Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: other
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: gemma-2-9b-control-4e-r2
+  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. -->
+
+# gemma-2-9b-control-4e-r2
+
+This model is a fine-tuned version of [/data/models/gemma-9b-compl](https://huggingface.co//data/models/gemma-9b-compl) on the ds1, the ds2, the ds3, the ds4, the kalo_opus_1, the claude_instruct, the claude_instruct_2 and the epic_synth_2 datasets.
+
+## 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: 3e-06
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 12
+- total_train_batch_size: 24
+- total_eval_batch_size: 96
+- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+e000cf0ad9.nv24.10
+- Datasets 3.0.2
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 648773332107264.0,
+    "train_loss": 0.9660957064397535,
+    "train_runtime": 3882.5924,
+    "train_samples_per_second": 5.59,
+    "train_steps_per_second": 0.234
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "output_dir",
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 8,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 8,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3517a057810510006aa291e9cfd8e24e487160b7f172ca8a15fbfd4939137235
+size 4903351912

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a62f6eb5ffe70a3219c125b5404245416195142a37b0a1021cb741126ac8686
+size 4947570872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c187b922fa991d94981aa8c2511394b7b54651cc4fe9e6166f02e90c45a7d3
+size 4962221464

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6d218fd38213d92917261e1fbee0d87b234c25025c2d147d0e5dde98bbce2c
+size 3670322200

model.safetensors.index.json

@@ -0,0 +1,471 @@
+{
+  "metadata": {
+    "total_size": 18483411968
+  },
+  "weight_map": {
+    "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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.pre_feedforward_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-00003-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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.pre_feedforward_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-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-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.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.pre_feedforward_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.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00004-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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.pre_feedforward_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.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.pre_feedforward_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-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-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.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.pre_feedforward_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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>",
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e21773a4721128c9c62ba09a4fcbab3288cda68ecc00683b044f280dc0f440
+size 34356047

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f545c6099874ce0c5cf6e4ccecd5f2bce689852b576ddf9d49134081c9cb98
+size 4241007

tokenizer_config.json

@@ -0,0 +1,1760 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>",
+    "<|im_start|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 648773332107264.0,
+    "train_loss": 0.9660957064397535,
+    "train_runtime": 3882.5924,
+    "train_samples_per_second": 5.59,
+    "train_steps_per_second": 0.234
+}

trainer_log.jsonl

@@ -0,0 +1,91 @@
+{"current_steps": 10, "total_steps": 908, "loss": 1.4512, "learning_rate": 3.296703296703297e-07, "epoch": 0.04405286343612335, "percentage": 1.1, "elapsed_time": "0:00:44", "remaining_time": "1:06:25"}
+{"current_steps": 20, "total_steps": 908, "loss": 1.4723, "learning_rate": 6.593406593406594e-07, "epoch": 0.0881057268722467, "percentage": 2.2, "elapsed_time": "0:01:27", "remaining_time": "1:04:32"}
+{"current_steps": 30, "total_steps": 908, "loss": 1.3932, "learning_rate": 9.890109890109891e-07, "epoch": 0.13215859030837004, "percentage": 3.3, "elapsed_time": "0:02:10", "remaining_time": "1:03:24"}
+{"current_steps": 40, "total_steps": 908, "loss": 1.3093, "learning_rate": 1.3186813186813187e-06, "epoch": 0.1762114537444934, "percentage": 4.41, "elapsed_time": "0:02:52", "remaining_time": "1:02:26"}
+{"current_steps": 50, "total_steps": 908, "loss": 1.2687, "learning_rate": 1.6483516483516486e-06, "epoch": 0.22026431718061673, "percentage": 5.51, "elapsed_time": "0:03:35", "remaining_time": "1:01:34"}
+{"current_steps": 60, "total_steps": 908, "loss": 1.2427, "learning_rate": 1.9780219780219782e-06, "epoch": 0.2643171806167401, "percentage": 6.61, "elapsed_time": "0:04:17", "remaining_time": "1:00:46"}
