Deleting unnecessary directory

large-1/config.json

@@ -1,32 +0,0 @@
-{
-  "_name_or_path": "google/mt5-large",
-  "architectures": [
-    "MT5ForConditionalGeneration"
-  ],
-  "d_ff": 2816,
-  "d_kv": 64,
-  "d_model": 1024,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "mt5",
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
-  "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.29.1",
-  "use_cache": true,
-  "vocab_size": 250112
-}

large-1/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.29.1"
-}

large-1/output.txt

@@ -1,234 +0,0 @@
-{'loss': 29.3333, 'learning_rate': 1e-05, 'epoch': 0.03}
-{'loss': 12.5737, 'learning_rate': 2e-05, 'epoch': 0.06}
-{'loss': 2.3813, 'learning_rate': 1.9968976856735126e-05, 'epoch': 0.09}
-{'loss': 0.2316, 'learning_rate': 1.993795371347025e-05, 'epoch': 0.12}
-{'loss': 0.099, 'learning_rate': 1.9906930570205375e-05, 'epoch': 0.15}
-{'loss': 0.0608, 'learning_rate': 1.98759074269405e-05, 'epoch': 0.19}
-{'loss': 0.0565, 'learning_rate': 1.9844884283675623e-05, 'epoch': 0.22}
-{'loss': 0.0435, 'learning_rate': 1.9813861140410748e-05, 'epoch': 0.25}
-{'loss': 0.0354, 'learning_rate': 1.9782837997145872e-05, 'epoch': 0.28}
-{'loss': 0.0339, 'learning_rate': 1.9751814853880996e-05, 'epoch': 0.31}
-{'loss': 0.0294, 'learning_rate': 1.972079171061612e-05, 'epoch': 0.34}
-{'loss': 0.035, 'learning_rate': 1.9689768567351245e-05, 'epoch': 0.37}
-{'loss': 0.0515, 'learning_rate': 1.965874542408637e-05, 'epoch': 0.4}
-{'loss': 0.0232, 'learning_rate': 1.9627722280821494e-05, 'epoch': 0.43}
-{'loss': 0.0349, 'learning_rate': 1.9596699137556618e-05, 'epoch': 0.46}
-{'loss': 0.0226, 'learning_rate': 1.9565675994291742e-05, 'epoch': 0.49}
-{'loss': 0.0215, 'learning_rate': 1.9534652851026867e-05, 'epoch': 0.53}
-{'loss': 0.0204, 'learning_rate': 1.9503629707761994e-05, 'epoch': 0.56}
-{'loss': 0.0192, 'learning_rate': 1.9472606564497115e-05, 'epoch': 0.59}
-{'loss': 0.0194, 'learning_rate': 1.9441583421232243e-05, 'epoch': 0.62}
-{'loss': 0.0179, 'learning_rate': 1.9410560277967364e-05, 'epoch': 0.65}
-{'loss': 0.017, 'learning_rate': 1.937953713470249e-05, 'epoch': 0.68}
-{'loss': 0.0226, 'learning_rate': 1.9348513991437613e-05, 'epoch': 0.71}
-{'loss': 0.016, 'learning_rate': 1.9317490848172737e-05, 'epoch': 0.74}
-{'loss': 0.0154, 'learning_rate': 1.928646770490786e-05, 'epoch': 0.77}
-{'loss': 0.0157, 'learning_rate': 1.9255444561642986e-05, 'epoch': 0.8}
-{'loss': 0.0139, 'learning_rate': 1.9224421418378113e-05, 'epoch': 0.84}
-{'loss': 0.0129, 'learning_rate': 1.9193398275113234e-05, 'epoch': 0.87}
-{'loss': 0.0134, 'learning_rate': 1.9162375131848362e-05, 'epoch': 0.9}
