Training in progress, step 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "facebook/opt-125m",
+  "base_model_name_or_path": "samoline/tensoralchemistdev01__sv9-with-tokenizer",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -20,12 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
-    "out_proj",
-    "fc2",
+    "up_proj",
     "v_proj",
-    "fc1"
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05686df72045bffebf586dd27939b8096508de77909d902574b3cc3327a6d7e
-size 2673480
+oid sha256:b4e1613b89c1ab22fe70a45711b65ca5ffa67b7e107a5c976ce6e9167c09ab60
+size 25741592

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endofprompt|>": 100276,
+  "<|im_end|>": 100265,
+  "<|im_start|>": 100264
+}

config.json

@@ -1,32 +1,37 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "facebook/opt-125m",
-  "_remove_final_layer_norm": false,
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
+  "_name_or_path": "samoline/tensoralchemistdev01__sv9-with-tokenizer",
   "architectures": [
-    "OPTForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "do_layer_norm_before": true,
-  "dropout": 0.1,
-  "enable_bias": true,
-  "eos_token_id": 2,
-  "ffn_dim": 3072,
-  "hidden_size": 768,
-  "init_std": 0.02,
-  "layer_norm_elementwise_affine": true,
-  "layerdrop": 0.0,
-  "max_position_embeddings": 2048,
-  "model_type": "opt",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "prefix": "</s>",
-  "torch_dtype": "float16",
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
   "transformers_version": "4.46.0",
   "use_cache": false,
-  "vocab_size": 50272,
-  "word_embed_proj_dim": 768
+  "vocab_size": 100263
 }

special_tokens_map.json

@@ -1,29 +1,29 @@
 {
   "bos_token": {
-    "content": "</s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "</s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -1,31 +1,70 @@
 {
-  "add_bos_token": true,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "1": {
-      "content": "<pad>",
+    "100257": {
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "100258": {
+      "content": "<|fim_prefix|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "</s>",
+  "bos_token": "<|endoftext|>",
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "errors": "replace",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "</s>"
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc015c8c2031c5d355137a5eb97fe79b484bf40e500349a764a72b91951b0ed
+oid sha256:6e8b9317c790c50187140ab6cd1817c9b63e921ac3dd381eecb663fb4dbb2f97
 size 6712