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-chat-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: 1700419101
main: model base = 'llama-2-7b-chat-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 190 samples (min length 22) that are shorter than context length of 128.
tokenize_file: total number of samples: 192
main: number of training tokens: 8099
main: number of unique tokens: 948
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=1/192 sched=0.000000 loss=0.000000 |->
train_opt_callback: iter=     1 sample=9/192 sched=0.010000 loss=7.639391 dt=00:32:55 eta=5d 19:55:06 |->
train_opt_callback: iter=     2 sample=17/192 sched=0.020000 loss=8.123040 dt=00:32:58 eta=5d 19:35:29 |>
train_opt_callback: iter=     3 sample=25/192 sched=0.030000 loss=6.609226 dt=00:32:58 eta=5d 19:01:49 |----------->
train_opt_callback: iter=     4 sample=33/192 sched=0.040000 loss=7.152853 dt=00:32:56 eta=5d 18:21:48 |------>
train_opt_callback: iter=     5 sample=41/192 sched=0.050000 loss=6.951632 dt=00:32:51 eta=5d 17:29:11 |-------->
train_opt_callback: iter=     6 sample=49/192 sched=0.060000 loss=5.657753 dt=00:32:48 eta=5d 16:43:22 |--------------------->
train_opt_callback: iter=     7 sample=57/192 sched=0.070000 loss=4.757537 dt=00:32:51 eta=5d 16:23:32 |------------------------------>
train_opt_callback: iter=     8 sample=65/192 sched=0.080000 loss=4.564727 dt=00:32:43 eta=5d 15:14:19 |-------------------------------->
train_opt_callback: iter=     9 sample=73/192 sched=0.090000 loss=3.958102 dt=00:32:42 eta=5d 14:37:57 |-------------------------------------->
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=81/192 sched=0.100000 loss=3.537075 dt=00:32:55 eta=5d 14:57:33 |------------------------------------------>
train_opt_callback: iter=    11 sample=89/192 sched=0.110000 loss=2.946956 dt=00:33:00 eta=5d 14:45:12 |------------------------------------------------>
train_opt_callback: iter=    12 sample=97/192 sched=0.120000 loss=2.738868 dt=00:33:02 eta=5d 14:22:33 |-------------------------------------------------->
train_opt_callback: iter=    13 sample=105/192 sched=0.130000 loss=2.126371 dt=00:33:00 eta=5d 13:40:51 |-------------------------------------------------------->
train_opt_callback: iter=    14 sample=113/192 sched=0.140000 loss=1.546756 dt=00:32:58 eta=5d 13:01:56 |-------------------------------------------------------------->
train_opt_callback: iter=    15 sample=121/192 sched=0.150000 loss=1.432991 dt=00:33:00 eta=5d 12:36:59 |--------------------------------------------------------------->
train_opt_callback: iter=    16 sample=129/192 sched=0.160000 loss=1.533808 dt=00:32:54 eta=5d 11:36:32 |-------------------------------------------------------------->
train_opt_callback: iter=    17 sample=137/192 sched=0.170000 loss=1.147277 dt=00:33:00 eta=5d 11:27:14 |------------------------------------------------------------------>
train_opt_callback: iter=    18 sample=145/192 sched=0.180000 loss=1.295468 dt=00:33:12 eta=5d 11:42:18 |---------------------------------------------------------------->
train_opt_callback: iter=    19 sample=153/192 sched=0.190000 loss=1.036252 dt=00:33:05 eta=5d 10:43:54 |------------------------------------------------------------------->
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=161/192 sched=0.200000 loss=1.117745 dt=00:33:03 eta=5d 10:03:17 |------------------------------------------------------------------>
train_opt_callback: iter=    21 sample=169/192 sched=0.210000 loss=0.919692 dt=00:33:04 eta=5d 09:31:31 |-------------------------------------------------------------------->
train_opt_callback: iter=    22 sample=177/192 sched=0.220000 loss=0.958725 dt=00:32:52 eta=5d 08:11:11 |-------------------------------------------------------------------->
train_opt_callback: iter=    23 sample=185/192 sched=0.230000 loss=0.677074 dt=00:33:00 eta=5d 08:12:24 |----------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 1
train_opt_callback: iter=    24 sample=1/192 sched=0.240000 loss=0.648157 dt=00:33:16 eta=5d 08:39:19 |----------------------------------------------------------------------->
train_opt_callback: iter=    25 sample=9/192 sched=0.250000 loss=0.820849 dt=00:33:14 eta=5d 07:57:04 |--------------------------------------------------------------------->
train_opt_callback: iter=    26 sample=17/192 sched=0.260000 loss=0.679941 dt=00:33:12 eta=5d 07:17:18 |----------------------------------------------------------------------->
train_opt_callback: iter=    27 sample=25/192 sched=0.270000 loss=0.553361 dt=00:33:02 eta=5d 06:07:10 |------------------------------------------------------------------------>
train_opt_callback: iter=    28 sample=33/192 sched=0.280000 loss=0.656925 dt=00:32:59 eta=5d 05:22:14 |----------------------------------------------------------------------->
train_opt_callback: iter=    29 sample=41/192 sched=0.290000 loss=0.681380 dt=00:33:11 eta=5d 05:34:39 |----------------------------------------------------------------------->
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=49/192 sched=0.300000 loss=0.628787 dt=00:33:11 eta=5d 05:02:11 |----------------------------------------------------------------------->
train_opt_callback: iter=    31 sample=57/192 sched=0.310000 loss=0.453469 dt=00:33:25 eta=5d 05:20:01 |------------------------------------------------------------------------->
train_opt_callback: iter=    32 sample=65/192 sched=0.320000 loss=0.359532 dt=00:33:01 eta=5d 03:18:35 |-------------------------------------------------------------------------->
train_opt_callback: iter=    33 sample=73/192 sched=0.330000 loss=0.424839 dt=00:32:54 eta=5d 02:17:13 |------------------------------------------------------------------------->
