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_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_lr2.00E-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: 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: 0.1
+- 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": 0.5476873404603904,
+    "train_runtime": 11104.4038,
+    "train_samples_per_second": 71.315,
+    "train_steps_per_second": 0.07
+}

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 sha256:1d4a4649102f3e2f860fccd7832aca7cfed622247398ba063191c48bb9184a1c
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf989a66c56644617515846d262e028812a507cf8657a3fde3b5b20c26502c5
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1813979e14b438c5c29d4a9ce1dc5b4c4a748db9097258f17ad0381ceaa9076f
+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": 0.5476873404603904,
+    "train_runtime": 11104.4038,
+    "train_samples_per_second": 71.315,
+    "train_steps_per_second": 0.07
+}

trainer_log.jsonl

@@ -0,0 +1,78 @@
+{"current_steps": 10, "total_steps": 774, "loss": 0.8458, "learning_rate": 2.5641025641025636e-07, "epoch": 0.03875968992248062, "percentage": 1.29, "elapsed_time": "0:02:22", "remaining_time": "3:01:34"}
+{"current_steps": 20, "total_steps": 774, "loss": 0.7799, "learning_rate": 5.128205128205127e-07, "epoch": 0.07751937984496124, "percentage": 2.58, "elapsed_time": "0:04:42", "remaining_time": "2:57:35"}
+{"current_steps": 30, "total_steps": 774, "loss": 0.7108, "learning_rate": 7.692307692307693e-07, "epoch": 0.11627906976744186, "percentage": 3.88, "elapsed_time": "0:07:02", "remaining_time": "2:54:37"}
+{"current_steps": 40, "total_steps": 774, "loss": 0.6687, "learning_rate": 1.0256410256410255e-06, "epoch": 0.15503875968992248, "percentage": 5.17, "elapsed_time": "0:09:22", "remaining_time": "2:52:07"}
+{"current_steps": 50, "total_steps": 774, "loss": 0.6366, "learning_rate": 1.2820512820512822e-06, "epoch": 0.1937984496124031, "percentage": 6.46, "elapsed_time": "0:11:43", "remaining_time": "2:49:43"}
+{"current_steps": 60, "total_steps": 774, "loss": 0.6246, "learning_rate": 1.5384615384615385e-06, "epoch": 0.23255813953488372, "percentage": 7.75, "elapsed_time": "0:14:04", "remaining_time": "2:47:27"}
+{"current_steps": 70, "total_steps": 774, "loss": 0.6174, "learning_rate": 1.7948717948717948e-06, "epoch": 0.2713178294573643, "percentage": 9.04, "elapsed_time": "0:16:25", "remaining_time": "2:45:07"}
+{"current_steps": 80, "total_steps": 774, "loss": 0.6066, "learning_rate": 1.9999694388582144e-06, "epoch": 0.31007751937984496, "percentage": 10.34, "elapsed_time": "0:18:45", "remaining_time": "2:42:45"}
+{"current_steps": 90, "total_steps": 774, "loss": 0.6005, "learning_rate": 1.9989000603883424e-06, "epoch": 0.3488372093023256, "percentage": 11.63, "elapsed_time": "0:21:06", "remaining_time": "2:40:28"}
+{"current_steps": 100, "total_steps": 774, "loss": 0.5971, "learning_rate": 1.996305114539343e-06, "epoch": 0.3875968992248062, "percentage": 12.92, "elapsed_time": "0:23:28", "remaining_time": "2:38:11"}
+{"current_steps": 110, "total_steps": 774, "loss": 0.5918, "learning_rate": 1.992189887416728e-06, "epoch": 0.4263565891472868, "percentage": 14.21, "elapsed_time": "0:25:49", "remaining_time": "2:35:54"}
+{"current_steps": 120, "total_steps": 774, "loss": 0.5854, "learning_rate": 1.986562762056617e-06, "epoch": 0.46511627906976744, "percentage": 15.5, "elapsed_time": "0:28:11", "remaining_time": "2:33:37"}
+{"current_steps": 130, "total_steps": 774, "loss": 0.5868, "learning_rate": 1.9794352013488426e-06, "epoch": 0.5038759689922481, "percentage": 16.8, "elapsed_time": "0:30:33", "remaining_time": "2:31:22"}
+{"current_steps": 140, "total_steps": 774, "loss": 0.5841, "learning_rate": 1.970821724686156e-06, "epoch": 0.5426356589147286, "percentage": 18.09, "elapsed_time": "0:32:56", "remaining_time": "2:29:08"}
