MihaiPopa-1 commited on 20 days ago

Commit

c8758c1

verified ·

1 Parent(s): 22cafdb

Upload folder using huggingface_hub

Browse files

Files changed (33) hide show

checkpoint-1953/model.safetensors +3 -0
checkpoint-1953/optimizer.pt +3 -0
checkpoint-1953/rng_state.pth +3 -0
checkpoint-1953/scheduler.pt +3 -0
checkpoint-1953/tokenizer.json +0 -0
checkpoint-1953/tokenizer_config.json +17 -0
checkpoint-1953/trainer_state.json +66 -0
checkpoint-1953/training_args.bin +3 -0
checkpoint-3906/model.safetensors +3 -0
checkpoint-3906/optimizer.pt +3 -0
checkpoint-3906/rng_state.pth +3 -0
checkpoint-3906/scheduler.pt +3 -0
checkpoint-3906/tokenizer.json +0 -0
checkpoint-3906/tokenizer_config.json +17 -0
checkpoint-3906/trainer_state.json +105 -0
checkpoint-3906/training_args.bin +3 -0
checkpoint-5859/model.safetensors +3 -0
checkpoint-5859/optimizer.pt +3 -0
checkpoint-5859/rng_state.pth +3 -0
checkpoint-5859/scheduler.pt +3 -0
checkpoint-5859/tokenizer.json +0 -0
checkpoint-5859/tokenizer_config.json +17 -0
checkpoint-5859/trainer_state.json +144 -0
checkpoint-5859/training_args.bin +3 -0
model.safetensors +3 -0
optimizer.pt +3 -0
rng_state.pth +3 -0
runs/Mar28_13-58-32_6078593f7de5/events.out.tfevents.1774706312.6078593f7de5.7992.0 +3 -0
scheduler.pt +3 -0
tokenizer.json +0 -0
tokenizer_config.json +17 -0
trainer_state.json +144 -0
training_args.bin +3 -0

checkpoint-1953/model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7400cbdb1cc8249dd839f5ffe98f4556fcac45d32f2ac7bbc1f240c78e22c427
+size 46781032

checkpoint-1953/optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a4d27c2d4004eb84399da08b05324bb8afe325670480729c209b6e1720f778
+size 88853790

checkpoint-1953/rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:7b55f8eecdb2366444fb635d338c6c2e8aeed3c8770b339a705baf1af3af0965
+size 14709

checkpoint-1953/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:93042e4d76683626f6f0e5dff3455a21baea86355546c98695345d1062b9caa9
+size 1465

checkpoint-1953/tokenizer.json ADDED Viewed

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

checkpoint-1953/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "is_local": false,
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-1953/trainer_state.json ADDED Viewed

	@@ -0,0 +1,66 @@

+{
+  "best_global_step": 1953,
+  "best_metric": 0.07590867578983307,
+  "best_model_checkpoint": "./results_albert_punctuation_casing/checkpoint-1953",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1953,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2560163850486431,
+      "grad_norm": 7.659163475036621,
+      "learning_rate": 1.8296637651476362e-05,
+      "loss": 0.17497076416015625,
+      "step": 500
+    },
+    {
+      "epoch": 0.5120327700972862,
+      "grad_norm": 9.602242469787598,
+      "learning_rate": 1.6589861751152075e-05,
+      "loss": 0.09840100860595703,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7680491551459293,
+      "grad_norm": 2.2302889823913574,
+      "learning_rate": 1.4883085850827787e-05,
+      "loss": 0.08661653137207032,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_casing_accuracy": 0.5982128829536528,
+      "eval_loss": 0.07590867578983307,
+      "eval_overall_accuracy": 0.597888845247447,
+      "eval_punctuation_accuracy": 0.5975648075412412,
+      "eval_runtime": 11.014,
+      "eval_samples_per_second": 709.096,
+      "eval_steps_per_second": 44.398,
+      "step": 1953
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5859,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1953/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:564d1f2f5aef116f928ab806870d35d30703b30b96f0b6e8ba67019dc262c956
+size 5265

