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_schedulercosine_with_min_lr_warmup5.00E-02_minlr5.00E-07
+  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_schedulercosine_with_min_lr_warmup5.00E-02_minlr5.00E-07
+
+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: cosine_with_min_lr
+- 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": 0.5421019284300101,
+    "train_runtime": 11142.1795,
+    "train_samples_per_second": 71.073,
+    "train_steps_per_second": 0.069
+}

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:ee35a9744ebaf748b7b45302058c05d280363ef78adfc1184829b8dc07e871f1
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d57d66ba997127343f9a120cd4210f71469998665e5f5c8b977ab1a8b2164c
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd83b34661b9eb220b06d0066a796b96a0678b0bb0e29bd15642569aad587ce
+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": 0.5421019284300101,
+    "train_runtime": 11142.1795,
+    "train_samples_per_second": 71.073,
+    "train_steps_per_second": 0.069
+}

trainer_log.jsonl

@@ -0,0 +1,78 @@
+{"current_steps": 10, "total_steps": 774, "loss": 0.8385, "learning_rate": 5.128205128205127e-07, "epoch": 0.03875968992248062, "percentage": 1.29, "elapsed_time": "0:02:22", "remaining_time": "3:01:01"}
+{"current_steps": 20, "total_steps": 774, "loss": 0.7404, "learning_rate": 1.0256410256410255e-06, "epoch": 0.07751937984496124, "percentage": 2.58, "elapsed_time": "0:04:43", "remaining_time": "2:58:23"}
+{"current_steps": 30, "total_steps": 774, "loss": 0.677, "learning_rate": 1.5384615384615385e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:07:05", "remaining_time": "2:56:04"}
+{"current_steps": 40, "total_steps": 774, "loss": 0.6429, "learning_rate": 1.9999931489730838e-06, "epoch": 0.15503875968992248, "percentage": 5.17, "elapsed_time": "0:09:28", "remaining_time": "2:53:56"}
+{"current_steps": 50, "total_steps": 774, "loss": 0.618, "learning_rate": 1.9991711771810467e-06, "epoch": 0.1937984496124031, "percentage": 6.46, "elapsed_time": "0:11:51", "remaining_time": "2:51:46"}
+{"current_steps": 60, "total_steps": 774, "loss": 0.611, "learning_rate": 1.996980720496429e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:14:14", "remaining_time": "2:49:31"}
+{"current_steps": 70, "total_steps": 774, "loss": 0.6065, "learning_rate": 1.993425780150154e-06, "epoch": 0.2713178294573643, "percentage": 9.04, "elapsed_time": "0:16:38", "remaining_time": "2:47:24"}
+{"current_steps": 80, "total_steps": 774, "loss": 0.5972, "learning_rate": 1.988512849827918e-06, "epoch": 0.31007751937984496, "percentage": 10.34, "elapsed_time": "0:19:01", "remaining_time": "2:45:05"}
+{"current_steps": 90, "total_steps": 774, "loss": 0.5929, "learning_rate": 1.982250903808403e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:21:24", "remaining_time": "2:42:45"}
+{"current_steps": 100, "total_steps": 774, "loss": 0.5904, "learning_rate": 1.974651380570273e-06, "epoch": 0.3875968992248062, "percentage": 12.92, "elapsed_time": "0:23:47", "remaining_time": "2:40:23"}
+{"current_steps": 110, "total_steps": 774, "loss": 0.5854, "learning_rate": 1.965728161897904e-06, "epoch": 0.4263565891472868, "percentage": 14.21, "elapsed_time": "0:26:09", "remaining_time": "2:37:56"}
+{"current_steps": 120, "total_steps": 774, "loss": 0.5797, "learning_rate": 1.9554975475240117e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:28:33", "remaining_time": "2:35:36"}
+{"current_steps": 130, "total_steps": 774, "loss": 0.5818, "learning_rate": 1.9439782253554977e-06, "epoch": 0.5038759689922481, "percentage": 16.8, "elapsed_time": "0:30:56", "remaining_time": "2:33:17"}
