Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/bart-large",
+  "_name_or_path": "LLM_Teached_Bart_FromScratch",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ec732f17bafe8d626e1ec4fd822f8429a0db34a7b01a79b597c12658218741
+oid sha256:097b1548535b4ce07238f644e3f9df2582c545b3a363340955b8a57b677f0236
 size 1625426996

runs/Dec14_12-49-58_mgrqu6ctr1702517804785-49zpx/events.out.tfevents.1702529407.mgrqu6ctr1702517804785-49zpx.20588.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a146e41d9f112ee7350db212b79839b1ab64555a8110d2601a0017b9adad2948
+size 5753

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -48,10 +48,14 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 128,
   "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "BartTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c784343ed536a1ec2f12979afdd904ed6d0b07c93bf8d1b5e7a3b14f6e72528
+oid sha256:5b523e99b68fc9d5533bfa1a9ebc8d52c4c7008d7202e20ce51ba8d67c12470a
 size 4475