+{"current_steps": 70, "total_steps": 908, "loss": 1.2286, "learning_rate": 2.307692307692308e-06, "epoch": 0.30837004405286345, "percentage": 7.71, "elapsed_time": "0:05:00", "remaining_time": "0:59:59"}
+{"current_steps": 80, "total_steps": 908, "loss": 1.1827, "learning_rate": 2.6373626373626375e-06, "epoch": 0.3524229074889868, "percentage": 8.81, "elapsed_time": "0:05:43", "remaining_time": "0:59:13"}
+{"current_steps": 90, "total_steps": 908, "loss": 1.1941, "learning_rate": 2.9670329670329673e-06, "epoch": 0.3964757709251101, "percentage": 9.91, "elapsed_time": "0:06:26", "remaining_time": "0:58:29"}
+{"current_steps": 100, "total_steps": 908, "loss": 1.1731, "learning_rate": 2.999101829950985e-06, "epoch": 0.44052863436123346, "percentage": 11.01, "elapsed_time": "0:07:08", "remaining_time": "0:57:45"}
+{"current_steps": 110, "total_steps": 908, "loss": 1.1148, "learning_rate": 2.9959984254953274e-06, "epoch": 0.4845814977973568, "percentage": 12.11, "elapsed_time": "0:07:51", "remaining_time": "0:57:01"}
+{"current_steps": 120, "total_steps": 908, "loss": 1.191, "learning_rate": 2.9906832852013294e-06, "epoch": 0.5286343612334802, "percentage": 13.22, "elapsed_time": "0:08:34", "remaining_time": "0:56:17"}
+{"current_steps": 130, "total_steps": 908, "loss": 1.1818, "learning_rate": 2.9831642671563205e-06, "epoch": 0.5726872246696035, "percentage": 14.32, "elapsed_time": "0:09:17", "remaining_time": "0:55:33"}
+{"current_steps": 140, "total_steps": 908, "loss": 1.1969, "learning_rate": 2.9734524877367604e-06, "epoch": 0.6167400881057269, "percentage": 15.42, "elapsed_time": "0:09:59", "remaining_time": "0:54:50"}
+{"current_steps": 150, "total_steps": 908, "loss": 1.1203, "learning_rate": 2.961562305173399e-06, "epoch": 0.6607929515418502, "percentage": 16.52, "elapsed_time": "0:10:42", "remaining_time": "0:54:06"}
+{"current_steps": 160, "total_steps": 908, "loss": 1.2301, "learning_rate": 2.9475112983235753e-06, "epoch": 0.7048458149779736, "percentage": 17.62, "elapsed_time": "0:11:25", "remaining_time": "0:53:23"}
+{"current_steps": 170, "total_steps": 908, "loss": 1.183, "learning_rate": 2.9313202406820232e-06, "epoch": 0.748898678414097, "percentage": 18.72, "elapsed_time": "0:12:07", "remaining_time": "0:52:39"}
+{"current_steps": 180, "total_steps": 908, "loss": 1.1304, "learning_rate": 2.9130130696686196e-06, "epoch": 0.7929515418502202, "percentage": 19.82, "elapsed_time": "0:12:50", "remaining_time": "0:51:56"}
+{"current_steps": 190, "total_steps": 908, "loss": 1.1618, "learning_rate": 2.8926168512384744e-06, "epoch": 0.8370044052863436, "percentage": 20.93, "elapsed_time": "0:13:33", "remaining_time": "0:51:13"}
+{"current_steps": 200, "total_steps": 908, "loss": 1.1491, "learning_rate": 2.870161739866686e-06, "epoch": 0.8810572687224669, "percentage": 22.03, "elapsed_time": "0:14:15", "remaining_time": "0:50:30"}
+{"current_steps": 210, "total_steps": 908, "loss": 1.145, "learning_rate": 2.845680933966922e-06, "epoch": 0.9251101321585903, "percentage": 23.13, "elapsed_time": "0:14:58", "remaining_time": "0:49:46"}
+{"current_steps": 220, "total_steps": 908, "loss": 1.2206, "learning_rate": 2.8192106268097337e-06, "epoch": 0.9691629955947136, "percentage": 24.23, "elapsed_time": "0:15:41", "remaining_time": "0:49:03"}
+{"current_steps": 230, "total_steps": 908, "loss": 1.133, "learning_rate": 2.7907899530131763e-06, "epoch": 1.013215859030837, "percentage": 25.33, "elapsed_time": "0:16:23", "remaining_time": "0:48:20"}
+{"current_steps": 240, "total_steps": 908, "loss": 1.0399, "learning_rate": 2.7604609306848312e-06, "epoch": 1.0572687224669604, "percentage": 26.43, "elapsed_time": "0:17:06", "remaining_time": "0:47:37"}
+{"current_steps": 250, "total_steps": 908, "loss": 1.007, "learning_rate": 2.7282683993007865e-06, "epoch": 1.1013215859030836, "percentage": 27.53, "elapsed_time": "0:17:49", "remaining_time": "0:46:54"}
+{"current_steps": 260, "total_steps": 908, "loss": 1.0139, "learning_rate": 2.6942599534133987e-06, "epoch": 1.145374449339207, "percentage": 28.63, "elapsed_time": "0:18:31", "remaining_time": "0:46:11"}
+{"current_steps": 270, "total_steps": 908, "loss": 1.0493, "learning_rate": 2.658485872285863e-06, "epoch": 1.1894273127753303, "percentage": 29.74, "elapsed_time": "0:19:14", "remaining_time": "0:45:28"}
+{"current_steps": 280, "total_steps": 908, "loss": 0.9478, "learning_rate": 2.6209990455576105e-06, "epoch": 1.2334801762114538, "percentage": 30.84, "elapsed_time": "0:19:57", "remaining_time": "0:44:44"}
+{"current_steps": 290, "total_steps": 908, "loss": 1.0108, "learning_rate": 2.5818548950504342e-06, "epoch": 1.277533039647577, "percentage": 31.94, "elapsed_time": "0:20:39", "remaining_time": "0:44:01"}