+{"current_steps": 150, "total_steps": 774, "loss": 0.5873, "learning_rate": 1.960739878387102e-06, "epoch": 0.5813953488372093, "percentage": 19.38, "elapsed_time": "0:35:18", "remaining_time": "2:26:54"}
+{"current_steps": 160, "total_steps": 774, "loss": 0.5765, "learning_rate": 1.9492101999528085e-06, "epoch": 0.6201550387596899, "percentage": 20.67, "elapsed_time": "0:37:40", "remaining_time": "2:24:35"}
+{"current_steps": 170, "total_steps": 774, "loss": 0.5743, "learning_rate": 1.936256176230509e-06, "epoch": 0.6589147286821705, "percentage": 21.96, "elapsed_time": "0:40:03", "remaining_time": "2:22:18"}
+{"current_steps": 180, "total_steps": 774, "loss": 0.571, "learning_rate": 1.921904195569016e-06, "epoch": 0.6976744186046512, "percentage": 23.26, "elapsed_time": "0:42:25", "remaining_time": "2:19:59"}
+{"current_steps": 190, "total_steps": 774, "loss": 0.5792, "learning_rate": 1.906183494063612e-06, "epoch": 0.7364341085271318, "percentage": 24.55, "elapsed_time": "0:44:46", "remaining_time": "2:17:38"}
+{"current_steps": 200, "total_steps": 774, "loss": 0.569, "learning_rate": 1.8891260959998633e-06, "epoch": 0.7751937984496124, "percentage": 25.84, "elapsed_time": "0:47:08", "remaining_time": "2:15:19"}
+{"current_steps": 210, "total_steps": 774, "loss": 0.5719, "learning_rate": 1.8707667486176679e-06, "epoch": 0.813953488372093, "percentage": 27.13, "elapsed_time": "0:49:31", "remaining_time": "2:13:00"}
+{"current_steps": 220, "total_steps": 774, "loss": 0.5708, "learning_rate": 1.851142851328443e-06, "epoch": 0.8527131782945736, "percentage": 28.42, "elapsed_time": "0:51:53", "remaining_time": "2:10:40"}
+{"current_steps": 230, "total_steps": 774, "loss": 0.5675, "learning_rate": 1.8302943795296272e-06, "epoch": 0.8914728682170543, "percentage": 29.72, "elapsed_time": "0:54:15", "remaining_time": "2:08:19"}
+{"current_steps": 240, "total_steps": 774, "loss": 0.5679, "learning_rate": 1.8082638031717025e-06, "epoch": 0.9302325581395349, "percentage": 31.01, "elapsed_time": "0:56:37", "remaining_time": "2:05:59"}
+{"current_steps": 250, "total_steps": 774, "loss": 0.5623, "learning_rate": 1.78509600024362e-06, "epoch": 0.9689922480620154, "percentage": 32.3, "elapsed_time": "0:58:59", "remaining_time": "2:03:38"}
+{"current_steps": 260, "total_steps": 774, "loss": 0.5602, "learning_rate": 1.7608381653528608e-06, "epoch": 1.0077519379844961, "percentage": 33.59, "elapsed_time": "1:01:37", "remaining_time": "2:01:48"}
+{"current_steps": 270, "total_steps": 774, "loss": 0.5356, "learning_rate": 1.7355397135863707e-06, "epoch": 1.0465116279069768, "percentage": 34.88, "elapsed_time": "1:03:59", "remaining_time": "1:59:27"}
+{"current_steps": 280, "total_steps": 774, "loss": 0.5371, "learning_rate": 1.7092521798482026e-06, "epoch": 1.0852713178294573, "percentage": 36.18, "elapsed_time": "1:06:23", "remaining_time": "1:57:07"}
+{"current_steps": 290, "total_steps": 774, "loss": 0.532, "learning_rate": 1.6820291138789297e-06, "epoch": 1.124031007751938, "percentage": 37.47, "elapsed_time": "1:08:45", "remaining_time": "1:54:45"}
+{"current_steps": 300, "total_steps": 774, "loss": 0.5278, "learning_rate": 1.653925971170678e-06, "epoch": 1.1627906976744187, "percentage": 38.76, "elapsed_time": "1:11:08", "remaining_time": "1:52:24"}
+{"current_steps": 310, "total_steps": 774, "loss": 0.5343, "learning_rate": 1.625e-06, "epoch": 1.2015503875968991, "percentage": 40.05, "elapsed_time": "1:13:30", "remaining_time": "1:50:01"}
+{"current_steps": 320, "total_steps": 774, "loss": 0.5316, "learning_rate": 1.595310124808702e-06, "epoch": 1.2403100775193798, "percentage": 41.34, "elapsed_time": "1:15:52", "remaining_time": "1:47:38"}