+{"current_steps": 140, "total_steps": 774, "loss": 0.5795, "learning_rate": 1.9311912373369e-06, "epoch": 0.5426356589147286, "percentage": 18.09, "elapsed_time": "0:33:20", "remaining_time": "2:31:00"}
+{"current_steps": 150, "total_steps": 774, "loss": 0.5834, "learning_rate": 1.9171599410138086e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "0:35:43", "remaining_time": "2:28:38"}
+{"current_steps": 160, "total_steps": 774, "loss": 0.5731, "learning_rate": 1.901909966866448e-06, "epoch": 0.6201550387596899, "percentage": 20.67, "elapsed_time": "0:38:07", "remaining_time": "2:26:16"}
+{"current_steps": 170, "total_steps": 774, "loss": 0.5712, "learning_rate": 1.8854691714913721e-06, "epoch": 0.6589147286821705, "percentage": 21.96, "elapsed_time": "0:40:30", "remaining_time": "2:23:55"}
+{"current_steps": 180, "total_steps": 774, "loss": 0.5685, "learning_rate": 1.867867586716791e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:42:53", "remaining_time": "2:21:33"}
+{"current_steps": 190, "total_steps": 774, "loss": 0.5772, "learning_rate": 1.8491373647444753e-06, "epoch": 0.7364341085271318, "percentage": 24.55, "elapsed_time": "0:45:17", "remaining_time": "2:19:11"}
+{"current_steps": 200, "total_steps": 774, "loss": 0.5671, "learning_rate": 1.8293127194184494e-06, "epoch": 0.7751937984496124, "percentage": 25.84, "elapsed_time": "0:47:39", "remaining_time": "2:16:46"}
+{"current_steps": 210, "total_steps": 774, "loss": 0.57, "learning_rate": 1.8084298637277554e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "0:50:03", "remaining_time": "2:14:25"}
+{"current_steps": 220, "total_steps": 774, "loss": 0.5688, "learning_rate": 1.786526943657445e-06, "epoch": 0.8527131782945736, "percentage": 28.42, "elapsed_time": "0:52:25", "remaining_time": "2:12:01"}
+{"current_steps": 230, "total_steps": 774, "loss": 0.5655, "learning_rate": 1.7636439685086405e-06, "epoch": 0.8914728682170543, "percentage": 29.72, "elapsed_time": "0:54:48", "remaining_time": "2:09:37"}
+{"current_steps": 240, "total_steps": 774, "loss": 0.5661, "learning_rate": 1.7398227378149364e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:57:10", "remaining_time": "2:07:13"}
+{"current_steps": 250, "total_steps": 774, "loss": 0.5606, "learning_rate": 1.7151067649886472e-06, "epoch": 0.9689922480620154, "percentage": 32.3, "elapsed_time": "0:59:33", "remaining_time": "2:04:49"}
+{"current_steps": 260, "total_steps": 774, "loss": 0.5583, "learning_rate": 1.6895411978363736e-06, "epoch": 1.0077519379844961, "percentage": 33.59, "elapsed_time": "1:02:15", "remaining_time": "2:03:04"}
+{"current_steps": 270, "total_steps": 774, "loss": 0.5313, "learning_rate": 1.6631727360890767e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "1:04:51", "remaining_time": "2:01:03"}
+{"current_steps": 280, "total_steps": 774, "loss": 0.5325, "learning_rate": 1.6360495460973065e-06, "epoch": 1.0852713178294573, "percentage": 36.18, "elapsed_time": "1:07:14", "remaining_time": "1:58:37"}
+{"current_steps": 290, "total_steps": 774, "loss": 0.5273, "learning_rate": 1.6082211728474055e-06, "epoch": 1.124031007751938, "percentage": 37.47, "elapsed_time": "1:09:36", "remaining_time": "1:56:11"}
+{"current_steps": 300, "total_steps": 774, "loss": 0.5231, "learning_rate": 1.5797384494594117e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "1:11:59", "remaining_time": "1:53:44"}
+{"current_steps": 310, "total_steps": 774, "loss": 0.5298, "learning_rate": 1.5506534043319639e-06, "epoch": 1.2015503875968991, "percentage": 40.05, "elapsed_time": "1:14:22", "remaining_time": "1:51:19"}
+{"current_steps": 320, "total_steps": 774, "loss": 0.5268, "learning_rate": 1.5210191661038422e-06, "epoch": 1.2403100775193798, "percentage": 41.34, "elapsed_time": "1:16:44", "remaining_time": "1:48:52"}
