latest weight files

config.json

@@ -1,9 +1,8 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "deep-learning-analytics/GrammarCorrector",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "model_type" : "t5-base",
   "d_ff": 3072,
   "d_kv": 64,
   "d_model": 768,
@@ -52,7 +51,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.13.0",
+  "transformers_version": "4.15.0",
   "use_cache": true,
   "vocab_size": 32128
 }

scheduler.pt → tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c056a35a1fee2fe31a1ef5d72d11ff0bff40a9c996d02f6b0f7cb07f1710d957
-size 623
+oid sha256:ebe904081eba59ba9151310d624e20284c2be8bbf4e415701bce3c198357ea3d
+size 892145048

tokenizer_config.json

@@ -1 +1 @@
-{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/90de37880b5ff5ac7ab70ff0bd369f207e9b74133fa153c163d14c5bb0116207.8627f1bd5d270a9fd2e5a51c8bec3223896587cc3cfe13edeabb0992ab43c529", "name_or_path": "t5-base", "tokenizer_class": "T5Tokenizer"}
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/90de37880b5ff5ac7ab70ff0bd369f207e9b74133fa153c163d14c5bb0116207.8627f1bd5d270a9fd2e5a51c8bec3223896587cc3cfe13edeabb0992ab43c529", "name_or_path": "deep-learning-analytics/GrammarCorrector", "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -1,206 +0,0 @@
-{
-  "best_metric": 0.561149001121521,
-  "best_model_checkpoint": "/content/drive/MyDrive/c4_200m/weights/checkpoint-5000",
-  "epoch": 0.969681298080031,
-  "global_step": 5000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.1,
-      "learning_rate": 1.8072148952676496e-05,
-      "loss": 0.763,
-      "step": 500
-    },
-    {
-      "epoch": 0.1,
-      "eval_gen_len": 17.3073,
-      "eval_loss": 0.6263013482093811,
-      "eval_rouge1": 71.3829,
-      "eval_rouge2": 60.9575,
-      "eval_rougeL": 70.617,
-      "eval_rougeLsum": 70.6508,
-      "eval_runtime": 4434.8322,
-      "eval_samples_per_second": 12.402,
-      "eval_steps_per_second": 0.775,
-      "step": 500
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 1.6132660977501943e-05,
-      "loss": 0.6682,
-      "step": 1000
-    },
-    {
-      "epoch": 0.19,
-      "eval_gen_len": 17.2827,
-      "eval_loss": 0.5980147123336792,
-      "eval_rouge1": 71.6839,
-      "eval_rouge2": 61.5115,
-      "eval_rougeL": 70.9369,
-      "eval_rougeLsum": 70.9762,
-      "eval_runtime": 4421.7138,
-      "eval_samples_per_second": 12.439,
-      "eval_steps_per_second": 0.778,
-      "step": 1000
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 1.4193173002327387e-05,
-      "loss": 0.6547,
-      "step": 1500
-    },
-    {
-      "epoch": 0.29,
-      "eval_gen_len": 17.2674,
-      "eval_loss": 0.5852676630020142,
-      "eval_rouge1": 71.8716,
-      "eval_rouge2": 61.8264,
-      "eval_rougeL": 71.1345,
-      "eval_rougeLsum": 71.1741,
-      "eval_runtime": 4432.6842,
-      "eval_samples_per_second": 12.408,
-      "eval_steps_per_second": 0.776,
-      "step": 1500
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 1.2257564003103182e-05,
-      "loss": 0.6423,
-      "step": 2000
-    },
-    {
-      "epoch": 0.39,
-      "eval_gen_len": 17.2636,
-      "eval_loss": 0.5758475065231323,
-      "eval_rouge1": 71.9319,
-      "eval_rouge2": 61.9431,
-      "eval_rougeL": 71.1965,
-      "eval_rougeLsum": 71.2364,
