nohup.out

ggml_init_cublas: found 1 CUDA devices:
  Device 0: NVIDIA A10G, compute capability 8.6
llama_model_loader: loaded meta data with 16 key-value pairs and 291 tensors from llama-2-7b-q5_k_m.gguf (version GGUF V2 (latest))
llama_model_loader: - tensor    0:                token_embd.weight q5_K     [  4096, 32000,     1,     1 ]
llama_model_loader: - tensor    1:               output_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor    2:                    output.weight q6_K     [  4096, 32000,     1,     1 ]
llama_model_loader: - tensor    3:              blk.0.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    4:              blk.0.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    5:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    6:         blk.0.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor    7:            blk.0.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor    8:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor    9:              blk.0.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   10:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   11:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   12:              blk.1.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   13:              blk.1.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   14:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   15:         blk.1.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   16:            blk.1.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   17:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   18:              blk.1.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   19:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   20:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   21:              blk.2.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   22:              blk.2.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   23:              blk.2.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   24:         blk.2.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   25:            blk.2.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   26:            blk.2.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   27:              blk.2.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   28:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   29:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   30:              blk.3.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   31:              blk.3.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   32:              blk.3.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   33:         blk.3.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   34:            blk.3.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   35:            blk.3.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   36:              blk.3.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   37:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   38:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   39:              blk.4.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   40:              blk.4.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   41:              blk.4.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   42:         blk.4.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   43:            blk.4.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   44:            blk.4.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   45:              blk.4.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   46:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   47:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   48:              blk.5.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   49:              blk.5.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   50:              blk.5.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   51:         blk.5.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   52:            blk.5.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   53:            blk.5.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   54:              blk.5.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   55:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   56:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   57:              blk.6.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   58:              blk.6.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   59:              blk.6.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   60:         blk.6.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   61:            blk.6.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   62:            blk.6.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   63:              blk.6.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   64:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   65:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   66:              blk.7.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   67:              blk.7.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   68:              blk.7.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   69:         blk.7.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   70:            blk.7.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   71:            blk.7.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   72:              blk.7.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   73:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   74:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   75:              blk.8.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   76:              blk.8.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   77:              blk.8.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   78:         blk.8.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   79:            blk.8.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   80:            blk.8.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   81:              blk.8.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   82:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   83:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   84:              blk.9.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   85:              blk.9.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   86:              blk.9.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   87:         blk.9.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   88:            blk.9.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   89:            blk.9.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   90:              blk.9.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   91:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   92:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor   93:             blk.10.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   94:             blk.10.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   95:             blk.10.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   96:        blk.10.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor   97:           blk.10.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor   98:           blk.10.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor   99:             blk.10.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  100:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  101:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  102:             blk.11.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  103:             blk.11.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  104:             blk.11.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  105:        blk.11.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  106:           blk.11.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  107:           blk.11.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  108:             blk.11.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  109:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  110:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  111:             blk.12.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  112:             blk.12.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  113:             blk.12.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  114:        blk.12.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  115:           blk.12.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  116:           blk.12.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  117:             blk.12.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  118:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  119:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  120:             blk.13.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  121:             blk.13.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  122:             blk.13.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  123:        blk.13.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  124:           blk.13.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  125:           blk.13.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  126:             blk.13.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  127:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  128:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  129:             blk.14.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  130:             blk.14.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  131:             blk.14.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  132:        blk.14.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  133:           blk.14.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  134:           blk.14.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  135:             blk.14.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  136:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  137:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  138:             blk.15.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  139:             blk.15.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  140:             blk.15.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  141:        blk.15.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  142:           blk.15.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  143:           blk.15.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  144:             blk.15.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  145:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  146:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  147:             blk.16.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  148:             blk.16.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  149:             blk.16.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  150:        blk.16.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  151:           blk.16.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  152:           blk.16.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  153:             blk.16.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  154:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  155:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  156:             blk.17.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  157:             blk.17.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  158:             blk.17.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  159:        blk.17.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  160:           blk.17.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  161:           blk.17.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  162:             blk.17.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  163:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  164:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  165:             blk.18.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  166:             blk.18.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  167:             blk.18.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  168:        blk.18.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  169:           blk.18.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  170:           blk.18.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  171:             blk.18.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  172:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  173:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  174:             blk.19.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  175:             blk.19.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  176:             blk.19.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  177:        blk.19.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  178:           blk.19.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  179:           blk.19.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  180:             blk.19.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  181:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  182:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  183:             blk.20.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  184:             blk.20.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  185:             blk.20.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  186:        blk.20.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  187:           blk.20.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  188:           blk.20.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  189:             blk.20.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  190:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  191:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  192:             blk.21.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  193:             blk.21.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  194:             blk.21.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  195:        blk.21.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  196:           blk.21.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  197:           blk.21.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  198:             blk.21.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  199:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  200:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  201:             blk.22.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  202:             blk.22.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  203:             blk.22.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  204:        blk.22.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  205:           blk.22.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  206:           blk.22.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  207:             blk.22.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  208:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  209:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  210:             blk.23.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  211:             blk.23.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  212:             blk.23.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  213:        blk.23.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  214:           blk.23.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  215:           blk.23.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  216:             blk.23.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  217:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  218:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  219:             blk.24.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  220:             blk.24.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  221:             blk.24.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  222:        blk.24.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  223:           blk.24.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  224:           blk.24.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  225:             blk.24.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  226:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  227:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  228:             blk.25.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  229:             blk.25.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  230:             blk.25.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  231:        blk.25.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  232:           blk.25.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  233:           blk.25.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  234:             blk.25.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  235:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  236:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  237:             blk.26.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  238:             blk.26.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  239:             blk.26.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  240:        blk.26.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  241:           blk.26.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  242:           blk.26.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  243:             blk.26.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  244:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  245:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  246:             blk.27.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  247:             blk.27.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  248:             blk.27.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  249:        blk.27.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  250:           blk.27.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  251:           blk.27.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  252:             blk.27.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  253:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  254:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  255:             blk.28.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  256:             blk.28.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  257:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  258:        blk.28.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  259:           blk.28.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  260:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  261:             blk.28.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  262:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  263:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  264:             blk.29.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  265:             blk.29.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  266:             blk.29.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  267:        blk.29.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  268:           blk.29.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  269:           blk.29.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  270:             blk.29.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  271:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  272:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  273:             blk.30.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  274:             blk.30.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  275:             blk.30.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  276:        blk.30.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  277:           blk.30.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  278:           blk.30.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  279:             blk.30.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  280:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  281:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  282:             blk.31.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  283:             blk.31.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  284:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  285:        blk.31.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]
llama_model_loader: - tensor  286:           blk.31.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  287:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]
llama_model_loader: - tensor  288:             blk.31.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]
llama_model_loader: - tensor  289:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - tensor  290:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]
llama_model_loader: - kv   0:                       general.architecture str     
llama_model_loader: - kv   1:                               general.name str     
llama_model_loader: - kv   2:                       llama.context_length u32     
llama_model_loader: - kv   3:                     llama.embedding_length u32     
llama_model_loader: - kv   4:                          llama.block_count u32     
llama_model_loader: - kv   5:                  llama.feed_forward_length u32     
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32     
llama_model_loader: - kv   7:                 llama.attention.head_count u32     
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32     
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32     
llama_model_loader: - kv  10:                          general.file_type u32     
llama_model_loader: - kv  11:                       tokenizer.ggml.model str     
llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr     
llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr     
llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr     
llama_model_loader: - kv  15:               general.quantization_version u32     
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q5_K:  193 tensors
llama_model_loader: - type q6_K:   33 tensors
llm_load_print_meta: format           = GGUF V2 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = SPM
llm_load_print_meta: n_vocab          = 32000
llm_load_print_meta: n_merges         = 0
llm_load_print_meta: n_ctx_train      = 4096
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 32
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff             = 11008
llm_load_print_meta: freq_base_train  = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: model type       = 7B
llm_load_print_meta: model ftype      = mostly Q5_K - Medium
llm_load_print_meta: model params     = 6.74 B
llm_load_print_meta: model size       = 4.45 GiB (5.68 BPW) 
llm_load_print_meta: general.name   = LLaMA v2
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token  = 13 '<0x0A>'
llm_load_tensors: ggml ctx size =    0.10 MB
llm_load_tensors: using CUDA for GPU acceleration
llm_load_tensors: mem required  = 4560.96 MB
llm_load_tensors: offloading 0 repeating layers to GPU
llm_load_tensors: offloaded 0/35 layers to GPU
llm_load_tensors: VRAM used: 0.00 MB
..................................................................................................
