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_lr5.00E-06_schedulercosine_with_min_lr_warmup1.00E-01_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_lr5.00E-06_schedulercosine_with_min_lr_warmup1.00E-01_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: 5e-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: 0.1
+- 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": 0.5117943732005373,
+    "train_runtime": 11288.2174,
+    "train_samples_per_second": 70.154,
+    "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:a05fff76e2cb0ad17134e286da4b781c659ad01dc1b445105a507301ccdc141b
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ce301fab5101be818f3c0844ea6b8cf851fd50814c1f0dcc5fe72b5f8574d7
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525d1eb643bbcbeb81f95202de1a174779f2e5ebe8a45388d516034217615913
+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": 0.5117943732005373,
+    "train_runtime": 11288.2174,
+    "train_samples_per_second": 70.154,
+    "train_steps_per_second": 0.069
+}

trainer_log.jsonl

@@ -0,0 +1,78 @@
+{"current_steps": 10, "total_steps": 774, "loss": 0.8334, "learning_rate": 6.41025641025641e-07, "epoch": 0.03875968992248062, "percentage": 1.29, "elapsed_time": "0:02:22", "remaining_time": "3:02:01"}
+{"current_steps": 20, "total_steps": 774, "loss": 0.7312, "learning_rate": 1.282051282051282e-06, "epoch": 0.07751937984496124, "percentage": 2.58, "elapsed_time": "0:04:45", "remaining_time": "2:59:21"}
+{"current_steps": 30, "total_steps": 774, "loss": 0.6678, "learning_rate": 1.9230769230769234e-06, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:07:08", "remaining_time": "2:57:15"}
+{"current_steps": 40, "total_steps": 774, "loss": 0.6365, "learning_rate": 2.564102564102564e-06, "epoch": 0.15503875968992248, "percentage": 5.17, "elapsed_time": "0:09:33", "remaining_time": "2:55:19"}
+{"current_steps": 50, "total_steps": 774, "loss": 0.6144, "learning_rate": 3.205128205128206e-06, "epoch": 0.1937984496124031, "percentage": 6.46, "elapsed_time": "0:11:57", "remaining_time": "2:53:14"}
+{"current_steps": 60, "total_steps": 774, "loss": 0.6094, "learning_rate": 3.846153846153847e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:14:23", "remaining_time": "2:51:13"}
+{"current_steps": 70, "total_steps": 774, "loss": 0.6042, "learning_rate": 4.487179487179488e-06, "epoch": 0.2713178294573643, "percentage": 9.04, "elapsed_time": "0:16:48", "remaining_time": "2:49:00"}
+{"current_steps": 80, "total_steps": 774, "loss": 0.5943, "learning_rate": 4.999908316574644e-06, "epoch": 0.31007751937984496, "percentage": 10.34, "elapsed_time": "0:19:12", "remaining_time": "2:46:37"}
+{"current_steps": 90, "total_steps": 774, "loss": 0.589, "learning_rate": 4.996700181165029e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:21:37", "remaining_time": "2:44:17"}
+{"current_steps": 100, "total_steps": 774, "loss": 0.586, "learning_rate": 4.98891534361803e-06, "epoch": 0.3875968992248062, "percentage": 12.92, "elapsed_time": "0:24:01", "remaining_time": "2:41:55"}
+{"current_steps": 110, "total_steps": 774, "loss": 0.5809, "learning_rate": 4.976569662250185e-06, "epoch": 0.4263565891472868, "percentage": 14.21, "elapsed_time": "0:26:25", "remaining_time": "2:39:31"}
+{"current_steps": 120, "total_steps": 774, "loss": 0.5747, "learning_rate": 4.9596882861698515e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:28:51", "remaining_time": "2:37:14"}
+{"current_steps": 130, "total_steps": 774, "loss": 0.5767, "learning_rate": 4.938305604046528e-06, "epoch": 0.5038759689922481, "percentage": 16.8, "elapsed_time": "0:31:16", "remaining_time": "2:34:54"}