train_opt_callback: iter=    34 sample=81/192 sched=0.340000 loss=0.433118 dt=00:33:01 eta=5d 02:10:01 |------------------------------------------------------------------------->
train_opt_callback: iter=    35 sample=89/192 sched=0.350000 loss=0.473854 dt=00:32:59 eta=5d 01:31:52 |------------------------------------------------------------------------->
train_opt_callback: iter=    36 sample=97/192 sched=0.360000 loss=0.399268 dt=00:33:03 eta=5d 01:12:33 |------------------------------------------------------------------------->
train_opt_callback: iter=    37 sample=105/192 sched=0.370000 loss=0.560971 dt=00:31:58 eta=4d 20:41:25 |------------------------------------------------------------------------>
train_opt_callback: iter=    38 sample=113/192 sched=0.380000 loss=0.401658 dt=00:20:32 eta=3d 02:37:22 |------------------------------------------------------------------------->
train_opt_callback: iter=    39 sample=121/192 sched=0.390000 loss=0.358174 dt=00:17:02 eta=2d 13:38:29 |-------------------------------------------------------------------------->
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=129/192 sched=0.400000 loss=0.378025 dt=00:15:54 eta=2d 09:17:30 |-------------------------------------------------------------------------->
train_opt_callback: iter=    41 sample=137/192 sched=0.410000 loss=0.428651 dt=00:15:37 eta=2d 07:59:48 |------------------------------------------------------------------------->
train_opt_callback: iter=    42 sample=145/192 sched=0.420000 loss=0.323726 dt=00:15:40 eta=2d 07:55:10 |-------------------------------------------------------------------------->
train_opt_callback: iter=    43 sample=153/192 sched=0.430000 loss=0.296268 dt=00:15:40 eta=2d 07:37:30 |-------------------------------------------------------------------------->
train_opt_callback: iter=    44 sample=161/192 sched=0.440000 loss=0.285518 dt=00:15:32 eta=2d 06:55:17 |--------------------------------------------------------------------------->
train_opt_callback: iter=    45 sample=169/192 sched=0.450000 loss=0.342957 dt=00:15:33 eta=2d 06:43:16 |-------------------------------------------------------------------------->
train_opt_callback: iter=    46 sample=177/192 sched=0.460000 loss=0.194749 dt=00:15:46 eta=2d 07:11:14 |--------------------------------------------------------------------------->
train_opt_callback: iter=    47 sample=185/192 sched=0.470000 loss=0.244491 dt=00:15:39 eta=2d 06:34:14 |--------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 2
train_opt_callback: iter=    48 sample=1/192 sched=0.480000 loss=0.222005 dt=00:15:37 eta=2d 06:10:32 |--------------------------------------------------------------------------->
train_opt_callback: iter=    49 sample=9/192 sched=0.490000 loss=0.342179 dt=00:15:37 eta=2d 05:54:36 |-------------------------------------------------------------------------->
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=17/192 sched=0.500000 loss=0.334579 dt=00:15:37 eta=2d 05:38:32 |-------------------------------------------------------------------------->
train_opt_callback: iter=    51 sample=25/192 sched=0.510000 loss=0.361630 dt=00:15:33 eta=2d 05:09:21 |-------------------------------------------------------------------------->
train_opt_callback: iter=    52 sample=33/192 sched=0.520000 loss=0.188962 dt=00:15:34 eta=2d 04:56:45 |---------------------------------------------------------------------------->
train_opt_callback: iter=    53 sample=41/192 sched=0.530000 loss=0.238500 dt=00:15:38 eta=2d 04:54:09 |--------------------------------------------------------------------------->
train_opt_callback: iter=    54 sample=49/192 sched=0.540000 loss=0.263577 dt=00:15:34 eta=2d 04:26:19 |--------------------------------------------------------------------------->
train_opt_callback: iter=    55 sample=57/192 sched=0.550000 loss=0.194148 dt=00:15:36 eta=2d 04:16:57 |--------------------------------------------------------------------------->
train_opt_callback: iter=    56 sample=65/192 sched=0.560000 loss=0.216232 dt=00:15:29 eta=2d 03:38:30 |--------------------------------------------------------------------------->
train_opt_callback: iter=    57 sample=73/192 sched=0.570000 loss=0.113424 dt=00:15:31 eta=2d 03:30:22 |---------------------------------------------------------------------------->
train_opt_callback: iter=    58 sample=81/192 sched=0.580000 loss=0.191995 dt=00:15:37 eta=2d 03:32:15 |--------------------------------------------------------------------------->
train_opt_callback: iter=    59 sample=89/192 sched=0.590000 loss=0.183454 dt=00:15:31 eta=2d 02:59:52 |---------------------------------------------------------------------------->
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=97/192 sched=0.600000 loss=0.155663 dt=00:15:34 eta=2d 02:53:06 |---------------------------------------------------------------------------->
train_opt_callback: iter=    61 sample=105/192 sched=0.610000 loss=0.198579 dt=00:15:32 eta=2d 02:29:39 |--------------------------------------------------------------------------->
train_opt_callback: iter=    62 sample=113/192 sched=0.620000 loss=0.209679 dt=00:15:27 eta=2d 02:00:01 |--------------------------------------------------------------------------->
train_opt_callback: iter=    63 sample=121/192 sched=0.630000 loss=0.134847 dt=00:15:33 eta=2d 02:02:22 |---------------------------------------------------------------------------->
train_opt_callback: iter=    64 sample=129/192 sched=0.640000 loss=0.284779 dt=00:15:36 eta=2d 01:57:23 |--------------------------------------------------------------------------->
train_opt_callback: iter=    65 sample=137/192 sched=0.650000 loss=0.155553 dt=00:15:35 eta=2d 01:38:03 |---------------------------------------------------------------------------->
