diff --git a/checkpoints/checkpoint-10/config.json b/checkpoints/checkpoint-10/config.json deleted file mode 100644 index 2506d9c463c6d75329ce5833d85f630f8fcfad69..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/config.json +++ /dev/null @@ -1,36 +0,0 @@ -{ - "_name_or_path": "meta-llama/Meta-Llama-3.1-8B", - "architectures": [ - "LlamaForCausalLM" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 128000, - "eos_token_id": 128001, - "head_dim": 128, - "hidden_act": "silu", - "hidden_size": 4096, - "initializer_range": 0.02, - "intermediate_size": 14336, - "max_position_embeddings": 131072, - "mlp_bias": false, - "model_type": "llama", - "num_attention_heads": 32, - "num_hidden_layers": 32, - "num_key_value_heads": 8, - "pretraining_tp": 1, - "rms_norm_eps": 1e-05, - "rope_scaling": { - "factor": 8.0, - "high_freq_factor": 4.0, - "low_freq_factor": 1.0, - "original_max_position_embeddings": 8192, - "rope_type": "llama3" - }, - "rope_theta": 500000.0, - "tie_word_embeddings": false, - "torch_dtype": "float32", - "transformers_version": "4.47.1", - "use_cache": true, - "vocab_size": 138626 -} diff --git a/checkpoints/checkpoint-10/generation_config.json b/checkpoints/checkpoint-10/generation_config.json deleted file mode 100644 index 41de1af1b10386ca8193ae61bdb014263a2402e1..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "bos_token_id": 128000, - "do_sample": true, - "eos_token_id": 128001, - "temperature": 0.6, - "top_p": 0.9, - "transformers_version": "4.47.1" -} diff --git a/checkpoints/checkpoint-10/model-00001-of-00007.safetensors b/checkpoints/checkpoint-10/model-00001-of-00007.safetensors deleted file mode 100644 index 4d719d96359d672c2b79c1b3ae9b62b88c184830..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/model-00001-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d6ad3d1f1c49b141a9735e995f67581dd6c7704be5ce27ad953fa9112cd4fae5 -size 4989259264 diff --git a/checkpoints/checkpoint-10/model-00002-of-00007.safetensors b/checkpoints/checkpoint-10/model-00002-of-00007.safetensors deleted file mode 100644 index 7bc53d248cdbc2381afcd68c20be60d819beeb0c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/model-00002-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b28e50e95c787e68fdf10680635ba27e6d440763a69744dc6ddf473f852231a -size 4899116432 diff --git a/checkpoints/checkpoint-10/model-00003-of-00007.safetensors b/checkpoints/checkpoint-10/model-00003-of-00007.safetensors deleted file mode 100644 index 5501e045b181a6449b2b0997f4ca9f8ce68156ff..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/model-00003-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97 -size 4999813112 diff --git a/checkpoints/checkpoint-10/model-00004-of-00007.safetensors b/checkpoints/checkpoint-10/model-00004-of-00007.safetensors deleted file mode 100644 index 0ea5edb447c5d0bf0491276907abf457c5b0f94a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/model-00004-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042 -size 4999813128 diff --git a/checkpoints/checkpoint-10/model-00005-of-00007.safetensors b/checkpoints/checkpoint-10/model-00005-of-00007.safetensors deleted file mode 100644 index d308635d86f98645d1b129703f4ba4ecc6a84a89..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/model-00005-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7 -size 4832007496 diff --git a/checkpoints/checkpoint-10/model-00006-of-00007.safetensors b/checkpoints/checkpoint-10/model-00006-of-00007.safetensors deleted file mode 100644 index 5e9acc12ad0001a7141778818ba987af85b57b44..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/model-00006-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:68db45b73e0ba04aec9bef14f87dbb7e86d8845d7082ee5da627192a3efa1e1c -size 4999813120 diff --git a/checkpoints/checkpoint-10/model-00007-of-00007.safetensors b/checkpoints/checkpoint-10/model-00007-of-00007.safetensors deleted file mode 100644 index 1232d7d292002985d97e039fc7a0f297c2129a9d..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/model-00007-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fb477d57ec312577d4bee920a2b29ae9731c8cdc13e59ff366820922f076fa18 -size 2741060264 diff --git a/checkpoints/checkpoint-10/model.safetensors.index.json b/checkpoints/checkpoint-10/model.safetensors.index.json deleted file mode 100644 index 0cafabdb5d1403c452cdce739dda1d56d565cf30..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/model.safetensors.index.json +++ /dev/null @@ -1,298 +0,0 @@ -{ - "metadata": { - "total_size": 32460849152 - }, - "weight_map": { - "lm_head.weight": "model-00007-of-00007.safetensors", - "model.embed_tokens.weight": "model-00001-of-00007.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.norm.weight": "model-00007-of-00007.safetensors" - } -} diff --git a/checkpoints/checkpoint-10/optimizer.pt b/checkpoints/checkpoint-10/optimizer.pt deleted file mode 100644 index a481779070afb8232eb83f8b8e92316888f87248..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ec4eb4332c6769d12c1903ec8c898118151e565886c005ab5aa3e78726d339dc -size 9084996512 diff --git a/checkpoints/checkpoint-10/rng_state.pth b/checkpoints/checkpoint-10/rng_state.pth deleted file mode 100644 index 93a52228ea16468eaab41b66555ced3eaaea002c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 -size 14244 diff --git a/checkpoints/checkpoint-10/scheduler.pt b/checkpoints/checkpoint-10/scheduler.pt deleted file mode 100644 index 9f6566f04dc86e4775506ff06ef6bf6468c71c2f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:40e4c309dd42208fdd0a4d16bbdd1e4e2605b9b3bb8d27a9e320633a3db2515e -size 1064 diff --git a/checkpoints/checkpoint-10/special_tokens_map.json b/checkpoints/checkpoint-10/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/checkpoint-10/tokenizer.json b/checkpoints/checkpoint-10/tokenizer.json deleted file mode 100644 index 3b22630724c3503a6df7866a0136d243fb73cb54..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9166d26b16aaa1671e1ecaf1c03bb1dffd06aaa89a5ad56b20e839102e0c1046 -size 18161559 diff --git a/checkpoints/checkpoint-10/tokenizer_config.json b/checkpoints/checkpoint-10/tokenizer_config.json deleted file mode 100644 index ea552528311fe7a370c1b1e63600b0a6f525cb14..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "138370": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138371": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138372": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138373": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138374": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138375": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138376": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138377": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138378": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138379": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138380": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138381": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138382": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138383": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138384": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138385": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138386": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138387": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138388": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138389": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138390": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138391": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138392": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138393": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138394": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138395": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138396": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138397": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138398": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138399": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138400": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138401": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138402": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138403": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138404": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138405": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138406": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138407": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138408": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138409": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138410": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138411": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138412": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138413": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138414": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138415": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138416": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138417": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138418": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138419": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138420": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138421": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138422": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138423": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138424": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138425": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138426": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138427": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138428": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138429": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138430": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138431": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138432": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138433": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138434": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138435": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138436": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138437": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138438": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138439": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138440": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138441": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138442": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138443": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138444": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138445": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138446": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138447": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138448": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138449": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138450": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138451": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138452": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138453": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138454": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138455": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138456": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138457": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138458": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138459": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138460": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138461": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138462": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138463": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138464": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138465": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138466": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138467": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138468": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138469": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138470": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138471": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138472": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138473": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138474": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138475": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138476": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138477": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138478": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138479": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138480": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138481": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138482": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138483": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138484": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138485": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138486": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138487": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138488": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138489": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138490": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138491": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138492": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138493": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138494": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138495": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138496": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138497": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138498": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138499": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138500": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138501": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138502": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138503": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138504": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138505": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138506": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138507": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138508": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138509": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138510": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138511": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138512": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138513": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138514": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138515": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138516": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138517": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138518": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138519": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138520": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138521": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138522": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138523": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138524": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138525": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138526": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138527": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138528": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138529": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138530": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138531": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138532": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138533": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138534": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138535": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138536": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138537": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138538": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138539": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138540": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138541": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138542": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138543": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138544": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138545": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138546": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138547": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138548": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138549": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138550": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138551": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138552": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138553": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138554": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138555": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138556": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138557": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138558": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138559": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138560": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138561": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138562": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138563": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138564": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138565": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138566": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138567": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138568": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138569": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138570": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138571": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138572": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138573": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138574": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138575": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138576": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138577": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138578": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138579": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138580": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138581": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138582": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138583": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138584": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138585": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138586": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138587": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138588": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138589": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138590": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138591": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138592": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138593": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138594": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138595": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138596": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138597": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138598": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138599": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138600": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138601": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138602": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138603": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138604": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138605": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138606": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138607": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138608": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138609": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138610": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138611": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138612": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138613": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138614": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138615": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138616": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138617": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138618": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138619": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138620": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138621": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138622": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138623": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138624": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138625": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/checkpoint-10/trainer_state.json b/checkpoints/checkpoint-10/trainer_state.json deleted file mode 100644 index d5e2374c652d969c8a1d5ff9ec2002de76e38dc4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/trainer_state.json +++ /dev/null @@ -1,32 +0,0 @@ -{ - "best_metric": null, - "best_model_checkpoint": null, - "epoch": 0.02680965147453083, - "eval_steps": 100, - "global_step": 10, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [], - "logging_steps": 100, - "max_steps": 100, - "num_input_tokens_seen": 0, - "num_train_epochs": 1, - "save_steps": 5, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": false - }, - "attributes": {} - } - }, - "total_flos": 1854849071185920.