Initial commit

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: train_2024-07-16-09-46-28_llama3
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_2024-07-16-09-46-28_llama3
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the truth_train_0716 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0a0+ebedce2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.887459807073955,
+    "num_input_tokens_seen": 1208400,
+    "total_flos": 5.441370708980531e+16,
+    "train_loss": 0.5078434096239538,
+    "train_runtime": 2562.642,
+    "train_samples_per_second": 9.693,
+    "train_steps_per_second": 0.074
+}

checkpoint-190/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-190/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.42.3"
+}

checkpoint-190/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5bf83651c6ff42b140c7aa627ab5f79c2d0affeddb8770f7bf7c30cd719e19
+size 12045399116

checkpoint-190/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5257630b420a8debfa8c71b54ad3dd861f79094d236031e51555525098093cd1
+size 12045399948

checkpoint-190/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9d0693d76a926d89c3451dc4b9e58cfad7eeb75664e893afcbaa64e35505ed
+size 12045400204

checkpoint-190/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1367f7bcae31e852a41369c0a77dd33d692353e990a0f2b6e478996b37ed621
+size 12045399948

checkpoint-190/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6356be9c4981109792745b24ad284415b1883b8a98b73f8832a4404155fc4d
+size 12045400204

checkpoint-190/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53bab3cfd5f002d4f0284a4b9ec054c54390f83c964119a0a3d86ee8a92fd0e
+size 12045400268

checkpoint-190/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ee845725ef014b5daa09b7e3551278bdcf7a145c55a12545a3e55e9e4c000b
+size 12045399948

checkpoint-190/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c0d1eb602eeda6db1d30ed57595e6049a64780eb66b6e8c3384cadbff7d3bc
+size 12045398796

checkpoint-190/global_step190/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02507fd1a3bfa357f230ddf691ff4ded2d95995624cdec1fc6da83ed553a061e
+size 16060610616

checkpoint-190/latest

@@ -0,0 +1 @@
+global_step190

checkpoint-190/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edf4ea2e752ee2cdaa5306c36a9df4993e550809e7119b58ad6e822f11dcb3e
+size 4976698672

checkpoint-190/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f90ed6cc342f4ce5b217e38fe9b6ba34ae47d6accae3ef146aaeefc3a1fd33e
+size 4999802720

checkpoint-190/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5478badd4e2d1ea445b7e37587fa74a3eee1f8fa1fb11ce8ea9cf76f941e90
+size 4915916176

checkpoint-190/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9663dceae3a8fdf1f2589357abc81d4d26cdea0ae337d106c64c2e4d08c67db3
+size 1168138808

checkpoint-190/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-190/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0ef6f96a48e59aa52c4b471312c2a62378c19acc7ebbae839612b03a7d775a
+size 15984

checkpoint-190/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab11d533c0fdad46ea8b8e295ba5fdb705e078eeb88cc28f37d82913508766e9
+size 15984

checkpoint-190/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615c168147e3465ce5bfab6da2ff4afc68566ce00ec0f0c6c9fc988038a58d0a
+size 15984

checkpoint-190/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f71e8f8674ecaef9f8cdcbf7ac457a8b8ff15b12694ba2a2fffcb4b43f0f08
+size 15984

checkpoint-190/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88cf6d674dab5545c300a55135f08ca935730a3d35e2c419fb0b333f19482c19
+size 15984

checkpoint-190/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2754f2cd8824702f027870d93748b3c0491b0ecd30f1e3d8e937116b2be6151f
+size 15984

checkpoint-190/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1385124ac55604598f45ea6e2d141f29456647d3e7c10d12ca64ec93d312be8d
+size 15984

checkpoint-190/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416538efaec7391fa8fe782fb15146b83e5612d9e1961292c34c53e964806873
+size 15984

checkpoint-190/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e610dd5e9f27fcc75487bd147a6e92e36d0c3d068f260ff6e94230dced07d21d
+size 1064

checkpoint-190/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<|eot_id|>"
+}

checkpoint-190/tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "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": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "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": "<|reserved_special_token_4|>",
+      "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": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-190/trainer_state.json