train_opt_callback: iter=    66 sample=145/192 sched=0.660000 loss=0.231996 dt=00:15:34 eta=2d 01:17:50 |--------------------------------------------------------------------------->
train_opt_callback: iter=    67 sample=153/192 sched=0.670000 loss=0.237264 dt=00:15:29 eta=2d 00:47:50 |--------------------------------------------------------------------------->
train_opt_callback: iter=    68 sample=161/192 sched=0.680000 loss=0.176222 dt=00:15:34 eta=2d 00:49:20 |---------------------------------------------------------------------------->
train_opt_callback: iter=    69 sample=169/192 sched=0.690000 loss=0.126854 dt=00:15:32 eta=2d 00:25:54 |---------------------------------------------------------------------------->
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=177/192 sched=0.700000 loss=0.163200 dt=00:15:30 eta=2d 00:05:29 |---------------------------------------------------------------------------->
train_opt_callback: iter=    71 sample=185/192 sched=0.710000 loss=0.382751 dt=00:15:29 eta=1d 23:46:04 |-------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 3
train_opt_callback: iter=    72 sample=1/192 sched=0.720000 loss=0.249731 dt=00:15:30 eta=1d 23:35:02 |--------------------------------------------------------------------------->
train_opt_callback: iter=    73 sample=9/192 sched=0.730000 loss=0.240528 dt=00:15:35 eta=1d 23:34:26 |--------------------------------------------------------------------------->
train_opt_callback: iter=    74 sample=17/192 sched=0.740000 loss=0.125279 dt=00:15:29 eta=1d 23:00:17 |---------------------------------------------------------------------------->
train_opt_callback: iter=    75 sample=25/192 sched=0.750000 loss=0.230016 dt=00:15:34 eta=1d 22:57:46 |--------------------------------------------------------------------------->
train_opt_callback: iter=    76 sample=33/192 sched=0.760000 loss=0.187424 dt=00:15:32 eta=1d 22:36:58 |---------------------------------------------------------------------------->
train_opt_callback: iter=    77 sample=41/192 sched=0.770000 loss=0.198255 dt=00:15:37 eta=1d 22:37:52 |--------------------------------------------------------------------------->
train_opt_callback: iter=    78 sample=49/192 sched=0.780000 loss=0.058203 dt=00:15:31 eta=1d 22:03:32 |----------------------------------------------------------------------------->
train_opt_callback: iter=    79 sample=57/192 sched=0.790000 loss=0.110901 dt=00:15:27 eta=1d 21:36:39 |---------------------------------------------------------------------------->
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=65/192 sched=0.800000 loss=0.198940 dt=00:15:41 eta=1d 22:00:42 |--------------------------------------------------------------------------->
train_opt_callback: iter=    81 sample=73/192 sched=0.810000 loss=0.101694 dt=00:15:39 eta=1d 21:38:50 |---------------------------------------------------------------------------->
train_opt_callback: iter=    82 sample=81/192 sched=0.820000 loss=0.140884 dt=00:15:35 eta=1d 21:14:18 |---------------------------------------------------------------------------->
train_opt_callback: iter=    83 sample=89/192 sched=0.830000 loss=0.160913 dt=00:15:30 eta=1d 20:42:40 |---------------------------------------------------------------------------->
train_opt_callback: iter=    84 sample=97/192 sched=0.840000 loss=0.147126 dt=00:15:34 eta=1d 20:39:51 |---------------------------------------------------------------------------->
train_opt_callback: iter=    85 sample=105/192 sched=0.850000 loss=0.104718 dt=00:15:35 eta=1d 20:24:55 |---------------------------------------------------------------------------->
train_opt_callback: iter=    86 sample=113/192 sched=0.860000 loss=0.143592 dt=00:15:31 eta=1d 19:58:35 |---------------------------------------------------------------------------->
train_opt_callback: iter=    87 sample=121/192 sched=0.870000 loss=0.101460 dt=00:15:29 eta=1d 19:39:18 |---------------------------------------------------------------------------->
train_opt_callback: iter=    88 sample=129/192 sched=0.880000 loss=0.172694 dt=00:15:31 eta=1d 19:26:54 |---------------------------------------------------------------------------->
train_opt_callback: iter=    89 sample=137/192 sched=0.890000 loss=0.097297 dt=00:15:29 eta=1d 19:07:34 |---------------------------------------------------------------------------->
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=145/192 sched=0.900000 loss=0.203012 dt=00:15:27 eta=1d 18:47:01 |--------------------------------------------------------------------------->
train_opt_callback: iter=    91 sample=153/192 sched=0.910000 loss=0.061470 dt=00:15:31 eta=1d 18:41:13 |----------------------------------------------------------------------------->
train_opt_callback: iter=    92 sample=161/192 sched=0.920000 loss=0.186582 dt=00:15:32 eta=1d 18:29:30 |---------------------------------------------------------------------------->
train_opt_callback: iter=    93 sample=169/192 sched=0.930000 loss=0.136616 dt=00:15:30 eta=1d 18:08:52 |---------------------------------------------------------------------------->
train_opt_callback: iter=    94 sample=177/192 sched=0.940000 loss=0.107690 dt=00:15:26 eta=1d 17:41:06 |---------------------------------------------------------------------------->
train_opt_callback: iter=    95 sample=185/192 sched=0.950000 loss=0.125770 dt=00:15:33 eta=1d 17:45:06 |---------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 4
train_opt_callback: iter=    96 sample=1/192 sched=0.960000 loss=0.147633 dt=00:15:31 eta=1d 17:23:56 |---------------------------------------------------------------------------->
train_opt_callback: iter=    97 sample=9/192 sched=0.970000 loss=0.112660 dt=00:15:27 eta=1d 16:59:02 |---------------------------------------------------------------------------->
