Mix Trained marian model over 9 languages of ALT dataset + 18K senetences from en-zh opus dataset.

last-checkpoint/config.json

@@ -1,62 +0,0 @@
-{
-  "_name_or_path": "Helsinki-NLP/opus-mt-en-zh",
-  "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": [
-    [
-      65000
-    ]
-  ],
-  "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": 65000,
-  "do_blenderbot_90_layernorm": false,
-  "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": 0,
-  "force_bos_token_to_be_generated": false,
-  "forced_eos_token_id": 0,
-  "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": 512,
-  "max_position_embeddings": 512,
-  "model_type": "marian",
-  "normalize_before": false,
-  "normalize_embedding": false,
-  "num_beams": 4,
-  "num_hidden_layers": 6,
-  "pad_token_id": 65000,
-  "scale_embedding": true,
-  "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.15.0",
-  "use_cache": true,
-  "vocab_size": 101452
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7dd035e4b7f154ca67a5e827f94dde0c3943eda1b1eebec5f05e33e3d56ced39
-size 768802253

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:28f25c68a0cf29ea50176781ab7073cc5001efefecdff92973e4dbf5cb6efd80
-size 384827845

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7611315dfec0b436e47fb6dd6b2e81144c20633935e13fada627fe3665210c35
-size 14503

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5368f7f534ec825f60c19bab138293e63db2d680360440af385721e34463a6e8
-size 559

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aa541328a304ec574eb6085b477bec95c4e258191041c83a037f6e027f4fea37
-size 623

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer_config.json

@@ -1 +0,0 @@
-{"source_lang": "eng", "target_lang": "zho", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-en-zh", "tokenizer_class": "MarianTokenizer"}

last-checkpoint/trainer_state.json

@@ -1,136 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.7863522686673812,
-  "global_step": 10000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.09,
-      "learning_rate": 9.826661901358113e-05,
-      "loss": 2.8742,
-      "step": 500
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 9.647962830593282e-05,
-      "loss": 1.8355,
-      "step": 1000
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 9.46926375982845e-05,
-      "loss": 1.6456,
-      "step": 1500
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 9.290564689063618e-05,
-      "loss": 1.5151,
-      "step": 2000
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 9.111865618298785e-05,
-      "loss": 1.3961,
-      "step": 2500
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 8.933166547533954e-05,
-      "loss": 1.3182,
-      "step": 3000
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 8.754467476769121e-05,
-      "loss": 1.2625,
-      "step": 3500
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 8.575768406004289e-05,
-      "loss": 1.2033,
-      "step": 4000
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 8.397069335239457e-05,
-      "loss": 1.1532,
-      "step": 4500
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 8.218370264474626e-05,
-      "loss": 1.1099,
-      "step": 5000
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 8.039671193709793e-05,
-      "loss": 1.0695,
-      "step": 5500
-    },
-    {
-      "epoch": 1.07,
-      "learning_rate": 7.860972122944961e-05,
-      "loss": 1.0133,
-      "step": 6000
-    },
-    {
-      "epoch": 1.16,
-      "learning_rate": 7.682273052180129e-05,
-      "loss": 0.964,
-      "step": 6500
-    },
-    {
-      "epoch": 1.25,
-      "learning_rate": 7.503573981415298e-05,
-      "loss": 0.9535,
-      "step": 7000
-    },
-    {
-      "epoch": 1.34,
-      "learning_rate": 7.324874910650465e-05,
-      "loss": 0.9368,
-      "step": 7500
-    },
-    {
-      "epoch": 1.43,
-      "learning_rate": 7.146175839885633e-05,
-      "loss": 0.91,
-      "step": 8000
-    },
-    {
-      "epoch": 1.52,
-      "learning_rate": 6.9674767691208e-05,
-      "loss": 0.8902,
-      "step": 8500
-    },
-    {
-      "epoch": 1.61,
-      "learning_rate": 6.78877769835597e-05,
-      "loss": 0.8761,
-      "step": 9000
-    },
-    {
-      "epoch": 1.7,
-      "learning_rate": 6.610078627591136e-05,
-      "loss": 0.8699,
-      "step": 9500
-    },
-    {
-      "epoch": 1.79,
-      "learning_rate": 6.431379556826305e-05,
-      "loss": 0.8455,
-      "step": 10000
-    }
-  ],
-  "max_steps": 27990,
-  "num_train_epochs": 5,
-  "total_flos": 1.08466293178368e+16,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:782a61f9b4b81744b4a6cea3c7764006510c094d62fb54b163ccda9c79bc115f
-size 3119

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f25c68a0cf29ea50176781ab7073cc5001efefecdff92973e4dbf5cb6efd80
+oid sha256:416b4cf7935412622b6d7807238c1e1ad1095c667e1f009a54f178f46a2322f5
 size 384827845

runs/Jan13_15-44-20_ba04f2c84f0c/events.out.tfevents.1642088673.ba04f2c84f0c.73.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86607b8935f472edebf53b553cb1fb90af80f3d53f237d76126223f3f2ddfb20
-size 7345
+oid sha256:55645d79e2f12a144ecf5b939a3e695a01760b33d311fa4ad60e2e2d8fddc85d
+size 13646