+{"current_steps": 300, "total_steps": 908, "loss": 1.0294, "learning_rate": 2.541111292830951e-06, "epoch": 1.3215859030837005, "percentage": 33.04, "elapsed_time": "0:21:22", "remaining_time": "0:43:18"}
+{"current_steps": 310, "total_steps": 908, "loss": 0.9748, "learning_rate": 2.4988284756505333e-06, "epoch": 1.3656387665198237, "percentage": 34.14, "elapsed_time": "0:22:04", "remaining_time": "0:42:35"}
+{"current_steps": 320, "total_steps": 908, "loss": 1.0054, "learning_rate": 2.455068955889216e-06, "epoch": 1.4096916299559472, "percentage": 35.24, "elapsed_time": "0:22:47", "remaining_time": "0:41:52"}
+{"current_steps": 330, "total_steps": 908, "loss": 1.0155, "learning_rate": 2.4098974291352257e-06, "epoch": 1.4537444933920705, "percentage": 36.34, "elapsed_time": "0:23:30", "remaining_time": "0:41:09"}
+{"current_steps": 340, "total_steps": 908, "loss": 1.0677, "learning_rate": 2.3633806785367873e-06, "epoch": 1.497797356828194, "percentage": 37.44, "elapsed_time": "0:24:12", "remaining_time": "0:40:26"}
+{"current_steps": 350, "total_steps": 908, "loss": 0.987, "learning_rate": 2.315587476067607e-06, "epoch": 1.5418502202643172, "percentage": 38.55, "elapsed_time": "0:24:55", "remaining_time": "0:39:43"}
+{"current_steps": 360, "total_steps": 908, "loss": 1.0526, "learning_rate": 2.2665884808520048e-06, "epoch": 1.5859030837004404, "percentage": 39.65, "elapsed_time": "0:25:37", "remaining_time": "0:39:00"}
+{"current_steps": 370, "total_steps": 908, "loss": 1.0304, "learning_rate": 2.2164561347000213e-06, "epoch": 1.6299559471365639, "percentage": 40.75, "elapsed_time": "0:26:20", "remaining_time": "0:38:17"}
+{"current_steps": 380, "total_steps": 908, "loss": 0.9921, "learning_rate": 2.1652645550069394e-06, "epoch": 1.6740088105726874, "percentage": 41.85, "elapsed_time": "0:27:02", "remaining_time": "0:37:34"}
+{"current_steps": 390, "total_steps": 908, "loss": 1.0062, "learning_rate": 2.113089425175561e-06, "epoch": 1.7180616740088106, "percentage": 42.95, "elapsed_time": "0:27:45", "remaining_time": "0:36:51"}
+{"current_steps": 400, "total_steps": 908, "loss": 0.993, "learning_rate": 2.0600078827232473e-06, "epoch": 1.7621145374449338, "percentage": 44.05, "elapsed_time": "0:28:27", "remaining_time": "0:36:09"}
+{"current_steps": 410, "total_steps": 908, "loss": 0.989, "learning_rate": 2.006098405239142e-06, "epoch": 1.8061674008810573, "percentage": 45.15, "elapsed_time": "0:29:10", "remaining_time": "0:35:26"}
+{"current_steps": 420, "total_steps": 908, "loss": 1.0184, "learning_rate": 1.95144069436019e-06, "epoch": 1.8502202643171806, "percentage": 46.26, "elapsed_time": "0:29:53", "remaining_time": "0:34:43"}
+{"current_steps": 430, "total_steps": 908, "loss": 1.0655, "learning_rate": 1.896115557937476e-06, "epoch": 1.894273127753304, "percentage": 47.36, "elapsed_time": "0:30:35", "remaining_time": "0:34:00"}
+{"current_steps": 440, "total_steps": 908, "loss": 1.0139, "learning_rate": 1.8402047905671065e-06, "epoch": 1.9383259911894273, "percentage": 48.46, "elapsed_time": "0:31:18", "remaining_time": "0:33:17"}
+{"current_steps": 450, "total_steps": 908, "loss": 1.0103, "learning_rate": 1.7837910526622437e-06, "epoch": 1.9823788546255505, "percentage": 49.56, "elapsed_time": "0:32:00", "remaining_time": "0:32:34"}
+{"current_steps": 460, "total_steps": 908, "loss": 0.8977, "learning_rate": 1.726957748245093e-06, "epoch": 2.026431718061674, "percentage": 50.66, "elapsed_time": "0:32:43", "remaining_time": "0:31:52"}
+{"current_steps": 470, "total_steps": 908, "loss": 0.8438, "learning_rate": 1.6697889016395088e-06, "epoch": 2.0704845814977975, "percentage": 51.76, "elapsed_time": "0:33:25", "remaining_time": "0:31:09"}
+{"current_steps": 480, "total_steps": 908, "loss": 0.9008, "learning_rate": 1.6123690332465296e-06, "epoch": 2.1145374449339207, "percentage": 52.86, "elapsed_time": "0:34:08", "remaining_time": "0:30:26"}
+{"current_steps": 490, "total_steps": 908, "loss": 0.8176, "learning_rate": 1.5547830345864886e-06, "epoch": 2.158590308370044, "percentage": 53.96, "elapsed_time": "0:34:50", "remaining_time": "0:29:43"}
+{"current_steps": 500, "total_steps": 908, "loss": 0.8901, "learning_rate": 1.4971160427924554e-06, "epoch": 2.202643171806167, "percentage": 55.07, "elapsed_time": "0:35:33", "remaining_time": "0:29:00"}
+{"current_steps": 510, "total_steps": 908, "loss": 0.8247, "learning_rate": 1.439453314740552e-06, "epoch": 2.246696035242291, "percentage": 56.17, "elapsed_time": "0:36:22", "remaining_time": "0:28:23"}
+{"current_steps": 520, "total_steps": 908, "loss": 0.8294, "learning_rate": 1.381880101003235e-06, "epoch": 2.290748898678414, "percentage": 57.27, "elapsed_time": "0:37:04", "remaining_time": "0:27:40"}
+{"current_steps": 530, "total_steps": 908, "loss": 0.9032, "learning_rate": 1.3244815198119024e-06, "epoch": 2.3348017621145374, "percentage": 58.37, "elapsed_time": "0:37:47", "remaining_time": "0:26:57"}