-{'loss': 0.0134, 'learning_rate': 1.9131351988583483e-05, 'epoch': 0.93}
-{'loss': 0.0133, 'learning_rate': 1.910032884531861e-05, 'epoch': 0.96}
-{'loss': 0.0133, 'learning_rate': 1.9069305702053732e-05, 'epoch': 0.99}
-{'eval_loss': 0.007159320637583733, 'eval_runtime': 63.5558, 'eval_samples_per_second': 113.05, 'eval_steps_per_second': 7.08, 'epoch': 1.0}
-{'loss': 0.0118, 'learning_rate': 1.903828255878886e-05, 'epoch': 1.02}
-{'loss': 0.0114, 'learning_rate': 1.900725941552398e-05, 'epoch': 1.05}
-{'loss': 0.0115, 'learning_rate': 1.8976236272259108e-05, 'epoch': 1.08}
-{'loss': 0.0115, 'learning_rate': 1.8945213128994233e-05, 'epoch': 1.11}
-{'loss': 0.0118, 'learning_rate': 1.8914189985729357e-05, 'epoch': 1.14}
-{'loss': 0.0119, 'learning_rate': 1.888316684246448e-05, 'epoch': 1.18}
-{'loss': 0.0117, 'learning_rate': 1.8852143699199606e-05, 'epoch': 1.21}
-{'loss': 0.0113, 'learning_rate': 1.882112055593473e-05, 'epoch': 1.24}
-{'loss': 0.0102, 'learning_rate': 1.8790097412669854e-05, 'epoch': 1.27}
-{'loss': 0.0109, 'learning_rate': 1.875907426940498e-05, 'epoch': 1.3}
-{'loss': 0.0096, 'learning_rate': 1.87280511261401e-05, 'epoch': 1.33}
-{'loss': 0.0105, 'learning_rate': 1.8697027982875227e-05, 'epoch': 1.36}
-{'loss': 0.0093, 'learning_rate': 1.866600483961035e-05, 'epoch': 1.39}
-{'loss': 0.0096, 'learning_rate': 1.8634981696345476e-05, 'epoch': 1.42}
-{'loss': 0.0091, 'learning_rate': 1.86039585530806e-05, 'epoch': 1.45}
-{'loss': 0.0099, 'learning_rate': 1.8572935409815725e-05, 'epoch': 1.48}
-{'loss': 0.009, 'learning_rate': 1.854191226655085e-05, 'epoch': 1.52}
-{'loss': 0.0097, 'learning_rate': 1.8510889123285973e-05, 'epoch': 1.55}
-{'loss': 0.0089, 'learning_rate': 1.8479865980021098e-05, 'epoch': 1.58}
-{'loss': 0.0097, 'learning_rate': 1.8448842836756222e-05, 'epoch': 1.61}
-{'loss': 0.0099, 'learning_rate': 1.8417819693491346e-05, 'epoch': 1.64}
-{'loss': 0.0092, 'learning_rate': 1.838679655022647e-05, 'epoch': 1.67}
-{'loss': 0.0094, 'learning_rate': 1.8355773406961595e-05, 'epoch': 1.7}
-{'loss': 0.0087, 'learning_rate': 1.832475026369672e-05, 'epoch': 1.73}
-{'loss': 0.0091, 'learning_rate': 1.8293727120431844e-05, 'epoch': 1.76}
-{'loss': 0.0098, 'learning_rate': 1.8262703977166968e-05, 'epoch': 1.79}
-{'loss': 0.0093, 'learning_rate': 1.8231680833902092e-05, 'epoch': 1.82}
-{'loss': 0.0088, 'learning_rate': 1.8200657690637217e-05, 'epoch': 1.86}
-{'loss': 0.008, 'learning_rate': 1.816963454737234e-05, 'epoch': 1.89}
-{'loss': 0.0088, 'learning_rate': 1.8138611404107465e-05, 'epoch': 1.92}
-{'loss': 0.0084, 'learning_rate': 1.810758826084259e-05, 'epoch': 1.95}