train_opt_callback: iter=    98 sample=17/192 sched=0.980000 loss=0.071028 dt=00:15:34 eta=1d 17:00:34 |----------------------------------------------------------------------------->
train_opt_callback: iter=    99 sample=25/192 sched=0.990000 loss=0.148655 dt=00:15:27 eta=1d 16:25:43 |---------------------------------------------------------------------------->
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=33/192 sched=0.977975 loss=0.122147 dt=00:16:26 eta=1d 18:46:11 |---------------------------------------------------------------------------->
train_opt_callback: iter=   101 sample=41/192 sched=0.977536 loss=0.075263 dt=00:15:59 eta=1d 17:17:59 |----------------------------------------------------------------------------->
train_opt_callback: iter=   102 sample=49/192 sched=0.977093 loss=0.098616 dt=00:15:43 eta=1d 16:21:33 |---------------------------------------------------------------------------->
train_opt_callback: iter=   103 sample=57/192 sched=0.976646 loss=0.071327 dt=00:15:40 eta=1d 15:59:30 |----------------------------------------------------------------------------->
train_opt_callback: iter=   104 sample=65/192 sched=0.976194 loss=0.079295 dt=00:15:36 eta=1d 15:33:37 |----------------------------------------------------------------------------->
train_opt_callback: iter=   105 sample=73/192 sched=0.975738 loss=0.073060 dt=00:15:35 eta=1d 15:13:33 |----------------------------------------------------------------------------->
train_opt_callback: iter=   106 sample=81/192 sched=0.975278 loss=0.126725 dt=00:15:42 eta=1d 15:15:25 |---------------------------------------------------------------------------->
train_opt_callback: iter=   107 sample=89/192 sched=0.974814 loss=0.099712 dt=00:15:35 eta=1d 14:42:32 |---------------------------------------------------------------------------->
train_opt_callback: iter=   108 sample=97/192 sched=0.974346 loss=0.069941 dt=00:15:30 eta=1d 14:14:28 |----------------------------------------------------------------------------->
train_opt_callback: iter=   109 sample=105/192 sched=0.973873 loss=0.098124 dt=00:15:34 eta=1d 14:09:41 |---------------------------------------------------------------------------->
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=113/192 sched=0.973396 loss=0.098537 dt=00:15:34 eta=1d 13:54:34 |---------------------------------------------------------------------------->
train_opt_callback: iter=   111 sample=121/192 sched=0.972915 loss=0.126159 dt=00:15:31 eta=1d 13:31:34 |---------------------------------------------------------------------------->
train_opt_callback: iter=   112 sample=129/192 sched=0.972430 loss=0.077748 dt=00:15:29 eta=1d 13:10:55 |----------------------------------------------------------------------------->
train_opt_callback: iter=   113 sample=137/192 sched=0.971941 loss=0.102149 dt=00:15:31 eta=1d 13:00:02 |---------------------------------------------------------------------------->
train_opt_callback: iter=   114 sample=145/192 sched=0.971447 loss=0.071937 dt=00:15:38 eta=1d 13:01:24 |----------------------------------------------------------------------------->
train_opt_callback: iter=   115 sample=153/192 sched=0.970950 loss=0.077037 dt=00:15:28 eta=1d 12:21:31 |----------------------------------------------------------------------------->
train_opt_callback: iter=   116 sample=161/192 sched=0.970448 loss=0.082243 dt=00:15:39 eta=1d 12:32:09 |----------------------------------------------------------------------------->
train_opt_callback: iter=   117 sample=169/192 sched=0.969942 loss=0.084385 dt=00:15:46 eta=1d 12:31:43 |----------------------------------------------------------------------------->
train_opt_callback: iter=   118 sample=177/192 sched=0.969432 loss=0.133562 dt=00:15:46 eta=1d 12:16:08 |---------------------------------------------------------------------------->
train_opt_callback: iter=   119 sample=185/192 sched=0.968918 loss=0.109072 dt=00:15:35 eta=1d 11:35:59 |---------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 5
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=1/192 sched=0.968399 loss=0.113454 dt=00:15:34 eta=1d 11:17:49 |---------------------------------------------------------------------------->
train_opt_callback: iter=   121 sample=9/192 sched=0.967877 loss=0.077776 dt=00:15:33 eta=1d 11:00:28 |----------------------------------------------------------------------------->
train_opt_callback: iter=   122 sample=17/192 sched=0.967350 loss=0.061315 dt=00:15:30 eta=1d 10:39:02 |----------------------------------------------------------------------------->
train_opt_callback: iter=   123 sample=25/192 sched=0.966820 loss=0.072449 dt=00:15:36 eta=1d 10:35:18 |----------------------------------------------------------------------------->
train_opt_callback: iter=   124 sample=33/192 sched=0.966285 loss=0.060652 dt=00:15:34 eta=1d 10:14:59 |----------------------------------------------------------------------------->
train_opt_callback: iter=   125 sample=41/192 sched=0.965746 loss=0.072381 dt=00:15:32 eta=1d 09:54:52 |----------------------------------------------------------------------------->
train_opt_callback: iter=   126 sample=49/192 sched=0.965203 loss=0.058497 dt=00:15:35 eta=1d 09:45:58 |----------------------------------------------------------------------------->
train_opt_callback: iter=   127 sample=57/192 sched=0.964656 loss=0.066129 dt=00:15:40 eta=1d 09:42:49 |----------------------------------------------------------------------------->
train_opt_callback: iter=   128 sample=65/192 sched=0.964104 loss=0.048283 dt=00:15:45 eta=1d 09:36:16 |----------------------------------------------------------------------------->
train_opt_callback: iter=   129 sample=73/192 sched=0.963549 loss=0.070143 dt=00:15:37 eta=1d 09:04:45 |----------------------------------------------------------------------------->