+{"current_steps": 140, "total_steps": 774, "loss": 0.5755, "learning_rate": 4.912465174058468e-06, "epoch": 0.5426356589147286, "percentage": 18.09, "elapsed_time": "0:33:40", "remaining_time": "2:32:31"}
+{"current_steps": 150, "total_steps": 774, "loss": 0.5787, "learning_rate": 4.882219635161306e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "0:36:05", "remaining_time": "2:30:07"}
+{"current_steps": 160, "total_steps": 774, "loss": 0.5677, "learning_rate": 4.847630599858426e-06, "epoch": 0.6201550387596899, "percentage": 20.67, "elapsed_time": "0:38:29", "remaining_time": "2:27:42"}
+{"current_steps": 170, "total_steps": 774, "loss": 0.5653, "learning_rate": 4.808768528691528e-06, "epoch": 0.6589147286821705, "percentage": 21.96, "elapsed_time": "0:40:53", "remaining_time": "2:25:18"}
+{"current_steps": 180, "total_steps": 774, "loss": 0.5621, "learning_rate": 4.765712586707048e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:43:18", "remaining_time": "2:22:56"}
+{"current_steps": 190, "total_steps": 774, "loss": 0.5698, "learning_rate": 4.718550482190837e-06, "epoch": 0.7364341085271318, "percentage": 24.55, "elapsed_time": "0:45:43", "remaining_time": "2:20:32"}
+{"current_steps": 200, "total_steps": 774, "loss": 0.5602, "learning_rate": 4.66737828799959e-06, "epoch": 0.7751937984496124, "percentage": 25.84, "elapsed_time": "0:48:08", "remaining_time": "2:18:10"}
+{"current_steps": 210, "total_steps": 774, "loss": 0.5629, "learning_rate": 4.612300245853004e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "0:50:33", "remaining_time": "2:15:46"}
+{"current_steps": 220, "total_steps": 774, "loss": 0.562, "learning_rate": 4.55342855398533e-06, "epoch": 0.8527131782945736, "percentage": 28.42, "elapsed_time": "0:52:58", "remaining_time": "2:13:23"}
+{"current_steps": 230, "total_steps": 774, "loss": 0.5591, "learning_rate": 4.490883138588882e-06, "epoch": 0.8914728682170543, "percentage": 29.72, "elapsed_time": "0:55:22", "remaining_time": "2:10:59"}
+{"current_steps": 240, "total_steps": 774, "loss": 0.5599, "learning_rate": 4.424791409515109e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:57:47", "remaining_time": "2:08:36"}
+{"current_steps": 250, "total_steps": 774, "loss": 0.5548, "learning_rate": 4.35528800073086e-06, "epoch": 0.9689922480620154, "percentage": 32.3, "elapsed_time": "1:00:12", "remaining_time": "2:06:11"}
+{"current_steps": 260, "total_steps": 774, "loss": 0.5484, "learning_rate": 4.282514496058583e-06, "epoch": 1.0077519379844961, "percentage": 33.59, "elapsed_time": "1:03:05", "remaining_time": "2:04:42"}
+{"current_steps": 270, "total_steps": 774, "loss": 0.503, "learning_rate": 4.206619140759113e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "1:05:35", "remaining_time": "2:02:25"}
+{"current_steps": 280, "total_steps": 774, "loss": 0.5026, "learning_rate": 4.127756539544609e-06, "epoch": 1.0852713178294573, "percentage": 36.18, "elapsed_time": "1:07:59", "remaining_time": "1:59:57"}
+{"current_steps": 290, "total_steps": 774, "loss": 0.4976, "learning_rate": 4.04608734163679e-06, "epoch": 1.124031007751938, "percentage": 37.47, "elapsed_time": "1:10:23", "remaining_time": "1:57:29"}
+{"current_steps": 300, "total_steps": 774, "loss": 0.4935, "learning_rate": 3.9617779135120345e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "1:12:47", "remaining_time": "1:55:00"}
+{"current_steps": 310, "total_steps": 774, "loss": 0.5001, "learning_rate": 3.875e-06, "epoch": 1.2015503875968991, "percentage": 40.05, "elapsed_time": "1:15:11", "remaining_time": "1:52:33"}
+{"current_steps": 320, "total_steps": 774, "loss": 0.4964, "learning_rate": 3.7859303744261066e-06, "epoch": 1.2403100775193798, "percentage": 41.34, "elapsed_time": "1:17:35", "remaining_time": "1:50:04"}
