Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: mistralai/Mistral-7B-v0.3
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: oh-mistral-bs1024_lr2.00E-06_schedulerconstant_warmup5.00E-02_minlr
+  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. -->
+
+# oh-mistral-bs1024_lr2.00E-06_schedulerconstant_warmup5.00E-02_minlr
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 64
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 1024
+- total_eval_batch_size: 512
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.0.2
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2591282618695680.0,
+    "train_loss": 0.5347004343372906,
+    "train_runtime": 11473.9369,
+    "train_samples_per_second": 69.018,
+    "train_steps_per_second": 0.067
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/marianna/models/mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e2900e400039b34ee5489b71e295919d9e38926f5cf8633a1aa91b1381c8cc
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbeadd9cb298063f655499d0312e7e760603e07deeb778be8f316949b192024
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66798a881c71a749bb1d90e537d23761db51a41f10b5b8bd7ec7cdb8baa8f8a
+size 4546807800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2591282618695680.0,
+    "train_loss": 0.5347004343372906,
+    "train_runtime": 11473.9369,
+    "train_samples_per_second": 69.018,
+    "train_steps_per_second": 0.067
+}

trainer_log.jsonl

@@ -0,0 +1,78 @@
+{"current_steps": 10, "total_steps": 774, "loss": 0.721, "learning_rate": 2e-06, "epoch": 0.03875968992248062, "percentage": 1.29, "elapsed_time": "0:02:26", "remaining_time": "3:06:21"}
+{"current_steps": 20, "total_steps": 774, "loss": 0.6438, "learning_rate": 2e-06, "epoch": 0.07751937984496124, "percentage": 2.58, "elapsed_time": "0:04:54", "remaining_time": "3:05:02"}
+{"current_steps": 30, "total_steps": 774, "loss": 0.6248, "learning_rate": 2e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:07:20", "remaining_time": "3:02:12"}
+{"current_steps": 40, "total_steps": 774, "loss": 0.6155, "learning_rate": 2e-06, "epoch": 0.15503875968992248, "percentage": 5.17, "elapsed_time": "0:09:49", "remaining_time": "3:00:25"}
+{"current_steps": 50, "total_steps": 774, "loss": 0.6022, "learning_rate": 2e-06, "epoch": 0.1937984496124031, "percentage": 6.46, "elapsed_time": "0:12:18", "remaining_time": "2:58:14"}
+{"current_steps": 60, "total_steps": 774, "loss": 0.6008, "learning_rate": 2e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:14:45", "remaining_time": "2:55:41"}
+{"current_steps": 70, "total_steps": 774, "loss": 0.5995, "learning_rate": 2e-06, "epoch": 0.2713178294573643, "percentage": 9.04, "elapsed_time": "0:17:13", "remaining_time": "2:53:12"}
+{"current_steps": 80, "total_steps": 774, "loss": 0.5919, "learning_rate": 2e-06, "epoch": 0.31007751937984496, "percentage": 10.34, "elapsed_time": "0:19:40", "remaining_time": "2:50:37"}
+{"current_steps": 90, "total_steps": 774, "loss": 0.5883, "learning_rate": 2e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:22:08", "remaining_time": "2:48:15"}
+{"current_steps": 100, "total_steps": 774, "loss": 0.5867, "learning_rate": 2e-06, "epoch": 0.3875968992248062, "percentage": 12.92, "elapsed_time": "0:24:36", "remaining_time": "2:45:54"}
+{"current_steps": 110, "total_steps": 774, "loss": 0.5824, "learning_rate": 2e-06, "epoch": 0.4263565891472868, "percentage": 14.21, "elapsed_time": "0:27:07", "remaining_time": "2:43:45"}
+{"current_steps": 120, "total_steps": 774, "loss": 0.5768, "learning_rate": 2e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:29:45", "remaining_time": "2:42:09"}
+{"current_steps": 130, "total_steps": 774, "loss": 0.5791, "learning_rate": 2e-06, "epoch": 0.5038759689922481, "percentage": 16.8, "elapsed_time": "0:32:11", "remaining_time": "2:39:30"}
+{"current_steps": 140, "total_steps": 774, "loss": 0.5769, "learning_rate": 2e-06, "epoch": 0.5426356589147286, "percentage": 18.09, "elapsed_time": "0:34:39", "remaining_time": "2:36:56"}
