stage base random ailem model

checkpoint-68000/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-68000/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-68000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2a810643cf0118821efd07e1221be8526cf4390e6ea15b90d52c8ca894644c
+size 597026309

checkpoint-68000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f89c9afa6c252900d404faf8dadcf9f2a2bba055b781dc7c4c97d2d6d21d1d
+size 298763205

checkpoint-68000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c670cab0b00234673ce5bff937c55bc2cea070210b1fb610c32f32418d26674
+size 14575

checkpoint-68000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7633ae87a15eb29240511d516e90e527955f8fe1adead90b50ff6dbeaa731880
+size 557

checkpoint-68000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a95090ee5e2e6e41e5a2b071c298dcb4087c3a6e08567f6fbbe15bb0eb0e1b8
+size 627

checkpoint-68000/special_tokens_map.json

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

checkpoint-68000/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-68000/trainer_state.json

@@ -0,0 +1,288 @@
+{
+  "best_metric": 42.5239,
+  "best_model_checkpoint": "opus_base_ailem_random/checkpoint-68000",
+  "epoch": 3.3517350157728707,
+  "global_step": 68000,
+  "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": 0.209,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "eval_bleu": 35.7559,
+      "eval_gen_len": 39.7057,
+      "eval_loss": 0.10894892364740372,
+      "eval_runtime": 186.2305,
+      "eval_samples_per_second": 5.601,
+      "eval_steps_per_second": 0.177,
+      "step": 4000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.950746746845426e-05,
+      "loss": 0.1757,
+      "step": 8000
+    },
+    {
+      "epoch": 0.39,
+      "eval_bleu": 36.6369,
+      "eval_gen_len": 39.395,
+      "eval_loss": 0.10665024816989899,
+      "eval_runtime": 150.2548,
+      "eval_samples_per_second": 6.942,
+      "eval_steps_per_second": 0.22,
+      "step": 8000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9261016364353314e-05,
+      "loss": 0.1686,
+      "step": 12000
+    },
+    {
+      "epoch": 0.59,
+      "eval_bleu": 41.2508,
+      "eval_gen_len": 35.1687,
+      "eval_loss": 0.10527685284614563,
+      "eval_runtime": 140.4867,
+      "eval_samples_per_second": 7.424,
+      "eval_steps_per_second": 0.235,
+      "step": 12000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.9014565260252367e-05,
+      "loss": 0.1631,
+      "step": 16000
+    },
+    {
+      "epoch": 0.79,
+      "eval_bleu": 41.4292,
+      "eval_gen_len": 35.1361,
+      "eval_loss": 0.104288749396801,
+      "eval_runtime": 117.5095,
+      "eval_samples_per_second": 8.876,
+      "eval_steps_per_second": 0.281,
+      "step": 16000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.876811415615142e-05,
+      "loss": 0.1608,
+      "step": 20000
+    },
+    {
+      "epoch": 0.99,
+      "eval_bleu": 41.7716,
+      "eval_gen_len": 35.5177,
+      "eval_loss": 0.10370208323001862,
+      "eval_runtime": 146.3536,
+      "eval_samples_per_second": 7.127,
+      "eval_steps_per_second": 0.225,
+      "step": 20000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.8521786277602524e-05,
+      "loss": 0.149,
+      "step": 24000
+    },
+    {
+      "epoch": 1.18,
+      "eval_bleu": 40.6317,
+      "eval_gen_len": 36.8993,
+      "eval_loss": 0.10362833738327026,
+      "eval_runtime": 131.4065,
+      "eval_samples_per_second": 7.937,
+      "eval_steps_per_second": 0.251,
+      "step": 24000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.827545839905363e-05,
+      "loss": 0.1488,
+      "step": 28000
+    },
+    {
+      "epoch": 1.38,
+      "eval_bleu": 41.8852,
+      "eval_gen_len": 35.3174,
+      "eval_loss": 0.10282401740550995,
+      "eval_runtime": 124.1856,
+      "eval_samples_per_second": 8.399,
+      "eval_steps_per_second": 0.266,
+      "step": 28000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.8029130520504733e-05,
+      "loss": 0.1484,
+      "step": 32000
+    },
+    {
+      "epoch": 1.58,
+      "eval_bleu": 41.5392,
+      "eval_gen_len": 35.9501,
+      "eval_loss": 0.10223321616649628,