@@ -0,0 +1,1553 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.887459807073955,
+  "eval_steps": 500,
+  "global_step": 190,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02572347266881029,
+      "grad_norm": 612.1110229492188,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 14.1364,
+      "num_input_tokens_seen": 6512,
+      "step": 1
+    },
+    {
+      "epoch": 0.05144694533762058,
+      "grad_norm": 608.3916625976562,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 13.7804,
+      "num_input_tokens_seen": 12848,
+      "step": 2
+    },
+    {
+      "epoch": 0.07717041800643087,
+      "grad_norm": 622.3192138671875,
+      "learning_rate": 1.5e-06,
+      "loss": 13.4871,
+      "num_input_tokens_seen": 19248,
+      "step": 3
+    },
+    {
+      "epoch": 0.10289389067524116,
+      "grad_norm": 611.6488647460938,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 12.79,
+      "num_input_tokens_seen": 25344,
+      "step": 4
+    },
+    {
+      "epoch": 0.12861736334405144,
+      "grad_norm": 508.9140319824219,
+      "learning_rate": 2.5e-06,
+      "loss": 9.2748,
+      "num_input_tokens_seen": 31968,
+      "step": 5
+    },
+    {
+      "epoch": 0.15434083601286175,
+      "grad_norm": 630.509521484375,
+      "learning_rate": 3e-06,
+      "loss": 6.5585,
+      "num_input_tokens_seen": 38160,
+      "step": 6
+    },
+    {
+      "epoch": 0.18006430868167203,
+      "grad_norm": 512.7638549804688,
+      "learning_rate": 3.5e-06,
+      "loss": 5.3984,
+      "num_input_tokens_seen": 44144,
+      "step": 7
+    },
+    {
+      "epoch": 0.2057877813504823,
+      "grad_norm": 220.47471618652344,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.9363,
+      "num_input_tokens_seen": 50432,
+      "step": 8
+    },
+    {
+      "epoch": 0.2315112540192926,
+      "grad_norm": 114.83863830566406,
+      "learning_rate": 4.5e-06,
+      "loss": 0.6783,
+      "num_input_tokens_seen": 56928,
+      "step": 9
+    },
+    {
+      "epoch": 0.2572347266881029,
+      "grad_norm": 383.7873229980469,
+      "learning_rate": 5e-06,
+      "loss": 2.9945,
+      "num_input_tokens_seen": 63344,
+      "step": 10
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 53.58182907104492,
+      "learning_rate": 4.9996192378909785e-06,
+      "loss": 0.2916,
+      "num_input_tokens_seen": 69568,
+      "step": 11
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 200.5736083984375,
+      "learning_rate": 4.99847706754774e-06,
+      "loss": 2.2775,
+      "num_input_tokens_seen": 75824,
+      "step": 12
+    },
+    {
+      "epoch": 0.33440514469453375,
+      "grad_norm": 89.13434600830078,
+      "learning_rate": 4.9965738368864345e-06,
+      "loss": 0.3757,
+      "num_input_tokens_seen": 82160,
+      "step": 13
+    },
+    {
+      "epoch": 0.36012861736334406,
+      "grad_norm": 149.89199829101562,
+      "learning_rate": 4.993910125649561e-06,
+      "loss": 1.9543,
+      "num_input_tokens_seen": 88624,
+      "step": 14
+    },
+    {
+      "epoch": 0.3858520900321543,
+      "grad_norm": 93.02680206298828,
+      "learning_rate": 4.990486745229364e-06,
+      "loss": 0.7398,
+      "num_input_tokens_seen": 94800,
+      "step": 15
+    },
+    {
+      "epoch": 0.4115755627009646,
+      "grad_norm": 274.1518249511719,
+      "learning_rate": 4.986304738420684e-06,
+      "loss": 1.1868,
+      "num_input_tokens_seen": 101360,
+      "step": 16
+    },
+    {
+      "epoch": 0.43729903536977494,
+      "grad_norm": 75.59544372558594,
+      "learning_rate": 4.981365379103306e-06,
+      "loss": 0.5418,
+      "num_input_tokens_seen": 107488,
+      "step": 17
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 21.915510177612305,
+      "learning_rate": 4.975670171853926e-06,
+      "loss": 0.2263,
+      "num_input_tokens_seen": 113920,
+      "step": 18
+    },
+    {
+      "epoch": 0.4887459807073955,
+      "grad_norm": 12.356107711791992,
+      "learning_rate": 4.9692208514878445e-06,
+      "loss": 0.1612,
+      "num_input_tokens_seen": 120352,
+      "step": 19
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 49.00923538208008,
+      "learning_rate": 4.962019382530521e-06,
+      "loss": 0.3299,
+      "num_input_tokens_seen": 126880,
+      "step": 20
+    },
+    {
+      "epoch": 0.5401929260450161,
+      "grad_norm": 35.158695220947266,
+      "learning_rate": 4.9540679586191605e-06,
+      "loss": 0.2013,
+      "num_input_tokens_seen": 133344,
+      "step": 21
+    },
+    {
+      "epoch": 0.5659163987138264,
+      "grad_norm": 30.501089096069336,
+      "learning_rate": 4.9453690018345144e-06,
+      "loss": 0.2446,
+      "num_input_tokens_seen": 139744,
+      "step": 22
+    },
+    {
+      "epoch": 0.5916398713826366,
+      "grad_norm": 29.609901428222656,
+      "learning_rate": 4.935925161963089e-06,
+      "loss": 0.2235,
+      "num_input_tokens_seen": 146144,
+      "step": 23
+    },
+    {
+      "epoch": 0.617363344051447,
+      "grad_norm": 7.487663745880127,
+      "learning_rate": 4.925739315689991e-06,
+      "loss": 0.116,
+      "num_input_tokens_seen": 152240,
+      "step": 24
+    },
+    {
+      "epoch": 0.6430868167202572,
+      "grad_norm": 37.3343620300293,
+      "learning_rate": 4.914814565722671e-06,
+      "loss": 0.2179,
+      "num_input_tokens_seen": 158512,
+      "step": 25
+    },
+    {
+      "epoch": 0.6688102893890675,
+      "grad_norm": 19.37504768371582,
+      "learning_rate": 4.903154239845798e-06,
+      "loss": 0.1414,
+      "num_input_tokens_seen": 164784,
+      "step": 26
+    },
+    {
+      "epoch": 0.6945337620578779,
+      "grad_norm": 7.562462329864502,
+      "learning_rate": 4.890761889907589e-06,
+      "loss": 0.1181,
+      "num_input_tokens_seen": 171312,
+      "step": 27
+    },
+    {
+      "epoch": 0.7202572347266881,
+      "grad_norm": 45.42784881591797,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.2753,
+      "num_input_tokens_seen": 177856,
+      "step": 28
+    },
+    {
+      "epoch": 0.7459807073954984,
+      "grad_norm": 42.35463333129883,
+      "learning_rate": 4.863796438998293e-06,
+      "loss": 0.3255,
+      "num_input_tokens_seen": 184368,
+      "step": 29
+    },
+    {
+      "epoch": 0.7717041800643086,
+      "grad_norm": 29.56382179260254,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 0.2352,
+      "num_input_tokens_seen": 190928,
+      "step": 30
+    },
+    {
+      "epoch": 0.797427652733119,
+      "grad_norm": 10.221027374267578,
+      "learning_rate": 4.833951066243004e-06,
+      "loss": 0.063,
+      "num_input_tokens_seen": 197232,
+      "step": 31
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 19.372211456298828,
+      "learning_rate": 4.817959636416969e-06,
+      "loss": 0.2042,
+      "num_input_tokens_seen": 203584,
+      "step": 32
+    },
+    {
+      "epoch": 0.8488745980707395,
+      "grad_norm": 15.362005233764648,
+      "learning_rate": 4.801262133631101e-06,
+      "loss": 0.1364,
+      "num_input_tokens_seen": 210128,
+      "step": 33
+    },
+    {
+      "epoch": 0.8745980707395499,
+      "grad_norm": 17.515932083129883,
+      "learning_rate": 4.783863644106502e-06,
+      "loss": 0.0934,
+      "num_input_tokens_seen": 216512,
+      "step": 34
+    },
+    {
+      "epoch": 0.9003215434083601,
+      "grad_norm": 10.493622779846191,
+      "learning_rate": 4.765769467591626e-06,
+      "loss": 0.1332,
+      "num_input_tokens_seen": 222928,
+      "step": 35
+    },
+    {
+      "epoch": 0.9260450160771704,
+      "grad_norm": 21.616741180419922,
+      "learning_rate": 4.746985115747918e-06,
+      "loss": 0.1595,
+      "num_input_tokens_seen": 229232,
+      "step": 36
+    },
+    {
+      "epoch": 0.9517684887459807,
+      "grad_norm": 18.24679946899414,
+      "learning_rate": 4.72751631047092e-06,
+      "loss": 0.1528,
+      "num_input_tokens_seen": 235680,
+      "step": 37
+    },
+    {
+      "epoch": 0.977491961414791,
+      "grad_norm": 8.862295150756836,
+      "learning_rate": 4.707368982147318e-06,
+      "loss": 0.1342,
+      "num_input_tokens_seen": 242192,
+      "step": 38
+    },
+    {
+      "epoch": 1.0032154340836013,
+      "grad_norm": 25.429838180541992,
+      "learning_rate": 4.68654926784849e-06,
+      "loss": 0.1586,
+      "num_input_tokens_seen": 248672,
+      "step": 39
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "grad_norm": 9.540814399719238,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 0.1072,
+      "num_input_tokens_seen": 255072,
+      "step": 40
+    },
+    {
+      "epoch": 1.0546623794212218,
+      "grad_norm": 3.9775660037994385,
+      "learning_rate": 4.642918251755281e-06,
+      "loss": 0.0357,
+      "num_input_tokens_seen": 261584,
+      "step": 41
+    },
+    {
+      "epoch": 1.0803858520900322,
+      "grad_norm": 8.192290306091309,
+      "learning_rate": 4.620120240391065e-06,
+      "loss": 0.06,
+      "num_input_tokens_seen": 268032,
+      "step": 42
+    },
+    {
+      "epoch": 1.1061093247588425,
+      "grad_norm": 6.468256950378418,
+      "learning_rate": 4.596676419863561e-06,
+      "loss": 0.0902,
+      "num_input_tokens_seen": 274560,
+      "step": 43
+    },
+    {
+      "epoch": 1.1318327974276527,
+      "grad_norm": 4.978611469268799,
+      "learning_rate": 4.572593931387604e-06,
+      "loss": 0.0202,
+      "num_input_tokens_seen": 280960,
+      "step": 44
+    },
+    {
+      "epoch": 1.157556270096463,
+      "grad_norm": 7.448028564453125,
+      "learning_rate": 4.54788011072248e-06,
+      "loss": 0.038,
+      "num_input_tokens_seen": 287104,
+      "step": 45
+    },
+    {
+      "epoch": 1.1832797427652733,
+      "grad_norm": 10.028037071228027,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.0379,
+      "num_input_tokens_seen": 293520,
+      "step": 46
+    },
+    {
+      "epoch": 1.2090032154340835,
+      "grad_norm": 13.968883514404297,
+      "learning_rate": 4.496588775118232e-06,
+      "loss": 0.0742,
+      "num_input_tokens_seen": 299936,
+      "step": 47
+    },
+    {
+      "epoch": 1.234726688102894,
+      "grad_norm": 8.629486083984375,
+      "learning_rate": 4.470026884016805e-06,
+      "loss": 0.0658,
+      "num_input_tokens_seen": 305936,
+      "step": 48
+    },
+    {
+      "epoch": 1.2604501607717042,
+      "grad_norm": 11.009612083435059,
+      "learning_rate": 4.442864903642428e-06,
+      "loss": 0.0336,
+      "num_input_tokens_seen": 312528,
+      "step": 49
+    },
+    {
+      "epoch": 1.2861736334405145,
+      "grad_norm": 7.794949531555176,
+      "learning_rate": 4.415111107797445e-06,
+      "loss": 0.1021,
+      "num_input_tokens_seen": 318752,
+      "step": 50
+    },
+    {
+      "epoch": 1.3118971061093248,
+      "grad_norm": 12.327733039855957,
+      "learning_rate": 4.386773950556931e-06,
+      "loss": 0.1312,
+      "num_input_tokens_seen": 325088,
+      "step": 51
+    },
+    {
+      "epoch": 1.337620578778135,
+      "grad_norm": 8.146430969238281,
+      "learning_rate": 4.357862063693486e-06,
+      "loss": 0.0665,
+      "num_input_tokens_seen": 331424,
+      "step": 52
+    },
+    {
+      "epoch": 1.3633440514469453,
+      "grad_norm": 6.919386386871338,
+      "learning_rate": 4.328384254047927e-06,
+      "loss": 0.0679,
+      "num_input_tokens_seen": 337776,
+      "step": 53
+    },
+    {
+      "epoch": 1.3890675241157555,
+      "grad_norm": 2.923135280609131,
+      "learning_rate": 4.2983495008466285e-06,
+      "loss": 0.0579,
+      "num_input_tokens_seen": 344000,
+      "step": 54
+    },
+    {
+      "epoch": 1.414790996784566,
+      "grad_norm": 5.682593822479248,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0542,
+      "num_input_tokens_seen": 350528,
+      "step": 55
+    },
+    {
+      "epoch": 1.4405144694533762,
+      "grad_norm": 5.936847686767578,
+      "learning_rate": 4.236645926147493e-06,
+      "loss": 0.0476,
+      "num_input_tokens_seen": 356896,
+      "step": 56
+    },
+    {
+      "epoch": 1.4662379421221865,
+      "grad_norm": 3.671848773956299,
+      "learning_rate": 4.204995900156247e-06,
+      "loss": 0.0613,
+      "num_input_tokens_seen": 363376,
+      "step": 57
+    },
+    {
+      "epoch": 1.4919614147909968,
+      "grad_norm": 6.306807994842529,
+      "learning_rate": 4.172826515897146e-06,
+      "loss": 0.0995,
+      "num_input_tokens_seen": 369680,
+      "step": 58
+    },
+    {
+      "epoch": 1.517684887459807,
+      "grad_norm": 7.488581657409668,
+      "learning_rate": 4.140147572476269e-06,
+      "loss": 0.0532,
+      "num_input_tokens_seen": 375904,
+      "step": 59
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "grad_norm": 8.461729049682617,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 0.0824,
+      "num_input_tokens_seen": 382304,
+      "step": 60
+    },
+    {
+      "epoch": 1.5691318327974275,
+      "grad_norm": 4.186163902282715,
+      "learning_rate": 4.073300977624594e-06,
+      "loss": 0.0499,
+      "num_input_tokens_seen": 388688,
+      "step": 61
+    },
+    {
+      "epoch": 1.594855305466238,
+      "grad_norm": 4.451269149780273,
+      "learning_rate": 4.039153688314146e-06,
+      "loss": 0.0413,
+      "num_input_tokens_seen": 395152,
+      "step": 62
+    },
+    {
+      "epoch": 1.6205787781350482,
+      "grad_norm": 7.160181999206543,
+      "learning_rate": 4.0045375578801216e-06,
+      "loss": 0.0637,
+      "num_input_tokens_seen": 401728,
+      "step": 63
+    },
+    {
+      "epoch": 1.6463022508038585,
+      "grad_norm": 8.231119155883789,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.0529,
+      "num_input_tokens_seen": 407904,
+      "step": 64
+    },
+    {
+      "epoch": 1.6720257234726688,
+      "grad_norm": 5.919021129608154,
+      "learning_rate": 3.933941090877615e-06,
+      "loss": 0.0474,
+      "num_input_tokens_seen": 414240,
+      "step": 65
+    },
+    {
+      "epoch": 1.697749196141479,
+      "grad_norm": 5.378300189971924,
+      "learning_rate": 3.897982258676867e-06,
+      "loss": 0.0649,
+      "num_input_tokens_seen": 420448,
+      "step": 66
+    },
+    {
+      "epoch": 1.7234726688102895,
+      "grad_norm": 9.992879867553711,
+      "learning_rate": 3.861597587537568e-06,
+      "loss": 0.0505,
+      "num_input_tokens_seen": 426784,
+      "step": 67
+    },
+    {
+      "epoch": 1.7491961414790995,
+      "grad_norm": 5.876017093658447,
+      "learning_rate": 3.824798160583012e-06,
+      "loss": 0.0621,
+      "num_input_tokens_seen": 432816,
+      "step": 68
+    },
+    {
+      "epoch": 1.77491961414791,
+      "grad_norm": 8.401307106018066,
+      "learning_rate": 3.787595187275136e-06,
+      "loss": 0.0769,
+      "num_input_tokens_seen": 439232,
+      "step": 69
+    },
+    {
+      "epoch": 1.8006430868167203,
+      "grad_norm": 8.439587593078613,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0435,
+      "num_input_tokens_seen": 445792,
+      "step": 70
+    },
+    {
+      "epoch": 1.8263665594855305,
+      "grad_norm": 6.123202323913574,
+      "learning_rate": 3.7120240506158433e-06,
+      "loss": 0.0673,
+      "num_input_tokens_seen": 452400,
+      "step": 71
+    },
+    {
+      "epoch": 1.852090032154341,
+      "grad_norm": 12.049100875854492,
+      "learning_rate": 3.6736789069647273e-06,
+      "loss": 0.1316,
+      "num_input_tokens_seen": 458528,
+      "step": 72
+    },
+    {
+      "epoch": 1.877813504823151,
+      "grad_norm": 6.853906631469727,
+      "learning_rate": 3.634976249348867e-06,
+      "loss": 0.0531,
+      "num_input_tokens_seen": 464976,
+      "step": 73
+    },
+    {
+      "epoch": 1.9035369774919615,
+      "grad_norm": 3.6796371936798096,
+      "learning_rate": 3.595927866972694e-06,
+      "loss": 0.0287,
+      "num_input_tokens_seen": 471440,
+      "step": 74
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "grad_norm": 11.764636039733887,
+      "learning_rate": 3.556545654351749e-06,
+      "loss": 0.0648,
+      "num_input_tokens_seen": 477776,
+      "step": 75
+    },
+    {
+      "epoch": 1.954983922829582,
+      "grad_norm": 15.143081665039062,
+      "learning_rate": 3.516841607689501e-06,
+      "loss": 0.1211,
+      "num_input_tokens_seen": 484096,
+      "step": 76
+    },
+    {
+      "epoch": 1.9807073954983923,
+      "grad_norm": 13.158181190490723,
+      "learning_rate": 3.476827821223184e-06,
+      "loss": 0.0879,
+      "num_input_tokens_seen": 490176,
+      "step": 77
+    },
+    {
+      "epoch": 2.0064308681672025,
+      "grad_norm": 5.389456748962402,
+      "learning_rate": 3.436516483539781e-06,
+      "loss": 0.0227,
+      "num_input_tokens_seen": 496672,
+      "step": 78
+    },
+    {
+      "epoch": 2.032154340836013,
+      "grad_norm": 1.3878227472305298,
+      "learning_rate": 3.39591987386325e-06,
+      "loss": 0.0228,
+      "num_input_tokens_seen": 503088,
+      "step": 79
+    },
+    {
+      "epoch": 2.057877813504823,
+      "grad_norm": 4.809704303741455,
+      "learning_rate": 3.3550503583141726e-06,
+      "loss": 0.036,
+      "num_input_tokens_seen": 509472,
+      "step": 80
+    },
+    {
+      "epoch": 2.0836012861736335,
+      "grad_norm": 4.475839614868164,
+      "learning_rate": 3.313920386142892e-06,
+      "loss": 0.0138,
+      "num_input_tokens_seen": 515728,
+      "step": 81
+    },
+    {
+      "epoch": 2.1093247588424435,
+      "grad_norm": 9.445964813232422,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.0697,
+      "num_input_tokens_seen": 521904,
+      "step": 82
+    },
+    {
+      "epoch": 2.135048231511254,
+      "grad_norm": 5.295349597930908,
+      "learning_rate": 3.230929261806842e-06,
+      "loss": 0.0508,
+      "num_input_tokens_seen": 527952,
+      "step": 83
+    },
+    {
+      "epoch": 2.1607717041800645,
+      "grad_norm": 5.535093307495117,
+      "learning_rate": 3.189093389542498e-06,
+      "loss": 0.0088,
+      "num_input_tokens_seen": 534624,
+      "step": 84
+    },
+    {
+      "epoch": 2.1864951768488745,
+      "grad_norm": 1.4181060791015625,
+      "learning_rate": 3.147047612756302e-06,
+      "loss": 0.0158,
+      "num_input_tokens_seen": 541168,
+      "step": 85
+    },
+    {
+      "epoch": 2.212218649517685,
+      "grad_norm": 4.84325647354126,
+      "learning_rate": 3.1048047389991693e-06,
+      "loss": 0.006,
+      "num_input_tokens_seen": 547488,
+      "step": 86
+    },
+    {
+      "epoch": 2.237942122186495,
+      "grad_norm": 7.397033214569092,
+      "learning_rate": 3.062377635859663e-06,
+      "loss": 0.038,
+      "num_input_tokens_seen": 554272,
+      "step": 87
+    },
+    {
+      "epoch": 2.2636655948553055,
+      "grad_norm": 0.08836190402507782,
+      "learning_rate": 3.019779227044398e-06,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 560528,
+      "step": 88
+    },
+    {
+      "epoch": 2.289389067524116,
+      "grad_norm": 2.0779523849487305,
+      "learning_rate": 2.9770224884413625e-06,
+      "loss": 0.0111,
+      "num_input_tokens_seen": 566784,
+      "step": 89
+    },
+    {
+      "epoch": 2.315112540192926,
+      "grad_norm": 1.6369861364364624,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 0.0008,
+      "num_input_tokens_seen": 573344,
+      "step": 90
+    },
+    {
+      "epoch": 2.3408360128617365,
+      "grad_norm": 4.53826904296875,
+      "learning_rate": 2.8910861626005774e-06,
+      "loss": 0.0182,
+      "num_input_tokens_seen": 579776,
+      "step": 91
+    },
+    {
+      "epoch": 2.3665594855305465,
+      "grad_norm": 5.374476909637451,
+      "learning_rate": 2.847932752400164e-06,
+      "loss": 0.0491,
+      "num_input_tokens_seen": 586096,
+      "step": 92
+    },
+    {
+      "epoch": 2.392282958199357,
+      "grad_norm": 1.1637392044067383,
+      "learning_rate": 2.804673358512869e-06,
+      "loss": 0.004,
+      "num_input_tokens_seen": 592528,
+      "step": 93
+    },
+    {
+      "epoch": 2.418006430868167,
+      "grad_norm": 1.8136231899261475,
+      "learning_rate": 2.761321158169134e-06,
+      "loss": 0.0176,
+      "num_input_tokens_seen": 598960,
+      "step": 94
+    },
+    {
+      "epoch": 2.4437299035369775,
+      "grad_norm": 11.001687049865723,
+      "learning_rate": 2.717889356869146e-06,
+      "loss": 0.019,
+      "num_input_tokens_seen": 605232,
+      "step": 95
+    },
+    {
+      "epoch": 2.469453376205788,
+      "grad_norm": 4.748091697692871,
+      "learning_rate": 2.6743911843603134e-06,
+      "loss": 0.027,
+      "num_input_tokens_seen": 611344,
+      "step": 96
+    },
+    {
+      "epoch": 2.495176848874598,
+      "grad_norm": 4.990153789520264,
+      "learning_rate": 2.6308398906073603e-06,
+      "loss": 0.0354,
+      "num_input_tokens_seen": 617712,
+      "step": 97
+    },
+    {
+      "epoch": 2.5209003215434085,
+      "grad_norm": 10.616851806640625,
+      "learning_rate": 2.587248741756253e-06,
+      "loss": 0.0741,
+      "num_input_tokens_seen": 624208,
+      "step": 98
+    },
+    {
+      "epoch": 2.5466237942122185,
+      "grad_norm": 6.855626106262207,
+      "learning_rate": 2.543631016093209e-06,
+      "loss": 0.0582,
+      "num_input_tokens_seen": 630496,
+      "step": 99
+    },
+    {
+      "epoch": 2.572347266881029,
+      "grad_norm": 4.2168426513671875,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0096,
+      "num_input_tokens_seen": 637040,
+      "step": 100
+    },
+    {
+      "epoch": 2.598070739549839,
+      "grad_norm": 6.813520908355713,
+      "learning_rate": 2.4563689839067913e-06,
+      "loss": 0.0263,
+      "num_input_tokens_seen": 643472,
+      "step": 101
+    },
+    {
+      "epoch": 2.6237942122186495,
+      "grad_norm": 0.9154559373855591,
+      "learning_rate": 2.4127512582437486e-06,
+      "loss": 0.0121,