+{"current_steps": 330, "total_steps": 774, "loss": 0.5317, "learning_rate": 1.5649168261701984e-06, "epoch": 1.2790697674418605, "percentage": 42.64, "elapsed_time": "1:18:14", "remaining_time": "1:45:16"}
+{"current_steps": 340, "total_steps": 774, "loss": 0.5351, "learning_rate": 1.5338820175859021e-06, "epoch": 1.3178294573643412, "percentage": 43.93, "elapsed_time": "1:20:37", "remaining_time": "1:42:54"}
+{"current_steps": 350, "total_steps": 774, "loss": 0.5319, "learning_rate": 1.5022689193626311e-06, "epoch": 1.3565891472868217, "percentage": 45.22, "elapsed_time": "1:22:59", "remaining_time": "1:40:32"}
+{"current_steps": 360, "total_steps": 774, "loss": 0.5357, "learning_rate": 1.4701419298279508e-06, "epoch": 1.3953488372093024, "percentage": 46.51, "elapsed_time": "1:25:21", "remaining_time": "1:38:10"}
+{"current_steps": 370, "total_steps": 774, "loss": 0.5335, "learning_rate": 1.437566494145797e-06, "epoch": 1.4341085271317828, "percentage": 47.8, "elapsed_time": "1:27:44", "remaining_time": "1:35:48"}
+{"current_steps": 380, "total_steps": 774, "loss": 0.5303, "learning_rate": 1.4046089709996126e-06, "epoch": 1.4728682170542635, "percentage": 49.1, "elapsed_time": "1:30:07", "remaining_time": "1:33:26"}
+{"current_steps": 390, "total_steps": 774, "loss": 0.5338, "learning_rate": 1.3713364974145735e-06, "epoch": 1.5116279069767442, "percentage": 50.39, "elapsed_time": "1:32:29", "remaining_time": "1:31:03"}
+{"current_steps": 400, "total_steps": 774, "loss": 0.5301, "learning_rate": 1.3378168519942735e-06, "epoch": 1.550387596899225, "percentage": 51.68, "elapsed_time": "1:34:51", "remaining_time": "1:28:41"}
+{"current_steps": 410, "total_steps": 774, "loss": 0.5255, "learning_rate": 1.304118316850462e-06, "epoch": 1.5891472868217056, "percentage": 52.97, "elapsed_time": "1:37:14", "remaining_time": "1:26:19"}
+{"current_steps": 420, "total_steps": 774, "loss": 0.5307, "learning_rate": 1.2703095385071009e-06, "epoch": 1.627906976744186, "percentage": 54.26, "elapsed_time": "1:39:37", "remaining_time": "1:23:58"}
+{"current_steps": 430, "total_steps": 774, "loss": 0.5336, "learning_rate": 1.2364593880620795e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:41:59", "remaining_time": "1:21:35"}
+{"current_steps": 440, "total_steps": 774, "loss": 0.5291, "learning_rate": 1.2026368208914614e-06, "epoch": 1.7054263565891472, "percentage": 56.85, "elapsed_time": "1:44:22", "remaining_time": "1:19:13"}
+{"current_steps": 450, "total_steps": 774, "loss": 0.5322, "learning_rate": 1.1689107361820438e-06, "epoch": 1.744186046511628, "percentage": 58.14, "elapsed_time": "1:46:45", "remaining_time": "1:16:51"}
+{"current_steps": 460, "total_steps": 774, "loss": 0.528, "learning_rate": 1.1353498365783853e-06, "epoch": 1.7829457364341086, "percentage": 59.43, "elapsed_time": "1:49:08", "remaining_time": "1:14:29"}
+{"current_steps": 470, "total_steps": 774, "loss": 0.5294, "learning_rate": 1.1020224882302e-06, "epoch": 1.8217054263565893, "percentage": 60.72, "elapsed_time": "1:51:31", "remaining_time": "1:12:07"}
+{"current_steps": 480, "total_steps": 774, "loss": 0.532, "learning_rate": 1.0689965815252208e-06, "epoch": 1.8604651162790697, "percentage": 62.02, "elapsed_time": "1:53:54", "remaining_time": "1:09:46"}
+{"current_steps": 490, "total_steps": 774, "loss": 0.5275, "learning_rate": 1.036339392791225e-06, "epoch": 1.8992248062015504, "percentage": 63.31, "elapsed_time": "1:56:27", "remaining_time": "1:07:29"}
+{"current_steps": 500, "total_steps": 774, "loss": 0.5302, "learning_rate": 1.0041174472489488e-06, "epoch": 1.937984496124031, "percentage": 64.6, "elapsed_time": "1:58:49", "remaining_time": "1:05:07"}
+{"current_steps": 510, "total_steps": 774, "loss": 0.5275, "learning_rate": 9.723963834950642e-07, "epoch": 1.9767441860465116, "percentage": 65.89, "elapsed_time": "2:01:13", "remaining_time": "1:02:44"}