+{"current_steps": 330, "total_steps": 774, "loss": 0.4981, "learning_rate": 3.694750478510596e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "1:19:59", "remaining_time": "1:47:38"}
+{"current_steps": 340, "total_steps": 774, "loss": 0.5025, "learning_rate": 3.6016460527577067e-06, "epoch": 1.3178294573643412, "percentage": 43.93, "elapsed_time": "1:22:23", "remaining_time": "1:45:10"}
+{"current_steps": 350, "total_steps": 774, "loss": 0.4996, "learning_rate": 3.506806758087894e-06, "epoch": 1.3565891472868217, "percentage": 45.22, "elapsed_time": "1:24:48", "remaining_time": "1:42:43"}
+{"current_steps": 360, "total_steps": 774, "loss": 0.5035, "learning_rate": 3.410425789483854e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "1:27:11", "remaining_time": "1:40:16"}
+{"current_steps": 370, "total_steps": 774, "loss": 0.502, "learning_rate": 3.3126994824373922e-06, "epoch": 1.4341085271317828, "percentage": 47.8, "elapsed_time": "1:29:36", "remaining_time": "1:37:50"}
+{"current_steps": 380, "total_steps": 774, "loss": 0.4991, "learning_rate": 3.213826912998838e-06, "epoch": 1.4728682170542635, "percentage": 49.1, "elapsed_time": "1:32:00", "remaining_time": "1:35:24"}
+{"current_steps": 390, "total_steps": 774, "loss": 0.5025, "learning_rate": 3.1140094922437213e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "1:34:26", "remaining_time": "1:32:58"}
+{"current_steps": 400, "total_steps": 774, "loss": 0.499, "learning_rate": 3.0134505559828203e-06, "epoch": 1.550387596899225, "percentage": 51.68, "elapsed_time": "1:36:49", "remaining_time": "1:30:32"}
+{"current_steps": 410, "total_steps": 774, "loss": 0.4948, "learning_rate": 2.9123549505513872e-06, "epoch": 1.5891472868217056, "percentage": 52.97, "elapsed_time": "1:39:14", "remaining_time": "1:28:06"}
+{"current_steps": 420, "total_steps": 774, "loss": 0.4994, "learning_rate": 2.8109286155213032e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "1:41:38", "remaining_time": "1:25:40"}
+{"current_steps": 430, "total_steps": 774, "loss": 0.5026, "learning_rate": 2.7093781641862387e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:44:03", "remaining_time": "1:23:14"}
+{"current_steps": 440, "total_steps": 774, "loss": 0.4969, "learning_rate": 2.6079104626743844e-06, "epoch": 1.7054263565891472, "percentage": 56.85, "elapsed_time": "1:46:27", "remaining_time": "1:20:49"}
+{"current_steps": 450, "total_steps": 774, "loss": 0.4994, "learning_rate": 2.5067322085461317e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "1:48:51", "remaining_time": "1:18:22"}
+{"current_steps": 460, "total_steps": 774, "loss": 0.4952, "learning_rate": 2.4060495097351562e-06, "epoch": 1.7829457364341086, "percentage": 59.43, "elapsed_time": "1:51:16", "remaining_time": "1:15:57"}
+{"current_steps": 470, "total_steps": 774, "loss": 0.4963, "learning_rate": 2.3060674646906003e-06, "epoch": 1.8217054263565893, "percentage": 60.72, "elapsed_time": "1:53:41", "remaining_time": "1:13:31"}
+{"current_steps": 480, "total_steps": 774, "loss": 0.4992, "learning_rate": 2.206989744575663e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "1:56:05", "remaining_time": "1:11:06"}
+{"current_steps": 490, "total_steps": 774, "loss": 0.4952, "learning_rate": 2.109018178373675e-06, "epoch": 1.8992248062015504, "percentage": 63.31, "elapsed_time": "1:58:30", "remaining_time": "1:08:41"}
+{"current_steps": 500, "total_steps": 774, "loss": 0.498, "learning_rate": 2.0123523417468465e-06, "epoch": 1.937984496124031, "percentage": 64.6, "elapsed_time": "2:00:55", "remaining_time": "1:06:15"}
+{"current_steps": 510, "total_steps": 774, "loss": 0.4956, "learning_rate": 1.9171891504851926e-06, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "2:03:20", "remaining_time": "1:03:50"}