+      "num_input_tokens_seen": 649760,
+      "step": 102
+    },
+    {
+      "epoch": 2.64951768488746,
+      "grad_norm": 6.223565101623535,
+      "learning_rate": 2.3691601093926406e-06,
+      "loss": 0.0204,
+      "num_input_tokens_seen": 656096,
+      "step": 103
+    },
+    {
+      "epoch": 2.67524115755627,
+      "grad_norm": 2.3013968467712402,
+      "learning_rate": 2.325608815639687e-06,
+      "loss": 0.0325,
+      "num_input_tokens_seen": 662624,
+      "step": 104
+    },
+    {
+      "epoch": 2.7009646302250805,
+      "grad_norm": 2.195141077041626,
+      "learning_rate": 2.2821106431308546e-06,
+      "loss": 0.0076,
+      "num_input_tokens_seen": 668768,
+      "step": 105
+    },
+    {
+      "epoch": 2.7266881028938905,
+      "grad_norm": 14.679264068603516,
+      "learning_rate": 2.238678841830867e-06,
+      "loss": 0.0485,
+      "num_input_tokens_seen": 674992,
+      "step": 106
+    },
+    {
+      "epoch": 2.752411575562701,
+      "grad_norm": 2.058547258377075,
+      "learning_rate": 2.195326641487132e-06,
+      "loss": 0.007,
+      "num_input_tokens_seen": 681120,
+      "step": 107
+    },
+    {
+      "epoch": 2.778135048231511,
+      "grad_norm": 2.056870460510254,
+      "learning_rate": 2.1520672475998374e-06,
+      "loss": 0.0347,
+      "num_input_tokens_seen": 687376,
+      "step": 108
+    },
+    {
+      "epoch": 2.8038585209003215,
+      "grad_norm": 3.1806418895721436,
+      "learning_rate": 2.1089138373994226e-06,
+      "loss": 0.0142,
+      "num_input_tokens_seen": 693984,
+      "step": 109
+    },
+    {
+      "epoch": 2.829581993569132,
+      "grad_norm": 4.262523651123047,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 0.0414,
+      "num_input_tokens_seen": 700352,
+      "step": 110
+    },
+    {
+      "epoch": 2.855305466237942,
+      "grad_norm": 4.998467445373535,
+      "learning_rate": 2.022977511558638e-06,
+      "loss": 0.0419,
+      "num_input_tokens_seen": 706768,
+      "step": 111
+    },
+    {
+      "epoch": 2.8810289389067525,
+      "grad_norm": 4.63454532623291,
+      "learning_rate": 1.9802207729556023e-06,
+      "loss": 0.043,
+      "num_input_tokens_seen": 713248,
+      "step": 112
+    },
+    {
+      "epoch": 2.906752411575563,
+      "grad_norm": 2.7104055881500244,
+      "learning_rate": 1.937622364140338e-06,
+      "loss": 0.0192,
+      "num_input_tokens_seen": 719568,
+      "step": 113
+    },
+    {
+      "epoch": 2.932475884244373,
+      "grad_norm": 5.943557262420654,
+      "learning_rate": 1.895195261000831e-06,
+      "loss": 0.0427,
+      "num_input_tokens_seen": 725984,
+      "step": 114
+    },
+    {
+      "epoch": 2.958199356913183,
+      "grad_norm": 1.0689281225204468,
+      "learning_rate": 1.852952387243698e-06,
+      "loss": 0.0116,
+      "num_input_tokens_seen": 732224,
+      "step": 115
+    },
+    {
+      "epoch": 2.9839228295819935,
+      "grad_norm": 3.041832208633423,
+      "learning_rate": 1.8109066104575023e-06,
+      "loss": 0.0135,
+      "num_input_tokens_seen": 738496,
+      "step": 116
+    },
+    {
+      "epoch": 3.009646302250804,
+      "grad_norm": 2.22163462638855,
+      "learning_rate": 1.7690707381931585e-06,
+      "loss": 0.0128,
+      "num_input_tokens_seen": 744880,
+      "step": 117
+    },
+    {
+      "epoch": 3.035369774919614,
+      "grad_norm": 0.32683318853378296,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.0021,
+      "num_input_tokens_seen": 751408,
+      "step": 118
+    },
+    {
+      "epoch": 3.0610932475884245,
+      "grad_norm": 0.8898715972900391,
+      "learning_rate": 1.686079613857109e-06,
+      "loss": 0.0057,
+      "num_input_tokens_seen": 757632,
+      "step": 119
+    },
+    {
+      "epoch": 3.0868167202572345,
+      "grad_norm": 2.082993984222412,
+      "learning_rate": 1.6449496416858285e-06,
+      "loss": 0.0197,
+      "num_input_tokens_seen": 763936,
+      "step": 120
+    },
+    {
+      "epoch": 3.112540192926045,
+      "grad_norm": 0.7368833422660828,
+      "learning_rate": 1.6040801261367494e-06,
+      "loss": 0.0017,
+      "num_input_tokens_seen": 770064,
+      "step": 121
+    },
+    {
+      "epoch": 3.1382636655948555,
+      "grad_norm": 1.7324296236038208,
+      "learning_rate": 1.56348351646022e-06,
+      "loss": 0.0068,
+      "num_input_tokens_seen": 776176,
+      "step": 122
+    },
+    {
+      "epoch": 3.1639871382636655,
+      "grad_norm": 2.4004085063934326,
+      "learning_rate": 1.5231721787768162e-06,
+      "loss": 0.0022,
+      "num_input_tokens_seen": 782464,
+      "step": 123
+    },
+    {
+      "epoch": 3.189710610932476,
+      "grad_norm": 3.6328651905059814,
+      "learning_rate": 1.4831583923105e-06,
+      "loss": 0.0162,
+      "num_input_tokens_seen": 789072,
+      "step": 124
+    },
+    {
+      "epoch": 3.215434083601286,
+      "grad_norm": 0.8305163979530334,
+      "learning_rate": 1.443454345648252e-06,
+      "loss": 0.0014,
+      "num_input_tokens_seen": 795536,
+      "step": 125
+    },
+    {
+      "epoch": 3.2411575562700965,
+      "grad_norm": 6.007119178771973,
+      "learning_rate": 1.4040721330273063e-06,
+      "loss": 0.0063,
+      "num_input_tokens_seen": 801888,
+      "step": 126
+    },
+    {
+      "epoch": 3.266881028938907,
+      "grad_norm": 1.4245920181274414,
+      "learning_rate": 1.3650237506511333e-06,
+      "loss": 0.0282,
+      "num_input_tokens_seen": 808432,
+      "step": 127
+    },
+    {
+      "epoch": 3.292604501607717,
+      "grad_norm": 0.36083319783210754,
+      "learning_rate": 1.3263210930352737e-06,
+      "loss": 0.0003,
+      "num_input_tokens_seen": 814896,
+      "step": 128
+    },
+    {
+      "epoch": 3.3183279742765275,
+      "grad_norm": 0.05347484350204468,
+      "learning_rate": 1.2879759493841577e-06,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 821200,
+      "step": 129
+    },
+    {
+      "epoch": 3.3440514469453375,
+      "grad_norm": 0.16537031531333923,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 827584,
+      "step": 130
+    },
+    {
+      "epoch": 3.369774919614148,
+      "grad_norm": 1.4132962226867676,
+      "learning_rate": 1.2124048127248644e-06,
+      "loss": 0.0169,
+      "num_input_tokens_seen": 834048,
+      "step": 131
+    },
+    {
+      "epoch": 3.395498392282958,
+      "grad_norm": 11.695096969604492,
+      "learning_rate": 1.1752018394169882e-06,
+      "loss": 0.0127,
+      "num_input_tokens_seen": 840240,
+      "step": 132
+    },
+    {
+      "epoch": 3.4212218649517685,
+      "grad_norm": 2.03340482711792,
+      "learning_rate": 1.1384024124624324e-06,
+      "loss": 0.0045,
+      "num_input_tokens_seen": 846448,
+      "step": 133
+    },
+    {
+      "epoch": 3.446945337620579,
+      "grad_norm": 15.712054252624512,
+      "learning_rate": 1.1020177413231334e-06,
+      "loss": 0.0924,
+      "num_input_tokens_seen": 852928,
+      "step": 134
+    },
+    {
+      "epoch": 3.472668810289389,
+      "grad_norm": 3.9320309162139893,
+      "learning_rate": 1.0660589091223854e-06,
+      "loss": 0.0067,
+      "num_input_tokens_seen": 859312,
+      "step": 135
+    },
+    {
+      "epoch": 3.4983922829581995,
+      "grad_norm": 1.599960207939148,
+      "learning_rate": 1.0305368692688175e-06,
+      "loss": 0.003,
+      "num_input_tokens_seen": 865440,
+      "step": 136
+    },
+    {
+      "epoch": 3.5241157556270095,
+      "grad_norm": 8.650961875915527,
+      "learning_rate": 9.95462442119879e-07,
+      "loss": 0.0164,
+      "num_input_tokens_seen": 871968,
+      "step": 137
+    },
+    {
+      "epoch": 3.54983922829582,
+      "grad_norm": 2.1372265815734863,
+      "learning_rate": 9.608463116858544e-07,
+      "loss": 0.0018,
+      "num_input_tokens_seen": 878352,
+      "step": 138
+    },
+    {
+      "epoch": 3.57556270096463,
+      "grad_norm": 1.8475613594055176,
+      "learning_rate": 9.266990223754069e-07,
+      "loss": 0.0226,
+      "num_input_tokens_seen": 884736,
+      "step": 139
+    },
+    {
+      "epoch": 3.6012861736334405,
+      "grad_norm": 0.2472313642501831,
+      "learning_rate": 8.930309757836517e-07,
+      "loss": 0.0008,
+      "num_input_tokens_seen": 891008,
+      "step": 140
+    },
+    {
+      "epoch": 3.627009646302251,
+      "grad_norm": 0.13111230731010437,
+      "learning_rate": 8.598524275237321e-07,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 897120,
+      "step": 141
+    },
+    {
+      "epoch": 3.652733118971061,
+      "grad_norm": 0.23976323008537292,
+      "learning_rate": 8.271734841028553e-07,
+      "loss": 0.0008,
+      "num_input_tokens_seen": 903536,
+      "step": 142
+    },
+    {
+      "epoch": 3.6784565916398715,
+      "grad_norm": 4.404489517211914,
+      "learning_rate": 7.950040998437541e-07,
+      "loss": 0.0256,
+      "num_input_tokens_seen": 909824,
+      "step": 143
+    },
+    {
+      "epoch": 3.7041800643086815,
+      "grad_norm": 0.16712801158428192,
+      "learning_rate": 7.633540738525066e-07,
+      "loss": 0.0005,
+      "num_input_tokens_seen": 916112,
+      "step": 144
+    },
+    {
+      "epoch": 3.729903536977492,
+      "grad_norm": 0.4478089213371277,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.0045,
+      "num_input_tokens_seen": 922592,
+      "step": 145
+    },
+    {
+      "epoch": 3.755627009646302,
+      "grad_norm": 0.14608968794345856,
+      "learning_rate": 7.016504991533727e-07,
+      "loss": 0.0005,
+      "num_input_tokens_seen": 928640,
+      "step": 146
+    },
+    {
+      "epoch": 3.7813504823151125,
+      "grad_norm": 1.1640571355819702,
+      "learning_rate": 6.716157459520739e-07,
+      "loss": 0.0069,
+      "num_input_tokens_seen": 935488,
+      "step": 147
+    },
+    {
+      "epoch": 3.807073954983923,
+      "grad_norm": 5.529272079467773,
+      "learning_rate": 6.421379363065142e-07,
+      "loss": 0.015,
+      "num_input_tokens_seen": 941952,
+      "step": 148
+    },
+    {
+      "epoch": 3.832797427652733,
+      "grad_norm": 2.3761372566223145,
+      "learning_rate": 6.1322604944307e-07,
+      "loss": 0.0012,
+      "num_input_tokens_seen": 948368,
+      "step": 149
+    },
+    {
+      "epoch": 3.8585209003215435,
+      "grad_norm": 2.560185670852661,
+      "learning_rate": 5.848888922025553e-07,
+      "loss": 0.0095,
+      "num_input_tokens_seen": 954752,
+      "step": 150
+    },
+    {
+      "epoch": 3.884244372990354,
+      "grad_norm": 1.6769373416900635,
+      "learning_rate": 5.571350963575728e-07,
+      "loss": 0.0271,
+      "num_input_tokens_seen": 961248,
+      "step": 151
+    },
+    {
+      "epoch": 3.909967845659164,
+      "grad_norm": 1.4693336486816406,
+      "learning_rate": 5.299731159831953e-07,
+      "loss": 0.0201,
+      "num_input_tokens_seen": 967424,
+      "step": 152
+    },
+    {
+      "epoch": 3.935691318327974,
+      "grad_norm": 1.2330920696258545,
+      "learning_rate": 5.034112248817685e-07,
+      "loss": 0.012,
+      "num_input_tokens_seen": 973696,
+      "step": 153
+    },
+    {
+      "epoch": 3.9614147909967845,
+      "grad_norm": 8.100526809692383,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.023,
+      "num_input_tokens_seen": 980144,
+      "step": 154
+    },
+    {
+      "epoch": 3.987138263665595,
+      "grad_norm": 1.439001202583313,
+      "learning_rate": 4.5211988927752026e-07,
+      "loss": 0.0156,
+      "num_input_tokens_seen": 986352,
+      "step": 155
+    },
+    {
+      "epoch": 4.012861736334405,
+      "grad_norm": 0.2862737476825714,
+      "learning_rate": 4.27406068612396e-07,
+      "loss": 0.0009,
+      "num_input_tokens_seen": 992880,
+      "step": 156
+    },
+    {
+      "epoch": 4.038585209003215,
+      "grad_norm": 0.575637936592102,
+      "learning_rate": 4.033235801364402e-07,
+      "loss": 0.0017,
+      "num_input_tokens_seen": 999200,
+      "step": 157
+    },
+    {
+      "epoch": 4.064308681672026,
+      "grad_norm": 0.47944220900535583,
+      "learning_rate": 3.798797596089351e-07,
+      "loss": 0.0015,
+      "num_input_tokens_seen": 1005568,
+      "step": 158
+    },
+    {
+      "epoch": 4.090032154340836,
+      "grad_norm": 0.6407404541969299,
+      "learning_rate": 3.5708174824471947e-07,
+      "loss": 0.0035,
+      "num_input_tokens_seen": 1011728,
+      "step": 159
+    },
+    {
+      "epoch": 4.115755627009646,
+      "grad_norm": 0.29835206270217896,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 0.0016,
+      "num_input_tokens_seen": 1018272,
+      "step": 160
+    },
+    {
+      "epoch": 4.141479099678457,
+      "grad_norm": 0.8626136183738708,
+      "learning_rate": 3.134507321515107e-07,
+      "loss": 0.0028,
+      "num_input_tokens_seen": 1024688,
+      "step": 161
+    },
+    {
+      "epoch": 4.167202572347267,
+      "grad_norm": 0.19084709882736206,
+      "learning_rate": 2.9263101785268253e-07,
+      "loss": 0.0006,
+      "num_input_tokens_seen": 1031152,
+      "step": 162
+    },
+    {
+      "epoch": 4.192926045016077,
+      "grad_norm": 0.34228870272636414,
+      "learning_rate": 2.7248368952908055e-07,
+      "loss": 0.0013,
+      "num_input_tokens_seen": 1037632,
+      "step": 163
+    },
+    {
+      "epoch": 4.218649517684887,
+      "grad_norm": 0.19209067523479462,
+      "learning_rate": 2.53014884252083e-07,
+      "loss": 0.0006,
+      "num_input_tokens_seen": 1043936,
+      "step": 164
+    },
+    {
+      "epoch": 4.244372990353698,
+      "grad_norm": 0.5416057705879211,
+      "learning_rate": 2.3423053240837518e-07,
+      "loss": 0.0017,
+      "num_input_tokens_seen": 1050048,
+      "step": 165
+    },
+    {
+      "epoch": 4.270096463022508,
+      "grad_norm": 0.12837135791778564,
+      "learning_rate": 2.1613635589349756e-07,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 1056496,
+      "step": 166
+    },
+    {
+      "epoch": 4.295819935691318,
+      "grad_norm": 3.4782867431640625,
+      "learning_rate": 1.9873786636889908e-07,
+      "loss": 0.0049,
+      "num_input_tokens_seen": 1062848,
+      "step": 167
+    },
+    {
+      "epoch": 4.321543408360129,
+      "grad_norm": 4.008510112762451,
+      "learning_rate": 1.8204036358303173e-07,
+      "loss": 0.0071,
+      "num_input_tokens_seen": 1069136,
+      "step": 168
+    },
+    {
+      "epoch": 4.347266881028939,
+      "grad_norm": 0.38916894793510437,
+      "learning_rate": 1.6604893375699594e-07,
+      "loss": 0.0011,
+      "num_input_tokens_seen": 1075328,
+      "step": 169
+    },
+    {
+      "epoch": 4.372990353697749,
+      "grad_norm": 0.11064338684082031,
+      "learning_rate": 1.507684480352292e-07,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 1081696,
+      "step": 170
+    },
+    {
+      "epoch": 4.39871382636656,
+      "grad_norm": 0.20267654955387115,
+      "learning_rate": 1.362035610017079e-07,
+      "loss": 0.0007,
+      "num_input_tokens_seen": 1088112,
+      "step": 171
+    },
+    {
+      "epoch": 4.42443729903537,
+      "grad_norm": 0.35677772760391235,
+      "learning_rate": 1.223587092621162e-07,
+      "loss": 0.0017,
+      "num_input_tokens_seen": 1094512,
+      "step": 172
+    },
+    {
+      "epoch": 4.45016077170418,
+      "grad_norm": 0.3713955581188202,
+      "learning_rate": 1.0923811009241142e-07,
+      "loss": 0.0007,
+      "num_input_tokens_seen": 1101040,
+      "step": 173
+    },
+    {
+      "epoch": 4.47588424437299,
+      "grad_norm": 0.1514904946088791,
+      "learning_rate": 9.684576015420277e-08,
+      "loss": 0.0003,
+      "num_input_tokens_seen": 1107168,
+      "step": 174
+    },
+    {
+      "epoch": 4.501607717041801,
+      "grad_norm": 4.804702281951904,
+      "learning_rate": 8.518543427732951e-08,
+      "loss": 0.0046,
+      "num_input_tokens_seen": 1113408,
+      "step": 175
+    },
+    {
+      "epoch": 4.527331189710611,
+      "grad_norm": 0.9991558194160461,
+      "learning_rate": 7.426068431000883e-08,
+      "loss": 0.0038,
+      "num_input_tokens_seen": 1119568,
+      "step": 176
+    },
+    {
+      "epoch": 4.553054662379421,
+      "grad_norm": 2.726783037185669,
+      "learning_rate": 6.407483803691216e-08,
+      "loss": 0.0036,
+      "num_input_tokens_seen": 1126048,
+      "step": 177
+    },
+    {
+      "epoch": 4.578778135048232,
+      "grad_norm": 1.2259963750839233,
+      "learning_rate": 5.463099816548578e-08,
+      "loss": 0.0056,
+      "num_input_tokens_seen": 1132400,
+      "step": 178
+    },
+    {
+      "epoch": 4.604501607717042,
+      "grad_norm": 3.010671615600586,
+      "learning_rate": 4.593204138084006e-08,
+      "loss": 0.0057,
+      "num_input_tokens_seen": 1138832,
+      "step": 179
+    },
+    {
+      "epoch": 4.630225080385852,
+      "grad_norm": 0.9592411518096924,
+      "learning_rate": 3.798061746947995e-08,
+      "loss": 0.002,
+      "num_input_tokens_seen": 1145344,
+      "step": 180
+    },
+    {
+      "epoch": 4.655948553054662,
+      "grad_norm": 0.09295938909053802,
+      "learning_rate": 3.077914851215585e-08,
+      "loss": 0.0003,
+      "num_input_tokens_seen": 1151536,
+      "step": 181
+    },
+    {
+      "epoch": 4.681672025723473,
+      "grad_norm": 0.06213412061333656,
+      "learning_rate": 2.4329828146074096e-08,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 1157696,
+      "step": 182
+    },
+    {
+      "epoch": 4.707395498392283,
+      "grad_norm": 1.2592134475708008,
+      "learning_rate": 1.8634620896695044e-08,
+      "loss": 0.0043,
+      "num_input_tokens_seen": 1163712,
+      "step": 183
+    },
+    {
+      "epoch": 4.733118971061093,
+      "grad_norm": 0.05733427032828331,
+      "learning_rate": 1.3695261579316776e-08,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 1169888,
+      "step": 184
+    },
+    {
+      "epoch": 4.758842443729904,
+      "grad_norm": 0.38288363814353943,
+      "learning_rate": 9.513254770636138e-09,
+      "loss": 0.0013,
+      "num_input_tokens_seen": 1176272,
+      "step": 185
+    },
+    {
+      "epoch": 4.784565916398714,
+      "grad_norm": 0.6540606617927551,
+      "learning_rate": 6.089874350439507e-09,
+      "loss": 0.0023,
+      "num_input_tokens_seen": 1182688,
+      "step": 186
+    },
+    {
+      "epoch": 4.810289389067524,
+      "grad_norm": 0.0432482548058033,
+      "learning_rate": 3.4261631135654174e-09,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 1189360,
+      "step": 187
+    },
+    {
+      "epoch": 4.836012861736334,
+      "grad_norm": 0.8218325972557068,
+      "learning_rate": 1.5229324522605949e-09,
+      "loss": 0.0015,
+      "num_input_tokens_seen": 1195632,
+      "step": 188
+    },
+    {
+      "epoch": 4.861736334405145,
+      "grad_norm": 0.05609305202960968,
+      "learning_rate": 3.8076210902182607e-10,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 1202016,
+      "step": 189
+    },
+    {
+      "epoch": 4.887459807073955,
+      "grad_norm": 3.791782855987549,
+      "learning_rate": 0.0,
+      "loss": 0.0028,
+      "num_input_tokens_seen": 1208400,
+      "step": 190
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 190,
+  "num_input_tokens_seen": 1208400,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.441370708980531e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-190/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd080bf34222db640e5df447c0955c50426b3473fa57de2bcaf77a92b9002bf4
+size 6584

checkpoint-190/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/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 . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+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)
+
+        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 files:
+        state_dict = torch.load(f, map_location=device)
+        # 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}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) 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")
+
+
+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 = fp32_flat_groups[0].numel() * 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
+    for name, shape in param_shapes.items():
+
+        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}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        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 get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=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
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    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.
+
+    """
+    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")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, 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_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``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
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+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_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    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_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.42.3"
+}

llamaboard_config.yaml

@@ -0,0 +1,65 @@
+top.booster: auto
+top.checkpoint_path: null
+top.finetuning_type: full
+top.model_name: LLaMA3-8B-Chat
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: llama3
+top.visual_inputs: false
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 1024
+train.dataset:
+- truth_train_0716
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: '2'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-6
+train.logging_steps: 1
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '5.0'
+train.optim: adamw_torch
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 1000
+train.shift_attn: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 10