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoints/checkpoint-10/training_args.bin b/checkpoints/checkpoint-10/training_args.bin deleted file mode 100644 index 120c0b8b387b1dd0663ca87ef2a3696e6bbb13a4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-10/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95 -size 5304 diff --git a/checkpoints/checkpoint-15/config.json b/checkpoints/checkpoint-15/config.json deleted file mode 100644 index f54bef4af7553abccb880c0698d8e3e3ea0c12ff..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/config.json +++ /dev/null @@ -1,36 +0,0 @@ -{ - "_name_or_path": "./results/checkpoints/checkpoint-10", - "architectures": [ - "LlamaForCausalLM" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 128000, - "eos_token_id": 128001, - "head_dim": 128, - "hidden_act": "silu", - "hidden_size": 4096, - "initializer_range": 0.02, - "intermediate_size": 14336, - "max_position_embeddings": 131072, - "mlp_bias": false, - "model_type": "llama", - "num_attention_heads": 32, - "num_hidden_layers": 32, - "num_key_value_heads": 8, - "pretraining_tp": 1, - "rms_norm_eps": 1e-05, - "rope_scaling": { - "factor": 8.0, - "high_freq_factor": 4.0, - "low_freq_factor": 1.0, - "original_max_position_embeddings": 8192, - "rope_type": "llama3" - }, - "rope_theta": 500000.0, - "tie_word_embeddings": false, - "torch_dtype": "float32", - "transformers_version": "4.47.1", - "use_cache": true, - "vocab_size": 138626 -} diff --git a/checkpoints/checkpoint-15/generation_config.json b/checkpoints/checkpoint-15/generation_config.json deleted file mode 100644 index 41de1af1b10386ca8193ae61bdb014263a2402e1..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "bos_token_id": 128000, - "do_sample": true, - "eos_token_id": 128001, - "temperature": 0.6, - "top_p": 0.9, - "transformers_version": "4.47.1" -} diff --git a/checkpoints/checkpoint-15/model-00001-of-00007.safetensors b/checkpoints/checkpoint-15/model-00001-of-00007.safetensors deleted file mode 100644 index e8fd297c6805c2fecaa6861eca8f3f0d8e1ddfc9..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/model-00001-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:88a3cd0063572aef99d16b3f15999c65a43775a6fd8369a99aefb28809aad3f3 -size 4989259264 diff --git a/checkpoints/checkpoint-15/model-00002-of-00007.safetensors b/checkpoints/checkpoint-15/model-00002-of-00007.safetensors deleted file mode 100644 index 7bc53d248cdbc2381afcd68c20be60d819beeb0c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/model-00002-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b28e50e95c787e68fdf10680635ba27e6d440763a69744dc6ddf473f852231a -size 4899116432 diff --git a/checkpoints/checkpoint-15/model-00003-of-00007.safetensors b/checkpoints/checkpoint-15/model-00003-of-00007.safetensors deleted file mode 100644 index 5501e045b181a6449b2b0997f4ca9f8ce68156ff..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/model-00003-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97 -size 4999813112 diff --git a/checkpoints/checkpoint-15/model-00004-of-00007.safetensors b/checkpoints/checkpoint-15/model-00004-of-00007.safetensors deleted file mode 100644 index 0ea5edb447c5d0bf0491276907abf457c5b0f94a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/model-00004-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042 -size 4999813128 diff --git a/checkpoints/checkpoint-15/model-00005-of-00007.safetensors b/checkpoints/checkpoint-15/model-00005-of-00007.safetensors deleted file mode 100644 index d308635d86f98645d1b129703f4ba4ecc6a84a89..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/model-00005-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7 -size 4832007496 diff --git a/checkpoints/checkpoint-15/model-00006-of-00007.safetensors b/checkpoints/checkpoint-15/model-00006-of-00007.safetensors deleted file mode 100644 index 5e9acc12ad0001a7141778818ba987af85b57b44..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/model-00006-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:68db45b73e0ba04aec9bef14f87dbb7e86d8845d7082ee5da627192a3efa1e1c -size 4999813120 diff --git a/checkpoints/checkpoint-15/model-00007-of-00007.safetensors b/checkpoints/checkpoint-15/model-00007-of-00007.safetensors deleted file mode 100644 index ef5300014158c6385d26aefb91c732577204b9fc..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/model-00007-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:46deaf856d1fc1b7927266f11055e6a718f534dca86b236a730af5b32447bacf -size 2741060264 diff --git a/checkpoints/checkpoint-15/model.safetensors.index.json b/checkpoints/checkpoint-15/model.safetensors.index.json deleted file mode 100644 index 0cafabdb5d1403c452cdce739dda1d56d565cf30..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/model.safetensors.index.json +++ /dev/null @@ -1,298 +0,0 @@ -{ - "metadata": { - "total_size": 32460849152 - }, - "weight_map": { - "lm_head.weight": "model-00007-of-00007.safetensors", - "model.embed_tokens.weight": "model-00001-of-00007.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.norm.weight": "model-00007-of-00007.safetensors" - } -} diff --git a/checkpoints/checkpoint-15/optimizer.pt b/checkpoints/checkpoint-15/optimizer.pt deleted file mode 100644 index fa61a334aa2deeb1561c1429e8945310e34f2e20..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3ba6b4002b06044c8ac695902add2bea15f51848493af5b2dfecee4f4b22f9ec -size 9084996512 diff --git a/checkpoints/checkpoint-15/rng_state.pth b/checkpoints/checkpoint-15/rng_state.pth deleted file mode 100644 index 93a52228ea16468eaab41b66555ced3eaaea002c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 -size 14244 diff --git a/checkpoints/checkpoint-15/scheduler.pt b/checkpoints/checkpoint-15/scheduler.pt deleted file mode 100644 index 68263d70bb854566fb8c1423daf8236880509ebc..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:df9ab88cfb4f34a33b2015463a12ee7173a22155a5b882e825f80daa1447a739 -size 1064 diff --git a/checkpoints/checkpoint-15/special_tokens_map.json b/checkpoints/checkpoint-15/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/checkpoint-15/tokenizer.json b/checkpoints/checkpoint-15/tokenizer.json deleted file mode 100644 index 3b22630724c3503a6df7866a0136d243fb73cb54..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9166d26b16aaa1671e1ecaf1c03bb1dffd06aaa89a5ad56b20e839102e0c1046 -size 18161559 diff --git a/checkpoints/checkpoint-15/tokenizer_config.json b/checkpoints/checkpoint-15/tokenizer_config.json deleted file mode 100644 index ea552528311fe7a370c1b1e63600b0a6f525cb14..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "138370": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138371": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138372": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138373": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138374": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138375": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138376": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138377": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138378": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138379": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138380": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138381": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138382": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138383": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138384": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138385": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138386": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138387": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138388": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138389": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138390": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138391": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138392": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138393": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138394": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138395": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138396": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138397": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138398": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138399": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138400": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138401": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138402": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138403": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138404": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138405": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138406": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138407": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138408": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138409": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138410": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138411": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138412": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138413": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138414": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138415": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138416": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138417": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138418": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138419": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138420": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138421": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138422": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138423": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138424": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138425": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138426": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138427": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138428": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138429": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138430": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138431": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138432": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138433": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138434": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138435": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138436": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138437": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138438": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138439": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138440": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138441": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138442": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138443": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138444": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138445": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138446": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138447": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138448": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138449": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138450": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138451": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138452": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138453": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138454": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138455": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138456": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138457": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138458": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138459": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138460": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138461": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138462": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138463": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138464": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138465": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138466": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138467": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138468": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138469": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138470": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138471": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138472": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138473": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138474": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138475": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138476": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138477": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138478": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138479": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138480": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138481": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138482": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138483": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138484": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138485": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138486": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138487": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138488": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138489": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138490": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138491": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138492": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138493": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138494": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138495": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138496": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138497": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138498": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138499": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138500": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138501": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138502": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138503": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138504": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138505": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138506": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138507": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138508": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138509": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138510": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138511": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138512": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138513": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138514": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138515": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138516": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138517": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138518": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138519": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138520": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138521": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138522": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138523": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138524": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138525": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138526": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138527": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138528": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138529": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138530": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138531": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138532": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138533": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138534": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138535": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138536": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138537": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138538": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138539": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138540": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138541": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138542": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138543": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138544": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138545": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138546": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138547": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138548": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138549": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138550": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138551": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138552": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