+{"current_steps": 520, "total_steps": 774, "loss": 0.4744, "learning_rate": 1.8237224593738325e-06, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "2:06:12", "remaining_time": "1:01:38"}
+{"current_steps": 530, "total_steps": 774, "loss": 0.4398, "learning_rate": 1.7321426672957898e-06, "epoch": 2.054263565891473, "percentage": 68.48, "elapsed_time": "2:08:37", "remaining_time": "0:59:13"}
+{"current_steps": 540, "total_steps": 774, "loss": 0.4366, "learning_rate": 1.6426363293747336e-06, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "2:11:02", "remaining_time": "0:56:47"}
+{"current_steps": 550, "total_steps": 774, "loss": 0.4358, "learning_rate": 1.5553857769477554e-06, "epoch": 2.1317829457364343, "percentage": 71.06, "elapsed_time": "2:13:27", "remaining_time": "0:54:21"}
+{"current_steps": 560, "total_steps": 774, "loss": 0.4392, "learning_rate": 1.4705687461423209e-06, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "2:15:52", "remaining_time": "0:51:55"}
+{"current_steps": 570, "total_steps": 774, "loss": 0.4359, "learning_rate": 1.3883580158140291e-06, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "2:18:16", "remaining_time": "0:49:29"}
+{"current_steps": 580, "total_steps": 774, "loss": 0.4369, "learning_rate": 1.3089210555827084e-06, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "2:20:41", "remaining_time": "0:47:03"}
+{"current_steps": 590, "total_steps": 774, "loss": 0.4389, "learning_rate": 1.232419684683844e-06, "epoch": 2.2868217054263567, "percentage": 76.23, "elapsed_time": "2:23:05", "remaining_time": "0:44:37"}
+{"current_steps": 600, "total_steps": 774, "loss": 0.4359, "learning_rate": 1.1590097423302681e-06, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "2:25:30", "remaining_time": "0:42:11"}
+{"current_steps": 610, "total_steps": 774, "loss": 0.4394, "learning_rate": 1.0888407702556283e-06, "epoch": 2.3643410852713176, "percentage": 78.81, "elapsed_time": "2:27:55", "remaining_time": "0:39:46"}
+{"current_steps": 620, "total_steps": 774, "loss": 0.4385, "learning_rate": 1.0220557080862984e-06, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "2:30:20", "remaining_time": "0:37:20"}
+{"current_steps": 630, "total_steps": 774, "loss": 0.4373, "learning_rate": 9.587906021623017e-07, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "2:32:44", "remaining_time": "0:34:54"}
+{"current_steps": 640, "total_steps": 774, "loss": 0.4397, "learning_rate": 8.991743284003851e-07, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "2:35:09", "remaining_time": "0:32:29"}
+{"current_steps": 650, "total_steps": 774, "loss": 0.4361, "learning_rate": 8.433283297638052e-07, "epoch": 2.5193798449612403, "percentage": 83.98, "elapsed_time": "2:37:33", "remaining_time": "0:30:03"}
+{"current_steps": 660, "total_steps": 774, "loss": 0.4385, "learning_rate": 7.913663688736131e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "2:39:57", "remaining_time": "0:27:37"}
+{"current_steps": 670, "total_steps": 774, "loss": 0.4413, "learning_rate": 7.4339429626539e-07, "epoch": 2.5968992248062017, "percentage": 86.56, "elapsed_time": "2:42:21", "remaining_time": "0:25:12"}
+{"current_steps": 680, "total_steps": 774, "loss": 0.435, "learning_rate": 6.995098347635173e-07, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "2:44:45", "remaining_time": "0:22:46"}
+{"current_steps": 690, "total_steps": 774, "loss": 0.4378, "learning_rate": 6.598023804122194e-07, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "2:47:09", "remaining_time": "0:20:21"}
+{"current_steps": 700, "total_steps": 774, "loss": 0.4377, "learning_rate": 6.243528203689025e-07, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "2:49:34", "remaining_time": "0:17:55"}