+{"current_steps": 540, "total_steps": 908, "loss": 0.8862, "learning_rate": 1.2673424312151519e-06, "epoch": 2.3788546255506606, "percentage": 59.47, "elapsed_time": "0:38:29", "remaining_time": "0:26:14"}
+{"current_steps": 550, "total_steps": 908, "loss": 0.894, "learning_rate": 1.2105473116187517e-06, "epoch": 2.4229074889867843, "percentage": 60.57, "elapsed_time": "0:39:12", "remaining_time": "0:25:31"}
+{"current_steps": 560, "total_steps": 908, "loss": 0.8126, "learning_rate": 1.154180128892796e-06, "epoch": 2.4669603524229076, "percentage": 61.67, "elapsed_time": "0:39:54", "remaining_time": "0:24:48"}
+{"current_steps": 570, "total_steps": 908, "loss": 0.8059, "learning_rate": 1.0983242182307033e-06, "epoch": 2.511013215859031, "percentage": 62.78, "elapsed_time": "0:40:37", "remaining_time": "0:24:05"}
+{"current_steps": 580, "total_steps": 908, "loss": 0.8959, "learning_rate": 1.0430621589435803e-06, "epoch": 2.555066079295154, "percentage": 63.88, "elapsed_time": "0:41:20", "remaining_time": "0:23:22"}
+{"current_steps": 590, "total_steps": 908, "loss": 0.8393, "learning_rate": 9.884756523721117e-07, "epoch": 2.5991189427312777, "percentage": 64.98, "elapsed_time": "0:42:02", "remaining_time": "0:22:39"}
+{"current_steps": 600, "total_steps": 908, "loss": 0.862, "learning_rate": 9.346454010964724e-07, "epoch": 2.643171806167401, "percentage": 66.08, "elapsed_time": "0:42:45", "remaining_time": "0:21:56"}
+{"current_steps": 610, "total_steps": 908, "loss": 0.859, "learning_rate": 8.816509896228376e-07, "epoch": 2.6872246696035242, "percentage": 67.18, "elapsed_time": "0:43:27", "remaining_time": "0:21:13"}
+{"current_steps": 620, "total_steps": 908, "loss": 0.8348, "learning_rate": 8.295707667228987e-07, "epoch": 2.7312775330396475, "percentage": 68.28, "elapsed_time": "0:44:10", "remaining_time": "0:20:31"}
+{"current_steps": 630, "total_steps": 908, "loss": 0.8668, "learning_rate": 7.784817296003237e-07, "epoch": 2.7753303964757707, "percentage": 69.38, "elapsed_time": "0:44:52", "remaining_time": "0:19:48"}
+{"current_steps": 640, "total_steps": 908, "loss": 0.8627, "learning_rate": 7.284594100554311e-07, "epoch": 2.8193832599118944, "percentage": 70.48, "elapsed_time": "0:45:35", "remaining_time": "0:19:05"}
+{"current_steps": 650, "total_steps": 908, "loss": 0.855, "learning_rate": 6.7957776281636e-07, "epoch": 2.8634361233480177, "percentage": 71.59, "elapsed_time": "0:46:17", "remaining_time": "0:18:22"}
+{"current_steps": 660, "total_steps": 908, "loss": 0.8849, "learning_rate": 6.31909056201842e-07, "epoch": 2.907488986784141, "percentage": 72.69, "elapsed_time": "0:47:00", "remaining_time": "0:17:39"}
+{"current_steps": 670, "total_steps": 908, "loss": 0.8629, "learning_rate": 5.855237652772183e-07, "epoch": 2.951541850220264, "percentage": 73.79, "elapsed_time": "0:47:43", "remaining_time": "0:16:57"}
+{"current_steps": 680, "total_steps": 908, "loss": 0.8796, "learning_rate": 5.404904676616635e-07, "epoch": 2.995594713656388, "percentage": 74.89, "elapsed_time": "0:48:25", "remaining_time": "0:16:14"}
+{"current_steps": 690, "total_steps": 908, "loss": 0.779, "learning_rate": 4.968757421406609e-07, "epoch": 3.039647577092511, "percentage": 75.99, "elapsed_time": "0:49:08", "remaining_time": "0:15:31"}
+{"current_steps": 700, "total_steps": 908, "loss": 0.7582, "learning_rate": 4.547440702336238e-07, "epoch": 3.0837004405286343, "percentage": 77.09, "elapsed_time": "0:49:50", "remaining_time": "0:14:48"}
+{"current_steps": 710, "total_steps": 908, "loss": 0.7063, "learning_rate": 4.1415774086218277e-07, "epoch": 3.1277533039647576, "percentage": 78.19, "elapsed_time": "0:50:33", "remaining_time": "0:14:05"}
+{"current_steps": 720, "total_steps": 908, "loss": 0.752, "learning_rate": 3.7517675826009083e-07, "epoch": 3.171806167400881, "percentage": 79.3, "elapsed_time": "0:51:15", "remaining_time": "0:13:23"}
+{"current_steps": 730, "total_steps": 908, "loss": 0.7829, "learning_rate": 3.378587532608872e-07, "epoch": 3.2158590308370045, "percentage": 80.4, "elapsed_time": "0:51:58", "remaining_time": "0:12:40"}
+{"current_steps": 740, "total_steps": 908, "loss": 0.72, "learning_rate": 3.0225889809447925e-07, "epoch": 3.2599118942731278, "percentage": 81.5, "elapsed_time": "0:52:41", "remaining_time": "0:11:57"}
+{"current_steps": 750, "total_steps": 908, "loss": 0.7852, "learning_rate": 2.684298248186077e-07, "epoch": 3.303964757709251, "percentage": 82.6, "elapsed_time": "0:53:23", "remaining_time": "0:11:14"}
+{"current_steps": 760, "total_steps": 908, "loss": 0.7912, "learning_rate": 2.3642154750579275e-07, "epoch": 3.3480176211453743, "percentage": 83.7, "elapsed_time": "0:54:06", "remaining_time": "0:10:32"}
+{"current_steps": 770, "total_steps": 908, "loss": 0.7456, "learning_rate": 2.0628138830079696e-07, "epoch": 3.392070484581498, "percentage": 84.8, "elapsed_time": "0:54:48", "remaining_time": "0:09:49"}
