Delete logs

logs/checkpoint-1815/config.json

@@ -1,49 +0,0 @@
-{
-  "architectures": [
-    "LlamaForSequenceClassification"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 3072,
-  "id2label": {
-    "0": "LABEL_0"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "max_position_embeddings": 131072,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "pad_token_id": 128256,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 32.0,
-    "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": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
-  "use_cache": true,
-  "vhead_layer_type": "mlp",
-  "vhead_num_layers": 1,
-  "vhead_num_neurons": 1024,
-  "vocab_size": 128257
-}

logs/checkpoint-1815/global_step1812/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:99d4e8521264ab2b77f0d6416a9a676707e22e719b55624f62b13d67ad8c4f9f
-size 95632

logs/checkpoint-1815/global_step1812/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e1795546d102e050ed99e44bee094d4f8cdde3a888030f09361cf6860da0dd6
-size 95632

logs/checkpoint-1815/global_step1812/mp_rank_00_model_states.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1d296b86467f1cf14de623e8649952da8e7a1c8b19ab937615117ffab6ee3749
-size 12851250040

logs/checkpoint-1815/latest

@@ -1 +0,0 @@
-global_step1812

logs/checkpoint-1815/model-00001-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:649345472fb9b944ace6ec268be695b3dea6f2d36bf2d4c7a23fa4806bbc8d7e
-size 4965805330

logs/checkpoint-1815/model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:20bcf0e5b82fed50412cd5ac5346c18302d16a55c7c43fe3542a6194f1164619
-size 1459760760

logs/checkpoint-1815/model.safetensors.index.json

@@ -1,263 +0,0 @@
-{
-  "metadata": {
-    "total_size": 6425536522
-  },
-  "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors",
-    "router": "model-00001-of-00002.safetensors",
-    "score.weight": "model-00002-of-00002.safetensors"
-  }
-}

logs/checkpoint-1815/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:00966419e724d11705023e7781a58b7701f9de92d041e32217c7a585598d5410
-size 14512

logs/checkpoint-1815/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:510aa91f662bf70736bc6291c6c96993786fb6ce228f4d554295d49dadcd130d
-size 14512

logs/checkpoint-1815/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c24ddb178619d5224e3f4aa5a8821a5a2c70f3fd97195fb9c848542f6db121e0
-size 1064

logs/checkpoint-1815/special_tokens_map.json

@@ -1,23 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

logs/checkpoint-1815/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e8485b8900f2ef3a891091dbe5ef0edc56f6922c0a23c7dfbb4baf64854f7de4
-size 17210102