+{"current_steps": 150, "total_steps": 774, "loss": 0.5808, "learning_rate": 2e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "0:37:08", "remaining_time": "2:34:30"}
+{"current_steps": 160, "total_steps": 774, "loss": 0.5704, "learning_rate": 2e-06, "epoch": 0.6201550387596899, "percentage": 20.67, "elapsed_time": "0:39:36", "remaining_time": "2:31:58"}
+{"current_steps": 170, "total_steps": 774, "loss": 0.5689, "learning_rate": 2e-06, "epoch": 0.6589147286821705, "percentage": 21.96, "elapsed_time": "0:42:04", "remaining_time": "2:29:28"}
+{"current_steps": 180, "total_steps": 774, "loss": 0.5668, "learning_rate": 2e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:44:32", "remaining_time": "2:27:00"}
+{"current_steps": 190, "total_steps": 774, "loss": 0.5753, "learning_rate": 2e-06, "epoch": 0.7364341085271318, "percentage": 24.55, "elapsed_time": "0:47:01", "remaining_time": "2:24:32"}
+{"current_steps": 200, "total_steps": 774, "loss": 0.5652, "learning_rate": 2e-06, "epoch": 0.7751937984496124, "percentage": 25.84, "elapsed_time": "0:49:28", "remaining_time": "2:21:58"}
+{"current_steps": 210, "total_steps": 774, "loss": 0.5683, "learning_rate": 2e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "0:51:55", "remaining_time": "2:19:26"}
+{"current_steps": 220, "total_steps": 774, "loss": 0.5673, "learning_rate": 2e-06, "epoch": 0.8527131782945736, "percentage": 28.42, "elapsed_time": "0:54:22", "remaining_time": "2:16:56"}
+{"current_steps": 230, "total_steps": 774, "loss": 0.5643, "learning_rate": 2e-06, "epoch": 0.8914728682170543, "percentage": 29.72, "elapsed_time": "0:56:49", "remaining_time": "2:14:25"}
+{"current_steps": 240, "total_steps": 774, "loss": 0.5649, "learning_rate": 2e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:59:17", "remaining_time": "2:11:54"}
+{"current_steps": 250, "total_steps": 774, "loss": 0.5597, "learning_rate": 2e-06, "epoch": 0.9689922480620154, "percentage": 32.3, "elapsed_time": "1:01:44", "remaining_time": "2:09:25"}
+{"current_steps": 260, "total_steps": 774, "loss": 0.5571, "learning_rate": 2e-06, "epoch": 1.0077519379844961, "percentage": 33.59, "elapsed_time": "1:04:32", "remaining_time": "2:07:35"}
+{"current_steps": 270, "total_steps": 774, "loss": 0.5299, "learning_rate": 2e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "1:07:00", "remaining_time": "2:05:04"}
+{"current_steps": 280, "total_steps": 774, "loss": 0.5317, "learning_rate": 2e-06, "epoch": 1.0852713178294573, "percentage": 36.18, "elapsed_time": "1:09:28", "remaining_time": "2:02:34"}
+{"current_steps": 290, "total_steps": 774, "loss": 0.5275, "learning_rate": 2e-06, "epoch": 1.124031007751938, "percentage": 37.47, "elapsed_time": "1:11:55", "remaining_time": "2:00:01"}
+{"current_steps": 300, "total_steps": 774, "loss": 0.5236, "learning_rate": 2e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "1:14:25", "remaining_time": "1:57:35"}
+{"current_steps": 310, "total_steps": 774, "loss": 0.5306, "learning_rate": 2e-06, "epoch": 1.2015503875968991, "percentage": 40.05, "elapsed_time": "1:16:54", "remaining_time": "1:55:06"}
+{"current_steps": 320, "total_steps": 774, "loss": 0.5277, "learning_rate": 2e-06, "epoch": 1.2403100775193798, "percentage": 41.34, "elapsed_time": "1:19:20", "remaining_time": "1:52:34"}
+{"current_steps": 330, "total_steps": 774, "loss": 0.5274, "learning_rate": 2e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "1:21:48", "remaining_time": "1:50:03"}
+{"current_steps": 340, "total_steps": 774, "loss": 0.531, "learning_rate": 2e-06, "epoch": 1.3178294573643412, "percentage": 43.93, "elapsed_time": "1:24:16", "remaining_time": "1:47:34"}
+{"current_steps": 350, "total_steps": 774, "loss": 0.5275, "learning_rate": 2e-06, "epoch": 1.3565891472868217, "percentage": 45.22, "elapsed_time": "1:26:42", "remaining_time": "1:45:02"}
+{"current_steps": 360, "total_steps": 774, "loss": 0.5317, "learning_rate": 2e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "1:29:12", "remaining_time": "1:42:35"}
