Add Files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+global_step194526_universal/* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "/fs/archive/share/yulan/data/aa_mini/output/miniyulan-2B-final-stage19-hyw-2/checkpoint-184795-rms_norm",
+  "architectures": [
+    "MiniYuLanModelForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dim_model_base": 1920,
+  "dim_model_base_attn": 64,
+  "dim_model_base_init": null,
+  "dim_model_base_lmh": 1,
+  "dim_model_base_logits": 1920.0,
+  "dim_model_base_lr": 256.0,
+  "down_proj_alpha": 0.03450327796711771,
+  "embed_tokens_alpha": 1,
+  "embedding_ln": false,
+  "embedding_rmsln": false,
+  "eos_token_id": 2,
+  "gate_up_proj_alpha": 0.3651483716701107,
+  "gradient_checkpointing_step": 11,
+  "hidden_act": "silu",
+  "hidden_size": 1920,
+  "hidden_states_shrink": 0.18708286933869706,
+  "init_scale_o": 1,
+  "initializer_range": 5e-05,
+  "input_layernorm_alpha": 1.0,
+  "intermediate_size": 4800,
+  "k_proj_alpha": 0.3651483716701107,
+  "layer_norm_eps": 1e-06,
+  "lm_head_alpha": 1.0,
+  "ln_scale": 1,
+  "max_position_embeddings": 4096,
+  "model_reproduce": "transformer",
+  "model_type": "miniyulan",
+  "norm_alpha": 1.0,
+  "num_attention_heads": 30,
+  "num_epochs_trained_before_this_epoch": 19,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 6,
+  "num_steps_trained_before_this_epoch": 184795,
+  "o_proj_alpha": 0.03450327796711771,
+  "post_attention_layernorm_alpha": 1.0,
+  "q_proj_alpha": 0.3651483716701107,
+  "qk_layernorm": false,
+  "rms_norm_eps": 1e-06,
+  "rms_type": "llama",
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "scale_emb": 10.0,
+  "shrink_alpha": 1,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": false,
+  "use_emb_alpha": true,
+  "use_liger": true,
+  "use_norm_alpha": true,
+  "use_sliding_window": false,
+  "v_proj_alpha": 0.3651483716701107,
+  "vocab_size": 99000,
+  "wesar_weights": true,
+  "z_loss": 0.0001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0385d81e1abc139255726b6ffed93d21a678bd776423c82db068dd9752c23635
+size 4848661852

special_tokens_map.json

@@ -0,0 +1,60 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<reasoning_step>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,82 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "<reasoning_step>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}\n    {% set offset = 1 %}\n{% else %}\n    {% set offset = 0 %}\n{% endif %}\n\n{{ bos_token }}\n{% for message in messages %}\n    {% if (message['role'] == 'user') != (loop.index0 % 2 == offset) %}\n        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n    {% endif %}\n\n    {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}\n{% endfor %}\n\n{% if add_generation_prompt %}\n    {{ '<|start_header_id|>' + 'assistant' + '<|end_header_id|>\n\n' }}\n{% endif %}"
+}

trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0,
+  "eval_steps": 500,
+  "global_step": 0,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+  ],
+  "logging_steps": 3,
+  "max_steps": 0,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 0,
+  "save_steps": "NEED CHANGE",
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0,
+  "train_batch_size": "NEED CHANGE",
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b091a9c9025c7790c7a991a1394f67c8da76d9287da770d886b4a698f5acc51c
+size 10872