138553": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138554": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138555": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138556": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138557": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138558": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138559": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138560": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138561": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138562": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138563": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138564": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138565": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138566": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138567": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138568": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138569": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138570": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138571": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138572": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138573": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138574": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138575": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138576": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138577": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138578": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138579": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138580": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138581": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138582": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138583": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138584": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138585": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138586": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138587": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138588": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138589": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138590": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138591": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138592": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138593": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138594": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138595": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138596": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138597": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138598": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138599": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138600": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138601": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138602": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138603": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138604": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138605": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138606": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138607": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138608": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138609": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138610": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138611": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138612": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138613": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138614": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138615": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138616": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138617": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138618": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138619": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138620": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138621": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138622": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138623": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138624": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138625": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/checkpoint-15/trainer_state.json b/checkpoints/checkpoint-15/trainer_state.json deleted file mode 100644 index 373f2e44a28b44a1d007bb40e0e0ba91d9bccc95..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/trainer_state.json +++ /dev/null @@ -1,32 +0,0 @@ -{ - "best_metric": null, - "best_model_checkpoint": null, - "epoch": 0.040214477211796246, - "eval_steps": 100, - "global_step": 15, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [], - "logging_steps": 100, - "max_steps": 100, - "num_input_tokens_seen": 0, - "num_train_epochs": 1, - "save_steps": 5, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": false - }, - "attributes": {} - } - }, - "total_flos": 2782273606778880.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoints/checkpoint-15/training_args.bin b/checkpoints/checkpoint-15/training_args.bin deleted file mode 100644 index 120c0b8b387b1dd0663ca87ef2a3696e6bbb13a4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-15/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95 -size 5304 diff --git a/checkpoints/checkpoint-20/config.json b/checkpoints/checkpoint-20/config.json deleted file mode 100644 index 4a9603c71f7156f2c31bc6d6b8d080d51b80952f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/config.json +++ /dev/null @@ -1,36 +0,0 @@ -{ - "_name_or_path": "./results/checkpoints/checkpoint-15", - "architectures": [ - "LlamaForCausalLM" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 128000, - "eos_token_id": 128001, - "head_dim": 128, - "hidden_act": "silu", - "hidden_size": 4096, - "initializer_range": 0.02, - "intermediate_size": 14336, - "max_position_embeddings": 131072, - "mlp_bias": false, - "model_type": "llama", - "num_attention_heads": 32, - "num_hidden_layers": 32, - "num_key_value_heads": 8, - "pretraining_tp": 1, - "rms_norm_eps": 1e-05, - "rope_scaling": { - "factor": 8.0, - "high_freq_factor": 4.0, - "low_freq_factor": 1.0, - "original_max_position_embeddings": 8192, - "rope_type": "llama3" - }, - "rope_theta": 500000.0, - "tie_word_embeddings": false, - "torch_dtype": "float32", - "transformers_version": "4.47.1", - "use_cache": true, - "vocab_size": 138626 -} diff --git a/checkpoints/checkpoint-20/generation_config.json b/checkpoints/checkpoint-20/generation_config.json deleted file mode 100644 index 41de1af1b10386ca8193ae61bdb014263a2402e1..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "bos_token_id": 128000, - "do_sample": true, - "eos_token_id": 128001, - "temperature": 0.6, - "top_p": 0.9, - "transformers_version": "4.47.1" -} diff --git a/checkpoints/checkpoint-20/model-00001-of-00007.safetensors b/checkpoints/checkpoint-20/model-00001-of-00007.safetensors deleted file mode 100644 index 92cce76a569f71c55403af6cc7e42255ee36804e..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/model-00001-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:441a649e85ffbee80d11608ee32af8c0ccaa94090f762a22bd70a676c62f08e3 -size 4989259264 diff --git a/checkpoints/checkpoint-20/model-00002-of-00007.safetensors b/checkpoints/checkpoint-20/model-00002-of-00007.safetensors deleted file mode 100644 index 7bc53d248cdbc2381afcd68c20be60d819beeb0c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/model-00002-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b28e50e95c787e68fdf10680635ba27e6d440763a69744dc6ddf473f852231a -size 4899116432 diff --git a/checkpoints/checkpoint-20/model-00003-of-00007.safetensors b/checkpoints/checkpoint-20/model-00003-of-00007.safetensors deleted file mode 100644 index 5501e045b181a6449b2b0997f4ca9f8ce68156ff..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/model-00003-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97 -size 4999813112 diff --git a/checkpoints/checkpoint-20/model-00004-of-00007.safetensors b/checkpoints/checkpoint-20/model-00004-of-00007.safetensors deleted file mode 100644 index 0ea5edb447c5d0bf0491276907abf457c5b0f94a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/model-00004-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042 -size 4999813128 diff --git a/checkpoints/checkpoint-20/model-00005-of-00007.safetensors b/checkpoints/checkpoint-20/model-00005-of-00007.safetensors deleted file mode 100644 index d308635d86f98645d1b129703f4ba4ecc6a84a89..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/model-00005-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7 -size 4832007496 diff --git a/checkpoints/checkpoint-20/model-00006-of-00007.safetensors b/checkpoints/checkpoint-20/model-00006-of-00007.safetensors deleted file mode 100644 index 5e9acc12ad0001a7141778818ba987af85b57b44..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/model-00006-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:68db45b73e0ba04aec9bef14f87dbb7e86d8845d7082ee5da627192a3efa1e1c -size 4999813120 diff --git a/checkpoints/checkpoint-20/model-00007-of-00007.safetensors b/checkpoints/checkpoint-20/model-00007-of-00007.safetensors deleted file mode 100644 index f96af40165eec38e213576aee618bbdaf86fc7a9..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/model-00007-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d0cd5d82128b464579cfe05cdff6a9322487495cd3a04226fcd8329bd24d9669 -size 2741060264 diff --git a/checkpoints/checkpoint-20/model.safetensors.index.json b/checkpoints/checkpoint-20/model.safetensors.index.json deleted file mode 100644 index 0cafabdb5d1403c452cdce739dda1d56d565cf30..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/model.safetensors.index.json +++ /dev/null @@ -1,298 +0,0 @@ -{ - "metadata": { - "total_size": 32460849152 - }, - "weight_map": { - "lm_head.weight": "model-00007-of-00007.safetensors", - "model.embed_tokens.weight": "model-00001-of-00007.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.norm.weight": "model-00007-of-00007.safetensors" - } -} diff --git a/checkpoints/checkpoint-20/optimizer.pt b/checkpoints/checkpoint-20/optimizer.pt deleted file mode 100644 index 87e53988412c2cf74d3dd5b32f6b070ad1f1d949..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7c92d90cef29c09f4715fab538dd3bb212ddd3209f0522feedcfed9e3f684101 -size 9084996512 diff --git a/checkpoints/checkpoint-20/rng_state.pth b/checkpoints/checkpoint-20/rng_state.pth deleted file mode 100644 index 93a52228ea16468eaab41b66555ced3eaaea002c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 -size 14244 diff --git a/checkpoints/checkpoint-20/scheduler.pt b/checkpoints/checkpoint-20/scheduler.pt deleted file mode 100644 index 8badb168336db0db6e7534c7780f2b4f30b21098..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:75adc302d05956609e54639b36ebd36ce527e3456397bc26ea54a5b4dd881a56 -size 1064 diff --git a/checkpoints/checkpoint-20/special_tokens_map.json b/checkpoints/checkpoint-20/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/checkpoint-20/tokenizer.json b/checkpoints/checkpoint-20/tokenizer.json deleted file mode 100644 index 3b22630724c3503a6df7866a0136d243fb73cb54..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9166d26b16aaa1671e1ecaf1c03bb1dffd06aaa89a5ad56b20e839102e0c1046 -size 18161559 diff --git a/checkpoints/checkpoint-20/tokenizer_config.json b/checkpoints/checkpoint-20/tokenizer_config.json deleted file mode 100644 index ea552528311fe7a370c1b1e63600b0a6f525cb14..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "138370": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138371": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138372": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138373": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138374": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138375": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138376": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138377": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138378": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138379": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138380": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138381": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138382": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138383": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138384": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138385": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138386": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138387": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138388": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138389": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138390": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138391": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138392": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138393": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138394": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138395": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138396": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138397": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138398": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138399": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138400": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138401": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138402": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138403": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138404": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138405": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138406": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138407": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138408": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138409": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138410": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138411": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138412": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138413": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138414": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138415": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138416": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138417": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138418": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138419": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138420": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138421": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138422": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138423": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138424": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138425": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138426": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138427": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138428": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138429": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138430": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138431": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138432": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138433": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138434": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138435": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138436": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138437": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138438": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138439": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138440": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138441": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138442": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138443": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138444": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138445": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138446": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138447": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138448": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138449": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138450": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138451": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138452": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138453": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138454": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138455": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138456": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138457": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138458": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138459": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138460": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138461": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138462": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138463": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138464": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138465": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138466": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138467": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138468": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138469": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138470": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138471": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138472": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138473": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138474": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138475": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138476": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138477": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138478": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138479": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138480": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138481": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138482": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138483": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138484": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138485": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138486": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138487": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138488": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138489": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138490": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138491": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138492": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138493": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138494": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138495": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138496": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138497": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138498": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138499": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138500": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138501": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138502": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138503": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138504": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138505": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138506": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138507": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