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edf4ea2e752ee2cdaa5306c36a9df4993e550809e7119b58ad6e822f11dcb3e
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f90ed6cc342f4ce5b217e38fe9b6ba34ae47d6accae3ef146aaeefc3a1fd33e
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5478badd4e2d1ea445b7e37587fa74a3eee1f8fa1fb11ce8ea9cf76f941e90
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9663dceae3a8fdf1f2589357abc81d4d26cdea0ae337d106c64c2e4d08c67db3
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

running_log.txt

@@ -0,0 +1,667 @@
+07/16/2024 09:47:54 - INFO - llamafactory.hparams.parser - Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|parser.py:325] 2024-07-16 09:47:54,375 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+07/16/2024 09:47:54 - INFO - llamafactory.hparams.parser - Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+07/16/2024 09:47:54 - INFO - llamafactory.hparams.parser - Process rank: 2, device: cuda:2, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+07/16/2024 09:47:54 - INFO - llamafactory.hparams.parser - Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+07/16/2024 09:47:54 - INFO - llamafactory.hparams.parser - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+07/16/2024 09:47:54 - INFO - llamafactory.hparams.parser - Process rank: 6, device: cuda:6, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+07/16/2024 09:47:54 - INFO - llamafactory.hparams.parser - Process rank: 7, device: cuda:7, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16
+
+[INFO|tokenization_utils_base.py:2161] 2024-07-16 09:47:54,671 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/tokenizer.json
+
+[INFO|tokenization_utils_base.py:2161] 2024-07-16 09:47:54,671 >> loading file added_tokens.json from cache at None
+
+[INFO|tokenization_utils_base.py:2161] 2024-07-16 09:47:54,671 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/special_tokens_map.json
+
+[INFO|tokenization_utils_base.py:2161] 2024-07-16 09:47:54,672 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/tokenizer_config.json
+
+[WARNING|logging.py:313] 2024-07-16 09:47:54,959 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|template.py:270] 2024-07-16 09:47:54,960 >> Replace eos token: <|eot_id|>
+
+[INFO|template.py:372] 2024-07-16 09:47:54,960 >> Add pad token: <|eot_id|>
+
+[INFO|loader.py:50] 2024-07-16 09:47:54,960 >> Loading dataset 0716_truthfulqa_benchmark_train.json...
+
+07/16/2024 09:47:54 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
+
+07/16/2024 09:47:54 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
+
+07/16/2024 09:47:54 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
+
+07/16/2024 09:47:54 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
+
+07/16/2024 09:47:54 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
+
+07/16/2024 09:47:54 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
+
+07/16/2024 09:47:54 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
+
+07/16/2024 09:47:55 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+07/16/2024 09:47:55 - INFO - llamafactory.data.template - Replace eos token: <|eot_id|>
+
+07/16/2024 09:47:55 - INFO - llamafactory.data.template - Add pad token: <|eot_id|>
+
+07/16/2024 09:47:56 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
+
+07/16/2024 09:47:56 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
+
+07/16/2024 09:47:56 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
+
+07/16/2024 09:47:56 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
+
+07/16/2024 09:47:56 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
+
+07/16/2024 09:47:56 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
+
+07/16/2024 09:47:56 - INFO - llamafactory.data.loader - Loading dataset 0716_truthfulqa_benchmark_train.json...
+
+[INFO|configuration_utils.py:733] 2024-07-16 09:48:00,277 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/config.json
+
+[INFO|configuration_utils.py:800] 2024-07-16 09:48:00,280 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|modeling_utils.py:3556] 2024-07-16 09:48:00,330 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/model.safetensors.index.json
+
+[INFO|modeling_utils.py:1531] 2024-07-16 09:48:00,332 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|configuration_utils.py:1000] 2024-07-16 09:48:00,334 >> Generate config GenerationConfig {
+  "bos_token_id": 128000,
+  "eos_token_id": 128009
+}
+
+
+[INFO|modeling_utils.py:4364] 2024-07-16 09:48:04,157 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
+
+
+[INFO|modeling_utils.py:4372] 2024-07-16 09:48:04,157 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Meta-Llama-3-8B-Instruct.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
+
+[INFO|configuration_utils.py:955] 2024-07-16 09:48:04,331 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa/generation_config.json
+
+[INFO|configuration_utils.py:1000] 2024-07-16 09:48:04,332 >> Generate config GenerationConfig {
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9
+}
+
+
+[INFO|checkpointing.py:103] 2024-07-16 09:48:04,339 >> Gradient checkpointing enabled.
+
+[INFO|attention.py:80] 2024-07-16 09:48:04,339 >> Using torch SDPA for faster training and inference.
+
+[INFO|adapter.py:302] 2024-07-16 09:48:04,339 >> Upcasting trainable params to float32.
+
+[INFO|adapter.py:48] 2024-07-16 09:48:04,339 >> Fine-tuning method: Full
+
+[INFO|loader.py:196] 2024-07-16 09:48:04,384 >> trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+07/16/2024 09:48:04 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+[INFO|trainer.py:642] 2024-07-16 09:48:04,390 >> Using auto half precision backend
+
+07/16/2024 09:48:05 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+07/16/2024 09:48:05 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+07/16/2024 09:48:05 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+07/16/2024 09:48:05 - INFO - llamafactory.model.adapter - Fine-tuning method: Full
+
+07/16/2024 09:48:05 - INFO - llamafactory.model.loader - trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000
+
+[INFO|trainer.py:2128] 2024-07-16 09:48:27,728 >> ***** Running training *****
+
+[INFO|trainer.py:2129] 2024-07-16 09:48:27,728 >>   Num examples = 4,968
+
+[INFO|trainer.py:2130] 2024-07-16 09:48:27,728 >>   Num Epochs = 5
+
+[INFO|trainer.py:2131] 2024-07-16 09:48:27,729 >>   Instantaneous batch size per device = 2
+
+[INFO|trainer.py:2134] 2024-07-16 09:48:27,729 >>   Total train batch size (w. parallel, distributed & accumulation) = 128
+
+[INFO|trainer.py:2135] 2024-07-16 09:48:27,729 >>   Gradient Accumulation steps = 8
+
+[INFO|trainer.py:2136] 2024-07-16 09:48:27,729 >>   Total optimization steps = 190
+
+[INFO|trainer.py:2137] 2024-07-16 09:48:27,730 >>   Number of trainable parameters = 8,030,261,248
+
+[INFO|callbacks.py:310] 2024-07-16 09:48:41,429 >> {'loss': 14.1364, 'learning_rate': 5.0000e-07, 'epoch': 0.03, 'throughput': 475.41}
+
+[INFO|callbacks.py:310] 2024-07-16 09:48:54,626 >> {'loss': 13.7804, 'learning_rate': 1.0000e-06, 'epoch': 0.05, 'throughput': 477.72}
+
+[INFO|callbacks.py:310] 2024-07-16 09:49:07,808 >> {'loss': 13.4871, 'learning_rate': 1.5000e-06, 'epoch': 0.08, 'throughput': 480.28}
+
+[INFO|callbacks.py:310] 2024-07-16 09:49:20,995 >> {'loss': 12.7900, 'learning_rate': 2.0000e-06, 'epoch': 0.10, 'throughput': 475.82}
+
+[INFO|callbacks.py:310] 2024-07-16 09:49:34,157 >> {'loss': 9.2748, 'learning_rate': 2.5000e-06, 'epoch': 0.13, 'throughput': 481.26}
+
+[INFO|callbacks.py:310] 2024-07-16 09:49:47,321 >> {'loss': 6.5585, 'learning_rate': 3.0000e-06, 'epoch': 0.15, 'throughput': 479.46}
+
+[INFO|callbacks.py:310] 2024-07-16 09:50:00,485 >> {'loss': 5.3984, 'learning_rate': 3.5000e-06, 'epoch': 0.18, 'throughput': 475.92}
+
+[INFO|callbacks.py:310] 2024-07-16 09:50:13,669 >> {'loss': 1.9363, 'learning_rate': 4.0000e-06, 'epoch': 0.21, 'throughput': 476.05}
+
+[INFO|callbacks.py:310] 2024-07-16 09:50:26,844 >> {'loss': 0.6783, 'learning_rate': 4.5000e-06, 'epoch': 0.23, 'throughput': 477.93}
+
+[INFO|callbacks.py:310] 2024-07-16 09:50:40,003 >> {'loss': 2.9945, 'learning_rate': 5.0000e-06, 'epoch': 0.26, 'throughput': 478.89}
+
+[INFO|callbacks.py:310] 2024-07-16 09:50:53,164 >> {'loss': 0.2916, 'learning_rate': 4.9996e-06, 'epoch': 0.28, 'throughput': 478.35}
+
+[INFO|callbacks.py:310] 2024-07-16 09:51:06,343 >> {'loss': 2.2775, 'learning_rate': 4.9985e-06, 'epoch': 0.31, 'throughput': 478.05}
+
+[INFO|callbacks.py:310] 2024-07-16 09:51:19,511 >> {'loss': 0.3757, 'learning_rate': 4.9966e-06, 'epoch': 0.33, 'throughput': 478.29}
+
+[INFO|callbacks.py:310] 2024-07-16 09:51:32,674 >> {'loss': 1.9543, 'learning_rate': 4.9939e-06, 'epoch': 0.36, 'throughput': 479.20}
+
+[INFO|callbacks.py:310] 2024-07-16 09:51:45,855 >> {'loss': 0.7398, 'learning_rate': 4.9905e-06, 'epoch': 0.39, 'throughput': 478.49}
+
+[INFO|callbacks.py:310] 2024-07-16 09:51:59,041 >> {'loss': 1.1868, 'learning_rate': 4.9863e-06, 'epoch': 0.41, 'throughput': 479.67}
+
+[INFO|callbacks.py:310] 2024-07-16 09:52:12,210 >> {'loss': 0.5418, 'learning_rate': 4.9814e-06, 'epoch': 0.44, 'throughput': 478.83}
+
+[INFO|callbacks.py:310] 2024-07-16 09:52:25,377 >> {'loss': 0.2263, 'learning_rate': 4.9757e-06, 'epoch': 0.46, 'throughput': 479.37}
+
+[INFO|callbacks.py:310] 2024-07-16 09:52:38,537 >> {'loss': 0.1612, 'learning_rate': 4.9692e-06, 'epoch': 0.49, 'throughput': 479.86}
+
+[INFO|callbacks.py:310] 2024-07-16 09:52:51,713 >> {'loss': 0.3299, 'learning_rate': 4.9620e-06, 'epoch': 0.51, 'throughput': 480.64}
+
+[INFO|callbacks.py:310] 2024-07-16 09:53:04,885 >> {'loss': 0.2013, 'learning_rate': 4.9541e-06, 'epoch': 0.54, 'throughput': 481.12}
+
+[INFO|callbacks.py:310] 2024-07-16 09:53:18,042 >> {'loss': 0.2446, 'learning_rate': 4.9454e-06, 'epoch': 0.57, 'throughput': 481.36}
+
+[INFO|callbacks.py:310] 2024-07-16 09:53:31,215 >> {'loss': 0.2235, 'learning_rate': 4.9359e-06, 'epoch': 0.59, 'throughput': 481.55}
+
+[INFO|callbacks.py:310] 2024-07-16 09:53:44,385 >> {'loss': 0.1160, 'learning_rate': 4.9257e-06, 'epoch': 0.62, 'throughput': 480.78}
+
+[INFO|callbacks.py:310] 2024-07-16 09:53:57,544 >> {'loss': 0.2179, 'learning_rate': 4.9148e-06, 'epoch': 0.64, 'throughput': 480.61}
+
+[INFO|callbacks.py:310] 2024-07-16 09:54:10,712 >> {'loss': 0.1414, 'learning_rate': 4.9032e-06, 'epoch': 0.67, 'throughput': 480.45}
+
+[INFO|callbacks.py:310] 2024-07-16 09:54:23,865 >> {'loss': 0.1181, 'learning_rate': 4.8908e-06, 'epoch': 0.69, 'throughput': 481.03}
+
+[INFO|callbacks.py:310] 2024-07-16 09:54:37,030 >> {'loss': 0.2753, 'learning_rate': 4.8776e-06, 'epoch': 0.72, 'throughput': 481.61}
+
+[INFO|callbacks.py:310] 2024-07-16 09:54:50,171 >> {'loss': 0.3255, 'learning_rate': 4.8638e-06, 'epoch': 0.75, 'throughput': 482.08}
+
+[INFO|callbacks.py:310] 2024-07-16 09:55:03,354 >> {'loss': 0.2352, 'learning_rate': 4.8492e-06, 'epoch': 0.77, 'throughput': 482.60}
+
+[INFO|callbacks.py:310] 2024-07-16 09:55:16,515 >> {'loss': 0.0630, 'learning_rate': 4.8340e-06, 'epoch': 0.80, 'throughput': 482.48}
+
+[INFO|callbacks.py:310] 2024-07-16 09:55:29,668 >> {'loss': 0.2042, 'learning_rate': 4.8180e-06, 'epoch': 0.82, 'throughput': 482.50}
+
+[INFO|callbacks.py:310] 2024-07-16 09:55:42,841 >> {'loss': 0.1364, 'learning_rate': 4.8013e-06, 'epoch': 0.85, 'throughput': 482.93}
+
+[INFO|callbacks.py:310] 2024-07-16 09:55:56,012 >> {'loss': 0.0934, 'learning_rate': 4.7839e-06, 'epoch': 0.87, 'throughput': 482.98}
+
+[INFO|callbacks.py:310] 2024-07-16 09:56:09,170 >> {'loss': 0.1332, 'learning_rate': 4.7658e-06, 'epoch': 0.90, 'throughput': 483.11}
+
+[INFO|callbacks.py:310] 2024-07-16 09:56:22,332 >> {'loss': 0.1595, 'learning_rate': 4.7470e-06, 'epoch': 0.93, 'throughput': 483.00}
+
+[INFO|callbacks.py:310] 2024-07-16 09:56:35,503 >> {'loss': 0.1528, 'learning_rate': 4.7275e-06, 'epoch': 0.95, 'throughput': 483.18}
+
+[INFO|callbacks.py:310] 2024-07-16 09:56:48,669 >> {'loss': 0.1342, 'learning_rate': 4.7074e-06, 'epoch': 0.98, 'throughput': 483.48}
+
+[INFO|callbacks.py:310] 2024-07-16 09:57:01,819 >> {'loss': 0.1586, 'learning_rate': 4.6865e-06, 'epoch': 1.00, 'throughput': 483.71}
+
+[INFO|callbacks.py:310] 2024-07-16 09:57:14,986 >> {'loss': 0.1072, 'learning_rate': 4.6651e-06, 'epoch': 1.03, 'throughput': 483.77}
+
+[INFO|callbacks.py:310] 2024-07-16 09:57:28,147 >> {'loss': 0.0357, 'learning_rate': 4.6429e-06, 'epoch': 1.05, 'throughput': 484.04}
+
+[INFO|callbacks.py:310] 2024-07-16 09:57:41,316 >> {'loss': 0.0600, 'learning_rate': 4.6201e-06, 'epoch': 1.08, 'throughput': 484.18}
+
+[INFO|callbacks.py:310] 2024-07-16 09:57:54,470 >> {'loss': 0.0902, 'learning_rate': 4.5967e-06, 'epoch': 1.11, 'throughput': 484.46}
+
+[INFO|callbacks.py:310] 2024-07-16 09:58:07,621 >> {'loss': 0.0202, 'learning_rate': 4.5726e-06, 'epoch': 1.13, 'throughput': 484.51}
+
+[INFO|callbacks.py:310] 2024-07-16 09:58:20,803 >> {'loss': 0.0380, 'learning_rate': 4.5479e-06, 'epoch': 1.16, 'throughput': 484.10}
+
+[INFO|callbacks.py:310] 2024-07-16 09:58:33,969 >> {'loss': 0.0379, 'learning_rate': 4.5225e-06, 'epoch': 1.18, 'throughput': 484.17}
+
+[INFO|callbacks.py:310] 2024-07-16 09:58:47,129 >> {'loss': 0.0742, 'learning_rate': 4.4966e-06, 'epoch': 1.21, 'throughput': 484.24}
+
+[INFO|callbacks.py:310] 2024-07-16 09:59:00,303 >> {'loss': 0.0658, 'learning_rate': 4.4700e-06, 'epoch': 1.23, 'throughput': 483.64}
+
+[INFO|callbacks.py:310] 2024-07-16 09:59:13,461 >> {'loss': 0.0336, 'learning_rate': 4.4429e-06, 'epoch': 1.26, 'throughput': 483.99}
+
+[INFO|callbacks.py:310] 2024-07-16 09:59:26,622 >> {'loss': 0.1021, 'learning_rate': 4.4151e-06, 'epoch': 1.29, 'throughput': 483.77}
+
+[INFO|callbacks.py:310] 2024-07-16 09:59:39,766 >> {'loss': 0.1312, 'learning_rate': 4.3868e-06, 'epoch': 1.31, 'throughput': 483.74}
+
+[INFO|callbacks.py:310] 2024-07-16 09:59:52,949 >> {'loss': 0.0665, 'learning_rate': 4.3579e-06, 'epoch': 1.34, 'throughput': 483.68}
+
+[INFO|callbacks.py:310] 2024-07-16 10:00:06,104 >> {'loss': 0.0679, 'learning_rate': 4.3284e-06, 'epoch': 1.36, 'throughput': 483.66}
+
+[INFO|callbacks.py:310] 2024-07-16 10:00:19,266 >> {'loss': 0.0579, 'learning_rate': 4.2983e-06, 'epoch': 1.39, 'throughput': 483.46}
+
+[INFO|callbacks.py:310] 2024-07-16 10:00:32,433 >> {'loss': 0.0542, 'learning_rate': 4.2678e-06, 'epoch': 1.41, 'throughput': 483.69}
+
+[INFO|callbacks.py:310] 2024-07-16 10:00:45,598 >> {'loss': 0.0476, 'learning_rate': 4.2366e-06, 'epoch': 1.44, 'throughput': 483.69}
+
+[INFO|callbacks.py:310] 2024-07-16 10:00:58,749 >> {'loss': 0.0613, 'learning_rate': 4.2050e-06, 'epoch': 1.47, 'throughput': 483.84}
+
+[INFO|callbacks.py:310] 2024-07-16 10:01:11,904 >> {'loss': 0.0995, 'learning_rate': 4.1728e-06, 'epoch': 1.49, 'throughput': 483.76}
+
+[INFO|callbacks.py:310] 2024-07-16 10:01:25,086 >> {'loss': 0.0532, 'learning_rate': 4.1401e-06, 'epoch': 1.52, 'throughput': 483.57}
+
+[INFO|callbacks.py:310] 2024-07-16 10:01:38,265 >> {'loss': 0.0824, 'learning_rate': 4.1070e-06, 'epoch': 1.54, 'throughput': 483.60}
+
+[INFO|callbacks.py:310] 2024-07-16 10:01:51,421 >> {'loss': 0.0499, 'learning_rate': 4.0733e-06, 'epoch': 1.57, 'throughput': 483.63}
+
+[INFO|callbacks.py:310] 2024-07-16 10:02:04,575 >> {'loss': 0.0413, 'learning_rate': 4.0392e-06, 'epoch': 1.59, 'throughput': 483.75}
+
+[INFO|callbacks.py:310] 2024-07-16 10:02:17,738 >> {'loss': 0.0637, 'learning_rate': 4.0045e-06, 'epoch': 1.62, 'throughput': 484.01}
+
+[INFO|callbacks.py:310] 2024-07-16 10:02:30,912 >> {'loss': 0.0529, 'learning_rate': 3.9695e-06, 'epoch': 1.65, 'throughput': 483.77}
+
+[INFO|callbacks.py:310] 2024-07-16 10:02:44,068 >> {'loss': 0.0474, 'learning_rate': 3.9339e-06, 'epoch': 1.67, 'throughput': 483.73}
+
+[INFO|callbacks.py:310] 2024-07-16 10:02:57,237 >> {'loss': 0.0649, 'learning_rate': 3.8980e-06, 'epoch': 1.70, 'throughput': 483.55}
+
+[INFO|callbacks.py:310] 2024-07-16 10:03:10,409 >> {'loss': 0.0505, 'learning_rate': 3.8616e-06, 'epoch': 1.72, 'throughput': 483.51}
+
+[INFO|callbacks.py:310] 2024-07-16 10:03:23,580 >> {'loss': 0.0621, 'learning_rate': 3.8248e-06, 'epoch': 1.75, 'throughput': 483.14}
+
+[INFO|callbacks.py:310] 2024-07-16 10:03:36,735 >> {'loss': 0.0769, 'learning_rate': 3.7876e-06, 'epoch': 1.77, 'throughput': 483.20}
+
+[INFO|callbacks.py:310] 2024-07-16 10:03:49,897 >> {'loss': 0.0435, 'learning_rate': 3.7500e-06, 'epoch': 1.80, 'throughput': 483.42}
+
+[INFO|callbacks.py:310] 2024-07-16 10:04:03,040 >> {'loss': 0.0673, 'learning_rate': 3.7120e-06, 'epoch': 1.83, 'throughput': 483.69}
+
+[INFO|callbacks.py:310] 2024-07-16 10:04:16,202 >> {'loss': 0.1316, 'learning_rate': 3.6737e-06, 'epoch': 1.85, 'throughput': 483.44}
+
+[INFO|callbacks.py:310] 2024-07-16 10:04:29,356 >> {'loss': 0.0531, 'learning_rate': 3.6350e-06, 'epoch': 1.88, 'throughput': 483.53}
+
+[INFO|callbacks.py:310] 2024-07-16 10:04:42,540 >> {'loss': 0.0287, 'learning_rate': 3.5959e-06, 'epoch': 1.90, 'throughput': 483.62}
+
+[INFO|callbacks.py:310] 2024-07-16 10:04:55,704 >> {'loss': 0.0648, 'learning_rate': 3.5565e-06, 'epoch': 1.93, 'throughput': 483.59}
+
+[INFO|callbacks.py:310] 2024-07-16 10:05:08,874 >> {'loss': 0.1211, 'learning_rate': 3.5168e-06, 'epoch': 1.95, 'throughput': 483.54}
+
+[INFO|callbacks.py:310] 2024-07-16 10:05:22,046 >> {'loss': 0.0879, 'learning_rate': 3.4768e-06, 'epoch': 1.98, 'throughput': 483.26}
+
+[INFO|callbacks.py:310] 2024-07-16 10:05:35,205 >> {'loss': 0.0227, 'learning_rate': 3.4365e-06, 'epoch': 2.01, 'throughput': 483.39}
+
+[INFO|callbacks.py:310] 2024-07-16 10:05:48,359 >> {'loss': 0.0228, 'learning_rate': 3.3959e-06, 'epoch': 2.03, 'throughput': 483.45}
+
+[INFO|callbacks.py:310] 2024-07-16 10:06:01,518 >> {'loss': 0.0360, 'learning_rate': 3.3551e-06, 'epoch': 2.06, 'throughput': 483.47}
+
+[INFO|callbacks.py:310] 2024-07-16 10:06:14,696 >> {'loss': 0.0138, 'learning_rate': 3.3139e-06, 'epoch': 2.08, 'throughput': 483.36}
+
