File size: 3,409 Bytes
572cfa6 b424ef4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | 2025-12-11 16:44:01,560 __main__ <module> [INFO] OUT_DIR set to outputs/2025-12-11/16-44-01
2025-12-11 16:44:01,561 __main__ <module> [INFO] Args: app/src/S3_6_sft.py --sft.per_device_train_batch_size 32 --sft.per_device_eval_batch_size 32 --sft.gradient_accumulation_steps 32 --sft.push_to_hub --mode pre_str --model.model_name_or_path tokyotech-llm/Llama-3.1-Swallow-8B-v0.5
2025-12-11 16:44:02,259 accelerate.utils.modeling get_balanced_memory [INFO] We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk).
2025-12-11 16:44:14,571 __main__ load_model [INFO] Model loaded from tokyotech-llm/Llama-3.1-Swallow-8B-v0.5
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(128256, 4096)
(layers): ModuleList(
(0-31): 32 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear4bit(in_features=4096, out_features=4096, bias=False)
(k_proj): Linear4bit(in_features=4096, out_features=1024, bias=False)
(v_proj): Linear4bit(in_features=4096, out_features=1024, bias=False)
(o_proj): Linear4bit(in_features=4096, out_features=4096, bias=False)
)
(mlp): LlamaMLP(
(gate_proj): Linear4bit(in_features=4096, out_features=14336, bias=False)
(up_proj): Linear4bit(in_features=4096, out_features=14336, bias=False)
(down_proj): Linear4bit(in_features=14336, out_features=4096, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
(post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
)
)
(norm): LlamaRMSNorm((4096,), eps=1e-05)
(rotary_emb): LlamaRotaryEmbedding()
)
(lm_head): Linear(in_features=4096, out_features=128256, bias=False)
)
2025-12-11 16:44:18,359 __main__ load_jwtd [INFO] Dataset shuffled, seed=42
2025-12-11 16:44:18,359 __main__ load_jwtd [INFO] Dataset loaded, N=57062
2025-12-11 16:44:19,509 __main__ load_jwtd [INFO] Dataset loaded, N=12228
2025-12-11 16:44:19,509 __main__ main [INFO] Filtered dataset: train 57062 rows, eval 12228 rows
2025-12-11 16:44:19,516 __main__ add_train_str_with_ratio [INFO] pre_str:posts_str = 57062:0 = 1.000:0.000
2025-12-11 16:44:19,639 __main__ add_train_str_with_ratio [INFO] pre_str:posts_str = 12228:0 = 1.000:0.000
2025-12-11 16:44:34,492 __main__ main [INFO] wandb initialized
2025-12-11 16:44:37,207 __main__ main [INFO] Starting SFT training with SFTTrainer
2025-12-11 16:49:29,186 root evaluate_probability_ratio [INFO] Results epoch 0: outputs/2025-12-11/16-44-01/probability_ratio_epoch_0.json
2025-12-11 17:06:18,971 root evaluate_probability_ratio [INFO] Results epoch 1: outputs/2025-12-11/16-44-01/probability_ratio_epoch_1.json
2025-12-11 17:23:07,666 root evaluate_probability_ratio [INFO] Results epoch 2: outputs/2025-12-11/16-44-01/probability_ratio_epoch_2.json
2025-12-11 17:39:53,894 root evaluate_probability_ratio [INFO] Results epoch 3: outputs/2025-12-11/16-44-01/probability_ratio_epoch_3.json
2025-12-11 17:56:53,639 root evaluate_probability_ratio [INFO] Results epoch 4: outputs/2025-12-11/16-44-01/probability_ratio_epoch_4.json
2025-12-11 18:13:44,741 root evaluate_probability_ratio [INFO] Results epoch 5: outputs/2025-12-11/16-44-01/probability_ratio_epoch_5.json
|