dehio commited on Jan 19, 2022

Commit

66eb02f

•

1 Parent(s): 08a9f06

Initial commit

Browse files

Files changed (38) hide show

README.md +55 -0
added_tokens.json +1 -0
all_results.json +15 -0
checkpoint-500/added_tokens.json +1 -0
checkpoint-500/config.json +62 -0
checkpoint-500/optimizer.pt +3 -0
checkpoint-500/pytorch_model.bin +3 -0
checkpoint-500/rng_state.pth +3 -0
checkpoint-500/scheduler.pt +3 -0
checkpoint-500/special_tokens_map.json +1 -0
checkpoint-500/spiece.model +3 -0
checkpoint-500/tokenizer.json +0 -0
checkpoint-500/tokenizer_config.json +1 -0
checkpoint-500/trainer_state.json +46 -0
checkpoint-500/training_args.bin +3 -0
config.json +62 -0
generated_predictions.txt +0 -0
labels.txt +0 -0
predictions.txt +0 -0
pytorch_model.bin +3 -0
runs/Jan19_12-53-00_7cf8fe6c7293/1642596802.460296/events.out.tfevents.1642596802.7cf8fe6c7293.668.1 +3 -0
runs/Jan19_12-53-00_7cf8fe6c7293/events.out.tfevents.1642596802.7cf8fe6c7293.668.0 +3 -0
runs/Jan19_12-54-25_7cf8fe6c7293/1642596880.8129342/events.out.tfevents.1642596880.7cf8fe6c7293.718.1 +3 -0
runs/Jan19_12-54-25_7cf8fe6c7293/events.out.tfevents.1642596880.7cf8fe6c7293.718.0 +3 -0
runs/Jan19_12-55-27_7cf8fe6c7293/1642596942.3387752/events.out.tfevents.1642596942.7cf8fe6c7293.750.1 +3 -0
runs/Jan19_12-55-27_7cf8fe6c7293/events.out.tfevents.1642596942.7cf8fe6c7293.750.0 +3 -0
runs/Jan19_13-17-49_7cf8fe6c7293/1642598288.1092122/events.out.tfevents.1642598288.7cf8fe6c7293.913.1 +3 -0
runs/Jan19_13-17-49_7cf8fe6c7293/events.out.tfevents.1642598288.7cf8fe6c7293.913.0 +3 -0
runs/Jan19_14-10-20_7cf8fe6c7293/1642601438.4479742/events.out.tfevents.1642601438.7cf8fe6c7293.1429.1 +3 -0
runs/Jan19_14-10-20_7cf8fe6c7293/events.out.tfevents.1642601438.7cf8fe6c7293.1429.0 +3 -0
special_tokens_map.json +1 -0
spiece.model +3 -0
test_results.json +9 -0
tokenizer.json +0 -0
tokenizer_config.json +1 -0
train_results.json +8 -0
trainer_state.json +67 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,55 @@

+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- data
+model-index:
+- name: german-qg-t5-e2e-quad
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# german-qg-t5-e2e-quad
+This model is a fine-tuned version of [valhalla/t5-base-e2e-qg](https://huggingface.co/valhalla/t5-base-e2e-qg) on the data dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+### Training results
+### Framework versions
+- Transformers 4.16.0.dev0
+- Pytorch 1.10.0+cu111
+- Datasets 1.16.1
+- Tokenizers 0.10.3

added_tokens.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"<sep>": 32100, "<hl>": 32101}

all_results.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+    "epoch": 10.0,
+    "predict_bleu": 15.0146,
+    "predict_gen_len": 123.8797,
+    "predict_loss": 1.5464541912078857,
+    "predict_runtime": 1193.4414,
+    "predict_samples": 474,
+    "predict_samples_per_second": 0.397,
+    "predict_steps_per_second": 0.1,
+    "train_loss": 1.4465530395507813,
+    "train_runtime": 7665.0914,
+    "train_samples": 2540,
+    "train_samples_per_second": 3.314,
+    "train_steps_per_second": 0.103
+}

checkpoint-500/added_tokens.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"<sep>": 32100, "<hl>": 32101}

checkpoint-500/config.json ADDED Viewed

	@@ -0,0 +1,62 @@

+{
+  "_name_or_path": "valhalla/t5-base-e2e-qg",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32102
+}

checkpoint-500/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:948525b0aa8dc1fc5763e169cd1aca753b177263baa1b7f5be4e5c3f0bfb1d8e
+size 1783219389

checkpoint-500/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:71039639b1987ded849bbb4aaa9eb183f9af155539af60cf216148569570cb3e
+size 891651007

checkpoint-500/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bba26607dfe634191d975f09a73dfacf9effdfcc778854798f84b699099bed9d
+size 14503

checkpoint-500/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:26eab845218018d9515ebdee68340a063bea33586c5b2d308186c022fcd2f104
+size 623

checkpoint-500/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "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>"]}

checkpoint-500/spiece.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

checkpoint-500/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-500/tokenizer_config.json ADDED Viewed