-{'loss': 0.0087, 'learning_rate': 1.8076565117577714e-05, 'epoch': 1.98}
-{'eval_loss': 0.005626102443784475, 'eval_runtime': 63.5514, 'eval_samples_per_second': 113.058, 'eval_steps_per_second': 7.081, 'epoch': 2.0}
-{'loss': 0.0081, 'learning_rate': 1.804554197431284e-05, 'epoch': 2.01}
-{'loss': 0.007, 'learning_rate': 1.8014518831047963e-05, 'epoch': 2.04}
-{'loss': 0.0072, 'learning_rate': 1.7983495687783087e-05, 'epoch': 2.07}
-{'loss': 0.0069, 'learning_rate': 1.795247254451821e-05, 'epoch': 2.1}
-{'loss': 0.0072, 'learning_rate': 1.7921449401253336e-05, 'epoch': 2.13}
-{'loss': 0.0067, 'learning_rate': 1.789042625798846e-05, 'epoch': 2.16}
-{'loss': 0.007, 'learning_rate': 1.7859403114723584e-05, 'epoch': 2.2}
-{'loss': 0.0072, 'learning_rate': 1.782837997145871e-05, 'epoch': 2.23}
-{'loss': 0.0074, 'learning_rate': 1.7797356828193833e-05, 'epoch': 2.26}
-{'loss': 0.0075, 'learning_rate': 1.7766333684928957e-05, 'epoch': 2.29}
-{'loss': 0.0072, 'learning_rate': 1.7735310541664085e-05, 'epoch': 2.32}
-{'loss': 0.0061, 'learning_rate': 1.7704287398399206e-05, 'epoch': 2.35}
-{'loss': 0.0071, 'learning_rate': 1.7673264255134334e-05, 'epoch': 2.38}
-{'loss': 0.0074, 'learning_rate': 1.7642241111869455e-05, 'epoch': 2.41}
-{'loss': 0.0072, 'learning_rate': 1.7611217968604582e-05, 'epoch': 2.44}
-{'loss': 0.0072, 'learning_rate': 1.7580194825339703e-05, 'epoch': 2.47}
-{'loss': 0.0075, 'learning_rate': 1.754917168207483e-05, 'epoch': 2.51}
-{'loss': 0.0069, 'learning_rate': 1.7518148538809952e-05, 'epoch': 2.54}
-{'loss': 0.007, 'learning_rate': 1.7487125395545076e-05, 'epoch': 2.57}
-{'loss': 0.0058, 'learning_rate': 1.7456102252280204e-05, 'epoch': 2.6}
-{'loss': 0.0064, 'learning_rate': 1.7425079109015325e-05, 'epoch': 2.63}
-{'loss': 0.0067, 'learning_rate': 1.7394055965750453e-05, 'epoch': 2.66}
-{'loss': 0.0062, 'learning_rate': 1.7363032822485574e-05, 'epoch': 2.69}
-{'loss': 0.0066, 'learning_rate': 1.73320096792207e-05, 'epoch': 2.72}
-{'loss': 0.0066, 'learning_rate': 1.7300986535955822e-05, 'epoch': 2.75}
-{'loss': 0.0071, 'learning_rate': 1.726996339269095e-05, 'epoch': 2.78}
-{'loss': 0.0065, 'learning_rate': 1.723894024942607e-05, 'epoch': 2.81}
-{'loss': 0.0065, 'learning_rate': 1.72079171061612e-05, 'epoch': 2.85}
-{'loss': 0.0065, 'learning_rate': 1.7176893962896323e-05, 'epoch': 2.88}
-{'loss': 0.0062, 'learning_rate': 1.7145870819631448e-05, 'epoch': 2.91}
-{'loss': 0.0075, 'learning_rate': 1.7114847676366572e-05, 'epoch': 2.94}
-{'loss': 0.0064, 'learning_rate': 1.7083824533101696e-05, 'epoch': 2.97}
-{'loss': 0.0063, 'learning_rate': 1.705280138983682e-05, 'epoch': 3.0}