logs/checkpoint-1815/tokenizer_config.json

@@ -1,2072 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "128000": {
-      "content": "<|begin_of_text|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128001": {
-      "content": "<|end_of_text|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128002": {
-      "content": "<|reserved_special_token_0|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128003": {
-      "content": "<|reserved_special_token_1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128004": {
-      "content": "<|finetune_right_pad_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128005": {
-      "content": "<|reserved_special_token_2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128006": {
-      "content": "<|start_header_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128007": {
-      "content": "<|end_header_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128008": {
-      "content": "<|eom_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128009": {
-      "content": "<|eot_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128010": {
-      "content": "<|python_tag|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128011": {
-      "content": "<|reserved_special_token_3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128012": {
-      "content": "<|reserved_special_token_4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128013": {
-      "content": "<|reserved_special_token_5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128014": {
-      "content": "<|reserved_special_token_6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128015": {
-      "content": "<|reserved_special_token_7|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128016": {
-      "content": "<|reserved_special_token_8|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128017": {
-      "content": "<|reserved_special_token_9|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128018": {
-      "content": "<|reserved_special_token_10|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128019": {
-      "content": "<|reserved_special_token_11|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128020": {
-      "content": "<|reserved_special_token_12|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128021": {
-      "content": "<|reserved_special_token_13|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128022": {
-      "content": "<|reserved_special_token_14|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128023": {
-      "content": "<|reserved_special_token_15|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128024": {
-      "content": "<|reserved_special_token_16|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128025": {
-      "content": "<|reserved_special_token_17|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128026": {
-      "content": "<|reserved_special_token_18|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128027": {
-      "content": "<|reserved_special_token_19|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128028": {
-      "content": "<|reserved_special_token_20|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128029": {
-      "content": "<|reserved_special_token_21|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128030": {
-      "content": "<|reserved_special_token_22|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128031": {
-      "content": "<|reserved_special_token_23|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128032": {
-      "content": "<|reserved_special_token_24|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128033": {
-      "content": "<|reserved_special_token_25|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128034": {
-      "content": "<|reserved_special_token_26|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128035": {
-      "content": "<|reserved_special_token_27|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128036": {
-      "content": "<|reserved_special_token_28|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128037": {
-      "content": "<|reserved_special_token_29|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128038": {
-      "content": "<|reserved_special_token_30|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128039": {
-      "content": "<|reserved_special_token_31|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128040": {
-      "content": "<|reserved_special_token_32|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128041": {
-      "content": "<|reserved_special_token_33|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128042": {
-      "content": "<|reserved_special_token_34|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128043": {
-      "content": "<|reserved_special_token_35|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128044": {
-      "content": "<|reserved_special_token_36|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128045": {
-      "content": "<|reserved_special_token_37|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128046": {
-      "content": "<|reserved_special_token_38|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128047": {
-      "content": "<|reserved_special_token_39|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128048": {
-      "content": "<|reserved_special_token_40|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128049": {
-      "content": "<|reserved_special_token_41|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128050": {
-      "content": "<|reserved_special_token_42|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128051": {
-      "content": "<|reserved_special_token_43|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128052": {
-      "content": "<|reserved_special_token_44|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128053": {
-      "content": "<|reserved_special_token_45|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128054": {
-      "content": "<|reserved_special_token_46|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128055": {
-      "content": "<|reserved_special_token_47|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128056": {
-      "content": "<|reserved_special_token_48|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128057": {
-      "content": "<|reserved_special_token_49|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128058": {
-      "content": "<|reserved_special_token_50|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128059": {
-      "content": "<|reserved_special_token_51|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128060": {
-      "content": "<|reserved_special_token_52|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128061": {
-      "content": "<|reserved_special_token_53|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128062": {
-      "content": "<|reserved_special_token_54|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128063": {
-      "content": "<|reserved_special_token_55|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128064": {
-      "content": "<|reserved_special_token_56|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128065": {
-      "content": "<|reserved_special_token_57|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128066": {
-      "content": "<|reserved_special_token_58|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128067": {
-      "content": "<|reserved_special_token_59|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128068": {
-      "content": "<|reserved_special_token_60|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128069": {
-      "content": "<|reserved_special_token_61|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128070": {
-      "content": "<|reserved_special_token_62|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128071": {
-      "content": "<|reserved_special_token_63|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128072": {
-      "content": "<|reserved_special_token_64|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128073": {
-      "content": "<|reserved_special_token_65|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128074": {
-      "content": "<|reserved_special_token_66|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128075": {
-      "content": "<|reserved_special_token_67|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128076": {
-      "content": "<|reserved_special_token_68|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128077": {
-      "content": "<|reserved_special_token_69|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128078": {
-      "content": "<|reserved_special_token_70|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128079": {
-      "content": "<|reserved_special_token_71|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128080": {
-      "content": "<|reserved_special_token_72|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128081": {
-      "content": "<|reserved_special_token_73|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128082": {
-      "content": "<|reserved_special_token_74|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128083": {
-      "content": "<|reserved_special_token_75|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128084": {
-      "content": "<|reserved_special_token_76|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128085": {
-      "content": "<|reserved_special_token_77|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128086": {
-      "content": "<|reserved_special_token_78|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128087": {
-      "content": "<|reserved_special_token_79|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128088": {
-      "content": "<|reserved_special_token_80|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128089": {
-      "content": "<|reserved_special_token_81|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128090": {
-      "content": "<|reserved_special_token_82|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128091": {
-      "content": "<|reserved_special_token_83|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128092": {
-      "content": "<|reserved_special_token_84|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128093": {
-      "content": "<|reserved_special_token_85|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128094": {
-      "content": "<|reserved_special_token_86|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128095": {
-      "content": "<|reserved_special_token_87|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128096": {
-      "content": "<|reserved_special_token_88|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128097": {
-      "content": "<|reserved_special_token_89|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128098": {
-      "content": "<|reserved_special_token_90|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128099": {
-      "content": "<|reserved_special_token_91|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128100": {
-      "content": "<|reserved_special_token_92|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128101": {
-      "content": "<|reserved_special_token_93|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128102": {
-      "content": "<|reserved_special_token_94|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128103": {
-      "content": "<|reserved_special_token_95|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128104": {
-      "content": "<|reserved_special_token_96|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128105": {
-      "content": "<|reserved_special_token_97|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128106": {
-      "content": "<|reserved_special_token_98|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128107": {
-      "content": "<|reserved_special_token_99|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128108": {
-      "content": "<|reserved_special_token_100|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128109": {
-      "content": "<|reserved_special_token_101|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128110": {
-      "content": "<|reserved_special_token_102|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128111": {
-      "content": "<|reserved_special_token_103|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128112": {
-      "content": "<|reserved_special_token_104|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128113": {
-      "content": "<|reserved_special_token_105|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128114": {
-      "content": "<|reserved_special_token_106|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128115": {
-      "content": "<|reserved_special_token_107|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128116": {
-      "content": "<|reserved_special_token_108|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128117": {
-      "content": "<|reserved_special_token_109|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128118": {
-      "content": "<|reserved_special_token_110|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128119": {
-      "content": "<|reserved_special_token_111|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128120": {
-      "content": "<|reserved_special_token_112|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128121": {
-      "content": "<|reserved_special_token_113|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128122": {
-      "content": "<|reserved_special_token_114|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128123": {
-      "content": "<|reserved_special_token_115|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128124": {
-      "content": "<|reserved_special_token_116|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128125": {
-      "content": "<|reserved_special_token_117|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128126": {
-      "content": "<|reserved_special_token_118|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128127": {
-      "content": "<|reserved_special_token_119|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128128": {
-      "content": "<|reserved_special_token_120|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128129": {
-      "content": "<|reserved_special_token_121|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128130": {
-      "content": "<|reserved_special_token_122|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128131": {
-      "content": "<|reserved_special_token_123|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128132": {
-      "content": "<|reserved_special_token_124|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128133": {
-      "content": "<|reserved_special_token_125|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128134": {
-      "content": "<|reserved_special_token_126|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128135": {
-      "content": "<|reserved_special_token_127|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128136": {
-      "content": "<|reserved_special_token_128|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128137": {
-      "content": "<|reserved_special_token_129|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128138": {
-      "content": "<|reserved_special_token_130|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128139": {
-      "content": "<|reserved_special_token_131|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128140": {
-      "content": "<|reserved_special_token_132|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128141": {
-      "content": "<|reserved_special_token_133|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128142": {
-      "content": "<|reserved_special_token_134|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128143": {
-      "content": "<|reserved_special_token_135|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128144": {
-      "content": "<|reserved_special_token_136|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128145": {
-      "content": "<|reserved_special_token_137|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128146": {
-      "content": "<|reserved_special_token_138|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128147": {
-      "content": "<|reserved_special_token_139|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128148": {
-      "content": "<|reserved_special_token_140|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128149": {
-      "content": "<|reserved_special_token_141|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128150": {
-      "content": "<|reserved_special_token_142|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128151": {
-      "content": "<|reserved_special_token_143|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128152": {
-      "content": "<|reserved_special_token_144|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128153": {
-      "content": "<|reserved_special_token_145|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128154": {
-      "content": "<|reserved_special_token_146|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128155": {
-      "content": "<|reserved_special_token_147|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128156": {
-      "content": "<|reserved_special_token_148|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128157": {
-      "content": "<|reserved_special_token_149|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128158": {
-      "content": "<|reserved_special_token_150|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128159": {
-      "content": "<|reserved_special_token_151|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128160": {
-      "content": "<|reserved_special_token_152|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128161": {
-      "content": "<|reserved_special_token_153|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128162": {
-      "content": "<|reserved_special_token_154|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128163": {
-      "content": "<|reserved_special_token_155|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128164": {
-      "content": "<|reserved_special_token_156|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128165": {
-      "content": "<|reserved_special_token_157|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128166": {
-      "content": "<|reserved_special_token_158|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128167": {
-      "content": "<|reserved_special_token_159|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128168": {
-      "content": "<|reserved_special_token_160|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128169": {
-      "content": "<|reserved_special_token_161|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128170": {
-      "content": "<|reserved_special_token_162|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128171": {
-      "content": "<|reserved_special_token_163|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128172": {
-      "content": "<|reserved_special_token_164|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128173": {
-      "content": "<|reserved_special_token_165|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128174": {
-      "content": "<|reserved_special_token_166|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128175": {
-      "content": "<|reserved_special_token_167|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128176": {
-      "content": "<|reserved_special_token_168|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128177": {
-      "content": "<|reserved_special_token_169|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128178": {
-      "content": "<|reserved_special_token_170|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128179": {
-      "content": "<|reserved_special_token_171|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128180": {
-      "content": "<|reserved_special_token_172|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128181": {
-      "content": "<|reserved_special_token_173|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128182": {
-      "content": "<|reserved_special_token_174|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128183": {
-      "content": "<|reserved_special_token_175|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128184": {
-      "content": "<|reserved_special_token_176|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128185": {
-      "content": "<|reserved_special_token_177|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128186": {
-      "content": "<|reserved_special_token_178|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128187": {
-      "content": "<|reserved_special_token_179|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128188": {
-      "content": "<|reserved_special_token_180|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128189": {
-      "content": "<|reserved_special_token_181|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128190": {
-      "content": "<|reserved_special_token_182|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128191": {
-      "content": "<|reserved_special_token_183|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128192": {
-      "content": "<|reserved_special_token_184|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128193": {
-      "content": "<|reserved_special_token_185|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128194": {
-      "content": "<|reserved_special_token_186|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128195": {
-      "content": "<|reserved_special_token_187|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128196": {
-      "content": "<|reserved_special_token_188|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128197": {
-      "content": "<|reserved_special_token_189|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128198": {
-      "content": "<|reserved_special_token_190|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128199": {
-      "content": "<|reserved_special_token_191|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128200": {
-      "content": "<|reserved_special_token_192|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128201": {
-      "content": "<|reserved_special_token_193|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128202": {
-      "content": "<|reserved_special_token_194|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128203": {
-      "content": "<|reserved_special_token_195|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128204": {
-      "content": "<|reserved_special_token_196|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128205": {
-      "content": "<|reserved_special_token_197|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128206": {
-      "content": "<|reserved_special_token_198|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128207": {
-      "content": "<|reserved_special_token_199|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128208": {
-      "content": "<|reserved_special_token_200|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128209": {
-      "content": "<|reserved_special_token_201|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128210": {
-      "content": "<|reserved_special_token_202|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128211": {
-      "content": "<|reserved_special_token_203|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128212": {
-      "content": "<|reserved_special_token_204|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128213": {
-      "content": "<|reserved_special_token_205|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128214": {
-      "content": "<|reserved_special_token_206|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128215": {
-      "content": "<|reserved_special_token_207|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128216": {
-      "content": "<|reserved_special_token_208|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128217": {
-      "content": "<|reserved_special_token_209|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128218": {
-      "content": "<|reserved_special_token_210|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128219": {
-      "content": "<|reserved_special_token_211|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128220": {
-      "content": "<|reserved_special_token_212|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128221": {
-      "content": "<|reserved_special_token_213|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128222": {
-      "content": "<|reserved_special_token_214|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128223": {
-      "content": "<|reserved_special_token_215|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128224": {
-      "content": "<|reserved_special_token_216|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128225": {
-      "content": "<|reserved_special_token_217|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128226": {
-      "content": "<|reserved_special_token_218|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128227": {
-      "content": "<|reserved_special_token_219|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128228": {
-      "content": "<|reserved_special_token_220|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128229": {
-      "content": "<|reserved_special_token_221|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128230": {
-      "content": "<|reserved_special_token_222|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128231": {
-      "content": "<|reserved_special_token_223|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128232": {
-      "content": "<|reserved_special_token_224|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128233": {
-      "content": "<|reserved_special_token_225|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128234": {
-      "content": "<|reserved_special_token_226|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128235": {
-      "content": "<|reserved_special_token_227|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128236": {
-      "content": "<|reserved_special_token_228|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128237": {
-      "content": "<|reserved_special_token_229|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128238": {
-      "content": "<|reserved_special_token_230|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128239": {
-      "content": "<|reserved_special_token_231|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128240": {
-      "content": "<|reserved_special_token_232|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128241": {
-      "content": "<|reserved_special_token_233|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128242": {
-      "content": "<|reserved_special_token_234|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128243": {
-      "content": "<|reserved_special_token_235|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128244": {
-      "content": "<|reserved_special_token_236|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128245": {
-      "content": "<|reserved_special_token_237|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128246": {
-      "content": "<|reserved_special_token_238|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128247": {
-      "content": "<|reserved_special_token_239|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128248": {
-      "content": "<|reserved_special_token_240|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128249": {
-      "content": "<|reserved_special_token_241|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128250": {
-      "content": "<|reserved_special_token_242|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128251": {
-      "content": "<|reserved_special_token_243|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128252": {
-      "content": "<|reserved_special_token_244|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128253": {
-      "content": "<|reserved_special_token_245|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128254": {
-      "content": "<|reserved_special_token_246|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128255": {
-      "content": "<|reserved_special_token_247|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128256": {
-      "content": "[PAD]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|begin_of_text|>",
-  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
-  "extra_special_tokens": {},
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 4096,
-  "pad_token": "[PAD]",
-  "tokenizer_class": "PreTrainedTokenizer"
-}

