Training in progress, epoch 1

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "deepseek-ai/DeepSeek-V2-Lite--configuration_deepseek.DeepseekV2Config",
+    "AutoModel": "deepseek-ai/DeepSeek-V2-Lite--modeling_deepseek.DeepseekV2Model",
+    "AutoModelForCausalLM": "deepseek-ai/DeepSeek-V2-Lite--modeling_deepseek.DeepseekV2ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 1408,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 27,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "q_lora_rank": null,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 0.707,
+    "mscale_all_dim": 0.707,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": false,
+  "v_head_dim": 128,
+  "vocab_size": 102400
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9dad2a27a6507faaed8ce5d409eabfe61dba3412e80c261c8326f6bf5eec44d
+size 4994763632

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a0086eeb53e82250b86b5b96e41a840d421e9ff2a6ac44966e29d4db488a63
+size 4995044944

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a9e149bfc70cdc8b648f4e59c8d22d4bc08fc907551ea358b8d917e22df6fff
+size 4996085000

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ffa8bb7873a87a4ccafeb6a5f63ef08d9a05dc04796c9af11a9aaa430550fa
+size 4996085224

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f890b766a271ed62c5e5bc49e4df2609479e4ff408ac970b281f4fd7d551ad
+size 4996085224

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb55f0c43e76af1d27e53977553ebcbb583d0f681c444a7724211cc3d9aaf3c5
+size 4995045792

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76af3c6573acd78f0edf67a9e7f4a9909014019e747d87daadfdc996034cae8
+size 1440515736

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<｜end▁of▁sentence｜>"
+}

tokenizer_config.json

@@ -0,0 +1,36 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "fast_tokenizer": true,
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