llama_new_context_with_model: n_ctx      = 512
llama_new_context_with_model: freq_base  = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: kv self size  =  256.00 MB
llama_new_context_with_model: compute buffer total size = 76.63 MB
llama_new_context_with_model: VRAM scratch buffer: 70.50 MB
llama_new_context_with_model: total VRAM used: 70.50 MB (model: 0.00 MB, context: 70.50 MB)
main: seed: 1699909515
main: model base = 'llama-2-7b-q5_k_m.gguf'
main: init model
print_params: n_vocab:   32000
print_params: n_ctx:     128
print_params: n_embd:    4096
print_params: n_ff:      11008
print_params: n_head:    32
print_params: n_head_kv: 32
print_params: n_layer:   32
print_params: norm_rms_eps          : 0.000010
print_params: rope_freq_base        : 10000.000000
print_params: rope_freq_scale       : 1.000000
print_lora_params: n_rank_attention_norm : 1
print_lora_params: n_rank_wq             : 4
print_lora_params: n_rank_wk             : 4
print_lora_params: n_rank_wv             : 4
print_lora_params: n_rank_wo             : 4
print_lora_params: n_rank_ffn_norm       : 1
print_lora_params: n_rank_w1             : 4
print_lora_params: n_rank_w2             : 4
print_lora_params: n_rank_w3             : 4
print_lora_params: n_rank_tok_embeddings : 4
print_lora_params: n_rank_norm           : 1
print_lora_params: n_rank_output         : 4
main: total train_iterations 0
main: seen train_samples     0
main: seen train_tokens      0
main: completed train_epochs 0
main: lora_size = 84807904 bytes (80.9 MB)
main: opt_size  = 126592864 bytes (120.7 MB)
main: opt iter 0
main: input_size = 131076128 bytes (125.0 MB)
main: compute_size = 14064566880 bytes (13413.0 MB)
main: evaluation order = RIGHT_TO_LEFT
main: tokenize training data
tokenize_file: warning: found 2 samples (max length 197) that exceed context length of 128. samples will be cut off.
tokenize_file: warning: found 176 samples (min length 22) that are shorter than context length of 128.
tokenize_file: total number of samples: 178
main: number of training tokens: 7605
main: number of unique tokens: 868
main: train data seems to have changed. restarting shuffled epoch.
main: begin training
main: work_size = 1024512 bytes (1.0 MB)
train_opt_callback: iter=     0 sample=1/178 sched=0.000000 loss=0.000000 |->
train_opt_callback: iter=     1 sample=9/178 sched=0.010000 loss=7.328270 dt=00:22:48 eta=4d 00:57:37 |->
train_opt_callback: iter=     2 sample=17/178 sched=0.020000 loss=8.033629 dt=00:22:06 eta=3d 21:33:24 |>
train_opt_callback: iter=     3 sample=25/178 sched=0.030000 loss=7.241049 dt=00:22:01 eta=3d 20:50:38 |-->
train_opt_callback: iter=     4 sample=33/178 sched=0.040000 loss=7.332203 dt=00:22:01 eta=3d 20:31:55 |->
train_opt_callback: iter=     5 sample=41/178 sched=0.050000 loss=6.324121 dt=00:22:06 eta=3d 20:28:16 |----------->
train_opt_callback: iter=     6 sample=49/178 sched=0.060000 loss=6.477211 dt=00:21:48 eta=3d 18:50:01 |---------->
train_opt_callback: iter=     7 sample=57/178 sched=0.070000 loss=6.291273 dt=00:21:33 eta=3d 17:28:16 |----------->
train_opt_callback: iter=     8 sample=65/178 sched=0.080000 loss=5.716275 dt=00:21:31 eta=3d 16:58:39 |----------------->
train_opt_callback: iter=     9 sample=73/178 sched=0.090000 loss=5.227144 dt=00:20:14 eta=3d 11:18:46 |---------------------->
save_checkpoint_lora_file: saving to checkpoint-10.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    10 sample=81/178 sched=0.100000 loss=3.905872 dt=00:20:21 eta=3d 11:29:58 |----------------------------------->
train_opt_callback: iter=    11 sample=89/178 sched=0.110000 loss=4.364841 dt=00:20:18 eta=3d 10:54:52 |------------------------------->
train_opt_callback: iter=    12 sample=97/178 sched=0.120000 loss=3.937706 dt=00:19:51 eta=3d 08:45:23 |----------------------------------->
train_opt_callback: iter=    13 sample=105/178 sched=0.130000 loss=3.677362 dt=00:19:57 eta=3d 08:51:14 |-------------------------------------->
train_opt_callback: iter=    14 sample=113/178 sched=0.140000 loss=3.055107 dt=00:20:02 eta=3d 08:48:46 |-------------------------------------------->
train_opt_callback: iter=    15 sample=121/178 sched=0.150000 loss=2.682614 dt=00:19:53 eta=3d 07:51:55 |----------------------------------------------->
train_opt_callback: iter=    16 sample=129/178 sched=0.160000 loss=2.312799 dt=00:19:23 eta=3d 05:34:55 |--------------------------------------------------->
train_opt_callback: iter=    17 sample=137/178 sched=0.170000 loss=2.060043 dt=00:19:56 eta=3d 07:25:27 |------------------------------------------------------>
train_opt_callback: iter=    18 sample=145/178 sched=0.180000 loss=1.396019 dt=00:19:21 eta=3d 04:47:53 |------------------------------------------------------------>
train_opt_callback: iter=    19 sample=153/178 sched=0.190000 loss=1.361716 dt=00:20:04 eta=3d 07:16:02 |------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-20.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    20 sample=161/178 sched=0.200000 loss=1.122364 dt=00:20:00 eta=3d 06:42:08 |--------------------------------------------------------------->
train_opt_callback: iter=    21 sample=169/178 sched=0.210000 loss=0.910218 dt=00:19:20 eta=3d 03:46:44 |----------------------------------------------------------------->
train_opt_callback: iter=    22 sample=177/178 sched=0.220000 loss=0.621250 dt=00:19:16 eta=3d 03:11:10 |-------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 1
train_opt_callback: iter=    23 sample=1/178 sched=0.230000 loss=0.700246 dt=00:19:57 eta=3d 05:28:50 |------------------------------------------------------------------->
train_opt_callback: iter=    24 sample=9/178 sched=0.240000 loss=0.660297 dt=00:20:08 eta=3d 05:53:15 |-------------------------------------------------------------------->
train_opt_callback: iter=    25 sample=17/178 sched=0.250000 loss=0.512518 dt=00:19:38 eta=3d 03:38:30 |--------------------------------------------------------------------->
train_opt_callback: iter=    26 sample=25/178 sched=0.260000 loss=0.517694 dt=00:18:59 eta=3d 00:49:36 |--------------------------------------------------------------------->
train_opt_callback: iter=    27 sample=33/178 sched=0.270000 loss=0.490942 dt=00:19:42 eta=3d 03:14:53 |--------------------------------------------------------------------->
train_opt_callback: iter=    28 sample=41/178 sched=0.280000 loss=0.361570 dt=00:19:29 eta=3d 02:04:09 |----------------------------------------------------------------------->
train_opt_callback: iter=    29 sample=49/178 sched=0.290000 loss=0.203198 dt=00:19:54 eta=3d 03:18:15 |------------------------------------------------------------------------>
save_checkpoint_lora_file: saving to checkpoint-30.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    30 sample=57/178 sched=0.300000 loss=0.292865 dt=00:19:01 eta=2d 23:38:19 |----------------------------------------------------------------------->