+{"current_steps": 520, "total_steps": 774, "loss": 0.5175, "learning_rate": 9.412408197912775e-07, "epoch": 2.0155038759689923, "percentage": 67.18, "elapsed_time": "2:03:50", "remaining_time": "1:00:29"}
+{"current_steps": 530, "total_steps": 774, "loss": 0.5004, "learning_rate": 9.107142224319299e-07, "epoch": 2.054263565891473, "percentage": 68.48, "elapsed_time": "2:06:14", "remaining_time": "0:58:07"}
+{"current_steps": 540, "total_steps": 774, "loss": 0.4979, "learning_rate": 8.808787764582444e-07, "epoch": 2.0930232558139537, "percentage": 69.77, "elapsed_time": "2:08:37", "remaining_time": "0:55:44"}
+{"current_steps": 550, "total_steps": 774, "loss": 0.4978, "learning_rate": 8.51795258982585e-07, "epoch": 2.1317829457364343, "percentage": 71.06, "elapsed_time": "2:11:00", "remaining_time": "0:53:21"}
+{"current_steps": 560, "total_steps": 774, "loss": 0.5008, "learning_rate": 8.235229153807735e-07, "epoch": 2.1705426356589146, "percentage": 72.35, "elapsed_time": "2:13:23", "remaining_time": "0:50:58"}
+{"current_steps": 570, "total_steps": 774, "loss": 0.4976, "learning_rate": 7.961193386046763e-07, "epoch": 2.2093023255813953, "percentage": 73.64, "elapsed_time": "2:15:45", "remaining_time": "0:48:35"}
+{"current_steps": 580, "total_steps": 774, "loss": 0.4974, "learning_rate": 7.696403518609027e-07, "epoch": 2.248062015503876, "percentage": 74.94, "elapsed_time": "2:18:08", "remaining_time": "0:46:12"}
+{"current_steps": 590, "total_steps": 774, "loss": 0.5003, "learning_rate": 7.441398948946146e-07, "epoch": 2.2868217054263567, "percentage": 76.23, "elapsed_time": "2:20:36", "remaining_time": "0:43:51"}
+{"current_steps": 600, "total_steps": 774, "loss": 0.4968, "learning_rate": 7.196699141100894e-07, "epoch": 2.3255813953488373, "percentage": 77.52, "elapsed_time": "2:22:59", "remaining_time": "0:41:27"}
+{"current_steps": 610, "total_steps": 774, "loss": 0.5005, "learning_rate": 6.962802567518761e-07, "epoch": 2.3643410852713176, "percentage": 78.81, "elapsed_time": "2:25:22", "remaining_time": "0:39:04"}
+{"current_steps": 620, "total_steps": 774, "loss": 0.4995, "learning_rate": 6.740185693620994e-07, "epoch": 2.4031007751937983, "percentage": 80.1, "elapsed_time": "2:27:44", "remaining_time": "0:36:41"}
+{"current_steps": 630, "total_steps": 774, "loss": 0.498, "learning_rate": 6.529302007207671e-07, "epoch": 2.441860465116279, "percentage": 81.4, "elapsed_time": "2:30:08", "remaining_time": "0:34:18"}
+{"current_steps": 640, "total_steps": 774, "loss": 0.5007, "learning_rate": 6.33058109466795e-07, "epoch": 2.4806201550387597, "percentage": 82.69, "elapsed_time": "2:32:30", "remaining_time": "0:31:55"}
+{"current_steps": 650, "total_steps": 774, "loss": 0.497, "learning_rate": 6.144427765879349e-07, "epoch": 2.5193798449612403, "percentage": 83.98, "elapsed_time": "2:34:53", "remaining_time": "0:29:32"}
+{"current_steps": 660, "total_steps": 774, "loss": 0.5, "learning_rate": 5.97122122957871e-07, "epoch": 2.558139534883721, "percentage": 85.27, "elapsed_time": "2:37:16", "remaining_time": "0:27:09"}
+{"current_steps": 670, "total_steps": 774, "loss": 0.5023, "learning_rate": 5.811314320884633e-07, "epoch": 2.5968992248062017, "percentage": 86.56, "elapsed_time": "2:39:39", "remaining_time": "0:24:46"}
+{"current_steps": 680, "total_steps": 774, "loss": 0.4958, "learning_rate": 5.665032782545057e-07, "epoch": 2.6356589147286824, "percentage": 87.86, "elapsed_time": "2:42:02", "remaining_time": "0:22:24"}
+{"current_steps": 690, "total_steps": 774, "loss": 0.4988, "learning_rate": 5.532674601374064e-07, "epoch": 2.6744186046511627, "percentage": 89.15, "elapsed_time": "2:44:28", "remaining_time": "0:20:01"}
+{"current_steps": 700, "total_steps": 774, "loss": 0.4986, "learning_rate": 5.414509401229674e-07, "epoch": 2.7131782945736433, "percentage": 90.44, "elapsed_time": "2:46:51", "remaining_time": "0:17:38"}