+[INFO|callbacks.py:310] 2024-07-16 10:06:27,870 >> {'loss': 0.0697, 'learning_rate': 3.2725e-06, 'epoch': 2.11, 'throughput': 483.18}
+
+[INFO|callbacks.py:310] 2024-07-16 10:06:41,041 >> {'loss': 0.0508, 'learning_rate': 3.2309e-06, 'epoch': 2.14, 'throughput': 482.89}
+
+[INFO|callbacks.py:310] 2024-07-16 10:06:54,208 >> {'loss': 0.0088, 'learning_rate': 3.1891e-06, 'epoch': 2.16, 'throughput': 483.18}
+
+[INFO|callbacks.py:310] 2024-07-16 10:07:07,375 >> {'loss': 0.0158, 'learning_rate': 3.1470e-06, 'epoch': 2.19, 'throughput': 483.34}
+
+[INFO|callbacks.py:310] 2024-07-16 10:07:20,542 >> {'loss': 0.0060, 'learning_rate': 3.1048e-06, 'epoch': 2.21, 'throughput': 483.30}
+
+[INFO|callbacks.py:310] 2024-07-16 10:07:33,693 >> {'loss': 0.0380, 'learning_rate': 3.0624e-06, 'epoch': 2.24, 'throughput': 483.67}
+
+[INFO|callbacks.py:310] 2024-07-16 10:07:46,864 >> {'loss': 0.0004, 'learning_rate': 3.0198e-06, 'epoch': 2.26, 'throughput': 483.58}
+
+[INFO|callbacks.py:310] 2024-07-16 10:08:00,047 >> {'loss': 0.0111, 'learning_rate': 2.9770e-06, 'epoch': 2.29, 'throughput': 483.47}
+
+[INFO|callbacks.py:310] 2024-07-16 10:08:13,201 >> {'loss': 0.0008, 'learning_rate': 2.9341e-06, 'epoch': 2.32, 'throughput': 483.64}
+
+[INFO|callbacks.py:310] 2024-07-16 10:08:26,357 >> {'loss': 0.0182, 'learning_rate': 2.8911e-06, 'epoch': 2.34, 'throughput': 483.70}
+
+[INFO|callbacks.py:310] 2024-07-16 10:08:39,526 >> {'loss': 0.0491, 'learning_rate': 2.8479e-06, 'epoch': 2.37, 'throughput': 483.66}
+
+[INFO|callbacks.py:310] 2024-07-16 10:08:52,691 >> {'loss': 0.0040, 'learning_rate': 2.8047e-06, 'epoch': 2.39, 'throughput': 483.71}
+
+[INFO|callbacks.py:310] 2024-07-16 10:09:05,854 >> {'loss': 0.0176, 'learning_rate': 2.7613e-06, 'epoch': 2.42, 'throughput': 483.76}
+
+[INFO|callbacks.py:310] 2024-07-16 10:09:19,001 >> {'loss': 0.0190, 'learning_rate': 2.7179e-06, 'epoch': 2.44, 'throughput': 483.69}
+
+[INFO|callbacks.py:310] 2024-07-16 10:09:32,181 >> {'loss': 0.0270, 'learning_rate': 2.6744e-06, 'epoch': 2.47, 'throughput': 483.49}
+
+[INFO|callbacks.py:310] 2024-07-16 10:09:45,346 >> {'loss': 0.0354, 'learning_rate': 2.6308e-06, 'epoch': 2.50, 'throughput': 483.49}
+
+[INFO|callbacks.py:310] 2024-07-16 10:09:58,504 >> {'loss': 0.0741, 'learning_rate': 2.5872e-06, 'epoch': 2.52, 'throughput': 483.59}
+
+[INFO|callbacks.py:310] 2024-07-16 10:10:11,684 >> {'loss': 0.0582, 'learning_rate': 2.5436e-06, 'epoch': 2.55, 'throughput': 483.53}
+
+[INFO|callbacks.py:310] 2024-07-16 10:10:24,850 >> {'loss': 0.0096, 'learning_rate': 2.5000e-06, 'epoch': 2.57, 'throughput': 483.66}
+
+[INFO|callbacks.py:310] 2024-07-16 10:10:38,015 >> {'loss': 0.0263, 'learning_rate': 2.4564e-06, 'epoch': 2.60, 'throughput': 483.71}
+
+[INFO|callbacks.py:310] 2024-07-16 10:10:51,176 >> {'loss': 0.0121, 'learning_rate': 2.4128e-06, 'epoch': 2.62, 'throughput': 483.65}
+
+[INFO|callbacks.py:310] 2024-07-16 10:11:04,355 >> {'loss': 0.0204, 'learning_rate': 2.3692e-06, 'epoch': 2.65, 'throughput': 483.62}
+
+[INFO|callbacks.py:310] 2024-07-16 10:11:17,518 >> {'loss': 0.0325, 'learning_rate': 2.3256e-06, 'epoch': 2.68, 'throughput': 483.74}
+
+[INFO|callbacks.py:310] 2024-07-16 10:11:30,679 >> {'loss': 0.0076, 'learning_rate': 2.2821e-06, 'epoch': 2.70, 'throughput': 483.58}
+
+[INFO|callbacks.py:310] 2024-07-16 10:11:43,845 >> {'loss': 0.0485, 'learning_rate': 2.2387e-06, 'epoch': 2.73, 'throughput': 483.48}
+
+[INFO|callbacks.py:310] 2024-07-16 10:11:57,010 >> {'loss': 0.0070, 'learning_rate': 2.1953e-06, 'epoch': 2.75, 'throughput': 483.31}
+
+[INFO|callbacks.py:310] 2024-07-16 10:12:10,178 >> {'loss': 0.0347, 'learning_rate': 2.1521e-06, 'epoch': 2.78, 'throughput': 483.23}
+
+[INFO|callbacks.py:310] 2024-07-16 10:12:23,333 >> {'loss': 0.0142, 'learning_rate': 2.1089e-06, 'epoch': 2.80, 'throughput': 483.41}
+
+[INFO|callbacks.py:310] 2024-07-16 10:12:36,503 >> {'loss': 0.0414, 'learning_rate': 2.0659e-06, 'epoch': 2.83, 'throughput': 483.41}
+
+[INFO|callbacks.py:310] 2024-07-16 10:12:49,670 >> {'loss': 0.0419, 'learning_rate': 2.0230e-06, 'epoch': 2.86, 'throughput': 483.45}
+
+[INFO|callbacks.py:310] 2024-07-16 10:13:02,837 >> {'loss': 0.0430, 'learning_rate': 1.9802e-06, 'epoch': 2.88, 'throughput': 483.52}
+
+[INFO|callbacks.py:310] 2024-07-16 10:13:15,995 >> {'loss': 0.0192, 'learning_rate': 1.9376e-06, 'epoch': 2.91, 'throughput': 483.49}
+
+[INFO|callbacks.py:310] 2024-07-16 10:13:29,163 >> {'loss': 0.0427, 'learning_rate': 1.8952e-06, 'epoch': 2.93, 'throughput': 483.53}
+
+[INFO|callbacks.py:310] 2024-07-16 10:13:42,332 >> {'loss': 0.0116, 'learning_rate': 1.8530e-06, 'epoch': 2.96, 'throughput': 483.44}
+
+[INFO|callbacks.py:310] 2024-07-16 10:13:55,503 >> {'loss': 0.0135, 'learning_rate': 1.8109e-06, 'epoch': 2.98, 'throughput': 483.38}
+
+[INFO|callbacks.py:310] 2024-07-16 10:14:08,655 >> {'loss': 0.0128, 'learning_rate': 1.7691e-06, 'epoch': 3.01, 'throughput': 483.40}
+
+[INFO|callbacks.py:310] 2024-07-16 10:14:21,830 >> {'loss': 0.0021, 'learning_rate': 1.7275e-06, 'epoch': 3.04, 'throughput': 483.50}
+
+[INFO|callbacks.py:310] 2024-07-16 10:14:35,006 >> {'loss': 0.0057, 'learning_rate': 1.6861e-06, 'epoch': 3.06, 'throughput': 483.41}
+
+[INFO|callbacks.py:310] 2024-07-16 10:14:48,169 >> {'loss': 0.0197, 'learning_rate': 1.6449e-06, 'epoch': 3.09, 'throughput': 483.37}
+
+[INFO|callbacks.py:310] 2024-07-16 10:15:01,334 >> {'loss': 0.0017, 'learning_rate': 1.6041e-06, 'epoch': 3.11, 'throughput': 483.22}
+
+[INFO|callbacks.py:310] 2024-07-16 10:15:14,501 >> {'loss': 0.0068, 'learning_rate': 1.5635e-06, 'epoch': 3.14, 'throughput': 483.07}
+
+[INFO|callbacks.py:310] 2024-07-16 10:15:27,662 >> {'loss': 0.0022, 'learning_rate': 1.5232e-06, 'epoch': 3.16, 'throughput': 483.02}
+
+[INFO|callbacks.py:310] 2024-07-16 10:15:40,803 >> {'loss': 0.0162, 'learning_rate': 1.4832e-06, 'epoch': 3.19, 'throughput': 483.18}
+
+[INFO|callbacks.py:310] 2024-07-16 10:15:53,978 >> {'loss': 0.0014, 'learning_rate': 1.4435e-06, 'epoch': 3.22, 'throughput': 483.24}
+
+[INFO|callbacks.py:310] 2024-07-16 10:16:07,150 >> {'loss': 0.0063, 'learning_rate': 1.4041e-06, 'epoch': 3.24, 'throughput': 483.23}
+
+[INFO|callbacks.py:310] 2024-07-16 10:16:20,313 >> {'loss': 0.0282, 'learning_rate': 1.3650e-06, 'epoch': 3.27, 'throughput': 483.34}
+
+[INFO|callbacks.py:310] 2024-07-16 10:16:33,471 >> {'loss': 0.0003, 'learning_rate': 1.3263e-06, 'epoch': 3.29, 'throughput': 483.41}
+
+[INFO|callbacks.py:310] 2024-07-16 10:16:46,637 >> {'loss': 0.0002, 'learning_rate': 1.2880e-06, 'epoch': 3.32, 'throughput': 483.37}
+
+[INFO|callbacks.py:310] 2024-07-16 10:16:59,801 >> {'loss': 0.0004, 'learning_rate': 1.2500e-06, 'epoch': 3.34, 'throughput': 483.38}
+
+[INFO|callbacks.py:310] 2024-07-16 10:17:12,952 >> {'loss': 0.0169, 'learning_rate': 1.2124e-06, 'epoch': 3.37, 'throughput': 483.44}
+
+[INFO|callbacks.py:310] 2024-07-16 10:17:26,129 >> {'loss': 0.0127, 'learning_rate': 1.1752e-06, 'epoch': 3.40, 'throughput': 483.34}
+
+[INFO|callbacks.py:310] 2024-07-16 10:17:39,308 >> {'loss': 0.0045, 'learning_rate': 1.1384e-06, 'epoch': 3.42, 'throughput': 483.25}
+
+[INFO|callbacks.py:310] 2024-07-16 10:17:52,479 >> {'loss': 0.0924, 'learning_rate': 1.1020e-06, 'epoch': 3.45, 'throughput': 483.31}
+
+[INFO|callbacks.py:310] 2024-07-16 10:18:05,645 >> {'loss': 0.0067, 'learning_rate': 1.0661e-06, 'epoch': 3.47, 'throughput': 483.33}
+
+[INFO|callbacks.py:310] 2024-07-16 10:18:18,814 >> {'loss': 0.0030, 'learning_rate': 1.0305e-06, 'epoch': 3.50, 'throughput': 483.19}
+
+[INFO|callbacks.py:310] 2024-07-16 10:18:31,962 >> {'loss': 0.0164, 'learning_rate': 9.9546e-07, 'epoch': 3.52, 'throughput': 483.29}
+
+[INFO|callbacks.py:310] 2024-07-16 10:18:45,120 >> {'loss': 0.0018, 'learning_rate': 9.6085e-07, 'epoch': 3.55, 'throughput': 483.30}
+
+[INFO|callbacks.py:310] 2024-07-16 10:18:58,287 >> {'loss': 0.0226, 'learning_rate': 9.2670e-07, 'epoch': 3.58, 'throughput': 483.32}
+
+[INFO|callbacks.py:310] 2024-07-16 10:19:11,468 >> {'loss': 0.0008, 'learning_rate': 8.9303e-07, 'epoch': 3.60, 'throughput': 483.26}
+
+[INFO|callbacks.py:310] 2024-07-16 10:19:24,632 >> {'loss': 0.0004, 'learning_rate': 8.5985e-07, 'epoch': 3.63, 'throughput': 483.13}
+
+[INFO|callbacks.py:310] 2024-07-16 10:19:37,805 >> {'loss': 0.0008, 'learning_rate': 8.2717e-07, 'epoch': 3.65, 'throughput': 483.16}
+
+[INFO|callbacks.py:310] 2024-07-16 10:19:50,961 >> {'loss': 0.0256, 'learning_rate': 7.9500e-07, 'epoch': 3.68, 'throughput': 483.12}
+
+[INFO|callbacks.py:310] 2024-07-16 10:20:04,127 >> {'loss': 0.0005, 'learning_rate': 7.6335e-07, 'epoch': 3.70, 'throughput': 483.08}
+
+[INFO|callbacks.py:310] 2024-07-16 10:20:17,283 >> {'loss': 0.0045, 'learning_rate': 7.3223e-07, 'epoch': 3.73, 'throughput': 483.15}
+
+[INFO|callbacks.py:310] 2024-07-16 10:20:30,443 >> {'loss': 0.0005, 'learning_rate': 7.0165e-07, 'epoch': 3.76, 'throughput': 482.98}
+
+[INFO|callbacks.py:310] 2024-07-16 10:20:43,619 >> {'loss': 0.0069, 'learning_rate': 6.7162e-07, 'epoch': 3.78, 'throughput': 483.23}
+
+[INFO|callbacks.py:310] 2024-07-16 10:20:56,776 >> {'loss': 0.0150, 'learning_rate': 6.4214e-07, 'epoch': 3.81, 'throughput': 483.29}
+
+[INFO|callbacks.py:310] 2024-07-16 10:21:09,946 >> {'loss': 0.0012, 'learning_rate': 6.1323e-07, 'epoch': 3.83, 'throughput': 483.32}
+
+[INFO|callbacks.py:310] 2024-07-16 10:21:23,109 >> {'loss': 0.0095, 'learning_rate': 5.8489e-07, 'epoch': 3.86, 'throughput': 483.33}
+
+[INFO|callbacks.py:310] 2024-07-16 10:21:36,282 >> {'loss': 0.0271, 'learning_rate': 5.5714e-07, 'epoch': 3.88, 'throughput': 483.39}
+
+[INFO|callbacks.py:310] 2024-07-16 10:21:49,454 >> {'loss': 0.0201, 'learning_rate': 5.2997e-07, 'epoch': 3.91, 'throughput': 483.30}
+
+[INFO|callbacks.py:310] 2024-07-16 10:22:02,608 >> {'loss': 0.0120, 'learning_rate': 5.0341e-07, 'epoch': 3.94, 'throughput': 483.25}
+
+[INFO|callbacks.py:310] 2024-07-16 10:22:15,786 >> {'loss': 0.0230, 'learning_rate': 4.7746e-07, 'epoch': 3.96, 'throughput': 483.29}
+
+[INFO|callbacks.py:310] 2024-07-16 10:22:28,957 >> {'loss': 0.0156, 'learning_rate': 4.5212e-07, 'epoch': 3.99, 'throughput': 483.22}
+
+[INFO|callbacks.py:310] 2024-07-16 10:22:42,130 >> {'loss': 0.0009, 'learning_rate': 4.2741e-07, 'epoch': 4.01, 'throughput': 483.29}
+
+[INFO|callbacks.py:310] 2024-07-16 10:22:55,293 >> {'loss': 0.0017, 'learning_rate': 4.0332e-07, 'epoch': 4.04, 'throughput': 483.27}
+
+[INFO|callbacks.py:310] 2024-07-16 10:23:08,453 >> {'loss': 0.0015, 'learning_rate': 3.7988e-07, 'epoch': 4.06, 'throughput': 483.28}
+
+[INFO|callbacks.py:310] 2024-07-16 10:23:21,618 >> {'loss': 0.0035, 'learning_rate': 3.5708e-07, 'epoch': 4.09, 'throughput': 483.18}
+
+[INFO|callbacks.py:310] 2024-07-16 10:23:34,786 >> {'loss': 0.0016, 'learning_rate': 3.3494e-07, 'epoch': 4.12, 'throughput': 483.27}
+
+[INFO|callbacks.py:310] 2024-07-16 10:23:47,940 >> {'loss': 0.0028, 'learning_rate': 3.1345e-07, 'epoch': 4.14, 'throughput': 483.30}
+
+[INFO|callbacks.py:310] 2024-07-16 10:24:01,115 >> {'loss': 0.0006, 'learning_rate': 2.9263e-07, 'epoch': 4.17, 'throughput': 483.34}
+
+[INFO|callbacks.py:310] 2024-07-16 10:24:14,287 >> {'loss': 0.0013, 'learning_rate': 2.7248e-07, 'epoch': 4.19, 'throughput': 483.39}
+
+[INFO|callbacks.py:310] 2024-07-16 10:24:27,446 >> {'loss': 0.0006, 'learning_rate': 2.5301e-07, 'epoch': 4.22, 'throughput': 483.37}
+
+[INFO|callbacks.py:310] 2024-07-16 10:24:40,617 >> {'loss': 0.0017, 'learning_rate': 2.3423e-07, 'epoch': 4.24, 'throughput': 483.25}
+
+[INFO|callbacks.py:310] 2024-07-16 10:24:53,794 >> {'loss': 0.0004, 'learning_rate': 2.1614e-07, 'epoch': 4.27, 'throughput': 483.29}
+
+[INFO|callbacks.py:310] 2024-07-16 10:25:06,960 >> {'loss': 0.0049, 'learning_rate': 1.9874e-07, 'epoch': 4.30, 'throughput': 483.28}
+
+[INFO|callbacks.py:310] 2024-07-16 10:25:20,117 >> {'loss': 0.0071, 'learning_rate': 1.8204e-07, 'epoch': 4.32, 'throughput': 483.25}
+
+[INFO|callbacks.py:310] 2024-07-16 10:25:33,302 >> {'loss': 0.0011, 'learning_rate': 1.6605e-07, 'epoch': 4.35, 'throughput': 483.17}
+
+[INFO|callbacks.py:310] 2024-07-16 10:25:46,468 >> {'loss': 0.0004, 'learning_rate': 1.5077e-07, 'epoch': 4.37, 'throughput': 483.17}
+
+[INFO|callbacks.py:310] 2024-07-16 10:25:59,629 >> {'loss': 0.0007, 'learning_rate': 1.3620e-07, 'epoch': 4.40, 'throughput': 483.20}
+
+[INFO|callbacks.py:310] 2024-07-16 10:26:12,794 >> {'loss': 0.0017, 'learning_rate': 1.2236e-07, 'epoch': 4.42, 'throughput': 483.21}
+
+[INFO|callbacks.py:310] 2024-07-16 10:26:25,961 >> {'loss': 0.0007, 'learning_rate': 1.0924e-07, 'epoch': 4.45, 'throughput': 483.29}
+
+[INFO|callbacks.py:310] 2024-07-16 10:26:39,133 >> {'loss': 0.0003, 'learning_rate': 9.6846e-08, 'epoch': 4.48, 'throughput': 483.18}
+
+[INFO|callbacks.py:310] 2024-07-16 10:26:52,302 >> {'loss': 0.0046, 'learning_rate': 8.5185e-08, 'epoch': 4.50, 'throughput': 483.13}
+
+[INFO|callbacks.py:310] 2024-07-16 10:27:05,483 >> {'loss': 0.0038, 'learning_rate': 7.4261e-08, 'epoch': 4.53, 'throughput': 483.04}
+
+[INFO|callbacks.py:310] 2024-07-16 10:27:18,649 >> {'loss': 0.0036, 'learning_rate': 6.4075e-08, 'epoch': 4.55, 'throughput': 483.09}
+
+[INFO|callbacks.py:310] 2024-07-16 10:27:31,802 >> {'loss': 0.0056, 'learning_rate': 5.4631e-08, 'epoch': 4.58, 'throughput': 483.09}
+
+[INFO|callbacks.py:310] 2024-07-16 10:27:44,968 >> {'loss': 0.0057, 'learning_rate': 4.5932e-08, 'epoch': 4.60, 'throughput': 483.12}
+
+[INFO|callbacks.py:310] 2024-07-16 10:27:58,128 >> {'loss': 0.0020, 'learning_rate': 3.7981e-08, 'epoch': 4.63, 'throughput': 483.19}
+
+[INFO|callbacks.py:310] 2024-07-16 10:28:11,283 >> {'loss': 0.0003, 'learning_rate': 3.0779e-08, 'epoch': 4.66, 'throughput': 483.12}
+
+[INFO|callbacks.py:310] 2024-07-16 10:28:24,450 >> {'loss': 0.0002, 'learning_rate': 2.4330e-08, 'epoch': 4.68, 'throughput': 483.03}
+
+[INFO|callbacks.py:310] 2024-07-16 10:28:37,620 >> {'loss': 0.0043, 'learning_rate': 1.8635e-08, 'epoch': 4.71, 'throughput': 482.89}
+
+[INFO|callbacks.py:310] 2024-07-16 10:28:50,799 >> {'loss': 0.0002, 'learning_rate': 1.3695e-08, 'epoch': 4.73, 'throughput': 482.81}
+
+[INFO|callbacks.py:310] 2024-07-16 10:29:03,962 >> {'loss': 0.0013, 'learning_rate': 9.5133e-09, 'epoch': 4.76, 'throughput': 482.82}
+
+[INFO|callbacks.py:310] 2024-07-16 10:29:17,116 >> {'loss': 0.0023, 'learning_rate': 6.0899e-09, 'epoch': 4.78, 'throughput': 482.85}
+
+[INFO|callbacks.py:310] 2024-07-16 10:29:30,281 >> {'loss': 0.0002, 'learning_rate': 3.4262e-09, 'epoch': 4.81, 'throughput': 482.98}
+
+[INFO|callbacks.py:310] 2024-07-16 10:29:43,438 >> {'loss': 0.0015, 'learning_rate': 1.5229e-09, 'epoch': 4.84, 'throughput': 482.95}
+
+[INFO|callbacks.py:310] 2024-07-16 10:29:56,602 >> {'loss': 0.0002, 'learning_rate': 3.8076e-10, 'epoch': 4.86, 'throughput': 482.96}
+
+[INFO|callbacks.py:310] 2024-07-16 10:30:09,755 >> {'loss': 0.0028, 'learning_rate': 0.0000e+00, 'epoch': 4.89, 'throughput': 482.97}
+
+[INFO|trainer.py:3478] 2024-07-16 10:30:17,367 >> Saving model checkpoint to saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/checkpoint-190
+
+[INFO|configuration_utils.py:472] 2024-07-16 10:30:17,370 >> Configuration saved in saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/checkpoint-190/config.json
+
+[INFO|configuration_utils.py:769] 2024-07-16 10:30:17,371 >> Configuration saved in saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/checkpoint-190/generation_config.json
+
+[INFO|modeling_utils.py:2698] 2024-07-16 10:30:33,564 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/checkpoint-190/model.safetensors.index.json.
+
+[INFO|tokenization_utils_base.py:2574] 2024-07-16 10:30:33,568 >> tokenizer config file saved in saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/checkpoint-190/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2583] 2024-07-16 10:30:33,568 >> Special tokens file saved in saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/checkpoint-190/special_tokens_map.json
+
+[INFO|trainer.py:2383] 2024-07-16 10:31:10,372 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|trainer.py:3478] 2024-07-16 10:31:17,984 >> Saving model checkpoint to saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3
+
+[INFO|configuration_utils.py:472] 2024-07-16 10:31:17,987 >> Configuration saved in saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/config.json
+
+[INFO|configuration_utils.py:769] 2024-07-16 10:31:17,988 >> Configuration saved in saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/generation_config.json
+
+[INFO|modeling_utils.py:2698] 2024-07-16 10:31:35,440 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/model.safetensors.index.json.
+
+[INFO|tokenization_utils_base.py:2574] 2024-07-16 10:31:35,443 >> tokenizer config file saved in saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/tokenizer_config.json
+
+[INFO|tokenization_utils_base.py:2583] 2024-07-16 10:31:35,444 >> Special tokens file saved in saves/LLaMA3-8B-Chat/full/train_2024-07-16-09-46-28_llama3/special_tokens_map.json
+
+[WARNING|ploting.py:89] 2024-07-16 10:31:36,770 >> No metric eval_loss to plot.
+
+[WARNING|ploting.py:89] 2024-07-16 10:31:36,770 >> No metric eval_accuracy to plot.
+
+[INFO|modelcard.py:449] 2024-07-16 10:31:36,770 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<|eot_id|>"
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "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": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "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": "<|reserved_special_token_4|>",
+      "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": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.887459807073955,
+    "num_input_tokens_seen": 1208400,
+    "total_flos": 5.441370708980531e+16,
+    "train_loss": 0.5078434096239538,
+    "train_runtime": 2562.642,
+    "train_samples_per_second": 9.693,
+    "train_steps_per_second": 0.074
+}