logs/checkpoint-1815/trainer_state.json

@@ -1,1301 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 4.988300068823125,
-  "eval_steps": 500,
-  "global_step": 1815,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.02752924982794219,
-      "grad_norm": 0.21950913965702057,
-      "learning_rate": 0.00019780219780219779,
-      "loss": 0.0337,
-      "step": 10
-    },
-    {
-      "epoch": 0.05505849965588438,
-      "grad_norm": 0.2621772885322571,
-      "learning_rate": 0.0004175824175824176,
-      "loss": -0.0517,
-      "step": 20
-    },
-    {
-      "epoch": 0.08258774948382656,
-      "grad_norm": 0.13839857280254364,
-      "learning_rate": 0.0006373626373626373,
-      "loss": -0.1342,
-      "step": 30
-    },
-    {
-      "epoch": 0.11011699931176876,
-      "grad_norm": 0.22325846552848816,
-      "learning_rate": 0.0008571428571428571,
-      "loss": -0.1481,
-      "step": 40
-    },
-    {
-      "epoch": 0.13764624913971094,
-      "grad_norm": 0.09140709787607193,
-      "learning_rate": 0.0010769230769230769,
-      "loss": -0.1026,
-      "step": 50
-    },
-    {
-      "epoch": 0.16517549896765313,
-      "grad_norm": 0.1731194257736206,
-      "learning_rate": 0.0012967032967032969,
-      "loss": -0.1302,
-      "step": 60
-    },
-    {
-      "epoch": 0.19270474879559532,
-      "grad_norm": 0.13070443272590637,
-      "learning_rate": 0.0015164835164835164,
-      "loss": -0.1363,
-      "step": 70
-    },
-    {
-      "epoch": 0.2202339986235375,
-      "grad_norm": 0.10590607672929764,
-      "learning_rate": 0.0017362637362637364,
-      "loss": -0.1567,
-      "step": 80
-    },
-    {
-      "epoch": 0.2477632484514797,
-      "grad_norm": 0.10256265103816986,
-      "learning_rate": 0.001956043956043956,
-      "loss": -0.1802,
-      "step": 90
-    },
-    {
-      "epoch": 0.27529249827942187,
-      "grad_norm": 0.07979273796081543,
-      "learning_rate": 0.0019998937405633103,
-      "loss": -0.1857,
-      "step": 100
-    },
-    {
-      "epoch": 0.30282174810736406,
-      "grad_norm": 0.13701443374156952,
-      "learning_rate": 0.0019994621003042484,
-      "loss": -0.1589,
-      "step": 110
-    },
-    {
-      "epoch": 0.33035099793530626,
-      "grad_norm": 0.1182035580277443,
-      "learning_rate": 0.001998698581227109,
-      "loss": -0.1698,
-      "step": 120
-    },
-    {
-      "epoch": 0.35788024776324845,
-      "grad_norm": 0.09107693284749985,
-      "learning_rate": 0.001997603436864077,
-      "loss": -0.1914,
-      "step": 130
-    },
-    {
-      "epoch": 0.38540949759119064,
-      "grad_norm": 0.1944652646780014,
-      "learning_rate": 0.0019961770308659765,
-      "loss": -0.1668,
-      "step": 140
-    },
-    {
-      "epoch": 0.41293874741913283,
-      "grad_norm": 0.07951785624027252,
-      "learning_rate": 0.0019944198368815193,
-      "loss": -0.1877,
-      "step": 150
-    },
-    {
-      "epoch": 0.440467997247075,
-      "grad_norm": 0.17512911558151245,
-      "learning_rate": 0.0019923324384000275,
-      "loss": -0.1703,
-      "step": 160
-    },
-    {
-      "epoch": 0.4679972470750172,
-      "grad_norm": 0.09950096160173416,
-      "learning_rate": 0.001989915528557679,
-      "loss": -0.2199,
-      "step": 170
-    },
-    {
-      "epoch": 0.4955264969029594,
-      "grad_norm": 0.1280299872159958,
-      "learning_rate": 0.001987169909907349,
-      "loss": -0.1734,
-      "step": 180
-    },
-    {
-      "epoch": 0.5230557467309016,
-      "grad_norm": 0.1005721464753151,
-      "learning_rate": 0.0019840964941521154,
-      "loss": -0.1855,
-      "step": 190
-    },
-    {
-      "epoch": 0.5505849965588437,
-      "grad_norm": 0.07456175982952118,
-      "learning_rate": 0.001980696301842519,
-      "loss": -0.1828,
-      "step": 200
-    },
-    {
-      "epoch": 0.578114246386786,
-      "grad_norm": 0.2459397166967392,
-      "learning_rate": 0.0019769704620376865,
-      "loss": -0.1943,
-      "step": 210
-    },
-    {
-      "epoch": 0.6056434962147281,
-      "grad_norm": 0.10127563774585724,
-      "learning_rate": 0.0019729202119304137,
-      "loss": -0.2253,
-      "step": 220
-    },
-    {
-      "epoch": 0.6331727460426704,
-      "grad_norm": 0.09506753087043762,
-      "learning_rate": 0.0019685468964363495,
-      "loss": -0.2088,
-      "step": 230
-    },
-    {
-      "epoch": 0.6607019958706125,
-      "grad_norm": 0.08143377304077148,
-      "learning_rate": 0.001963851967747404,
-      "loss": -0.1838,
-      "step": 240
-    },
-    {
-      "epoch": 0.6882312456985548,
-      "grad_norm": 0.13531577587127686,
-      "learning_rate": 0.0019588369848495394,
-      "loss": -0.2389,
-      "step": 250
-    },
-    {
-      "epoch": 0.7157604955264969,
-      "grad_norm": 0.07151653617620468,
-      "learning_rate": 0.0019535036130050973,
-      "loss": -0.21,
-      "step": 260
-    },
-    {
-      "epoch": 0.7432897453544391,
-      "grad_norm": 0.07007952779531479,
-      "learning_rate": 0.0019478536231998342,
-      "loss": -0.2252,
-      "step": 270
-    },
-    {
-      "epoch": 0.7708189951823813,
-      "grad_norm": 0.09915212541818619,
-      "learning_rate": 0.001941888891554854,
-      "loss": -0.2095,
-      "step": 280
-    },
-    {
-      "epoch": 0.7983482450103234,
-      "grad_norm": 0.0757177397608757,
-      "learning_rate": 0.0019356113987036268,
-      "loss": -0.2386,
-      "step": 290
-    },
-    {
-      "epoch": 0.8258774948382657,
-      "grad_norm": 0.0779600515961647,
-      "learning_rate": 0.0019290232291343066,
-      "loss": -0.2089,
-      "step": 300
-    },
-    {
-      "epoch": 0.8534067446662078,
-      "grad_norm": 0.14942707121372223,
-      "learning_rate": 0.00192212657049756,
-      "loss": -0.2076,
-      "step": 310
-    },
-    {
-      "epoch": 0.88093599449415,
-      "grad_norm": 0.2603641152381897,
-      "learning_rate": 0.0019149237128801401,
-      "loss": -0.2257,
-      "step": 320
-    },
-    {
-      "epoch": 0.9084652443220922,
-      "grad_norm": 0.11928076297044754,
-      "learning_rate": 0.0019074170480444495,
-      "loss": -0.1596,
-      "step": 330
-    },
-    {
-      "epoch": 0.9359944941500344,
-      "grad_norm": 0.06584256887435913,
-      "learning_rate": 0.0018996090686343328,
-      "loss": -0.2225,
-      "step": 340
-    },
-    {
-      "epoch": 0.9635237439779766,
-      "grad_norm": 0.07399892061948776,
-      "learning_rate": 0.0018915023673473797,
-      "loss": -0.2386,
-      "step": 350
-    },
-    {
-      "epoch": 0.9910529938059188,
-      "grad_norm": 0.09290285408496857,
-      "learning_rate": 0.0018830996360739989,
-      "loss": -0.2191,
-      "step": 360
-    },
-    {
-      "epoch": 1.0165175498967653,
-      "grad_norm": 0.16244958341121674,
-      "learning_rate": 0.0018744036650035563,
-      "loss": -0.2564,
-      "step": 370
-    },
-    {
-      "epoch": 1.0440467997247076,
-      "grad_norm": 0.054774392396211624,
-      "learning_rate": 0.0018654173416978712,
-      "loss": -0.2483,
-      "step": 380
-    },
-    {
-      "epoch": 1.0715760495526496,
-      "grad_norm": 0.08119138330221176,
-      "learning_rate": 0.0018561436501323804,
-      "loss": -0.2089,
-      "step": 390
-    },
-    {
-      "epoch": 1.0991052993805919,
-      "grad_norm": 0.07407746464014053,
-      "learning_rate": 0.001846585669705288,
-      "loss": -0.2344,
-      "step": 400
-    },
-    {
-      "epoch": 1.1266345492085341,
-      "grad_norm": 0.10089724510908127,
-      "learning_rate": 0.0018367465742150253,
-      "loss": -0.2591,
-      "step": 410
-    },
-    {
-      "epoch": 1.1541637990364761,
-      "grad_norm": 0.07331768423318863,
-      "learning_rate": 0.0018266296308063717,
-      "loss": -0.2344,
-      "step": 420
-    },
-    {
-      "epoch": 1.1816930488644184,
-      "grad_norm": 0.0706942081451416,
-      "learning_rate": 0.0018162381988855718,
-      "loss": -0.2429,
-      "step": 430
-    },
-    {
-      "epoch": 1.2092222986923606,
-      "grad_norm": 0.08661209791898727,
-      "learning_rate": 0.00180557572900482,
-      "loss": -0.23,
-      "step": 440
-    },
-    {
-      "epoch": 1.236751548520303,
-      "grad_norm": 0.21729320287704468,
-      "learning_rate": 0.0017946457617164806,
-      "loss": -0.2277,