checkpoint-3906/model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:29710bfae86de683cfaab56f0be1872477993b2bb922a0bcb8316d9185f496ec
+size 46781032

checkpoint-3906/optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:70446afa570eddb4c5b4440a5fa3832f1c97bc25956520405bf398009e906dc6
+size 88853790

checkpoint-3906/rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:10142afb48383537512bbda75d1a3659f03009b79fddbe13d6a83040da090afc
+size 14709

checkpoint-3906/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef01b065e0b9ef65b0bb44e0c2cfff6ee797121d76aaf2deccd9c953a0a973ca
+size 1465

checkpoint-3906/tokenizer.json ADDED Viewed

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

checkpoint-3906/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "is_local": false,
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-3906/trainer_state.json ADDED Viewed

	@@ -0,0 +1,105 @@

+{
+  "best_global_step": 3906,
+  "best_metric": 0.0746106207370758,
+  "best_model_checkpoint": "./results_albert_punctuation_casing/checkpoint-3906",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3906,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2560163850486431,
+      "grad_norm": 7.659163475036621,
+      "learning_rate": 1.8296637651476362e-05,
+      "loss": 0.17497076416015625,
+      "step": 500
+    },
+    {
+      "epoch": 0.5120327700972862,
+      "grad_norm": 9.602242469787598,
+      "learning_rate": 1.6589861751152075e-05,
+      "loss": 0.09840100860595703,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7680491551459293,
+      "grad_norm": 2.2302889823913574,
+      "learning_rate": 1.4883085850827787e-05,
+      "loss": 0.08661653137207032,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_casing_accuracy": 0.5982128829536528,
+      "eval_loss": 0.07590867578983307,
+      "eval_overall_accuracy": 0.597888845247447,
+      "eval_punctuation_accuracy": 0.5975648075412412,
+      "eval_runtime": 11.014,
+      "eval_samples_per_second": 709.096,
+      "eval_steps_per_second": 44.398,
+      "step": 1953
+    },
+    {
+      "epoch": 1.0240655401945724,
+      "grad_norm": 0.46477240324020386,
+      "learning_rate": 1.3176309950503501e-05,
+      "loss": 0.08205690765380859,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2800819252432156,
+      "grad_norm": 6.8253865242004395,
+      "learning_rate": 1.1469534050179212e-05,
+      "loss": 0.0625931053161621,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5360983102918588,
+      "grad_norm": 3.1819510459899902,
+      "learning_rate": 9.762758149854925e-06,
+      "loss": 0.06253623962402344,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7921146953405018,
+      "grad_norm": 4.698487281799316,
+      "learning_rate": 8.055982249530637e-06,
+      "loss": 0.053002174377441404,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_casing_accuracy": 0.5975058915946583,
+      "eval_loss": 0.0746106207370758,
+      "eval_overall_accuracy": 0.5965730557737627,
+      "eval_punctuation_accuracy": 0.5956402199528672,
+      "eval_runtime": 11.2558,
+      "eval_samples_per_second": 693.865,
+      "eval_steps_per_second": 43.444,
+      "step": 3906
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5859,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3906/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:564d1f2f5aef116f928ab806870d35d30703b30b96f0b6e8ba67019dc262c956
+size 5265

checkpoint-5859/model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0593de29e7a6c178e88a9363450ae261bb62f4a2270ded7bb19bc2611f14a9
+size 46781032

checkpoint-5859/optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cba2752c31dd57eceb7b761ead10a5d9615e3a78a549ffbd7a0f54e5190eb9
+size 88853790

checkpoint-5859/rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc889aeff6d9d6990d071a5d590b5ed43cf56675e6edb53189a2c60098beb746
+size 14709

checkpoint-5859/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:82bc495f0e9d473971fac867a4529e9a1ecda97719ace06ceef20966f1cc19ea
+size 1465

checkpoint-5859/tokenizer.json ADDED Viewed

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

checkpoint-5859/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "is_local": false,
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-5859/trainer_state.json ADDED Viewed

