Initial model upload

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: PartAI/TookaBERT-Base
+tags:
+- generated_from_trainer
+datasets:
+- IRI2070/PersianSQuAD_v2_fa_tourism_agumented
+model-index:
+- name: trainer_output
+  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. -->
+
+# trainer_output
+
+This model is a fine-tuned version of [PartAI/TookaBERT-Base](https://huggingface.co/PartAI/TookaBERT-Base) on the IRI2070/PersianSQuAD_v2_fa_tourism_agumented 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: 3e-05
+- train_batch_size: 40
+- eval_batch_size: 40
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.0.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.1
+- Tokenizers 0.22.1

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 3.0,
+    "eval_HasAns_exact": 64.67894792886807,
+    "eval_HasAns_f1": 82.43932625167922,
+    "eval_HasAns_total": 9391,
+    "eval_NoAns_exact": 91.40980293077311,
+    "eval_NoAns_f1": 91.40980293077311,
+    "eval_NoAns_total": 1979,
+    "eval_best_exact": 69.34036939313984,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 84.00947342387933,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 69.33157431838171,
+    "eval_f1": 84.00067834912133,
+    "eval_runtime": 187.7647,
+    "eval_samples": 11642,
+    "eval_samples_per_second": 62.003,
+    "eval_steps_per_second": 1.555,
+    "eval_total": 11370,
+    "total_flos": 1.2323538937939968e+17,
+    "train_loss": 0.7285093832974275,
+    "train_runtime": 30100.617,
+    "train_samples": 157210,
+    "train_samples_per_second": 15.668,
+    "train_steps_per_second": 0.392
+}

checkpoint-11793/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 48000
+}

checkpoint-11793/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1919e62ac603260226db94a6cf63f587fc0370524317345e62c34583f186e2
+size 489288488

checkpoint-11793/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178815236e8f5b1cd123cd411a405b7789ecdbfac089136af8ba2e762966c3ea
+size 978696762

checkpoint-11793/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491dee19e01cb60d93136110291e58b4dacf3dd9ae9706c91c2a4ec628d89735
+size 14244

checkpoint-11793/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099a2bad42513a69676e5b3b8e66217f8268cbab0bded8dd0412781397878869
+size 1064