-      "step": 450
-    },
-    {
-      "epoch": 1.2642807983482451,
-      "grad_norm": 0.12371935695409775,
-      "learning_rate": 0.0017834519263974196,
-      "loss": -0.2034,
-      "step": 460
-    },
-    {
-      "epoch": 1.2918100481761872,
-      "grad_norm": 0.09967722743749619,
-      "learning_rate": 0.0017719979400438433,
-      "loss": -0.2474,
-      "step": 470
-    },
-    {
-      "epoch": 1.3193392980041294,
-      "grad_norm": 0.08221154659986496,
-      "learning_rate": 0.0017602876060370427,
-      "loss": -0.2348,
-      "step": 480
-    },
-    {
-      "epoch": 1.3468685478320714,
-      "grad_norm": 0.10625653713941574,
-      "learning_rate": 0.001748324812880452,
-      "loss": -0.2811,
-      "step": 490
-    },
-    {
-      "epoch": 1.3743977976600137,
-      "grad_norm": 0.05927477404475212,
-      "learning_rate": 0.0017361135329084427,
-      "loss": -0.2529,
-      "step": 500
-    },
-    {
-      "epoch": 1.401927047487956,
-      "grad_norm": 0.0709695816040039,
-      "learning_rate": 0.0017236578209672798,
-      "loss": -0.2664,
-      "step": 510
-    },
-    {
-      "epoch": 1.4294562973158982,
-      "grad_norm": 0.0896676555275917,
-      "learning_rate": 0.0017109618130686792,
-      "loss": -0.2538,
-      "step": 520
-    },
-    {
-      "epoch": 1.4569855471438404,
-      "grad_norm": 0.06331639736890793,
-      "learning_rate": 0.0016980297250164171,
-      "loss": -0.2541,
-      "step": 530
-    },
-    {
-      "epoch": 1.4845147969717825,
-      "grad_norm": 0.08317861706018448,
-      "learning_rate": 0.0016848658510064376,
-      "loss": -0.2498,
-      "step": 540
-    },
-    {
-      "epoch": 1.5120440467997247,
-      "grad_norm": 0.0974503830075264,
-      "learning_rate": 0.0016714745622009356,
-      "loss": -0.2436,
-      "step": 550
-    },
-    {
-      "epoch": 1.5395732966276667,
-      "grad_norm": 0.09252775460481644,
-      "learning_rate": 0.0016578603052768786,
-      "loss": -0.2449,
-      "step": 560
-    },
-    {
-      "epoch": 1.567102546455609,
-      "grad_norm": 0.07080177962779999,
-      "learning_rate": 0.0016440276009494546,
-      "loss": -0.2714,
-      "step": 570
-    },
-    {
-      "epoch": 1.5946317962835512,
-      "grad_norm": 0.07411246746778488,
-      "learning_rate": 0.001629981042470936,
-      "loss": -0.2708,
-      "step": 580
-    },
-    {
-      "epoch": 1.6221610461114935,
-      "grad_norm": 0.07521508634090424,
-      "learning_rate": 0.0016157252941054545,
-      "loss": -0.2489,
-      "step": 590
-    },
-    {
-      "epoch": 1.6496902959394357,
-      "grad_norm": 0.08179710805416107,
-      "learning_rate": 0.0016012650895801995,
-      "loss": -0.2413,
-      "step": 600
-    },
-    {
-      "epoch": 1.677219545767378,
-      "grad_norm": 0.12953896820545197,
-      "learning_rate": 0.001586605230513546,
-      "loss": -0.2389,
-      "step": 610
-    },
-    {
-      "epoch": 1.70474879559532,
-      "grad_norm": 0.06573023647069931,
-      "learning_rate": 0.0015717505848206455,
-      "loss": -0.258,
-      "step": 620
-    },
-    {
-      "epoch": 1.7322780454232622,
-      "grad_norm": 0.05939861387014389,
-      "learning_rate": 0.0015567060850969945,
-      "loss": -0.2722,
-      "step": 630
-    },
-    {
-      "epoch": 1.7598072952512043,
-      "grad_norm": 0.1493271291255951,
-      "learning_rate": 0.0015414767269805317,
-      "loss": -0.2639,
-      "step": 640
-    },
-    {
-      "epoch": 1.7873365450791465,
-      "grad_norm": 0.06282184273004532,
-      "learning_rate": 0.0015260675674927998,
-      "loss": -0.2561,
-      "step": 650
-    },
-    {
-      "epoch": 1.8148657949070888,
-      "grad_norm": 0.06654730439186096,
-      "learning_rate": 0.0015104837233597221,
-      "loss": -0.2546,
-      "step": 660
-    },
-    {
-      "epoch": 1.842395044735031,
-      "grad_norm": 0.08558861166238785,
-      "learning_rate": 0.0014947303693125572,
-      "loss": -0.2807,
-      "step": 670
-    },
-    {
-      "epoch": 1.8699242945629733,
-      "grad_norm": 0.07311326265335083,
-      "learning_rate": 0.0014788127363695896,
-      "loss": -0.2362,
-      "step": 680
-    },
-    {
-      "epoch": 1.8974535443909153,
-      "grad_norm": 0.08213303983211517,
-      "learning_rate": 0.0014627361100991334,
-      "loss": -0.2949,
-      "step": 690
-    },
-    {
-      "epoch": 1.9249827942188575,
-      "grad_norm": 0.06794822961091995,
-      "learning_rate": 0.0014465058288644173,
-      "loss": -0.25,
-      "step": 700
-    },
-    {
-      "epoch": 1.9525120440467996,
-      "grad_norm": 0.11336816847324371,
-      "learning_rate": 0.0014301272820509436,
-      "loss": -0.2769,
-      "step": 710
-    },
-    {
-      "epoch": 1.9800412938747418,
-      "grad_norm": 0.05777375027537346,
-      "learning_rate": 0.0014136059082769017,
-      "loss": -0.2683,
-      "step": 720
-    },
-    {
-      "epoch": 2.0055058499655884,
-      "grad_norm": 0.08020348846912384,
-      "learning_rate": 0.0013969471935872345,
-      "loss": -0.2263,
-      "step": 730
-    },
-    {
-      "epoch": 2.0330350997935307,
-      "grad_norm": 0.09895347058773041,
-      "learning_rate": 0.0013801566696319562,
-      "loss": -0.2815,
-      "step": 740
-    },
-    {
-      "epoch": 2.060564349621473,
-      "grad_norm": 0.08933740854263306,
-      "learning_rate": 0.0013632399118293289,
-      "loss": -0.2319,
-      "step": 750
-    },
-    {
-      "epoch": 2.088093599449415,
-      "grad_norm": 0.07838021963834763,
-      "learning_rate": 0.0013462025375145,
-      "loss": -0.2757,
-      "step": 760
-    },
-    {
-      "epoch": 2.115622849277357,
-      "grad_norm": 0.07352108508348465,
-      "learning_rate": 0.001329050204074227,
-      "loss": -0.2546,
-      "step": 770
-    },
-    {
-      "epoch": 2.1431520991052992,
-      "grad_norm": 0.06982218474149704,
-      "learning_rate": 0.001311788607068299,
-      "loss": -0.2558,
-      "step": 780
-    },
-    {
-      "epoch": 2.1706813489332415,
-      "grad_norm": 0.07919827103614807,
-      "learning_rate": 0.0012944234783382842,
-      "loss": -0.2186,
-      "step": 790
-    },
-    {
-      "epoch": 2.1982105987611837,
-      "grad_norm": 0.07763735204935074,
-      "learning_rate": 0.0012769605841042298,
-      "loss": -0.261,
-      "step": 800
-    },
-    {
-      "epoch": 2.225739848589126,
-      "grad_norm": 0.07711489498615265,
-      "learning_rate": 0.0012594057230499445,
-      "loss": -0.2699,
-      "step": 810
-    },
-    {
-      "epoch": 2.2532690984170682,
-      "grad_norm": 0.06311825662851334,
-      "learning_rate": 0.001241764724397503,
-      "loss": -0.2818,
-      "step": 820
-    },
-    {
-      "epoch": 2.2807983482450105,
-      "grad_norm": 0.058821260929107666,
-      "learning_rate": 0.0012240434459716099,
-      "loss": -0.3003,
-      "step": 830
-    },
-    {
-      "epoch": 2.3083275980729523,
-      "grad_norm": 0.08163290470838547,
-      "learning_rate": 0.0012062477722544656,
-      "loss": -0.2895,
-      "step": 840
-    },
-    {
-      "epoch": 2.3358568479008945,
-      "grad_norm": 0.06689217686653137,
-      "learning_rate": 0.001188383612431779,
-      "loss": -0.2979,
-      "step": 850
-    },
-    {
-      "epoch": 2.363386097728837,
-      "grad_norm": 0.07341046631336212,
-      "learning_rate": 0.0011704568984305802,
-      "loss": -0.2963,
-      "step": 860
-    },
-    {
-      "epoch": 2.390915347556779,
-      "grad_norm": 0.05612272769212723,
-      "learning_rate": 0.0011524735829494782,
-      "loss": -0.2689,
-      "step": 870
-    },
-    {
-      "epoch": 2.4184445973847213,
-      "grad_norm": 0.08049242198467255,
-      "learning_rate": 0.0011344396374820243,
-      "loss": -0.2705,
-      "step": 880
-    },
-    {
-      "epoch": 2.4459738472126635,
-      "grad_norm": 0.0535312257707119,
-      "learning_rate": 0.001116361050333834,
-      "loss": -0.2957,
-      "step": 890
-    },
-    {
-      "epoch": 2.473503097040606,
-      "grad_norm": 0.0912913978099823,
-      "learning_rate": 0.0010982438246341238,
-      "loss": -0.3098,
-      "step": 900
-    },
-    {
-      "epoch": 2.5010323468685476,
-      "grad_norm": 0.10070489346981049,
-      "learning_rate": 0.001080093976342328,