	@@ -0,0 +1,144 @@

+{
+  "best_global_step": 3906,
+  "best_metric": 0.0746106207370758,
+  "best_model_checkpoint": "./results_albert_punctuation_casing/checkpoint-3906",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5859,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2560163850486431,
+      "grad_norm": 7.659163475036621,
+      "learning_rate": 1.8296637651476362e-05,
+      "loss": 0.17497076416015625,
+      "step": 500
+    },
+    {
+      "epoch": 0.5120327700972862,
+      "grad_norm": 9.602242469787598,
+      "learning_rate": 1.6589861751152075e-05,
+      "loss": 0.09840100860595703,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7680491551459293,
+      "grad_norm": 2.2302889823913574,
+      "learning_rate": 1.4883085850827787e-05,
+      "loss": 0.08661653137207032,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_casing_accuracy": 0.5982128829536528,
+      "eval_loss": 0.07590867578983307,
+      "eval_overall_accuracy": 0.597888845247447,
+      "eval_punctuation_accuracy": 0.5975648075412412,
+      "eval_runtime": 11.014,
+      "eval_samples_per_second": 709.096,
+      "eval_steps_per_second": 44.398,
+      "step": 1953
+    },
+    {
+      "epoch": 1.0240655401945724,
+      "grad_norm": 0.46477240324020386,
+      "learning_rate": 1.3176309950503501e-05,
+      "loss": 0.08205690765380859,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2800819252432156,
+      "grad_norm": 6.8253865242004395,
+      "learning_rate": 1.1469534050179212e-05,
+      "loss": 0.0625931053161621,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5360983102918588,
+      "grad_norm": 3.1819510459899902,
+      "learning_rate": 9.762758149854925e-06,
+      "loss": 0.06253623962402344,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7921146953405018,
+      "grad_norm": 4.698487281799316,
+      "learning_rate": 8.055982249530637e-06,
+      "loss": 0.053002174377441404,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_casing_accuracy": 0.5975058915946583,
+      "eval_loss": 0.0746106207370758,
+      "eval_overall_accuracy": 0.5965730557737627,
+      "eval_punctuation_accuracy": 0.5956402199528672,
+      "eval_runtime": 11.2558,
+      "eval_samples_per_second": 693.865,
+      "eval_steps_per_second": 43.444,
+      "step": 3906
+    },
+    {
+      "epoch": 2.048131080389145,
+      "grad_norm": 0.29059869050979614,
+      "learning_rate": 6.349206349206349e-06,
+      "loss": 0.057237117767333985,
+      "step": 4000
+    },
+    {
+      "epoch": 2.3041474654377883,
+      "grad_norm": 1.9593513011932373,
+      "learning_rate": 4.642430448882062e-06,
+      "loss": 0.03903835678100586,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5601638504864312,
+      "grad_norm": 4.75918436050415,
+      "learning_rate": 2.9356545485577746e-06,
+      "loss": 0.03857281112670898,
+      "step": 5000
+    },
+    {
+      "epoch": 2.8161802355350742,
+      "grad_norm": 1.5033795833587646,
+      "learning_rate": 1.228878648233487e-06,
+      "loss": 0.03791716384887695,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_casing_accuracy": 0.5970542026708563,
+      "eval_loss": 0.07589453458786011,
+      "eval_overall_accuracy": 0.5967596229379419,
+      "eval_punctuation_accuracy": 0.5964650432050275,
+      "eval_runtime": 11.3344,
+      "eval_samples_per_second": 689.056,
+      "eval_steps_per_second": 43.143,
+      "step": 5859
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5859,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5859/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:564d1f2f5aef116f928ab806870d35d30703b30b96f0b6e8ba67019dc262c956
+size 5265

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0593de29e7a6c178e88a9363450ae261bb62f4a2270ded7bb19bc2611f14a9
+size 46781032

optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cba2752c31dd57eceb7b761ead10a5d9615e3a78a549ffbd7a0f54e5190eb9
+size 88853790

rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc889aeff6d9d6990d071a5d590b5ed43cf56675e6edb53189a2c60098beb746
+size 14709

runs/Mar28_13-58-32_6078593f7de5/events.out.tfevents.1774706312.6078593f7de5.7992.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7a21151d221884ff4261a4a96a55175e7fc0b3f896c5f23eed46a5926d41c1
+size 7650

scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:82bc495f0e9d473971fac867a4529e9a1ecda97719ace06ceef20966f1cc19ea
+size 1465

tokenizer.json ADDED Viewed

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "is_local": false,
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,144 @@