+{"current_steps": 370, "total_steps": 774, "loss": 0.5297, "learning_rate": 2e-06, "epoch": 1.4341085271317828, "percentage": 47.8, "elapsed_time": "1:31:38", "remaining_time": "1:40:04"}
+{"current_steps": 380, "total_steps": 774, "loss": 0.526, "learning_rate": 2e-06, "epoch": 1.4728682170542635, "percentage": 49.1, "elapsed_time": "1:34:03", "remaining_time": "1:37:31"}
+{"current_steps": 390, "total_steps": 774, "loss": 0.5293, "learning_rate": 2e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "1:36:33", "remaining_time": "1:35:04"}
+{"current_steps": 400, "total_steps": 774, "loss": 0.5255, "learning_rate": 2e-06, "epoch": 1.550387596899225, "percentage": 51.68, "elapsed_time": "1:38:58", "remaining_time": "1:32:32"}
+{"current_steps": 410, "total_steps": 774, "loss": 0.5211, "learning_rate": 2e-06, "epoch": 1.5891472868217056, "percentage": 52.97, "elapsed_time": "1:41:24", "remaining_time": "1:30:01"}
+{"current_steps": 420, "total_steps": 774, "loss": 0.526, "learning_rate": 2e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "1:43:50", "remaining_time": "1:27:31"}
+{"current_steps": 430, "total_steps": 774, "loss": 0.5288, "learning_rate": 2e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:46:17", "remaining_time": "1:25:01"}
+{"current_steps": 440, "total_steps": 774, "loss": 0.5241, "learning_rate": 2e-06, "epoch": 1.7054263565891472, "percentage": 56.85, "elapsed_time": "1:48:42", "remaining_time": "1:22:31"}
+{"current_steps": 450, "total_steps": 774, "loss": 0.5272, "learning_rate": 2e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "1:51:10", "remaining_time": "1:20:02"}
+{"current_steps": 460, "total_steps": 774, "loss": 0.5226, "learning_rate": 2e-06, "epoch": 1.7829457364341086, "percentage": 59.43, "elapsed_time": "1:53:35", "remaining_time": "1:17:32"}
+{"current_steps": 470, "total_steps": 774, "loss": 0.5242, "learning_rate": 2e-06, "epoch": 1.8217054263565893, "percentage": 60.72, "elapsed_time": "1:56:01", "remaining_time": "1:15:02"}
+{"current_steps": 480, "total_steps": 774, "loss": 0.5273, "learning_rate": 2e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "1:58:29", "remaining_time": "1:12:34"}
+{"current_steps": 490, "total_steps": 774, "loss": 0.5236, "learning_rate": 2e-06, "epoch": 1.8992248062015504, "percentage": 63.31, "elapsed_time": "2:00:55", "remaining_time": "1:10:05"}
+{"current_steps": 500, "total_steps": 774, "loss": 0.5263, "learning_rate": 2e-06, "epoch": 1.937984496124031, "percentage": 64.6, "elapsed_time": "2:03:23", "remaining_time": "1:07:36"}
+{"current_steps": 510, "total_steps": 774, "loss": 0.5231, "learning_rate": 2e-06, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "2:05:49", "remaining_time": "1:05:07"}
+{"current_steps": 520, "total_steps": 774, "loss": 0.5092, "learning_rate": 2e-06, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "2:08:30", "remaining_time": "1:02:46"}
+{"current_steps": 530, "total_steps": 774, "loss": 0.4867, "learning_rate": 2e-06, "epoch": 2.054263565891473, "percentage": 68.48, "elapsed_time": "2:10:59", "remaining_time": "1:00:18"}
+{"current_steps": 540, "total_steps": 774, "loss": 0.4842, "learning_rate": 2e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "2:13:25", "remaining_time": "0:57:48"}
+{"current_steps": 550, "total_steps": 774, "loss": 0.4843, "learning_rate": 2e-06, "epoch": 2.1317829457364343, "percentage": 71.06, "elapsed_time": "2:15:51", "remaining_time": "0:55:19"}
+{"current_steps": 560, "total_steps": 774, "loss": 0.4878, "learning_rate": 2e-06, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "2:18:17", "remaining_time": "0:52:50"}
+{"current_steps": 570, "total_steps": 774, "loss": 0.4852, "learning_rate": 2e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "2:20:42", "remaining_time": "0:50:21"}
+{"current_steps": 580, "total_steps": 774, "loss": 0.4858, "learning_rate": 2e-06, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "2:23:09", "remaining_time": "0:47:53"}