checkpoint-11793/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}

checkpoint-11793/trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 11793,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1271940981938438,
+      "grad_norm": 20.986921310424805,
+      "learning_rate": 2.873060290002544e-05,
+      "loss": 1.7205758056640625,
+      "step": 500
+    },
+    {
+      "epoch": 0.2543881963876876,
+      "grad_norm": 12.114559173583984,
+      "learning_rate": 2.7458661918087002e-05,
+      "loss": 1.1848350830078125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3815822945815314,
+      "grad_norm": 14.860601425170898,
+      "learning_rate": 2.6186720936148565e-05,
+      "loss": 1.0746712646484375,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5087763927753752,
+      "grad_norm": 11.910303115844727,
+      "learning_rate": 2.4914779954210127e-05,
+      "loss": 1.0038060302734375,
+      "step": 2000
+    },
+    {
+      "epoch": 0.635970490969219,
+      "grad_norm": 8.553890228271484,
+      "learning_rate": 2.3642838972271685e-05,
+      "loss": 0.9559959106445313,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7631645891630628,
+      "grad_norm": 9.562394142150879,
+      "learning_rate": 2.2370897990333247e-05,
+      "loss": 0.9281796875,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8903586873569066,
+      "grad_norm": 8.361549377441406,
+      "learning_rate": 2.1098957008394813e-05,
+      "loss": 0.9157453002929687,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0175527855507505,
+      "grad_norm": 7.545825004577637,
+      "learning_rate": 1.9827016026456375e-05,
+      "loss": 0.8658336181640625,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1447468837445942,
+      "grad_norm": 13.105203628540039,
+      "learning_rate": 1.8555075044517934e-05,
+      "loss": 0.6820219116210937,
+      "step": 4500
+    },
+    {
+      "epoch": 1.271940981938438,
+      "grad_norm": 9.773395538330078,
+      "learning_rate": 1.7283134062579496e-05,
+      "loss": 0.6653152465820312,
+      "step": 5000
+    },
+    {
+      "epoch": 1.399135080132282,
+      "grad_norm": 9.450806617736816,
+      "learning_rate": 1.6011193080641058e-05,
+      "loss": 0.6671427612304688,
+      "step": 5500
+    },
+    {
+      "epoch": 1.5263291783261257,
+      "grad_norm": 10.44336223602295,
+      "learning_rate": 1.4739252098702622e-05,
+      "loss": 0.6522406616210937,
+      "step": 6000
+    },
+    {
+      "epoch": 1.6535232765199694,
+      "grad_norm": 10.461090087890625,
+      "learning_rate": 1.3467311116764182e-05,
+      "loss": 0.6547742309570312,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7807173747138134,
+      "grad_norm": 6.990764141082764,
+      "learning_rate": 1.2195370134825746e-05,
+      "loss": 0.6391011352539062,
+      "step": 7000
+    },
+    {
+      "epoch": 1.907911472907657,
+      "grad_norm": 11.571297645568848,
+      "learning_rate": 1.0923429152887306e-05,
+      "loss": 0.6334611206054688,
+      "step": 7500
+    },
+    {
+      "epoch": 2.035105571101501,
+      "grad_norm": 7.267425060272217,
+      "learning_rate": 9.651488170948868e-06,
+      "loss": 0.5740706176757813,
+      "step": 8000
+    },
+    {
+      "epoch": 2.162299669295345,
+      "grad_norm": 20.655519485473633,
+      "learning_rate": 8.37954718901043e-06,
+      "loss": 0.4668221435546875,
+      "step": 8500
+    },
+    {
+      "epoch": 2.2894937674891884,
+      "grad_norm": 8.184877395629883,
+      "learning_rate": 7.107606207071992e-06,
+      "loss": 0.44616903686523435,
+      "step": 9000
+    },
+    {
+      "epoch": 2.4166878656830324,
+      "grad_norm": 10.177411079406738,
+      "learning_rate": 5.8356652251335545e-06,
+      "loss": 0.4526641235351562,
+      "step": 9500
+    },
+    {
+      "epoch": 2.543881963876876,
+      "grad_norm": 13.613941192626953,
+      "learning_rate": 4.563724243195116e-06,
+      "loss": 0.43699600219726564,
+      "step": 10000
+    },
+    {
+      "epoch": 2.67107606207072,
+      "grad_norm": 14.783905982971191,
+      "learning_rate": 3.291783261256678e-06,
+      "loss": 0.4329667663574219,
+      "step": 10500
+    },
+    {
+      "epoch": 2.798270160264564,
+      "grad_norm": 12.480794906616211,
+      "learning_rate": 2.0198422793182395e-06,
+      "loss": 0.4396368408203125,
+      "step": 11000
+    },
+    {
+      "epoch": 2.9254642584584074,
+      "grad_norm": 14.206427574157715,
+      "learning_rate": 7.479012973798015e-07,
+      "loss": 0.4308229064941406,
+      "step": 11500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11793,
+  "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": 1.2323538937939968e+17,
+  "train_batch_size": 40,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-11793/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbbb93dbe3024cc32c87ed48af3b10c31bb46c98c186414f3c18fb0c9e5fded
+size 4728

checkpoint-7862/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 48000
+}

checkpoint-7862/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9253fd2bf199b1fd83bac1c7f69220270df1e35e11c7d4408b0c1460188ce4ab
+size 489288488

checkpoint-7862/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e2362f81d4a696939b3441fdc00749c156429017c2ed9d34c1e8433ea7c75c
+size 978696762

checkpoint-7862/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d836331a67f59cb8beedbcb485c75df009741f93ab8b919fec08d9d7afb16d9e
+size 14244

checkpoint-7862/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c8fb4bf58580f50d20620661da4c965a40c2e07eed540b73f44fe8ea18d80c7
+size 1064