+{"current_steps": 710, "total_steps": 774, "loss": 0.4949, "learning_rate": 5.31077789376919e-07, "epoch": 2.751937984496124, "percentage": 91.73, "elapsed_time": "2:49:15", "remaining_time": "0:15:15"}
+{"current_steps": 720, "total_steps": 774, "loss": 0.5007, "learning_rate": 5.221691388100914e-07, "epoch": 2.7906976744186047, "percentage": 93.02, "elapsed_time": "2:51:37", "remaining_time": "0:12:52"}
+{"current_steps": 730, "total_steps": 774, "loss": 0.501, "learning_rate": 5.147431360331148e-07, "epoch": 2.8294573643410854, "percentage": 94.32, "elapsed_time": "2:54:00", "remaining_time": "0:10:29"}
+{"current_steps": 740, "total_steps": 774, "loss": 0.5004, "learning_rate": 5.088149083883318e-07, "epoch": 2.8682170542635657, "percentage": 95.61, "elapsed_time": "2:56:23", "remaining_time": "0:08:06"}
+{"current_steps": 750, "total_steps": 774, "loss": 0.4972, "learning_rate": 5.043965321342303e-07, "epoch": 2.9069767441860463, "percentage": 96.9, "elapsed_time": "2:58:45", "remaining_time": "0:05:43"}
+{"current_steps": 760, "total_steps": 774, "loss": 0.499, "learning_rate": 5.014970078451707e-07, "epoch": 2.945736434108527, "percentage": 98.19, "elapsed_time": "3:01:10", "remaining_time": "0:03:20"}
+{"current_steps": 770, "total_steps": 774, "loss": 0.4989, "learning_rate": 5.001222420765189e-07, "epoch": 2.9844961240310077, "percentage": 99.48, "elapsed_time": "3:03:34", "remaining_time": "0:00:57"}
+{"current_steps": 774, "total_steps": 774, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:05:01", "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": 10.504178991363052,
+      "learning_rate": 2.5641025641025636e-07,
+      "loss": 0.8458,
+      "step": 10
+    },
+    {
+      "epoch": 0.07751937984496124,
+      "grad_norm": 7.381947977323151,
+      "learning_rate": 5.128205128205127e-07,
+      "loss": 0.7799,
+      "step": 20
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 2.5826285235437,
+      "learning_rate": 7.692307692307693e-07,
+      "loss": 0.7108,
+      "step": 30
+    },
+    {
+      "epoch": 0.15503875968992248,
+      "grad_norm": 1.3836555525424847,
+      "learning_rate": 1.0256410256410255e-06,
+      "loss": 0.6687,
+      "step": 40
+    },
+    {
+      "epoch": 0.1937984496124031,
+      "grad_norm": 1.014458539772153,
+      "learning_rate": 1.2820512820512822e-06,
+      "loss": 0.6366,
+      "step": 50
+    },
+    {
+      "epoch": 0.23255813953488372,
+      "grad_norm": 1.585981691295269,
+      "learning_rate": 1.5384615384615385e-06,
+      "loss": 0.6246,
+      "step": 60
+    },
+    {
+      "epoch": 0.2713178294573643,
+      "grad_norm": 3.44825159434466,
+      "learning_rate": 1.7948717948717948e-06,
+      "loss": 0.6174,
+      "step": 70
+    },
+    {
+      "epoch": 0.31007751937984496,
+      "grad_norm": 1.982674865546014,
+      "learning_rate": 1.9999694388582144e-06,
+      "loss": 0.6066,
+      "step": 80
+    },
+    {
+      "epoch": 0.3488372093023256,
+      "grad_norm": 2.458444987689359,
+      "learning_rate": 1.9989000603883424e-06,
+      "loss": 0.6005,
+      "step": 90
+    },
+    {
+      "epoch": 0.3875968992248062,
+      "grad_norm": 2.343381635913089,
+      "learning_rate": 1.996305114539343e-06,
+      "loss": 0.5971,
+      "step": 100
+    },
+    {
+      "epoch": 0.4263565891472868,
+      "grad_norm": 2.116790057563806,
+      "learning_rate": 1.992189887416728e-06,
+      "loss": 0.5918,
+      "step": 110
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 1.8817692202495955,
+      "learning_rate": 1.986562762056617e-06,
+      "loss": 0.5854,
+      "step": 120
+    },
+    {
+      "epoch": 0.5038759689922481,
+      "grad_norm": 1.1555850303351525,