+{"current_steps": 330, "total_steps": 774, "loss": 0.5269, "learning_rate": 1.490889866605734e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "1:19:06", "remaining_time": "1:46:26"}
+{"current_steps": 340, "total_steps": 774, "loss": 0.5307, "learning_rate": 1.460320541979502e-06, "epoch": 1.3178294573643412, "percentage": 43.93, "elapsed_time": "1:21:29", "remaining_time": "1:44:00"}
+{"current_steps": 350, "total_steps": 774, "loss": 0.5279, "learning_rate": 1.429367032145583e-06, "epoch": 1.3565891472868217, "percentage": 45.22, "elapsed_time": "1:23:51", "remaining_time": "1:41:35"}
+{"current_steps": 360, "total_steps": 774, "loss": 0.5317, "learning_rate": 1.3980858788021502e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "1:26:13", "remaining_time": "1:39:09"}
+{"current_steps": 370, "total_steps": 774, "loss": 0.5295, "learning_rate": 1.3665342221423621e-06, "epoch": 1.4341085271317828, "percentage": 47.8, "elapsed_time": "1:28:35", "remaining_time": "1:36:44"}
+{"current_steps": 380, "total_steps": 774, "loss": 0.5263, "learning_rate": 1.3347696964783628e-06, "epoch": 1.4728682170542635, "percentage": 49.1, "elapsed_time": "1:30:58", "remaining_time": "1:34:19"}
+{"current_steps": 390, "total_steps": 774, "loss": 0.5299, "learning_rate": 1.3028503249626903e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "1:33:21", "remaining_time": "1:31:55"}
+{"current_steps": 400, "total_steps": 774, "loss": 0.5263, "learning_rate": 1.270834413599407e-06, "epoch": 1.550387596899225, "percentage": 51.68, "elapsed_time": "1:35:43", "remaining_time": "1:29:30"}
+{"current_steps": 410, "total_steps": 774, "loss": 0.5216, "learning_rate": 1.2387804447385523e-06, "epoch": 1.5891472868217056, "percentage": 52.97, "elapsed_time": "1:38:06", "remaining_time": "1:27:05"}
+{"current_steps": 420, "total_steps": 774, "loss": 0.5265, "learning_rate": 1.2067469702484692e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "1:40:28", "remaining_time": "1:24:41"}
+{"current_steps": 430, "total_steps": 774, "loss": 0.5294, "learning_rate": 1.1747925045611484e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:42:51", "remaining_time": "1:22:17"}
+{"current_steps": 440, "total_steps": 774, "loss": 0.5248, "learning_rate": 1.1429754177859534e-06, "epoch": 1.7054263565891472, "percentage": 56.85, "elapsed_time": "1:45:14", "remaining_time": "1:19:53"}
+{"current_steps": 450, "total_steps": 774, "loss": 0.5281, "learning_rate": 1.1113538290869735e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "1:47:37", "remaining_time": "1:17:29"}
+{"current_steps": 460, "total_steps": 774, "loss": 0.5236, "learning_rate": 1.0799855005187725e-06, "epoch": 1.7829457364341086, "percentage": 59.43, "elapsed_time": "1:49:59", "remaining_time": "1:15:05"}
+{"current_steps": 470, "total_steps": 774, "loss": 0.5251, "learning_rate": 1.0489277315144551e-06, "epoch": 1.8217054263565893, "percentage": 60.72, "elapsed_time": "1:52:21", "remaining_time": "1:12:40"}
+{"current_steps": 480, "total_steps": 774, "loss": 0.5277, "learning_rate": 1.0182372542187895e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "1:54:44", "remaining_time": "1:10:16"}
+{"current_steps": 490, "total_steps": 774, "loss": 0.5233, "learning_rate": 9.879701298575733e-07, "epoch": 1.8992248062015504, "percentage": 63.31, "elapsed_time": "1:57:07", "remaining_time": "1:07:52"}
+{"current_steps": 500, "total_steps": 774, "loss": 0.5261, "learning_rate": 9.581816463325465e-07, "epoch": 1.937984496124031, "percentage": 64.6, "elapsed_time": "1:59:29", "remaining_time": "1:05:28"}
+{"current_steps": 510, "total_steps": 774, "loss": 0.5234, "learning_rate": 9.28926217228906e-07, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "2:01:52", "remaining_time": "1:03:05"}