+{"current_steps": 780, "total_steps": 908, "loss": 0.7654, "learning_rate": 1.7805390745792993e-07, "epoch": 3.436123348017621, "percentage": 85.9, "elapsed_time": "0:55:31", "remaining_time": "0:09:06"}
+{"current_steps": 790, "total_steps": 908, "loss": 0.7437, "learning_rate": 1.5178083746162667e-07, "epoch": 3.4801762114537445, "percentage": 87.0, "elapsed_time": "0:56:13", "remaining_time": "0:08:23"}
+{"current_steps": 800, "total_steps": 908, "loss": 0.7834, "learning_rate": 1.2750102132769738e-07, "epoch": 3.5242290748898677, "percentage": 88.11, "elapsed_time": "0:56:56", "remaining_time": "0:07:41"}
+{"current_steps": 810, "total_steps": 908, "loss": 0.7943, "learning_rate": 1.0525035517647014e-07, "epoch": 3.568281938325991, "percentage": 89.21, "elapsed_time": "0:57:39", "remaining_time": "0:06:58"}
+{"current_steps": 820, "total_steps": 908, "loss": 0.7826, "learning_rate": 8.50617351627232e-08, "epoch": 3.6123348017621146, "percentage": 90.31, "elapsed_time": "0:58:21", "remaining_time": "0:06:15"}
+{"current_steps": 830, "total_steps": 908, "loss": 0.8379, "learning_rate": 6.696500884087259e-08, "epoch": 3.656387665198238, "percentage": 91.41, "elapsed_time": "0:59:04", "remaining_time": "0:05:33"}
+{"current_steps": 840, "total_steps": 908, "loss": 0.7614, "learning_rate": 5.0986931037314666e-08, "epoch": 3.700440528634361, "percentage": 92.51, "elapsed_time": "0:59:46", "remaining_time": "0:04:50"}
+{"current_steps": 850, "total_steps": 908, "loss": 0.8152, "learning_rate": 3.7151124295163374e-08, "epoch": 3.744493392070485, "percentage": 93.61, "elapsed_time": "1:00:29", "remaining_time": "0:04:07"}
+{"current_steps": 860, "total_steps": 908, "loss": 0.7517, "learning_rate": 2.5478043949868192e-08, "epoch": 3.788546255506608, "percentage": 94.71, "elapsed_time": "1:01:12", "remaining_time": "0:03:24"}
+{"current_steps": 870, "total_steps": 908, "loss": 0.7697, "learning_rate": 1.5984947887334623e-08, "epoch": 3.8325991189427313, "percentage": 95.81, "elapsed_time": "1:01:54", "remaining_time": "0:02:42"}
+{"current_steps": 880, "total_steps": 908, "loss": 0.7506, "learning_rate": 8.685871029272318e-09, "epoch": 3.8766519823788546, "percentage": 96.92, "elapsed_time": "1:02:37", "remaining_time": "0:01:59"}
+{"current_steps": 890, "total_steps": 908, "loss": 0.7273, "learning_rate": 3.5916045834781253e-09, "epoch": 3.920704845814978, "percentage": 98.02, "elapsed_time": "1:03:19", "remaining_time": "0:01:16"}
+{"current_steps": 900, "total_steps": 908, "loss": 0.8123, "learning_rate": 7.096800897425371e-10, "epoch": 3.964757709251101, "percentage": 99.12, "elapsed_time": "1:04:02", "remaining_time": "0:00:34"}
+{"current_steps": 908, "total_steps": 908, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:04:42", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,672 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 908,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04405286343612335,
+      "grad_norm": 10.519313963525699,
+      "learning_rate": 3.296703296703297e-07,
+      "loss": 1.4512,
+      "step": 10
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": 5.275494720043015,
+      "learning_rate": 6.593406593406594e-07,
+      "loss": 1.4723,
+      "step": 20
+    },
+    {
+      "epoch": 0.13215859030837004,
+      "grad_norm": 1.8226315526905816,
+      "learning_rate": 9.890109890109891e-07,
+      "loss": 1.3932,
+      "step": 30
+    },
+    {
+      "epoch": 0.1762114537444934,
+      "grad_norm": 2.044759232085493,
+      "learning_rate": 1.3186813186813187e-06,
+      "loss": 1.3093,
+      "step": 40
+    },
+    {
+      "epoch": 0.22026431718061673,
+      "grad_norm": 1.7807644006153884,
+      "learning_rate": 1.6483516483516486e-06,
+      "loss": 1.2687,
+      "step": 50
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 1.5054649369651574,
+      "learning_rate": 1.9780219780219782e-06,
+      "loss": 1.2427,
+      "step": 60
+    },
+    {
+      "epoch": 0.30837004405286345,
+      "grad_norm": 1.645138466222819,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.2286,
+      "step": 70
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 1.4999909747158735,
+      "learning_rate": 2.6373626373626375e-06,
+      "loss": 1.1827,
+      "step": 80
+    },
+    {
+      "epoch": 0.3964757709251101,
+      "grad_norm": 1.7582872706972468,
+      "learning_rate": 2.9670329670329673e-06,
+      "loss": 1.1941,
+      "step": 90
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 1.693711129252621,
+      "learning_rate": 2.999101829950985e-06,
+      "loss": 1.1731,
+      "step": 100
+    },
+    {
+      "epoch": 0.4845814977973568,
+      "grad_norm": 1.4467996095205224,
+      "learning_rate": 2.9959984254953274e-06,
+      "loss": 1.1148,
+      "step": 110
+    },
+    {