+      "eval_runtime": 120.3748,
+      "eval_samples_per_second": 8.665,
+      "eval_steps_per_second": 0.274,
+      "step": 32000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.7782802641955836e-05,
+      "loss": 0.147,
+      "step": 36000
+    },
+    {
+      "epoch": 1.77,
+      "eval_bleu": 40.5681,
+      "eval_gen_len": 37.5935,
+      "eval_loss": 0.10191329568624496,
+      "eval_runtime": 110.8617,
+      "eval_samples_per_second": 9.408,
+      "eval_steps_per_second": 0.298,
+      "step": 36000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.7536474763406942e-05,
+      "loss": 0.1461,
+      "step": 40000
+    },
+    {
+      "epoch": 1.97,
+      "eval_bleu": 42.3964,
+      "eval_gen_len": 34.768,
+      "eval_loss": 0.10204007476568222,
+      "eval_runtime": 112.6476,
+      "eval_samples_per_second": 9.259,
+      "eval_steps_per_second": 0.293,
+      "step": 40000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.7290146884858045e-05,
+      "loss": 0.1386,
+      "step": 44000
+    },
+    {
+      "epoch": 2.17,
+      "eval_bleu": 40.217,
+      "eval_gen_len": 37.1946,
+      "eval_loss": 0.10240339487791061,
+      "eval_runtime": 170.37,
+      "eval_samples_per_second": 6.122,
+      "eval_steps_per_second": 0.194,
+      "step": 44000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.7043757393533123e-05,
+      "loss": 0.1376,
+      "step": 48000
+    },
+    {
+      "epoch": 2.37,
+      "eval_bleu": 41.5097,
+      "eval_gen_len": 36.3797,
+      "eval_loss": 0.1021459624171257,
+      "eval_runtime": 146.1468,
+      "eval_samples_per_second": 7.137,
+      "eval_steps_per_second": 0.226,
+      "step": 48000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.6797491127760255e-05,
+      "loss": 0.1366,
+      "step": 52000
+    },
+    {
+      "epoch": 2.56,
+      "eval_bleu": 42.2181,
+      "eval_gen_len": 35.0019,
+      "eval_loss": 0.10173720866441727,
+      "eval_runtime": 158.0705,
+      "eval_samples_per_second": 6.598,
+      "eval_steps_per_second": 0.209,
+      "step": 52000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.6551101636435333e-05,
+      "loss": 0.1368,
+      "step": 56000
+    },
+    {
+      "epoch": 2.76,
+      "eval_bleu": 41.65,
+      "eval_gen_len": 36.2694,
+      "eval_loss": 0.10165542364120483,
+      "eval_runtime": 160.9591,
+      "eval_samples_per_second": 6.48,
+      "eval_steps_per_second": 0.205,
+      "step": 56000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.630471214511041e-05,
+      "loss": 0.1371,
+      "step": 60000
+    },
+    {
+      "epoch": 2.96,
+      "eval_bleu": 42.5203,
+      "eval_gen_len": 34.1112,
+      "eval_loss": 0.10101941227912903,
+      "eval_runtime": 105.5932,
+      "eval_samples_per_second": 9.878,
+      "eval_steps_per_second": 0.313,
+      "step": 60000
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 1.6058384266561514e-05,
+      "loss": 0.1308,
+      "step": 64000
+    },
+    {
+      "epoch": 3.15,
+      "eval_bleu": 42.2011,
+      "eval_gen_len": 35.1908,
+      "eval_loss": 0.10181207209825516,
+      "eval_runtime": 118.0171,
+      "eval_samples_per_second": 8.838,
+      "eval_steps_per_second": 0.28,
+      "step": 64000
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 1.581205638801262e-05,
+      "loss": 0.1302,
+      "step": 68000
+    },
+    {
+      "epoch": 3.35,
+      "eval_bleu": 42.5239,
+      "eval_gen_len": 34.8715,
+      "eval_loss": 0.10198543220758438,
+      "eval_runtime": 121.4795,
+      "eval_samples_per_second": 8.586,
+      "eval_steps_per_second": 0.272,
+      "step": 68000
+    }
+  ],
+  "max_steps": 324608,
+  "num_train_epochs": 16,
+  "total_flos": 1.1723875993622938e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-68000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6b4d69457e8457bc8ba7157cadf6f7f462ddf893ce54473c85704df3bd5050
+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 sha256:69f89c9afa6c252900d404faf8dadcf9f2a2bba055b781dc7c4c97d2d6d21d1d
+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:fb6b4d69457e8457bc8ba7157cadf6f7f462ddf893ce54473c85704df3bd5050
+size 3771