checkpoint-7862/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}

checkpoint-7862/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 7862,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1271940981938438,
+      "grad_norm": 20.986921310424805,
+      "learning_rate": 2.873060290002544e-05,
+      "loss": 1.7205758056640625,
+      "step": 500
+    },
+    {
+      "epoch": 0.2543881963876876,
+      "grad_norm": 12.114559173583984,
+      "learning_rate": 2.7458661918087002e-05,
+      "loss": 1.1848350830078125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3815822945815314,
+      "grad_norm": 14.860601425170898,
+      "learning_rate": 2.6186720936148565e-05,
+      "loss": 1.0746712646484375,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5087763927753752,
+      "grad_norm": 11.910303115844727,
+      "learning_rate": 2.4914779954210127e-05,
+      "loss": 1.0038060302734375,
+      "step": 2000
+    },
+    {
+      "epoch": 0.635970490969219,
+      "grad_norm": 8.553890228271484,
+      "learning_rate": 2.3642838972271685e-05,
+      "loss": 0.9559959106445313,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7631645891630628,
+      "grad_norm": 9.562394142150879,
+      "learning_rate": 2.2370897990333247e-05,
+      "loss": 0.9281796875,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8903586873569066,
+      "grad_norm": 8.361549377441406,
+      "learning_rate": 2.1098957008394813e-05,
+      "loss": 0.9157453002929687,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0175527855507505,
+      "grad_norm": 7.545825004577637,
+      "learning_rate": 1.9827016026456375e-05,
+      "loss": 0.8658336181640625,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1447468837445942,
+      "grad_norm": 13.105203628540039,
+      "learning_rate": 1.8555075044517934e-05,
+      "loss": 0.6820219116210937,
+      "step": 4500
+    },
+    {
+      "epoch": 1.271940981938438,
+      "grad_norm": 9.773395538330078,
+      "learning_rate": 1.7283134062579496e-05,
+      "loss": 0.6653152465820312,
+      "step": 5000
+    },
+    {
+      "epoch": 1.399135080132282,
+      "grad_norm": 9.450806617736816,
+      "learning_rate": 1.6011193080641058e-05,
+      "loss": 0.6671427612304688,
+      "step": 5500
+    },
+    {
+      "epoch": 1.5263291783261257,
+      "grad_norm": 10.44336223602295,
+      "learning_rate": 1.4739252098702622e-05,
+      "loss": 0.6522406616210937,
+      "step": 6000
+    },
+    {
+      "epoch": 1.6535232765199694,
+      "grad_norm": 10.461090087890625,
+      "learning_rate": 1.3467311116764182e-05,
+      "loss": 0.6547742309570312,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7807173747138134,
+      "grad_norm": 6.990764141082764,
+      "learning_rate": 1.2195370134825746e-05,
+      "loss": 0.6391011352539062,
+      "step": 7000
+    },
+    {
+      "epoch": 1.907911472907657,
+      "grad_norm": 11.571297645568848,
+      "learning_rate": 1.0923429152887306e-05,
+      "loss": 0.6334611206054688,
+      "step": 7500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11793,
+  "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": 8.215692625293312e+16,
+  "train_batch_size": 40,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-7862/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbbb93dbe3024cc32c87ed48af3b10c31bb46c98c186414f3c18fb0c9e5fded
+size 4728

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 48000
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0bcd17b2993a4006b5047b04d8714980c2308075b42ec578238bc0bc80b6a8d
+size 92441519

eval_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 3.0,
+    "eval_HasAns_exact": 64.67894792886807,
+    "eval_HasAns_f1": 82.43932625167922,
+    "eval_HasAns_total": 9391,
+    "eval_NoAns_exact": 91.40980293077311,
+    "eval_NoAns_f1": 91.40980293077311,
+    "eval_NoAns_total": 1979,
+    "eval_best_exact": 69.34036939313984,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 84.00947342387933,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 69.33157431838171,
+    "eval_f1": 84.00067834912133,
+    "eval_runtime": 187.7647,
+    "eval_samples": 11642,
+    "eval_samples_per_second": 62.003,
+    "eval_steps_per_second": 1.555,
+    "eval_total": 11370
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1919e62ac603260226db94a6cf63f587fc0370524317345e62c34583f186e2
+size 489288488

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2323538937939968e+17,
+    "train_loss": 0.7285093832974275,
+    "train_runtime": 30100.617,
+    "train_samples": 157210,
+    "train_samples_per_second": 15.668,
+    "train_steps_per_second": 0.392
+}

trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 11793,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1271940981938438,
+      "grad_norm": 20.986921310424805,
+      "learning_rate": 2.873060290002544e-05,
+      "loss": 1.7205758056640625,
+      "step": 500
+    },
+    {
+      "epoch": 0.2543881963876876,
+      "grad_norm": 12.114559173583984,
+      "learning_rate": 2.7458661918087002e-05,
+      "loss": 1.1848350830078125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3815822945815314,
+      "grad_norm": 14.860601425170898,
+      "learning_rate": 2.6186720936148565e-05,
+      "loss": 1.0746712646484375,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5087763927753752,
+      "grad_norm": 11.910303115844727,
+      "learning_rate": 2.4914779954210127e-05,
+      "loss": 1.0038060302734375,
+      "step": 2000
+    },
+    {
+      "epoch": 0.635970490969219,
+      "grad_norm": 8.553890228271484,
+      "learning_rate": 2.3642838972271685e-05,
+      "loss": 0.9559959106445313,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7631645891630628,
+      "grad_norm": 9.562394142150879,
+      "learning_rate": 2.2370897990333247e-05,
+      "loss": 0.9281796875,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8903586873569066,
+      "grad_norm": 8.361549377441406,
+      "learning_rate": 2.1098957008394813e-05,
+      "loss": 0.9157453002929687,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0175527855507505,
+      "grad_norm": 7.545825004577637,
+      "learning_rate": 1.9827016026456375e-05,
+      "loss": 0.8658336181640625,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1447468837445942,
+      "grad_norm": 13.105203628540039,
+      "learning_rate": 1.8555075044517934e-05,
+      "loss": 0.6820219116210937,
+      "step": 4500
+    },
+    {
+      "epoch": 1.271940981938438,
+      "grad_norm": 9.773395538330078,
+      "learning_rate": 1.7283134062579496e-05,
+      "loss": 0.6653152465820312,
+      "step": 5000
+    },
+    {
+      "epoch": 1.399135080132282,
+      "grad_norm": 9.450806617736816,
+      "learning_rate": 1.6011193080641058e-05,
+      "loss": 0.6671427612304688,
+      "step": 5500
+    },
+    {
+      "epoch": 1.5263291783261257,
+      "grad_norm": 10.44336223602295,
+      "learning_rate": 1.4739252098702622e-05,
+      "loss": 0.6522406616210937,
+      "step": 6000
+    },
+    {
+      "epoch": 1.6535232765199694,
+      "grad_norm": 10.461090087890625,
+      "learning_rate": 1.3467311116764182e-05,
+      "loss": 0.6547742309570312,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7807173747138134,
+      "grad_norm": 6.990764141082764,
+      "learning_rate": 1.2195370134825746e-05,
+      "loss": 0.6391011352539062,
+      "step": 7000
+    },
+    {
+      "epoch": 1.907911472907657,
+      "grad_norm": 11.571297645568848,
+      "learning_rate": 1.0923429152887306e-05,
+      "loss": 0.6334611206054688,
+      "step": 7500
+    },
+    {
+      "epoch": 2.035105571101501,
+      "grad_norm": 7.267425060272217,
+      "learning_rate": 9.651488170948868e-06,
+      "loss": 0.5740706176757813,
+      "step": 8000
+    },
+    {
+      "epoch": 2.162299669295345,
+      "grad_norm": 20.655519485473633,
+      "learning_rate": 8.37954718901043e-06,
+      "loss": 0.4668221435546875,
+      "step": 8500
+    },
+    {
+      "epoch": 2.2894937674891884,
+      "grad_norm": 8.184877395629883,
+      "learning_rate": 7.107606207071992e-06,
+      "loss": 0.44616903686523435,
+      "step": 9000
+    },
+    {
+      "epoch": 2.4166878656830324,
+      "grad_norm": 10.177411079406738,
+      "learning_rate": 5.8356652251335545e-06,
+      "loss": 0.4526641235351562,
+      "step": 9500
+    },
+    {
+      "epoch": 2.543881963876876,
+      "grad_norm": 13.613941192626953,
+      "learning_rate": 4.563724243195116e-06,
+      "loss": 0.43699600219726564,
+      "step": 10000
+    },
+    {
+      "epoch": 2.67107606207072,
+      "grad_norm": 14.783905982971191,
+      "learning_rate": 3.291783261256678e-06,
+      "loss": 0.4329667663574219,
+      "step": 10500
+    },
+    {
+      "epoch": 2.798270160264564,
+      "grad_norm": 12.480794906616211,
+      "learning_rate": 2.0198422793182395e-06,
+      "loss": 0.4396368408203125,
+      "step": 11000
+    },
+    {
+      "epoch": 2.9254642584584074,
+      "grad_norm": 14.206427574157715,
+      "learning_rate": 7.479012973798015e-07,
+      "loss": 0.4308229064941406,
+      "step": 11500
+    },
+    {
+      "epoch": 3.0,
+      "step": 11793,
+      "total_flos": 1.2323538937939968e+17,
+      "train_loss": 0.7285093832974275,
+      "train_runtime": 30100.617,
+      "train_samples_per_second": 15.668,
+      "train_steps_per_second": 0.392
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11793,
+  "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": 1.2323538937939968e+17,
+  "train_batch_size": 40,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbbb93dbe3024cc32c87ed48af3b10c31bb46c98c186414f3c18fb0c9e5fded
+size 4728