+      "epoch": 0.5286343612334802,
+      "grad_norm": 1.5298410629642052,
+      "learning_rate": 2.9906832852013294e-06,
+      "loss": 1.191,
+      "step": 120
+    },
+    {
+      "epoch": 0.5726872246696035,
+      "grad_norm": 1.4536712154523523,
+      "learning_rate": 2.9831642671563205e-06,
+      "loss": 1.1818,
+      "step": 130
+    },
+    {
+      "epoch": 0.6167400881057269,
+      "grad_norm": 1.5305738885906355,
+      "learning_rate": 2.9734524877367604e-06,
+      "loss": 1.1969,
+      "step": 140
+    },
+    {
+      "epoch": 0.6607929515418502,
+      "grad_norm": 1.4595832724906421,
+      "learning_rate": 2.961562305173399e-06,
+      "loss": 1.1203,
+      "step": 150
+    },
+    {
+      "epoch": 0.7048458149779736,
+      "grad_norm": 1.7304480079500448,
+      "learning_rate": 2.9475112983235753e-06,
+      "loss": 1.2301,
+      "step": 160
+    },
+    {
+      "epoch": 0.748898678414097,
+      "grad_norm": 1.5486760284827386,
+      "learning_rate": 2.9313202406820232e-06,
+      "loss": 1.183,
+      "step": 170
+    },
+    {
+      "epoch": 0.7929515418502202,
+      "grad_norm": 1.700519163465852,
+      "learning_rate": 2.9130130696686196e-06,
+      "loss": 1.1304,
+      "step": 180
+    },
+    {
+      "epoch": 0.8370044052863436,
+      "grad_norm": 1.4763145358774594,
+      "learning_rate": 2.8926168512384744e-06,
+      "loss": 1.1618,
+      "step": 190
+    },
+    {
+      "epoch": 0.8810572687224669,
+      "grad_norm": 1.5267413192202046,
+      "learning_rate": 2.870161739866686e-06,
+      "loss": 1.1491,
+      "step": 200
+    },
+    {
+      "epoch": 0.9251101321585903,
+      "grad_norm": 1.733908977152635,
+      "learning_rate": 2.845680933966922e-06,
+      "loss": 1.145,
+      "step": 210
+    },
+    {
+      "epoch": 0.9691629955947136,
+      "grad_norm": 1.498098134685152,
+      "learning_rate": 2.8192106268097337e-06,
+      "loss": 1.2206,
+      "step": 220
+    },
+    {
+      "epoch": 1.013215859030837,
+      "grad_norm": 4.7125491501567724,
+      "learning_rate": 2.7907899530131763e-06,
+      "loss": 1.133,
+      "step": 230
+    },
+    {
+      "epoch": 1.0572687224669604,
+      "grad_norm": 2.038277716111568,
+      "learning_rate": 2.7604609306848312e-06,
+      "loss": 1.0399,
+      "step": 240
+    },
+    {
+      "epoch": 1.1013215859030836,
+      "grad_norm": 1.8451563548941678,
+      "learning_rate": 2.7282683993007865e-06,
+      "loss": 1.007,
+      "step": 250
+    },
+    {
+      "epoch": 1.145374449339207,
+      "grad_norm": 1.5438408367179703,
+      "learning_rate": 2.6942599534133987e-06,
+      "loss": 1.0139,
+      "step": 260
+    },
+    {
+      "epoch": 1.1894273127753303,
+      "grad_norm": 1.6126849019096945,
+      "learning_rate": 2.658485872285863e-06,
+      "loss": 1.0493,
+      "step": 270
+    },
+    {
+      "epoch": 1.2334801762114538,
+      "grad_norm": 1.9217991771681158,
+      "learning_rate": 2.6209990455576105e-06,
+      "loss": 0.9478,
+      "step": 280
+    },
+    {
+      "epoch": 1.277533039647577,
+      "grad_norm": 1.981595215749417,
+      "learning_rate": 2.5818548950504342e-06,
+      "loss": 1.0108,
+      "step": 290
+    },
+    {
+      "epoch": 1.3215859030837005,
+      "grad_norm": 1.6455591880816465,
+      "learning_rate": 2.541111292830951e-06,
+      "loss": 1.0294,
+      "step": 300
+    },
+    {
+      "epoch": 1.3656387665198237,
+      "grad_norm": 1.5108115682140577,
+      "learning_rate": 2.4988284756505333e-06,
+      "loss": 0.9748,
+      "step": 310
+    },
+    {
+      "epoch": 1.4096916299559472,
+      "grad_norm": 1.5787304886557472,
+      "learning_rate": 2.455068955889216e-06,
+      "loss": 1.0054,
+      "step": 320
+    },
+    {
+      "epoch": 1.4537444933920705,
+      "grad_norm": 1.6633458413004865,
+      "learning_rate": 2.4098974291352257e-06,
+      "loss": 1.0155,
+      "step": 330
+    },
+    {
+      "epoch": 1.497797356828194,
+      "grad_norm": 1.7167391655172333,
+      "learning_rate": 2.3633806785367873e-06,
+      "loss": 1.0677,
+      "step": 340
+    },
+    {
+      "epoch": 1.5418502202643172,
+      "grad_norm": 1.519612290214899,
+      "learning_rate": 2.315587476067607e-06,
+      "loss": 0.987,
+      "step": 350
+    },
+    {
+      "epoch": 1.5859030837004404,
+      "grad_norm": 1.6948233763887988,
+      "learning_rate": 2.2665884808520048e-06,
+      "loss": 1.0526,
+      "step": 360
+    },
+    {
+      "epoch": 1.6299559471365639,
+      "grad_norm": 1.6931931897778194,
+      "learning_rate": 2.2164561347000213e-06,
+      "loss": 1.0304,
+      "step": 370
+    },
+    {
+      "epoch": 1.6740088105726874,
+      "grad_norm": 1.5818868292083217,
+      "learning_rate": 2.1652645550069394e-06,
+      "loss": 0.9921,
+      "step": 380
+    },
+    {
+      "epoch": 1.7180616740088106,
