End of training

.gitattributes

@@ -32,3 +32,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,16 @@
+{
+    "eval_HasAns_exact": 71.86234817813765,
+    "eval_HasAns_f1": 77.47654791050284,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 68.27586206896552,
+    "eval_NoAns_f1": 68.27586206896552,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 70.06653752210899,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 72.86961812629183,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 70.06653752210899,
+    "eval_f1": 72.86961812629174,
+    "eval_samples": 12458,
+    "eval_total": 11873
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Atnafu/mt5-base-squad2-fin",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "eval_HasAns_exact": 71.86234817813765,
+    "eval_HasAns_f1": 77.47654791050284,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 68.27586206896552,
+    "eval_NoAns_f1": 68.27586206896552,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 70.06653752210899,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 72.86961812629183,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 70.06653752210899,
+    "eval_f1": 72.86961812629174,
+    "eval_samples": 12458,
+    "eval_total": 11873
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ee5c5022e02547088b7074da8f3c156b00e2bbab91041d6a005460bb201ac0
+size 2329702453

runs/Mar15_10-06-06_7f786f353413/events.out.tfevents.1678875081.7f786f353413.3201.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6268ac46bfb8a09fd24482814f276868eb4ef033f2ad0d79dc66521b5268f68e
+size 696

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2367c5e6ea9fd74eb410302c1e4a85d8cc1a017d68ae472c7facdc60d95c32
+size 16315384

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "Atnafu/mt5-base-squad2-fin",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc140fd966fae40d3eb302001a60e35e3db199de8dfd3200c3b375dda3c0cc3a
+size 3771