+{"current_steps": 520, "total_steps": 774, "loss": 0.5134, "learning_rate": 9.002572824199062e-07, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "2:04:32", "remaining_time": "1:00:50"}
+{"current_steps": 530, "total_steps": 774, "loss": 0.4961, "learning_rate": 8.722272104501032e-07, "epoch": 2.054263565891473, "percentage": 68.48, "elapsed_time": "2:07:03", "remaining_time": "0:58:29"}
+{"current_steps": 540, "total_steps": 774, "loss": 0.4939, "learning_rate": 8.448872028755601e-07, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "2:09:26", "remaining_time": "0:56:05"}
+{"current_steps": 550, "total_steps": 774, "loss": 0.4937, "learning_rate": 8.182872007357449e-07, "epoch": 2.1317829457364343, "percentage": 71.06, "elapsed_time": "2:11:48", "remaining_time": "0:53:41"}
+{"current_steps": 560, "total_steps": 774, "loss": 0.4968, "learning_rate": 7.924757933279774e-07, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "2:14:11", "remaining_time": "0:51:16"}
+{"current_steps": 570, "total_steps": 774, "loss": 0.4936, "learning_rate": 7.675001294510496e-07, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "2:16:34", "remaining_time": "0:48:52"}
+{"current_steps": 580, "total_steps": 774, "loss": 0.4934, "learning_rate": 7.43405831280158e-07, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "2:18:57", "remaining_time": "0:46:28"}
+{"current_steps": 590, "total_steps": 774, "loss": 0.4963, "learning_rate": 7.202369110304663e-07, "epoch": 2.2868217054263567, "percentage": 76.23, "elapsed_time": "2:21:20", "remaining_time": "0:44:04"}
+{"current_steps": 600, "total_steps": 774, "loss": 0.4928, "learning_rate": 6.980356905615238e-07, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "2:23:42", "remaining_time": "0:41:40"}
+{"current_steps": 610, "total_steps": 774, "loss": 0.4965, "learning_rate": 6.768427240693994e-07, "epoch": 2.3643410852713176, "percentage": 78.81, "elapsed_time": "2:26:05", "remaining_time": "0:39:16"}
+{"current_steps": 620, "total_steps": 774, "loss": 0.4957, "learning_rate": 6.566967240077442e-07, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "2:28:28", "remaining_time": "0:36:52"}
+{"current_steps": 630, "total_steps": 774, "loss": 0.4941, "learning_rate": 6.376344903731009e-07, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "2:30:50", "remaining_time": "0:34:28"}
+{"current_steps": 640, "total_steps": 774, "loss": 0.4968, "learning_rate": 6.196908434836327e-07, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "2:33:13", "remaining_time": "0:32:04"}
+{"current_steps": 650, "total_steps": 774, "loss": 0.4931, "learning_rate": 6.028985603740602e-07, "epoch": 2.5193798449612403, "percentage": 83.98, "elapsed_time": "2:35:36", "remaining_time": "0:29:41"}
+{"current_steps": 660, "total_steps": 774, "loss": 0.4961, "learning_rate": 5.872883149229934e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "2:37:59", "remaining_time": "0:27:17"}
+{"current_steps": 670, "total_steps": 774, "loss": 0.4985, "learning_rate": 5.728886218220279e-07, "epoch": 2.5968992248062017, "percentage": 86.56, "elapsed_time": "2:40:21", "remaining_time": "0:24:53"}
+{"current_steps": 680, "total_steps": 774, "loss": 0.4921, "learning_rate": 5.597257844889494e-07, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "2:42:44", "remaining_time": "0:22:29"}
+{"current_steps": 690, "total_steps": 774, "loss": 0.495, "learning_rate": 5.47823847020197e-07, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "2:45:07", "remaining_time": "0:20:06"}
+{"current_steps": 700, "total_steps": 774, "loss": 0.4948, "learning_rate": 5.372045502703509e-07, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "2:47:30", "remaining_time": "0:17:42"}
