Training in progress, step 200

config.json

@@ -1,29 +1,29 @@
-{
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "head_dim": 64,
-  "hidden_act": "silu",
-  "hidden_size": 256,
-  "initializer_range": 0.02,
-  "intermediate_size": 688,
-  "max_position_embeddings": 64,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 12,
-  "num_key_value_heads": 2,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
-  "use_cache": true,
-  "vocab_size": 32769
-}
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 688,
+  "max_position_embeddings": 64,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32769
+}

generation_config.json

@@ -1,6 +1,6 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.46.2"
-}
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ca17cfdeaf3f180549bc26e5b8ffd3e83a8d4a7fed1485f0bfbc8c15e73dca
+oid sha256:1436d9b9a57e3644525cd8f3eead4c83d5a44197178b2ffbac9f6936dc12bb0e
 size 101948208

special_tokens_map.json

@@ -24,7 +24,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<end_of_sen>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -146,7 +146,7 @@
   "eos_token": "<end_of_sen>",
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<end_of_sen>",
+  "pad_token": "<pad>",
   "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "truncation_side": "right",

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc5ef191448be70d7be891b8b0093fe711bdcce08e851f668b6c540f166cbb9
+size 5240