train_opt_callback: iter=    31 sample=65/178 sched=0.310000 loss=0.222613 dt=00:19:52 eta=3d 02:32:32 |------------------------------------------------------------------------>
train_opt_callback: iter=    32 sample=73/178 sched=0.320000 loss=0.316802 dt=00:19:59 eta=3d 02:38:17 |----------------------------------------------------------------------->
train_opt_callback: iter=    33 sample=81/178 sched=0.330000 loss=0.215638 dt=00:20:12 eta=3d 03:05:38 |------------------------------------------------------------------------>
train_opt_callback: iter=    34 sample=89/178 sched=0.340000 loss=0.362912 dt=00:19:53 eta=3d 01:36:27 |----------------------------------------------------------------------->
train_opt_callback: iter=    35 sample=97/178 sched=0.350000 loss=0.246244 dt=00:19:59 eta=3d 01:37:07 |------------------------------------------------------------------------>
train_opt_callback: iter=    36 sample=105/178 sched=0.360000 loss=0.497322 dt=00:19:35 eta=2d 23:50:30 |--------------------------------------------------------------------->
train_opt_callback: iter=    37 sample=113/178 sched=0.370000 loss=0.196620 dt=00:20:08 eta=3d 01:29:45 |------------------------------------------------------------------------>
train_opt_callback: iter=    38 sample=121/178 sched=0.380000 loss=0.306589 dt=00:20:24 eta=3d 02:07:39 |----------------------------------------------------------------------->
train_opt_callback: iter=    39 sample=129/178 sched=0.390000 loss=0.328856 dt=00:20:04 eta=3d 00:36:32 |----------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-40.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    40 sample=137/178 sched=0.400000 loss=0.170141 dt=00:20:12 eta=3d 00:44:45 |------------------------------------------------------------------------->
train_opt_callback: iter=    41 sample=145/178 sched=0.410000 loss=0.230015 dt=00:19:48 eta=2d 22:57:37 |------------------------------------------------------------------------>
train_opt_callback: iter=    42 sample=153/178 sched=0.420000 loss=0.577738 dt=00:19:51 eta=2d 22:49:02 |--------------------------------------------------------------------->
train_opt_callback: iter=    43 sample=161/178 sched=0.430000 loss=0.129285 dt=00:19:13 eta=2d 20:15:05 |------------------------------------------------------------------------->
train_opt_callback: iter=    44 sample=169/178 sched=0.440000 loss=0.355127 dt=00:19:19 eta=2d 20:17:36 |----------------------------------------------------------------------->
train_opt_callback: iter=    45 sample=177/178 sched=0.450000 loss=0.384705 dt=00:19:16 eta=2d 19:47:27 |---------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 2
train_opt_callback: iter=    46 sample=1/178 sched=0.460000 loss=0.239497 dt=00:19:13 eta=2d 19:18:54 |------------------------------------------------------------------------>
train_opt_callback: iter=    47 sample=9/178 sched=0.470000 loss=0.228520 dt=00:18:52 eta=2d 17:45:31 |------------------------------------------------------------------------>
train_opt_callback: iter=    48 sample=17/178 sched=0.480000 loss=0.113592 dt=00:19:51 eta=2d 20:51:04 |------------------------------------------------------------------------->
train_opt_callback: iter=    49 sample=25/178 sched=0.490000 loss=0.388964 dt=00:19:32 eta=2d 19:24:00 |---------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-50.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    50 sample=33/178 sched=0.500000 loss=0.242294 dt=00:19:36 eta=2d 19:19:47 |------------------------------------------------------------------------>
train_opt_callback: iter=    51 sample=41/178 sched=0.510000 loss=0.104918 dt=00:19:19 eta=2d 18:02:58 |------------------------------------------------------------------------->
train_opt_callback: iter=    52 sample=49/178 sched=0.520000 loss=0.132959 dt=00:19:45 eta=2d 19:11:15 |------------------------------------------------------------------------->
train_opt_callback: iter=    53 sample=57/178 sched=0.530000 loss=0.270326 dt=00:19:59 eta=2d 19:36:51 |------------------------------------------------------------------------>
train_opt_callback: iter=    54 sample=65/178 sched=0.540000 loss=0.214551 dt=00:19:51 eta=2d 18:51:20 |------------------------------------------------------------------------>
train_opt_callback: iter=    55 sample=73/178 sched=0.550000 loss=0.227192 dt=00:19:42 eta=2d 18:02:10 |------------------------------------------------------------------------>
train_opt_callback: iter=    56 sample=81/178 sched=0.560000 loss=0.193324 dt=00:19:34 eta=2d 17:15:30 |------------------------------------------------------------------------>
train_opt_callback: iter=    57 sample=89/178 sched=0.570000 loss=0.092658 dt=00:19:42 eta=2d 17:21:29 |------------------------------------------------------------------------->
train_opt_callback: iter=    58 sample=97/178 sched=0.580000 loss=0.288017 dt=00:19:52 eta=2d 17:34:28 |----------------------------------------------------------------------->
train_opt_callback: iter=    59 sample=105/178 sched=0.590000 loss=0.303981 dt=00:19:22 eta=2d 15:36:34 |----------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-60.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    60 sample=113/178 sched=0.600000 loss=0.135095 dt=00:19:02 eta=2d 14:13:25 |------------------------------------------------------------------------->
train_opt_callback: iter=    61 sample=121/178 sched=0.610000 loss=0.103868 dt=00:19:55 eta=2d 16:44:49 |------------------------------------------------------------------------->
train_opt_callback: iter=    62 sample=129/178 sched=0.620000 loss=0.101314 dt=00:19:34 eta=2d 15:18:35 |------------------------------------------------------------------------->
train_opt_callback: iter=    63 sample=137/178 sched=0.630000 loss=0.206111 dt=00:19:36 eta=2d 15:05:07 |------------------------------------------------------------------------>
train_opt_callback: iter=    64 sample=145/178 sched=0.640000 loss=0.238083 dt=00:19:10 eta=2d 13:22:03 |------------------------------------------------------------------------>
train_opt_callback: iter=    65 sample=153/178 sched=0.650000 loss=0.238338 dt=00:19:21 eta=2d 13:38:19 |------------------------------------------------------------------------>
train_opt_callback: iter=    66 sample=161/178 sched=0.660000 loss=0.057109 dt=00:19:45 eta=2d 14:32:54 |-------------------------------------------------------------------------->
train_opt_callback: iter=    67 sample=169/178 sched=0.670000 loss=0.222538 dt=00:19:59 eta=2d 14:57:58 |------------------------------------------------------------------------>
train_opt_callback: iter=    68 sample=177/178 sched=0.680000 loss=0.243102 dt=00:19:50 eta=2d 14:09:54 |------------------------------------------------------------------------>