+{"current_steps": 590, "total_steps": 774, "loss": 0.4893, "learning_rate": 2e-06, "epoch": 2.2868217054263567, "percentage": 76.23, "elapsed_time": "2:25:36", "remaining_time": "0:45:24"}
+{"current_steps": 600, "total_steps": 774, "loss": 0.4858, "learning_rate": 2e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "2:28:03", "remaining_time": "0:42:56"}
+{"current_steps": 610, "total_steps": 774, "loss": 0.4893, "learning_rate": 2e-06, "epoch": 2.3643410852713176, "percentage": 78.81, "elapsed_time": "2:30:30", "remaining_time": "0:40:27"}
+{"current_steps": 620, "total_steps": 774, "loss": 0.4893, "learning_rate": 2e-06, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "2:32:56", "remaining_time": "0:37:59"}
+{"current_steps": 630, "total_steps": 774, "loss": 0.4879, "learning_rate": 2e-06, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "2:35:23", "remaining_time": "0:35:31"}
+{"current_steps": 640, "total_steps": 774, "loss": 0.4905, "learning_rate": 2e-06, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "2:37:49", "remaining_time": "0:33:02"}
+{"current_steps": 650, "total_steps": 774, "loss": 0.4861, "learning_rate": 2e-06, "epoch": 2.5193798449612403, "percentage": 83.98, "elapsed_time": "2:40:15", "remaining_time": "0:30:34"}
+{"current_steps": 660, "total_steps": 774, "loss": 0.4893, "learning_rate": 2e-06, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "2:42:41", "remaining_time": "0:28:06"}
+{"current_steps": 670, "total_steps": 774, "loss": 0.4915, "learning_rate": 2e-06, "epoch": 2.5968992248062017, "percentage": 86.56, "elapsed_time": "2:45:08", "remaining_time": "0:25:38"}
+{"current_steps": 680, "total_steps": 774, "loss": 0.4847, "learning_rate": 2e-06, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "2:47:35", "remaining_time": "0:23:10"}
+{"current_steps": 690, "total_steps": 774, "loss": 0.4876, "learning_rate": 2e-06, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "2:50:01", "remaining_time": "0:20:41"}
+{"current_steps": 700, "total_steps": 774, "loss": 0.4876, "learning_rate": 2e-06, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "2:52:28", "remaining_time": "0:18:14"}
+{"current_steps": 710, "total_steps": 774, "loss": 0.4839, "learning_rate": 2e-06, "epoch": 2.751937984496124, "percentage": 91.73, "elapsed_time": "2:54:55", "remaining_time": "0:15:46"}
+{"current_steps": 720, "total_steps": 774, "loss": 0.4898, "learning_rate": 2e-06, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "2:57:21", "remaining_time": "0:13:18"}
+{"current_steps": 730, "total_steps": 774, "loss": 0.4899, "learning_rate": 2e-06, "epoch": 2.8294573643410854, "percentage": 94.32, "elapsed_time": "2:59:47", "remaining_time": "0:10:50"}
+{"current_steps": 740, "total_steps": 774, "loss": 0.4892, "learning_rate": 2e-06, "epoch": 2.8682170542635657, "percentage": 95.61, "elapsed_time": "3:02:13", "remaining_time": "0:08:22"}
+{"current_steps": 750, "total_steps": 774, "loss": 0.4864, "learning_rate": 2e-06, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "3:04:39", "remaining_time": "0:05:54"}
+{"current_steps": 760, "total_steps": 774, "loss": 0.4881, "learning_rate": 2e-06, "epoch": 2.945736434108527, "percentage": 98.19, "elapsed_time": "3:07:06", "remaining_time": "0:03:26"}
+{"current_steps": 770, "total_steps": 774, "loss": 0.488, "learning_rate": 2e-06, "epoch": 2.9844961240310077, "percentage": 99.48, "elapsed_time": "3:09:33", "remaining_time": "0:00:59"}
+{"current_steps": 774, "total_steps": 774, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:11:10", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,581 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 774,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03875968992248062,
+      "grad_norm": 2.577054727951972,
+      "learning_rate": 2e-06,
+      "loss": 0.721,
+      "step": 10
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 1.3292498101090573,
+      "learning_rate": 2e-06,
+      "loss": 0.6438,
+      "step": 20
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 2.3414148705752926,
