-05,
+      "loss": 2.3049,
+      "step": 5500
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 1.696035242290749e-05,
+      "loss": 2.2268,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 20.9986,
+      "eval_gen_len": 42.8578,
+      "eval_loss": 2.4010252952575684,
+      "eval_runtime": 35.0954,
+      "eval_samples_per_second": 6.411,
+      "eval_steps_per_second": 0.826,
+      "step": 6356
+    },
+    {
+      "epoch": 7.16,
+      "learning_rate": 1.420704845814978e-05,
+      "loss": 2.2282,
+      "step": 6500
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 1.1453744493392071e-05,
+      "loss": 2.1703,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu": 22.8201,
+      "eval_gen_len": 36.8267,
+      "eval_loss": 2.3867766857147217,
+      "eval_runtime": 23.8243,
+      "eval_samples_per_second": 9.444,
+      "eval_steps_per_second": 1.217,
+      "step": 7264
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 8.700440528634362e-06,
+      "loss": 2.1589,
+      "step": 7500
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 5.947136563876652e-06,
+      "loss": 2.1223,
+      "step": 8000
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu": 22.9591,
+      "eval_gen_len": 37.3422,
+      "eval_loss": 2.3790900707244873,
+      "eval_runtime": 28.3931,
+      "eval_samples_per_second": 7.924,
+      "eval_steps_per_second": 1.021,
+      "step": 8172
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 3.193832599118943e-06,
+      "loss": 2.0995,
+      "step": 8500
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 4.4052863436123357e-07,
+      "loss": 2.1029,
+      "step": 9000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9080,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2122263810146304.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac49814691ca1f48770eb6a35c6117165ddb6d2fb57f0f26e611d5cdd1837e5
+size 4728