train_opt_callback: reshuffle samples. completed epochs: 3
train_opt_callback: iter=    69 sample=1/178 sched=0.690000 loss=0.221211 dt=00:19:18 eta=2d 12:12:07 |------------------------------------------------------------------------>
save_checkpoint_lora_file: saving to checkpoint-70.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    70 sample=9/178 sched=0.700000 loss=0.131074 dt=00:20:02 eta=2d 14:07:11 |------------------------------------------------------------------------->
train_opt_callback: iter=    71 sample=17/178 sched=0.710000 loss=0.196565 dt=00:20:10 eta=2d 14:11:15 |------------------------------------------------------------------------>
train_opt_callback: iter=    72 sample=25/178 sched=0.720000 loss=0.136248 dt=00:20:44 eta=2d 15:35:57 |------------------------------------------------------------------------->
train_opt_callback: iter=    73 sample=33/178 sched=0.730000 loss=0.075492 dt=00:19:47 eta=2d 12:21:42 |-------------------------------------------------------------------------->
train_opt_callback: iter=    74 sample=41/178 sched=0.740000 loss=0.062405 dt=00:20:34 eta=2d 14:24:44 |-------------------------------------------------------------------------->
train_opt_callback: iter=    75 sample=49/178 sched=0.750000 loss=0.100914 dt=00:20:27 eta=2d 13:43:23 |------------------------------------------------------------------------->
train_opt_callback: iter=    76 sample=57/178 sched=0.760000 loss=0.179218 dt=00:20:04 eta=2d 12:14:05 |------------------------------------------------------------------------>
train_opt_callback: iter=    77 sample=65/178 sched=0.770000 loss=0.087842 dt=00:20:00 eta=2d 11:40:49 |------------------------------------------------------------------------->
train_opt_callback: iter=    78 sample=73/178 sched=0.780000 loss=0.068578 dt=00:20:27 eta=2d 12:41:37 |-------------------------------------------------------------------------->
train_opt_callback: iter=    79 sample=81/178 sched=0.790000 loss=0.261990 dt=00:20:28 eta=2d 12:23:13 |------------------------------------------------------------------------>
save_checkpoint_lora_file: saving to checkpoint-80.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    80 sample=89/178 sched=0.800000 loss=0.069881 dt=00:20:09 eta=2d 11:06:42 |-------------------------------------------------------------------------->
train_opt_callback: iter=    81 sample=97/178 sched=0.810000 loss=0.109635 dt=00:19:46 eta=2d 09:41:27 |------------------------------------------------------------------------->
train_opt_callback: iter=    82 sample=105/178 sched=0.820000 loss=0.272391 dt=00:19:51 eta=2d 09:34:54 |------------------------------------------------------------------------>
train_opt_callback: iter=    83 sample=113/178 sched=0.830000 loss=0.148119 dt=00:20:06 eta=2d 09:58:26 |------------------------------------------------------------------------->
train_opt_callback: iter=    84 sample=121/178 sched=0.840000 loss=0.086822 dt=00:20:35 eta=2d 11:03:01 |------------------------------------------------------------------------->
train_opt_callback: iter=    85 sample=129/178 sched=0.850000 loss=0.163737 dt=00:20:25 eta=2d 10:13:42 |------------------------------------------------------------------------->
train_opt_callback: iter=    86 sample=137/178 sched=0.860000 loss=0.120277 dt=00:19:35 eta=2d 07:31:11 |------------------------------------------------------------------------->
train_opt_callback: iter=    87 sample=145/178 sched=0.870000 loss=0.109836 dt=00:19:36 eta=2d 07:14:41 |------------------------------------------------------------------------->
train_opt_callback: iter=    88 sample=153/178 sched=0.880000 loss=0.084462 dt=00:24:40 eta=2d 21:06:45 |------------------------------------------------------------------------->
train_opt_callback: iter=    89 sample=161/178 sched=0.890000 loss=0.116081 dt=00:33:20 eta=3d 20:48:09 |------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-90.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=    90 sample=169/178 sched=0.900000 loss=0.148298 dt=00:35:32 eta=4d 02:18:40 |------------------------------------------------------------------------->
train_opt_callback: iter=    91 sample=177/178 sched=0.910000 loss=0.150541 dt=00:36:14 eta=4d 03:40:13 |------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 4
train_opt_callback: iter=    92 sample=1/178 sched=0.920000 loss=0.141938 dt=00:36:22 eta=4d 03:24:30 |------------------------------------------------------------------------->
train_opt_callback: iter=    93 sample=9/178 sched=0.930000 loss=0.110087 dt=00:36:44 eta=4d 03:50:07 |------------------------------------------------------------------------->
train_opt_callback: iter=    94 sample=17/178 sched=0.940000 loss=0.096049 dt=00:36:50 eta=4d 03:27:39 |------------------------------------------------------------------------->
train_opt_callback: iter=    95 sample=25/178 sched=0.950000 loss=0.062458 dt=00:36:49 eta=4d 02:47:38 |-------------------------------------------------------------------------->
train_opt_callback: iter=    96 sample=33/178 sched=0.960000 loss=0.050658 dt=00:36:30 eta=4d 01:22:08 |-------------------------------------------------------------------------->
train_opt_callback: iter=    97 sample=41/178 sched=0.970000 loss=0.131350 dt=00:36:30 eta=4d 00:44:21 |------------------------------------------------------------------------->
train_opt_callback: iter=    98 sample=49/178 sched=0.980000 loss=0.068363 dt=00:36:25 eta=3d 23:55:10 |-------------------------------------------------------------------------->
train_opt_callback: iter=    99 sample=57/178 sched=0.990000 loss=0.066281 dt=00:36:32 eta=3d 23:36:49 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-100.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   100 sample=65/178 sched=0.977975 loss=0.104312 dt=00:36:39 eta=3d 23:19:47 |------------------------------------------------------------------------->
train_opt_callback: iter=   101 sample=73/178 sched=0.977536 loss=0.067689 dt=00:36:36 eta=3d 22:35:05 |-------------------------------------------------------------------------->
train_opt_callback: iter=   102 sample=81/178 sched=0.977093 loss=0.048579 dt=00:36:25 eta=3d 21:28:57 |-------------------------------------------------------------------------->
train_opt_callback: iter=   103 sample=89/178 sched=0.976646 loss=0.077060 dt=00:36:20 eta=3d 20:39:11 |-------------------------------------------------------------------------->
train_opt_callback: iter=   104 sample=97/178 sched=0.976194 loss=0.070578 dt=00:36:27 eta=3d 20:20:47 |-------------------------------------------------------------------------->
train_opt_callback: iter=   105 sample=105/178 sched=0.975738 loss=0.086573 dt=00:36:33 eta=3d 20:01:28 |------------------------------------------------------------------------->
