Training in progress, step 25

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "JackFram/llama-68m",
+  "base_model_name_or_path": "NousResearch/CodeLlama-7b-hf",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
-    "up_proj",
     "o_proj",
-    "down_proj",
+    "up_proj",
     "q_proj",
+    "v_proj",
+    "down_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b06af5f4d674e95da71d8fffbbebfe717c11fbc7ba9acccacaa9c760ce52d64
-size 4525640
+oid sha256:f27c2604d9e7337ab4542f90e0c89242a31d9836ee80ff314eb95bb23d00afed
+size 319876032

config.json

@@ -1,32 +1,33 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "JackFram/llama-68m",
+  "_name_or_path": "NousResearch/CodeLlama-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
+  "auto_map": {
+    "AutoConfig": "NousResearch/CodeLlama-7b-hf--configuration_llama.LlamaConfig",
+    "AutoModel": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaModel",
+    "AutoModelForCausalLM": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaForCausalLM",
+    "AutoModelForSequenceClassification": "NousResearch/CodeLlama-7b-hf--modeling_llama.LlamaForSequenceClassification"
+  },
+  "bos_token_id": 1,
   "eos_token_id": 2,
-  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 768,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "max_position_embeddings": 2048,
-  "mlp_bias": false,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
   "model_type": "llama",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 2,
-  "num_key_value_heads": 12,
-  "pad_token_id": 1,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 1000000,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.46.0",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 32016
 }

special_tokens_map.json

@@ -2,14 +2,14 @@
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -23,7 +23,7 @@
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -1,12 +1,12 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -14,7 +14,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -36,9 +36,7 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "use_fast": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14e530752f6a359422ae7d8a515ed8850b278aab111a89e772d281ad9c894bfc
+oid sha256:10fa75858312944c66542aee6d6a3e31ea121a457c0727d1a86e3c74f020b648
 size 6776