+{"current_steps": 710, "total_steps": 774, "loss": 0.4343, "learning_rate": 5.93233368130757e-07, "epoch": 2.751937984496124, "percentage": 91.73, "elapsed_time": "2:51:59", "remaining_time": "0:15:30"}
+{"current_steps": 720, "total_steps": 774, "loss": 0.4396, "learning_rate": 5.665074164302742e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "2:54:23", "remaining_time": "0:13:04"}
+{"current_steps": 730, "total_steps": 774, "loss": 0.4401, "learning_rate": 5.442294080993445e-07, "epoch": 2.8294573643410854, "percentage": 94.32, "elapsed_time": "2:56:48", "remaining_time": "0:10:39"}
+{"current_steps": 740, "total_steps": 774, "loss": 0.4388, "learning_rate": 5.264447251649954e-07, "epoch": 2.8682170542635657, "percentage": 95.61, "elapsed_time": "2:59:12", "remaining_time": "0:08:14"}
+{"current_steps": 750, "total_steps": 774, "loss": 0.4368, "learning_rate": 5.131895964026909e-07, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "3:01:36", "remaining_time": "0:05:48"}
+{"current_steps": 760, "total_steps": 774, "loss": 0.4378, "learning_rate": 5.044910235355121e-07, "epoch": 2.945736434108527, "percentage": 98.19, "elapsed_time": "3:04:01", "remaining_time": "0:03:23"}
+{"current_steps": 770, "total_steps": 774, "loss": 0.4376, "learning_rate": 5.003667262295572e-07, "epoch": 2.9844961240310077, "percentage": 99.48, "elapsed_time": "3:06:25", "remaining_time": "0:00:58"}
+{"current_steps": 774, "total_steps": 774, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:08:06", "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": 6.53225748428384,
+      "learning_rate": 6.41025641025641e-07,
+      "loss": 0.8334,
+      "step": 10
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 3.0904457812637434,
+      "learning_rate": 1.282051282051282e-06,
+      "loss": 0.7312,
+      "step": 20
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 1.7344719342361075,
+      "learning_rate": 1.9230769230769234e-06,
+      "loss": 0.6678,
+      "step": 30
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 2.016968940501497,
+      "learning_rate": 2.564102564102564e-06,
+      "loss": 0.6365,
+      "step": 40
+    },
+    {
+      "epoch": 0.1937984496124031,
+      "grad_norm": 4.7658779965469735,
+      "learning_rate": 3.205128205128206e-06,
+      "loss": 0.6144,
+      "step": 50
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 3.5451343101967243,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.6094,
+      "step": 60
+    },
+    {
+      "epoch": 0.2713178294573643,
+      "grad_norm": 3.5661181210560637,
+      "learning_rate": 4.487179487179488e-06,
+      "loss": 0.6042,
+      "step": 70
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 2.945943530898172,
+      "learning_rate": 4.999908316574644e-06,
+      "loss": 0.5943,
+      "step": 80
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 2.737038607234326,
+      "learning_rate": 4.996700181165029e-06,
+      "loss": 0.589,
+      "step": 90
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 2.5241085748069985,
+      "learning_rate": 4.98891534361803e-06,
+      "loss": 0.586,
+      "step": 100
+    },
+    {
+      "epoch": 0.4263565891472868,
+      "grad_norm": 2.037685934354263,
+      "learning_rate": 4.976569662250185e-06,
+      "loss": 0.5809,
+      "step": 110
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.4280244267800808,
+      "learning_rate": 4.9596882861698515e-06,
+      "loss": 0.5747,
+      "step": 120
+    },
+    {
+      "epoch": 0.5038759689922481,
+      "grad_norm": 1.2982987237654093,
+      "learning_rate": 4.938305604046528e-06,
+      "loss": 0.5767,
+      "step": 130
+    },
+    {
+      "epoch": 0.5426356589147286,
+      "grad_norm": 1.7719975144237177,