-{'eval_loss': 0.005162048153579235, 'eval_runtime': 63.5102, 'eval_samples_per_second': 113.132, 'eval_steps_per_second': 7.085, 'epoch': 3.0}
-{'loss': 0.0055, 'learning_rate': 1.7021778246571945e-05, 'epoch': 3.03}
-{'loss': 0.0055, 'learning_rate': 1.699075510330707e-05, 'epoch': 3.06}
-{'loss': 0.0059, 'learning_rate': 1.6959731960042194e-05, 'epoch': 3.09}
-{'loss': 0.0052, 'learning_rate': 1.6928708816777318e-05, 'epoch': 3.12}
-{'loss': 0.0053, 'learning_rate': 1.6897685673512442e-05, 'epoch': 3.15}
-{'loss': 0.005, 'learning_rate': 1.6866662530247567e-05, 'epoch': 3.19}
-{'loss': 0.0056, 'learning_rate': 1.683563938698269e-05, 'epoch': 3.22}
-{'loss': 0.0051, 'learning_rate': 1.6804616243717815e-05, 'epoch': 3.25}
-{'loss': 0.0053, 'learning_rate': 1.677359310045294e-05, 'epoch': 3.28}
-{'loss': 0.0053, 'learning_rate': 1.6742569957188064e-05, 'epoch': 3.31}
-{'loss': 0.0051, 'learning_rate': 1.6711546813923188e-05, 'epoch': 3.34}
-{'loss': 0.0056, 'learning_rate': 1.6680523670658313e-05, 'epoch': 3.37}
-{'loss': 0.0068, 'learning_rate': 1.6649500527393437e-05, 'epoch': 3.4}
-{'loss': 0.0054, 'learning_rate': 1.661847738412856e-05, 'epoch': 3.43}
-{'loss': 0.0055, 'learning_rate': 1.6587454240863686e-05, 'epoch': 3.46}
-{'loss': 0.0056, 'learning_rate': 1.655643109759881e-05, 'epoch': 3.49}
-{'loss': 0.0053, 'learning_rate': 1.6525407954333934e-05, 'epoch': 3.53}
-{'loss': 0.0051, 'learning_rate': 1.649438481106906e-05, 'epoch': 3.56}
-{'loss': 0.005, 'learning_rate': 1.6463361667804183e-05, 'epoch': 3.59}
-{'loss': 0.0055, 'learning_rate': 1.6432338524539307e-05, 'epoch': 3.62}
-{'loss': 0.0048, 'learning_rate': 1.640131538127443e-05, 'epoch': 3.65}
-{'loss': 0.0052, 'learning_rate': 1.6370292238009556e-05, 'epoch': 3.68}
-{'loss': 0.0048, 'learning_rate': 1.633926909474468e-05, 'epoch': 3.71}
-{'loss': 0.0049, 'learning_rate': 1.6308245951479805e-05, 'epoch': 3.74}
-{'loss': 0.0054, 'learning_rate': 1.627722280821493e-05, 'epoch': 3.77}
-{'loss': 0.0052, 'learning_rate': 1.6246199664950053e-05, 'epoch': 3.8}
-{'loss': 0.0053, 'learning_rate': 1.6215176521685178e-05, 'epoch': 3.83}
-{'loss': 0.0052, 'learning_rate': 1.6184153378420302e-05, 'epoch': 3.87}
-{'loss': 0.0053, 'learning_rate': 1.6153130235155426e-05, 'epoch': 3.9}
-{'loss': 0.0052, 'learning_rate': 1.612210709189055e-05, 'epoch': 3.93}
-{'loss': 0.0052, 'learning_rate': 1.6091083948625675e-05, 'epoch': 3.96}
-{'loss': 0.0054, 'learning_rate': 1.60600608053608e-05, 'epoch': 3.99}
-{'eval_loss': 0.004835214000195265, 'eval_runtime': 63.5993, 'eval_samples_per_second': 112.973, 'eval_steps_per_second': 7.076, 'epoch': 4.0}
