Training in progress, epoch 1

config.json

@@ -1,14 +1,14 @@
 {
-  "_name_or_path": "DeepSeek-V3-1B-Test",
+  "_name_or_path": "tonyshark/deepseek-v3-1b",
   "architectures": [
     "DeepseekV3ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
-    "AutoModel": "modeling_deepseek.DeepseekV3Model",
-    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+    "AutoConfig": "tonyshark/deepseek-v3-1b--configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "tonyshark/deepseek-v3-1b--modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "tonyshark/deepseek-v3-1b--modeling_deepseek.DeepseekV3ForCausalLM"
   },
   "aux_loss_alpha": 0.001,
   "bos_token_id": 0,
@@ -54,8 +54,8 @@
   "tie_word_embeddings": false,
   "topk_group": 4,
   "topk_method": "noaux_tc",
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 129280

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9db5309afa023828200507bbe04d1aaff8667510b47b24ac999f340876da1ee
-size 2099235336
+oid sha256:e4d0893b4a6f7ad8282fe4255f087a31b6c0b1f6d95b956cb1d85a85e11fa7e3
+size 4198331024

runs/Jan13_01-01-54_46046415ec16/events.out.tfevents.1736730115.46046415ec16.261.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906a12664fe166fc82b3a97f8ae7993546d54364ee2ab0b60419d4bdc75d9b7b
+size 6719

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 1,
+    "pad_type_id": 0,
+    "pad_token": "<｜end▁of▁sentence｜>"
+  },
   "added_tokens": [
     {
       "id": 0,
@@ -7419,6 +7431,12 @@
           "id": "A",
           "type_id": 0
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "<｜end▁of▁sentence｜>",
+          "type_id": 0
+        }
       }
     ],
     "pair": [
@@ -7434,6 +7452,12 @@
           "type_id": 0
         }
       },
+      {
+        "SpecialToken": {
+          "id": "<｜end▁of▁sentence｜>",
+          "type_id": 0
+        }
+      },
       {
         "SpecialToken": {
           "id": "<｜begin▁of▁sentence｜>",
@@ -7445,6 +7469,12 @@
           "id": "B",
           "type_id": 1
         }
+      },
+      {
+        "SpecialToken": {
+          "id": "<｜end▁of▁sentence｜>",
+          "type_id": 1
+        }
       }
     ],
     "special_tokens": {
@@ -7456,6 +7486,15 @@
         "tokens": [
           "<｜begin▁of▁sentence｜>"
         ]
+      },
+      "<｜end▁of▁sentence｜>": {
+        "id": "<｜end▁of▁sentence｜>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "<｜end▁of▁sentence｜>"
+        ]
       }
     }
   },

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "add_bos_token": true,
-  "add_eos_token": false,
+  "add_eos_token": true,
   "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64839e50b7edf20ea18785ae47789266b16e874589534193bc54617cdebab4c4
+size 5560