+      "learning_rate": 1.9794352013488426e-06,
+      "loss": 0.5868,
+      "step": 130
+    },
+    {
+      "epoch": 0.5426356589147286,
+      "grad_norm": 1.2072266062129773,
+      "learning_rate": 1.970821724686156e-06,
+      "loss": 0.5841,
+      "step": 140
+    },
+    {
+      "epoch": 0.5813953488372093,
+      "grad_norm": 1.2712859440886186,
+      "learning_rate": 1.960739878387102e-06,
+      "loss": 0.5873,
+      "step": 150
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 1.0711769823831143,
+      "learning_rate": 1.9492101999528085e-06,
+      "loss": 0.5765,
+      "step": 160
+    },
+    {
+      "epoch": 0.6589147286821705,
+      "grad_norm": 1.1252486933707169,
+      "learning_rate": 1.936256176230509e-06,
+      "loss": 0.5743,
+      "step": 170
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 1.236488936450148,
+      "learning_rate": 1.921904195569016e-06,
+      "loss": 0.571,
+      "step": 180
+    },
+    {
+      "epoch": 0.7364341085271318,
+      "grad_norm": 1.5164803706542536,
+      "learning_rate": 1.906183494063612e-06,
+      "loss": 0.5792,
+      "step": 190
+    },
+    {
+      "epoch": 0.7751937984496124,
+      "grad_norm": 1.6046208537277091,
+      "learning_rate": 1.8891260959998633e-06,
+      "loss": 0.569,
+      "step": 200
+    },
+    {
+      "epoch": 0.813953488372093,
+      "grad_norm": 1.9817910238276475,
+      "learning_rate": 1.8707667486176679e-06,
+      "loss": 0.5719,
+      "step": 210
+    },
+    {
+      "epoch": 0.8527131782945736,
+      "grad_norm": 1.9272271539347614,
+      "learning_rate": 1.851142851328443e-06,
+      "loss": 0.5708,
+      "step": 220
+    },
+    {
+      "epoch": 0.8914728682170543,
+      "grad_norm": 1.5196843393234274,
+      "learning_rate": 1.8302943795296272e-06,
+      "loss": 0.5675,
+      "step": 230
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 1.2912623979172295,
+      "learning_rate": 1.8082638031717025e-06,
+      "loss": 0.5679,
+      "step": 240
+    },
+    {
+      "epoch": 0.9689922480620154,
+      "grad_norm": 1.7822192653962246,
+      "learning_rate": 1.78509600024362e-06,
+      "loss": 0.5623,
+      "step": 250
+    },
+    {
+      "epoch": 1.0077519379844961,
+      "grad_norm": 1.62410750447254,
+      "learning_rate": 1.7608381653528608e-06,
+      "loss": 0.5602,
+      "step": 260
+    },
+    {
+      "epoch": 1.0465116279069768,
+      "grad_norm": 1.8870207655397844,
+      "learning_rate": 1.7355397135863707e-06,
+      "loss": 0.5356,
+      "step": 270
+    },
+    {
+      "epoch": 1.0852713178294573,
+      "grad_norm": 1.6710151041733234,
+      "learning_rate": 1.7092521798482026e-06,
+      "loss": 0.5371,
+      "step": 280
+    },
+    {
+      "epoch": 1.124031007751938,
+      "grad_norm": 1.5395040454216624,
+      "learning_rate": 1.6820291138789297e-06,
+      "loss": 0.532,
+      "step": 290
+    },
+    {
+      "epoch": 1.1627906976744187,
+      "grad_norm": 2.052202291851852,
+      "learning_rate": 1.653925971170678e-06,
+      "loss": 0.5278,
+      "step": 300
+    },
+    {
+      "epoch": 1.2015503875968991,
+      "grad_norm": 1.5844551006372056,
+      "learning_rate": 1.625e-06,
+      "loss": 0.5343,
+      "step": 310
+    },
+    {
+      "epoch": 1.2403100775193798,
+      "grad_norm": 1.3812034501539154,
+      "learning_rate": 1.595310124808702e-06,
+      "loss": 0.5316,
+      "step": 320
+    },
+    {
+      "epoch": 1.2790697674418605,
+      "grad_norm": 1.7723638115971123,
+      "learning_rate": 1.5649168261701984e-06,
+      "loss": 0.5317,
+      "step": 330
+    },
+    {
+      "epoch": 1.3178294573643412,
+      "grad_norm": 1.2780759033872613,
+      "learning_rate": 1.5338820175859021e-06,
+      "loss": 0.5351,
+      "step": 340