train_opt_callback: iter=   106 sample=113/178 sched=0.975278 loss=0.094845 dt=00:36:18 eta=3d 18:46:37 |------------------------------------------------------------------------->
train_opt_callback: iter=   107 sample=121/178 sched=0.974814 loss=0.104385 dt=00:36:35 eta=3d 18:52:51 |------------------------------------------------------------------------->
train_opt_callback: iter=   108 sample=129/178 sched=0.974346 loss=0.079805 dt=00:36:33 eta=3d 18:11:51 |------------------------------------------------------------------------->
train_opt_callback: iter=   109 sample=137/178 sched=0.973873 loss=0.115604 dt=00:36:27 eta=3d 17:18:30 |------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-110.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   110 sample=145/178 sched=0.973396 loss=0.106835 dt=00:36:14 eta=3d 16:12:18 |------------------------------------------------------------------------->
train_opt_callback: iter=   111 sample=153/178 sched=0.972915 loss=0.108404 dt=00:36:22 eta=3d 15:55:32 |------------------------------------------------------------------------->
train_opt_callback: iter=   112 sample=161/178 sched=0.972430 loss=0.150818 dt=00:36:43 eta=3d 16:08:57 |------------------------------------------------------------------------->
train_opt_callback: iter=   113 sample=169/178 sched=0.971941 loss=0.111072 dt=00:36:30 eta=3d 15:00:24 |------------------------------------------------------------------------->
train_opt_callback: iter=   114 sample=177/178 sched=0.971447 loss=0.176334 dt=00:36:31 eta=3d 14:27:00 |------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 5
train_opt_callback: iter=   115 sample=1/178 sched=0.970950 loss=0.071819 dt=00:36:31 eta=3d 13:49:09 |-------------------------------------------------------------------------->
train_opt_callback: iter=   116 sample=9/178 sched=0.970448 loss=0.089301 dt=00:36:39 eta=3d 13:32:39 |------------------------------------------------------------------------->
train_opt_callback: iter=   117 sample=17/178 sched=0.969942 loss=0.069022 dt=00:36:31 eta=3d 12:37:25 |-------------------------------------------------------------------------->
train_opt_callback: iter=   118 sample=25/178 sched=0.969432 loss=0.088029 dt=00:36:37 eta=3d 12:14:04 |------------------------------------------------------------------------->
train_opt_callback: iter=   119 sample=33/178 sched=0.968918 loss=0.103543 dt=00:36:30 eta=3d 11:21:17 |------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-120.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   120 sample=41/178 sched=0.968399 loss=0.080645 dt=00:36:33 eta=3d 10:51:58 |------------------------------------------------------------------------->
train_opt_callback: iter=   121 sample=49/178 sched=0.967877 loss=0.059648 dt=00:36:21 eta=3d 09:48:08 |-------------------------------------------------------------------------->
train_opt_callback: iter=   122 sample=57/178 sched=0.967350 loss=0.091482 dt=00:36:19 eta=3d 09:07:40 |------------------------------------------------------------------------->
train_opt_callback: iter=   123 sample=65/178 sched=0.966820 loss=0.057773 dt=00:36:28 eta=3d 08:51:08 |-------------------------------------------------------------------------->
train_opt_callback: iter=   124 sample=73/178 sched=0.966285 loss=0.091841 dt=00:36:34 eta=3d 08:26:52 |------------------------------------------------------------------------->
train_opt_callback: iter=   125 sample=81/178 sched=0.965746 loss=0.077759 dt=00:36:18 eta=3d 07:15:57 |-------------------------------------------------------------------------->
train_opt_callback: iter=   126 sample=89/178 sched=0.965203 loss=0.084306 dt=00:36:27 eta=3d 06:59:43 |------------------------------------------------------------------------->
train_opt_callback: iter=   127 sample=97/178 sched=0.964656 loss=0.062791 dt=00:36:34 eta=3d 06:37:24 |-------------------------------------------------------------------------->
train_opt_callback: iter=   128 sample=105/178 sched=0.964104 loss=0.065764 dt=00:36:47 eta=3d 06:30:19 |-------------------------------------------------------------------------->
train_opt_callback: iter=   129 sample=113/178 sched=0.963549 loss=0.063520 dt=00:37:09 eta=3d 06:38:29 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-130.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   130 sample=121/178 sched=0.962990 loss=0.091305 dt=00:37:05 eta=3d 05:53:43 |------------------------------------------------------------------------->
train_opt_callback: iter=   131 sample=129/178 sched=0.962426 loss=0.076932 dt=00:36:59 eta=3d 05:04:49 |-------------------------------------------------------------------------->
train_opt_callback: iter=   132 sample=137/178 sched=0.961859 loss=0.077943 dt=00:36:58 eta=3d 04:25:42 |-------------------------------------------------------------------------->
train_opt_callback: iter=   133 sample=145/178 sched=0.961287 loss=0.078317 dt=00:36:36 eta=3d 03:02:19 |------------------------------------------------------------------------->
train_opt_callback: iter=   134 sample=153/178 sched=0.960711 loss=0.099851 dt=00:36:49 eta=3d 02:51:55 |------------------------------------------------------------------------->
train_opt_callback: iter=   135 sample=161/178 sched=0.960131 loss=0.066786 dt=00:37:01 eta=3d 02:40:55 |-------------------------------------------------------------------------->
train_opt_callback: iter=   136 sample=169/178 sched=0.959548 loss=0.068781 dt=00:36:53 eta=3d 01:46:21 |-------------------------------------------------------------------------->
train_opt_callback: iter=   137 sample=177/178 sched=0.958960 loss=0.083668 dt=00:36:34 eta=3d 00:33:19 |------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 6
train_opt_callback: iter=   138 sample=1/178 sched=0.958368 loss=0.062936 dt=00:36:48 eta=3d 00:22:24 |-------------------------------------------------------------------------->
train_opt_callback: iter=   139 sample=9/178 sched=0.957772 loss=0.062042 dt=00:36:42 eta=2d 23:34:22 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-140.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   140 sample=17/178 sched=0.957172 loss=0.049663 dt=00:36:44 eta=2d 23:01:33 |-------------------------------------------------------------------------->
train_opt_callback: iter=   141 sample=25/178 sched=0.956568 loss=0.068019 dt=00:37:00 eta=2d 22:56:35 |-------------------------------------------------------------------------->
train_opt_callback: iter=   142 sample=33/178 sched=0.955960 loss=0.063782 dt=00:37:03 eta=2d 22:24:35 |-------------------------------------------------------------------------->
train_opt_callback: iter=   143 sample=41/178 sched=0.955348 loss=0.057332 dt=00:36:59 eta=2d 21:39:13 |-------------------------------------------------------------------------->