-      "eval_runtime": 4426.8507,
-      "eval_samples_per_second": 12.424,
-      "eval_steps_per_second": 0.777,
-      "step": 2000
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 1.0318076027928628e-05,
-      "loss": 0.6319,
-      "step": 2500
-    },
-    {
-      "epoch": 0.48,
-      "eval_gen_len": 17.2555,
-      "eval_loss": 0.5706557631492615,
-      "eval_rouge1": 72.004,
-      "eval_rouge2": 62.0721,
-      "eval_rougeL": 71.2739,
-      "eval_rougeLsum": 71.3176,
-      "eval_runtime": 4455.9486,
-      "eval_samples_per_second": 12.343,
-      "eval_steps_per_second": 0.772,
-      "step": 2500
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 8.378588052754074e-06,
-      "loss": 0.6239,
-      "step": 3000
-    },
-    {
-      "epoch": 0.58,
-      "eval_gen_len": 17.251,
-      "eval_loss": 0.5678849220275879,
-      "eval_rouge1": 72.0655,
-      "eval_rouge2": 62.1749,
-      "eval_rougeL": 71.3432,
-      "eval_rougeLsum": 71.3854,
-      "eval_runtime": 4483.3834,
-      "eval_samples_per_second": 12.268,
-      "eval_steps_per_second": 0.767,
-      "step": 3000
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 6.43910007757952e-06,
-      "loss": 0.619,
-      "step": 3500
-    },
-    {
-      "epoch": 0.68,
-      "eval_gen_len": 17.25,
-      "eval_loss": 0.5634791851043701,
-      "eval_rouge1": 72.0893,
-      "eval_rouge2": 62.2244,
-      "eval_rougeL": 71.3669,
-      "eval_rougeLsum": 71.4087,
-      "eval_runtime": 4466.0069,
-      "eval_samples_per_second": 12.315,
-      "eval_steps_per_second": 0.77,
-      "step": 3500
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 4.499612102404966e-06,
-      "loss": 0.6248,
-      "step": 4000
-    },
-    {
-      "epoch": 0.78,
-      "eval_gen_len": 17.246,
-      "eval_loss": 0.5618749260902405,
-      "eval_rouge1": 72.1096,
-      "eval_rouge2": 62.261,
-      "eval_rougeL": 71.3877,
-      "eval_rougeLsum": 71.4304,
-      "eval_runtime": 4436.9366,
-      "eval_samples_per_second": 12.396,
-      "eval_steps_per_second": 0.775,
-      "step": 4000
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 2.560124127230411e-06,
-      "loss": 0.6159,
-      "step": 4500
-    },
-    {
-      "epoch": 0.87,
-      "eval_gen_len": 17.2457,
-      "eval_loss": 0.5612673163414001,
-      "eval_rouge1": 72.1232,
-      "eval_rouge2": 62.2834,
-      "eval_rougeL": 71.4006,
-      "eval_rougeLsum": 71.4433,
-      "eval_runtime": 4436.0596,
-      "eval_samples_per_second": 12.398,
-      "eval_steps_per_second": 0.775,
-      "step": 4500
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 6.206361520558573e-07,
-      "loss": 0.6118,
-      "step": 5000
-    },
-    {
-      "epoch": 0.97,
-      "eval_gen_len": 17.2461,
-      "eval_loss": 0.561149001121521,
-      "eval_rouge1": 72.1272,
-      "eval_rouge2": 62.2947,
-      "eval_rougeL": 71.4073,
-      "eval_rougeLsum": 71.4508,
-      "eval_runtime": 4447.3157,
-      "eval_samples_per_second": 12.367,
-      "eval_steps_per_second": 0.773,
-      "step": 5000
-    }
-  ],
-  "max_steps": 5156,
-  "num_train_epochs": 1,
-  "total_flos": 7.061289205579776e+16,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a8e74a3d1321d4059986bdb1bc89a6f629111c8bf281d2a2ee15efdbfbc1babb
-size 2991