138508": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138509": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138510": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138511": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138512": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138513": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138514": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138515": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138516": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138517": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138518": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138519": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138520": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138521": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138522": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138523": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138524": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138525": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138526": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138527": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138528": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138529": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138530": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138531": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138532": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138533": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138534": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138535": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138536": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138537": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138538": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138539": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138540": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138541": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138542": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138543": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138544": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138545": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138546": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138547": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138548": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138549": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138550": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138551": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138552": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138553": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138554": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138555": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138556": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138557": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138558": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138559": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138560": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138561": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138562": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138563": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138564": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138565": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138566": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138567": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138568": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138569": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138570": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138571": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138572": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138573": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138574": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138575": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138576": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138577": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138578": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138579": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138580": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138581": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138582": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138583": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138584": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138585": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138586": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138587": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138588": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138589": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138590": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138591": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138592": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138593": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138594": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138595": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138596": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138597": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138598": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138599": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138600": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138601": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138602": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138603": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138604": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138605": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138606": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138607": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138608": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138609": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138610": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138611": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138612": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138613": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138614": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138615": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138616": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138617": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138618": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138619": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138620": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138621": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138622": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138623": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138624": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138625": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/checkpoint-20/trainer_state.json b/checkpoints/checkpoint-20/trainer_state.json deleted file mode 100644 index 490ad67ec6ac4d54e9afb251a87816ed30ae9af7..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/trainer_state.json +++ /dev/null @@ -1,32 +0,0 @@ -{ - "best_metric": null, - "best_model_checkpoint": null, - "epoch": 0.05361930294906166, - "eval_steps": 100, - "global_step": 20, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [], - "logging_steps": 100, - "max_steps": 100, - "num_input_tokens_seen": 0, - "num_train_epochs": 1, - "save_steps": 5, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": false - }, - "attributes": {} - } - }, - "total_flos": 3709698142371840.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoints/checkpoint-20/training_args.bin b/checkpoints/checkpoint-20/training_args.bin deleted file mode 100644 index 120c0b8b387b1dd0663ca87ef2a3696e6bbb13a4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-20/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95 -size 5304 diff --git a/checkpoints/checkpoint-25/config.json b/checkpoints/checkpoint-25/config.json deleted file mode 100644 index 4a9603c71f7156f2c31bc6d6b8d080d51b80952f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/config.json +++ /dev/null @@ -1,36 +0,0 @@ -{ - "_name_or_path": "./results/checkpoints/checkpoint-15", - "architectures": [ - "LlamaForCausalLM" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 128000, - "eos_token_id": 128001, - "head_dim": 128, - "hidden_act": "silu", - "hidden_size": 4096, - "initializer_range": 0.02, - "intermediate_size": 14336, - "max_position_embeddings": 131072, - "mlp_bias": false, - "model_type": "llama", - "num_attention_heads": 32, - "num_hidden_layers": 32, - "num_key_value_heads": 8, - "pretraining_tp": 1, - "rms_norm_eps": 1e-05, - "rope_scaling": { - "factor": 8.0, - "high_freq_factor": 4.0, - "low_freq_factor": 1.0, - "original_max_position_embeddings": 8192, - "rope_type": "llama3" - }, - "rope_theta": 500000.0, - "tie_word_embeddings": false, - "torch_dtype": "float32", - "transformers_version": "4.47.1", - "use_cache": true, - "vocab_size": 138626 -} diff --git a/checkpoints/checkpoint-25/generation_config.json b/checkpoints/checkpoint-25/generation_config.json deleted file mode 100644 index 41de1af1b10386ca8193ae61bdb014263a2402e1..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "bos_token_id": 128000, - "do_sample": true, - "eos_token_id": 128001, - "temperature": 0.6, - "top_p": 0.9, - "transformers_version": "4.47.1" -} diff --git a/checkpoints/checkpoint-25/model-00001-of-00007.safetensors b/checkpoints/checkpoint-25/model-00001-of-00007.safetensors deleted file mode 100644 index 8029f6e4d801617974900343be68eb9dd001f30f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/model-00001-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4543852a7cf14d8d1b6e340d75818dbab7d337abca680d0319a3cf9f21412ddb -size 4989259264 diff --git a/checkpoints/checkpoint-25/model-00002-of-00007.safetensors b/checkpoints/checkpoint-25/model-00002-of-00007.safetensors deleted file mode 100644 index 7bc53d248cdbc2381afcd68c20be60d819beeb0c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/model-00002-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b28e50e95c787e68fdf10680635ba27e6d440763a69744dc6ddf473f852231a -size 4899116432 diff --git a/checkpoints/checkpoint-25/model-00003-of-00007.safetensors b/checkpoints/checkpoint-25/model-00003-of-00007.safetensors deleted file mode 100644 index 5501e045b181a6449b2b0997f4ca9f8ce68156ff..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/model-00003-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97 -size 4999813112 diff --git a/checkpoints/checkpoint-25/model-00004-of-00007.safetensors b/checkpoints/checkpoint-25/model-00004-of-00007.safetensors deleted file mode 100644 index 0ea5edb447c5d0bf0491276907abf457c5b0f94a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/model-00004-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042 -size 4999813128 diff --git a/checkpoints/checkpoint-25/model-00005-of-00007.safetensors b/checkpoints/checkpoint-25/model-00005-of-00007.safetensors deleted file mode 100644 index d308635d86f98645d1b129703f4ba4ecc6a84a89..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/model-00005-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7 -size 4832007496 diff --git a/checkpoints/checkpoint-25/model-00006-of-00007.safetensors b/checkpoints/checkpoint-25/model-00006-of-00007.safetensors deleted file mode 100644 index 5e9acc12ad0001a7141778818ba987af85b57b44..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/model-00006-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:68db45b73e0ba04aec9bef14f87dbb7e86d8845d7082ee5da627192a3efa1e1c -size 4999813120 diff --git a/checkpoints/checkpoint-25/model-00007-of-00007.safetensors b/checkpoints/checkpoint-25/model-00007-of-00007.safetensors deleted file mode 100644 index d341a802341bfd5b17e03013066426c5195b9129..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/model-00007-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:841741aa10d1b525a25699cfc5f3b4dee1cfb4fec65116f4ca5b3bad21dca5d5 -size 2741060264 diff --git a/checkpoints/checkpoint-25/model.safetensors.index.json b/checkpoints/checkpoint-25/model.safetensors.index.json deleted file mode 100644 index 0cafabdb5d1403c452cdce739dda1d56d565cf30..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/model.safetensors.index.json +++ /dev/null @@ -1,298 +0,0 @@ -{ - "metadata": { - "total_size": 32460849152 - }, - "weight_map": { - "lm_head.weight": "model-00007-of-00007.safetensors", - "model.embed_tokens.weight": "model-00001-of-00007.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.norm.weight": "model-00007-of-00007.safetensors" - } -} diff --git a/checkpoints/checkpoint-25/optimizer.pt b/checkpoints/checkpoint-25/optimizer.pt deleted file mode 100644 index bb4a1af94f611573e266721b6c5ad976edde9186..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:09d167c5ed440a3ce75f2a6ee5d0340705c3390628915a54bd528dbde2804913 -size 9084996512 diff --git a/checkpoints/checkpoint-25/rng_state.pth b/checkpoints/checkpoint-25/rng_state.pth deleted file mode 100644 index 93a52228ea16468eaab41b66555ced3eaaea002c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 -size 14244 diff --git a/checkpoints/checkpoint-25/scheduler.pt b/checkpoints/checkpoint-25/scheduler.pt deleted file mode 100644 index 4885f0bef4c1508a048ebd99e8d67287ca6f1316..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f488c969dcdda0b6575dd0bfd06cac6927d47ffa52b09770220ad7fdbf864c37 -size 1064 diff --git a/checkpoints/checkpoint-25/special_tokens_map.json b/checkpoints/checkpoint-25/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/checkpoint-25/tokenizer.json b/checkpoints/checkpoint-25/tokenizer.json deleted file mode 100644 index 3b22630724c3503a6df7866a0136d243fb73cb54..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9166d26b16aaa1671e1ecaf1c03bb1dffd06aaa89a5ad56b20e839102e0c1046 -size 18161559 diff --git a/checkpoints/checkpoint-25/tokenizer_config.json b/checkpoints/checkpoint-25/tokenizer_config.json deleted file mode 100644 index ea552528311fe7a370c1b1e63600b0a6f525cb14..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "138370": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138371": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138372": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138373": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138374": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138375": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138376": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138377": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138378": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138379": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138380": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138381": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138382": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138383": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138384": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138385": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138386": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138387": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138388": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138389": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138390": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138391": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138392": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138393": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138394": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138395": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138396": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138397": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138398": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138399": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138400": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138401": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138402": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138403": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138404": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138405": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138406": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138407": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138408": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138409": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138410": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138411": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138412": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138413": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138414": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138415": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138416": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138417": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138418": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138419": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138420": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138421": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138422": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138423": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138424": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138425": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138426": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138427": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138428": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138429": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138430": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138431": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138432": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138433": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138434": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138435": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138436": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138437": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138438": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138439": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138440": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138441": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138442": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138443": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138444": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138445": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138446": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138447": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138448": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138449": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138450": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138451": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138452": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138453": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138454": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138455": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138456": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138457": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138458": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138459": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138460": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138461": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138462": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