+{"current_steps": 710, "total_steps": 774, "loss": 0.491, "learning_rate": 5.278872921388693e-07, "epoch": 2.751937984496124, "percentage": 91.73, "elapsed_time": "2:49:53", "remaining_time": "0:15:18"}
+{"current_steps": 720, "total_steps": 774, "loss": 0.497, "learning_rate": 5.198890921366215e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "2:52:15", "remaining_time": "0:12:55"}
+{"current_steps": 730, "total_steps": 774, "loss": 0.4971, "learning_rate": 5.132245602969409e-07, "epoch": 2.8294573643410854, "percentage": 94.32, "elapsed_time": "2:54:38", "remaining_time": "0:10:31"}
+{"current_steps": 740, "total_steps": 774, "loss": 0.4967, "learning_rate": 5.079058704879855e-07, "epoch": 2.8682170542635657, "percentage": 95.61, "elapsed_time": "2:57:01", "remaining_time": "0:08:08"}
+{"current_steps": 750, "total_steps": 774, "loss": 0.4936, "learning_rate": 5.039427381751569e-07, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "2:59:24", "remaining_time": "0:05:44"}
+{"current_steps": 760, "total_steps": 774, "loss": 0.4952, "learning_rate": 5.013424026741986e-07, "epoch": 2.945736434108527, "percentage": 98.19, "elapsed_time": "3:01:47", "remaining_time": "0:03:20"}
+{"current_steps": 770, "total_steps": 774, "loss": 0.4952, "learning_rate": 5.001096139273895e-07, "epoch": 2.9844961240310077, "percentage": 99.48, "elapsed_time": "3:04:10", "remaining_time": "0:00:57"}
+{"current_steps": 774, "total_steps": 774, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:05:38", "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": 9.307331330168184,
+      "learning_rate": 5.128205128205127e-07,
+      "loss": 0.8385,
+      "step": 10
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 5.138955252575586,
+      "learning_rate": 1.0256410256410255e-06,
+      "loss": 0.7404,
+      "step": 20
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 1.4657702103443784,
+      "learning_rate": 1.5384615384615385e-06,
+      "loss": 0.677,
+      "step": 30
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 1.1787847973902308,
+      "learning_rate": 1.9999931489730838e-06,
+      "loss": 0.6429,
+      "step": 40
+    },
+    {
+      "epoch": 0.1937984496124031,
+      "grad_norm": 2.6185016575045927,
+      "learning_rate": 1.9991711771810467e-06,
+      "loss": 0.618,
+      "step": 50
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 2.310229592961748,
+      "learning_rate": 1.996980720496429e-06,
+      "loss": 0.611,
+      "step": 60
+    },
+    {
+      "epoch": 0.2713178294573643,
+      "grad_norm": 2.0623431200974873,
+      "learning_rate": 1.993425780150154e-06,
+      "loss": 0.6065,
+      "step": 70
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 2.0900993234072054,
+      "learning_rate": 1.988512849827918e-06,
+      "loss": 0.5972,
+      "step": 80
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 3.001250825324938,
+      "learning_rate": 1.982250903808403e-06,
+      "loss": 0.5929,
+      "step": 90
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 1.9339680688833176,
+      "learning_rate": 1.974651380570273e-06,
+      "loss": 0.5904,
+      "step": 100
+    },
+    {
+      "epoch": 0.4263565891472868,
+      "grad_norm": 2.2198781533521443,
+      "learning_rate": 1.965728161897904e-06,
+      "loss": 0.5854,
+      "step": 110
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.7006495394504098,
+      "learning_rate": 1.9554975475240117e-06,
+      "loss": 0.5797,
+      "step": 120
+    },
+    {
+      "epoch": 0.5038759689922481,
+      "grad_norm": 1.9318648791065463,
+      "learning_rate": 1.9439782253554977e-06,
+      "loss": 0.5818,
+      "step": 130
+    },
+    {
+      "epoch": 0.5426356589147286,
+      "grad_norm": 2.6613018117479275,
+      "learning_rate": 1.9311912373369e-06,