-      "loss": -0.2446,
-      "step": 910
-    },
-    {
-      "epoch": 2.5285615966964903,
-      "grad_norm": 0.07906454056501389,
-      "learning_rate": 0.001061917532250456,
-      "loss": -0.2794,
-      "step": 920
-    },
-    {
-      "epoch": 2.556090846524432,
-      "grad_norm": 0.07486985623836517,
-      "learning_rate": 0.00104372052798185,
-      "loss": -0.2704,
-      "step": 930
-    },
-    {
-      "epoch": 2.5836200963523743,
-      "grad_norm": 0.06839898973703384,
-      "learning_rate": 0.0010255090059870108,
-      "loss": -0.2616,
-      "step": 940
-    },
-    {
-      "epoch": 2.6111493461803166,
-      "grad_norm": 0.0692797526717186,
-      "learning_rate": 0.001007289013537159,
-      "loss": -0.295,
-      "step": 950
-    },
-    {
-      "epoch": 2.638678596008259,
-      "grad_norm": 0.08830973505973816,
-      "learning_rate": 0.0009890666007161928,
-      "loss": -0.3022,
-      "step": 960
-    },
-    {
-      "epoch": 2.666207845836201,
-      "grad_norm": 0.08625375479459763,
-      "learning_rate": 0.0009708478184117124,
-      "loss": -0.2723,
-      "step": 970
-    },
-    {
-      "epoch": 2.693737095664143,
-      "grad_norm": 0.076654814183712,
-      "learning_rate": 0.0009526387163057777,
-      "loss": -0.2794,
-      "step": 980
-    },
-    {
-      "epoch": 2.7212663454920856,
-      "grad_norm": 0.08966702222824097,
-      "learning_rate": 0.0009344453408660669,
-      "loss": -0.2244,
-      "step": 990
-    },
-    {
-      "epoch": 2.7487955953200274,
-      "grad_norm": 0.056653983891010284,
-      "learning_rate": 0.0009162737333381019,
-      "loss": -0.2383,
-      "step": 1000
-    },
-    {
-      "epoch": 2.7763248451479696,
-      "grad_norm": 0.09579630941152573,
-      "learning_rate": 0.0008981299277392079,
-      "loss": -0.2521,
-      "step": 1010
-    },
-    {
-      "epoch": 2.803854094975912,
-      "grad_norm": 0.0744895190000534,
-      "learning_rate": 0.0008800199488548729,
-      "loss": -0.299,
-      "step": 1020
-    },
-    {
-      "epoch": 2.831383344803854,
-      "grad_norm": 0.0786685198545456,
-      "learning_rate": 0.0008619498102381722,
-      "loss": -0.2852,
-      "step": 1030
-    },
-    {
-      "epoch": 2.8589125946317964,
-      "grad_norm": 0.06602706015110016,
-      "learning_rate": 0.0008439255122129254,
-      "loss": -0.2413,
-      "step": 1040
-    },
-    {
-      "epoch": 2.8864418444597386,
-      "grad_norm": 0.08209407329559326,
-      "learning_rate": 0.0008259530398812421,
-      "loss": -0.281,
-      "step": 1050
-    },
-    {
-      "epoch": 2.913971094287681,
-      "grad_norm": 0.0787435993552208,
-      "learning_rate": 0.0008080383611361254,
-      "loss": -0.2687,
-      "step": 1060
-    },
-    {
-      "epoch": 2.9415003441156227,
-      "grad_norm": 0.07260625064373016,
-      "learning_rate": 0.0007901874246797889,
-      "loss": -0.3005,
-      "step": 1070
-    },
-    {
-      "epoch": 2.969029593943565,
-      "grad_norm": 0.0846058577299118,
-      "learning_rate": 0.0007724061580483449,
-      "loss": -0.3199,
-      "step": 1080
-    },
-    {
-      "epoch": 2.996558843771507,
-      "grad_norm": 0.09303789585828781,
-      "learning_rate": 0.000754700465643523,
-      "loss": -0.2842,
-      "step": 1090
-    },
-    {
-      "epoch": 3.022023399862354,
-      "grad_norm": 0.06388015300035477,
-      "learning_rate": 0.0007370762267720685,
-      "loss": -0.2655,
-      "step": 1100
-    },
-    {
-      "epoch": 3.049552649690296,
-      "grad_norm": 0.07934300601482391,
-      "learning_rate": 0.000719539293693477,
-      "loss": -0.2678,
-      "step": 1110
-    },
-    {
-      "epoch": 3.0770818995182383,
-      "grad_norm": 0.13151037693023682,
-      "learning_rate": 0.0007020954896767057,
-      "loss": -0.2369,
-      "step": 1120
-    },
-    {
-      "epoch": 3.10461114934618,
-      "grad_norm": 0.07448447495698929,
-      "learning_rate": 0.0006847506070665144,
-      "loss": -0.2632,
-      "step": 1130
-    },
-    {
-      "epoch": 3.1321403991741223,
-      "grad_norm": 0.08742206543684006,
-      "learning_rate": 0.0006675104053600762,
-      "loss": -0.2892,
-      "step": 1140
-    },
-    {
-      "epoch": 3.1596696490020646,
-      "grad_norm": 0.10627385973930359,
-      "learning_rate": 0.0006503806092944902,
-      "loss": -0.2905,
-      "step": 1150
-    },
-    {
-      "epoch": 3.187198898830007,
-      "grad_norm": 0.11084494739770889,
-      "learning_rate": 0.0006333669069458432,
-      "loss": -0.2847,
-      "step": 1160
-    },
-    {
-      "epoch": 3.214728148657949,
-      "grad_norm": 0.04558253660798073,
-      "learning_rate": 0.0006164749478404407,
-      "loss": -0.309,
-      "step": 1170
-    },
-    {
-      "epoch": 3.2422573984858913,
-      "grad_norm": 0.05357061326503754,
-      "learning_rate": 0.0005997103410788385,
-      "loss": -0.2899,
-      "step": 1180
-    },
-    {
-      "epoch": 3.2697866483138336,
-      "grad_norm": 0.09318793565034866,
-      "learning_rate": 0.0005830786534733011,
-      "loss": -0.2563,
-      "step": 1190
-    },
-    {
-      "epoch": 3.2973158981417754,
-      "grad_norm": 0.07737188041210175,
-      "learning_rate": 0.0005665854076992991,
-      "loss": -0.2929,
-      "step": 1200
-    },
-    {
-      "epoch": 3.3248451479697176,
-      "grad_norm": 0.0780494436621666,
-      "learning_rate": 0.0005502360804616644,
-      "loss": -0.3057,
-      "step": 1210
-    },
-    {
-      "epoch": 3.35237439779766,
-      "grad_norm": 0.06877736002206802,
-      "learning_rate": 0.0005340361006760082,
-      "loss": -0.3181,
-      "step": 1220
-    },
-    {
-      "epoch": 3.379903647625602,
-      "grad_norm": 0.07256918400526047,
-      "learning_rate": 0.0005179908476660118,
-      "loss": -0.3095,
-      "step": 1230
-    },
-    {
-      "epoch": 3.4074328974535444,
-      "grad_norm": 0.07428444921970367,
-      "learning_rate": 0.0005021056493771805,
-      "loss": -0.3056,
-      "step": 1240
-    },
-    {
-      "epoch": 3.4349621472814866,
-      "grad_norm": 0.0776098445057869,
-      "learning_rate": 0.0004863857806076588,
-      "loss": -0.28,
-      "step": 1250
-    },
-    {
-      "epoch": 3.462491397109429,
-      "grad_norm": 0.10839086771011353,
-      "learning_rate": 0.0004708364612566969,
-      "loss": -0.2906,
-      "step": 1260
-    },
-    {
-      "epoch": 3.490020646937371,
-      "grad_norm": 0.06351841241121292,
-      "learning_rate": 0.00045546285459134296,
-      "loss": -0.2919,
-      "step": 1270
-    },
-    {
-      "epoch": 3.5175498967653134,
-      "grad_norm": 0.06724438071250916,
-      "learning_rate": 0.00044027006553194113,
-      "loss": -0.3229,
-      "step": 1280
-    },
-    {
-      "epoch": 3.545079146593255,
-      "grad_norm": 0.05398397520184517,
-      "learning_rate": 0.00042526313895700676,
-      "loss": -0.2975,
-      "step": 1290
-    },
-    {
-      "epoch": 3.5726083964211974,
-      "grad_norm": 0.09356964379549026,
-      "learning_rate": 0.0004104470580280357,
-      "loss": -0.2461,
-      "step": 1300
-    },
-    {
-      "epoch": 3.6001376462491397,
-      "grad_norm": 0.06000690162181854,
-      "learning_rate": 0.00039582674253480844,
-      "loss": -0.2891,
-      "step": 1310
-    },
-    {
-      "epoch": 3.627666896077082,
-      "grad_norm": 0.06541986018419266,
-      "learning_rate": 0.0003814070472617375,
-      "loss": -0.298,
-      "step": 1320
-    },
-    {
-      "epoch": 3.655196145905024,
-      "grad_norm": 0.06478281319141388,
-      "learning_rate": 0.0003671927603758012,
-      "loss": -0.275,
-      "step": 1330
-    },
-    {
-      "epoch": 3.6827253957329664,
-      "grad_norm": 0.06622861325740814,
-      "learning_rate": 0.0003531886018365954,
-      "loss": -0.3363,
-      "step": 1340
-    },
-    {
-      "epoch": 3.7102546455609087,
-      "grad_norm": 0.07772338390350342,
-      "learning_rate": 0.0003393992218290376,
-      "loss": -0.2927,
-      "step": 1350
-    },
-    {
-      "epoch": 3.7377838953888505,
-      "grad_norm": 0.0797075554728508,
-      "learning_rate": 0.0003258291992192377,
-      "loss": -0.3114,
-      "step": 1360
-    },
-    {
-      "epoch": 3.7653131452167927,
-      "grad_norm": 0.058061715215444565,
