stage base adaptified ailem model

checkpoint-48000/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
+}

checkpoint-48000/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"
+}

checkpoint-48000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcd487fe77bfb86ac11f3cb79028f7bb3bd07421125e8628c688c500e19120d
+size 597025797

checkpoint-48000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0774ab9476872adac62a2bdc9ae11a4ed42b28f1e5d93d8fb857405c3a50e3
+size 298763205

checkpoint-48000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4986fff843eda4aaf8cdc5c0480025f3e4323b4384b9452dbb1812beea25ba89
+size 14575

checkpoint-48000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d258312d6dfd03c91b297fac5f9df7c8938b783fe1a9b2ce2bb06e6b5ea9b3
+size 557

checkpoint-48000/scheduler.pt

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

checkpoint-48000/special_tokens_map.json

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

checkpoint-48000/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>"
+}

checkpoint-48000/trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": 42.5638,
+  "best_model_checkpoint": "opus_base_ailem_adaptified/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": 0.2032,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "eval_bleu": 35.1474,
+      "eval_gen_len": 40.395,
+      "eval_loss": 0.10896337777376175,
+      "eval_runtime": 179.3655,
+      "eval_samples_per_second": 5.815,
+      "eval_steps_per_second": 0.184,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.950746746845426e-05,
+      "loss": 0.1702,
+      "step": 8000
+    },
+    {
+      "epoch": 0.39,
+      "eval_bleu": 41.0648,
+      "eval_gen_len": 34.5983,
+      "eval_loss": 0.10649073868989944,
+      "eval_runtime": 166.3848,
+      "eval_samples_per_second": 6.269,
+      "eval_steps_per_second": 0.198,
+      "step": 8000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9261016364353314e-05,
+      "loss": 0.1634,
+      "step": 12000
+    },
+    {
+      "epoch": 0.59,
+      "eval_bleu": 41.4064,
+      "eval_gen_len": 34.4353,
+      "eval_loss": 0.10525061935186386,
+      "eval_runtime": 157.1928,
+      "eval_samples_per_second": 6.635,
+      "eval_steps_per_second": 0.21,
+      "step": 12000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.9014565260252367e-05,
+      "loss": 0.1581,
+      "step": 16000
+    },
+    {
+      "epoch": 0.79,
+      "eval_bleu": 40.6981,
+      "eval_gen_len": 36.0038,
+      "eval_loss": 0.10416892915964127,
+      "eval_runtime": 135.6043,
+      "eval_samples_per_second": 7.691,
+      "eval_steps_per_second": 0.243,
+      "step": 16000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.876811415615142e-05,
+      "loss": 0.1558,
+      "step": 20000
+    },
+    {
+      "epoch": 0.99,
+      "eval_bleu": 41.7673,
+      "eval_gen_len": 35.4631,
+      "eval_loss": 0.10361550748348236,
+      "eval_runtime": 156.992,
+      "eval_samples_per_second": 6.644,
+      "eval_steps_per_second": 0.21,
+      "step": 20000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.8521786277602524e-05,
+      "loss": 0.1444,
+      "step": 24000
+    },
+    {
+      "epoch": 1.18,
+      "eval_bleu": 41.5766,
+      "eval_gen_len": 35.7536,
+      "eval_loss": 0.10351266711950302,
+      "eval_runtime": 148.1282,
+      "eval_samples_per_second": 7.041,
+      "eval_steps_per_second": 0.223,
+      "step": 24000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.827545839905363e-05,
+      "loss": 0.1442,
+      "step": 28000
+    },
+    {
+      "epoch": 1.38,
+      "eval_bleu": 41.2765,
+      "eval_gen_len": 35.535,
+      "eval_loss": 0.10269948095083237,
+      "eval_runtime": 139.1706,
+      "eval_samples_per_second": 7.494,
+      "eval_steps_per_second": 0.237,
+      "step": 28000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.8029130520504733e-05,
+      "loss": 0.1438,
+      "step": 32000
+    },
+    {
+      "epoch": 1.58,
+      "eval_bleu": 42.0634,
+      "eval_gen_len": 34.8495,
+      "eval_loss": 0.10216742753982544,
+      "eval_runtime": 138.1687,
+      "eval_samples_per_second": 7.549,
+      "eval_steps_per_second": 0.239,
+      "step": 32000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.7782802641955836e-05,
+      "loss": 0.1424,
+      "step": 36000
+    },
+    {
+      "epoch": 1.77,
+      "eval_bleu": 41.2763,
+      "eval_gen_len": 36.139,
+      "eval_loss": 0.10178232192993164,
+      "eval_runtime": 118.4305,
+      "eval_samples_per_second": 8.807,
+      "eval_steps_per_second": 0.279,
+      "step": 36000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.7536474763406942e-05,
+      "loss": 0.1416,
+      "step": 40000
+    },
+    {
+      "epoch": 1.97,
+      "eval_bleu": 42.3991,
+      "eval_gen_len": 34.4545,
+      "eval_loss": 0.10192298889160156,
+      "eval_runtime": 120.2656,
+      "eval_samples_per_second": 8.672,
+      "eval_steps_per_second": 0.274,
+      "step": 40000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.729008527208202e-05,
+      "loss": 0.1342,
+      "step": 44000
+    },
+    {
+      "epoch": 2.17,
+      "eval_bleu": 42.1688,
+      "eval_gen_len": 35.3145,
+      "eval_loss": 0.1022704690694809,
+      "eval_runtime": 137.0088,
+      "eval_samples_per_second": 7.613,
+      "eval_steps_per_second": 0.241,
+      "step": 44000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.70436957807571e-05,
+      "loss": 0.1334,
+      "step": 48000
+    },
+    {
+      "epoch": 2.37,
+      "eval_bleu": 42.5638,
+      "eval_gen_len": 35.0738,
+      "eval_loss": 0.10206188261508942,
+      "eval_runtime": 129.6219,
+      "eval_samples_per_second": 8.046,
+      "eval_steps_per_second": 0.255,
+      "step": 48000
+    }
+  ],
+  "max_steps": 324608,
+  "num_train_epochs": 16,
+  "total_flos": 8.279444701052928e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-48000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb79d8b854e02ccc5795cd91b8ba49e36367cb01aa95d1a05db465648548b6b
+size 3771

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"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0774ab9476872adac62a2bdc9ae11a4ed42b28f1e5d93d8fb857405c3a50e3
+size 298763205

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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb79d8b854e02ccc5795cd91b8ba49e36367cb01aa95d1a05db465648548b6b
+size 3771