138463": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138464": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138465": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138466": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138467": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138468": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138469": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138470": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138471": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138472": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138473": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138474": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138475": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138476": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138477": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138478": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138479": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138480": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138481": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138482": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138483": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138484": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138485": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138486": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138487": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138488": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138489": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138490": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138491": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138492": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138493": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138494": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138495": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138496": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138497": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138498": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138499": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138500": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138501": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138502": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138503": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138504": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138505": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138506": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138507": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138508": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138509": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138510": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138511": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138512": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138513": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138514": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138515": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138516": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138517": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138518": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138519": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138520": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138521": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138522": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138523": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138524": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138525": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138526": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138527": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138528": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138529": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138530": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138531": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138532": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138533": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138534": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138535": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138536": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138537": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138538": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138539": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138540": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138541": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138542": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138543": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138544": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138545": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138546": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138547": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138548": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138549": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138550": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138551": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138552": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138553": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138554": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138555": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138556": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138557": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138558": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138559": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138560": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138561": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138562": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138563": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138564": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138565": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138566": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138567": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138568": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138569": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138570": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138571": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138572": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138573": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138574": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138575": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138576": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138577": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138578": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138579": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138580": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138581": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138582": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138583": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138584": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138585": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138586": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138587": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138588": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138589": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138590": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138591": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138592": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138593": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138594": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138595": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138596": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138597": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138598": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138599": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138600": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138601": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138602": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138603": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138604": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138605": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138606": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138607": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138608": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138609": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138610": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138611": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138612": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138613": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138614": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138615": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138616": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138617": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138618": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138619": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138620": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138621": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138622": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138623": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138624": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138625": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/checkpoint-25/trainer_state.json b/checkpoints/checkpoint-25/trainer_state.json deleted file mode 100644 index 589129f146c39d8d6c93add76d11a0685c6008cb..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/trainer_state.json +++ /dev/null @@ -1,32 +0,0 @@ -{ - "best_metric": null, - "best_model_checkpoint": null, - "epoch": 0.06702412868632708, - "eval_steps": 100, - "global_step": 25, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [], - "logging_steps": 100, - "max_steps": 100, - "num_input_tokens_seen": 0, - "num_train_epochs": 1, - "save_steps": 5, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": false - }, - "attributes": {} - } - }, - "total_flos": 4637122677964800.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoints/checkpoint-25/training_args.bin b/checkpoints/checkpoint-25/training_args.bin deleted file mode 100644 index 120c0b8b387b1dd0663ca87ef2a3696e6bbb13a4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-25/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95 -size 5304 diff --git a/checkpoints/checkpoint-30/config.json b/checkpoints/checkpoint-30/config.json deleted file mode 100644 index 4a9603c71f7156f2c31bc6d6b8d080d51b80952f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/config.json +++ /dev/null @@ -1,36 +0,0 @@ -{ - "_name_or_path": "./results/checkpoints/checkpoint-15", - "architectures": [ - "LlamaForCausalLM" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 128000, - "eos_token_id": 128001, - "head_dim": 128, - "hidden_act": "silu", - "hidden_size": 4096, - "initializer_range": 0.02, - "intermediate_size": 14336, - "max_position_embeddings": 131072, - "mlp_bias": false, - "model_type": "llama", - "num_attention_heads": 32, - "num_hidden_layers": 32, - "num_key_value_heads": 8, - "pretraining_tp": 1, - "rms_norm_eps": 1e-05, - "rope_scaling": { - "factor": 8.0, - "high_freq_factor": 4.0, - "low_freq_factor": 1.0, - "original_max_position_embeddings": 8192, - "rope_type": "llama3" - }, - "rope_theta": 500000.0, - "tie_word_embeddings": false, - "torch_dtype": "float32", - "transformers_version": "4.47.1", - "use_cache": true, - "vocab_size": 138626 -} diff --git a/checkpoints/checkpoint-30/generation_config.json b/checkpoints/checkpoint-30/generation_config.json deleted file mode 100644 index 41de1af1b10386ca8193ae61bdb014263a2402e1..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "bos_token_id": 128000, - "do_sample": true, - "eos_token_id": 128001, - "temperature": 0.6, - "top_p": 0.9, - "transformers_version": "4.47.1" -} diff --git a/checkpoints/checkpoint-30/model-00001-of-00007.safetensors b/checkpoints/checkpoint-30/model-00001-of-00007.safetensors deleted file mode 100644 index 0882319d25f9af9683c156a475101bd822fa590a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/model-00001-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0f8004cf4936a236db8a09fe6ec6cabdeaf0fa3a540664b7cb27ad7625ef5e09 -size 4989259264 diff --git a/checkpoints/checkpoint-30/model-00002-of-00007.safetensors b/checkpoints/checkpoint-30/model-00002-of-00007.safetensors deleted file mode 100644 index 7bc53d248cdbc2381afcd68c20be60d819beeb0c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/model-00002-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b28e50e95c787e68fdf10680635ba27e6d440763a69744dc6ddf473f852231a -size 4899116432 diff --git a/checkpoints/checkpoint-30/model-00003-of-00007.safetensors b/checkpoints/checkpoint-30/model-00003-of-00007.safetensors deleted file mode 100644 index 5501e045b181a6449b2b0997f4ca9f8ce68156ff..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/model-00003-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97 -size 4999813112 diff --git a/checkpoints/checkpoint-30/model-00004-of-00007.safetensors b/checkpoints/checkpoint-30/model-00004-of-00007.safetensors deleted file mode 100644 index 0ea5edb447c5d0bf0491276907abf457c5b0f94a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/model-00004-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042 -size 4999813128 diff --git a/checkpoints/checkpoint-30/model-00005-of-00007.safetensors b/checkpoints/checkpoint-30/model-00005-of-00007.safetensors deleted file mode 100644 index d308635d86f98645d1b129703f4ba4ecc6a84a89..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/model-00005-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7 -size 4832007496 diff --git a/checkpoints/checkpoint-30/model-00006-of-00007.safetensors b/checkpoints/checkpoint-30/model-00006-of-00007.safetensors deleted file mode 100644 index 5e9acc12ad0001a7141778818ba987af85b57b44..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/model-00006-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:68db45b73e0ba04aec9bef14f87dbb7e86d8845d7082ee5da627192a3efa1e1c -size 4999813120 diff --git a/checkpoints/checkpoint-30/model-00007-of-00007.safetensors b/checkpoints/checkpoint-30/model-00007-of-00007.safetensors deleted file mode 100644 index 5503ee3761f99969f4c7bd300fe1e91185762a17..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/model-00007-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e0863336df41d524bff8280345c1ebfe65f21451a37e73b4eea1a33fb4b199e1 -size 2741060264 diff --git a/checkpoints/checkpoint-30/model.safetensors.index.json b/checkpoints/checkpoint-30/model.safetensors.index.json deleted file mode 100644 index 0cafabdb5d1403c452cdce739dda1d56d565cf30..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/model.safetensors.index.json +++ /dev/null @@ -1,298 +0,0 @@ -{ - "metadata": { - "total_size": 32460849152 - }, - "weight_map": { - "lm_head.weight": "model-00007-of-00007.safetensors", - "model.embed_tokens.weight": "model-00001-of-00007.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.norm.weight": "model-00007-of-00007.safetensors" - } -} diff --git a/checkpoints/checkpoint-30/optimizer.pt b/checkpoints/checkpoint-30/optimizer.pt deleted file mode 100644 index d18f992e3815675a81f9cf04037f52178b6b51d8..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e7a83afd79b268a35622711ee15ebf61d844cb5678b009aceb5855c40ed4958c -size 9084996512 diff --git a/checkpoints/checkpoint-30/rng_state.pth b/checkpoints/checkpoint-30/rng_state.pth deleted file mode 100644 index 93a52228ea16468eaab41b66555ced3eaaea002c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 -size 14244 diff --git a/checkpoints/checkpoint-30/scheduler.pt b/checkpoints/checkpoint-30/scheduler.pt deleted file mode 100644 index f4a35b4b6619e13fc72c92f4fa6742b472a35cb4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1de5136d02a1174158c3d02ec738a9c0a1a5531aa5bb49ea440cd3d0f7bb1f8f -size 1064 diff --git a/checkpoints/checkpoint-30/special_tokens_map.json b/checkpoints/checkpoint-30/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/checkpoint-30/tokenizer.json b/checkpoints/checkpoint-30/tokenizer.json deleted file mode 100644 index 3b22630724c3503a6df7866a0136d243fb73cb54..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9166d26b16aaa1671e1ecaf1c03bb1dffd06aaa89a5ad56b20e839102e0c1046 -size 18161559 diff --git a/checkpoints/checkpoint-30/tokenizer_config.json b/checkpoints/checkpoint-30/tokenizer_config.json deleted file mode 100644 index ea552528311fe7a370c1b1e63600b0a6f525cb14..