training.log

@@ -0,0 +1,422 @@
+2025-09-23 11:39:33 - INFO - __main__ - Model parameters ModelConfig(model_name_or_path='deepseek-ai/DeepSeek-V2-Lite', model_revision='main', torch_dtype='bfloat16', trust_remote_code=True, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, lora_task_type='CAUSAL_LM', use_rslora=False, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False)
+2025-09-23 11:39:33 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='fw407/Commonsense-15K', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False)
+2025-09-23 11:39:33 - INFO - __main__ - Training parameters SFTConfig(
+_n_gpu=1,
+accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+average_tokens_across_devices=False,
+batch_eval_metrics=False,
+benchmarks=[],
+bf16=True,
+bf16_full_eval=False,
+callbacks=[],
+chars_per_token=<CHARS_PER_TOKEN>,
+chat_template=None,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+dataset_batch_size=None,
+dataset_kwargs=None,
+dataset_num_proc=None,
+dataset_text_field=text,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800000000,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+do_eval=True,
+do_predict=False,
+do_train=False,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_on_start=False,
+eval_packing=None,
+eval_steps=None,
+eval_strategy=IntervalStrategy.NO,
+eval_use_gather_object=False,
+fp16=False,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+gradient_accumulation_steps=1,
+gradient_checkpointing=False,
+gradient_checkpointing_kwargs={'use_reentrant': False},
+greater_is_better=None,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=DeepSeek-V2-Lite-sft-commonsense15k,
+hub_model_revision=main,
+hub_private_repo=None,
+hub_strategy=HubStrategy.EVERY_SAVE,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_for_metrics=[],
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=1e-05,
+length_column_name=length,
+load_best_model_at_end=False,
+local_rank=0,
+log_level=info,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=/tmp/data/DeepSeek-V2-Lite/sft/commonsense15k/runs/Sep23_11-39-32_orchard-flame-14,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=1,
+logging_strategy=IntervalStrategy.STEPS,
+lr_scheduler_kwargs={'min_lr_rate': 0.1},
+lr_scheduler_type=SchedulerType.COSINE_WITH_MIN_LR,
+max_grad_norm=1.0,
+max_length=2048,
+max_seq_length=None,
+max_steps=-1,
+metric_for_best_model=None,
+model_init_kwargs=None,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_of_sequences=None,
+num_train_epochs=3,
+optim=OptimizerNames.ADAMW_TORCH,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/tmp/data/DeepSeek-V2-Lite/sft/commonsense15k,
+overwrite_hub_revision=False,
+overwrite_output_dir=True,
+packing=False,
+past_index=-1,
+per_device_eval_batch_size=16,
+per_device_train_batch_size=16,
+prediction_loss_only=False,
+push_to_hub=True,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_revision=False,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=True,
+report_to=['wandb'],
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+run_name=/tmp/data/DeepSeek-V2-Lite/sft/commonsense15k,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=500,
+save_strategy=SaveStrategy.EPOCH,
+save_total_limit=3,
+seed=1234,
+skip_memory_metrics=True,
+system_prompt=None,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torch_empty_cache_steps=None,
+torchdynamo=None,
+tp_size=0,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_liger=False,
+use_liger_kernel=False,
+use_mps_device=False,
+wandb_entity=None,
+wandb_project=None,
+warmup_ratio=0.1,
+warmup_steps=0,
+weight_decay=0.0,
+)
+2025-09-23 11:39:35 - INFO - __main__ - *** Initializing model kwargs ***
+2025-09-23 11:41:35 - INFO - __main__ - *** Train ***
+2025-09-23 11:41:35 - INFO - __main__ - DeepseekV2ForCausalLM(
+  (model): DeepseekV2Model(
+    (embed_tokens): Embedding(102400, 2048)
+    (layers): ModuleList(
+      (0): DeepseekV2DecoderLayer(
+        (self_attn): DeepseekV2FlashAttention2(
+          (q_proj): Linear(in_features=2048, out_features=3072, bias=False)
+          (kv_a_proj_with_mqa): Linear(in_features=2048, out_features=576, bias=False)
+          (kv_a_layernorm): DeepseekV2RMSNorm()
+          (kv_b_proj): Linear(in_features=512, out_features=4096, bias=False)
+          (o_proj): Linear(in_features=2048, out_features=2048, bias=False)
+          (rotary_emb): DeepseekV2YarnRotaryEmbedding()
+        )
+        (mlp): DeepseekV2MLP(
+          (gate_proj): Linear(in_features=2048, out_features=10944, bias=False)
+          (up_proj): Linear(in_features=2048, out_features=10944, bias=False)
