Upload 13 files

config.json

@@ -8,11 +8,6 @@
     "MarianMTModel"
   ],
   "attention_dropout": 0.0,
-  "bad_words_ids": [
-    [
-      61109
-    ]
-  ],
   "bos_token_id": 0,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
@@ -43,19 +38,19 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": 512,
+  "max_length": null,
   "max_position_embeddings": 512,
   "model_type": "marian",
   "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": 4,
+  "num_beams": null,
   "num_hidden_layers": 6,
   "pad_token_id": 61109,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 61110
 }

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 61109,
   "renormalize_logits": true,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.47.0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936badc9c7f886bf746bedb457115bbf63890afefa6161ee81c6076c51c8ba84
+size 301980760

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdda2f75090a1fa6a2183cc5bbf5d356776970ca21e20aa147053a61b48f34d5
+oid sha256:60e0dc487722a1366760c27d2ee970089f0fefc2794625d13aefa4169b2f0fc8
 size 603626106

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f75bdecce60610b3bcd1d97c52de3f414a5305efa9e61c49a11d3e65936d2668
+oid sha256:269b6dd0942bbfcf02a52761caca71a971630a96b91a601c369a0236a15beb2f
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc0f3a8a99bc754b73e55fd43baa7d572c046f5860346dbf5e6521b29bd9dff
+oid sha256:4daaed72356b285cd58234bc0f16bfd1bdd583b13d20d80a8722000fa49b28ef
 size 1064

special_tokens_map.json

@@ -1,5 +1,23 @@
 {
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -27,6 +27,7 @@
   },
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
+  "extra_special_tokens": {},
   "model_max_length": 512,
   "pad_token": "<pad>",
   "separate_vocabs": false,

