Upload 15 files

.gitattributes

@@ -32,3 +32,5 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,54 @@
 ---
-license: mit
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: indic-mALBERT-uncased
+  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. -->
+
+# indic-mALBERT-uncased
+
+This model is a fine-tuned version of [artifacts2/qa/adversarial_qa/indic-mALBERT-uncased-final](https://huggingface.co/artifacts2/qa/adversarial_qa/indic-mALBERT-uncased-final) on the squad_v2 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 814
+- num_epochs: 5.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.29.2
+- Pytorch 1.9.0+cu102
+- Datasets 2.12.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 5.0,
+    "eval_HasAns_exact": 53.54251012145749,
+    "eval_HasAns_f1": 63.501893668646716,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 75.10513036164845,
+    "eval_NoAns_f1": 75.10513036164845,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 64.3392571380443,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 69.31181888888628,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 64.3392571380443,
+    "eval_f1": 69.31181888888594,
+    "eval_runtime": 69.5054,
+    "eval_samples": 12000,
+    "eval_samples_per_second": 172.649,
+    "eval_steps_per_second": 5.395,
+    "eval_total": 11873,
+    "total_train_time(min)": 157.643,
+    "train_loss": 0.08469501011414156,
+    "train_runtime": 9458.5775,
+    "train_samples": 130898,
+    "train_samples_per_second": 69.195,
+    "train_steps_per_second": 2.163
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "artifacts2/qa/adversarial_qa/indic-mALBERT-uncased-final",
+  "architectures": [
+    "AlbertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "vocab_size": 200000
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1837a7746dc9d86c0bdb098117540f0ce1eb17713a7250c74fa0500ef6cb37f
+size 47775132

eval_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 5.0,
+    "eval_HasAns_exact": 53.54251012145749,
+    "eval_HasAns_f1": 63.501893668646716,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 75.10513036164845,
+    "eval_NoAns_f1": 75.10513036164845,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 64.3392571380443,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 69.31181888888628,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 64.3392571380443,
+    "eval_f1": 69.31181888888594,
+    "eval_runtime": 69.5054,
+    "eval_samples": 12000,
+    "eval_samples_per_second": 172.649,
+    "eval_steps_per_second": 5.395,
+    "eval_total": 11873
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5522653c1df356658938e9694dd5e161a02c4b62b1be9bae2d4d458e7045ea5
+size 131430551

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1173c2b6e144a02c001e289a05b5dbefddf247c50d4dcf42633158b2968fcb
+size 5646064

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf1da21c98d020b05be447c9af0a3ae2dada8b03a5be91344ccc5fb1284157e
+size 15273367

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_train_time(min)": 157.643,
+    "train_loss": 0.08469501011414156,
+    "train_runtime": 9458.5775,
+    "train_samples": 130898,
+    "train_samples_per_second": 69.195,
+    "train_steps_per_second": 2.163
+}

trainer_state.json

@@ -0,0 +1,155 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 20455,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.500229112570643e-05,
+      "loss": 0.2994,
+      "step": 4091
+    },
+    {
+      "epoch": 1.0,
+      "eval_HasAns_exact": 50.77597840755735,
+      "eval_HasAns_f1": 59.77609298252823,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 78.60386879730866,
+      "eval_NoAns_f1": 78.60386879730866,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 64.7098458687779,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 69.20345988380656,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 64.7098458687779,
+      "eval_f1": 69.20345988380627,
+      "eval_runtime": 69.4653,
+      "eval_samples_per_second": 172.748,
+      "eval_steps_per_second": 5.398,
+      "eval_total": 11873,
+      "step": 4091
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.875515503283947e-05,
+      "loss": 0.0681,
+      "step": 8182
+    },
+    {
+      "epoch": 2.0,
+      "eval_HasAns_exact": 54.97638326585695,
+      "eval_HasAns_f1": 66.01412319490598,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 68.04037005887301,
+      "eval_NoAns_f1": 68.04037005887301,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 61.517729301777145,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 67.02869723737984,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 61.517729301777145,
+      "eval_f1": 67.02869723737946,
+      "eval_runtime": 69.813,
+      "eval_samples_per_second": 171.888,
+      "eval_steps_per_second": 5.371,
+      "eval_total": 11873,
+      "step": 8182
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.2509546357110128e-05,
+      "loss": 0.0373,
+      "step": 12273
+    },
+    {
+      "epoch": 3.0,
+      "eval_HasAns_exact": 52.66531713900135,
+      "eval_HasAns_f1": 63.1366903466774,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 74.23044575273339,
+      "eval_NoAns_f1": 74.23044575273339,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 63.46332013812853,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 68.6915101806715,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 63.46332013812853,
+      "eval_f1": 68.6915101806711,
+      "eval_runtime": 69.5169,
+      "eval_samples_per_second": 172.62,
+      "eval_steps_per_second": 5.394,
+      "eval_total": 11873,
+      "step": 12273
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.262410264243165e-06,
+      "loss": 0.0144,
+      "step": 16364
+    },
+    {
+      "epoch": 4.0,
+      "eval_HasAns_exact": 53.07017543859649,
+      "eval_HasAns_f1": 63.174613714318006,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 74.88645920941968,
+      "eval_NoAns_f1": 74.88645920941968,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 63.99393582076981,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 69.03892108974036,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 63.99393582076981,
+      "eval_f1": 69.03892108973986,
+      "eval_runtime": 69.3973,
+      "eval_samples_per_second": 172.917,
+      "eval_steps_per_second": 5.404,
+      "eval_total": 11873,
+      "step": 16364
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.3746754238582558e-08,
+      "loss": 0.0043,
+      "step": 20455
+    },
+    {
+      "epoch": 5.0,
+      "eval_HasAns_exact": 53.54251012145749,
+      "eval_HasAns_f1": 63.501893668646716,
+      "eval_HasAns_total": 5928,
+      "eval_NoAns_exact": 75.10513036164845,
+      "eval_NoAns_f1": 75.10513036164845,
+      "eval_NoAns_total": 5945,
+      "eval_best_exact": 64.3392571380443,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 69.31181888888628,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 64.3392571380443,
+      "eval_f1": 69.31181888888594,
+      "eval_runtime": 69.762,
+      "eval_samples_per_second": 172.014,
+      "eval_steps_per_second": 5.375,
+      "eval_total": 11873,
+      "step": 20455
+    },
+    {
+      "epoch": 5.0,
+      "step": 20455,
+      "total_flos": 1.445362831448064e+16,
+      "train_loss": 0.08469501011414156,
+      "train_runtime": 9458.5775,
+      "train_samples_per_second": 69.195,
+      "train_steps_per_second": 2.163
+    }
+  ],
+  "max_steps": 20455,
+  "num_train_epochs": 5,
+  "total_flos": 1.445362831448064e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a4262a2fb2dab058e3460ff2ccb224e8a0f1a7f2df4ca1cf82ff25acd53e42
+size 4015