+      "learning_rate": 2e-06,
+      "loss": 0.6248,
+      "step": 30
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 2.621497754252154,
+      "learning_rate": 2e-06,
+      "loss": 0.6155,
+      "step": 40
+    },
+    {
+      "epoch": 0.1937984496124031,
+      "grad_norm": 1.642709929025015,
+      "learning_rate": 2e-06,
+      "loss": 0.6022,
+      "step": 50
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.4108572822591154,
+      "learning_rate": 2e-06,
+      "loss": 0.6008,
+      "step": 60
+    },
+    {
+      "epoch": 0.2713178294573643,
+      "grad_norm": 1.8320230338483412,
+      "learning_rate": 2e-06,
+      "loss": 0.5995,
+      "step": 70
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 2.0509677067609906,
+      "learning_rate": 2e-06,
+      "loss": 0.5919,
+      "step": 80
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 1.8615028380190877,
+      "learning_rate": 2e-06,
+      "loss": 0.5883,
+      "step": 90
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 1.651732467548723,
+      "learning_rate": 2e-06,
+      "loss": 0.5867,
+      "step": 100
+    },
+    {
+      "epoch": 0.4263565891472868,
+      "grad_norm": 1.827483286285098,
+      "learning_rate": 2e-06,
+      "loss": 0.5824,
+      "step": 110
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.878984672982078,
+      "learning_rate": 2e-06,
+      "loss": 0.5768,
+      "step": 120
+    },
+    {
+      "epoch": 0.5038759689922481,
+      "grad_norm": 1.461881748693503,
+      "learning_rate": 2e-06,
+      "loss": 0.5791,
+      "step": 130
+    },
+    {
+      "epoch": 0.5426356589147286,
+      "grad_norm": 1.7965397328352164,
+      "learning_rate": 2e-06,
+      "loss": 0.5769,
+      "step": 140
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 1.9228942975753127,
+      "learning_rate": 2e-06,
+      "loss": 0.5808,
+      "step": 150
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 1.1676070598043125,
+      "learning_rate": 2e-06,
+      "loss": 0.5704,
+      "step": 160
+    },
+    {
+      "epoch": 0.6589147286821705,
+      "grad_norm": 1.1754765506774811,
+      "learning_rate": 2e-06,
+      "loss": 0.5689,
+      "step": 170
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 1.7812488410180551,
+      "learning_rate": 2e-06,
+      "loss": 0.5668,
+      "step": 180
+    },
+    {
+      "epoch": 0.7364341085271318,
+      "grad_norm": 1.808692259046032,
+      "learning_rate": 2e-06,
+      "loss": 0.5753,
+      "step": 190
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 1.8584614057755389,
+      "learning_rate": 2e-06,
+      "loss": 0.5652,
+      "step": 200
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 1.599864515399134,
+      "learning_rate": 2e-06,
+      "loss": 0.5683,
+      "step": 210
+    },
+    {
+      "epoch": 0.8527131782945736,
+      "grad_norm": 1.6516869387309938,
+      "learning_rate": 2e-06,
+      "loss": 0.5673,
+      "step": 220
+    },
+    {
+      "epoch": 0.8914728682170543,
+      "grad_norm": 1.6848137903140608,
+      "learning_rate": 2e-06,
+      "loss": 0.5643,
+      "step": 230
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.3032607046739686,
+      "learning_rate": 2e-06,
+      "loss": 0.5649,
+      "step": 240
+    },
+    {
+      "epoch": 0.9689922480620154,
+      "grad_norm": 1.5431955138670315,
+      "learning_rate": 2e-06,
+      "loss": 0.5597,
+      "step": 250
+    },
+    {
+      "epoch": 1.0077519379844961,
+      "grad_norm": 2.0310291210286238,
+      "learning_rate": 2e-06,
+      "loss": 0.5571,
+      "step": 260
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 1.2551497648955234,
+      "learning_rate": 2e-06,
+      "loss": 0.5299,
+      "step": 270
+    },
+    {
+      "epoch": 1.0852713178294573,
+      "grad_norm": 1.1678057917636586,
+      "learning_rate": 2e-06,
+      "loss": 0.5317,
+      "step": 280
+    },
+    {
+      "epoch": 1.124031007751938,
+      "grad_norm": 1.125227296422933,