-{'loss': 0.0042, 'learning_rate': 1.6029037662095924e-05, 'epoch': 4.02}
-{'loss': 0.0044, 'learning_rate': 1.5998014518831048e-05, 'epoch': 4.05}
-{'loss': 0.0041, 'learning_rate': 1.5966991375566176e-05, 'epoch': 4.08}
-{'loss': 0.0046, 'learning_rate': 1.5935968232301297e-05, 'epoch': 4.11}
-{'loss': 0.004, 'learning_rate': 1.5904945089036424e-05, 'epoch': 4.14}
-{'loss': 0.0044, 'learning_rate': 1.5873921945771545e-05, 'epoch': 4.18}
-{'loss': 0.0047, 'learning_rate': 1.5842898802506673e-05, 'epoch': 4.21}
-{'loss': 0.0043, 'learning_rate': 1.5811875659241794e-05, 'epoch': 4.24}
-{'loss': 0.004, 'learning_rate': 1.5780852515976922e-05, 'epoch': 4.27}
-{'loss': 0.0043, 'learning_rate': 1.5749829372712043e-05, 'epoch': 4.3}
-{'loss': 0.0048, 'learning_rate': 1.571880622944717e-05, 'epoch': 4.33}
-{'loss': 0.0044, 'learning_rate': 1.5687783086182295e-05, 'epoch': 4.36}
-{'loss': 0.0042, 'learning_rate': 1.5656759942917416e-05, 'epoch': 4.39}
-{'loss': 0.0041, 'learning_rate': 1.5625736799652544e-05, 'epoch': 4.42}
-{'loss': 0.0045, 'learning_rate': 1.5594713656387664e-05, 'epoch': 4.45}
-{'loss': 0.0041, 'learning_rate': 1.5563690513122792e-05, 'epoch': 4.48}
-{'loss': 0.0044, 'learning_rate': 1.5532667369857913e-05, 'epoch': 4.52}
-{'loss': 0.0039, 'learning_rate': 1.550164422659304e-05, 'epoch': 4.55}
-{'loss': 0.0045, 'learning_rate': 1.5470621083328162e-05, 'epoch': 4.58}
-{'loss': 0.0039, 'learning_rate': 1.543959794006329e-05, 'epoch': 4.61}
-{'loss': 0.0044, 'learning_rate': 1.5408574796798414e-05, 'epoch': 4.64}
-{'loss': 0.004, 'learning_rate': 1.5377551653533538e-05, 'epoch': 4.67}
-{'loss': 0.0048, 'learning_rate': 1.5346528510268663e-05, 'epoch': 4.7}
-{'loss': 0.004, 'learning_rate': 1.5315505367003787e-05, 'epoch': 4.73}
-{'loss': 0.0046, 'learning_rate': 1.528448222373891e-05, 'epoch': 4.76}
-{'loss': 0.0043, 'learning_rate': 1.5253459080474036e-05, 'epoch': 4.79}
-{'loss': 0.0043, 'learning_rate': 1.5222435937209158e-05, 'epoch': 4.82}
-{'loss': 0.0042, 'learning_rate': 1.5191412793944284e-05, 'epoch': 4.86}
-{'loss': 0.0045, 'learning_rate': 1.5160389650679409e-05, 'epoch': 4.89}
-{'loss': 0.004, 'learning_rate': 1.5129366507414533e-05, 'epoch': 4.92}
-{'loss': 0.0037, 'learning_rate': 1.5098343364149657e-05, 'epoch': 4.95}
-{'loss': 0.0045, 'learning_rate': 1.506732022088478e-05, 'epoch': 4.98}
-{'eval_loss': 0.004868941381573677, 'eval_runtime': 63.5068, 'eval_samples_per_second': 113.137, 'eval_steps_per_second': 7.086, 'epoch': 5.0}
-{'loss': 0.0038, 'learning_rate': 1.5036297077619906e-05, 'epoch': 5.01}
-{'loss': 0.0035, 'learning_rate': 1.5005273934355029e-05, 'epoch': 5.04}
-{'loss': 0.0035, 'learning_rate': 1.4974250791090155e-05, 'epoch': 5.07}