	@@ -0,0 +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>"], "model_max_length": 512, "special_tokens_map_file": "models/t5-base-e2e-qg/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "valhalla/t5-base-e2e-qg", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

checkpoint-500/trainer_state.json ADDED Viewed

	@@ -0,0 +1,46 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.32755905511811,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.26,
+      "learning_rate": 8.734177215189874e-05,
+      "loss": 1.9271,
+      "step": 100
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.468354430379747e-05,
+      "loss": 1.5723,
+      "step": 200
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 6.20253164556962e-05,
+      "loss": 1.4655,
+      "step": 300
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 4.936708860759494e-05,
+      "loss": 1.4053,
+      "step": 400
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 3.670886075949367e-05,
+      "loss": 1.3442,
+      "step": 500
+    }
+  ],
+  "max_steps": 790,
+  "num_train_epochs": 10,
+  "total_flos": 8796387214172160.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d1c7ee3fc7ca3fc54caa0619765badf40de2954147f4239ab1ad292322a6a7
+size 3119

config.json ADDED Viewed

	@@ -0,0 +1,62 @@

+{
+  "_name_or_path": "valhalla/t5-base-e2e-qg",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 256,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "generate questions: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32102
+}

generated_predictions.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

labels.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

predictions.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1f16bf160477b1ace9d387905ae3df6b6af1bda43e0671b371638099829dc8
+size 891651007

runs/Jan19_12-53-00_7cf8fe6c7293/1642596802.460296/events.out.tfevents.1642596802.7cf8fe6c7293.668.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e001bada56838c177417a5614ee99d5df375c1d8e3a7501490ed991c252ef6d2
+size 5001

runs/Jan19_12-53-00_7cf8fe6c7293/events.out.tfevents.1642596802.7cf8fe6c7293.668.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:73dd19024d01a4843c7c7e94fa8554b247d1193c6f236bd08f3fb9a9049ba424
+size 4312

runs/Jan19_12-54-25_7cf8fe6c7293/1642596880.8129342/events.out.tfevents.1642596880.7cf8fe6c7293.718.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:16dfbc09c61c77ad339d08546a966ea5470a57af135909dac4afe7e2d27e9329
+size 5001

runs/Jan19_12-54-25_7cf8fe6c7293/events.out.tfevents.1642596880.7cf8fe6c7293.718.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8e374266569198366455a077948d407161898b09f240ff45c21f9ce028ccd290
+size 4309

runs/Jan19_12-55-27_7cf8fe6c7293/1642596942.3387752/events.out.tfevents.1642596942.7cf8fe6c7293.750.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc56e439959733451c2e457260f1dc6a8784d76a1488a06ca6eb59584d6035c
+size 5001

runs/Jan19_12-55-27_7cf8fe6c7293/events.out.tfevents.1642596942.7cf8fe6c7293.750.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ae84792071dd515410e7b940933836a749d415a6c35f0f62bde6b995b91f908b
+size 4657

runs/Jan19_13-17-49_7cf8fe6c7293/1642598288.1092122/events.out.tfevents.1642598288.7cf8fe6c7293.913.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:db7a976a18082bb064aba3cda058fceab9fab780628d66363f9a85b6e8f2a852
+size 5001

runs/Jan19_13-17-49_7cf8fe6c7293/events.out.tfevents.1642598288.7cf8fe6c7293.913.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ace15da7a997f88138522a29bf0fb4e0f45faef7f0ee9badf3fc784eebf155bc
+size 4657

runs/Jan19_14-10-20_7cf8fe6c7293/1642601438.4479742/events.out.tfevents.1642601438.7cf8fe6c7293.1429.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0781904291da3e1b02fd31fce0c32a8bbfebad0af0df50ff2a07a10fa9be71f4
+size 5001

runs/Jan19_14-10-20_7cf8fe6c7293/events.out.tfevents.1642601438.7cf8fe6c7293.1429.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa37bac9d1a3b865d86dbc09415f03a8d4f8bfcefd9a8dff7bf6f1edab523f38
+size 5760

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

spiece.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

test_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "predict_bleu": 15.0146,
+    "predict_gen_len": 123.8797,
+    "predict_loss": 1.5464541912078857,
+    "predict_runtime": 1193.4414,
+    "predict_samples": 474,
+    "predict_samples_per_second": 0.397,
+    "predict_steps_per_second": 0.1
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 10.0,
+    "train_loss": 1.4465530395507813,
+    "train_runtime": 7665.0914,
+    "train_samples": 2540,
+    "train_samples_per_second": 3.314,
+    "train_steps_per_second": 0.103
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,67 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.99527559055118,
+  "global_step": 790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.26,
+      "learning_rate": 8.734177215189874e-05,
+      "loss": 1.9271,
+      "step": 100
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.468354430379747e-05,
+      "loss": 1.5723,
+      "step": 200
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 6.20253164556962e-05,
+      "loss": 1.4655,
+      "step": 300
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 4.936708860759494e-05,
+      "loss": 1.4053,
+      "step": 400
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 3.670886075949367e-05,
+      "loss": 1.3442,
+      "step": 500
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 2.4050632911392405e-05,
+      "loss": 1.2954,
+      "step": 600
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 1.139240506329114e-05,
+      "loss": 1.28,
+      "step": 700
+    },
+    {
+      "epoch": 10.0,
+      "step": 790,
+      "total_flos": 1.388887369371648e+16,
+      "train_loss": 1.4465530395507813,
+      "train_runtime": 7665.0914,
+      "train_samples_per_second": 3.314,
+      "train_steps_per_second": 0.103
+    }
+  ],
+  "max_steps": 790,
+  "num_train_epochs": 10,
+  "total_flos": 1.388887369371648e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d1c7ee3fc7ca3fc54caa0619765badf40de2954147f4239ab1ad292322a6a7
+size 3119