+          (down_proj): Linear(in_features=10944, out_features=2048, bias=False)
+          (act_fn): SiLU()
+        )
+        (input_layernorm): DeepseekV2RMSNorm()
+        (post_attention_layernorm): DeepseekV2RMSNorm()
+      )
+      (1-26): 26 x DeepseekV2DecoderLayer(
+        (self_attn): DeepseekV2FlashAttention2(
+          (q_proj): Linear(in_features=2048, out_features=3072, bias=False)
+          (kv_a_proj_with_mqa): Linear(in_features=2048, out_features=576, bias=False)
+          (kv_a_layernorm): DeepseekV2RMSNorm()
+          (kv_b_proj): Linear(in_features=512, out_features=4096, bias=False)
+          (o_proj): Linear(in_features=2048, out_features=2048, bias=False)
+          (rotary_emb): DeepseekV2YarnRotaryEmbedding()
+        )
+        (mlp): DeepseekV2MoE(
+          (experts): ModuleList(
+            (0-63): 64 x DeepseekV2MLP(
+              (gate_proj): Linear(in_features=2048, out_features=1408, bias=False)
+              (up_proj): Linear(in_features=2048, out_features=1408, bias=False)
+              (down_proj): Linear(in_features=1408, out_features=2048, bias=False)
+              (act_fn): SiLU()
+            )
+          )
+          (gate): MoEGate()
+          (shared_experts): DeepseekV2MLP(
+            (gate_proj): Linear(in_features=2048, out_features=2816, bias=False)
+            (up_proj): Linear(in_features=2048, out_features=2816, bias=False)
+            (down_proj): Linear(in_features=2816, out_features=2048, bias=False)
+            (act_fn): SiLU()
+          )
+        )
+        (input_layernorm): DeepseekV2RMSNorm()
+        (post_attention_layernorm): DeepseekV2RMSNorm()
+      )
+    )
+    (norm): DeepseekV2RMSNorm()
+  )
+  (lm_head): Linear(in_features=2048, out_features=102400, bias=False)
+)
+2025-09-23 11:51:22 - INFO - __main__ - Model parameters ModelConfig(model_name_or_path='deepseek-ai/DeepSeek-V2-Lite', model_revision='main', torch_dtype='bfloat16', trust_remote_code=True, attn_implementation='flash_attention_2', use_peft=False, lora_r=16, lora_alpha=32, lora_dropout=0.05, lora_target_modules=None, lora_modules_to_save=None, lora_task_type='CAUSAL_LM', use_rslora=False, load_in_8bit=False, load_in_4bit=False, bnb_4bit_quant_type='nf4', use_bnb_nested_quant=False)
+2025-09-23 11:51:22 - INFO - __main__ - Script parameters ScriptArguments(dataset_name='fw407/Commonsense-15K', dataset_config=None, dataset_train_split='train', dataset_test_split='test', gradient_checkpointing_use_reentrant=False, ignore_bias_buffers=False)
+2025-09-23 11:51:22 - INFO - __main__ - Training parameters SFTConfig(
+_n_gpu=1,
+accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+auto_find_batch_size=False,
+average_tokens_across_devices=False,
+batch_eval_metrics=False,
+benchmarks=[],
+bf16=True,
+bf16_full_eval=False,
+callbacks=[],
+chars_per_token=<CHARS_PER_TOKEN>,
+chat_template=None,
+data_seed=None,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_persistent_workers=False,
+dataloader_pin_memory=True,
+dataloader_prefetch_factor=None,
+dataset_batch_size=None,
+dataset_kwargs=None,
+dataset_num_proc=None,
+dataset_text_field=text,
+ddp_backend=None,
+ddp_broadcast_buffers=None,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+ddp_timeout=1800000000,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+do_eval=True,
+do_predict=False,
+do_train=False,
+eval_accumulation_steps=None,
+eval_delay=0,
+eval_do_concat_batches=True,
+eval_on_start=False,
+eval_packing=None,
+eval_steps=None,
+eval_strategy=IntervalStrategy.NO,
+eval_use_gather_object=False,
+fp16=False,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+fsdp=[],
+fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
+fsdp_min_num_params=0,
+fsdp_transformer_layer_cls_to_wrap=None,
+full_determinism=False,
+gradient_accumulation_steps=1,
+gradient_checkpointing=True,
+gradient_checkpointing_kwargs={'use_reentrant': False},
+greater_is_better=None,
+group_by_length=False,
+half_precision_backend=auto,
+hub_always_push=False,
+hub_model_id=DeepSeek-V2-Lite-sft-commonsense15k,
+hub_model_revision=main,
+hub_private_repo=None,
+hub_strategy=HubStrategy.EVERY_SAVE,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+include_for_metrics=[],
+include_inputs_for_metrics=False,
+include_num_input_tokens_seen=False,
+include_tokens_per_second=False,
+jit_mode_eval=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=1e-05,
+length_column_name=length,
+load_best_model_at_end=False,
+local_rank=0,
+log_level=info,
+log_level_replica=warning,
+log_on_each_node=True,
+logging_dir=/tmp/data/DeepSeek-V2-Lite/sft/commonsense15k/runs/Sep23_11-51-21_orchard-flame-14,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=1,