+      "learning_rate": 4.912465174058468e-06,
+      "loss": 0.5755,
+      "step": 140
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 2.9804156260898864,
+      "learning_rate": 4.882219635161306e-06,
+      "loss": 0.5787,
+      "step": 150
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 1.7485237135240594,
+      "learning_rate": 4.847630599858426e-06,
+      "loss": 0.5677,
+      "step": 160
+    },
+    {
+      "epoch": 0.6589147286821705,
+      "grad_norm": 1.4393507841682058,
+      "learning_rate": 4.808768528691528e-06,
+      "loss": 0.5653,
+      "step": 170
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 1.4302360935739276,
+      "learning_rate": 4.765712586707048e-06,
+      "loss": 0.5621,
+      "step": 180
+    },
+    {
+      "epoch": 0.7364341085271318,
+      "grad_norm": 2.030360790300817,
+      "learning_rate": 4.718550482190837e-06,
+      "loss": 0.5698,
+      "step": 190
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 1.7605798994672424,
+      "learning_rate": 4.66737828799959e-06,
+      "loss": 0.5602,
+      "step": 200
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 1.4240359476262214,
+      "learning_rate": 4.612300245853004e-06,
+      "loss": 0.5629,
+      "step": 210
+    },
+    {
+      "epoch": 0.8527131782945736,
+      "grad_norm": 1.524648870664852,
+      "learning_rate": 4.55342855398533e-06,
+      "loss": 0.562,
+      "step": 220
+    },
+    {
+      "epoch": 0.8914728682170543,
+      "grad_norm": 1.6582401446676425,
+      "learning_rate": 4.490883138588882e-06,
+      "loss": 0.5591,
+      "step": 230
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.109613944861693,
+      "learning_rate": 4.424791409515109e-06,
+      "loss": 0.5599,
+      "step": 240
+    },
+    {
+      "epoch": 0.9689922480620154,
+      "grad_norm": 1.5447923575123774,
+      "learning_rate": 4.35528800073086e-06,
+      "loss": 0.5548,
+      "step": 250
+    },
+    {
+      "epoch": 1.0077519379844961,
+      "grad_norm": 1.791326992725856,
+      "learning_rate": 4.282514496058583e-06,
+      "loss": 0.5484,
+      "step": 260
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 1.4014731262966984,
+      "learning_rate": 4.206619140759113e-06,
+      "loss": 0.503,
+      "step": 270
+    },
+    {
+      "epoch": 1.0852713178294573,
+      "grad_norm": 1.4998419594951466,
+      "learning_rate": 4.127756539544609e-06,
+      "loss": 0.5026,
+      "step": 280
+    },
+    {
+      "epoch": 1.124031007751938,
+      "grad_norm": 1.5251098073246308,
+      "learning_rate": 4.04608734163679e-06,
+      "loss": 0.4976,
+      "step": 290
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 1.363737620635966,
+      "learning_rate": 3.9617779135120345e-06,
+      "loss": 0.4935,
+      "step": 300
+    },
+    {
+      "epoch": 1.2015503875968991,
+      "grad_norm": 1.0927688902174042,
+      "learning_rate": 3.875e-06,
+      "loss": 0.5001,
+      "step": 310
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 1.0532572280199268,
+      "learning_rate": 3.7859303744261066e-06,
+      "loss": 0.4964,
+      "step": 320
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 1.4752956932889283,
+      "learning_rate": 3.694750478510596e-06,
+      "loss": 0.4981,
+      "step": 330
+    },
+    {
+      "epoch": 1.3178294573643412,
+      "grad_norm": 1.3939757222442386,
+      "learning_rate": 3.6016460527577067e-06,
+      "loss": 0.5025,
+      "step": 340
+    },
+    {
+      "epoch": 1.3565891472868217,
+      "grad_norm": 1.1049115401101193,
+      "learning_rate": 3.506806758087894e-06,
+      "loss": 0.4996,
+      "step": 350
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.0150464425325063,