train_opt_callback: iter=   144 sample=49/178 sched=0.954732 loss=0.084136 dt=00:36:58 eta=2d 21:00:29 |------------------------------------------------------------------------->
train_opt_callback: iter=   145 sample=57/178 sched=0.954112 loss=0.056280 dt=00:36:56 eta=2d 20:19:54 |-------------------------------------------------------------------------->
train_opt_callback: iter=   146 sample=65/178 sched=0.953488 loss=0.072391 dt=00:36:46 eta=2d 19:25:17 |-------------------------------------------------------------------------->
train_opt_callback: iter=   147 sample=73/178 sched=0.952861 loss=0.091059 dt=00:36:51 eta=2d 18:57:15 |------------------------------------------------------------------------->
train_opt_callback: iter=   148 sample=81/178 sched=0.952229 loss=0.060017 dt=00:36:50 eta=2d 18:18:27 |-------------------------------------------------------------------------->
train_opt_callback: iter=   149 sample=89/178 sched=0.951593 loss=0.057328 dt=00:37:06 eta=2d 18:10:07 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-150.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   150 sample=97/178 sched=0.950953 loss=0.052103 dt=00:37:08 eta=2d 17:37:32 |-------------------------------------------------------------------------->
train_opt_callback: iter=   151 sample=105/178 sched=0.950309 loss=0.065442 dt=00:36:51 eta=2d 16:29:31 |-------------------------------------------------------------------------->
train_opt_callback: iter=   152 sample=113/178 sched=0.949661 loss=0.056746 dt=00:37:03 eta=2d 16:14:24 |-------------------------------------------------------------------------->
train_opt_callback: iter=   153 sample=121/178 sched=0.949010 loss=0.070758 dt=00:37:09 eta=2d 15:46:52 |-------------------------------------------------------------------------->
train_opt_callback: iter=   154 sample=129/178 sched=0.948354 loss=0.069517 dt=00:36:57 eta=2d 14:49:22 |-------------------------------------------------------------------------->
train_opt_callback: iter=   155 sample=137/178 sched=0.947695 loss=0.065151 dt=00:36:59 eta=2d 14:16:57 |-------------------------------------------------------------------------->
train_opt_callback: iter=   156 sample=145/178 sched=0.947031 loss=0.073535 dt=00:36:53 eta=2d 13:28:26 |-------------------------------------------------------------------------->
train_opt_callback: iter=   157 sample=153/178 sched=0.946364 loss=0.060402 dt=00:36:47 eta=2d 12:42:39 |-------------------------------------------------------------------------->
train_opt_callback: iter=   158 sample=161/178 sched=0.945692 loss=0.092005 dt=00:36:58 eta=2d 12:22:44 |------------------------------------------------------------------------->
train_opt_callback: iter=   159 sample=169/178 sched=0.945017 loss=0.065230 dt=00:36:52 eta=2d 11:36:24 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-160.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   160 sample=177/178 sched=0.944338 loss=0.081499 dt=00:36:32 eta=2d 10:27:42 |------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 7
train_opt_callback: iter=   161 sample=1/178 sched=0.943655 loss=0.074532 dt=00:36:23 eta=2d 09:36:26 |-------------------------------------------------------------------------->
train_opt_callback: iter=   162 sample=9/178 sched=0.942968 loss=0.047449 dt=00:36:36 eta=2d 09:20:45 |-------------------------------------------------------------------------->
train_opt_callback: iter=   163 sample=17/178 sched=0.942277 loss=0.075340 dt=00:36:40 eta=2d 08:50:47 |-------------------------------------------------------------------------->
train_opt_callback: iter=   164 sample=25/178 sched=0.941583 loss=0.058686 dt=00:36:31 eta=2d 08:00:13 |-------------------------------------------------------------------------->
train_opt_callback: iter=   165 sample=33/178 sched=0.940884 loss=0.078167 dt=00:36:19 eta=2d 07:05:45 |-------------------------------------------------------------------------->
train_opt_callback: iter=   166 sample=41/178 sched=0.940182 loss=0.049373 dt=00:36:17 eta=2d 06:26:38 |-------------------------------------------------------------------------->
train_opt_callback: iter=   167 sample=49/178 sched=0.939476 loss=0.071963 dt=00:36:13 eta=2d 05:44:20 |-------------------------------------------------------------------------->
train_opt_callback: iter=   168 sample=57/178 sched=0.938765 loss=0.061201 dt=00:36:17 eta=2d 05:13:00 |-------------------------------------------------------------------------->
train_opt_callback: iter=   169 sample=65/178 sched=0.938052 loss=0.054520 dt=00:36:32 eta=2d 04:59:19 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-170.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   170 sample=73/178 sched=0.937334 loss=0.055787 dt=00:36:42 eta=2d 04:36:15 |-------------------------------------------------------------------------->
train_opt_callback: iter=   171 sample=81/178 sched=0.936612 loss=0.058552 dt=00:36:31 eta=2d 03:44:10 |-------------------------------------------------------------------------->
train_opt_callback: iter=   172 sample=89/178 sched=0.935887 loss=0.066907 dt=00:36:37 eta=2d 03:16:36 |-------------------------------------------------------------------------->
train_opt_callback: iter=   173 sample=97/178 sched=0.935158 loss=0.051261 dt=00:36:19 eta=2d 02:15:00 |-------------------------------------------------------------------------->
train_opt_callback: iter=   174 sample=105/178 sched=0.934425 loss=0.053868 dt=00:36:38 eta=2d 02:04:51 |-------------------------------------------------------------------------->
train_opt_callback: iter=   175 sample=113/178 sched=0.933688 loss=0.056048 dt=00:36:30 eta=2d 01:16:42 |-------------------------------------------------------------------------->
train_opt_callback: iter=   176 sample=121/178 sched=0.932948 loss=0.045508 dt=00:36:29 eta=2d 00:39:40 |-------------------------------------------------------------------------->
train_opt_callback: iter=   177 sample=129/178 sched=0.932203 loss=0.068252 dt=00:36:19 eta=1d 23:50:09 |-------------------------------------------------------------------------->
train_opt_callback: iter=   178 sample=137/178 sched=0.931455 loss=0.048026 dt=00:36:19 eta=1d 23:12:56 |-------------------------------------------------------------------------->
train_opt_callback: iter=   179 sample=145/178 sched=0.930703 loss=0.047452 dt=00:36:29 eta=1d 22:49:28 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-180.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   180 sample=153/178 sched=0.929948 loss=0.079426 dt=00:36:15 eta=1d 21:55:25 |------------------------------------------------------------------------->
train_opt_callback: iter=   181 sample=161/178 sched=0.929188 loss=0.050863 dt=00:36:14 eta=1d 21:18:14 |-------------------------------------------------------------------------->