+logging_strategy=IntervalStrategy.STEPS,
+lr_scheduler_kwargs={'min_lr_rate': 0.1},
+lr_scheduler_type=SchedulerType.COSINE_WITH_MIN_LR,
+max_grad_norm=1.0,
+max_length=2048,
+max_seq_length=None,
+max_steps=-1,
+metric_for_best_model=None,
+model_init_kwargs=None,
+mp_parameters=,
+neftune_noise_alpha=None,
+no_cuda=False,
+num_of_sequences=None,
+num_train_epochs=3,
+optim=OptimizerNames.ADAMW_TORCH,
+optim_args=None,
+optim_target_modules=None,
+output_dir=/tmp/data/DeepSeek-V2-Lite/sft/commonsense15k,
+overwrite_hub_revision=False,
+overwrite_output_dir=True,
+packing=False,
+past_index=-1,
+per_device_eval_batch_size=16,
+per_device_train_batch_size=16,
+prediction_loss_only=False,
+push_to_hub=True,
+push_to_hub_model_id=None,
+push_to_hub_organization=None,
+push_to_hub_revision=False,
+push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
+ray_scope=last,
+remove_unused_columns=True,
+report_to=['wandb'],
+restore_callback_states_from_checkpoint=False,
+resume_from_checkpoint=None,
+run_name=/tmp/data/DeepSeek-V2-Lite/sft/commonsense15k,
+save_on_each_node=False,
+save_only_model=False,
+save_safetensors=True,
+save_steps=500,
+save_strategy=SaveStrategy.EPOCH,
+save_total_limit=3,
+seed=1234,
+skip_memory_metrics=True,
+system_prompt=None,
+tf32=None,
+torch_compile=False,
+torch_compile_backend=None,
+torch_compile_mode=None,
+torch_empty_cache_steps=None,
+torchdynamo=None,
+tp_size=0,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_cpu=False,
+use_ipex=False,
+use_legacy_prediction_loop=False,
+use_liger=False,
+use_liger_kernel=False,
+use_mps_device=False,
+wandb_entity=None,
+wandb_project=None,
+warmup_ratio=0.1,
+warmup_steps=0,
+weight_decay=0.0,
+)
+2025-09-23 11:51:24 - INFO - __main__ - *** Initializing model kwargs ***
+2025-09-23 11:52:43 - INFO - __main__ - *** Train ***
+2025-09-23 11:52:43 - INFO - __main__ - DeepseekV2ForCausalLM(
+  (model): DeepseekV2Model(
+    (embed_tokens): Embedding(102400, 2048)
+    (layers): ModuleList(
+      (0): DeepseekV2DecoderLayer(
+        (self_attn): DeepseekV2FlashAttention2(
+          (q_proj): Linear(in_features=2048, out_features=3072, bias=False)
+          (kv_a_proj_with_mqa): Linear(in_features=2048, out_features=576, bias=False)
+          (kv_a_layernorm): DeepseekV2RMSNorm()
+          (kv_b_proj): Linear(in_features=512, out_features=4096, bias=False)
+          (o_proj): Linear(in_features=2048, out_features=2048, bias=False)
+          (rotary_emb): DeepseekV2YarnRotaryEmbedding()
+        )
+        (mlp): DeepseekV2MLP(
+          (gate_proj): Linear(in_features=2048, out_features=10944, bias=False)
+          (up_proj): Linear(in_features=2048, out_features=10944, bias=False)
+          (down_proj): Linear(in_features=10944, out_features=2048, bias=False)
+          (act_fn): SiLU()
+        )
+        (input_layernorm): DeepseekV2RMSNorm()
+        (post_attention_layernorm): DeepseekV2RMSNorm()
+      )
+      (1-26): 26 x DeepseekV2DecoderLayer(
+        (self_attn): DeepseekV2FlashAttention2(
+          (q_proj): Linear(in_features=2048, out_features=3072, bias=False)
+          (kv_a_proj_with_mqa): Linear(in_features=2048, out_features=576, bias=False)
+          (kv_a_layernorm): DeepseekV2RMSNorm()
+          (kv_b_proj): Linear(in_features=512, out_features=4096, bias=False)
+          (o_proj): Linear(in_features=2048, out_features=2048, bias=False)
+          (rotary_emb): DeepseekV2YarnRotaryEmbedding()
+        )
+        (mlp): DeepseekV2MoE(
+          (experts): ModuleList(
+            (0-63): 64 x DeepseekV2MLP(
+              (gate_proj): Linear(in_features=2048, out_features=1408, bias=False)
+              (up_proj): Linear(in_features=2048, out_features=1408, bias=False)
+              (down_proj): Linear(in_features=1408, out_features=2048, bias=False)
+              (act_fn): SiLU()
+            )
+          )
+          (gate): MoEGate()
+          (shared_experts): DeepseekV2MLP(
+            (gate_proj): Linear(in_features=2048, out_features=2816, bias=False)
+            (up_proj): Linear(in_features=2048, out_features=2816, bias=False)
+            (down_proj): Linear(in_features=2816, out_features=2048, bias=False)
+            (act_fn): SiLU()
+          )
+        )
+        (input_layernorm): DeepseekV2RMSNorm()
+        (post_attention_layernorm): DeepseekV2RMSNorm()
+      )
+    )
+    (norm): DeepseekV2RMSNorm()
+  )
+  (lm_head): Linear(in_features=2048, out_features=102400, bias=False)
+)

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6318328df1f5137f775a77b33f6e64e49223aaae843bf6d05f7f85ce4084e775
+size 7544