+      "learning_rate": 3.410425789483854e-06,
+      "loss": 0.5035,
+      "step": 360
+    },
+    {
+      "epoch": 1.4341085271317828,
+      "grad_norm": 0.9402305423521259,
+      "learning_rate": 3.3126994824373922e-06,
+      "loss": 0.502,
+      "step": 370
+    },
+    {
+      "epoch": 1.4728682170542635,
+      "grad_norm": 1.2385522606875088,
+      "learning_rate": 3.213826912998838e-06,
+      "loss": 0.4991,
+      "step": 380
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 0.9996760969175614,
+      "learning_rate": 3.1140094922437213e-06,
+      "loss": 0.5025,
+      "step": 390
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 1.12355568148623,
+      "learning_rate": 3.0134505559828203e-06,
+      "loss": 0.499,
+      "step": 400
+    },
+    {
+      "epoch": 1.5891472868217056,
+      "grad_norm": 1.1570283841311328,
+      "learning_rate": 2.9123549505513872e-06,
+      "loss": 0.4948,
+      "step": 410
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.5811865125079974,
+      "learning_rate": 2.8109286155213032e-06,
+      "loss": 0.4994,
+      "step": 420
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.6106319490350816,
+      "learning_rate": 2.7093781641862387e-06,
+      "loss": 0.5026,
+      "step": 430
+    },
+    {
+      "epoch": 1.7054263565891472,
+      "grad_norm": 1.5867844144482488,
+      "learning_rate": 2.6079104626743844e-06,
+      "loss": 0.4969,
+      "step": 440
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 1.6302910176903578,
+      "learning_rate": 2.5067322085461317e-06,
+      "loss": 0.4994,
+      "step": 450
+    },
+    {
+      "epoch": 1.7829457364341086,
+      "grad_norm": 1.5439231814833114,
+      "learning_rate": 2.4060495097351562e-06,
+      "loss": 0.4952,
+      "step": 460
+    },
+    {
+      "epoch": 1.8217054263565893,
+      "grad_norm": 1.1778040502034184,
+      "learning_rate": 2.3060674646906003e-06,
+      "loss": 0.4963,
+      "step": 470
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 0.8638713759953142,
+      "learning_rate": 2.206989744575663e-06,
+      "loss": 0.4992,
+      "step": 480
+    },
+    {
+      "epoch": 1.8992248062015504,
+      "grad_norm": 0.8917193008685469,
+      "learning_rate": 2.109018178373675e-06,
+      "loss": 0.4952,
+      "step": 490
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 0.8557167845539484,
+      "learning_rate": 2.0123523417468465e-06,
+      "loss": 0.498,
+      "step": 500
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 0.9362469071035696,
+      "learning_rate": 1.9171891504851926e-06,
+      "loss": 0.4956,
+      "step": 510
+    },
+    {
+      "epoch": 2.0155038759689923,
+      "grad_norm": 2.2264407167335656,
+      "learning_rate": 1.8237224593738325e-06,
+      "loss": 0.4744,
+      "step": 520
+    },
+    {
+      "epoch": 2.054263565891473,
+      "grad_norm": 1.1781658957019514,
+      "learning_rate": 1.7321426672957898e-06,
+      "loss": 0.4398,
+      "step": 530
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 1.0507729618675103,
+      "learning_rate": 1.6426363293747336e-06,
+      "loss": 0.4366,
+      "step": 540
+    },
+    {
+      "epoch": 2.1317829457364343,
+      "grad_norm": 1.0528274672976718,
+      "learning_rate": 1.5553857769477554e-06,
+      "loss": 0.4358,
+      "step": 550
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 0.8494120586467812,
+      "learning_rate": 1.4705687461423209e-06,
+      "loss": 0.4392,
+      "step": 560
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 0.9181694486346843,
+      "learning_rate": 1.3883580158140291e-06,
+      "loss": 0.4359,
+      "step": 570
+    },
+    {
+      "epoch": 2.248062015503876,