+      "grad_norm": 1.670222373489549,
+      "learning_rate": 2.113089425175561e-06,
+      "loss": 1.0062,
+      "step": 390
+    },
+    {
+      "epoch": 1.7621145374449338,
+      "grad_norm": 1.5676805638818068,
+      "learning_rate": 2.0600078827232473e-06,
+      "loss": 0.993,
+      "step": 400
+    },
+    {
+      "epoch": 1.8061674008810573,
+      "grad_norm": 1.6518866030477966,
+      "learning_rate": 2.006098405239142e-06,
+      "loss": 0.989,
+      "step": 410
+    },
+    {
+      "epoch": 1.8502202643171806,
+      "grad_norm": 1.7025140153769915,
+      "learning_rate": 1.95144069436019e-06,
+      "loss": 1.0184,
+      "step": 420
+    },
+    {
+      "epoch": 1.894273127753304,
+      "grad_norm": 1.6535956905677116,
+      "learning_rate": 1.896115557937476e-06,
+      "loss": 1.0655,
+      "step": 430
+    },
+    {
+      "epoch": 1.9383259911894273,
+      "grad_norm": 1.6062899976218377,
+      "learning_rate": 1.8402047905671065e-06,
+      "loss": 1.0139,
+      "step": 440
+    },
+    {
+      "epoch": 1.9823788546255505,
+      "grad_norm": 1.6037621791723693,
+      "learning_rate": 1.7837910526622437e-06,
+      "loss": 1.0103,
+      "step": 450
+    },
+    {
+      "epoch": 2.026431718061674,
+      "grad_norm": 2.347205562826239,
+      "learning_rate": 1.726957748245093e-06,
+      "loss": 0.8977,
+      "step": 460
+    },
+    {
+      "epoch": 2.0704845814977975,
+      "grad_norm": 1.9061910666122825,
+      "learning_rate": 1.6697889016395088e-06,
+      "loss": 0.8438,
+      "step": 470
+    },
+    {
+      "epoch": 2.1145374449339207,
+      "grad_norm": 1.6451786150601784,
+      "learning_rate": 1.6123690332465296e-06,
+      "loss": 0.9008,
+      "step": 480
+    },
+    {
+      "epoch": 2.158590308370044,
+      "grad_norm": 1.8874201469690022,
+      "learning_rate": 1.5547830345864886e-06,
+      "loss": 0.8176,
+      "step": 490
+    },
+    {
+      "epoch": 2.202643171806167,
+      "grad_norm": 1.9254603832738357,
+      "learning_rate": 1.4971160427924554e-06,
+      "loss": 0.8901,
+      "step": 500
+    },
+    {
+      "epoch": 2.246696035242291,
+      "grad_norm": 1.835023323363367,
+      "learning_rate": 1.439453314740552e-06,
+      "loss": 0.8247,
+      "step": 510
+    },
+    {
+      "epoch": 2.290748898678414,
+      "grad_norm": 1.93123359826113,
+      "learning_rate": 1.381880101003235e-06,
+      "loss": 0.8294,
+      "step": 520
+    },
+    {
+      "epoch": 2.3348017621145374,
+      "grad_norm": 1.866122498094617,
+      "learning_rate": 1.3244815198119024e-06,
+      "loss": 0.9032,
+      "step": 530
+    },
+    {
+      "epoch": 2.3788546255506606,
+      "grad_norm": 1.7177415721533669,
+      "learning_rate": 1.2673424312151519e-06,
+      "loss": 0.8862,
+      "step": 540
+    },
+    {
+      "epoch": 2.4229074889867843,
+      "grad_norm": 2.1997603304322237,
+      "learning_rate": 1.2105473116187517e-06,
+      "loss": 0.894,
+      "step": 550
+    },
+    {
+      "epoch": 2.4669603524229076,
+      "grad_norm": 1.8715395183959846,
+      "learning_rate": 1.154180128892796e-06,
+      "loss": 0.8126,
+      "step": 560
+    },
+    {
+      "epoch": 2.511013215859031,
+      "grad_norm": 1.86690865903126,
+      "learning_rate": 1.0983242182307033e-06,
+      "loss": 0.8059,
+      "step": 570
+    },
+    {
+      "epoch": 2.555066079295154,
+      "grad_norm": 2.0917187570122517,
+      "learning_rate": 1.0430621589435803e-06,
+      "loss": 0.8959,
+      "step": 580
+    },
+    {
+      "epoch": 2.5991189427312777,
+      "grad_norm": 2.558938317516458,
+      "learning_rate": 9.884756523721117e-07,
+      "loss": 0.8393,
+      "step": 590
+    },
+    {
+      "epoch": 2.643171806167401,
+      "grad_norm": 1.5987062295416765,
+      "learning_rate": 9.346454010964724e-07,
+      "loss": 0.862,
+      "step": 600
+    },
+    {
+      "epoch": 2.6872246696035242,
+      "grad_norm": 1.6649451786987866,
+      "learning_rate": 8.816509896228376e-07,
+      "loss": 0.859,
+      "step": 610
+    },
+    {
+      "epoch": 2.7312775330396475,
+      "grad_norm": 1.6834312437789734,
+      "learning_rate": 8.295707667228987e-07,
+      "loss": 0.8348,
+      "step": 620
+    },
+    {
+      "epoch": 2.7753303964757707,
+      "grad_norm": 1.7102647759571665,
+      "learning_rate": 7.784817296003237e-07,
+      "loss": 0.8668,
+      "step": 630
+    },
+    {
+      "epoch": 2.8193832599118944,
+      "grad_norm": 1.7566168287161772,
+      "learning_rate": 7.284594100554311e-07,
+      "loss": 0.8627,
+      "step": 640
+    },
+    {
+      "epoch": 2.8634361233480177,
+      "grad_norm": 1.7731380983410612,
+      "learning_rate": 6.7957776281636e-07,
+      "loss": 0.855,
+      "step": 650
+    },
+    {
+      "epoch": 2.907488986784141,
+      "grad_norm": 3.413162667971741,
