Upload 12 files

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-gmq",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      54666
+    ]
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 54666,
+  "decoder_vocab_size": 54667,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 41839,
+  "forced_eos_token_id": 41839,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 512,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 54666,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 54667
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6ebd4e3834191476bbae5e6a657d36a1bf398a7bf5b1bba9c76dc041d058aa
+size 1858837965

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780645fbf064497871dfc436d34b257f6702407dc4fc87e615c4788ed76d0407
+size 929648645

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b440875e92c8701b0244b8f1defaf4a55f39130272d2d8182a45c2bf736e14
+size 14439

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77a8263d2c9ab2d2fd99749ca0bd684b2d23ea39ae6b5deffc35ec07d427d80
+size 623

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-gmq",
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "gmq",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu": 58.9649,
+      "eval_gen_len": 19.44,
+      "eval_loss": 0.6476399302482605,
+      "eval_runtime": 7.9533,
+      "eval_samples_per_second": 12.573,
+      "eval_steps_per_second": 6.287,
+      "step": 400
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.6755,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 59.7239,
+      "eval_gen_len": 19.21,
+      "eval_loss": 0.6683109998703003,
+      "eval_runtime": 7.5813,
+      "eval_samples_per_second": 13.19,
+      "eval_steps_per_second": 6.595,
+      "step": 800
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.2568,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 59.3781,
+      "eval_gen_len": 19.22,
+      "eval_loss": 0.7284716963768005,
+      "eval_runtime": 7.5691,
+      "eval_samples_per_second": 13.212,
+      "eval_steps_per_second": 6.606,
+      "step": 1200
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.25e-05,
+      "loss": 0.1116,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 60.1615,
+      "eval_gen_len": 19.14,
+      "eval_loss": 0.8120526075363159,
+      "eval_runtime": 7.4229,
+      "eval_samples_per_second": 13.472,
+      "eval_steps_per_second": 6.736,
+      "step": 1600
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1e-05,
+      "loss": 0.048,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 58.8865,
+      "eval_gen_len": 19.34,
+      "eval_loss": 0.8653954267501831,
+      "eval_runtime": 8.7147,
+      "eval_samples_per_second": 11.475,
+      "eval_steps_per_second": 5.737,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 58.2232,
+      "eval_gen_len": 19.07,
+      "eval_loss": 0.8903241157531738,
+      "eval_runtime": 8.0705,
+      "eval_samples_per_second": 12.391,
+      "eval_steps_per_second": 6.195,
+      "step": 2400
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.0178,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 58.0224,
+      "eval_gen_len": 19.22,
+      "eval_loss": 0.9194047451019287,
+      "eval_runtime": 8.0477,
+      "eval_samples_per_second": 12.426,
+      "eval_steps_per_second": 6.213,
+      "step": 2800
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 5e-06,
+      "loss": 0.0087,
+      "step": 3000
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu": 58.8822,
+      "eval_gen_len": 19.29,
+      "eval_loss": 0.930671751499176,
+      "eval_runtime": 7.9933,
+      "eval_samples_per_second": 12.51,
+      "eval_steps_per_second": 6.255,
+      "step": 3200
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0039,
+      "step": 3500
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu": 59.1049,
+      "eval_gen_len": 19.18,
+      "eval_loss": 0.9447950124740601,
+      "eval_runtime": 7.8845,
+      "eval_samples_per_second": 12.683,
+      "eval_steps_per_second": 6.342,
+      "step": 3600
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.0027,
+      "step": 4000
+    }
+  ],
+  "max_steps": 4000,
+  "num_train_epochs": 10,
+  "total_flos": 199212586500096.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c339b48e431102c24b1b77c27ac88c9ccab9d3f286d0e028efdd6f0d754a8eb
+size 3567