Training in progress, step 125

config.json

@@ -3,8 +3,10 @@
   "architectures": [
     "MistralForSequenceClassification"
   ],
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "head_dim": 48,
   "hidden_act": "silu",
   "hidden_size": 768,
   "initializer_range": 0.02,
@@ -20,7 +22,7 @@
   "sliding_window": 768,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c3d9e4c849616fb721fa88f241470c321c56c0f1ad30d540075740237e784f
+oid sha256:1e02d7fb650b0d80e4b4c573b72abb01167d69aeda6ca8c733ba34ef89c4bbbb
 size 239899848

tokenizer.json

@@ -36,23 +36,13 @@
       "special": true
     }
   ],
-  "normalizer": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
-      {
-        "type": "Replace",
-        "pattern": {
-          "String": " "
-        },
-        "content": "▁"
-      }
-    ]
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
   },
-  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
@@ -139,6 +129,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -1,4 +1,7 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -29,8 +32,8 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
-  "max_length": 30000,
+  "legacy": false,
+  "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
   "pad_to_multiple_of": null,
   "pad_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2bb060d61518375f44121ee4894d0fc41e84753f635b4c2502ca6d8770b8f1
-size 4536
+oid sha256:e74ef77809653d0f2da60c9bed7aed627936675cd46d134fdae657da36847a97
+size 5176