+    },
+    {
+      "epoch": 1.3565891472868217,
+      "grad_norm": 1.235123641088868,
+      "learning_rate": 1.5022689193626311e-06,
+      "loss": 0.5319,
+      "step": 350
+    },
+    {
+      "epoch": 1.3953488372093024,
+      "grad_norm": 1.2676746189931802,
+      "learning_rate": 1.4701419298279508e-06,
+      "loss": 0.5357,
+      "step": 360
+    },
+    {
+      "epoch": 1.4341085271317828,
+      "grad_norm": 1.241986972002011,
+      "learning_rate": 1.437566494145797e-06,
+      "loss": 0.5335,
+      "step": 370
+    },
+    {
+      "epoch": 1.4728682170542635,
+      "grad_norm": 1.3788277618241498,
+      "learning_rate": 1.4046089709996126e-06,
+      "loss": 0.5303,
+      "step": 380
+    },
+    {
+      "epoch": 1.5116279069767442,
+      "grad_norm": 1.4680842378269845,
+      "learning_rate": 1.3713364974145735e-06,
+      "loss": 0.5338,
+      "step": 390
+    },
+    {
+      "epoch": 1.550387596899225,
+      "grad_norm": 1.2172170594487848,
+      "learning_rate": 1.3378168519942735e-06,
+      "loss": 0.5301,
+      "step": 400
+    },
+    {
+      "epoch": 1.5891472868217056,
+      "grad_norm": 1.0674873334005204,
+      "learning_rate": 1.304118316850462e-06,
+      "loss": 0.5255,
+      "step": 410
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.0072080265190457,
+      "learning_rate": 1.2703095385071009e-06,
+      "loss": 0.5307,
+      "step": 420
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.9867912958850044,
+      "learning_rate": 1.2364593880620795e-06,
+      "loss": 0.5336,
+      "step": 430
+    },
+    {
+      "epoch": 1.7054263565891472,
+      "grad_norm": 1.1290015246787364,
+      "learning_rate": 1.2026368208914614e-06,
+      "loss": 0.5291,
+      "step": 440
+    },
+    {
+      "epoch": 1.744186046511628,
+      "grad_norm": 0.9563827008468312,
+      "learning_rate": 1.1689107361820438e-06,
+      "loss": 0.5322,
+      "step": 450
+    },
+    {
+      "epoch": 1.7829457364341086,
+      "grad_norm": 1.0257481624305507,
+      "learning_rate": 1.1353498365783853e-06,
+      "loss": 0.528,
+      "step": 460
+    },
+    {
+      "epoch": 1.8217054263565893,
+      "grad_norm": 1.1346492567202195,
+      "learning_rate": 1.1020224882302e-06,
+      "loss": 0.5294,
+      "step": 470
+    },
+    {
+      "epoch": 1.8604651162790697,
+      "grad_norm": 1.0115825667769958,
+      "learning_rate": 1.0689965815252208e-06,
+      "loss": 0.532,
+      "step": 480
+    },
+    {
+      "epoch": 1.8992248062015504,
+      "grad_norm": 1.0042229226871666,
+      "learning_rate": 1.036339392791225e-06,
+      "loss": 0.5275,
+      "step": 490
+    },
+    {
+      "epoch": 1.937984496124031,
+      "grad_norm": 1.005308949941088,
+      "learning_rate": 1.0041174472489488e-06,
+      "loss": 0.5302,
+      "step": 500
+    },
+    {
+      "epoch": 1.9767441860465116,
+      "grad_norm": 1.1117825561117929,
+      "learning_rate": 9.723963834950642e-07,
+      "loss": 0.5275,
+      "step": 510
+    },
+    {
+      "epoch": 2.0155038759689923,
+      "grad_norm": 1.9185294933169306,
+      "learning_rate": 9.412408197912775e-07,
+      "loss": 0.5175,
+      "step": 520
+    },
+    {
+      "epoch": 2.054263565891473,
+      "grad_norm": 0.9775717236599951,
+      "learning_rate": 9.107142224319299e-07,
+      "loss": 0.5004,
+      "step": 530
+    },
+    {
+      "epoch": 2.0930232558139537,
+      "grad_norm": 0.9698183378316411,
+      "learning_rate": 8.808787764582444e-07,
+      "loss": 0.4979,
+      "step": 540
+    },
+    {
+      "epoch": 2.1317829457364343,
+      "grad_norm": 0.8939753411141715,
+      "learning_rate": 8.51795258982585e-07,
+      "loss": 0.4978,
+      "step": 550
+    },
+    {
+      "epoch": 2.1705426356589146,
+      "grad_norm": 0.8669584237005413,