+      "learning_rate": 2e-06,
+      "loss": 0.5275,
+      "step": 290
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.3900860537725233,
+      "learning_rate": 2e-06,
+      "loss": 0.5236,
+      "step": 300
+    },
+    {
+      "epoch": 1.2015503875968991,
+      "grad_norm": 1.2021576698979493,
+      "learning_rate": 2e-06,
+      "loss": 0.5306,
+      "step": 310
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 1.2053080767276194,
+      "learning_rate": 2e-06,
+      "loss": 0.5277,
+      "step": 320
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 1.3991030309565773,
+      "learning_rate": 2e-06,
+      "loss": 0.5274,
+      "step": 330
+    },
+    {
+      "epoch": 1.3178294573643412,
+      "grad_norm": 1.1826629752006035,
+      "learning_rate": 2e-06,
+      "loss": 0.531,
+      "step": 340
+    },
+    {
+      "epoch": 1.3565891472868217,
+      "grad_norm": 1.1287968703954268,
+      "learning_rate": 2e-06,
+      "loss": 0.5275,
+      "step": 350
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.5127256802296236,
+      "learning_rate": 2e-06,
+      "loss": 0.5317,
+      "step": 360
+    },
+    {
+      "epoch": 1.4341085271317828,
+      "grad_norm": 1.5013875357775832,
+      "learning_rate": 2e-06,
+      "loss": 0.5297,
+      "step": 370
+    },
+    {
+      "epoch": 1.4728682170542635,
+      "grad_norm": 1.7614327167944768,
+      "learning_rate": 2e-06,
+      "loss": 0.526,
+      "step": 380
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 1.4214027958077065,
+      "learning_rate": 2e-06,
+      "loss": 0.5293,
+      "step": 390
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 1.6564120069131323,
+      "learning_rate": 2e-06,
+      "loss": 0.5255,
+      "step": 400
+    },
+    {
+      "epoch": 1.5891472868217056,
+      "grad_norm": 1.378206427304318,
+      "learning_rate": 2e-06,
+      "loss": 0.5211,
+      "step": 410
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.988629014217936,
+      "learning_rate": 2e-06,
+      "loss": 0.526,
+      "step": 420
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.9503056920319735,
+      "learning_rate": 2e-06,
+      "loss": 0.5288,
+      "step": 430
+    },
+    {
+      "epoch": 1.7054263565891472,
+      "grad_norm": 1.732782542682626,
+      "learning_rate": 2e-06,
+      "loss": 0.5241,
+      "step": 440
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 1.528224415622805,
+      "learning_rate": 2e-06,
+      "loss": 0.5272,
+      "step": 450
+    },
+    {
+      "epoch": 1.7829457364341086,
+      "grad_norm": 1.1793820983967487,
+      "learning_rate": 2e-06,
+      "loss": 0.5226,
+      "step": 460
+    },
+    {
+      "epoch": 1.8217054263565893,
+      "grad_norm": 1.1809068975224493,
+      "learning_rate": 2e-06,
+      "loss": 0.5242,
+      "step": 470
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 1.379981502891672,
+      "learning_rate": 2e-06,
+      "loss": 0.5273,
+      "step": 480
+    },
+    {
+      "epoch": 1.8992248062015504,
+      "grad_norm": 1.8940459651264965,
+      "learning_rate": 2e-06,
+      "loss": 0.5236,
+      "step": 490
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 1.898050329402726,
+      "learning_rate": 2e-06,
+      "loss": 0.5263,
+      "step": 500
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 1.6806097447928925,
+      "learning_rate": 2e-06,
+      "loss": 0.5231,
+      "step": 510
+    },
+    {
+      "epoch": 2.0155038759689923,
+      "grad_norm": 1.7706824956520133,
+      "learning_rate": 2e-06,
+      "loss": 0.5092,
+      "step": 520
+    },
+    {
+      "epoch": 2.054263565891473,
+      "grad_norm": 1.1944302472248438,
+      "learning_rate": 2e-06,
+      "loss": 0.4867,
+      "step": 530
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 1.3491176032576682,
+      "learning_rate": 2e-06,
+      "loss": 0.4842,
+      "step": 540
+    },
+    {
+      "epoch": 2.1317829457364343,
+      "grad_norm": 1.182447255831288,