-      "learning_rate": 0.00031248304003405047,
-      "loss": -0.2765,
-      "step": 1370
-    },
-    {
-      "epoch": 3.792842395044735,
-      "grad_norm": 0.09059327095746994,
-      "learning_rate": 0.00029936517596481813,
-      "loss": -0.2814,
-      "step": 1380
-    },
-    {
-      "epoch": 3.820371644872677,
-      "grad_norm": 0.07191544771194458,
-      "learning_rate": 0.0002864799628957926,
-      "loss": -0.289,
-      "step": 1390
-    },
-    {
-      "epoch": 3.8479008947006195,
-      "grad_norm": 0.09675148129463196,
-      "learning_rate": 0.00027383167945773144,
-      "loss": -0.318,
-      "step": 1400
-    },
-    {
-      "epoch": 3.8754301445285617,
-      "grad_norm": 0.0740475282073021,
-      "learning_rate": 0.0002614245256071486,
-      "loss": -0.3291,
-      "step": 1410
-    },
-    {
-      "epoch": 3.902959394356504,
-      "grad_norm": 0.07001981139183044,
-      "learning_rate": 0.0002492626212316862,
-      "loss": -0.2924,
-      "step": 1420
-    },
-    {
-      "epoch": 3.9304886441844458,
-      "grad_norm": 0.06735574454069138,
-      "learning_rate": 0.0002373500047820747,
-      "loss": -0.296,
-      "step": 1430
-    },
-    {
-      "epoch": 3.958017894012388,
-      "grad_norm": 0.10016655176877975,
-      "learning_rate": 0.00022569063193113715,
-      "loss": -0.2687,
-      "step": 1440
-    },
-    {
-      "epoch": 3.9855471438403303,
-      "grad_norm": 0.08626861870288849,
-      "learning_rate": 0.0002142883742602777,
-      "loss": -0.3233,
-      "step": 1450
-    },
-    {
-      "epoch": 4.011011699931177,
-      "grad_norm": 0.08658801019191742,
-      "learning_rate": 0.000203147017973893,
-      "loss": -0.3043,
-      "step": 1460
-    },
-    {
-      "epoch": 4.038540949759119,
-      "grad_norm": 0.0705769807100296,
-      "learning_rate": 0.00019227026264213753,
-      "loss": -0.2644,
-      "step": 1470
-    },
-    {
-      "epoch": 4.066070199587061,
-      "grad_norm": 0.05806250870227814,
-      "learning_rate": 0.00018166171997245119,
-      "loss": -0.2779,
-      "step": 1480
-    },
-    {
-      "epoch": 4.093599449415003,
-      "grad_norm": 0.07120814174413681,
-      "learning_rate": 0.0001713249126102665,
-      "loss": -0.2981,
-      "step": 1490
-    },
-    {
-      "epoch": 4.121128699242946,
-      "grad_norm": 0.060308583080768585,
-      "learning_rate": 0.0001612632729692881,
-      "loss": -0.2561,
-      "step": 1500
-    },
-    {
-      "epoch": 4.148657949070888,
-      "grad_norm": 0.049185026437044144,
-      "learning_rate": 0.00015148014209173368,
-      "loss": -0.3017,
-      "step": 1510
-    },
-    {
-      "epoch": 4.17618719889883,
-      "grad_norm": 0.06764695793390274,
-      "learning_rate": 0.00014197876853891555,
-      "loss": -0.3212,
-      "step": 1520
-    },
-    {
-      "epoch": 4.203716448726772,
-      "grad_norm": 0.0473322719335556,
-      "learning_rate": 0.00013276230731253347,
-      "loss": -0.3135,
-      "step": 1530
-    },
-    {
-      "epoch": 4.231245698554714,
-      "grad_norm": 0.09736400842666626,
-      "learning_rate": 0.00012383381880703138,
-      "loss": -0.293,
-      "step": 1540
-    },
-    {
-      "epoch": 4.258774948382657,
-      "grad_norm": 0.07775592803955078,
-      "learning_rate": 0.00011519626779337066,
-      "loss": -0.3067,
-      "step": 1550
-    },
-    {
-      "epoch": 4.2863041982105985,
-      "grad_norm": 0.07167046517133713,
-      "learning_rate": 0.00010685252243455712,
-      "loss": -0.297,
-      "step": 1560
-    },
-    {
-      "epoch": 4.313833448038541,
-      "grad_norm": 0.13709725439548492,
-      "learning_rate": 9.880535333324526e-05,
-      "loss": -0.3334,
-      "step": 1570
-    },
-    {
-      "epoch": 4.341362697866483,
-      "grad_norm": 0.10737737268209457,
-      "learning_rate": 9.105743261173859e-05,
-      "loss": -0.2614,
-      "step": 1580
-    },
-    {
-      "epoch": 4.368891947694426,
-      "grad_norm": 0.11335331946611404,
-      "learning_rate": 8.361133302469304e-05,
-      "loss": -0.3117,
-      "step": 1590
-    },
-    {
-      "epoch": 4.3964211975223675,
-      "grad_norm": 0.08087515830993652,
-      "learning_rate": 7.646952710481336e-05,
-      "loss": -0.3063,
-      "step": 1600
-    },
-    {
-      "epoch": 4.423950447350309,
-      "grad_norm": 0.05648915097117424,
-      "learning_rate": 6.963438634183072e-05,
-      "loss": -0.3006,
-      "step": 1610
-    },
-    {
-      "epoch": 4.451479697178252,
-      "grad_norm": 0.07118873298168182,
-      "learning_rate": 6.310818039503197e-05,
-      "loss": -0.3067,
-      "step": 1620
-    },
-    {
-      "epoch": 4.479008947006194,
-      "grad_norm": 0.08804015070199966,
-      "learning_rate": 5.68930763396025e-05,
-      "loss": -0.3039,
-      "step": 1630
-    },
-    {
-      "epoch": 4.5065381968341365,
-      "grad_norm": 0.05966779962182045,
-      "learning_rate": 5.099113794703225e-05,
-      "loss": -0.3179,
-      "step": 1640
-    },
-    {
-      "epoch": 4.534067446662078,
-      "grad_norm": 0.05672675371170044,
-      "learning_rate": 4.540432499982583e-05,
-      "loss": -0.2759,
-      "step": 1650
-    },
-    {
-      "epoch": 4.561596696490021,
-      "grad_norm": 0.0740792378783226,
-      "learning_rate": 4.013449264074187e-05,
-      "loss": -0.3206,
-      "step": 1660
-    },
-    {
-      "epoch": 4.589125946317963,
-      "grad_norm": 0.06297609955072403,
-      "learning_rate": 3.5183390756778455e-05,
-      "loss": -0.3127,
-      "step": 1670
-    },
-    {
-      "epoch": 4.616655196145905,
-      "grad_norm": 0.12687914073467255,
-      "learning_rate": 3.055266339811147e-05,
-      "loss": -0.2758,
-      "step": 1680
-    },
-    {
-      "epoch": 4.644184445973847,
-      "grad_norm": 0.06105898320674896,
-      "learning_rate": 2.6243848232174295e-05,
-      "loss": -0.2919,
-      "step": 1690
-    },
-    {
-      "epoch": 4.671713695801789,
-      "grad_norm": 0.05932333320379257,
-      "learning_rate": 2.2258376033064352e-05,
-      "loss": -0.2945,
-      "step": 1700
-    },
-    {
-      "epoch": 4.699242945629732,
-      "grad_norm": 0.06917830556631088,
-      "learning_rate": 1.8597570206444146e-05,
-      "loss": -0.3324,
-      "step": 1710
-    },
-    {
-      "epoch": 4.726772195457674,
-      "grad_norm": 0.05963951349258423,
-      "learning_rate": 1.5262646350094334e-05,
-      "loss": -0.2848,
-      "step": 1720
-    },
-    {
-      "epoch": 4.754301445285616,
-      "grad_norm": 0.07152219116687775,
-      "learning_rate": 1.2254711850265387e-05,
-      "loss": -0.2945,
-      "step": 1730
-    },
-    {
-      "epoch": 4.781830695113558,
-      "grad_norm": 0.17016345262527466,
-      "learning_rate": 9.57476551396197e-06,
-      "loss": -0.3083,
-      "step": 1740
-    },
-    {
-      "epoch": 4.8093599449415,
-      "grad_norm": 0.06282032281160355,
-      "learning_rate": 7.223697237281668e-06,
-      "loss": -0.3078,
-      "step": 1750
-    },
-    {
-      "epoch": 4.836889194769443,
-      "grad_norm": 0.07180521637201309,
-      "learning_rate": 5.20228770991793e-06,
-      "loss": -0.328,
-      "step": 1760
-    },
-    {
-      "epoch": 4.864418444597384,
-      "grad_norm": 0.052418265491724014,
-      "learning_rate": 3.5112081559267595e-06,
-      "loss": -0.312,
-      "step": 1770
-    },
-    {
-      "epoch": 4.891947694425327,
-      "grad_norm": 0.049820709973573685,
-      "learning_rate": 2.1510201108416726e-06,
-      "loss": -0.3354,
-      "step": 1780
-    },
-    {
-      "epoch": 4.919476944253269,
-      "grad_norm": 0.07788914442062378,
-      "learning_rate": 1.1221752352115199e-06,
-      "loss": -0.2894,
-      "step": 1790
-    },
-    {
-      "epoch": 4.947006194081212,
-      "grad_norm": 0.0543702207505703,
-      "learning_rate": 4.2501516462334357e-07,
-      "loss": -0.3034,
-      "step": 1800
-    },
-    {
-      "epoch": 4.974535443909153,
-      "grad_norm": 0.053358618170022964,
-      "learning_rate": 5.977139625945594e-08,
-      "loss": -0.3006,
-      "step": 1810
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1815,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 3.6471853422026424e+18,
-  "train_batch_size": 4,
-  "trial_name": null,
-  "trial_params": null
-}