trainer_log.jsonl

@@ -0,0 +1,191 @@
+{"current_steps": 1, "total_steps": 190, "loss": 14.1364, "learning_rate": 5.000000000000001e-07, "epoch": 0.02572347266881029, "percentage": 0.53, "elapsed_time": "0:00:13", "remaining_time": "0:43:08", "throughput": "475.41", "total_tokens": 6512}
+{"current_steps": 2, "total_steps": 190, "loss": 13.7804, "learning_rate": 1.0000000000000002e-06, "epoch": 0.05144694533762058, "percentage": 1.05, "elapsed_time": "0:00:26", "remaining_time": "0:42:08", "throughput": "477.72", "total_tokens": 12848}
+{"current_steps": 3, "total_steps": 190, "loss": 13.4871, "learning_rate": 1.5e-06, "epoch": 0.07717041800643087, "percentage": 1.58, "elapsed_time": "0:00:40", "remaining_time": "0:41:38", "throughput": "480.28", "total_tokens": 19248}
+{"current_steps": 4, "total_steps": 190, "loss": 12.79, "learning_rate": 2.0000000000000003e-06, "epoch": 0.10289389067524116, "percentage": 2.11, "elapsed_time": "0:00:53", "remaining_time": "0:41:16", "throughput": "475.82", "total_tokens": 25344}
+{"current_steps": 5, "total_steps": 190, "loss": 9.2748, "learning_rate": 2.5e-06, "epoch": 0.12861736334405144, "percentage": 2.63, "elapsed_time": "0:01:06", "remaining_time": "0:40:57", "throughput": "481.26", "total_tokens": 31968}
+{"current_steps": 6, "total_steps": 190, "loss": 6.5585, "learning_rate": 3e-06, "epoch": 0.15434083601286175, "percentage": 3.16, "elapsed_time": "0:01:19", "remaining_time": "0:40:40", "throughput": "479.46", "total_tokens": 38160}
+{"current_steps": 7, "total_steps": 190, "loss": 5.3984, "learning_rate": 3.5e-06, "epoch": 0.18006430868167203, "percentage": 3.68, "elapsed_time": "0:01:32", "remaining_time": "0:40:24", "throughput": "475.92", "total_tokens": 44144}
+{"current_steps": 8, "total_steps": 190, "loss": 1.9363, "learning_rate": 4.000000000000001e-06, "epoch": 0.2057877813504823, "percentage": 4.21, "elapsed_time": "0:01:45", "remaining_time": "0:40:10", "throughput": "476.05", "total_tokens": 50432}
+{"current_steps": 9, "total_steps": 190, "loss": 0.6783, "learning_rate": 4.5e-06, "epoch": 0.2315112540192926, "percentage": 4.74, "elapsed_time": "0:01:59", "remaining_time": "0:39:55", "throughput": "477.93", "total_tokens": 56928}
+{"current_steps": 10, "total_steps": 190, "loss": 2.9945, "learning_rate": 5e-06, "epoch": 0.2572347266881029, "percentage": 5.26, "elapsed_time": "0:02:12", "remaining_time": "0:39:40", "throughput": "478.89", "total_tokens": 63344}
+{"current_steps": 11, "total_steps": 190, "loss": 0.2916, "learning_rate": 4.9996192378909785e-06, "epoch": 0.2829581993569132, "percentage": 5.79, "elapsed_time": "0:02:25", "remaining_time": "0:39:26", "throughput": "478.35", "total_tokens": 69568}
+{"current_steps": 12, "total_steps": 190, "loss": 2.2775, "learning_rate": 4.99847706754774e-06, "epoch": 0.3086816720257235, "percentage": 6.32, "elapsed_time": "0:02:38", "remaining_time": "0:39:12", "throughput": "478.05", "total_tokens": 75824}
+{"current_steps": 13, "total_steps": 190, "loss": 0.3757, "learning_rate": 4.9965738368864345e-06, "epoch": 0.33440514469453375, "percentage": 6.84, "elapsed_time": "0:02:51", "remaining_time": "0:38:58", "throughput": "478.29", "total_tokens": 82160}
+{"current_steps": 14, "total_steps": 190, "loss": 1.9543, "learning_rate": 4.993910125649561e-06, "epoch": 0.36012861736334406, "percentage": 7.37, "elapsed_time": "0:03:04", "remaining_time": "0:38:44", "throughput": "479.20", "total_tokens": 88624}
+{"current_steps": 15, "total_steps": 190, "loss": 0.7398, "learning_rate": 4.990486745229364e-06, "epoch": 0.3858520900321543, "percentage": 7.89, "elapsed_time": "0:03:18", "remaining_time": "0:38:31", "throughput": "478.49", "total_tokens": 94800}
+{"current_steps": 16, "total_steps": 190, "loss": 1.1868, "learning_rate": 4.986304738420684e-06, "epoch": 0.4115755627009646, "percentage": 8.42, "elapsed_time": "0:03:31", "remaining_time": "0:38:17", "throughput": "479.67", "total_tokens": 101360}
+{"current_steps": 17, "total_steps": 190, "loss": 0.5418, "learning_rate": 4.981365379103306e-06, "epoch": 0.43729903536977494, "percentage": 8.95, "elapsed_time": "0:03:44", "remaining_time": "0:38:04", "throughput": "478.83", "total_tokens": 107488}
+{"current_steps": 18, "total_steps": 190, "loss": 0.2263, "learning_rate": 4.975670171853926e-06, "epoch": 0.4630225080385852, "percentage": 9.47, "elapsed_time": "0:03:57", "remaining_time": "0:37:50", "throughput": "479.37", "total_tokens": 113920}
+{"current_steps": 19, "total_steps": 190, "loss": 0.1612, "learning_rate": 4.9692208514878445e-06, "epoch": 0.4887459807073955, "percentage": 10.0, "elapsed_time": "0:04:10", "remaining_time": "0:37:37", "throughput": "479.86", "total_tokens": 120352}
+{"current_steps": 20, "total_steps": 190, "loss": 0.3299, "learning_rate": 4.962019382530521e-06, "epoch": 0.5144694533762058, "percentage": 10.53, "elapsed_time": "0:04:23", "remaining_time": "0:37:23", "throughput": "480.64", "total_tokens": 126880}
+{"current_steps": 21, "total_steps": 190, "loss": 0.2013, "learning_rate": 4.9540679586191605e-06, "epoch": 0.5401929260450161, "percentage": 11.05, "elapsed_time": "0:04:37", "remaining_time": "0:37:10", "throughput": "481.12", "total_tokens": 133344}
+{"current_steps": 22, "total_steps": 190, "loss": 0.2446, "learning_rate": 4.9453690018345144e-06, "epoch": 0.5659163987138264, "percentage": 11.58, "elapsed_time": "0:04:50", "remaining_time": "0:36:56", "throughput": "481.36", "total_tokens": 139744}
+{"current_steps": 23, "total_steps": 190, "loss": 0.2235, "learning_rate": 4.935925161963089e-06, "epoch": 0.5916398713826366, "percentage": 12.11, "elapsed_time": "0:05:03", "remaining_time": "0:36:43", "throughput": "481.55", "total_tokens": 146144}
+{"current_steps": 24, "total_steps": 190, "loss": 0.116, "learning_rate": 4.925739315689991e-06, "epoch": 0.617363344051447, "percentage": 12.63, "elapsed_time": "0:05:16", "remaining_time": "0:36:30", "throughput": "480.78", "total_tokens": 152240}
+{"current_steps": 25, "total_steps": 190, "loss": 0.2179, "learning_rate": 4.914814565722671e-06, "epoch": 0.6430868167202572, "percentage": 13.16, "elapsed_time": "0:05:29", "remaining_time": "0:36:16", "throughput": "480.61", "total_tokens": 158512}
+{"current_steps": 26, "total_steps": 190, "loss": 0.1414, "learning_rate": 4.903154239845798e-06, "epoch": 0.6688102893890675, "percentage": 13.68, "elapsed_time": "0:05:42", "remaining_time": "0:36:03", "throughput": "480.45", "total_tokens": 164784}
+{"current_steps": 27, "total_steps": 190, "loss": 0.1181, "learning_rate": 4.890761889907589e-06, "epoch": 0.6945337620578779, "percentage": 14.21, "elapsed_time": "0:05:56", "remaining_time": "0:35:49", "throughput": "481.03", "total_tokens": 171312}
+{"current_steps": 28, "total_steps": 190, "loss": 0.2753, "learning_rate": 4.8776412907378845e-06, "epoch": 0.7202572347266881, "percentage": 14.74, "elapsed_time": "0:06:09", "remaining_time": "0:35:36", "throughput": "481.61", "total_tokens": 177856}
+{"current_steps": 29, "total_steps": 190, "loss": 0.3255, "learning_rate": 4.863796438998293e-06, "epoch": 0.7459807073954984, "percentage": 15.26, "elapsed_time": "0:06:22", "remaining_time": "0:35:23", "throughput": "482.08", "total_tokens": 184368}
+{"current_steps": 30, "total_steps": 190, "loss": 0.2352, "learning_rate": 4.849231551964771e-06, "epoch": 0.7717041800643086, "percentage": 15.79, "elapsed_time": "0:06:35", "remaining_time": "0:35:09", "throughput": "482.60", "total_tokens": 190928}
+{"current_steps": 31, "total_steps": 190, "loss": 0.063, "learning_rate": 4.833951066243004e-06, "epoch": 0.797427652733119, "percentage": 16.32, "elapsed_time": "0:06:48", "remaining_time": "0:34:56", "throughput": "482.48", "total_tokens": 197232}
+{"current_steps": 32, "total_steps": 190, "loss": 0.2042, "learning_rate": 4.817959636416969e-06, "epoch": 0.8231511254019293, "percentage": 16.84, "elapsed_time": "0:07:01", "remaining_time": "0:34:43", "throughput": "482.50", "total_tokens": 203584}
+{"current_steps": 33, "total_steps": 190, "loss": 0.1364, "learning_rate": 4.801262133631101e-06, "epoch": 0.8488745980707395, "percentage": 17.37, "elapsed_time": "0:07:15", "remaining_time": "0:34:30", "throughput": "482.93", "total_tokens": 210128}
+{"current_steps": 34, "total_steps": 190, "loss": 0.0934, "learning_rate": 4.783863644106502e-06, "epoch": 0.8745980707395499, "percentage": 17.89, "elapsed_time": "0:07:28", "remaining_time": "0:34:16", "throughput": "482.98", "total_tokens": 216512}
+{"current_steps": 35, "total_steps": 190, "loss": 0.1332, "learning_rate": 4.765769467591626e-06, "epoch": 0.9003215434083601, "percentage": 18.42, "elapsed_time": "0:07:41", "remaining_time": "0:34:03", "throughput": "483.11", "total_tokens": 222928}
+{"current_steps": 36, "total_steps": 190, "loss": 0.1595, "learning_rate": 4.746985115747918e-06, "epoch": 0.9260450160771704, "percentage": 18.95, "elapsed_time": "0:07:54", "remaining_time": "0:33:50", "throughput": "483.00", "total_tokens": 229232}
+{"current_steps": 37, "total_steps": 190, "loss": 0.1528, "learning_rate": 4.72751631047092e-06, "epoch": 0.9517684887459807, "percentage": 19.47, "elapsed_time": "0:08:07", "remaining_time": "0:33:37", "throughput": "483.18", "total_tokens": 235680}
+{"current_steps": 38, "total_steps": 190, "loss": 0.1342, "learning_rate": 4.707368982147318e-06, "epoch": 0.977491961414791, "percentage": 20.0, "elapsed_time": "0:08:20", "remaining_time": "0:33:23", "throughput": "483.48", "total_tokens": 242192}
+{"current_steps": 39, "total_steps": 190, "loss": 0.1586, "learning_rate": 4.68654926784849e-06, "epoch": 1.0032154340836013, "percentage": 20.53, "elapsed_time": "0:08:34", "remaining_time": "0:33:10", "throughput": "483.71", "total_tokens": 248672}
+{"current_steps": 40, "total_steps": 190, "loss": 0.1072, "learning_rate": 4.665063509461098e-06, "epoch": 1.0289389067524115, "percentage": 21.05, "elapsed_time": "0:08:47", "remaining_time": "0:32:57", "throughput": "483.77", "total_tokens": 255072}
+{"current_steps": 41, "total_steps": 190, "loss": 0.0357, "learning_rate": 4.642918251755281e-06, "epoch": 1.0546623794212218, "percentage": 21.58, "elapsed_time": "0:09:00", "remaining_time": "0:32:43", "throughput": "484.04", "total_tokens": 261584}
+{"current_steps": 42, "total_steps": 190, "loss": 0.06, "learning_rate": 4.620120240391065e-06, "epoch": 1.0803858520900322, "percentage": 22.11, "elapsed_time": "0:09:13", "remaining_time": "0:32:30", "throughput": "484.18", "total_tokens": 268032}
+{"current_steps": 43, "total_steps": 190, "loss": 0.0902, "learning_rate": 4.596676419863561e-06, "epoch": 1.1061093247588425, "percentage": 22.63, "elapsed_time": "0:09:26", "remaining_time": "0:32:17", "throughput": "484.46", "total_tokens": 274560}
+{"current_steps": 44, "total_steps": 190, "loss": 0.0202, "learning_rate": 4.572593931387604e-06, "epoch": 1.1318327974276527, "percentage": 23.16, "elapsed_time": "0:09:39", "remaining_time": "0:32:04", "throughput": "484.51", "total_tokens": 280960}
+{"current_steps": 45, "total_steps": 190, "loss": 0.038, "learning_rate": 4.54788011072248e-06, "epoch": 1.157556270096463, "percentage": 23.68, "elapsed_time": "0:09:53", "remaining_time": "0:31:51", "throughput": "484.10", "total_tokens": 287104}
+{"current_steps": 46, "total_steps": 190, "loss": 0.0379, "learning_rate": 4.522542485937369e-06, "epoch": 1.1832797427652733, "percentage": 24.21, "elapsed_time": "0:10:06", "remaining_time": "0:31:37", "throughput": "484.17", "total_tokens": 293520}
+{"current_steps": 47, "total_steps": 190, "loss": 0.0742, "learning_rate": 4.496588775118232e-06, "epoch": 1.2090032154340835, "percentage": 24.74, "elapsed_time": "0:10:19", "remaining_time": "0:31:24", "throughput": "484.24", "total_tokens": 299936}
+{"current_steps": 48, "total_steps": 190, "loss": 0.0658, "learning_rate": 4.470026884016805e-06, "epoch": 1.234726688102894, "percentage": 25.26, "elapsed_time": "0:10:32", "remaining_time": "0:31:11", "throughput": "483.64", "total_tokens": 305936}
+{"current_steps": 49, "total_steps": 190, "loss": 0.0336, "learning_rate": 4.442864903642428e-06, "epoch": 1.2604501607717042, "percentage": 25.79, "elapsed_time": "0:10:45", "remaining_time": "0:30:58", "throughput": "483.99", "total_tokens": 312528}
+{"current_steps": 50, "total_steps": 190, "loss": 0.1021, "learning_rate": 4.415111107797445e-06, "epoch": 1.2861736334405145, "percentage": 26.32, "elapsed_time": "0:10:58", "remaining_time": "0:30:44", "throughput": "483.77", "total_tokens": 318752}
+{"current_steps": 51, "total_steps": 190, "loss": 0.1312, "learning_rate": 4.386773950556931e-06, "epoch": 1.3118971061093248, "percentage": 26.84, "elapsed_time": "0:11:12", "remaining_time": "0:30:31", "throughput": "483.74", "total_tokens": 325088}
+{"current_steps": 52, "total_steps": 190, "loss": 0.0665, "learning_rate": 4.357862063693486e-06, "epoch": 1.337620578778135, "percentage": 27.37, "elapsed_time": "0:11:25", "remaining_time": "0:30:18", "throughput": "483.68", "total_tokens": 331424}
+{"current_steps": 53, "total_steps": 190, "loss": 0.0679, "learning_rate": 4.328384254047927e-06, "epoch": 1.3633440514469453, "percentage": 27.89, "elapsed_time": "0:11:38", "remaining_time": "0:30:05", "throughput": "483.66", "total_tokens": 337776}
+{"current_steps": 54, "total_steps": 190, "loss": 0.0579, "learning_rate": 4.2983495008466285e-06, "epoch": 1.3890675241157555, "percentage": 28.42, "elapsed_time": "0:11:51", "remaining_time": "0:29:52", "throughput": "483.46", "total_tokens": 344000}
+{"current_steps": 55, "total_steps": 190, "loss": 0.0542, "learning_rate": 4.267766952966369e-06, "epoch": 1.414790996784566, "percentage": 28.95, "elapsed_time": "0:12:04", "remaining_time": "0:29:38", "throughput": "483.69", "total_tokens": 350528}
+{"current_steps": 56, "total_steps": 190, "loss": 0.0476, "learning_rate": 4.236645926147493e-06, "epoch": 1.4405144694533762, "percentage": 29.47, "elapsed_time": "0:12:17", "remaining_time": "0:29:25", "throughput": "483.69", "total_tokens": 356896}
+{"current_steps": 57, "total_steps": 190, "loss": 0.0613, "learning_rate": 4.204995900156247e-06, "epoch": 1.4662379421221865, "percentage": 30.0, "elapsed_time": "0:12:31", "remaining_time": "0:29:12", "throughput": "483.84", "total_tokens": 363376}
+{"current_steps": 58, "total_steps": 190, "loss": 0.0995, "learning_rate": 4.172826515897146e-06, "epoch": 1.4919614147909968, "percentage": 30.53, "elapsed_time": "0:12:44", "remaining_time": "0:28:59", "throughput": "483.76", "total_tokens": 369680}
+{"current_steps": 59, "total_steps": 190, "loss": 0.0532, "learning_rate": 4.140147572476269e-06, "epoch": 1.517684887459807, "percentage": 31.05, "elapsed_time": "0:12:57", "remaining_time": "0:28:45", "throughput": "483.57", "total_tokens": 375904}
+{"current_steps": 60, "total_steps": 190, "loss": 0.0824, "learning_rate": 4.106969024216348e-06, "epoch": 1.5434083601286175, "percentage": 31.58, "elapsed_time": "0:13:10", "remaining_time": "0:28:32", "throughput": "483.60", "total_tokens": 382304}
+{"current_steps": 61, "total_steps": 190, "loss": 0.0499, "learning_rate": 4.073300977624594e-06, "epoch": 1.5691318327974275, "percentage": 32.11, "elapsed_time": "0:13:23", "remaining_time": "0:28:19", "throughput": "483.63", "total_tokens": 388688}
+{"current_steps": 62, "total_steps": 190, "loss": 0.0413, "learning_rate": 4.039153688314146e-06, "epoch": 1.594855305466238, "percentage": 32.63, "elapsed_time": "0:13:36", "remaining_time": "0:28:06", "throughput": "483.75", "total_tokens": 395152}
+{"current_steps": 63, "total_steps": 190, "loss": 0.0637, "learning_rate": 4.0045375578801216e-06, "epoch": 1.6205787781350482, "percentage": 33.16, "elapsed_time": "0:13:50", "remaining_time": "0:27:53", "throughput": "484.01", "total_tokens": 401728}
+{"current_steps": 64, "total_steps": 190, "loss": 0.0529, "learning_rate": 3.969463130731183e-06, "epoch": 1.6463022508038585, "percentage": 33.68, "elapsed_time": "0:14:03", "remaining_time": "0:27:40", "throughput": "483.77", "total_tokens": 407904}
+{"current_steps": 65, "total_steps": 190, "loss": 0.0474, "learning_rate": 3.933941090877615e-06, "epoch": 1.6720257234726688, "percentage": 34.21, "elapsed_time": "0:14:16", "remaining_time": "0:27:26", "throughput": "483.73", "total_tokens": 414240}
+{"current_steps": 66, "total_steps": 190, "loss": 0.0649, "learning_rate": 3.897982258676867e-06, "epoch": 1.697749196141479, "percentage": 34.74, "elapsed_time": "0:14:29", "remaining_time": "0:27:13", "throughput": "483.55", "total_tokens": 420448}
+{"current_steps": 67, "total_steps": 190, "loss": 0.0505, "learning_rate": 3.861597587537568e-06, "epoch": 1.7234726688102895, "percentage": 35.26, "elapsed_time": "0:14:42", "remaining_time": "0:27:00", "throughput": "483.51", "total_tokens": 426784}
+{"current_steps": 68, "total_steps": 190, "loss": 0.0621, "learning_rate": 3.824798160583012e-06, "epoch": 1.7491961414790995, "percentage": 35.79, "elapsed_time": "0:14:55", "remaining_time": "0:26:47", "throughput": "483.14", "total_tokens": 432816}
+{"current_steps": 69, "total_steps": 190, "loss": 0.0769, "learning_rate": 3.787595187275136e-06, "epoch": 1.77491961414791, "percentage": 36.32, "elapsed_time": "0:15:09", "remaining_time": "0:26:34", "throughput": "483.20", "total_tokens": 439232}
+{"current_steps": 70, "total_steps": 190, "loss": 0.0435, "learning_rate": 3.7500000000000005e-06, "epoch": 1.8006430868167203, "percentage": 36.84, "elapsed_time": "0:15:22", "remaining_time": "0:26:20", "throughput": "483.42", "total_tokens": 445792}
+{"current_steps": 71, "total_steps": 190, "loss": 0.0673, "learning_rate": 3.7120240506158433e-06, "epoch": 1.8263665594855305, "percentage": 37.37, "elapsed_time": "0:15:35", "remaining_time": "0:26:07", "throughput": "483.69", "total_tokens": 452400}
+{"current_steps": 72, "total_steps": 190, "loss": 0.1316, "learning_rate": 3.6736789069647273e-06, "epoch": 1.852090032154341, "percentage": 37.89, "elapsed_time": "0:15:48", "remaining_time": "0:25:54", "throughput": "483.44", "total_tokens": 458528}
+{"current_steps": 73, "total_steps": 190, "loss": 0.0531, "learning_rate": 3.634976249348867e-06, "epoch": 1.877813504823151, "percentage": 38.42, "elapsed_time": "0:16:01", "remaining_time": "0:25:41", "throughput": "483.53", "total_tokens": 464976}
+{"current_steps": 74, "total_steps": 190, "loss": 0.0287, "learning_rate": 3.595927866972694e-06, "epoch": 1.9035369774919615, "percentage": 38.95, "elapsed_time": "0:16:14", "remaining_time": "0:25:28", "throughput": "483.62", "total_tokens": 471440}
+{"current_steps": 75, "total_steps": 190, "loss": 0.0648, "learning_rate": 3.556545654351749e-06, "epoch": 1.9292604501607717, "percentage": 39.47, "elapsed_time": "0:16:27", "remaining_time": "0:25:14", "throughput": "483.59", "total_tokens": 477776}
+{"current_steps": 76, "total_steps": 190, "loss": 0.1211, "learning_rate": 3.516841607689501e-06, "epoch": 1.954983922829582, "percentage": 40.0, "elapsed_time": "0:16:41", "remaining_time": "0:25:01", "throughput": "483.54", "total_tokens": 484096}
+{"current_steps": 77, "total_steps": 190, "loss": 0.0879, "learning_rate": 3.476827821223184e-06, "epoch": 1.9807073954983923, "percentage": 40.53, "elapsed_time": "0:16:54", "remaining_time": "0:24:48", "throughput": "483.26", "total_tokens": 490176}
+{"current_steps": 78, "total_steps": 190, "loss": 0.0227, "learning_rate": 3.436516483539781e-06, "epoch": 2.0064308681672025, "percentage": 41.05, "elapsed_time": "0:17:07", "remaining_time": "0:24:35", "throughput": "483.39", "total_tokens": 496672}
+{"current_steps": 79, "total_steps": 190, "loss": 0.0228, "learning_rate": 3.39591987386325e-06, "epoch": 2.032154340836013, "percentage": 41.58, "elapsed_time": "0:17:20", "remaining_time": "0:24:22", "throughput": "483.45", "total_tokens": 503088}
+{"current_steps": 80, "total_steps": 190, "loss": 0.036, "learning_rate": 3.3550503583141726e-06, "epoch": 2.057877813504823, "percentage": 42.11, "elapsed_time": "0:17:33", "remaining_time": "0:24:08", "throughput": "483.47", "total_tokens": 509472}
+{"current_steps": 81, "total_steps": 190, "loss": 0.0138, "learning_rate": 3.313920386142892e-06, "epoch": 2.0836012861736335, "percentage": 42.63, "elapsed_time": "0:17:46", "remaining_time": "0:23:55", "throughput": "483.36", "total_tokens": 515728}
+{"current_steps": 82, "total_steps": 190, "loss": 0.0697, "learning_rate": 3.272542485937369e-06, "epoch": 2.1093247588424435, "percentage": 43.16, "elapsed_time": "0:18:00", "remaining_time": "0:23:42", "throughput": "483.18", "total_tokens": 521904}
+{"current_steps": 83, "total_steps": 190, "loss": 0.0508, "learning_rate": 3.230929261806842e-06, "epoch": 2.135048231511254, "percentage": 43.68, "elapsed_time": "0:18:13", "remaining_time": "0:23:29", "throughput": "482.89", "total_tokens": 527952}
+{"current_steps": 84, "total_steps": 190, "loss": 0.0088, "learning_rate": 3.189093389542498e-06, "epoch": 2.1607717041800645, "percentage": 44.21, "elapsed_time": "0:18:26", "remaining_time": "0:23:16", "throughput": "483.18", "total_tokens": 534624}
+{"current_steps": 85, "total_steps": 190, "loss": 0.0158, "learning_rate": 3.147047612756302e-06, "epoch": 2.1864951768488745, "percentage": 44.74, "elapsed_time": "0:18:39", "remaining_time": "0:23:03", "throughput": "483.34", "total_tokens": 541168}
+{"current_steps": 86, "total_steps": 190, "loss": 0.006, "learning_rate": 3.1048047389991693e-06, "epoch": 2.212218649517685, "percentage": 45.26, "elapsed_time": "0:18:52", "remaining_time": "0:22:49", "throughput": "483.30", "total_tokens": 547488}
+{"current_steps": 87, "total_steps": 190, "loss": 0.038, "learning_rate": 3.062377635859663e-06, "epoch": 2.237942122186495, "percentage": 45.79, "elapsed_time": "0:19:05", "remaining_time": "0:22:36", "throughput": "483.67", "total_tokens": 554272}
+{"current_steps": 88, "total_steps": 190, "loss": 0.0004, "learning_rate": 3.019779227044398e-06, "epoch": 2.2636655948553055, "percentage": 46.32, "elapsed_time": "0:19:19", "remaining_time": "0:22:23", "throughput": "483.58", "total_tokens": 560528}
+{"current_steps": 89, "total_steps": 190, "loss": 0.0111, "learning_rate": 2.9770224884413625e-06, "epoch": 2.289389067524116, "percentage": 46.84, "elapsed_time": "0:19:32", "remaining_time": "0:22:10", "throughput": "483.47", "total_tokens": 566784}
+{"current_steps": 90, "total_steps": 190, "loss": 0.0008, "learning_rate": 2.9341204441673267e-06, "epoch": 2.315112540192926, "percentage": 47.37, "elapsed_time": "0:19:45", "remaining_time": "0:21:57", "throughput": "483.64", "total_tokens": 573344}
+{"current_steps": 91, "total_steps": 190, "loss": 0.0182, "learning_rate": 2.8910861626005774e-06, "epoch": 2.3408360128617365, "percentage": 47.89, "elapsed_time": "0:19:58", "remaining_time": "0:21:43", "throughput": "483.70", "total_tokens": 579776}
+{"current_steps": 92, "total_steps": 190, "loss": 0.0491, "learning_rate": 2.847932752400164e-06, "epoch": 2.3665594855305465, "percentage": 48.42, "elapsed_time": "0:20:11", "remaining_time": "0:21:30", "throughput": "483.66", "total_tokens": 586096}
+{"current_steps": 93, "total_steps": 190, "loss": 0.004, "learning_rate": 2.804673358512869e-06, "epoch": 2.392282958199357, "percentage": 48.95, "elapsed_time": "0:20:24", "remaining_time": "0:21:17", "throughput": "483.71", "total_tokens": 592528}
+{"current_steps": 94, "total_steps": 190, "loss": 0.0176, "learning_rate": 2.761321158169134e-06, "epoch": 2.418006430868167, "percentage": 49.47, "elapsed_time": "0:20:38", "remaining_time": "0:21:04", "throughput": "483.76", "total_tokens": 598960}
+{"current_steps": 95, "total_steps": 190, "loss": 0.019, "learning_rate": 2.717889356869146e-06, "epoch": 2.4437299035369775, "percentage": 50.0, "elapsed_time": "0:20:51", "remaining_time": "0:20:51", "throughput": "483.69", "total_tokens": 605232}
+{"current_steps": 96, "total_steps": 190, "loss": 0.027, "learning_rate": 2.6743911843603134e-06, "epoch": 2.469453376205788, "percentage": 50.53, "elapsed_time": "0:21:04", "remaining_time": "0:20:38", "throughput": "483.49", "total_tokens": 611344}