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=81/192 sched=0.962990 loss=0.071810 dt=00:15:37 eta=1d 08:49:34 |----------------------------------------------------------------------------->
train_opt_callback: iter=   131 sample=89/192 sched=0.962426 loss=0.073223 dt=00:15:33 eta=1d 08:24:44 |----------------------------------------------------------------------------->
train_opt_callback: iter=   132 sample=97/192 sched=0.961859 loss=0.073529 dt=00:15:35 eta=1d 08:12:35 |----------------------------------------------------------------------------->
train_opt_callback: iter=   133 sample=105/192 sched=0.961287 loss=0.075146 dt=00:15:38 eta=1d 08:04:55 |----------------------------------------------------------------------------->
train_opt_callback: iter=   134 sample=113/192 sched=0.960711 loss=0.068796 dt=00:15:34 eta=1d 07:39:44 |----------------------------------------------------------------------------->
train_opt_callback: iter=   135 sample=121/192 sched=0.960131 loss=0.076424 dt=00:15:30 eta=1d 07:15:46 |----------------------------------------------------------------------------->
train_opt_callback: iter=   136 sample=129/192 sched=0.959548 loss=0.081089 dt=00:15:36 eta=1d 07:12:43 |----------------------------------------------------------------------------->
train_opt_callback: iter=   137 sample=137/192 sched=0.958960 loss=0.059550 dt=00:15:37 eta=1d 06:58:43 |----------------------------------------------------------------------------->
train_opt_callback: iter=   138 sample=145/192 sched=0.958368 loss=0.066975 dt=00:15:34 eta=1d 06:38:48 |----------------------------------------------------------------------------->
train_opt_callback: iter=   139 sample=153/192 sched=0.957772 loss=0.048607 dt=00:15:39 eta=1d 06:31:42 |----------------------------------------------------------------------------->
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=161/192 sched=0.957172 loss=0.068270 dt=00:15:34 eta=1d 06:05:57 |----------------------------------------------------------------------------->
train_opt_callback: iter=   141 sample=169/192 sched=0.956568 loss=0.066943 dt=00:15:34 eta=1d 05:50:37 |----------------------------------------------------------------------------->
train_opt_callback: iter=   142 sample=177/192 sched=0.955960 loss=0.083575 dt=00:15:40 eta=1d 05:46:20 |----------------------------------------------------------------------------->
train_opt_callback: iter=   143 sample=185/192 sched=0.955348 loss=0.090246 dt=00:15:37 eta=1d 05:25:46 |---------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 6
train_opt_callback: iter=   144 sample=1/192 sched=0.954732 loss=0.085501 dt=00:15:31 eta=1d 04:59:31 |----------------------------------------------------------------------------->
train_opt_callback: iter=   145 sample=9/192 sched=0.954112 loss=0.061576 dt=00:15:32 eta=1d 04:45:20 |----------------------------------------------------------------------------->
train_opt_callback: iter=   146 sample=17/192 sched=0.953488 loss=0.056798 dt=00:15:38 eta=1d 04:40:07 |----------------------------------------------------------------------------->
train_opt_callback: iter=   147 sample=25/192 sched=0.952861 loss=0.049612 dt=00:15:51 eta=1d 04:49:02 |----------------------------------------------------------------------------->
train_opt_callback: iter=   148 sample=33/192 sched=0.952229 loss=0.052921 dt=00:15:52 eta=1d 04:33:53 |----------------------------------------------------------------------------->
train_opt_callback: iter=   149 sample=41/192 sched=0.951593 loss=0.060486 dt=00:15:43 eta=1d 04:01:47 |----------------------------------------------------------------------------->
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=49/192 sched=0.950953 loss=0.048820 dt=00:15:39 eta=1d 03:39:18 |----------------------------------------------------------------------------->
train_opt_callback: iter=   151 sample=57/192 sched=0.950309 loss=0.049720 dt=00:15:39 eta=1d 03:23:54 |----------------------------------------------------------------------------->
train_opt_callback: iter=   152 sample=65/192 sched=0.949661 loss=0.067127 dt=00:15:36 eta=1d 03:02:40 |----------------------------------------------------------------------------->
train_opt_callback: iter=   153 sample=73/192 sched=0.949010 loss=0.060491 dt=00:15:38 eta=1d 02:50:57 |----------------------------------------------------------------------------->
train_opt_callback: iter=   154 sample=81/192 sched=0.948354 loss=0.069643 dt=00:15:39 eta=1d 02:36:36 |----------------------------------------------------------------------------->
train_opt_callback: iter=   155 sample=89/192 sched=0.947695 loss=0.063830 dt=00:15:37 eta=1d 02:17:37 |----------------------------------------------------------------------------->
train_opt_callback: iter=   156 sample=97/192 sched=0.947031 loss=0.065827 dt=00:15:41 eta=1d 02:08:59 |----------------------------------------------------------------------------->
train_opt_callback: iter=   157 sample=105/192 sched=0.946364 loss=0.069183 dt=00:15:44 eta=1d 01:57:36 |----------------------------------------------------------------------------->
train_opt_callback: iter=   158 sample=113/192 sched=0.945692 loss=0.102524 dt=00:15:50 eta=1d 01:51:46 |---------------------------------------------------------------------------->
train_opt_callback: iter=   159 sample=121/192 sched=0.945017 loss=0.057947 dt=00:15:47 eta=1d 01:32:19 |----------------------------------------------------------------------------->
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=129/192 sched=0.944338 loss=0.050483 dt=00:15:44 eta=1d 01:11:31 |----------------------------------------------------------------------------->