-{'loss': 0.0037, 'learning_rate': 1.4943227647825277e-05, 'epoch': 5.1}
-{'loss': 0.0031, 'learning_rate': 1.4912204504560403e-05, 'epoch': 5.13}
-{'loss': 0.0035, 'learning_rate': 1.4881181361295528e-05, 'epoch': 5.16}
-{'loss': 0.0037, 'learning_rate': 1.4850158218030652e-05, 'epoch': 5.2}
-{'loss': 0.0033, 'learning_rate': 1.4819135074765776e-05, 'epoch': 5.23}
-{'loss': 0.0039, 'learning_rate': 1.47881119315009e-05, 'epoch': 5.26}
-{'loss': 0.0036, 'learning_rate': 1.4757088788236025e-05, 'epoch': 5.29}
-{'loss': 0.0039, 'learning_rate': 1.4726065644971151e-05, 'epoch': 5.32}
-{'loss': 0.0035, 'learning_rate': 1.4695042501706274e-05, 'epoch': 5.35}
-{'loss': 0.0034, 'learning_rate': 1.46640193584414e-05, 'epoch': 5.38}
-{'loss': 0.003, 'learning_rate': 1.4632996215176522e-05, 'epoch': 5.41}
-{'loss': 0.0034, 'learning_rate': 1.4601973071911648e-05, 'epoch': 5.44}
-{'loss': 0.0045, 'learning_rate': 1.4570949928646771e-05, 'epoch': 5.47}
-{'loss': 0.0036, 'learning_rate': 1.4539926785381897e-05, 'epoch': 5.51}
-{'loss': 0.0036, 'learning_rate': 1.450890364211702e-05, 'epoch': 5.54}
-{'loss': 0.0037, 'learning_rate': 1.4477880498852146e-05, 'epoch': 5.57}
-{'loss': 0.0035, 'learning_rate': 1.444685735558727e-05, 'epoch': 5.6}
-{'loss': 0.0037, 'learning_rate': 1.4415834212322393e-05, 'epoch': 5.63}
-{'loss': 0.0037, 'learning_rate': 1.4384811069057519e-05, 'epoch': 5.66}
-{'loss': 0.0035, 'learning_rate': 1.4353787925792641e-05, 'epoch': 5.69}
-{'loss': 0.0039, 'learning_rate': 1.4322764782527767e-05, 'epoch': 5.72}
-{'loss': 0.0038, 'learning_rate': 1.429174163926289e-05, 'epoch': 5.75}
-{'loss': 0.003, 'learning_rate': 1.4260718495998016e-05, 'epoch': 5.78}
-{'loss': 0.0033, 'learning_rate': 1.4229695352733139e-05, 'epoch': 5.81}
-{'loss': 0.004, 'learning_rate': 1.4198672209468265e-05, 'epoch': 5.85}
-{'loss': 0.0031, 'learning_rate': 1.4167649066203389e-05, 'epoch': 5.88}
-{'loss': 0.0034, 'learning_rate': 1.4136625922938513e-05, 'epoch': 5.91}
-{'loss': 0.0032, 'learning_rate': 1.4105602779673638e-05, 'epoch': 5.94}
-{'loss': 0.0036, 'learning_rate': 1.4074579636408762e-05, 'epoch': 5.97}
-{'loss': 0.0035, 'learning_rate': 1.4043556493143886e-05, 'epoch': 6.0}
-{'eval_loss': 0.004906239919364452, 'eval_runtime': 63.3798, 'eval_samples_per_second': 113.364, 'eval_steps_per_second': 7.1, 'epoch': 6.0}
-{'loss': 0.0029, 'learning_rate': 1.4012533349879013e-05, 'epoch': 6.03}
-{'loss': 0.0028, 'learning_rate': 1.3981510206614135e-05, 'epoch': 6.06}
-{'loss': 0.0026, 'learning_rate': 1.3950487063349261e-05, 'epoch': 6.09}
-{'loss': 0.0028, 'learning_rate': 1.3919463920084384e-05, 'epoch': 6.12}