+{"current_steps": 97, "total_steps": 190, "loss": 0.0354, "learning_rate": 2.6308398906073603e-06, "epoch": 2.495176848874598, "percentage": 51.05, "elapsed_time": "0:21:17", "remaining_time": "0:20:24", "throughput": "483.49", "total_tokens": 617712}
+{"current_steps": 98, "total_steps": 190, "loss": 0.0741, "learning_rate": 2.587248741756253e-06, "epoch": 2.5209003215434085, "percentage": 51.58, "elapsed_time": "0:21:30", "remaining_time": "0:20:11", "throughput": "483.59", "total_tokens": 624208}
+{"current_steps": 99, "total_steps": 190, "loss": 0.0582, "learning_rate": 2.543631016093209e-06, "epoch": 2.5466237942122185, "percentage": 52.11, "elapsed_time": "0:21:43", "remaining_time": "0:19:58", "throughput": "483.53", "total_tokens": 630496}
+{"current_steps": 100, "total_steps": 190, "loss": 0.0096, "learning_rate": 2.5e-06, "epoch": 2.572347266881029, "percentage": 52.63, "elapsed_time": "0:21:57", "remaining_time": "0:19:45", "throughput": "483.66", "total_tokens": 637040}
+{"current_steps": 101, "total_steps": 190, "loss": 0.0263, "learning_rate": 2.4563689839067913e-06, "epoch": 2.598070739549839, "percentage": 53.16, "elapsed_time": "0:22:10", "remaining_time": "0:19:32", "throughput": "483.71", "total_tokens": 643472}
+{"current_steps": 102, "total_steps": 190, "loss": 0.0121, "learning_rate": 2.4127512582437486e-06, "epoch": 2.6237942122186495, "percentage": 53.68, "elapsed_time": "0:22:23", "remaining_time": "0:19:19", "throughput": "483.65", "total_tokens": 649760}
+{"current_steps": 103, "total_steps": 190, "loss": 0.0204, "learning_rate": 2.3691601093926406e-06, "epoch": 2.64951768488746, "percentage": 54.21, "elapsed_time": "0:22:36", "remaining_time": "0:19:05", "throughput": "483.62", "total_tokens": 656096}
+{"current_steps": 104, "total_steps": 190, "loss": 0.0325, "learning_rate": 2.325608815639687e-06, "epoch": 2.67524115755627, "percentage": 54.74, "elapsed_time": "0:22:49", "remaining_time": "0:18:52", "throughput": "483.74", "total_tokens": 662624}
+{"current_steps": 105, "total_steps": 190, "loss": 0.0076, "learning_rate": 2.2821106431308546e-06, "epoch": 2.7009646302250805, "percentage": 55.26, "elapsed_time": "0:23:02", "remaining_time": "0:18:39", "throughput": "483.58", "total_tokens": 668768}
+{"current_steps": 106, "total_steps": 190, "loss": 0.0485, "learning_rate": 2.238678841830867e-06, "epoch": 2.7266881028938905, "percentage": 55.79, "elapsed_time": "0:23:16", "remaining_time": "0:18:26", "throughput": "483.48", "total_tokens": 674992}
+{"current_steps": 107, "total_steps": 190, "loss": 0.007, "learning_rate": 2.195326641487132e-06, "epoch": 2.752411575562701, "percentage": 56.32, "elapsed_time": "0:23:29", "remaining_time": "0:18:13", "throughput": "483.31", "total_tokens": 681120}
+{"current_steps": 108, "total_steps": 190, "loss": 0.0347, "learning_rate": 2.1520672475998374e-06, "epoch": 2.778135048231511, "percentage": 56.84, "elapsed_time": "0:23:42", "remaining_time": "0:18:00", "throughput": "483.23", "total_tokens": 687376}
+{"current_steps": 109, "total_steps": 190, "loss": 0.0142, "learning_rate": 2.1089138373994226e-06, "epoch": 2.8038585209003215, "percentage": 57.37, "elapsed_time": "0:23:55", "remaining_time": "0:17:46", "throughput": "483.41", "total_tokens": 693984}
+{"current_steps": 110, "total_steps": 190, "loss": 0.0414, "learning_rate": 2.0658795558326745e-06, "epoch": 2.829581993569132, "percentage": 57.89, "elapsed_time": "0:24:08", "remaining_time": "0:17:33", "throughput": "483.41", "total_tokens": 700352}
+{"current_steps": 111, "total_steps": 190, "loss": 0.0419, "learning_rate": 2.022977511558638e-06, "epoch": 2.855305466237942, "percentage": 58.42, "elapsed_time": "0:24:21", "remaining_time": "0:17:20", "throughput": "483.45", "total_tokens": 706768}
+{"current_steps": 112, "total_steps": 190, "loss": 0.043, "learning_rate": 1.9802207729556023e-06, "epoch": 2.8810289389067525, "percentage": 58.95, "elapsed_time": "0:24:35", "remaining_time": "0:17:07", "throughput": "483.52", "total_tokens": 713248}
+{"current_steps": 113, "total_steps": 190, "loss": 0.0192, "learning_rate": 1.937622364140338e-06, "epoch": 2.906752411575563, "percentage": 59.47, "elapsed_time": "0:24:48", "remaining_time": "0:16:54", "throughput": "483.49", "total_tokens": 719568}
+{"current_steps": 114, "total_steps": 190, "loss": 0.0427, "learning_rate": 1.895195261000831e-06, "epoch": 2.932475884244373, "percentage": 60.0, "elapsed_time": "0:25:01", "remaining_time": "0:16:40", "throughput": "483.53", "total_tokens": 725984}
+{"current_steps": 115, "total_steps": 190, "loss": 0.0116, "learning_rate": 1.852952387243698e-06, "epoch": 2.958199356913183, "percentage": 60.53, "elapsed_time": "0:25:14", "remaining_time": "0:16:27", "throughput": "483.44", "total_tokens": 732224}
+{"current_steps": 116, "total_steps": 190, "loss": 0.0135, "learning_rate": 1.8109066104575023e-06, "epoch": 2.9839228295819935, "percentage": 61.05, "elapsed_time": "0:25:27", "remaining_time": "0:16:14", "throughput": "483.38", "total_tokens": 738496}
+{"current_steps": 117, "total_steps": 190, "loss": 0.0128, "learning_rate": 1.7690707381931585e-06, "epoch": 3.009646302250804, "percentage": 61.58, "elapsed_time": "0:25:40", "remaining_time": "0:16:01", "throughput": "483.40", "total_tokens": 744880}
+{"current_steps": 118, "total_steps": 190, "loss": 0.0021, "learning_rate": 1.7274575140626318e-06, "epoch": 3.035369774919614, "percentage": 62.11, "elapsed_time": "0:25:54", "remaining_time": "0:15:48", "throughput": "483.50", "total_tokens": 751408}
+{"current_steps": 119, "total_steps": 190, "loss": 0.0057, "learning_rate": 1.686079613857109e-06, "epoch": 3.0610932475884245, "percentage": 62.63, "elapsed_time": "0:26:07", "remaining_time": "0:15:35", "throughput": "483.41", "total_tokens": 757632}
+{"current_steps": 120, "total_steps": 190, "loss": 0.0197, "learning_rate": 1.6449496416858285e-06, "epoch": 3.0868167202572345, "percentage": 63.16, "elapsed_time": "0:26:20", "remaining_time": "0:15:21", "throughput": "483.37", "total_tokens": 763936}
+{"current_steps": 121, "total_steps": 190, "loss": 0.0017, "learning_rate": 1.6040801261367494e-06, "epoch": 3.112540192926045, "percentage": 63.68, "elapsed_time": "0:26:33", "remaining_time": "0:15:08", "throughput": "483.22", "total_tokens": 770064}
+{"current_steps": 122, "total_steps": 190, "loss": 0.0068, "learning_rate": 1.56348351646022e-06, "epoch": 3.1382636655948555, "percentage": 64.21, "elapsed_time": "0:26:46", "remaining_time": "0:14:55", "throughput": "483.07", "total_tokens": 776176}
+{"current_steps": 123, "total_steps": 190, "loss": 0.0022, "learning_rate": 1.5231721787768162e-06, "epoch": 3.1639871382636655, "percentage": 64.74, "elapsed_time": "0:26:59", "remaining_time": "0:14:42", "throughput": "483.02", "total_tokens": 782464}
+{"current_steps": 124, "total_steps": 190, "loss": 0.0162, "learning_rate": 1.4831583923105e-06, "epoch": 3.189710610932476, "percentage": 65.26, "elapsed_time": "0:27:13", "remaining_time": "0:14:29", "throughput": "483.18", "total_tokens": 789072}
+{"current_steps": 125, "total_steps": 190, "loss": 0.0014, "learning_rate": 1.443454345648252e-06, "epoch": 3.215434083601286, "percentage": 65.79, "elapsed_time": "0:27:26", "remaining_time": "0:14:16", "throughput": "483.24", "total_tokens": 795536}
+{"current_steps": 126, "total_steps": 190, "loss": 0.0063, "learning_rate": 1.4040721330273063e-06, "epoch": 3.2411575562700965, "percentage": 66.32, "elapsed_time": "0:27:39", "remaining_time": "0:14:02", "throughput": "483.23", "total_tokens": 801888}
+{"current_steps": 127, "total_steps": 190, "loss": 0.0282, "learning_rate": 1.3650237506511333e-06, "epoch": 3.266881028938907, "percentage": 66.84, "elapsed_time": "0:27:52", "remaining_time": "0:13:49", "throughput": "483.34", "total_tokens": 808432}
+{"current_steps": 128, "total_steps": 190, "loss": 0.0003, "learning_rate": 1.3263210930352737e-06, "epoch": 3.292604501607717, "percentage": 67.37, "elapsed_time": "0:28:05", "remaining_time": "0:13:36", "throughput": "483.41", "total_tokens": 814896}
+{"current_steps": 129, "total_steps": 190, "loss": 0.0002, "learning_rate": 1.2879759493841577e-06, "epoch": 3.3183279742765275, "percentage": 67.89, "elapsed_time": "0:28:18", "remaining_time": "0:13:23", "throughput": "483.37", "total_tokens": 821200}
+{"current_steps": 130, "total_steps": 190, "loss": 0.0004, "learning_rate": 1.2500000000000007e-06, "epoch": 3.3440514469453375, "percentage": 68.42, "elapsed_time": "0:28:32", "remaining_time": "0:13:10", "throughput": "483.38", "total_tokens": 827584}
+{"current_steps": 131, "total_steps": 190, "loss": 0.0169, "learning_rate": 1.2124048127248644e-06, "epoch": 3.369774919614148, "percentage": 68.95, "elapsed_time": "0:28:45", "remaining_time": "0:12:57", "throughput": "483.44", "total_tokens": 834048}
+{"current_steps": 132, "total_steps": 190, "loss": 0.0127, "learning_rate": 1.1752018394169882e-06, "epoch": 3.395498392282958, "percentage": 69.47, "elapsed_time": "0:28:58", "remaining_time": "0:12:43", "throughput": "483.34", "total_tokens": 840240}
+{"current_steps": 133, "total_steps": 190, "loss": 0.0045, "learning_rate": 1.1384024124624324e-06, "epoch": 3.4212218649517685, "percentage": 70.0, "elapsed_time": "0:29:11", "remaining_time": "0:12:30", "throughput": "483.25", "total_tokens": 846448}
+{"current_steps": 134, "total_steps": 190, "loss": 0.0924, "learning_rate": 1.1020177413231334e-06, "epoch": 3.446945337620579, "percentage": 70.53, "elapsed_time": "0:29:24", "remaining_time": "0:12:17", "throughput": "483.31", "total_tokens": 852928}
+{"current_steps": 135, "total_steps": 190, "loss": 0.0067, "learning_rate": 1.0660589091223854e-06, "epoch": 3.472668810289389, "percentage": 71.05, "elapsed_time": "0:29:37", "remaining_time": "0:12:04", "throughput": "483.33", "total_tokens": 859312}
+{"current_steps": 136, "total_steps": 190, "loss": 0.003, "learning_rate": 1.0305368692688175e-06, "epoch": 3.4983922829581995, "percentage": 71.58, "elapsed_time": "0:29:51", "remaining_time": "0:11:51", "throughput": "483.19", "total_tokens": 865440}
+{"current_steps": 137, "total_steps": 190, "loss": 0.0164, "learning_rate": 9.95462442119879e-07, "epoch": 3.5241157556270095, "percentage": 72.11, "elapsed_time": "0:30:04", "remaining_time": "0:11:37", "throughput": "483.29", "total_tokens": 871968}
+{"current_steps": 138, "total_steps": 190, "loss": 0.0018, "learning_rate": 9.608463116858544e-07, "epoch": 3.54983922829582, "percentage": 72.63, "elapsed_time": "0:30:17", "remaining_time": "0:11:24", "throughput": "483.30", "total_tokens": 878352}
+{"current_steps": 139, "total_steps": 190, "loss": 0.0226, "learning_rate": 9.266990223754069e-07, "epoch": 3.57556270096463, "percentage": 73.16, "elapsed_time": "0:30:30", "remaining_time": "0:11:11", "throughput": "483.32", "total_tokens": 884736}
+{"current_steps": 140, "total_steps": 190, "loss": 0.0008, "learning_rate": 8.930309757836517e-07, "epoch": 3.6012861736334405, "percentage": 73.68, "elapsed_time": "0:30:43", "remaining_time": "0:10:58", "throughput": "483.26", "total_tokens": 891008}
+{"current_steps": 141, "total_steps": 190, "loss": 0.0004, "learning_rate": 8.598524275237321e-07, "epoch": 3.627009646302251, "percentage": 74.21, "elapsed_time": "0:30:56", "remaining_time": "0:10:45", "throughput": "483.13", "total_tokens": 897120}
+{"current_steps": 142, "total_steps": 190, "loss": 0.0008, "learning_rate": 8.271734841028553e-07, "epoch": 3.652733118971061, "percentage": 74.74, "elapsed_time": "0:31:10", "remaining_time": "0:10:32", "throughput": "483.16", "total_tokens": 903536}
+{"current_steps": 143, "total_steps": 190, "loss": 0.0256, "learning_rate": 7.950040998437541e-07, "epoch": 3.6784565916398715, "percentage": 75.26, "elapsed_time": "0:31:23", "remaining_time": "0:10:18", "throughput": "483.12", "total_tokens": 909824}
+{"current_steps": 144, "total_steps": 190, "loss": 0.0005, "learning_rate": 7.633540738525066e-07, "epoch": 3.7041800643086815, "percentage": 75.79, "elapsed_time": "0:31:36", "remaining_time": "0:10:05", "throughput": "483.08", "total_tokens": 916112}
+{"current_steps": 145, "total_steps": 190, "loss": 0.0045, "learning_rate": 7.322330470336314e-07, "epoch": 3.729903536977492, "percentage": 76.32, "elapsed_time": "0:31:49", "remaining_time": "0:09:52", "throughput": "483.15", "total_tokens": 922592}
+{"current_steps": 146, "total_steps": 190, "loss": 0.0005, "learning_rate": 7.016504991533727e-07, "epoch": 3.755627009646302, "percentage": 76.84, "elapsed_time": "0:32:02", "remaining_time": "0:09:39", "throughput": "482.98", "total_tokens": 928640}
+{"current_steps": 147, "total_steps": 190, "loss": 0.0069, "learning_rate": 6.716157459520739e-07, "epoch": 3.7813504823151125, "percentage": 77.37, "elapsed_time": "0:32:15", "remaining_time": "0:09:26", "throughput": "483.23", "total_tokens": 935488}
+{"current_steps": 148, "total_steps": 190, "loss": 0.015, "learning_rate": 6.421379363065142e-07, "epoch": 3.807073954983923, "percentage": 77.89, "elapsed_time": "0:32:29", "remaining_time": "0:09:13", "throughput": "483.29", "total_tokens": 941952}
+{"current_steps": 149, "total_steps": 190, "loss": 0.0012, "learning_rate": 6.1322604944307e-07, "epoch": 3.832797427652733, "percentage": 78.42, "elapsed_time": "0:32:42", "remaining_time": "0:08:59", "throughput": "483.32", "total_tokens": 948368}
+{"current_steps": 150, "total_steps": 190, "loss": 0.0095, "learning_rate": 5.848888922025553e-07, "epoch": 3.8585209003215435, "percentage": 78.95, "elapsed_time": "0:32:55", "remaining_time": "0:08:46", "throughput": "483.33", "total_tokens": 954752}
+{"current_steps": 151, "total_steps": 190, "loss": 0.0271, "learning_rate": 5.571350963575728e-07, "epoch": 3.884244372990354, "percentage": 79.47, "elapsed_time": "0:33:08", "remaining_time": "0:08:33", "throughput": "483.39", "total_tokens": 961248}
+{"current_steps": 152, "total_steps": 190, "loss": 0.0201, "learning_rate": 5.299731159831953e-07, "epoch": 3.909967845659164, "percentage": 80.0, "elapsed_time": "0:33:21", "remaining_time": "0:08:20", "throughput": "483.30", "total_tokens": 967424}
+{"current_steps": 153, "total_steps": 190, "loss": 0.012, "learning_rate": 5.034112248817685e-07, "epoch": 3.935691318327974, "percentage": 80.53, "elapsed_time": "0:33:34", "remaining_time": "0:08:07", "throughput": "483.25", "total_tokens": 973696}
+{"current_steps": 154, "total_steps": 190, "loss": 0.023, "learning_rate": 4.774575140626317e-07, "epoch": 3.9614147909967845, "percentage": 81.05, "elapsed_time": "0:33:48", "remaining_time": "0:07:54", "throughput": "483.29", "total_tokens": 980144}
+{"current_steps": 155, "total_steps": 190, "loss": 0.0156, "learning_rate": 4.5211988927752026e-07, "epoch": 3.987138263665595, "percentage": 81.58, "elapsed_time": "0:34:01", "remaining_time": "0:07:40", "throughput": "483.22", "total_tokens": 986352}
+{"current_steps": 156, "total_steps": 190, "loss": 0.0009, "learning_rate": 4.27406068612396e-07, "epoch": 4.012861736334405, "percentage": 82.11, "elapsed_time": "0:34:14", "remaining_time": "0:07:27", "throughput": "483.29", "total_tokens": 992880}
+{"current_steps": 157, "total_steps": 190, "loss": 0.0017, "learning_rate": 4.033235801364402e-07, "epoch": 4.038585209003215, "percentage": 82.63, "elapsed_time": "0:34:27", "remaining_time": "0:07:14", "throughput": "483.27", "total_tokens": 999200}
+{"current_steps": 158, "total_steps": 190, "loss": 0.0015, "learning_rate": 3.798797596089351e-07, "epoch": 4.064308681672026, "percentage": 83.16, "elapsed_time": "0:34:40", "remaining_time": "0:07:01", "throughput": "483.28", "total_tokens": 1005568}
+{"current_steps": 159, "total_steps": 190, "loss": 0.0035, "learning_rate": 3.5708174824471947e-07, "epoch": 4.090032154340836, "percentage": 83.68, "elapsed_time": "0:34:53", "remaining_time": "0:06:48", "throughput": "483.18", "total_tokens": 1011728}
+{"current_steps": 160, "total_steps": 190, "loss": 0.0016, "learning_rate": 3.3493649053890325e-07, "epoch": 4.115755627009646, "percentage": 84.21, "elapsed_time": "0:35:07", "remaining_time": "0:06:35", "throughput": "483.27", "total_tokens": 1018272}
+{"current_steps": 161, "total_steps": 190, "loss": 0.0028, "learning_rate": 3.134507321515107e-07, "epoch": 4.141479099678457, "percentage": 84.74, "elapsed_time": "0:35:20", "remaining_time": "0:06:21", "throughput": "483.30", "total_tokens": 1024688}
+{"current_steps": 162, "total_steps": 190, "loss": 0.0006, "learning_rate": 2.9263101785268253e-07, "epoch": 4.167202572347267, "percentage": 85.26, "elapsed_time": "0:35:33", "remaining_time": "0:06:08", "throughput": "483.34", "total_tokens": 1031152}
+{"current_steps": 163, "total_steps": 190, "loss": 0.0013, "learning_rate": 2.7248368952908055e-07, "epoch": 4.192926045016077, "percentage": 85.79, "elapsed_time": "0:35:46", "remaining_time": "0:05:55", "throughput": "483.39", "total_tokens": 1037632}
+{"current_steps": 164, "total_steps": 190, "loss": 0.0006, "learning_rate": 2.53014884252083e-07, "epoch": 4.218649517684887, "percentage": 86.32, "elapsed_time": "0:35:59", "remaining_time": "0:05:42", "throughput": "483.37", "total_tokens": 1043936}
+{"current_steps": 165, "total_steps": 190, "loss": 0.0017, "learning_rate": 2.3423053240837518e-07, "epoch": 4.244372990353698, "percentage": 86.84, "elapsed_time": "0:36:12", "remaining_time": "0:05:29", "throughput": "483.25", "total_tokens": 1050048}
+{"current_steps": 166, "total_steps": 190, "loss": 0.0004, "learning_rate": 2.1613635589349756e-07, "epoch": 4.270096463022508, "percentage": 87.37, "elapsed_time": "0:36:26", "remaining_time": "0:05:16", "throughput": "483.29", "total_tokens": 1056496}
+{"current_steps": 167, "total_steps": 190, "loss": 0.0049, "learning_rate": 1.9873786636889908e-07, "epoch": 4.295819935691318, "percentage": 87.89, "elapsed_time": "0:36:39", "remaining_time": "0:05:02", "throughput": "483.28", "total_tokens": 1062848}
+{"current_steps": 168, "total_steps": 190, "loss": 0.0071, "learning_rate": 1.8204036358303173e-07, "epoch": 4.321543408360129, "percentage": 88.42, "elapsed_time": "0:36:52", "remaining_time": "0:04:49", "throughput": "483.25", "total_tokens": 1069136}
+{"current_steps": 169, "total_steps": 190, "loss": 0.0011, "learning_rate": 1.6604893375699594e-07, "epoch": 4.347266881028939, "percentage": 88.95, "elapsed_time": "0:37:05", "remaining_time": "0:04:36", "throughput": "483.17", "total_tokens": 1075328}
+{"current_steps": 170, "total_steps": 190, "loss": 0.0004, "learning_rate": 1.507684480352292e-07, "epoch": 4.372990353697749, "percentage": 89.47, "elapsed_time": "0:37:18", "remaining_time": "0:04:23", "throughput": "483.17", "total_tokens": 1081696}
+{"current_steps": 171, "total_steps": 190, "loss": 0.0007, "learning_rate": 1.362035610017079e-07, "epoch": 4.39871382636656, "percentage": 90.0, "elapsed_time": "0:37:31", "remaining_time": "0:04:10", "throughput": "483.20", "total_tokens": 1088112}
+{"current_steps": 172, "total_steps": 190, "loss": 0.0017, "learning_rate": 1.223587092621162e-07, "epoch": 4.42443729903537, "percentage": 90.53, "elapsed_time": "0:37:45", "remaining_time": "0:03:57", "throughput": "483.21", "total_tokens": 1094512}
+{"current_steps": 173, "total_steps": 190, "loss": 0.0007, "learning_rate": 1.0923811009241142e-07, "epoch": 4.45016077170418, "percentage": 91.05, "elapsed_time": "0:37:58", "remaining_time": "0:03:43", "throughput": "483.29", "total_tokens": 1101040}
+{"current_steps": 174, "total_steps": 190, "loss": 0.0003, "learning_rate": 9.684576015420277e-08, "epoch": 4.47588424437299, "percentage": 91.58, "elapsed_time": "0:38:11", "remaining_time": "0:03:30", "throughput": "483.18", "total_tokens": 1107168}
+{"current_steps": 175, "total_steps": 190, "loss": 0.0046, "learning_rate": 8.518543427732951e-08, "epoch": 4.501607717041801, "percentage": 92.11, "elapsed_time": "0:38:24", "remaining_time": "0:03:17", "throughput": "483.13", "total_tokens": 1113408}
+{"current_steps": 176, "total_steps": 190, "loss": 0.0038, "learning_rate": 7.426068431000883e-08, "epoch": 4.527331189710611, "percentage": 92.63, "elapsed_time": "0:38:37", "remaining_time": "0:03:04", "throughput": "483.04", "total_tokens": 1119568}
+{"current_steps": 177, "total_steps": 190, "loss": 0.0036, "learning_rate": 6.407483803691216e-08, "epoch": 4.553054662379421, "percentage": 93.16, "elapsed_time": "0:38:50", "remaining_time": "0:02:51", "throughput": "483.09", "total_tokens": 1126048}
+{"current_steps": 178, "total_steps": 190, "loss": 0.0056, "learning_rate": 5.463099816548578e-08, "epoch": 4.578778135048232, "percentage": 93.68, "elapsed_time": "0:39:04", "remaining_time": "0:02:38", "throughput": "483.09", "total_tokens": 1132400}
+{"current_steps": 179, "total_steps": 190, "loss": 0.0057, "learning_rate": 4.593204138084006e-08, "epoch": 4.604501607717042, "percentage": 94.21, "elapsed_time": "0:39:17", "remaining_time": "0:02:24", "throughput": "483.12", "total_tokens": 1138832}
+{"current_steps": 180, "total_steps": 190, "loss": 0.002, "learning_rate": 3.798061746947995e-08, "epoch": 4.630225080385852, "percentage": 94.74, "elapsed_time": "0:39:30", "remaining_time": "0:02:11", "throughput": "483.19", "total_tokens": 1145344}
+{"current_steps": 181, "total_steps": 190, "loss": 0.0003, "learning_rate": 3.077914851215585e-08, "epoch": 4.655948553054662, "percentage": 95.26, "elapsed_time": "0:39:43", "remaining_time": "0:01:58", "throughput": "483.12", "total_tokens": 1151536}
+{"current_steps": 182, "total_steps": 190, "loss": 0.0002, "learning_rate": 2.4329828146074096e-08, "epoch": 4.681672025723473, "percentage": 95.79, "elapsed_time": "0:39:56", "remaining_time": "0:01:45", "throughput": "483.03", "total_tokens": 1157696}
+{"current_steps": 183, "total_steps": 190, "loss": 0.0043, "learning_rate": 1.8634620896695044e-08, "epoch": 4.707395498392283, "percentage": 96.32, "elapsed_time": "0:40:09", "remaining_time": "0:01:32", "throughput": "482.89", "total_tokens": 1163712}
+{"current_steps": 184, "total_steps": 190, "loss": 0.0002, "learning_rate": 1.3695261579316776e-08, "epoch": 4.733118971061093, "percentage": 96.84, "elapsed_time": "0:40:23", "remaining_time": "0:01:19", "throughput": "482.81", "total_tokens": 1169888}
+{"current_steps": 185, "total_steps": 190, "loss": 0.0013, "learning_rate": 9.513254770636138e-09, "epoch": 4.758842443729904, "percentage": 97.37, "elapsed_time": "0:40:36", "remaining_time": "0:01:05", "throughput": "482.82", "total_tokens": 1176272}
+{"current_steps": 186, "total_steps": 190, "loss": 0.0023, "learning_rate": 6.089874350439507e-09, "epoch": 4.784565916398714, "percentage": 97.89, "elapsed_time": "0:40:49", "remaining_time": "0:00:52", "throughput": "482.85", "total_tokens": 1182688}
+{"current_steps": 187, "total_steps": 190, "loss": 0.0002, "learning_rate": 3.4261631135654174e-09, "epoch": 4.810289389067524, "percentage": 98.42, "elapsed_time": "0:41:02", "remaining_time": "0:00:39", "throughput": "482.98", "total_tokens": 1189360}
+{"current_steps": 188, "total_steps": 190, "loss": 0.0015, "learning_rate": 1.5229324522605949e-09, "epoch": 4.836012861736334, "percentage": 98.95, "elapsed_time": "0:41:15", "remaining_time": "0:00:26", "throughput": "482.95", "total_tokens": 1195632}
+{"current_steps": 189, "total_steps": 190, "loss": 0.0002, "learning_rate": 3.8076210902182607e-10, "epoch": 4.861736334405145, "percentage": 99.47, "elapsed_time": "0:41:28", "remaining_time": "0:00:13", "throughput": "482.96", "total_tokens": 1202016}
+{"current_steps": 190, "total_steps": 190, "loss": 0.0028, "learning_rate": 0.0, "epoch": 4.887459807073955, "percentage": 100.0, "elapsed_time": "0:41:42", "remaining_time": "0:00:00", "throughput": "482.97", "total_tokens": 1208400}
+{"current_steps": 190, "total_steps": 190, "epoch": 4.887459807073955, "percentage": 100.0, "elapsed_time": "0:42:42", "remaining_time": "0:00:00", "throughput": "471.54", "total_tokens": 1208400}