+      "loss": 0.5795,
+      "step": 140
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 2.285875567754132,
+      "learning_rate": 1.9171599410138086e-06,
+      "loss": 0.5834,
+      "step": 150
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 1.6842813746079746,
+      "learning_rate": 1.901909966866448e-06,
+      "loss": 0.5731,
+      "step": 160
+    },
+    {
+      "epoch": 0.6589147286821705,
+      "grad_norm": 0.9898584263370955,
+      "learning_rate": 1.8854691714913721e-06,
+      "loss": 0.5712,
+      "step": 170
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 1.0394759151122948,
+      "learning_rate": 1.867867586716791e-06,
+      "loss": 0.5685,
+      "step": 180
+    },
+    {
+      "epoch": 0.7364341085271318,
+      "grad_norm": 1.5670656081596528,
+      "learning_rate": 1.8491373647444753e-06,
+      "loss": 0.5772,
+      "step": 190
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 1.4675156945580319,
+      "learning_rate": 1.8293127194184494e-06,
+      "loss": 0.5671,
+      "step": 200
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 1.1887906992002164,
+      "learning_rate": 1.8084298637277554e-06,
+      "loss": 0.57,
+      "step": 210
+    },
+    {
+      "epoch": 0.8527131782945736,
+      "grad_norm": 1.487844302447745,
+      "learning_rate": 1.786526943657445e-06,
+      "loss": 0.5688,
+      "step": 220
+    },
+    {
+      "epoch": 0.8914728682170543,
+      "grad_norm": 0.9346218255522173,
+      "learning_rate": 1.7636439685086405e-06,
+      "loss": 0.5655,
+      "step": 230
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.330759793238637,
+      "learning_rate": 1.7398227378149364e-06,
+      "loss": 0.5661,
+      "step": 240
+    },
+    {
+      "epoch": 0.9689922480620154,
+      "grad_norm": 1.4527232980930191,
+      "learning_rate": 1.7151067649886472e-06,
+      "loss": 0.5606,
+      "step": 250
+    },
+    {
+      "epoch": 1.0077519379844961,
+      "grad_norm": 1.747458529981774,
+      "learning_rate": 1.6895411978363736e-06,
+      "loss": 0.5583,
+      "step": 260
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 2.358930346941841,
+      "learning_rate": 1.6631727360890767e-06,
+      "loss": 0.5313,
+      "step": 270
+    },
+    {
+      "epoch": 1.0852713178294573,
+      "grad_norm": 1.8684830212946566,
+      "learning_rate": 1.6360495460973065e-06,
+      "loss": 0.5325,
+      "step": 280
+    },
+    {
+      "epoch": 1.124031007751938,
+      "grad_norm": 1.6373753948909144,
+      "learning_rate": 1.6082211728474055e-06,
+      "loss": 0.5273,
+      "step": 290
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.8848861878390135,
+      "learning_rate": 1.5797384494594117e-06,
+      "loss": 0.5231,
+      "step": 300
+    },
+    {
+      "epoch": 1.2015503875968991,
+      "grad_norm": 1.1713252769457778,
+      "learning_rate": 1.5506534043319639e-06,
+      "loss": 0.5298,
+      "step": 310
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 1.516027226094688,
+      "learning_rate": 1.5210191661038422e-06,
+      "loss": 0.5268,
+      "step": 320
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 1.0621047242629504,
+      "learning_rate": 1.490889866605734e-06,
+      "loss": 0.5269,
+      "step": 330
+    },
+    {
+      "epoch": 1.3178294573643412,
+      "grad_norm": 1.0951342502976817,
+      "learning_rate": 1.460320541979502e-06,
+      "loss": 0.5307,
+      "step": 340
+    },
+    {
+      "epoch": 1.3565891472868217,
+      "grad_norm": 1.021930442887122,
+      "learning_rate": 1.429367032145583e-06,
+      "loss": 0.5279,
+      "step": 350
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.0571616446897196,
+      "learning_rate": 1.3980858788021502e-06,
