Upload task output 0ae1acd6-039d-48a6-a664-b9c3d2722a55

config.json

@@ -1,33 +1,33 @@
 {
   "architectures": [
-    "LlamaForCausalLM"
+    "PhiForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
+  "bos_token_id": 50256,
   "dtype": "bfloat16",
-  "eos_token_id": 2,
-  "head_dim": 64,
-  "hidden_act": "silu",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 5632,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
-  "mlp_bias": false,
-  "model_type": "llama",
+  "model_type": "phi",
   "num_attention_heads": 32,
-  "num_hidden_layers": 22,
-  "num_key_value_heads": 4,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 50256,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
   "rope_parameters": {
+    "partial_rotary_factor": 0.5,
     "rope_theta": 10000.0,
     "rope_type": "default"
   },
   "tie_word_embeddings": false,
   "transformers_version": "5.12.1",
-  "unsloth_version": "2024.9",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 51200
 }

generation_config.json

@@ -1,9 +1,9 @@
 {
-  "bos_token_id": 1,
+  "_from_model_config": true,
+  "bos_token_id": 50256,
   "eos_token_id": [
-    2
+    50256
   ],
-  "max_length": 2048,
-  "pad_token_id": 0,
+  "pad_token_id": 50256,
   "transformers_version": "5.12.1"
 }

loss.txt

@@ -1,26 +1 @@
-120,1.6611337661743164
-140,1.6542129516601562
-160,1.651502251625061
-161,1.6513550281524658
-180,1.682282567024231
-200,1.6810812950134277
-220,1.6784807443618774
-240,1.680466890335083
-260,1.6775115728378296
-280,1.6715326309204102
-300,1.6727244853973389
-320,1.6700555086135864
-322,1.670729160308838
-340,1.8013241291046143
-360,1.8005415201187134
-380,1.8028724193572998
-380,1.6513550281524658
-380,1.6515198945999146
-380,1.6460199356079102
-380,1.6454099416732788
-380,1.640388011932373
-380,1.6403019428253174
-380,1.6407389640808105
-380,1.6412919759750366
-best checkpoint at step 380 (eval_loss=1.6403019428253174)
-final: soup(n=5/8) (dev_loss=1.640302)
+saved checkpoint at step 461 (no_eval)

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a8ffcd25249b3931f60a8704c779a8a21cbc281aad7461d415717010186c2c
-size 2200119864
+oid sha256:f2152a1cc16facf03c25462df5918e7f495f42a6cd1589d21668f6493ffb3ba8
+size 2836579040

tokenizer_config.json

@@ -1,16 +1,14 @@
 {
-  "add_prefix_space": null,
+  "add_prefix_space": false,
   "backend": "tokenizers",
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
   "is_local": true,
   "local_files_only": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<unk>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
 }