Upload 13 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-hi",
+  "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": [
+    [
+      61949
+    ]
+  ],
+  "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": 61949,
+  "decoder_vocab_size": 61950,
+  "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": 61950,
+  "forced_eos_token_id": 0,
+  "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": 61949,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 61950
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6b3ec355f50337697ab927920eedcb478ff134219f943f4107ac5f76ddc943d
+size 607003653

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e33215041d4b4fae52e27a9afbe40495370a210ce9bfa91b7656ee2a5b078f
+size 303761861

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bc7b7539deda0a621f236ed4e7ad4b418c91cde712c083323e037732035321
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10cdf52c87d81771463a1e272f59ea12587aeaf920cf9a1a8618f074dfc448c
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff7b38d8eaaae05bac91a9dbaa2d06cd6c4b0024e2c991833df8089cc29ce72
+size 627

special_tokens_map.json

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

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5529d3a72f8c1d5f7e357f1b6fd30e3cf58f6e1ba0401db135a118ac92f4a76
+size 1067935

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 11644,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9312950875987636e-05,
+      "loss": 0.5996,
+      "step": 500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8625901751975268e-05,
+      "loss": 0.6564,
+      "step": 1000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7938852627962902e-05,
+      "loss": 0.6654,
+      "step": 1500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7251803503950534e-05,
+      "loss": 0.6449,
+      "step": 2000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6564754379938165e-05,
+      "loss": 0.6363,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 11.080936212068192,
+      "eval_loss": 0.7257852554321289,
+      "eval_runtime": 19.0528,
+      "eval_samples_per_second": 67.917,
+      "eval_steps_per_second": 4.251,
+      "step": 2911
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.58777052559258e-05,
+      "loss": 0.6256,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.5192030230161459e-05,
+      "loss": 0.513,
+      "step": 3500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.4504981106149092e-05,
+      "loss": 0.5154,
+      "step": 4000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.3817931982136723e-05,
+      "loss": 0.5233,
+      "step": 4500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.3130882858124357e-05,
+      "loss": 0.5053,
+      "step": 5000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.244383373411199e-05,
+      "loss": 0.5053,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 11.760028545810009,
+      "eval_loss": 0.7024416923522949,
+      "eval_runtime": 19.0637,
+      "eval_samples_per_second": 67.878,
+      "eval_steps_per_second": 4.249,
+      "step": 5822
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.1756784610099623e-05,
+      "loss": 0.4781,
+      "step": 6000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.1069735486087256e-05,
+      "loss": 0.4301,
+      "step": 6500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.038268636207489e-05,
+      "loss": 0.4228,
+      "step": 7000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 9.697011336310546e-06,
+      "loss": 0.4341,
+      "step": 7500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 9.009962212298181e-06,
+      "loss": 0.4195,
+      "step": 8000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 8.322913088285814e-06,
+      "loss": 0.4226,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 16.148157890934268,
+      "eval_loss": 0.6924545168876648,
+      "eval_runtime": 18.804,
+      "eval_samples_per_second": 68.815,
+      "eval_steps_per_second": 4.308,
+      "step": 8733
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 7.63723806252147e-06,
+      "loss": 0.3849,
+      "step": 9000
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 6.9501889385091035e-06,
+      "loss": 0.3686,
+      "step": 9500
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 6.263139814496737e-06,
+      "loss": 0.3713,
+      "step": 10000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 5.5760906904843705e-06,
+      "loss": 0.3681,
+      "step": 10500
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 4.8890415664720035e-06,
+      "loss": 0.3708,
+      "step": 11000
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 4.2019924424596366e-06,
+      "loss": 0.3665,
+      "step": 11500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 15.230107565625683,
+      "eval_loss": 0.6867288947105408,
+      "eval_runtime": 18.8096,
+      "eval_samples_per_second": 68.795,
+      "eval_steps_per_second": 4.306,
+      "step": 11644
+    }
+  ],
+  "max_steps": 14555,
+  "num_train_epochs": 5,
+  "total_flos": 284658341511168.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93cd5f8e821455be59ed7ced52d776333d7dbdea2bc890832d4497d4f3e56565
+size 3579