train_opt_callback: iter=   161 sample=137/192 sched=0.943655 loss=0.065197 dt=00:15:40 eta=1d 00:48:28 |----------------------------------------------------------------------------->
train_opt_callback: iter=   162 sample=145/192 sched=0.942968 loss=0.060740 dt=00:15:37 eta=1d 00:28:16 |----------------------------------------------------------------------------->
train_opt_callback: iter=   163 sample=153/192 sched=0.942277 loss=0.052192 dt=00:15:34 eta=1d 00:09:01 |----------------------------------------------------------------------------->
train_opt_callback: iter=   164 sample=161/192 sched=0.941583 loss=0.053813 dt=00:15:38 eta=23:59:39 |----------------------------------------------------------------------------->
train_opt_callback: iter=   165 sample=169/192 sched=0.940884 loss=0.059665 dt=00:15:39 eta=23:45:11 |----------------------------------------------------------------------------->
train_opt_callback: iter=   166 sample=177/192 sched=0.940182 loss=0.058576 dt=00:15:32 eta=23:18:44 |----------------------------------------------------------------------------->
train_opt_callback: iter=   167 sample=185/192 sched=0.939476 loss=0.053657 dt=00:15:29 eta=22:59:26 |----------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 7
train_opt_callback: iter=   168 sample=1/192 sched=0.938765 loss=0.050923 dt=00:15:33 eta=22:48:52 |----------------------------------------------------------------------------->
train_opt_callback: iter=   169 sample=9/192 sched=0.938052 loss=0.044524 dt=00:15:37 eta=22:39:28 |----------------------------------------------------------------------------->
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=17/192 sched=0.937334 loss=0.046028 dt=00:15:24 eta=22:05:24 |----------------------------------------------------------------------------->
train_opt_callback: iter=   171 sample=25/192 sched=0.936612 loss=0.049158 dt=00:15:23 eta=21:48:21 |----------------------------------------------------------------------------->
train_opt_callback: iter=   172 sample=33/192 sched=0.935887 loss=0.053132 dt=00:15:26 eta=21:36:52 |----------------------------------------------------------------------------->
train_opt_callback: iter=   173 sample=41/192 sched=0.935158 loss=0.046411 dt=00:15:28 eta=21:24:48 |----------------------------------------------------------------------------->
train_opt_callback: iter=   174 sample=49/192 sched=0.934425 loss=0.048739 dt=00:15:25 eta=21:04:53 |----------------------------------------------------------------------------->
train_opt_callback: iter=   175 sample=57/192 sched=0.933688 loss=0.056599 dt=00:15:24 eta=20:48:33 |----------------------------------------------------------------------------->
train_opt_callback: iter=   176 sample=65/192 sched=0.932948 loss=0.056154 dt=00:15:30 eta=20:41:11 |----------------------------------------------------------------------------->
train_opt_callback: iter=   177 sample=73/192 sched=0.932203 loss=0.053577 dt=00:15:29 eta=20:23:34 |----------------------------------------------------------------------------->
train_opt_callback: iter=   178 sample=81/192 sched=0.931455 loss=0.056811 dt=00:15:22 eta=19:58:57 |----------------------------------------------------------------------------->
train_opt_callback: iter=   179 sample=89/192 sched=0.930703 loss=0.047785 dt=00:15:28 eta=19:51:41 |----------------------------------------------------------------------------->
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=97/192 sched=0.929948 loss=0.065201 dt=00:15:31 eta=19:40:29 |----------------------------------------------------------------------------->
train_opt_callback: iter=   181 sample=105/192 sched=0.929188 loss=0.064345 dt=00:15:29 eta=19:22:17 |----------------------------------------------------------------------------->
train_opt_callback: iter=   182 sample=113/192 sched=0.928425 loss=0.047728 dt=00:15:28 eta=19:05:23 |----------------------------------------------------------------------------->
train_opt_callback: iter=   183 sample=121/192 sched=0.927658 loss=0.058445 dt=00:15:25 eta=18:45:29 |----------------------------------------------------------------------------->
train_opt_callback: iter=   184 sample=129/192 sched=0.926888 loss=0.055892 dt=00:15:26 eta=18:31:55 |----------------------------------------------------------------------------->
train_opt_callback: iter=   185 sample=137/192 sched=0.926113 loss=0.053026 dt=00:15:27 eta=18:17:25 |----------------------------------------------------------------------------->
train_opt_callback: iter=   186 sample=145/192 sched=0.925335 loss=0.046620 dt=00:15:29 eta=18:04:11 |----------------------------------------------------------------------------->
train_opt_callback: iter=   187 sample=153/192 sched=0.924554 loss=0.061322 dt=00:15:30 eta=17:50:35 |----------------------------------------------------------------------------->
train_opt_callback: iter=   188 sample=161/192 sched=0.923768 loss=0.047851 dt=00:15:37 eta=17:42:26 |----------------------------------------------------------------------------->
train_opt_callback: iter=   189 sample=169/192 sched=0.922979 loss=0.048963 dt=00:15:35 eta=17:25:03 |----------------------------------------------------------------------------->
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=177/192 sched=0.922186 loss=0.047204 dt=00:15:36 eta=17:09:36 |----------------------------------------------------------------------------->
train_opt_callback: iter=   191 sample=185/192 sched=0.921390 loss=0.055146 dt=00:15:33 eta=16:50:51 |----------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 8
train_opt_callback: iter=   192 sample=1/192 sched=0.920590 loss=0.065108 dt=00:15:31 eta=16:33:42 |----------------------------------------------------------------------------->
train_opt_callback: iter=   193 sample=9/192 sched=0.919786 loss=0.045205 dt=00:15:29 eta=16:16:11 |----------------------------------------------------------------------------->