train_opt_callback: iter=   182 sample=169/178 sched=0.928425 loss=0.052199 dt=00:36:35 eta=1d 21:07:59 |-------------------------------------------------------------------------->
train_opt_callback: iter=   183 sample=177/178 sched=0.927658 loss=0.058410 dt=00:36:29 eta=1d 20:24:11 |-------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 8
train_opt_callback: iter=   184 sample=1/178 sched=0.926888 loss=0.045401 dt=00:36:22 eta=1d 19:39:23 |-------------------------------------------------------------------------->
train_opt_callback: iter=   185 sample=9/178 sched=0.926113 loss=0.052396 dt=00:36:31 eta=1d 19:13:49 |-------------------------------------------------------------------------->
train_opt_callback: iter=   186 sample=17/178 sched=0.925335 loss=0.067700 dt=00:36:31 eta=1d 18:37:00 |-------------------------------------------------------------------------->
train_opt_callback: iter=   187 sample=25/178 sched=0.924554 loss=0.046180 dt=00:36:16 eta=1d 17:42:56 |-------------------------------------------------------------------------->
train_opt_callback: iter=   188 sample=33/178 sched=0.923768 loss=0.050971 dt=00:36:36 eta=1d 17:29:09 |-------------------------------------------------------------------------->
train_opt_callback: iter=   189 sample=41/178 sched=0.922979 loss=0.049186 dt=00:36:34 eta=1d 16:50:17 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-190.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   190 sample=49/178 sched=0.922186 loss=0.062805 dt=00:36:44 eta=1d 16:24:30 |-------------------------------------------------------------------------->
train_opt_callback: iter=   191 sample=57/178 sched=0.921390 loss=0.047807 dt=00:36:43 eta=1d 15:46:58 |-------------------------------------------------------------------------->
train_opt_callback: iter=   192 sample=65/178 sched=0.920590 loss=0.049784 dt=00:37:41 eta=1d 16:12:06 |-------------------------------------------------------------------------->
train_opt_callback: iter=   193 sample=73/178 sched=0.919786 loss=0.055659 dt=00:37:01 eta=1d 14:52:57 |-------------------------------------------------------------------------->
train_opt_callback: iter=   194 sample=81/178 sched=0.918978 loss=0.051812 dt=00:36:56 eta=1d 14:10:26 |-------------------------------------------------------------------------->
train_opt_callback: iter=   195 sample=89/178 sched=0.918167 loss=0.051834 dt=00:37:03 eta=1d 13:40:34 |-------------------------------------------------------------------------->
train_opt_callback: iter=   196 sample=97/178 sched=0.917353 loss=0.063875 dt=00:37:02 eta=1d 13:02:30 |-------------------------------------------------------------------------->
train_opt_callback: iter=   197 sample=105/178 sched=0.916534 loss=0.044799 dt=00:36:46 eta=1d 12:09:21 |-------------------------------------------------------------------------->
train_opt_callback: iter=   198 sample=113/178 sched=0.915712 loss=0.052604 dt=00:36:42 eta=1d 11:29:15 |-------------------------------------------------------------------------->
train_opt_callback: iter=   199 sample=121/178 sched=0.914887 loss=0.052343 dt=00:36:41 eta=1d 10:51:43 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-200.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   200 sample=129/178 sched=0.914058 loss=0.053900 dt=00:36:28 eta=1d 10:02:57 |-------------------------------------------------------------------------->
train_opt_callback: iter=   201 sample=137/178 sched=0.913225 loss=0.047804 dt=00:36:32 eta=1d 09:29:47 |-------------------------------------------------------------------------->
train_opt_callback: iter=   202 sample=145/178 sched=0.912389 loss=0.045218 dt=00:37:16 eta=1d 09:33:15 |-------------------------------------------------------------------------->
train_opt_callback: iter=   203 sample=153/178 sched=0.911549 loss=0.056633 dt=00:37:15 eta=1d 08:54:29 |-------------------------------------------------------------------------->
train_opt_callback: iter=   204 sample=161/178 sched=0.910705 loss=0.087018 dt=00:37:17 eta=1d 08:18:48 |------------------------------------------------------------------------->
train_opt_callback: iter=   205 sample=169/178 sched=0.909858 loss=0.051251 dt=00:36:57 eta=1d 07:24:27 |-------------------------------------------------------------------------->
train_opt_callback: iter=   206 sample=177/178 sched=0.909007 loss=0.062427 dt=00:36:48 eta=1d 06:40:45 |-------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 9
train_opt_callback: iter=   207 sample=1/178 sched=0.908153 loss=0.054127 dt=00:36:54 eta=1d 06:08:18 |-------------------------------------------------------------------------->
train_opt_callback: iter=   208 sample=9/178 sched=0.907296 loss=0.051355 dt=00:36:40 eta=1d 05:20:41 |-------------------------------------------------------------------------->
train_opt_callback: iter=   209 sample=17/178 sched=0.906434 loss=0.045598 dt=00:36:52 eta=1d 04:53:05 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-210.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   210 sample=25/178 sched=0.905570 loss=0.045980 dt=00:36:39 eta=1d 04:06:27 |-------------------------------------------------------------------------->
train_opt_callback: iter=   211 sample=33/178 sched=0.904702 loss=0.050601 dt=00:36:36 eta=1d 03:27:37 |-------------------------------------------------------------------------->
train_opt_callback: iter=   212 sample=41/178 sched=0.903830 loss=0.050250 dt=00:36:59 eta=1d 03:07:28 |-------------------------------------------------------------------------->
train_opt_callback: iter=   213 sample=49/178 sched=0.902955 loss=0.043415 dt=00:36:52 eta=1d 02:25:32 |-------------------------------------------------------------------------->
train_opt_callback: iter=   214 sample=57/178 sched=0.902076 loss=0.059098 dt=00:37:10 eta=1d 02:01:34 |-------------------------------------------------------------------------->
train_opt_callback: iter=   215 sample=65/178 sched=0.901194 loss=0.047417 dt=00:36:53 eta=1d 01:12:38 |-------------------------------------------------------------------------->
train_opt_callback: iter=   216 sample=73/178 sched=0.900308 loss=0.047726 dt=00:36:57 eta=1d 00:38:27 |-------------------------------------------------------------------------->
train_opt_callback: iter=   217 sample=81/178 sched=0.899419 loss=0.064566 dt=00:36:56 eta=1d 00:00:34 |-------------------------------------------------------------------------->
train_opt_callback: iter=   218 sample=89/178 sched=0.898526 loss=0.046686 dt=00:36:22 eta=23:02:12 |-------------------------------------------------------------------------->
train_opt_callback: iter=   219 sample=97/178 sched=0.897630 loss=0.052115 dt=00:36:48 eta=22:42:04 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-220.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   220 sample=105/178 sched=0.896731 loss=0.052652 dt=00:36:57 eta=22:10:33 |-------------------------------------------------------------------------->