+      "learning_rate": 2e-06,
+      "loss": 0.4843,
+      "step": 550
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 1.0865626136425315,
+      "learning_rate": 2e-06,
+      "loss": 0.4878,
+      "step": 560
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 1.1893887821883726,
+      "learning_rate": 2e-06,
+      "loss": 0.4852,
+      "step": 570
+    },
+    {
+      "epoch": 2.248062015503876,
+      "grad_norm": 1.197021602818726,
+      "learning_rate": 2e-06,
+      "loss": 0.4858,
+      "step": 580
+    },
+    {
+      "epoch": 2.2868217054263567,
+      "grad_norm": 1.0736236283669167,
+      "learning_rate": 2e-06,
+      "loss": 0.4893,
+      "step": 590
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 1.017760123624255,
+      "learning_rate": 2e-06,
+      "loss": 0.4858,
+      "step": 600
+    },
+    {
+      "epoch": 2.3643410852713176,
+      "grad_norm": 1.1866183343445358,
+      "learning_rate": 2e-06,
+      "loss": 0.4893,
+      "step": 610
+    },
+    {
+      "epoch": 2.4031007751937983,
+      "grad_norm": 1.0875734211472181,
+      "learning_rate": 2e-06,
+      "loss": 0.4893,
+      "step": 620
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 1.4175668384873126,
+      "learning_rate": 2e-06,
+      "loss": 0.4879,
+      "step": 630
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 1.5445789270591548,
+      "learning_rate": 2e-06,
+      "loss": 0.4905,
+      "step": 640
+    },
+    {
+      "epoch": 2.5193798449612403,
+      "grad_norm": 1.1527990919509379,
+      "learning_rate": 2e-06,
+      "loss": 0.4861,
+      "step": 650
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 1.0983296348010934,
+      "learning_rate": 2e-06,
+      "loss": 0.4893,
+      "step": 660
+    },
+    {
+      "epoch": 2.5968992248062017,
+      "grad_norm": 1.7393177878547021,
+      "learning_rate": 2e-06,
+      "loss": 0.4915,
+      "step": 670
+    },
+    {
+      "epoch": 2.6356589147286824,
+      "grad_norm": 1.6766013258821928,
+      "learning_rate": 2e-06,
+      "loss": 0.4847,
+      "step": 680
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 1.5674228297707393,
+      "learning_rate": 2e-06,
+      "loss": 0.4876,
+      "step": 690
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 1.5303183442776453,
+      "learning_rate": 2e-06,
+      "loss": 0.4876,
+      "step": 700
+    },
+    {
+      "epoch": 2.751937984496124,
+      "grad_norm": 1.830851000547026,
+      "learning_rate": 2e-06,
+      "loss": 0.4839,
+      "step": 710
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 1.7047867407889794,
+      "learning_rate": 2e-06,
+      "loss": 0.4898,
+      "step": 720
+    },
+    {
+      "epoch": 2.8294573643410854,
+      "grad_norm": 1.5112038359871813,
+      "learning_rate": 2e-06,
+      "loss": 0.4899,
+      "step": 730
+    },
+    {
+      "epoch": 2.8682170542635657,
+      "grad_norm": 1.4351025379161033,
+      "learning_rate": 2e-06,
+      "loss": 0.4892,
+      "step": 740
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 1.222684031513469,
+      "learning_rate": 2e-06,
+      "loss": 0.4864,
+      "step": 750
+    },
+    {
+      "epoch": 2.945736434108527,
+      "grad_norm": 1.3407496538423456,
+      "learning_rate": 2e-06,
+      "loss": 0.4881,
+      "step": 760
+    },
+    {
+      "epoch": 2.9844961240310077,
+      "grad_norm": 1.5499167243320089,
+      "learning_rate": 2e-06,
+      "loss": 0.488,
+      "step": 770
+    },
+    {
+      "epoch": 3.0,
+      "step": 774,
+      "total_flos": 2591282618695680.0,
+      "train_loss": 0.5347004343372906,
+      "train_runtime": 11473.9369,
+      "train_samples_per_second": 69.018,
+      "train_steps_per_second": 0.067
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 774,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2591282618695680.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa1da517a83cfe108f943a9818d625fc17312480140ab1ef4d3671e770407da
+size 7544