+{
+  "best_global_step": 3906,
+  "best_metric": 0.0746106207370758,
+  "best_model_checkpoint": "./results_albert_punctuation_casing/checkpoint-3906",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5859,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2560163850486431,
+      "grad_norm": 7.659163475036621,
+      "learning_rate": 1.8296637651476362e-05,
+      "loss": 0.17497076416015625,
+      "step": 500
+    },
+    {
+      "epoch": 0.5120327700972862,
+      "grad_norm": 9.602242469787598,
+      "learning_rate": 1.6589861751152075e-05,
+      "loss": 0.09840100860595703,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7680491551459293,
+      "grad_norm": 2.2302889823913574,
+      "learning_rate": 1.4883085850827787e-05,
+      "loss": 0.08661653137207032,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_casing_accuracy": 0.5982128829536528,
+      "eval_loss": 0.07590867578983307,
+      "eval_overall_accuracy": 0.597888845247447,
+      "eval_punctuation_accuracy": 0.5975648075412412,
+      "eval_runtime": 11.014,
+      "eval_samples_per_second": 709.096,
+      "eval_steps_per_second": 44.398,
+      "step": 1953
+    },
+    {
+      "epoch": 1.0240655401945724,
+      "grad_norm": 0.46477240324020386,
+      "learning_rate": 1.3176309950503501e-05,
+      "loss": 0.08205690765380859,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2800819252432156,
+      "grad_norm": 6.8253865242004395,
+      "learning_rate": 1.1469534050179212e-05,
+      "loss": 0.0625931053161621,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5360983102918588,
+      "grad_norm": 3.1819510459899902,
+      "learning_rate": 9.762758149854925e-06,
+      "loss": 0.06253623962402344,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7921146953405018,
+      "grad_norm": 4.698487281799316,
+      "learning_rate": 8.055982249530637e-06,
+      "loss": 0.053002174377441404,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_casing_accuracy": 0.5975058915946583,
+      "eval_loss": 0.0746106207370758,
+      "eval_overall_accuracy": 0.5965730557737627,
+      "eval_punctuation_accuracy": 0.5956402199528672,
+      "eval_runtime": 11.2558,
+      "eval_samples_per_second": 693.865,
+      "eval_steps_per_second": 43.444,
+      "step": 3906
+    },
+    {
+      "epoch": 2.048131080389145,
+      "grad_norm": 0.29059869050979614,
+      "learning_rate": 6.349206349206349e-06,
+      "loss": 0.057237117767333985,
+      "step": 4000
+    },
+    {
+      "epoch": 2.3041474654377883,
+      "grad_norm": 1.9593513011932373,
+      "learning_rate": 4.642430448882062e-06,
+      "loss": 0.03903835678100586,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5601638504864312,
+      "grad_norm": 4.75918436050415,
+      "learning_rate": 2.9356545485577746e-06,
+      "loss": 0.03857281112670898,
+      "step": 5000
+    },
+    {
+      "epoch": 2.8161802355350742,
+      "grad_norm": 1.5033795833587646,
+      "learning_rate": 1.228878648233487e-06,
+      "loss": 0.03791716384887695,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_casing_accuracy": 0.5970542026708563,
+      "eval_loss": 0.07589453458786011,
+      "eval_overall_accuracy": 0.5967596229379419,
+      "eval_punctuation_accuracy": 0.5964650432050275,
+      "eval_runtime": 11.3344,
+      "eval_samples_per_second": 689.056,
+      "eval_steps_per_second": 43.143,
+      "step": 5859
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5859,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 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 sha256:564d1f2f5aef116f928ab806870d35d30703b30b96f0b6e8ba67019dc262c956
+size 5265