+      "loss": 0.5317,
+      "step": 360
+    },
+    {
+      "epoch": 1.4341085271317828,
+      "grad_norm": 1.118987878158059,
+      "learning_rate": 1.3665342221423621e-06,
+      "loss": 0.5295,
+      "step": 370
+    },
+    {
+      "epoch": 1.4728682170542635,
+      "grad_norm": 0.9595235784970936,
+      "learning_rate": 1.3347696964783628e-06,
+      "loss": 0.5263,
+      "step": 380
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 0.9135744785961647,
+      "learning_rate": 1.3028503249626903e-06,
+      "loss": 0.5299,
+      "step": 390
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 1.1040109518004744,
+      "learning_rate": 1.270834413599407e-06,
+      "loss": 0.5263,
+      "step": 400
+    },
+    {
+      "epoch": 1.5891472868217056,
+      "grad_norm": 1.0773046510045323,
+      "learning_rate": 1.2387804447385523e-06,
+      "loss": 0.5216,
+      "step": 410
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 0.8291987350988335,
+      "learning_rate": 1.2067469702484692e-06,
+      "loss": 0.5265,
+      "step": 420
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.8440119473799433,
+      "learning_rate": 1.1747925045611484e-06,
+      "loss": 0.5294,
+      "step": 430
+    },
+    {
+      "epoch": 1.7054263565891472,
+      "grad_norm": 0.8765230330042942,
+      "learning_rate": 1.1429754177859534e-06,
+      "loss": 0.5248,
+      "step": 440
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 0.8812454444783112,
+      "learning_rate": 1.1113538290869735e-06,
+      "loss": 0.5281,
+      "step": 450
+    },
+    {
+      "epoch": 1.7829457364341086,
+      "grad_norm": 1.0658383788938974,
+      "learning_rate": 1.0799855005187725e-06,
+      "loss": 0.5236,
+      "step": 460
+    },
+    {
+      "epoch": 1.8217054263565893,
+      "grad_norm": 0.8687919155487503,
+      "learning_rate": 1.0489277315144551e-06,
+      "loss": 0.5251,
+      "step": 470
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 1.1224535344747606,
+      "learning_rate": 1.0182372542187895e-06,
+      "loss": 0.5277,
+      "step": 480
+    },
+    {
+      "epoch": 1.8992248062015504,
+      "grad_norm": 1.035486114254949,
+      "learning_rate": 9.879701298575733e-07,
+      "loss": 0.5233,
+      "step": 490
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 0.8801797962238582,
+      "learning_rate": 9.581816463325465e-07,
+      "loss": 0.5261,
+      "step": 500
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 1.130215891164072,
+      "learning_rate": 9.28926217228906e-07,
+      "loss": 0.5234,
+      "step": 510
+    },
+    {
+      "epoch": 2.0155038759689923,
+      "grad_norm": 1.6776064672104285,
+      "learning_rate": 9.002572824199062e-07,
+      "loss": 0.5134,
+      "step": 520
+    },
+    {
+      "epoch": 2.054263565891473,
+      "grad_norm": 0.9766677497598724,
+      "learning_rate": 8.722272104501032e-07,
+      "loss": 0.4961,
+      "step": 530
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 0.8945190137757296,
+      "learning_rate": 8.448872028755601e-07,
+      "loss": 0.4939,
+      "step": 540
+    },
+    {
+      "epoch": 2.1317829457364343,
+      "grad_norm": 0.8636966097094951,
+      "learning_rate": 8.182872007357449e-07,
+      "loss": 0.4937,
+      "step": 550
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 0.8887420828016619,
+      "learning_rate": 7.924757933279774e-07,
+      "loss": 0.4968,
+      "step": 560
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 0.964909371903011,
+      "learning_rate": 7.675001294510496e-07,
+      "loss": 0.4936,
+      "step": 570
+    },
+    {
+      "epoch": 2.248062015503876,
+      "grad_norm": 0.9348345944114084,