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "138370": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138371": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138372": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138373": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138374": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138375": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138376": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138377": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138378": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138379": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138380": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138381": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138382": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138383": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138384": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138385": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138386": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138387": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138388": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138389": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138390": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138391": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138392": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138393": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138394": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138395": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138396": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138397": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138398": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138399": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138400": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138401": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138402": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138403": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138404": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138405": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138406": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138407": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138408": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138409": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138410": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138411": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138412": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138413": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138414": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138415": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138416": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138417": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138418": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138419": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138420": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138421": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138422": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138423": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138424": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138425": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138426": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138427": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138428": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138429": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138430": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138431": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138432": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138433": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138434": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138435": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138436": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138437": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138438": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138439": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138440": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138441": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138442": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138443": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138444": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138445": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138446": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138447": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138448": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138449": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138450": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138451": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138452": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138453": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138454": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138455": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138456": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138457": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138458": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138459": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138460": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138461": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138462": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138463": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138464": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138465": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138466": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138467": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138468": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138469": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138470": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138471": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138472": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138473": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138474": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138475": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138476": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138477": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138478": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138479": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138480": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138481": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138482": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138483": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138484": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138485": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138486": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138487": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138488": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138489": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138490": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138491": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138492": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138493": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138494": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138495": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138496": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138497": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138498": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138499": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138500": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138501": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138502": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138503": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138504": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138505": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138506": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138507": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138508": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138509": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138510": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138511": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138512": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138513": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138514": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138515": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138516": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138517": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138518": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138519": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138520": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138521": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138522": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138523": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138524": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138525": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138526": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138527": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138528": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138529": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138530": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138531": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138532": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138533": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138534": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138535": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138536": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138537": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138538": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138539": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138540": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138541": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138542": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138543": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138544": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138545": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138546": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138547": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138548": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138549": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138550": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138551": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138552": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138553": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138554": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138555": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138556": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138557": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138558": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138559": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138560": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138561": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138562": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138563": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138564": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138565": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138566": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138567": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138568": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138569": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138570": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138571": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138572": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138573": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138574": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138575": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138576": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138577": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138578": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138579": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138580": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138581": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138582": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138583": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138584": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138585": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138586": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138587": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138588": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138589": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138590": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138591": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138592": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138593": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138594": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138595": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138596": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138597": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138598": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138599": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138600": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138601": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138602": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138603": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138604": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138605": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138606": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138607": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138608": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138609": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138610": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138611": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138612": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138613": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138614": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138615": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138616": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138617": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138618": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138619": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138620": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138621": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138622": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138623": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138624": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138625": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/checkpoint-30/trainer_state.json b/checkpoints/checkpoint-30/trainer_state.json deleted file mode 100644 index 58c2a940fb9a16caca4ceb8713c2adf78bf619d9..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/trainer_state.json +++ /dev/null @@ -1,32 +0,0 @@ -{ - "best_metric": null, - "best_model_checkpoint": null, - "epoch": 0.08042895442359249, - "eval_steps": 100, - "global_step": 30, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [], - "logging_steps": 100, - "max_steps": 100, - "num_input_tokens_seen": 0, - "num_train_epochs": 1, - "save_steps": 5, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": false - }, - "attributes": {} - } - }, - "total_flos": 5564547213557760.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoints/checkpoint-30/training_args.bin b/checkpoints/checkpoint-30/training_args.bin deleted file mode 100644 index 120c0b8b387b1dd0663ca87ef2a3696e6bbb13a4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-30/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95 -size 5304 diff --git a/checkpoints/checkpoint-35/config.json b/checkpoints/checkpoint-35/config.json deleted file mode 100644 index 0c80563abca8d4a2b01cf752dba1eae5eebb0146..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/config.json +++ /dev/null @@ -1,36 +0,0 @@ -{ - "_name_or_path": "./results/checkpoints/checkpoint-30", - "architectures": [ - "LlamaForCausalLM" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 128000, - "eos_token_id": 128001, - "head_dim": 128, - "hidden_act": "silu", - "hidden_size": 4096, - "initializer_range": 0.02, - "intermediate_size": 14336, - "max_position_embeddings": 131072, - "mlp_bias": false, - "model_type": "llama", - "num_attention_heads": 32, - "num_hidden_layers": 32, - "num_key_value_heads": 8, - "pretraining_tp": 1, - "rms_norm_eps": 1e-05, - "rope_scaling": { - "factor": 8.0, - "high_freq_factor": 4.0, - "low_freq_factor": 1.0, - "original_max_position_embeddings": 8192, - "rope_type": "llama3" - }, - "rope_theta": 500000.0, - "tie_word_embeddings": false, - "torch_dtype": "float32", - "transformers_version": "4.47.1", - "use_cache": true, - "vocab_size": 138626 -} diff --git a/checkpoints/checkpoint-35/generation_config.json b/checkpoints/checkpoint-35/generation_config.json deleted file mode 100644 index 41de1af1b10386ca8193ae61bdb014263a2402e1..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "bos_token_id": 128000, - "do_sample": true, - "eos_token_id": 128001, - "temperature": 0.6, - "top_p": 0.9, - "transformers_version": "4.47.1" -} diff --git a/checkpoints/checkpoint-35/model-00001-of-00007.safetensors b/checkpoints/checkpoint-35/model-00001-of-00007.safetensors deleted file mode 100644 index be9ce298393ebd584d984f97bbe62c2762c0d84d..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/model-00001-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1c639cca74f3e21d0d21638ee1f69eedbe280e46c8f61380e17d96f8a7b54808 -size 4989259264 diff --git a/checkpoints/checkpoint-35/model-00002-of-00007.safetensors b/checkpoints/checkpoint-35/model-00002-of-00007.safetensors deleted file mode 100644 index 7bc53d248cdbc2381afcd68c20be60d819beeb0c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/model-00002-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b28e50e95c787e68fdf10680635ba27e6d440763a69744dc6ddf473f852231a -size 4899116432 diff --git a/checkpoints/checkpoint-35/model-00003-of-00007.safetensors b/checkpoints/checkpoint-35/model-00003-of-00007.safetensors deleted file mode 100644 index 5501e045b181a6449b2b0997f4ca9f8ce68156ff..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/model-00003-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97 -size 4999813112 diff --git a/checkpoints/checkpoint-35/model-00004-of-00007.safetensors b/checkpoints/checkpoint-35/model-00004-of-00007.safetensors deleted file mode 100644 index 0ea5edb447c5d0bf0491276907abf457c5b0f94a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/model-00004-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042 -size 4999813128 diff --git a/checkpoints/checkpoint-35/model-00005-of-00007.safetensors b/checkpoints/checkpoint-35/model-00005-of-00007.safetensors deleted file mode 100644 index d308635d86f98645d1b129703f4ba4ecc6a84a89..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/model-00005-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7 -size 4832007496 diff --git a/checkpoints/checkpoint-35/model-00006-of-00007.safetensors b/checkpoints/checkpoint-35/model-00006-of-00007.safetensors deleted file mode 100644 index 5e9acc12ad0001a7141778818ba987af85b57b44..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/model-00006-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:68db45b73e0ba04aec9bef14f87dbb7e86d8845d7082ee5da627192a3efa1e1c -size 4999813120 diff --git a/checkpoints/checkpoint-35/model-00007-of-00007.safetensors b/checkpoints/checkpoint-35/model-00007-of-00007.safetensors deleted file mode 100644 index a5e24759d047cfbb7951b4848688604bae6eb4cf..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/model-00007-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:704de3a6018eb9c6f697e4c7127e3abefa57f368847fcd4bfdda2e02a00bbec0 -size 2741060264 diff --git a/checkpoints/checkpoint-35/model.safetensors.index.json b/checkpoints/checkpoint-35/model.safetensors.index.json deleted file mode 100644 index 0cafabdb5d1403c452cdce739dda1d56d565cf30..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/model.safetensors.index.json +++ /dev/null @@ -1,298 +0,0 @@ -{ - "metadata": { - "total_size": 32460849152 - }, - "weight_map": { - "lm_head.weight": "model-00007-of-00007.safetensors", - "model.embed_tokens.weight": "model-00001-of-00007.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.norm.weight": "model-00007-of-00007.safetensors" - } -} diff --git a/checkpoints/checkpoint-35/optimizer.pt b/checkpoints/checkpoint-35/optimizer.pt deleted file mode 100644 index 1dc84105267be0b08e9f67159105065bef2edb81..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1861068c476e2f64120e8aa9da9bfdc328ba0881ddb61e9ef202da9a41d80a1a -size 9084996512 diff --git a/checkpoints/checkpoint-35/rng_state.pth b/checkpoints/checkpoint-35/rng_state.pth deleted file mode 100644 index 93a52228ea16468eaab41b66555ced3eaaea002c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 -size 14244 diff --git a/checkpoints/checkpoint-35/scheduler.pt b/checkpoints/checkpoint-35/scheduler.pt deleted file mode 100644 index a2e2db6ce48a7011af96547ed581e83f50afef33..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7cd480683d7fc39320e4d3d4366f483aed3eca57992419fd0cce1468782acbef -size 1064 diff --git a/checkpoints/checkpoint-35/special_tokens_map.json b/checkpoints/checkpoint-35/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/checkpoint-35/tokenizer.json b/checkpoints/checkpoint-35/tokenizer.json deleted file mode 100644 index 3b22630724c3503a6df7866a0136d243fb73cb54..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9166d26b16aaa1671e1ecaf1c03bb1dffd06aaa89a5ad56b20e839102e0c1046 -size 18161559 diff --git a/checkpoints/checkpoint-35/tokenizer_config.json b/checkpoints/checkpoint-35/tokenizer_config.json deleted file mode 100644 index ea552528311fe7a370c1b1e63600b0a6f525cb14..