stage best unsampled glossary simple adapt wce model

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
+  "_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": [
+    [
+      59513
+    ]
+  ],
+  "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": 59513,
+  "decoder_vocab_size": 59514,
+  "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,
+  "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": 59513,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 59514
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59513,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "transformers_version": "4.28.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7583b7db5b4887a66069b42fed890ab821a6fad290c0867c594216272c4a38
+size 597025797

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a106aecb172314e4da477653d9f28fd25dbdc55afa70e6cfeb27dc2c9ac079f
+size 298763205

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b67c244ae8d26d3b517afc41b769f6c1da70c8a4f20993d632bee5096c6c8b43
+size 14511

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9055f98a716635000cf1d7e829c9d11567d7385418e97f472b060f198d8cd5ef
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b7a114098847320a6017e1b247a9a2d2bd21ad9141534f49790c7a0e83f544
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "fr",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": 42.7412,
+  "best_model_checkpoint": "opus_base_adapt_wce_gloss_unsampled_bands_7_ubweight_1.5/checkpoint-48000",
+  "epoch": 2.365930599369085,
+  "global_step": 48000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9753918572555207e-05,
+      "loss": 0.2075,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "eval_bleu": 35.693,
+      "eval_gen_len": 39.837,
+      "eval_loss": 0.10906277596950531,
+      "eval_runtime": 203.6881,
+      "eval_samples_per_second": 5.121,
+      "eval_steps_per_second": 0.162,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.950746746845426e-05,
+      "loss": 0.1742,
+      "step": 8000
+    },
+    {
+      "epoch": 0.39,
+      "eval_bleu": 37.6497,
+      "eval_gen_len": 37.93,
+      "eval_loss": 0.10657652467489243,
+      "eval_runtime": 221.5331,
+      "eval_samples_per_second": 4.708,
+      "eval_steps_per_second": 0.149,
+      "step": 8000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9261016364353314e-05,
+      "loss": 0.1672,
+      "step": 12000
+    },
+    {
+      "epoch": 0.59,
+      "eval_bleu": 41.3565,
+      "eval_gen_len": 34.6529,
+      "eval_loss": 0.10534726828336716,
+      "eval_runtime": 168.8583,
+      "eval_samples_per_second": 6.177,
+      "eval_steps_per_second": 0.195,
+      "step": 12000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.9014565260252367e-05,
+      "loss": 0.1617,
+      "step": 16000
+    },
+    {
+      "epoch": 0.79,
+      "eval_bleu": 41.4881,
+      "eval_gen_len": 35.4343,
+      "eval_loss": 0.10427802801132202,
+      "eval_runtime": 136.9034,
+      "eval_samples_per_second": 7.619,
+      "eval_steps_per_second": 0.241,
+      "step": 16000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.876811415615142e-05,
+      "loss": 0.1593,
+      "step": 20000
+    },
+    {
+      "epoch": 0.99,
+      "eval_bleu": 41.6185,
+      "eval_gen_len": 35.9434,
+      "eval_loss": 0.10372872650623322,
+      "eval_runtime": 158.7854,
+      "eval_samples_per_second": 6.569,
+      "eval_steps_per_second": 0.208,
+      "step": 20000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.8521786277602524e-05,
+      "loss": 0.1475,
+      "step": 24000
+    },
+    {
+      "epoch": 1.18,
+      "eval_bleu": 41.9106,
+      "eval_gen_len": 35.1831,
+      "eval_loss": 0.10363597422838211,
+      "eval_runtime": 127.398,
+      "eval_samples_per_second": 8.187,
+      "eval_steps_per_second": 0.259,
+      "step": 24000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.8275520011829655e-05,
+      "loss": 0.1473,
+      "step": 28000
+    },
+    {
+      "epoch": 1.38,
+      "eval_bleu": 41.0151,
+      "eval_gen_len": 36.2119,
+      "eval_loss": 0.10283295065164566,
+      "eval_runtime": 132.5317,
+      "eval_samples_per_second": 7.87,
+      "eval_steps_per_second": 0.249,
+      "step": 28000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.8029130520504733e-05,
+      "loss": 0.1469,
+      "step": 32000
+    },
+    {
+      "epoch": 1.58,
+      "eval_bleu": 42.0417,
+      "eval_gen_len": 34.9779,
+      "eval_loss": 0.1022760346531868,
+      "eval_runtime": 134.6277,
+      "eval_samples_per_second": 7.747,
+      "eval_steps_per_second": 0.245,
+      "step": 32000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.7782741029179815e-05,
+      "loss": 0.1455,
+      "step": 36000
+    },
+    {
+      "epoch": 1.77,
+      "eval_bleu": 40.3879,
+      "eval_gen_len": 37.6788,
+      "eval_loss": 0.10188300907611847,
+      "eval_runtime": 124.1502,
+      "eval_samples_per_second": 8.401,
+      "eval_steps_per_second": 0.266,
+      "step": 36000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.7536413150630914e-05,
+      "loss": 0.1447,
+      "step": 40000
+    },
+    {
+      "epoch": 1.97,
+      "eval_bleu": 41.9744,
+      "eval_gen_len": 35.4314,
+      "eval_loss": 0.10198679566383362,
+      "eval_runtime": 133.2603,
+      "eval_samples_per_second": 7.827,
+      "eval_steps_per_second": 0.248,
+      "step": 40000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.729008527208202e-05,
+      "loss": 0.1371,
+      "step": 44000
+    },
+    {
+      "epoch": 2.17,
+      "eval_bleu": 42.1364,
+      "eval_gen_len": 34.9569,
+      "eval_loss": 0.10233627259731293,
+      "eval_runtime": 158.4624,
+      "eval_samples_per_second": 6.582,
+      "eval_steps_per_second": 0.208,
+      "step": 44000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.70436957807571e-05,
+      "loss": 0.1362,
+      "step": 48000
+    },
+    {
+      "epoch": 2.37,
+      "eval_bleu": 42.7412,
+      "eval_gen_len": 34.8322,
+      "eval_loss": 0.10221327096223831,
+      "eval_runtime": 107.2167,
+      "eval_samples_per_second": 9.728,
+      "eval_steps_per_second": 0.308,
+      "step": 48000
+    }
+  ],
+  "max_steps": 324608,
+  "num_train_epochs": 16,
+  "total_flos": 8.279444701052928e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1f93c831f987cfa33708fb3f580b30c722ec68916af1775bcb0dff1d2f0af4
+size 3835