trainer_state.json

@@ -0,0 +1,1563 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.887459807073955,
+  "eval_steps": 500,
+  "global_step": 190,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02572347266881029,
+      "grad_norm": 612.1110229492188,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 14.1364,
+      "num_input_tokens_seen": 6512,
+      "step": 1
+    },
+    {
+      "epoch": 0.05144694533762058,
+      "grad_norm": 608.3916625976562,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 13.7804,
+      "num_input_tokens_seen": 12848,
+      "step": 2
+    },
+    {
+      "epoch": 0.07717041800643087,
+      "grad_norm": 622.3192138671875,
+      "learning_rate": 1.5e-06,
+      "loss": 13.4871,
+      "num_input_tokens_seen": 19248,
+      "step": 3
+    },
+    {
+      "epoch": 0.10289389067524116,
+      "grad_norm": 611.6488647460938,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 12.79,
+      "num_input_tokens_seen": 25344,
+      "step": 4
+    },
+    {
+      "epoch": 0.12861736334405144,
+      "grad_norm": 508.9140319824219,
+      "learning_rate": 2.5e-06,
+      "loss": 9.2748,
+      "num_input_tokens_seen": 31968,
+      "step": 5
+    },
+    {
+      "epoch": 0.15434083601286175,
+      "grad_norm": 630.509521484375,
+      "learning_rate": 3e-06,
+      "loss": 6.5585,
+      "num_input_tokens_seen": 38160,
+      "step": 6
+    },
+    {
+      "epoch": 0.18006430868167203,
+      "grad_norm": 512.7638549804688,
+      "learning_rate": 3.5e-06,
+      "loss": 5.3984,
+      "num_input_tokens_seen": 44144,
+      "step": 7
+    },
+    {
+      "epoch": 0.2057877813504823,
+      "grad_norm": 220.47471618652344,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.9363,
+      "num_input_tokens_seen": 50432,
+      "step": 8
+    },
+    {
+      "epoch": 0.2315112540192926,
+      "grad_norm": 114.83863830566406,
+      "learning_rate": 4.5e-06,
+      "loss": 0.6783,
+      "num_input_tokens_seen": 56928,
+      "step": 9
+    },
+    {
+      "epoch": 0.2572347266881029,
+      "grad_norm": 383.7873229980469,
+      "learning_rate": 5e-06,
+      "loss": 2.9945,
+      "num_input_tokens_seen": 63344,
+      "step": 10
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 53.58182907104492,
+      "learning_rate": 4.9996192378909785e-06,
+      "loss": 0.2916,
+      "num_input_tokens_seen": 69568,
+      "step": 11
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 200.5736083984375,
+      "learning_rate": 4.99847706754774e-06,
+      "loss": 2.2775,
+      "num_input_tokens_seen": 75824,
+      "step": 12
+    },
+    {
+      "epoch": 0.33440514469453375,
+      "grad_norm": 89.13434600830078,
+      "learning_rate": 4.9965738368864345e-06,
+      "loss": 0.3757,
+      "num_input_tokens_seen": 82160,
+      "step": 13
+    },
+    {
+      "epoch": 0.36012861736334406,
+      "grad_norm": 149.89199829101562,
+      "learning_rate": 4.993910125649561e-06,
+      "loss": 1.9543,
+      "num_input_tokens_seen": 88624,
+      "step": 14
+    },
+    {
+      "epoch": 0.3858520900321543,
+      "grad_norm": 93.02680206298828,
+      "learning_rate": 4.990486745229364e-06,
+      "loss": 0.7398,
+      "num_input_tokens_seen": 94800,
+      "step": 15
+    },
+    {
+      "epoch": 0.4115755627009646,
+      "grad_norm": 274.1518249511719,
+      "learning_rate": 4.986304738420684e-06,
+      "loss": 1.1868,
+      "num_input_tokens_seen": 101360,
+      "step": 16
+    },
+    {
+      "epoch": 0.43729903536977494,
+      "grad_norm": 75.59544372558594,
+      "learning_rate": 4.981365379103306e-06,
+      "loss": 0.5418,
+      "num_input_tokens_seen": 107488,
+      "step": 17
+    },
+    {
+      "epoch": 0.4630225080385852,
+      "grad_norm": 21.915510177612305,
+      "learning_rate": 4.975670171853926e-06,
+      "loss": 0.2263,
+      "num_input_tokens_seen": 113920,
+      "step": 18
+    },
+    {
+      "epoch": 0.4887459807073955,
+      "grad_norm": 12.356107711791992,
+      "learning_rate": 4.9692208514878445e-06,
+      "loss": 0.1612,
+      "num_input_tokens_seen": 120352,
+      "step": 19
+    },
+    {
+      "epoch": 0.5144694533762058,
+      "grad_norm": 49.00923538208008,
+      "learning_rate": 4.962019382530521e-06,
+      "loss": 0.3299,
+      "num_input_tokens_seen": 126880,
+      "step": 20
+    },
+    {
+      "epoch": 0.5401929260450161,
+      "grad_norm": 35.158695220947266,
+      "learning_rate": 4.9540679586191605e-06,
+      "loss": 0.2013,
+      "num_input_tokens_seen": 133344,
+      "step": 21
+    },
+    {
+      "epoch": 0.5659163987138264,
+      "grad_norm": 30.501089096069336,
+      "learning_rate": 4.9453690018345144e-06,
+      "loss": 0.2446,
+      "num_input_tokens_seen": 139744,
+      "step": 22
+    },
+    {
+      "epoch": 0.5916398713826366,
+      "grad_norm": 29.609901428222656,
+      "learning_rate": 4.935925161963089e-06,
+      "loss": 0.2235,
+      "num_input_tokens_seen": 146144,
+      "step": 23
+    },
+    {
+      "epoch": 0.617363344051447,
+      "grad_norm": 7.487663745880127,
+      "learning_rate": 4.925739315689991e-06,
+      "loss": 0.116,
+      "num_input_tokens_seen": 152240,
+      "step": 24
+    },
+    {
+      "epoch": 0.6430868167202572,
+      "grad_norm": 37.3343620300293,
+      "learning_rate": 4.914814565722671e-06,
+      "loss": 0.2179,
+      "num_input_tokens_seen": 158512,
+      "step": 25
+    },
+    {
+      "epoch": 0.6688102893890675,
+      "grad_norm": 19.37504768371582,
+      "learning_rate": 4.903154239845798e-06,
+      "loss": 0.1414,
+      "num_input_tokens_seen": 164784,
+      "step": 26
+    },
+    {
+      "epoch": 0.6945337620578779,
+      "grad_norm": 7.562462329864502,
+      "learning_rate": 4.890761889907589e-06,
+      "loss": 0.1181,
+      "num_input_tokens_seen": 171312,
+      "step": 27
+    },
+    {
+      "epoch": 0.7202572347266881,
+      "grad_norm": 45.42784881591797,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.2753,
+      "num_input_tokens_seen": 177856,
+      "step": 28
+    },
+    {
+      "epoch": 0.7459807073954984,
+      "grad_norm": 42.35463333129883,
+      "learning_rate": 4.863796438998293e-06,
+      "loss": 0.3255,
+      "num_input_tokens_seen": 184368,
+      "step": 29
+    },
+    {
+      "epoch": 0.7717041800643086,
+      "grad_norm": 29.56382179260254,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 0.2352,
+      "num_input_tokens_seen": 190928,
+      "step": 30
+    },
+    {
+      "epoch": 0.797427652733119,
+      "grad_norm": 10.221027374267578,
+      "learning_rate": 4.833951066243004e-06,
+      "loss": 0.063,
+      "num_input_tokens_seen": 197232,
+      "step": 31
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 19.372211456298828,
+      "learning_rate": 4.817959636416969e-06,
+      "loss": 0.2042,
+      "num_input_tokens_seen": 203584,
+      "step": 32
+    },
+    {
+      "epoch": 0.8488745980707395,
+      "grad_norm": 15.362005233764648,
+      "learning_rate": 4.801262133631101e-06,
+      "loss": 0.1364,
+      "num_input_tokens_seen": 210128,
+      "step": 33
+    },
+    {
+      "epoch": 0.8745980707395499,
+      "grad_norm": 17.515932083129883,
+      "learning_rate": 4.783863644106502e-06,
+      "loss": 0.0934,
+      "num_input_tokens_seen": 216512,
+      "step": 34
+    },
+    {
+      "epoch": 0.9003215434083601,
+      "grad_norm": 10.493622779846191,
+      "learning_rate": 4.765769467591626e-06,
+      "loss": 0.1332,
+      "num_input_tokens_seen": 222928,
+      "step": 35
+    },
+    {
+      "epoch": 0.9260450160771704,
+      "grad_norm": 21.616741180419922,
+      "learning_rate": 4.746985115747918e-06,
+      "loss": 0.1595,
+      "num_input_tokens_seen": 229232,
+      "step": 36
+    },
+    {
+      "epoch": 0.9517684887459807,
+      "grad_norm": 18.24679946899414,
+      "learning_rate": 4.72751631047092e-06,
+      "loss": 0.1528,
+      "num_input_tokens_seen": 235680,
+      "step": 37
+    },
+    {
+      "epoch": 0.977491961414791,
+      "grad_norm": 8.862295150756836,
+      "learning_rate": 4.707368982147318e-06,
+      "loss": 0.1342,
+      "num_input_tokens_seen": 242192,
+      "step": 38
+    },
+    {
+      "epoch": 1.0032154340836013,
+      "grad_norm": 25.429838180541992,
+      "learning_rate": 4.68654926784849e-06,
+      "loss": 0.1586,
+      "num_input_tokens_seen": 248672,
+      "step": 39
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "grad_norm": 9.540814399719238,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 0.1072,
+      "num_input_tokens_seen": 255072,
+      "step": 40
+    },
+    {
+      "epoch": 1.0546623794212218,
+      "grad_norm": 3.9775660037994385,
+      "learning_rate": 4.642918251755281e-06,
+      "loss": 0.0357,
+      "num_input_tokens_seen": 261584,
+      "step": 41
+    },
+    {
+      "epoch": 1.0803858520900322,
+      "grad_norm": 8.192290306091309,
+      "learning_rate": 4.620120240391065e-06,
+      "loss": 0.06,
+      "num_input_tokens_seen": 268032,
+      "step": 42
+    },
+    {
+      "epoch": 1.1061093247588425,
+      "grad_norm": 6.468256950378418,
+      "learning_rate": 4.596676419863561e-06,
+      "loss": 0.0902,
+      "num_input_tokens_seen": 274560,
+      "step": 43
+    },
+    {
+      "epoch": 1.1318327974276527,
+      "grad_norm": 4.978611469268799,
+      "learning_rate": 4.572593931387604e-06,
+      "loss": 0.0202,
+      "num_input_tokens_seen": 280960,
+      "step": 44
+    },
+    {
+      "epoch": 1.157556270096463,
+      "grad_norm": 7.448028564453125,
+      "learning_rate": 4.54788011072248e-06,
+      "loss": 0.038,
+      "num_input_tokens_seen": 287104,
+      "step": 45
+    },
+    {
+      "epoch": 1.1832797427652733,
+      "grad_norm": 10.028037071228027,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.0379,
+      "num_input_tokens_seen": 293520,
+      "step": 46
+    },
+    {
+      "epoch": 1.2090032154340835,
+      "grad_norm": 13.968883514404297,
+      "learning_rate": 4.496588775118232e-06,
+      "loss": 0.0742,
+      "num_input_tokens_seen": 299936,
+      "step": 47
+    },
+    {
+      "epoch": 1.234726688102894,
+      "grad_norm": 8.629486083984375,
+      "learning_rate": 4.470026884016805e-06,
+      "loss": 0.0658,
+      "num_input_tokens_seen": 305936,
+      "step": 48
+    },
+    {
+      "epoch": 1.2604501607717042,
+      "grad_norm": 11.009612083435059,
+      "learning_rate": 4.442864903642428e-06,
+      "loss": 0.0336,
+      "num_input_tokens_seen": 312528,
+      "step": 49
+    },
+    {
+      "epoch": 1.2861736334405145,
+      "grad_norm": 7.794949531555176,
+      "learning_rate": 4.415111107797445e-06,
+      "loss": 0.1021,
+      "num_input_tokens_seen": 318752,
+      "step": 50
+    },
+    {
+      "epoch": 1.3118971061093248,
+      "grad_norm": 12.327733039855957,
+      "learning_rate": 4.386773950556931e-06,
+      "loss": 0.1312,
+      "num_input_tokens_seen": 325088,
+      "step": 51
+    },
+    {
+      "epoch": 1.337620578778135,
+      "grad_norm": 8.146430969238281,
+      "learning_rate": 4.357862063693486e-06,
+      "loss": 0.0665,
+      "num_input_tokens_seen": 331424,
+      "step": 52
+    },
+    {
+      "epoch": 1.3633440514469453,
+      "grad_norm": 6.919386386871338,
+      "learning_rate": 4.328384254047927e-06,
+      "loss": 0.0679,
+      "num_input_tokens_seen": 337776,
+      "step": 53
+    },
+    {
+      "epoch": 1.3890675241157555,
+      "grad_norm": 2.923135280609131,
+      "learning_rate": 4.2983495008466285e-06,
+      "loss": 0.0579,
+      "num_input_tokens_seen": 344000,
+      "step": 54
+    },
+    {
+      "epoch": 1.414790996784566,
+      "grad_norm": 5.682593822479248,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.0542,
+      "num_input_tokens_seen": 350528,
+      "step": 55
+    },
+    {
+      "epoch": 1.4405144694533762,
+      "grad_norm": 5.936847686767578,
+      "learning_rate": 4.236645926147493e-06,
+      "loss": 0.0476,
+      "num_input_tokens_seen": 356896,
+      "step": 56
+    },
+    {
+      "epoch": 1.4662379421221865,
+      "grad_norm": 3.671848773956299,
+      "learning_rate": 4.204995900156247e-06,
+      "loss": 0.0613,
+      "num_input_tokens_seen": 363376,
+      "step": 57
+    },
+    {
+      "epoch": 1.4919614147909968,
+      "grad_norm": 6.306807994842529,
+      "learning_rate": 4.172826515897146e-06,
+      "loss": 0.0995,
+      "num_input_tokens_seen": 369680,
+      "step": 58
+    },
+    {
+      "epoch": 1.517684887459807,
+      "grad_norm": 7.488581657409668,
+      "learning_rate": 4.140147572476269e-06,
+      "loss": 0.0532,
+      "num_input_tokens_seen": 375904,
+      "step": 59
+    },
+    {
+      "epoch": 1.5434083601286175,
+      "grad_norm": 8.461729049682617,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 0.0824,
+      "num_input_tokens_seen": 382304,
+      "step": 60
+    },
+    {
+      "epoch": 1.5691318327974275,
+      "grad_norm": 4.186163902282715,
+      "learning_rate": 4.073300977624594e-06,
+      "loss": 0.0499,
+      "num_input_tokens_seen": 388688,
+      "step": 61
+    },
+    {
+      "epoch": 1.594855305466238,
+      "grad_norm": 4.451269149780273,
+      "learning_rate": 4.039153688314146e-06,
+      "loss": 0.0413,
+      "num_input_tokens_seen": 395152,
+      "step": 62
+    },
+    {
+      "epoch": 1.6205787781350482,
+      "grad_norm": 7.160181999206543,
+      "learning_rate": 4.0045375578801216e-06,
+      "loss": 0.0637,
+      "num_input_tokens_seen": 401728,
+      "step": 63
+    },
+    {
+      "epoch": 1.6463022508038585,
+      "grad_norm": 8.231119155883789,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.0529,
+      "num_input_tokens_seen": 407904,
+      "step": 64
+    },
+    {
+      "epoch": 1.6720257234726688,
+      "grad_norm": 5.919021129608154,
+      "learning_rate": 3.933941090877615e-06,
+      "loss": 0.0474,
+      "num_input_tokens_seen": 414240,
+      "step": 65
+    },
+    {
+      "epoch": 1.697749196141479,
+      "grad_norm": 5.378300189971924,
+      "learning_rate": 3.897982258676867e-06,
+      "loss": 0.0649,
+      "num_input_tokens_seen": 420448,
+      "step": 66
+    },
+    {
+      "epoch": 1.7234726688102895,
+      "grad_norm": 9.992879867553711,
+      "learning_rate": 3.861597587537568e-06,
+      "loss": 0.0505,
+      "num_input_tokens_seen": 426784,
+      "step": 67
+    },
+    {
+      "epoch": 1.7491961414790995,
+      "grad_norm": 5.876017093658447,
+      "learning_rate": 3.824798160583012e-06,
+      "loss": 0.0621,
+      "num_input_tokens_seen": 432816,
+      "step": 68
+    },
+    {
+      "epoch": 1.77491961414791,
+      "grad_norm": 8.401307106018066,
+      "learning_rate": 3.787595187275136e-06,
+      "loss": 0.0769,
+      "num_input_tokens_seen": 439232,
+      "step": 69
+    },
+    {
+      "epoch": 1.8006430868167203,
+      "grad_norm": 8.439587593078613,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0435,
+      "num_input_tokens_seen": 445792,
+      "step": 70
+    },
+    {
+      "epoch": 1.8263665594855305,
+      "grad_norm": 6.123202323913574,
+      "learning_rate": 3.7120240506158433e-06,
+      "loss": 0.0673,
+      "num_input_tokens_seen": 452400,
+      "step": 71
+    },
+    {
+      "epoch": 1.852090032154341,
+      "grad_norm": 12.049100875854492,
+      "learning_rate": 3.6736789069647273e-06,
+      "loss": 0.1316,
+      "num_input_tokens_seen": 458528,
+      "step": 72
+    },
+    {
+      "epoch": 1.877813504823151,
+      "grad_norm": 6.853906631469727,
+      "learning_rate": 3.634976249348867e-06,
+      "loss": 0.0531,
+      "num_input_tokens_seen": 464976,
+      "step": 73
+    },
+    {
+      "epoch": 1.9035369774919615,
+      "grad_norm": 3.6796371936798096,
+      "learning_rate": 3.595927866972694e-06,
+      "loss": 0.0287,
+      "num_input_tokens_seen": 471440,
+      "step": 74
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "grad_norm": 11.764636039733887,
+      "learning_rate": 3.556545654351749e-06,
+      "loss": 0.0648,
+      "num_input_tokens_seen": 477776,
+      "step": 75
+    },
+    {
+      "epoch": 1.954983922829582,
+      "grad_norm": 15.143081665039062,
+      "learning_rate": 3.516841607689501e-06,
+      "loss": 0.1211,
+      "num_input_tokens_seen": 484096,
+      "step": 76
+    },
+    {
+      "epoch": 1.9807073954983923,
+      "grad_norm": 13.158181190490723,
+      "learning_rate": 3.476827821223184e-06,
+      "loss": 0.0879,
+      "num_input_tokens_seen": 490176,
+      "step": 77
+    },
+    {
+      "epoch": 2.0064308681672025,
+      "grad_norm": 5.389456748962402,
+      "learning_rate": 3.436516483539781e-06,
+      "loss": 0.0227,
+      "num_input_tokens_seen": 496672,
+      "step": 78
+    },
+    {
+      "epoch": 2.032154340836013,
+      "grad_norm": 1.3878227472305298,
+      "learning_rate": 3.39591987386325e-06,
+      "loss": 0.0228,
+      "num_input_tokens_seen": 503088,
+      "step": 79
+    },
+    {
+      "epoch": 2.057877813504823,
+      "grad_norm": 4.809704303741455,
+      "learning_rate": 3.3550503583141726e-06,
+      "loss": 0.036,
+      "num_input_tokens_seen": 509472,
+      "step": 80
+    },
+    {
+      "epoch": 2.0836012861736335,
+      "grad_norm": 4.475839614868164,
+      "learning_rate": 3.313920386142892e-06,
+      "loss": 0.0138,
+      "num_input_tokens_seen": 515728,
+      "step": 81
+    },
+    {
+      "epoch": 2.1093247588424435,
+      "grad_norm": 9.445964813232422,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.0697,
+      "num_input_tokens_seen": 521904,
+      "step": 82
+    },
+    {
+      "epoch": 2.135048231511254,
+      "grad_norm": 5.295349597930908,
+      "learning_rate": 3.230929261806842e-06,
+      "loss": 0.0508,
+      "num_input_tokens_seen": 527952,
+      "step": 83
+    },
+    {
+      "epoch": 2.1607717041800645,
+      "grad_norm": 5.535093307495117,
+      "learning_rate": 3.189093389542498e-06,
+      "loss": 0.0088,
+      "num_input_tokens_seen": 534624,
+      "step": 84
+    },
+    {
+      "epoch": 2.1864951768488745,
+      "grad_norm": 1.4181060791015625,
+      "learning_rate": 3.147047612756302e-06,
+      "loss": 0.0158,
+      "num_input_tokens_seen": 541168,
+      "step": 85
+    },
+    {
+      "epoch": 2.212218649517685,
+      "grad_norm": 4.84325647354126,
+      "learning_rate": 3.1048047389991693e-06,
+      "loss": 0.006,
+      "num_input_tokens_seen": 547488,
+      "step": 86
+    },
+    {
+      "epoch": 2.237942122186495,
+      "grad_norm": 7.397033214569092,
+      "learning_rate": 3.062377635859663e-06,
+      "loss": 0.038,
+      "num_input_tokens_seen": 554272,
+      "step": 87
+    },
+    {
+      "epoch": 2.2636655948553055,
+      "grad_norm": 0.08836190402507782,
+      "learning_rate": 3.019779227044398e-06,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 560528,
+      "step": 88
+    },
+    {
+      "epoch": 2.289389067524116,
+      "grad_norm": 2.0779523849487305,
+      "learning_rate": 2.9770224884413625e-06,
+      "loss": 0.0111,
+      "num_input_tokens_seen": 566784,
+      "step": 89
+    },
+    {
+      "epoch": 2.315112540192926,
+      "grad_norm": 1.6369861364364624,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 0.0008,
+      "num_input_tokens_seen": 573344,
+      "step": 90
+    },
+    {
+      "epoch": 2.3408360128617365,
+      "grad_norm": 4.53826904296875,
+      "learning_rate": 2.8910861626005774e-06,
+      "loss": 0.0182,
+      "num_input_tokens_seen": 579776,
+      "step": 91
+    },
+    {
+      "epoch": 2.3665594855305465,
+      "grad_norm": 5.374476909637451,
+      "learning_rate": 2.847932752400164e-06,
+      "loss": 0.0491,
+      "num_input_tokens_seen": 586096,
+      "step": 92
+    },
+    {
+      "epoch": 2.392282958199357,
+      "grad_norm": 1.1637392044067383,
+      "learning_rate": 2.804673358512869e-06,
+      "loss": 0.004,
+      "num_input_tokens_seen": 592528,
+      "step": 93
+    },
+    {
+      "epoch": 2.418006430868167,
+      "grad_norm": 1.8136231899261475,
+      "learning_rate": 2.761321158169134e-06,
+      "loss": 0.0176,
+      "num_input_tokens_seen": 598960,
+      "step": 94
+    },
+    {
+      "epoch": 2.4437299035369775,
+      "grad_norm": 11.001687049865723,
+      "learning_rate": 2.717889356869146e-06,
+      "loss": 0.019,
+      "num_input_tokens_seen": 605232,
+      "step": 95
+    },
+    {
+      "epoch": 2.469453376205788,
+      "grad_norm": 4.748091697692871,
+      "learning_rate": 2.6743911843603134e-06,
+      "loss": 0.027,
+      "num_input_tokens_seen": 611344,
+      "step": 96
+    },
+    {
+      "epoch": 2.495176848874598,
+      "grad_norm": 4.990153789520264,
+      "learning_rate": 2.6308398906073603e-06,
+      "loss": 0.0354,
+      "num_input_tokens_seen": 617712,
+      "step": 97
+    },
+    {
+      "epoch": 2.5209003215434085,
+      "grad_norm": 10.616851806640625,
+      "learning_rate": 2.587248741756253e-06,
+      "loss": 0.0741,
+      "num_input_tokens_seen": 624208,
+      "step": 98
+    },
+    {
+      "epoch": 2.5466237942122185,
+      "grad_norm": 6.855626106262207,
+      "learning_rate": 2.543631016093209e-06,
+      "loss": 0.0582,
+      "num_input_tokens_seen": 630496,
+      "step": 99
+    },
+    {
+      "epoch": 2.572347266881029,
+      "grad_norm": 4.2168426513671875,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0096,
+      "num_input_tokens_seen": 637040,
+      "step": 100
+    },
+    {
+      "epoch": 2.598070739549839,
+      "grad_norm": 6.813520908355713,
+      "learning_rate": 2.4563689839067913e-06,
+      "loss": 0.0263,
+      "num_input_tokens_seen": 643472,
+      "step": 101
+    },
+    {
+      "epoch": 2.6237942122186495,
+      "grad_norm": 0.9154559373855591,
+      "learning_rate": 2.4127512582437486e-06,
+      "loss": 0.0121,
+      "num_input_tokens_seen": 649760,
+      "step": 102
+    },
+    {
+      "epoch": 2.64951768488746,
+      "grad_norm": 6.223565101623535,
+      "learning_rate": 2.3691601093926406e-06,
+      "loss": 0.0204,
+      "num_input_tokens_seen": 656096,
+      "step": 103
+    },
+    {
+      "epoch": 2.67524115755627,
+      "grad_norm": 2.3013968467712402,
+      "learning_rate": 2.325608815639687e-06,
+      "loss": 0.0325,
+      "num_input_tokens_seen": 662624,
+      "step": 104
+    },
+    {
+      "epoch": 2.7009646302250805,
+      "grad_norm": 2.195141077041626,
+      "learning_rate": 2.2821106431308546e-06,
+      "loss": 0.0076,
+      "num_input_tokens_seen": 668768,
+      "step": 105
+    },
+    {
+      "epoch": 2.7266881028938905,
+      "grad_norm": 14.679264068603516,
+      "learning_rate": 2.238678841830867e-06,
+      "loss": 0.0485,
+      "num_input_tokens_seen": 674992,
+      "step": 106
+    },
+    {
+      "epoch": 2.752411575562701,
+      "grad_norm": 2.058547258377075,
+      "learning_rate": 2.195326641487132e-06,
+      "loss": 0.007,
+      "num_input_tokens_seen": 681120,
+      "step": 107
+    },
+    {
+      "epoch": 2.778135048231511,
+      "grad_norm": 2.056870460510254,
+      "learning_rate": 2.1520672475998374e-06,
+      "loss": 0.0347,
+      "num_input_tokens_seen": 687376,
+      "step": 108
+    },
+    {
+      "epoch": 2.8038585209003215,
+      "grad_norm": 3.1806418895721436,
+      "learning_rate": 2.1089138373994226e-06,
+      "loss": 0.0142,
+      "num_input_tokens_seen": 693984,
+      "step": 109
+    },
+    {
+      "epoch": 2.829581993569132,
+      "grad_norm": 4.262523651123047,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 0.0414,
+      "num_input_tokens_seen": 700352,
+      "step": 110
+    },
+    {
+      "epoch": 2.855305466237942,
+      "grad_norm": 4.998467445373535,
+      "learning_rate": 2.022977511558638e-06,
+      "loss": 0.0419,
+      "num_input_tokens_seen": 706768,
+      "step": 111
+    },
+    {
+      "epoch": 2.8810289389067525,
+      "grad_norm": 4.63454532623291,
+      "learning_rate": 1.9802207729556023e-06,
+      "loss": 0.043,
+      "num_input_tokens_seen": 713248,
+      "step": 112
+    },
+    {
+      "epoch": 2.906752411575563,
+      "grad_norm": 2.7104055881500244,
+      "learning_rate": 1.937622364140338e-06,
+      "loss": 0.0192,
+      "num_input_tokens_seen": 719568,
+      "step": 113
+    },
+    {
+      "epoch": 2.932475884244373,
+      "grad_norm": 5.943557262420654,
+      "learning_rate": 1.895195261000831e-06,
+      "loss": 0.0427,
+      "num_input_tokens_seen": 725984,
+      "step": 114
+    },
+    {
+      "epoch": 2.958199356913183,
+      "grad_norm": 1.0689281225204468,
+      "learning_rate": 1.852952387243698e-06,
+      "loss": 0.0116,
+      "num_input_tokens_seen": 732224,
+      "step": 115
+    },
+    {
+      "epoch": 2.9839228295819935,
+      "grad_norm": 3.041832208633423,
+      "learning_rate": 1.8109066104575023e-06,
+      "loss": 0.0135,
+      "num_input_tokens_seen": 738496,
+      "step": 116
+    },
+    {
+      "epoch": 3.009646302250804,
+      "grad_norm": 2.22163462638855,
+      "learning_rate": 1.7690707381931585e-06,
+      "loss": 0.0128,
+      "num_input_tokens_seen": 744880,
+      "step": 117
+    },
+    {
+      "epoch": 3.035369774919614,
+      "grad_norm": 0.32683318853378296,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.0021,
+      "num_input_tokens_seen": 751408,
+      "step": 118
+    },
+    {
+      "epoch": 3.0610932475884245,
+      "grad_norm": 0.8898715972900391,
+      "learning_rate": 1.686079613857109e-06,
+      "loss": 0.0057,
+      "num_input_tokens_seen": 757632,
+      "step": 119
+    },
+    {
+      "epoch": 3.0868167202572345,
+      "grad_norm": 2.082993984222412,
+      "learning_rate": 1.6449496416858285e-06,
+      "loss": 0.0197,
+      "num_input_tokens_seen": 763936,
+      "step": 120
+    },
+    {
+      "epoch": 3.112540192926045,
+      "grad_norm": 0.7368833422660828,
+      "learning_rate": 1.6040801261367494e-06,
+      "loss": 0.0017,
+      "num_input_tokens_seen": 770064,
+      "step": 121
+    },
+    {
+      "epoch": 3.1382636655948555,
+      "grad_norm": 1.7324296236038208,
+      "learning_rate": 1.56348351646022e-06,
+      "loss": 0.0068,
+      "num_input_tokens_seen": 776176,
+      "step": 122
+    },
+    {
+      "epoch": 3.1639871382636655,
+      "grad_norm": 2.4004085063934326,
+      "learning_rate": 1.5231721787768162e-06,
+      "loss": 0.0022,
+      "num_input_tokens_seen": 782464,
+      "step": 123
+    },
+    {
+      "epoch": 3.189710610932476,
+      "grad_norm": 3.6328651905059814,
+      "learning_rate": 1.4831583923105e-06,
+      "loss": 0.0162,
+      "num_input_tokens_seen": 789072,
+      "step": 124
+    },
+    {
+      "epoch": 3.215434083601286,
+      "grad_norm": 0.8305163979530334,
+      "learning_rate": 1.443454345648252e-06,
+      "loss": 0.0014,
+      "num_input_tokens_seen": 795536,
+      "step": 125
+    },
+    {
+      "epoch": 3.2411575562700965,
+      "grad_norm": 6.007119178771973,
+      "learning_rate": 1.4040721330273063e-06,
+      "loss": 0.0063,
+      "num_input_tokens_seen": 801888,
+      "step": 126
+    },
+    {
+      "epoch": 3.266881028938907,
+      "grad_norm": 1.4245920181274414,
+      "learning_rate": 1.3650237506511333e-06,
+      "loss": 0.0282,
+      "num_input_tokens_seen": 808432,
+      "step": 127
+    },
+    {
+      "epoch": 3.292604501607717,
+      "grad_norm": 0.36083319783210754,
+      "learning_rate": 1.3263210930352737e-06,
+      "loss": 0.0003,
+      "num_input_tokens_seen": 814896,
+      "step": 128
+    },
+    {
+      "epoch": 3.3183279742765275,
+      "grad_norm": 0.05347484350204468,
+      "learning_rate": 1.2879759493841577e-06,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 821200,
+      "step": 129
+    },
+    {
+      "epoch": 3.3440514469453375,
+      "grad_norm": 0.16537031531333923,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 827584,
+      "step": 130
+    },
+    {
+      "epoch": 3.369774919614148,
+      "grad_norm": 1.4132962226867676,
+      "learning_rate": 1.2124048127248644e-06,
+      "loss": 0.0169,
+      "num_input_tokens_seen": 834048,
+      "step": 131
+    },
+    {
+      "epoch": 3.395498392282958,
+      "grad_norm": 11.695096969604492,
+      "learning_rate": 1.1752018394169882e-06,
+      "loss": 0.0127,
+      "num_input_tokens_seen": 840240,
+      "step": 132
+    },
+    {
+      "epoch": 3.4212218649517685,
+      "grad_norm": 2.03340482711792,
+      "learning_rate": 1.1384024124624324e-06,
+      "loss": 0.0045,
+      "num_input_tokens_seen": 846448,
+      "step": 133
+    },
+    {
+      "epoch": 3.446945337620579,
+      "grad_norm": 15.712054252624512,
+      "learning_rate": 1.1020177413231334e-06,
+      "loss": 0.0924,
+      "num_input_tokens_seen": 852928,
+      "step": 134
+    },
+    {
+      "epoch": 3.472668810289389,
+      "grad_norm": 3.9320309162139893,
+      "learning_rate": 1.0660589091223854e-06,
+      "loss": 0.0067,
+      "num_input_tokens_seen": 859312,
+      "step": 135
+    },
+    {
+      "epoch": 3.4983922829581995,
+      "grad_norm": 1.599960207939148,
+      "learning_rate": 1.0305368692688175e-06,
+      "loss": 0.003,
+      "num_input_tokens_seen": 865440,
+      "step": 136
+    },
+    {
+      "epoch": 3.5241157556270095,
+      "grad_norm": 8.650961875915527,
+      "learning_rate": 9.95462442119879e-07,
+      "loss": 0.0164,
+      "num_input_tokens_seen": 871968,
+      "step": 137
+    },
+    {
+      "epoch": 3.54983922829582,
+      "grad_norm": 2.1372265815734863,
+      "learning_rate": 9.608463116858544e-07,
+      "loss": 0.0018,
+      "num_input_tokens_seen": 878352,
+      "step": 138
+    },
+    {
+      "epoch": 3.57556270096463,
+      "grad_norm": 1.8475613594055176,
+      "learning_rate": 9.266990223754069e-07,
+      "loss": 0.0226,
+      "num_input_tokens_seen": 884736,
+      "step": 139
+    },
+    {
+      "epoch": 3.6012861736334405,
+      "grad_norm": 0.2472313642501831,
+      "learning_rate": 8.930309757836517e-07,
+      "loss": 0.0008,
+      "num_input_tokens_seen": 891008,
+      "step": 140
+    },
+    {
+      "epoch": 3.627009646302251,
+      "grad_norm": 0.13111230731010437,
+      "learning_rate": 8.598524275237321e-07,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 897120,
+      "step": 141
+    },
+    {
+      "epoch": 3.652733118971061,
+      "grad_norm": 0.23976323008537292,
+      "learning_rate": 8.271734841028553e-07,
+      "loss": 0.0008,
+      "num_input_tokens_seen": 903536,
+      "step": 142
+    },
+    {
+      "epoch": 3.6784565916398715,
+      "grad_norm": 4.404489517211914,
+      "learning_rate": 7.950040998437541e-07,
+      "loss": 0.0256,
+      "num_input_tokens_seen": 909824,
+      "step": 143
+    },
+    {
+      "epoch": 3.7041800643086815,
+      "grad_norm": 0.16712801158428192,
+      "learning_rate": 7.633540738525066e-07,
+      "loss": 0.0005,
+      "num_input_tokens_seen": 916112,
+      "step": 144
+    },
+    {
+      "epoch": 3.729903536977492,
+      "grad_norm": 0.4478089213371277,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.0045,
+      "num_input_tokens_seen": 922592,
+      "step": 145
+    },
+    {
+      "epoch": 3.755627009646302,
+      "grad_norm": 0.14608968794345856,
+      "learning_rate": 7.016504991533727e-07,
+      "loss": 0.0005,
+      "num_input_tokens_seen": 928640,
+      "step": 146
+    },
+    {
+      "epoch": 3.7813504823151125,
+      "grad_norm": 1.1640571355819702,
+      "learning_rate": 6.716157459520739e-07,
+      "loss": 0.0069,
+      "num_input_tokens_seen": 935488,
+      "step": 147
+    },
+    {
+      "epoch": 3.807073954983923,
+      "grad_norm": 5.529272079467773,
+      "learning_rate": 6.421379363065142e-07,
+      "loss": 0.015,
+      "num_input_tokens_seen": 941952,
+      "step": 148
+    },
+    {
+      "epoch": 3.832797427652733,
+      "grad_norm": 2.3761372566223145,
+      "learning_rate": 6.1322604944307e-07,
+      "loss": 0.0012,
+      "num_input_tokens_seen": 948368,
+      "step": 149
+    },
+    {
+      "epoch": 3.8585209003215435,
+      "grad_norm": 2.560185670852661,
+      "learning_rate": 5.848888922025553e-07,
+      "loss": 0.0095,
+      "num_input_tokens_seen": 954752,
+      "step": 150
+    },
+    {
+      "epoch": 3.884244372990354,
+      "grad_norm": 1.6769373416900635,
+      "learning_rate": 5.571350963575728e-07,
+      "loss": 0.0271,
+      "num_input_tokens_seen": 961248,
+      "step": 151
+    },
+    {
+      "epoch": 3.909967845659164,
+      "grad_norm": 1.4693336486816406,
+      "learning_rate": 5.299731159831953e-07,
+      "loss": 0.0201,
+      "num_input_tokens_seen": 967424,
+      "step": 152
+    },
+    {
+      "epoch": 3.935691318327974,
+      "grad_norm": 1.2330920696258545,
+      "learning_rate": 5.034112248817685e-07,
+      "loss": 0.012,
+      "num_input_tokens_seen": 973696,
+      "step": 153
+    },
+    {
+      "epoch": 3.9614147909967845,
+      "grad_norm": 8.100526809692383,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.023,
+      "num_input_tokens_seen": 980144,
+      "step": 154
+    },
+    {
+      "epoch": 3.987138263665595,
+      "grad_norm": 1.439001202583313,
+      "learning_rate": 4.5211988927752026e-07,
+      "loss": 0.0156,
+      "num_input_tokens_seen": 986352,
+      "step": 155
+    },
+    {
+      "epoch": 4.012861736334405,
+      "grad_norm": 0.2862737476825714,
+      "learning_rate": 4.27406068612396e-07,
+      "loss": 0.0009,
+      "num_input_tokens_seen": 992880,
+      "step": 156
+    },
+    {
+      "epoch": 4.038585209003215,
+      "grad_norm": 0.575637936592102,
+      "learning_rate": 4.033235801364402e-07,
+      "loss": 0.0017,
+      "num_input_tokens_seen": 999200,
+      "step": 157
+    },
+    {
+      "epoch": 4.064308681672026,
+      "grad_norm": 0.47944220900535583,
+      "learning_rate": 3.798797596089351e-07,
+      "loss": 0.0015,
+      "num_input_tokens_seen": 1005568,
+      "step": 158
+    },
+    {
+      "epoch": 4.090032154340836,
+      "grad_norm": 0.6407404541969299,
+      "learning_rate": 3.5708174824471947e-07,
+      "loss": 0.0035,
+      "num_input_tokens_seen": 1011728,
+      "step": 159
+    },
+    {
+      "epoch": 4.115755627009646,
+      "grad_norm": 0.29835206270217896,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 0.0016,
+      "num_input_tokens_seen": 1018272,
+      "step": 160
+    },
+    {
+      "epoch": 4.141479099678457,
+      "grad_norm": 0.8626136183738708,
+      "learning_rate": 3.134507321515107e-07,
+      "loss": 0.0028,
+      "num_input_tokens_seen": 1024688,
+      "step": 161
+    },
+    {
+      "epoch": 4.167202572347267,
+      "grad_norm": 0.19084709882736206,
+      "learning_rate": 2.9263101785268253e-07,
+      "loss": 0.0006,
+      "num_input_tokens_seen": 1031152,
+      "step": 162
+    },
+    {
+      "epoch": 4.192926045016077,
+      "grad_norm": 0.34228870272636414,
+      "learning_rate": 2.7248368952908055e-07,
+      "loss": 0.0013,
+      "num_input_tokens_seen": 1037632,
+      "step": 163
+    },
+    {
+      "epoch": 4.218649517684887,
+      "grad_norm": 0.19209067523479462,
+      "learning_rate": 2.53014884252083e-07,
+      "loss": 0.0006,
+      "num_input_tokens_seen": 1043936,
+      "step": 164
+    },
+    {
+      "epoch": 4.244372990353698,
+      "grad_norm": 0.5416057705879211,
+      "learning_rate": 2.3423053240837518e-07,
+      "loss": 0.0017,
+      "num_input_tokens_seen": 1050048,
+      "step": 165
+    },
+    {
+      "epoch": 4.270096463022508,
+      "grad_norm": 0.12837135791778564,
+      "learning_rate": 2.1613635589349756e-07,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 1056496,
+      "step": 166
+    },
+    {
+      "epoch": 4.295819935691318,
+      "grad_norm": 3.4782867431640625,
+      "learning_rate": 1.9873786636889908e-07,
+      "loss": 0.0049,
+      "num_input_tokens_seen": 1062848,
+      "step": 167
+    },
+    {
+      "epoch": 4.321543408360129,
+      "grad_norm": 4.008510112762451,
+      "learning_rate": 1.8204036358303173e-07,
+      "loss": 0.0071,
+      "num_input_tokens_seen": 1069136,
+      "step": 168
+    },
+    {
+      "epoch": 4.347266881028939,
+      "grad_norm": 0.38916894793510437,
+      "learning_rate": 1.6604893375699594e-07,
+      "loss": 0.0011,
+      "num_input_tokens_seen": 1075328,
+      "step": 169
+    },
+    {
+      "epoch": 4.372990353697749,
+      "grad_norm": 0.11064338684082031,
+      "learning_rate": 1.507684480352292e-07,
+      "loss": 0.0004,
+      "num_input_tokens_seen": 1081696,
+      "step": 170
+    },
+    {
+      "epoch": 4.39871382636656,
+      "grad_norm": 0.20267654955387115,
+      "learning_rate": 1.362035610017079e-07,
+      "loss": 0.0007,
+      "num_input_tokens_seen": 1088112,
+      "step": 171
+    },
+    {
+      "epoch": 4.42443729903537,
+      "grad_norm": 0.35677772760391235,
+      "learning_rate": 1.223587092621162e-07,
+      "loss": 0.0017,
+      "num_input_tokens_seen": 1094512,
+      "step": 172
+    },
+    {
+      "epoch": 4.45016077170418,
+      "grad_norm": 0.3713955581188202,
+      "learning_rate": 1.0923811009241142e-07,
+      "loss": 0.0007,
+      "num_input_tokens_seen": 1101040,
+      "step": 173
+    },
+    {
+      "epoch": 4.47588424437299,
+      "grad_norm": 0.1514904946088791,
+      "learning_rate": 9.684576015420277e-08,
+      "loss": 0.0003,
+      "num_input_tokens_seen": 1107168,
+      "step": 174
+    },
+    {
+      "epoch": 4.501607717041801,
+      "grad_norm": 4.804702281951904,
+      "learning_rate": 8.518543427732951e-08,
+      "loss": 0.0046,
+      "num_input_tokens_seen": 1113408,
+      "step": 175
+    },
+    {
+      "epoch": 4.527331189710611,
+      "grad_norm": 0.9991558194160461,
+      "learning_rate": 7.426068431000883e-08,
+      "loss": 0.0038,
+      "num_input_tokens_seen": 1119568,
+      "step": 176
+    },
+    {
+      "epoch": 4.553054662379421,
+      "grad_norm": 2.726783037185669,
+      "learning_rate": 6.407483803691216e-08,
+      "loss": 0.0036,
+      "num_input_tokens_seen": 1126048,
+      "step": 177
+    },
+    {
+      "epoch": 4.578778135048232,
+      "grad_norm": 1.2259963750839233,
+      "learning_rate": 5.463099816548578e-08,
+      "loss": 0.0056,
+      "num_input_tokens_seen": 1132400,
+      "step": 178
+    },
+    {
+      "epoch": 4.604501607717042,
+      "grad_norm": 3.010671615600586,
+      "learning_rate": 4.593204138084006e-08,
+      "loss": 0.0057,
+      "num_input_tokens_seen": 1138832,
+      "step": 179
+    },
+    {
+      "epoch": 4.630225080385852,
+      "grad_norm": 0.9592411518096924,
+      "learning_rate": 3.798061746947995e-08,
+      "loss": 0.002,
+      "num_input_tokens_seen": 1145344,
+      "step": 180
+    },
+    {
+      "epoch": 4.655948553054662,
+      "grad_norm": 0.09295938909053802,
+      "learning_rate": 3.077914851215585e-08,
+      "loss": 0.0003,
+      "num_input_tokens_seen": 1151536,
+      "step": 181
+    },
+    {
+      "epoch": 4.681672025723473,
+      "grad_norm": 0.06213412061333656,
+      "learning_rate": 2.4329828146074096e-08,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 1157696,
+      "step": 182
+    },
+    {
+      "epoch": 4.707395498392283,
+      "grad_norm": 1.2592134475708008,
+      "learning_rate": 1.8634620896695044e-08,
+      "loss": 0.0043,
+      "num_input_tokens_seen": 1163712,
+      "step": 183
+    },
+    {
+      "epoch": 4.733118971061093,
+      "grad_norm": 0.05733427032828331,
+      "learning_rate": 1.3695261579316776e-08,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 1169888,
+      "step": 184
+    },
+    {
+      "epoch": 4.758842443729904,
+      "grad_norm": 0.38288363814353943,
+      "learning_rate": 9.513254770636138e-09,
+      "loss": 0.0013,
+      "num_input_tokens_seen": 1176272,
+      "step": 185
+    },
+    {
+      "epoch": 4.784565916398714,
+      "grad_norm": 0.6540606617927551,
+      "learning_rate": 6.089874350439507e-09,
+      "loss": 0.0023,
+      "num_input_tokens_seen": 1182688,
+      "step": 186
+    },
+    {
+      "epoch": 4.810289389067524,
+      "grad_norm": 0.0432482548058033,
+      "learning_rate": 3.4261631135654174e-09,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 1189360,
+      "step": 187
+    },
+    {
+      "epoch": 4.836012861736334,
+      "grad_norm": 0.8218325972557068,
+      "learning_rate": 1.5229324522605949e-09,
+      "loss": 0.0015,
+      "num_input_tokens_seen": 1195632,
+      "step": 188
+    },
+    {
+      "epoch": 4.861736334405145,
+      "grad_norm": 0.05609305202960968,
+      "learning_rate": 3.8076210902182607e-10,
+      "loss": 0.0002,
+      "num_input_tokens_seen": 1202016,
+      "step": 189
+    },
+    {
+      "epoch": 4.887459807073955,
+      "grad_norm": 3.791782855987549,
+      "learning_rate": 0.0,
+      "loss": 0.0028,
+      "num_input_tokens_seen": 1208400,
+      "step": 190
+    },
+    {
+      "epoch": 4.887459807073955,
+      "num_input_tokens_seen": 1208400,
+      "step": 190,
+      "total_flos": 5.441370708980531e+16,
+      "train_loss": 0.5078434096239538,
+      "train_runtime": 2562.642,
+      "train_samples_per_second": 9.693,
+      "train_steps_per_second": 0.074
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 190,
+  "num_input_tokens_seen": 1208400,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.441370708980531e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd080bf34222db640e5df447c0955c50426b3473fa57de2bcaf77a92b9002bf4
+size 6584