logs/checkpoint-1815/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0959f5f03d63010ab92f5df0c251a58814c9980c78f55e26b8c32536f5db0bb3
-size 6840

logs/checkpoint-1815/zero_to_fp32.py

@@ -1,760 +0,0 @@
-#!/usr/bin/env python
-
-# Copyright (c) Microsoft Corporation.
-# SPDX-License-Identifier: Apache-2.0
-
-# DeepSpeed Team
-
-# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
-# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
-# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
-# application.
-#
-# example:
-#   python zero_to_fp32.py . output_dir/
-#   or
-#   python zero_to_fp32.py . output_dir/ --safe_serialization
-
-import argparse
-import torch
-import glob
-import math
-import os
-import re
-import gc
-import json
-import numpy as np
-from tqdm import tqdm
-from collections import OrderedDict
-from dataclasses import dataclass
-
-# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
-# DeepSpeed data structures it has to be available in the current python environment.
-from deepspeed.utils import logger
-from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
-                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
-                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
-
-
-@dataclass
-class zero_model_state:
-    buffers: dict()
-    param_shapes: dict()
-    shared_params: list
-    ds_version: int
-    frozen_param_shapes: dict()
-    frozen_param_fragments: dict()
-
-
-debug = 0
-
-# load to cpu
-device = torch.device('cpu')
-
-
-def atoi(text):
-    return int(text) if text.isdigit() else text
-
-
-def natural_keys(text):
-    '''
-    alist.sort(key=natural_keys) sorts in human order
-    http://nedbatchelder.com/blog/200712/human_sorting.html
-    (See Toothy's implementation in the comments)
-    '''
-    return [atoi(c) for c in re.split(r'(\d+)', text)]
-
-
-def get_model_state_file(checkpoint_dir, zero_stage):
-    if not os.path.isdir(checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
-
-    # there should be only one file
-    if zero_stage <= 2:
-        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
-    elif zero_stage == 3:
-        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
-
-    if not os.path.exists(file):
-        raise FileNotFoundError(f"can't find model states file at '{file}'")
-
-    return file
-
-
-def get_checkpoint_files(checkpoint_dir, glob_pattern):
-    # XXX: need to test that this simple glob rule works for multi-node setup too
-    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
-
-    if len(ckpt_files) == 0:
-        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
-
-    return ckpt_files
-
-
-def get_optim_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
-
-
-def get_model_state_files(checkpoint_dir):
-    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
-
-
-def parse_model_states(files):
-    zero_model_states = []
-    for file in files:
-        state_dict = torch.load(file, map_location=device, weights_only=False)
-
-        if BUFFER_NAMES not in state_dict:
-            raise ValueError(f"{file} is not a model state checkpoint")
-        buffer_names = state_dict[BUFFER_NAMES]
-        if debug:
-            print("Found buffers:", buffer_names)
-
-        # recover just the buffers while restoring them to fp32 if they were saved in fp16
-        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
-        param_shapes = state_dict[PARAM_SHAPES]
-
-        # collect parameters that are included in param_shapes
-        param_names = []
-        for s in param_shapes:
-            for name in s.keys():
-                param_names.append(name)
-
-        # update with frozen parameters
-        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
-        if frozen_param_shapes is not None:
-            if debug:
-                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
-            param_names += list(frozen_param_shapes.keys())
-
-        # handle shared params
-        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
-
-        ds_version = state_dict.get(DS_VERSION, None)
-
-        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
-
-        z_model_state = zero_model_state(buffers=buffers,
-                                         param_shapes=param_shapes,
-                                         shared_params=shared_params,
-                                         ds_version=ds_version,
-                                         frozen_param_shapes=frozen_param_shapes,
-                                         frozen_param_fragments=frozen_param_fragments)
-        zero_model_states.append(z_model_state)
-
-    return zero_model_states
-
-
-def parse_optim_states(files, ds_checkpoint_dir):
-    total_files = len(files)
-    state_dicts = []
-    for f in tqdm(files, desc='Loading checkpoint shards'):
-        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
-        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
-        # and also handle the case where it was already removed by another helper script
-        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
-        state_dicts.append(state_dict)
-
-    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
-        raise ValueError(f"{files[0]} is not a zero checkpoint")
-    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
-    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
-
-    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
-    # parameters can be different from data parallelism for non-expert parameters. So we can just
-    # use the max of the partition_count to get the dp world_size.
-
-    if type(world_size) is list:
-        world_size = max(world_size)
-
-    if world_size != total_files:
-        raise ValueError(
-            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
-            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
-        )
-
-    # the groups are named differently in each stage
-    if zero_stage <= 2:
-        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
-    elif zero_stage == 3:
-        fp32_groups_key = FP32_FLAT_GROUPS
-    else:
-        raise ValueError(f"unknown zero stage {zero_stage}")
-
-    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
-    return zero_stage, world_size, fp32_flat_groups
-
-
-def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
-    """
-    Returns fp32 state_dict reconstructed from ds checkpoint
-
-    Args:
-        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
-
-    """
-    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
-
-    optim_files = get_optim_files(ds_checkpoint_dir)
-    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
-    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
-
-    model_files = get_model_state_files(ds_checkpoint_dir)
-
-    zero_model_states = parse_model_states(model_files)
-    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
-
-    if zero_stage <= 2:
-        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                                          exclude_frozen_parameters)
-    elif zero_stage == 3:
-        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                                          exclude_frozen_parameters)
-
-
-def _zero2_merge_frozen_params(state_dict, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
-
-    if debug:
-        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
-        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        state_dict[name] = frozen_param_fragments[name]
-
-        if debug:
-            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _has_callable(obj, fn):
-    attr = getattr(obj, fn, None)
-    return callable(attr)
-
-
-def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-
-    # Reconstruction protocol:
-    #
-    # XXX: document this
-
-    if debug:
-        for i in range(world_size):
-            for j in range(len(fp32_flat_groups[0])):
-                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
-
-    # XXX: memory usage doubles here (zero2)
-    num_param_groups = len(fp32_flat_groups[0])
-    merged_single_partition_of_fp32_groups = []
-    for i in range(num_param_groups):
-        merged_partitions = [sd[i] for sd in fp32_flat_groups]
-        full_single_fp32_vector = torch.cat(merged_partitions, 0)
-        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
-    avail_numel = sum(
-        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
-
-    if debug:
-        wanted_params = sum([len(shapes) for shapes in param_shapes])
-        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
-        # not asserting if there is a mismatch due to possible padding
-        print(f"Have {avail_numel} numels to process.")
-        print(f"Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    total_numel = 0
-    total_params = 0
-    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
-        offset = 0
-        avail_numel = full_single_fp32_vector.numel()
-        for name, shape in shapes.items():
-
-            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
-            total_numel += unpartitioned_numel
-            total_params += 1
-
-            if debug:
-                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
-            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
-            offset += unpartitioned_numel
-
-        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
-        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
-        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
-        # live optimizer object, so we are checking that the numbers are within the right range
-        align_to = 2 * world_size
-
-        def zero2_align(x):
-            return align_to * math.ceil(x / align_to)
-
-        if debug:
-            print(f"original offset={offset}, avail_numel={avail_numel}")
-
-        offset = zero2_align(offset)
-        avail_numel = zero2_align(avail_numel)
-
-        if debug:
-            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
-
-        # Sanity check
-        if offset != avail_numel:
-            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                               exclude_frozen_parameters):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    if not exclude_frozen_parameters:
-        _zero2_merge_frozen_params(state_dict, zero_model_states)
-
-    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def zero3_partitioned_param_info(unpartitioned_numel, world_size):
-    remainder = unpartitioned_numel % world_size
-    padding_numel = (world_size - remainder) if remainder else 0
-    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
-    return partitioned_numel, padding_numel
-
-
-def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
-    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
-        return
-
-    if debug:
-        for i in range(world_size):
-            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
-            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
-
-        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
-        wanted_params = len(frozen_param_shapes)
-        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
-        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
-        print(f'Frozen params: Have {avail_numel} numels to process.')
-        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
-
-    total_params = 0
-    total_numel = 0
-    for name, shape in zero_model_states[0].frozen_param_shapes.items():
-        total_params += 1
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-
-        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
-        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
-
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
-
-
-class GatheredTensor:
-    """
-    A pseudo tensor that collects partitioned weights.
-    It is more memory efficient when there are multiple groups.
-    """
-
-    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
-        self.flat_groups = flat_groups
-        self.flat_groups_offset = flat_groups_offset
-        self.offset = offset
-        self.partitioned_numel = partitioned_numel
-        self.shape = shape
-        self.dtype = self.flat_groups[0][0].dtype
-
-    def contiguous(self):
-        """
-        Merge partitioned weights from flat_groups into a single tensor.
-        """
-        end_idx = self.offset + self.partitioned_numel
-        world_size = len(self.flat_groups)
-        pad_flat_param_chunks = []
-
-        for rank_i in range(world_size):
-            # for each rank, we need to collect weights from related group/groups
-            flat_groups_at_rank_i = self.flat_groups[rank_i]
-            start_group_id = None
-            end_group_id = None
-            for group_id in range(len(self.flat_groups_offset)):
-                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
-                    start_group_id = group_id
-                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
-                    end_group_id = group_id
-                    break