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "138370": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138371": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138372": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138373": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138374": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138375": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138376": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138377": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138378": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138379": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138380": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138381": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138382": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138383": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138384": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138385": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138386": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138387": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138388": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138389": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138390": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138391": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138392": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138393": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138394": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138395": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138396": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138397": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138398": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138399": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138400": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138401": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138402": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138403": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138404": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138405": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138406": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138407": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138408": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138409": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138410": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138411": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138412": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138413": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138414": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138415": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138416": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138417": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138418": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138419": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138420": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138421": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138422": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138423": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138424": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138425": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138426": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138427": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138428": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138429": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138430": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138431": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138432": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138433": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138434": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138435": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138436": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138437": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138438": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138439": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138440": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138441": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138442": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138443": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138444": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138445": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138446": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138447": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138448": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138449": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138450": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138451": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138452": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138453": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138454": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138455": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138456": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138457": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138458": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138459": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138460": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138461": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138462": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138463": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138464": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138465": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138466": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138467": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138468": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138469": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138470": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138471": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138472": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138473": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138474": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138475": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138476": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138477": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138478": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138479": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138480": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138481": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138482": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138483": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138484": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138485": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138486": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138487": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138488": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138489": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138490": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138491": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138492": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138493": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138494": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138495": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138496": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138497": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138498": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138499": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138500": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138501": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138502": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138503": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138504": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138505": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138506": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138507": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138508": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138509": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138510": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138511": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138512": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138513": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138514": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138515": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138516": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138517": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138518": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138519": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138520": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138521": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138522": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138523": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138524": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138525": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138526": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138527": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138528": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138529": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138530": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138531": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138532": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138533": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138534": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138535": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138536": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138537": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138538": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138539": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138540": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138541": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138542": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138543": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138544": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138545": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138546": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138547": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138548": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138549": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138550": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138551": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138552": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138553": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138554": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138555": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138556": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138557": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138558": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138559": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138560": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138561": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138562": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138563": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138564": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138565": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138566": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138567": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138568": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138569": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138570": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138571": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138572": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138573": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138574": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138575": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138576": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138577": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138578": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138579": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138580": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138581": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138582": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138583": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138584": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138585": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138586": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138587": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138588": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138589": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138590": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138591": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138592": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138593": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138594": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138595": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138596": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138597": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138598": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138599": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138600": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138601": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138602": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138603": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138604": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138605": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138606": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138607": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138608": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138609": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138610": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138611": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138612": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138613": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138614": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138615": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138616": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138617": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138618": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138619": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138620": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138621": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138622": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138623": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138624": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138625": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/checkpoint-35/trainer_state.json b/checkpoints/checkpoint-35/trainer_state.json deleted file mode 100644 index c7bab3d4ca494f9dba5427ec4a905c141c059693..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/trainer_state.json +++ /dev/null @@ -1,32 +0,0 @@ -{ - "best_metric": null, - "best_model_checkpoint": null, - "epoch": 0.0938337801608579, - "eval_steps": 100, - "global_step": 35, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [], - "logging_steps": 100, - "max_steps": 100, - "num_input_tokens_seen": 0, - "num_train_epochs": 1, - "save_steps": 5, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": false - }, - "attributes": {} - } - }, - "total_flos": 6491971749150720.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoints/checkpoint-35/training_args.bin b/checkpoints/checkpoint-35/training_args.bin deleted file mode 100644 index 120c0b8b387b1dd0663ca87ef2a3696e6bbb13a4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-35/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95 -size 5304 diff --git a/checkpoints/checkpoint-5/config.json b/checkpoints/checkpoint-5/config.json deleted file mode 100644 index 2506d9c463c6d75329ce5833d85f630f8fcfad69..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/config.json +++ /dev/null @@ -1,36 +0,0 @@ -{ - "_name_or_path": "meta-llama/Meta-Llama-3.1-8B", - "architectures": [ - "LlamaForCausalLM" - ], - "attention_bias": false, - "attention_dropout": 0.0, - "bos_token_id": 128000, - "eos_token_id": 128001, - "head_dim": 128, - "hidden_act": "silu", - "hidden_size": 4096, - "initializer_range": 0.02, - "intermediate_size": 14336, - "max_position_embeddings": 131072, - "mlp_bias": false, - "model_type": "llama", - "num_attention_heads": 32, - "num_hidden_layers": 32, - "num_key_value_heads": 8, - "pretraining_tp": 1, - "rms_norm_eps": 1e-05, - "rope_scaling": { - "factor": 8.0, - "high_freq_factor": 4.0, - "low_freq_factor": 1.0, - "original_max_position_embeddings": 8192, - "rope_type": "llama3" - }, - "rope_theta": 500000.0, - "tie_word_embeddings": false, - "torch_dtype": "float32", - "transformers_version": "4.47.1", - "use_cache": true, - "vocab_size": 138626 -} diff --git a/checkpoints/checkpoint-5/generation_config.json b/checkpoints/checkpoint-5/generation_config.json deleted file mode 100644 index 41de1af1b10386ca8193ae61bdb014263a2402e1..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/generation_config.json +++ /dev/null @@ -1,9 +0,0 @@ -{ - "_from_model_config": true, - "bos_token_id": 128000, - "do_sample": true, - "eos_token_id": 128001, - "temperature": 0.6, - "top_p": 0.9, - "transformers_version": "4.47.1" -} diff --git a/checkpoints/checkpoint-5/model-00001-of-00007.safetensors b/checkpoints/checkpoint-5/model-00001-of-00007.safetensors deleted file mode 100644 index b9bd0a14146bea9b0b7ee3985ccf4b66523dfa21..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/model-00001-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:096c333a951ea83c2f28b22bfa7011ed7e2ec44aa3aca1730626e16162a3137e -size 4989259264 diff --git a/checkpoints/checkpoint-5/model-00002-of-00007.safetensors b/checkpoints/checkpoint-5/model-00002-of-00007.safetensors deleted file mode 100644 index 7bc53d248cdbc2381afcd68c20be60d819beeb0c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/model-00002-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b28e50e95c787e68fdf10680635ba27e6d440763a69744dc6ddf473f852231a -size 4899116432 diff --git a/checkpoints/checkpoint-5/model-00003-of-00007.safetensors b/checkpoints/checkpoint-5/model-00003-of-00007.safetensors deleted file mode 100644 index 5501e045b181a6449b2b0997f4ca9f8ce68156ff..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/model-00003-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:afa0e22bcade9527b5aeb86066e139cc30979f8492c753ff3277e6189863ab97 -size 4999813112 diff --git a/checkpoints/checkpoint-5/model-00004-of-00007.safetensors b/checkpoints/checkpoint-5/model-00004-of-00007.safetensors deleted file mode 100644 index 0ea5edb447c5d0bf0491276907abf457c5b0f94a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/model-00004-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dc4f5352f30ea036b0a4e24ba9b029dd94a2b30a716c81acc1c4a5e7bb47a042 -size 4999813128 diff --git a/checkpoints/checkpoint-5/model-00005-of-00007.safetensors b/checkpoints/checkpoint-5/model-00005-of-00007.safetensors deleted file mode 100644 index d308635d86f98645d1b129703f4ba4ecc6a84a89..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/model-00005-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d9450b209df4cb026b6669e618fcdb6ff4f5bd0a711fb2e502afe0b95eb3ad7 -size 4832007496 diff --git a/checkpoints/checkpoint-5/model-00006-of-00007.safetensors b/checkpoints/checkpoint-5/model-00006-of-00007.safetensors deleted file mode 100644 index 5e9acc12ad0001a7141778818ba987af85b57b44..