Training in progress, epoch 1

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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-*/

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "ahmeddbahaa/mT5_multilingual_XLSum-finetuned-fa",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "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": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684c7d657c38e0117c13c9f8e3317330a94204f6f3fe499a8ab225f5ed19438e
+size 2329700301

runs/Jun08_17-55-59_d1f93c50154b/1654710986.2403066/events.out.tfevents.1654710986.d1f93c50154b.81.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421f47d97afd811438f7c1ce67220b9689a93400d5e3617443caabfc400f2172
+size 5486

runs/Jun08_17-55-59_d1f93c50154b/events.out.tfevents.1654710986.d1f93c50154b.81.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c2ceb4104d8b686145368c402862d9f7c1849ddb67f8c5b01a2cdb2c38cbc3
+size 3954

runs/Jun08_17-58-07_d1f93c50154b/1654711103.7096794/events.out.tfevents.1654711103.d1f93c50154b.419.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77cd67197bf1cd4cc02b3c45e935fae9e448defc1ebea77d289159e4afa7e6ef
+size 5486

runs/Jun08_17-58-07_d1f93c50154b/events.out.tfevents.1654711103.d1f93c50154b.419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb093e2436aa90c0c7a5f90f1b605392b86e756acc06d6903855f4b9e130980
+size 4111

special_tokens_map.json

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

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 sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
+size 16315219

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "ahmeddbahaa/mT5_multilingual_XLSum-finetuned-fa", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44fcb0b511a768c1c30ad3139253373514eab541699e96adb1a4258a7ecaf72d
+size 3375