+      "learning_rate": 7.43405831280158e-07,
+      "loss": 0.4934,
+      "step": 580
+    },
+    {
+      "epoch": 2.2868217054263567,
+      "grad_norm": 0.8274041177559192,
+      "learning_rate": 7.202369110304663e-07,
+      "loss": 0.4963,
+      "step": 590
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 0.8546457079530284,
+      "learning_rate": 6.980356905615238e-07,
+      "loss": 0.4928,
+      "step": 600
+    },
+    {
+      "epoch": 2.3643410852713176,
+      "grad_norm": 0.8301922843955071,
+      "learning_rate": 6.768427240693994e-07,
+      "loss": 0.4965,
+      "step": 610
+    },
+    {
+      "epoch": 2.4031007751937983,
+      "grad_norm": 0.9560928404163074,
+      "learning_rate": 6.566967240077442e-07,
+      "loss": 0.4957,
+      "step": 620
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 0.8654288154446055,
+      "learning_rate": 6.376344903731009e-07,
+      "loss": 0.4941,
+      "step": 630
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 0.8712004331468729,
+      "learning_rate": 6.196908434836327e-07,
+      "loss": 0.4968,
+      "step": 640
+    },
+    {
+      "epoch": 2.5193798449612403,
+      "grad_norm": 0.8907665674854127,
+      "learning_rate": 6.028985603740602e-07,
+      "loss": 0.4931,
+      "step": 650
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 0.8323522905029972,
+      "learning_rate": 5.872883149229934e-07,
+      "loss": 0.4961,
+      "step": 660
+    },
+    {
+      "epoch": 2.5968992248062017,
+      "grad_norm": 0.9483290431659331,
+      "learning_rate": 5.728886218220279e-07,
+      "loss": 0.4985,
+      "step": 670
+    },
+    {
+      "epoch": 2.6356589147286824,
+      "grad_norm": 0.9098934513394534,
+      "learning_rate": 5.597257844889494e-07,
+      "loss": 0.4921,
+      "step": 680
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 0.8944235472033026,
+      "learning_rate": 5.47823847020197e-07,
+      "loss": 0.495,
+      "step": 690
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 0.8478985898883433,
+      "learning_rate": 5.372045502703509e-07,
+      "loss": 0.4948,
+      "step": 700
+    },
+    {
+      "epoch": 2.751937984496124,
+      "grad_norm": 0.8854520577932926,
+      "learning_rate": 5.278872921388693e-07,
+      "loss": 0.491,
+      "step": 710
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.8642415418625066,
+      "learning_rate": 5.198890921366215e-07,
+      "loss": 0.497,
+      "step": 720
+    },
+    {
+      "epoch": 2.8294573643410854,
+      "grad_norm": 0.8143119664045128,
+      "learning_rate": 5.132245602969409e-07,
+      "loss": 0.4971,
+      "step": 730
+    },
+    {
+      "epoch": 2.8682170542635657,
+      "grad_norm": 0.9532004699007264,
+      "learning_rate": 5.079058704879855e-07,
+      "loss": 0.4967,
+      "step": 740
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.8909767930528603,
+      "learning_rate": 5.039427381751569e-07,
+      "loss": 0.4936,
+      "step": 750
+    },
+    {
+      "epoch": 2.945736434108527,
+      "grad_norm": 0.8343081954961633,
+      "learning_rate": 5.013424026741986e-07,
+      "loss": 0.4952,
+      "step": 760
+    },
+    {
+      "epoch": 2.9844961240310077,
+      "grad_norm": 0.8822952324229475,
+      "learning_rate": 5.001096139273895e-07,
+      "loss": 0.4952,
+      "step": 770
+    },
+    {
+      "epoch": 3.0,
+      "step": 774,
+      "total_flos": 2591282618695680.0,
+      "train_loss": 0.5421019284300101,
+      "train_runtime": 11142.1795,
+      "train_samples_per_second": 71.073,
+      "train_steps_per_second": 0.069
+    }
+  ],
+  "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 sha256:3287448642bfc725e29613f5fb2220968c61ebe968aec140479ade1d8ce3f291
+size 7672