train_opt_callback: iter=   194 sample=17/192 sched=0.918978 loss=0.049374 dt=00:15:33 eta=16:05:03 |----------------------------------------------------------------------------->
train_opt_callback: iter=   195 sample=25/192 sched=0.918167 loss=0.047677 dt=00:15:41 eta=15:56:52 |----------------------------------------------------------------------------->
train_opt_callback: iter=   196 sample=33/192 sched=0.917353 loss=0.044926 dt=00:15:31 eta=15:31:04 |----------------------------------------------------------------------------->
train_opt_callback: iter=   197 sample=41/192 sched=0.916534 loss=0.046525 dt=00:15:10 eta=14:55:20 |----------------------------------------------------------------------------->
train_opt_callback: iter=   198 sample=49/192 sched=0.915712 loss=0.045030 dt=00:15:05 eta=14:35:23 |----------------------------------------------------------------------------->
train_opt_callback: iter=   199 sample=57/192 sched=0.914887 loss=0.045530 dt=00:15:00 eta=14:15:47 |----------------------------------------------------------------------------->
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=65/192 sched=0.914058 loss=0.046049 dt=00:15:00 eta=14:00:14 |----------------------------------------------------------------------------->
train_opt_callback: iter=   201 sample=73/192 sched=0.913225 loss=0.053930 dt=00:14:58 eta=13:43:57 |----------------------------------------------------------------------------->
train_opt_callback: iter=   202 sample=81/192 sched=0.912389 loss=0.051443 dt=00:14:58 eta=13:28:28 |----------------------------------------------------------------------------->
train_opt_callback: iter=   203 sample=89/192 sched=0.911549 loss=0.046394 dt=00:14:58 eta=13:13:19 |----------------------------------------------------------------------------->
train_opt_callback: iter=   204 sample=97/192 sched=0.910705 loss=0.046575 dt=00:15:00 eta=13:00:36 |----------------------------------------------------------------------------->
train_opt_callback: iter=   205 sample=105/192 sched=0.909858 loss=0.049402 dt=00:15:03 eta=12:48:18 |----------------------------------------------------------------------------->
train_opt_callback: iter=   206 sample=113/192 sched=0.909007 loss=0.043352 dt=00:15:01 eta=12:31:19 |----------------------------------------------------------------------------->
train_opt_callback: iter=   207 sample=121/192 sched=0.908153 loss=0.053521 dt=00:14:58 eta=12:14:09 |----------------------------------------------------------------------------->
train_opt_callback: iter=   208 sample=129/192 sched=0.907296 loss=0.049153 dt=00:15:01 eta=12:00:50 |----------------------------------------------------------------------------->
train_opt_callback: iter=   209 sample=137/192 sched=0.906434 loss=0.050224 dt=00:15:01 eta=11:46:09 |----------------------------------------------------------------------------->
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=145/192 sched=0.905570 loss=0.051670 dt=00:15:05 eta=11:33:58 |----------------------------------------------------------------------------->
train_opt_callback: iter=   211 sample=153/192 sched=0.904702 loss=0.051875 dt=00:15:06 eta=11:19:33 |----------------------------------------------------------------------------->
train_opt_callback: iter=   212 sample=161/192 sched=0.903830 loss=0.057988 dt=00:15:01 eta=11:00:52 |----------------------------------------------------------------------------->
train_opt_callback: iter=   213 sample=169/192 sched=0.902955 loss=0.048556 dt=00:15:04 eta=10:48:32 |----------------------------------------------------------------------------->
train_opt_callback: iter=   214 sample=177/192 sched=0.902076 loss=0.052551 dt=00:14:59 eta=10:29:59 |----------------------------------------------------------------------------->
train_opt_callback: iter=   215 sample=185/192 sched=0.901194 loss=0.057498 dt=00:15:05 eta=10:18:53 |----------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 9
train_opt_callback: iter=   216 sample=1/192 sched=0.900308 loss=0.051821 dt=00:15:01 eta=10:01:08 |----------------------------------------------------------------------------->
train_opt_callback: iter=   217 sample=9/192 sched=0.899419 loss=0.042146 dt=00:15:01 eta=09:45:51 |----------------------------------------------------------------------------->
train_opt_callback: iter=   218 sample=17/192 sched=0.898526 loss=0.048716 dt=00:15:01 eta=09:30:57 |----------------------------------------------------------------------------->
train_opt_callback: iter=   219 sample=25/192 sched=0.897630 loss=0.079733 dt=00:15:01 eta=09:16:01 |----------------------------------------------------------------------------->
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=33/192 sched=0.896731 loss=0.045738 dt=00:14:57 eta=08:58:40 |----------------------------------------------------------------------------->
train_opt_callback: iter=   221 sample=41/192 sched=0.895828 loss=0.049312 dt=00:15:01 eta=08:46:03 |----------------------------------------------------------------------------->
train_opt_callback: iter=   222 sample=49/192 sched=0.894922 loss=0.044266 dt=00:15:04 eta=08:32:43 |----------------------------------------------------------------------------->
train_opt_callback: iter=   223 sample=57/192 sched=0.894012 loss=0.043147 dt=00:15:01 eta=08:15:58 |----------------------------------------------------------------------------->
train_opt_callback: iter=   224 sample=65/192 sched=0.893099 loss=0.055512 dt=00:15:28 eta=08:15:06 |----------------------------------------------------------------------------->
train_opt_callback: iter=   225 sample=73/192 sched=0.892183 loss=0.049956 dt=00:15:25 eta=07:58:08 |----------------------------------------------------------------------------->