-{'loss': 0.0025, 'learning_rate': 1.388844077681951e-05, 'epoch': 6.15}
-{'loss': 0.0027, 'learning_rate': 1.3857417633554633e-05, 'epoch': 6.19}
-{'loss': 0.0029, 'learning_rate': 1.3826394490289757e-05, 'epoch': 6.22}
-{'loss': 0.0029, 'learning_rate': 1.3795371347024881e-05, 'epoch': 6.25}
-{'loss': 0.0027, 'learning_rate': 1.3764348203760006e-05, 'epoch': 6.28}
-{'loss': 0.0032, 'learning_rate': 1.373332506049513e-05, 'epoch': 6.31}
-{'loss': 0.0031, 'learning_rate': 1.3702301917230254e-05, 'epoch': 6.34}
-{'loss': 0.0032, 'learning_rate': 1.367127877396538e-05, 'epoch': 6.37}
-{'loss': 0.0029, 'learning_rate': 1.3640255630700503e-05, 'epoch': 6.4}
-{'loss': 0.0031, 'learning_rate': 1.3609232487435629e-05, 'epoch': 6.43}
-{'loss': 0.0029, 'learning_rate': 1.3578209344170752e-05, 'epoch': 6.46}
-{'loss': 0.0031, 'learning_rate': 1.3547186200905878e-05, 'epoch': 6.49}
-{'loss': 0.003, 'learning_rate': 1.3516163057641e-05, 'epoch': 6.53}
-{'loss': 0.0033, 'learning_rate': 1.3485139914376126e-05, 'epoch': 6.56}
-{'loss': 0.0028, 'learning_rate': 1.3454116771111249e-05, 'epoch': 6.59}
-{'loss': 0.0029, 'learning_rate': 1.3423093627846375e-05, 'epoch': 6.62}
-{'loss': 0.003, 'learning_rate': 1.33920704845815e-05, 'epoch': 6.65}
-{'loss': 0.0027, 'learning_rate': 1.3361047341316624e-05, 'epoch': 6.68}
-{'loss': 0.0029, 'learning_rate': 1.3330024198051748e-05, 'epoch': 6.71}
-{'loss': 0.003, 'learning_rate': 1.3299001054786872e-05, 'epoch': 6.74}
-{'loss': 0.003, 'learning_rate': 1.3267977911521997e-05, 'epoch': 6.77}
-{'loss': 0.0031, 'learning_rate': 1.3236954768257123e-05, 'epoch': 6.8}
-{'loss': 0.0027, 'learning_rate': 1.3205931624992245e-05, 'epoch': 6.83}
-{'loss': 0.0034, 'learning_rate': 1.3174908481727368e-05, 'epoch': 6.87}
-{'loss': 0.0029, 'learning_rate': 1.3143885338462494e-05, 'epoch': 6.9}
-{'loss': 0.0028, 'learning_rate': 1.3112862195197618e-05, 'epoch': 6.93}
-{'loss': 0.0027, 'learning_rate': 1.3081839051932743e-05, 'epoch': 6.96}
-{'loss': 0.0032, 'learning_rate': 1.3050815908667867e-05, 'epoch': 6.99}
-{'eval_loss': 0.005266720894724131, 'eval_runtime': 63.4285, 'eval_samples_per_second': 113.277, 'eval_steps_per_second': 7.095, 'epoch': 7.0}
-{'train_runtime': 28268.4419, 'train_samples_per_second': 45.751, 'train_steps_per_second': 11.438, 'train_loss': 0.20489513011235258, 'epoch': 7.0}

large-1/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80f51a079ead19b7f0e9d82d46e113eee42e614b574c8b285b733727812a3be1
-size 4918519065

large-1/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a3edc56f0f0e1d7be1ce3265d43ba3e04b7d248bf3e6aeba8adfbe111cabeb09
-size 4027