-            # collect weights from related group/groups
-            for group_id in range(start_group_id, end_group_id + 1):
-                flat_tensor = flat_groups_at_rank_i[group_id]
-                start_offset = self.offset - self.flat_groups_offset[group_id]
-                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
-                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
-
-        # collect weights from all ranks
-        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
-        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
-        return param
-
-
-def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
-    param_shapes = zero_model_states[0].param_shapes
-    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
-
-    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
-    # param, re-consolidating each param, while dealing with padding if any
-
-    # merge list of dicts, preserving order
-    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
-
-    if debug:
-        for i in range(world_size):
-            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
-
-        wanted_params = len(param_shapes)
-        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
-        # not asserting if there is a mismatch due to possible padding
-        avail_numel = fp32_flat_groups[0].numel() * world_size
-        print(f"Trainable params: Have {avail_numel} numels to process.")
-        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
-
-    # params
-    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
-    # out-of-core computing solution
-    offset = 0
-    total_numel = 0
-    total_params = 0
-    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
-    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
-        unpartitioned_numel = shape.numel()
-        total_numel += unpartitioned_numel
-        total_params += 1
-        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
-
-        if debug:
-            print(
-                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
-            )
-
-        # memory efficient tensor
-        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
-        state_dict[name] = tensor
-        offset += partitioned_numel
-
-    offset *= world_size
-
-    # Sanity check
-    if offset != avail_numel:
-        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
-
-    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
-
-
-def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
-                                               exclude_frozen_parameters):
-    state_dict = OrderedDict()
-
-    # buffers
-    buffers = zero_model_states[0].buffers
-    state_dict.update(buffers)
-    if debug:
-        print(f"added {len(buffers)} buffers")
-
-    if not exclude_frozen_parameters:
-        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
-
-    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
-
-    # recover shared parameters
-    for pair in zero_model_states[0].shared_params:
-        if pair[1] in state_dict:
-            state_dict[pair[0]] = state_dict[pair[1]]
-
-    return state_dict
-
-
-def to_torch_tensor(state_dict, return_empty_tensor=False):
-    """
-    Convert state_dict of GatheredTensor to torch tensor
-    """
-    torch_state_dict = {}
-    converted_tensors = {}
-    for name, tensor in state_dict.items():
-        tensor_id = id(tensor)
-        if tensor_id in converted_tensors:  # shared tensors
-            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
-            torch_state_dict[name] = shared_tensor
-        else:
-            converted_tensors[tensor_id] = name
-            if return_empty_tensor:
-                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
-            else:
-                torch_state_dict[name] = tensor.contiguous()
-    return torch_state_dict
-
-
-def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
-                                             tag=None,
-                                             exclude_frozen_parameters=False,
-                                             lazy_mode=False):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
-    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
-    via a model hub.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
-        - ``exclude_frozen_parameters``: exclude frozen parameters
-        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
-          Convert the pesduo tensor to torch tensor by ``.contiguous()``
-
-    Returns:
-        - pytorch ``state_dict``
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        # do the training and checkpoint saving
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
-        model = model.cpu() # move to cpu
-        model.load_state_dict(state_dict)
-        # submit to model hub or save the model to share with others
-
-    In this example the ``model`` will no longer be usable in the deepspeed context of the same
-    application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
-
-    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
-    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
-    the checkpoint. Or you can load state_dict in lazy mode ::
-
-        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
-        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
-        for name, lazy_tensor in state_dict.item():
-            tensor = lazy_tensor.contiguous()  # to cpu
-            print(name, tensor)
-            # del tensor to release memory if it no longer in use
-    """
-    if tag is None:
-        latest_path = os.path.join(checkpoint_dir, 'latest')
-        if os.path.isfile(latest_path):
-            with open(latest_path, 'r') as fd:
-                tag = fd.read().strip()
-        else:
-            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
-
-    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
-
-    if not os.path.isdir(ds_checkpoint_dir):
-        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
-
-    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
-    if lazy_mode:
-        return state_dict
-    else:
-        return to_torch_tensor(state_dict)
-
-
-def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
-                                               output_dir,
-                                               max_shard_size="5GB",
-                                               safe_serialization=False,
-                                               tag=None,
-                                               exclude_frozen_parameters=False):
-    """
-    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
-    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
-
-    Args:
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``output_dir``: directory to the pytorch fp32 state_dict output files
-        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
-        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-        - ``exclude_frozen_parameters``: exclude frozen parameters
-    """
-
-    # Dependency pre-check
-    if safe_serialization:
-        try:
-            from safetensors.torch import save_file
-        except ImportError:
-            print('If you want to use `safe_serialization`, please `pip install safetensors`')
-            raise
-    if max_shard_size is not None:
-        try:
-            from huggingface_hub import split_torch_state_dict_into_shards
-        except ImportError:
-            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
-            raise
-
-    # Convert zero checkpoint to state_dict
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
-                                                          tag,
-                                                          exclude_frozen_parameters,
-                                                          lazy_mode=True)
-
-    # Shard the model if it is too big.
-    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
-    if max_shard_size is not None:
-        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
-        # an memory-efficient approach for sharding
-        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
-        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
-                                                              filename_pattern=filename_pattern,
-                                                              max_shard_size=max_shard_size)
-    else:
-        from collections import namedtuple
-        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
-        state_dict_split = StateDictSplit(is_sharded=False,
-                                          filename_to_tensors={weights_name: list(state_dict.keys())})
-
-    # Save the model by shard
-    os.makedirs(output_dir, exist_ok=True)
-    filename_to_tensors = state_dict_split.filename_to_tensors.items()
-    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
-        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
-        shard_state_dict = to_torch_tensor(shard_state_dict)
-        output_path = os.path.join(output_dir, shard_file)
-        if safe_serialization:
-            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
-        else:
-            torch.save(shard_state_dict, output_path)
-        # release the memory of current shard
-        for tensor_name in list(shard_state_dict.keys()):
-            del state_dict[tensor_name]
-            del shard_state_dict[tensor_name]
-        del shard_state_dict
-        gc.collect()
-
-    # Save index if sharded
-    if state_dict_split.is_sharded:
-        index = {
-            "metadata": state_dict_split.metadata,
-            "weight_map": state_dict_split.tensor_to_filename,
-        }
-        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
-        save_index_file = os.path.join(output_dir, save_index_file)
-        with open(save_index_file, "w", encoding="utf-8") as f:
-            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
-            f.write(content)
-
-
-def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
-    """
-    1. Put the provided model to cpu
-    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
-    3. Load it into the provided model
-
-    Args:
-        - ``model``: the model object to update
-        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
-        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
-
-    Returns:
-        - ``model`: modified model
-
-    Make sure you have plenty of CPU memory available before you call this function. If you don't
-    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
-    conveniently placed for you in the checkpoint folder.
-
-    A typical usage might be ::
-
-        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
-        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
-        # submit to model hub or save the model to share with others
-
-    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
-    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
-    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
-
-    """
-    logger.info(f"Extracting fp32 weights")
-    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
-
-    logger.info(f"Overwriting model with fp32 weights")
-    model = model.cpu()
-    model.load_state_dict(state_dict, strict=False)
-
-    return model
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("checkpoint_dir",
-                        type=str,
-                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
-    parser.add_argument("output_dir",
-                        type=str,
-                        help="directory to the pytorch fp32 state_dict output files"
-                        "(e.g. path/checkpoint-12-output/)")
-    parser.add_argument(
-        "--max_shard_size",
-        type=str,
-        default="5GB",
-        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
-        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
-        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
-        "without CPU OOM issues.")
-    parser.add_argument(
-        "--safe_serialization",
-        default=False,
-        action='store_true',
-        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
-    parser.add_argument("-t",
-                        "--tag",
-                        type=str,
-                        default=None,
-                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
-    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
-    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
-    args = parser.parse_args()
-
-    debug = args.debug
-
-    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
-                                               args.output_dir,
-                                               max_shard_size=args.max_shard_size,
-                                               safe_serialization=args.safe_serialization,
-                                               tag=args.tag,
-                                               exclude_frozen_parameters=args.exclude_frozen_parameters)