train_opt_callback: iter=   226 sample=81/192 sched=0.891263 loss=0.050909 dt=00:15:33 eta=07:46:37 |----------------------------------------------------------------------------->
train_opt_callback: iter=   227 sample=89/192 sched=0.890340 loss=0.050016 dt=00:15:38 eta=07:33:34 |----------------------------------------------------------------------------->
train_opt_callback: iter=   228 sample=97/192 sched=0.889413 loss=0.050583 dt=00:15:41 eta=07:19:09 |----------------------------------------------------------------------------->
train_opt_callback: iter=   229 sample=105/192 sched=0.888483 loss=0.043942 dt=00:15:42 eta=07:03:57 |----------------------------------------------------------------------------->
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=113/192 sched=0.887550 loss=0.048901 dt=00:15:41 eta=06:48:05 |----------------------------------------------------------------------------->
train_opt_callback: iter=   231 sample=121/192 sched=0.886613 loss=0.048936 dt=00:15:39 eta=06:31:31 |----------------------------------------------------------------------------->
train_opt_callback: iter=   232 sample=129/192 sched=0.885674 loss=0.047928 dt=00:15:42 eta=06:16:52 |----------------------------------------------------------------------------->
train_opt_callback: iter=   233 sample=137/192 sched=0.884730 loss=0.046294 dt=00:15:32 eta=05:57:30 |----------------------------------------------------------------------------->
train_opt_callback: iter=   234 sample=145/192 sched=0.883784 loss=0.047876 dt=00:15:36 eta=05:43:17 |----------------------------------------------------------------------------->
train_opt_callback: iter=   235 sample=153/192 sched=0.882834 loss=0.048621 dt=00:15:35 eta=05:27:27 |----------------------------------------------------------------------------->
train_opt_callback: iter=   236 sample=161/192 sched=0.881881 loss=0.046712 dt=00:15:30 eta=05:10:09 |----------------------------------------------------------------------------->
train_opt_callback: iter=   237 sample=169/192 sched=0.880924 loss=0.048654 dt=00:15:26 eta=04:53:31 |----------------------------------------------------------------------------->
train_opt_callback: iter=   238 sample=177/192 sched=0.879965 loss=0.044374 dt=00:15:39 eta=04:41:55 |----------------------------------------------------------------------------->
train_opt_callback: iter=   239 sample=185/192 sched=0.879002 loss=0.045983 dt=00:15:30 eta=04:23:39 |----------------------------------------------------------------------------->
train_opt_callback: reshuffle samples. completed epochs: 10
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=1/192 sched=0.878036 loss=0.048949 dt=00:15:33 eta=04:08:52 |----------------------------------------------------------------------------->
train_opt_callback: iter=   241 sample=9/192 sched=0.877066 loss=0.044107 dt=00:15:26 eta=03:51:38 |----------------------------------------------------------------------------->
train_opt_callback: iter=   242 sample=17/192 sched=0.876094 loss=0.042922 dt=00:15:33 eta=03:37:55 |----------------------------------------------------------------------------->
train_opt_callback: iter=   243 sample=25/192 sched=0.875118 loss=0.048055 dt=00:15:30 eta=03:21:30 |----------------------------------------------------------------------------->
train_opt_callback: iter=   244 sample=33/192 sched=0.874139 loss=0.052699 dt=00:15:31 eta=03:06:22 |----------------------------------------------------------------------------->
train_opt_callback: iter=   245 sample=41/192 sched=0.873157 loss=0.056998 dt=00:15:33 eta=02:51:13 |----------------------------------------------------------------------------->
train_opt_callback: iter=   246 sample=49/192 sched=0.872171 loss=0.048870 dt=00:15:31 eta=02:35:19 |----------------------------------------------------------------------------->
train_opt_callback: iter=   247 sample=57/192 sched=0.871183 loss=0.043034 dt=00:15:32 eta=02:19:51 |----------------------------------------------------------------------------->
train_opt_callback: iter=   248 sample=65/192 sched=0.870191 loss=0.051389 dt=00:15:33 eta=02:04:27 |----------------------------------------------------------------------------->
train_opt_callback: iter=   249 sample=73/192 sched=0.869196 loss=0.046855 dt=00:15:38 eta=01:49:30 |----------------------------------------------------------------------------->
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=81/192 sched=0.868198 loss=0.045374 dt=00:15:34 eta=01:33:28 |----------------------------------------------------------------------------->
train_opt_callback: iter=   251 sample=89/192 sched=0.867197 loss=0.046577 dt=00:15:37 eta=01:18:09 |----------------------------------------------------------------------------->
train_opt_callback: iter=   252 sample=97/192 sched=0.866192 loss=0.044559 dt=00:15:29 eta=01:01:59 |----------------------------------------------------------------------------->
train_opt_callback: iter=   253 sample=105/192 sched=0.865185 loss=0.042789 dt=00:15:34 eta=00:46:42 |----------------------------------------------------------------------------->
train_opt_callback: iter=   254 sample=113/192 sched=0.864174 loss=0.048775 dt=00:15:35 eta=00:31:10 |----------------------------------------------------------------------------->
train_opt_callback: iter=   255 sample=121/192 sched=0.863161 loss=0.052028 dt=00:15:28 eta=00:15:28 |----------------------------------------------------------------------------->
train_opt_callback: iter=   256 sample=129/192 sched=0.862144 loss=0.048282 dt=00:15:34 eta=0.0ms |----------------------------------------------------------------------------->
main: total training time: 3d 05:13:40
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