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/model-00006-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:68db45b73e0ba04aec9bef14f87dbb7e86d8845d7082ee5da627192a3efa1e1c -size 4999813120 diff --git a/checkpoints/checkpoint-5/model-00007-of-00007.safetensors b/checkpoints/checkpoint-5/model-00007-of-00007.safetensors deleted file mode 100644 index 315beca371e4a14645aacdc18fe2825af2c4044a..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/model-00007-of-00007.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5b0ee123763155e1fd509834bfa8651508532c4a6bfca01a114843a02fc78a7b -size 2741060264 diff --git a/checkpoints/checkpoint-5/model.safetensors.index.json b/checkpoints/checkpoint-5/model.safetensors.index.json deleted file mode 100644 index 0cafabdb5d1403c452cdce739dda1d56d565cf30..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/model.safetensors.index.json +++ /dev/null @@ -1,298 +0,0 @@ -{ - "metadata": { - "total_size": 32460849152 - }, - "weight_map": { - "lm_head.weight": "model-00007-of-00007.safetensors", - "model.embed_tokens.weight": "model-00001-of-00007.safetensors", - "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", - "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", - "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", - "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", - "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", - "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", - "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", - "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", - "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", - "model.norm.weight": "model-00007-of-00007.safetensors" - } -} diff --git a/checkpoints/checkpoint-5/optimizer.pt b/checkpoints/checkpoint-5/optimizer.pt deleted file mode 100644 index f6def2f02ae4cb1cec5182ece6507425a0604980..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:443d3eac1007c36eac4aca97c64ebe30f23f11022476c2f1277faf8cb34e2222 -size 9084996512 diff --git a/checkpoints/checkpoint-5/rng_state.pth b/checkpoints/checkpoint-5/rng_state.pth deleted file mode 100644 index 93a52228ea16468eaab41b66555ced3eaaea002c..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 -size 14244 diff --git a/checkpoints/checkpoint-5/scheduler.pt b/checkpoints/checkpoint-5/scheduler.pt deleted file mode 100644 index 2e425577b0946a3cbecfbefc0a54fe08da534f86..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8df43d8f55fa78c375b338d10b20812d07eb9723ebaf98918ff2a22cf17d6612 -size 1064 diff --git a/checkpoints/checkpoint-5/special_tokens_map.json b/checkpoints/checkpoint-5/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/checkpoint-5/tokenizer.json b/checkpoints/checkpoint-5/tokenizer.json deleted file mode 100644 index 3b22630724c3503a6df7866a0136d243fb73cb54..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9166d26b16aaa1671e1ecaf1c03bb1dffd06aaa89a5ad56b20e839102e0c1046 -size 18161559 diff --git a/checkpoints/checkpoint-5/tokenizer_config.json b/checkpoints/checkpoint-5/tokenizer_config.json deleted file mode 100644 index ea552528311fe7a370c1b1e63600b0a6f525cb14..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "138370": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138371": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138372": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138373": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138374": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138375": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138376": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138377": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138378": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138379": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138380": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138381": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138382": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138383": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138384": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138385": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138386": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138387": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138388": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138389": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138390": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138391": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138392": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138393": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138394": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138395": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138396": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138397": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138398": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138399": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138400": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138401": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138402": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138403": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138404": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138405": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138406": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138407": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138408": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138409": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138410": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138411": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138412": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138413": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138414": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138415": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138416": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138417": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138418": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138419": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138420": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138421": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138422": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138423": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138424": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138425": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138426": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138427": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138428": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138429": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138430": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138431": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138432": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138433": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138434": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138435": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138436": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138437": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138438": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138439": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138440": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138441": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138442": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138443": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138444": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138445": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138446": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138447": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138448": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138449": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138450": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138451": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138452": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138453": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138454": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138455": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138456": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138457": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138458": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138459": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138460": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138461": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138462": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138463": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138464": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138465": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138466": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138467": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138468": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138469": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138470": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138471": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138472": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138473": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138474": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138475": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138476": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138477": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138478": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138479": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138480": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138481": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138482": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138483": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138484": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138485": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138486": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138487": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138488": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138489": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138490": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138491": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138492": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138493": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138494": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138495": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138496": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138497": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138498": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138499": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138500": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138501": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138502": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138503": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138504": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138505": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138506": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138507": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138508": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138509": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138510": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138511": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138512": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138513": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138514": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138515": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138516": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138517": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138518": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138519": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138520": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138521": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138522": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138523": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138524": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138525": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138526": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138527": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138528": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138529": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138530": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138531": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138532": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138533": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138534": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138535": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138536": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138537": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138538": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138539": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138540": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138541": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138542": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138543": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138544": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138545": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138546": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138547": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138548": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138549": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138550": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138551": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138552": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138553": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138554": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138555": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138556": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138557": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138558": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138559": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138560": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138561": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138562": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138563": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138564": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138565": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138566": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138567": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138568": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138569": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138570": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138571": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138572": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138573": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138574": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138575": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138576": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138577": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138578": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138579": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138580": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138581": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138582": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138583": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138584": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138585": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138586": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138587": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138588": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138589": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138590": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138591": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138592": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138593": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138594": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138595": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138596": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138597": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138598": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138599": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138600": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138601": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138602": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138603": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138604": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138605": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138606": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138607": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138608": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138609": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138610": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138611": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138612": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138613": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138614": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138615": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138616": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138617": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138618": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138619": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138620": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138621": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138622": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138623": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138624": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "138625": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/checkpoint-5/trainer_state.json b/checkpoints/checkpoint-5/trainer_state.json deleted file mode 100644 index 2f156b048553f691618a93f16c99bbab89e85700..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/trainer_state.json +++ /dev/null @@ -1,32 +0,0 @@ -{ - "best_metric": null, - "best_model_checkpoint": null, - "epoch": 0.013404825737265416, - "eval_steps": 100, - "global_step": 5, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [], - "logging_steps": 100, - "max_steps": 100, - "num_input_tokens_seen": 0, - "num_train_epochs": 1, - "save_steps": 5, - "stateful_callbacks": { - "TrainerControl": { - "args": { - "should_epoch_stop": false, - "should_evaluate": false, - "should_log": false, - "should_save": true, - "should_training_stop": false - }, - "attributes": {} - } - }, - "total_flos": 927424535592960.0, - "train_batch_size": 8, - "trial_name": null, - "trial_params": null -} diff --git a/checkpoints/checkpoint-5/training_args.bin b/checkpoints/checkpoint-5/training_args.bin deleted file mode 100644 index 120c0b8b387b1dd0663ca87ef2a3696e6bbb13a4..0000000000000000000000000000000000000000 --- a/checkpoints/checkpoint-5/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95 -size 5304