train_opt_callback: iter=   221 sample=113/178 sched=0.895828 loss=0.048956 dt=00:36:57 eta=21:33:23 |-------------------------------------------------------------------------->
train_opt_callback: iter=   222 sample=121/178 sched=0.894922 loss=0.047552 dt=00:36:44 eta=20:49:26 |-------------------------------------------------------------------------->
train_opt_callback: iter=   223 sample=129/178 sched=0.894012 loss=0.043168 dt=00:36:43 eta=20:12:03 |-------------------------------------------------------------------------->
train_opt_callback: iter=   224 sample=137/178 sched=0.893099 loss=0.050130 dt=00:36:45 eta=19:36:25 |-------------------------------------------------------------------------->
train_opt_callback: iter=   225 sample=145/178 sched=0.892183 loss=0.044088 dt=00:36:37 eta=18:55:10 |-------------------------------------------------------------------------->
train_opt_callback: iter=   226 sample=153/178 sched=0.891263 loss=0.058652 dt=00:36:50 eta=18:25:05 |-------------------------------------------------------------------------->
train_opt_callback: iter=   227 sample=161/178 sched=0.890340 loss=0.048266 dt=00:37:02 eta=17:54:22 |-------------------------------------------------------------------------->
train_opt_callback: iter=   228 sample=169/178 sched=0.889413 loss=0.049002 dt=00:36:38 eta=17:05:46 |-------------------------------------------------------------------------->
train_opt_callback: iter=   229 sample=177/178 sched=0.888483 loss=0.071915 dt=00:36:51 eta=16:35:14 |-------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 10
save_checkpoint_lora_file: saving to checkpoint-230.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   230 sample=1/178 sched=0.887550 loss=0.050140 dt=00:36:56 eta=16:00:20 |-------------------------------------------------------------------------->
train_opt_callback: iter=   231 sample=9/178 sched=0.886613 loss=0.041014 dt=00:36:44 eta=15:18:38 |-------------------------------------------------------------------------->
train_opt_callback: iter=   232 sample=17/178 sched=0.885674 loss=0.056183 dt=00:36:38 eta=14:39:14 |-------------------------------------------------------------------------->
train_opt_callback: iter=   233 sample=25/178 sched=0.884730 loss=0.047450 dt=00:36:33 eta=14:00:56 |-------------------------------------------------------------------------->
train_opt_callback: iter=   234 sample=33/178 sched=0.883784 loss=0.041083 dt=00:36:26 eta=13:21:44 |-------------------------------------------------------------------------->
train_opt_callback: iter=   235 sample=41/178 sched=0.882834 loss=0.051407 dt=00:36:35 eta=12:48:19 |-------------------------------------------------------------------------->
train_opt_callback: iter=   236 sample=49/178 sched=0.881881 loss=0.046471 dt=00:36:29 eta=12:09:58 |-------------------------------------------------------------------------->
train_opt_callback: iter=   237 sample=57/178 sched=0.880924 loss=0.051171 dt=00:36:35 eta=11:35:10 |-------------------------------------------------------------------------->
train_opt_callback: iter=   238 sample=65/178 sched=0.879965 loss=0.039778 dt=00:36:19 eta=10:53:58 |-------------------------------------------------------------------------->
train_opt_callback: iter=   239 sample=73/178 sched=0.879002 loss=0.048262 dt=00:36:51 eta=10:26:33 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-240.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   240 sample=81/178 sched=0.878036 loss=0.050442 dt=00:37:14 eta=09:55:45 |-------------------------------------------------------------------------->
train_opt_callback: iter=   241 sample=89/178 sched=0.877066 loss=0.051114 dt=00:37:23 eta=09:20:55 |-------------------------------------------------------------------------->
train_opt_callback: iter=   242 sample=97/178 sched=0.876094 loss=0.046777 dt=00:36:59 eta=08:37:59 |-------------------------------------------------------------------------->
train_opt_callback: iter=   243 sample=105/178 sched=0.875118 loss=0.063385 dt=00:37:02 eta=08:01:26 |-------------------------------------------------------------------------->
train_opt_callback: iter=   244 sample=113/178 sched=0.874139 loss=0.047352 dt=00:37:05 eta=07:25:05 |-------------------------------------------------------------------------->
train_opt_callback: iter=   245 sample=121/178 sched=0.873157 loss=0.053672 dt=00:37:24 eta=06:51:27 |-------------------------------------------------------------------------->
train_opt_callback: iter=   246 sample=129/178 sched=0.872171 loss=0.054228 dt=00:37:03 eta=06:10:35 |-------------------------------------------------------------------------->
train_opt_callback: iter=   247 sample=137/178 sched=0.871183 loss=0.044063 dt=00:36:52 eta=05:31:50 |-------------------------------------------------------------------------->
train_opt_callback: iter=   248 sample=145/178 sched=0.870191 loss=0.047287 dt=00:36:50 eta=04:54:40 |-------------------------------------------------------------------------->
train_opt_callback: iter=   249 sample=153/178 sched=0.869196 loss=0.049908 dt=00:36:47 eta=04:17:31 |-------------------------------------------------------------------------->
save_checkpoint_lora_file: saving to checkpoint-250.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin
train_opt_callback: iter=   250 sample=161/178 sched=0.868198 loss=0.057780 dt=00:36:36 eta=03:39:38 |-------------------------------------------------------------------------->
train_opt_callback: iter=   251 sample=169/178 sched=0.867197 loss=0.055477 dt=00:36:23 eta=03:01:55 |-------------------------------------------------------------------------->
train_opt_callback: iter=   252 sample=177/178 sched=0.866192 loss=0.047620 dt=00:36:53 eta=02:27:35 |-------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 11
train_opt_callback: iter=   253 sample=1/178 sched=0.865185 loss=0.044904 dt=00:36:49 eta=01:50:29 |-------------------------------------------------------------------------->
train_opt_callback: iter=   254 sample=9/178 sched=0.864174 loss=0.048317 dt=00:36:59 eta=01:13:59 |-------------------------------------------------------------------------->
train_opt_callback: iter=   255 sample=17/178 sched=0.863161 loss=0.046755 dt=00:36:48 eta=00:36:48 |-------------------------------------------------------------------------->
train_opt_callback: iter=   256 sample=25/178 sched=0.862144 loss=0.045131 dt=00:36:48 eta=0.0ms |-------------------------------------------------------------------------->
main: total training time: 5d 12:53:46
save_checkpoint_lora_file: saving to checkpoint-256.gguf
save_checkpoint_lora_file: saving to checkpoint-LATEST.gguf
save_as_llama_lora: saving to lora.bin
save_as_llama_lora: saving to lora.bin