trainer_state.json

@@ -3,182 +3,84 @@
   "best_model_checkpoint": null,
   "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 7280,
+  "global_step": 224,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.5494505494505495,
-      "grad_norm": 7.208542823791504,
-      "learning_rate": 1.862637362637363e-05,
-      "loss": 1.4229,
-      "step": 500
-    },
     {
       "epoch": 1.0,
-      "eval_bleu": 45.1493,
-      "eval_gen_len": 21.1512,
-      "eval_loss": 0.9880260229110718,
-      "eval_runtime": 159.8583,
-      "eval_samples_per_second": 11.379,
-      "eval_steps_per_second": 0.713,
-      "step": 910
-    },
-    {
-      "epoch": 1.098901098901099,
-      "grad_norm": 5.381701469421387,
-      "learning_rate": 1.7252747252747256e-05,
-      "loss": 1.1197,
-      "step": 1000
-    },
-    {
-      "epoch": 1.6483516483516483,
-      "grad_norm": 4.710964679718018,
-      "learning_rate": 1.587912087912088e-05,
-      "loss": 0.9205,
-      "step": 1500
+      "eval_bleu": 28.3319,
+      "eval_gen_len": 32.6,
+      "eval_loss": 1.7957160472869873,
+      "eval_runtime": 11.0612,
+      "eval_samples_per_second": 4.972,
+      "eval_steps_per_second": 0.362,
+      "step": 28
     },
     {
       "epoch": 2.0,
-      "eval_bleu": 48.9448,
-      "eval_gen_len": 21.4244,
-      "eval_loss": 0.8794811367988586,
-      "eval_runtime": 164.115,
-      "eval_samples_per_second": 11.084,
-      "eval_steps_per_second": 0.695,
-      "step": 1820
-    },
-    {
-      "epoch": 2.197802197802198,
-      "grad_norm": 3.468052864074707,
-      "learning_rate": 1.4505494505494506e-05,
-      "loss": 0.8318,
-      "step": 2000
-    },
-    {
-      "epoch": 2.7472527472527473,
-      "grad_norm": 3.9397318363189697,
-      "learning_rate": 1.3131868131868134e-05,
-      "loss": 0.7509,
-      "step": 2500
+      "eval_bleu": 36.2391,
+      "eval_gen_len": 35.6727,
+      "eval_loss": 1.7393983602523804,
+      "eval_runtime": 11.6367,
+      "eval_samples_per_second": 4.726,
+      "eval_steps_per_second": 0.344,
+      "step": 56
     },
     {
       "epoch": 3.0,
-      "eval_bleu": 50.7507,
-      "eval_gen_len": 21.4739,
-      "eval_loss": 0.83347487449646,
-      "eval_runtime": 167.1805,
-      "eval_samples_per_second": 10.88,
-      "eval_steps_per_second": 0.682,
-      "step": 2730
-    },
-    {
-      "epoch": 3.2967032967032965,
-      "grad_norm": 4.654043197631836,
-      "learning_rate": 1.1758241758241759e-05,
-      "loss": 0.7075,
-      "step": 3000
-    },
-    {
-      "epoch": 3.8461538461538463,
-      "grad_norm": 3.244563341140747,
-      "learning_rate": 1.0384615384615386e-05,
-      "loss": 0.6522,
-      "step": 3500
+      "eval_bleu": 38.5694,
+      "eval_gen_len": 36.0545,
+      "eval_loss": 1.6639301776885986,
+      "eval_runtime": 11.4577,
+      "eval_samples_per_second": 4.8,
+      "eval_steps_per_second": 0.349,
+      "step": 84
     },
     {
       "epoch": 4.0,
-      "eval_bleu": 51.8451,
-      "eval_gen_len": 21.4134,
-      "eval_loss": 0.8046153783798218,
-      "eval_runtime": 167.5891,
-      "eval_samples_per_second": 10.854,
-      "eval_steps_per_second": 0.68,
-      "step": 3640
-    },
-    {
-      "epoch": 4.395604395604396,
-      "grad_norm": 4.202299118041992,
-      "learning_rate": 9.010989010989011e-06,
-      "loss": 0.6097,
-      "step": 4000
-    },
-    {
-      "epoch": 4.945054945054945,
-      "grad_norm": 6.508543968200684,
-      "learning_rate": 7.637362637362638e-06,
-      "loss": 0.5877,
-      "step": 4500
+      "eval_bleu": 39.6319,
+      "eval_gen_len": 35.3818,
+      "eval_loss": 1.6301159858703613,
+      "eval_runtime": 11.224,
+      "eval_samples_per_second": 4.9,
+      "eval_steps_per_second": 0.356,
+      "step": 112
     },
     {
       "epoch": 5.0,
-      "eval_bleu": 52.489,
-      "eval_gen_len": 21.453,
-      "eval_loss": 0.7915568947792053,
-      "eval_runtime": 170.447,
-      "eval_samples_per_second": 10.672,
-      "eval_steps_per_second": 0.669,
-      "step": 4550
-    },
-    {
-      "epoch": 5.4945054945054945,
-      "grad_norm": 4.693784236907959,
-      "learning_rate": 6.2637362637362645e-06,
-      "loss": 0.5454,
-      "step": 5000
+      "eval_bleu": 38.9538,
+      "eval_gen_len": 35.6182,
+      "eval_loss": 1.6278760433197021,
+      "eval_runtime": 11.1051,
+      "eval_samples_per_second": 4.953,
+      "eval_steps_per_second": 0.36,
+      "step": 140
     },
     {
       "epoch": 6.0,
-      "eval_bleu": 53.267,
-      "eval_gen_len": 21.4063,
-      "eval_loss": 0.7819094657897949,
-      "eval_runtime": 166.0221,
-      "eval_samples_per_second": 10.956,
-      "eval_steps_per_second": 0.687,
-      "step": 5460
-    },
-    {
-      "epoch": 6.043956043956044,
-      "grad_norm": 3.2858574390411377,
-      "learning_rate": 4.890109890109891e-06,
-      "loss": 0.5319,
-      "step": 5500
-    },
-    {
-      "epoch": 6.593406593406593,
-      "grad_norm": 4.065381050109863,
-      "learning_rate": 3.516483516483517e-06,
-      "loss": 0.5039,
-      "step": 6000
+      "eval_bleu": 40.6136,
+      "eval_gen_len": 35.4909,
+      "eval_loss": 1.6254886388778687,
+      "eval_runtime": 11.4878,
+      "eval_samples_per_second": 4.788,
+      "eval_steps_per_second": 0.348,
+      "step": 168
     },
     {
       "epoch": 7.0,
-      "eval_bleu": 53.3718,
-      "eval_gen_len": 21.5014,
-      "eval_loss": 0.7780753970146179,
-      "eval_runtime": 172.3653,
-      "eval_samples_per_second": 10.553,
-      "eval_steps_per_second": 0.661,
-      "step": 6370
-    },
-    {
-      "epoch": 7.142857142857143,
-      "grad_norm": 3.438549280166626,
-      "learning_rate": 2.1428571428571427e-06,
-      "loss": 0.5018,
-      "step": 6500
-    },
-    {
-      "epoch": 7.6923076923076925,
-      "grad_norm": 4.464223384857178,
-      "learning_rate": 7.692307692307694e-07,
-      "loss": 0.4847,
-      "step": 7000
+      "eval_bleu": 40.7205,
+      "eval_gen_len": 35.2545,
+      "eval_loss": 1.6089469194412231,
+      "eval_runtime": 10.925,
+      "eval_samples_per_second": 5.034,
+      "eval_steps_per_second": 0.366,
+      "step": 196
     }
   ],
   "logging_steps": 500,
-  "max_steps": 7280,
+  "max_steps": 224,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 500,
@@ -194,7 +96,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2444491603574784.0,
+  "total_flos": 114320117071872.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20449154fe68ba8250b81371c6832942b4bdd0b93d2c344989c41f78532d92ce
-size 5368
+oid sha256:1b823e3073621345cee91e7b5f83dc767f79444cac218b57c790356f7ac5e3e7
+size 5496