+      "grad_norm": 0.9043588771730569,
+      "learning_rate": 1.3089210555827084e-06,
+      "loss": 0.4369,
+      "step": 580
+    },
+    {
+      "epoch": 2.2868217054263567,
+      "grad_norm": 0.8703168556105839,
+      "learning_rate": 1.232419684683844e-06,
+      "loss": 0.4389,
+      "step": 590
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 0.8944609832737697,
+      "learning_rate": 1.1590097423302681e-06,
+      "loss": 0.4359,
+      "step": 600
+    },
+    {
+      "epoch": 2.3643410852713176,
+      "grad_norm": 0.8333565490040669,
+      "learning_rate": 1.0888407702556283e-06,
+      "loss": 0.4394,
+      "step": 610
+    },
+    {
+      "epoch": 2.4031007751937983,
+      "grad_norm": 0.8610917180846815,
+      "learning_rate": 1.0220557080862984e-06,
+      "loss": 0.4385,
+      "step": 620
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 0.8231565330686974,
+      "learning_rate": 9.587906021623017e-07,
+      "loss": 0.4373,
+      "step": 630
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 0.835061113996068,
+      "learning_rate": 8.991743284003851e-07,
+      "loss": 0.4397,
+      "step": 640
+    },
+    {
+      "epoch": 2.5193798449612403,
+      "grad_norm": 0.8459183442268626,
+      "learning_rate": 8.433283297638052e-07,
+      "loss": 0.4361,
+      "step": 650
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 0.8175093032183381,
+      "learning_rate": 7.913663688736131e-07,
+      "loss": 0.4385,
+      "step": 660
+    },
+    {
+      "epoch": 2.5968992248062017,
+      "grad_norm": 0.8732673590648053,
+      "learning_rate": 7.4339429626539e-07,
+      "loss": 0.4413,
+      "step": 670
+    },
+    {
+      "epoch": 2.6356589147286824,
+      "grad_norm": 0.8741541815734528,
+      "learning_rate": 6.995098347635173e-07,
+      "loss": 0.435,
+      "step": 680
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 0.8568342459690883,
+      "learning_rate": 6.598023804122194e-07,
+      "loss": 0.4378,
+      "step": 690
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 0.816348223527435,
+      "learning_rate": 6.243528203689025e-07,
+      "loss": 0.4377,
+      "step": 700
+    },
+    {
+      "epoch": 2.751937984496124,
+      "grad_norm": 0.8356273530876691,
+      "learning_rate": 5.93233368130757e-07,
+      "loss": 0.4343,
+      "step": 710
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.8348822512820131,
+      "learning_rate": 5.665074164302742e-07,
+      "loss": 0.4396,
+      "step": 720
+    },
+    {
+      "epoch": 2.8294573643410854,
+      "grad_norm": 0.7945972959985691,
+      "learning_rate": 5.442294080993445e-07,
+      "loss": 0.4401,
+      "step": 730
+    },
+    {
+      "epoch": 2.8682170542635657,
+      "grad_norm": 0.837365677773524,
+      "learning_rate": 5.264447251649954e-07,
+      "loss": 0.4388,
+      "step": 740
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.8082178684556108,
+      "learning_rate": 5.131895964026909e-07,
+      "loss": 0.4368,
+      "step": 750
+    },
+    {
+      "epoch": 2.945736434108527,
+      "grad_norm": 0.8284588236448697,
+      "learning_rate": 5.044910235355121e-07,
+      "loss": 0.4378,
+      "step": 760
+    },
+    {
+      "epoch": 2.9844961240310077,
+      "grad_norm": 0.8033699382168696,
+      "learning_rate": 5.003667262295572e-07,
+      "loss": 0.4376,
+      "step": 770
+    },
+    {
+      "epoch": 3.0,
+      "step": 774,
+      "total_flos": 2591282618695680.0,
+      "train_loss": 0.5117943732005373,
+      "train_runtime": 11288.2174,
+      "train_samples_per_second": 70.154,
+      "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 sha256:2578a660a40240090abf913d860db96d2d901f62173f467f9775cf860294e56c
+size 7672