+      "learning_rate": 6.31909056201842e-07,
+      "loss": 0.8849,
+      "step": 660
+    },
+    {
+      "epoch": 2.951541850220264,
+      "grad_norm": 1.793806206724264,
+      "learning_rate": 5.855237652772183e-07,
+      "loss": 0.8629,
+      "step": 670
+    },
+    {
+      "epoch": 2.995594713656388,
+      "grad_norm": 1.7832177184392761,
+      "learning_rate": 5.404904676616635e-07,
+      "loss": 0.8796,
+      "step": 680
+    },
+    {
+      "epoch": 3.039647577092511,
+      "grad_norm": 13.295009142965908,
+      "learning_rate": 4.968757421406609e-07,
+      "loss": 0.779,
+      "step": 690
+    },
+    {
+      "epoch": 3.0837004405286343,
+      "grad_norm": 1.8559346739765339,
+      "learning_rate": 4.547440702336238e-07,
+      "loss": 0.7582,
+      "step": 700
+    },
+    {
+      "epoch": 3.1277533039647576,
+      "grad_norm": 1.7949928357857732,
+      "learning_rate": 4.1415774086218277e-07,
+      "loss": 0.7063,
+      "step": 710
+    },
+    {
+      "epoch": 3.171806167400881,
+      "grad_norm": 1.778323655929332,
+      "learning_rate": 3.7517675826009083e-07,
+      "loss": 0.752,
+      "step": 720
+    },
+    {
+      "epoch": 3.2158590308370045,
+      "grad_norm": 6.004368017727455,
+      "learning_rate": 3.378587532608872e-07,
+      "loss": 0.7829,
+      "step": 730
+    },
+    {
+      "epoch": 3.2599118942731278,
+      "grad_norm": 1.9250826926237672,
+      "learning_rate": 3.0225889809447925e-07,
+      "loss": 0.72,
+      "step": 740
+    },
+    {
+      "epoch": 3.303964757709251,
+      "grad_norm": 1.8286462728037371,
+      "learning_rate": 2.684298248186077e-07,
+      "loss": 0.7852,
+      "step": 750
+    },
+    {
+      "epoch": 3.3480176211453743,
+      "grad_norm": 1.8502492223085096,
+      "learning_rate": 2.3642154750579275e-07,
+      "loss": 0.7912,
+      "step": 760
+    },
+    {
+      "epoch": 3.392070484581498,
+      "grad_norm": 1.8690732598717457,
+      "learning_rate": 2.0628138830079696e-07,
+      "loss": 0.7456,
+      "step": 770
+    },
+    {
+      "epoch": 3.436123348017621,
+      "grad_norm": 2.841225832952903,
+      "learning_rate": 1.7805390745792993e-07,
+      "loss": 0.7654,
+      "step": 780
+    },
+    {
+      "epoch": 3.4801762114537445,
+      "grad_norm": 2.2582022273376845,
+      "learning_rate": 1.5178083746162667e-07,
+      "loss": 0.7437,
+      "step": 790
+    },
+    {
+      "epoch": 3.5242290748898677,
+      "grad_norm": 1.874522268468866,
+      "learning_rate": 1.2750102132769738e-07,
+      "loss": 0.7834,
+      "step": 800
+    },
+    {
+      "epoch": 3.568281938325991,
+      "grad_norm": 2.037336725579371,
+      "learning_rate": 1.0525035517647014e-07,
+      "loss": 0.7943,
+      "step": 810
+    },
+    {
+      "epoch": 3.6123348017621146,
+      "grad_norm": 1.7256797980612035,
+      "learning_rate": 8.50617351627232e-08,
+      "loss": 0.7826,
+      "step": 820
+    },
+    {
+      "epoch": 3.656387665198238,
+      "grad_norm": 1.8660504133848668,
+      "learning_rate": 6.696500884087259e-08,
+      "loss": 0.8379,
+      "step": 830
+    },
+    {
+      "epoch": 3.700440528634361,
+      "grad_norm": 1.6608110580956394,
+      "learning_rate": 5.0986931037314666e-08,
+      "loss": 0.7614,
+      "step": 840
+    },
+    {
+      "epoch": 3.744493392070485,
+      "grad_norm": 2.132591912569078,
+      "learning_rate": 3.7151124295163374e-08,
+      "loss": 0.8152,
+      "step": 850
+    },
+    {
+      "epoch": 3.788546255506608,
+      "grad_norm": 2.142924158927503,
+      "learning_rate": 2.5478043949868192e-08,
+      "loss": 0.7517,
+      "step": 860
+    },
+    {
+      "epoch": 3.8325991189427313,
+      "grad_norm": 2.1270227065723284,
+      "learning_rate": 1.5984947887334623e-08,
+      "loss": 0.7697,
+      "step": 870
+    },
+    {
+      "epoch": 3.8766519823788546,
+      "grad_norm": 1.8195791930606864,
+      "learning_rate": 8.685871029272318e-09,
+      "loss": 0.7506,
+      "step": 880
+    },
+    {
+      "epoch": 3.920704845814978,
+      "grad_norm": 2.2849986922595553,
+      "learning_rate": 3.5916045834781253e-09,
+      "loss": 0.7273,
+      "step": 890
+    },
+    {
+      "epoch": 3.964757709251101,
+      "grad_norm": 1.8303283767313243,
+      "learning_rate": 7.096800897425371e-10,
+      "loss": 0.8123,
+      "step": 900
+    },
+    {
+      "epoch": 4.0,
+      "step": 908,
+      "total_flos": 648773332107264.0,
+      "train_loss": 0.9660957064397535,
+      "train_runtime": 3882.5924,
+      "train_samples_per_second": 5.59,
+      "train_steps_per_second": 0.234
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 648773332107264.0,
+  "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 sha256:99f241f6bbafa577e72e3c7d4fb8440e32b855b9de95aec1a49a5eb46128cb11
+size 7160