+      "learning_rate": 8.235229153807735e-07,
+      "loss": 0.5008,
+      "step": 560
+    },
+    {
+      "epoch": 2.2093023255813953,
+      "grad_norm": 0.9193128763310806,
+      "learning_rate": 7.961193386046763e-07,
+      "loss": 0.4976,
+      "step": 570
+    },
+    {
+      "epoch": 2.248062015503876,
+      "grad_norm": 0.9439462012499107,
+      "learning_rate": 7.696403518609027e-07,
+      "loss": 0.4974,
+      "step": 580
+    },
+    {
+      "epoch": 2.2868217054263567,
+      "grad_norm": 0.8206429610687878,
+      "learning_rate": 7.441398948946146e-07,
+      "loss": 0.5003,
+      "step": 590
+    },
+    {
+      "epoch": 2.3255813953488373,
+      "grad_norm": 0.9065243765505303,
+      "learning_rate": 7.196699141100894e-07,
+      "loss": 0.4968,
+      "step": 600
+    },
+    {
+      "epoch": 2.3643410852713176,
+      "grad_norm": 0.858508861854295,
+      "learning_rate": 6.962802567518761e-07,
+      "loss": 0.5005,
+      "step": 610
+    },
+    {
+      "epoch": 2.4031007751937983,
+      "grad_norm": 0.9833838563590535,
+      "learning_rate": 6.740185693620994e-07,
+      "loss": 0.4995,
+      "step": 620
+    },
+    {
+      "epoch": 2.441860465116279,
+      "grad_norm": 0.885153736445547,
+      "learning_rate": 6.529302007207671e-07,
+      "loss": 0.498,
+      "step": 630
+    },
+    {
+      "epoch": 2.4806201550387597,
+      "grad_norm": 0.8996981573726175,
+      "learning_rate": 6.33058109466795e-07,
+      "loss": 0.5007,
+      "step": 640
+    },
+    {
+      "epoch": 2.5193798449612403,
+      "grad_norm": 0.8673239172314842,
+      "learning_rate": 6.144427765879349e-07,
+      "loss": 0.497,
+      "step": 650
+    },
+    {
+      "epoch": 2.558139534883721,
+      "grad_norm": 0.8366781370200579,
+      "learning_rate": 5.97122122957871e-07,
+      "loss": 0.5,
+      "step": 660
+    },
+    {
+      "epoch": 2.5968992248062017,
+      "grad_norm": 0.9702642475051838,
+      "learning_rate": 5.811314320884633e-07,
+      "loss": 0.5023,
+      "step": 670
+    },
+    {
+      "epoch": 2.6356589147286824,
+      "grad_norm": 0.9136475357025224,
+      "learning_rate": 5.665032782545057e-07,
+      "loss": 0.4958,
+      "step": 680
+    },
+    {
+      "epoch": 2.6744186046511627,
+      "grad_norm": 0.8658836817074663,
+      "learning_rate": 5.532674601374064e-07,
+      "loss": 0.4988,
+      "step": 690
+    },
+    {
+      "epoch": 2.7131782945736433,
+      "grad_norm": 0.8855084789592435,
+      "learning_rate": 5.414509401229674e-07,
+      "loss": 0.4986,
+      "step": 700
+    },
+    {
+      "epoch": 2.751937984496124,
+      "grad_norm": 0.8490347378943165,
+      "learning_rate": 5.31077789376919e-07,
+      "loss": 0.4949,
+      "step": 710
+    },
+    {
+      "epoch": 2.7906976744186047,
+      "grad_norm": 0.8691819524646007,
+      "learning_rate": 5.221691388100914e-07,
+      "loss": 0.5007,
+      "step": 720
+    },
+    {
+      "epoch": 2.8294573643410854,
+      "grad_norm": 0.8260085837299043,
+      "learning_rate": 5.147431360331148e-07,
+      "loss": 0.501,
+      "step": 730
+    },
+    {
+      "epoch": 2.8682170542635657,
+      "grad_norm": 0.9467715896533448,
+      "learning_rate": 5.088149083883318e-07,
+      "loss": 0.5004,
+      "step": 740
+    },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.8998684475047533,
+      "learning_rate": 5.043965321342303e-07,
+      "loss": 0.4972,
+      "step": 750
+    },
+    {
+      "epoch": 2.945736434108527,
+      "grad_norm": 0.8540133287241886,
+      "learning_rate": 5.014970078451707e-07,
+      "loss": 0.499,
+      "step": 760
+    },
+    {
+      "epoch": 2.9844961240310077,
+      "grad_norm": 0.9000594166628875,
+      "learning_rate": 5.001222420765189e-07,
+      "loss": 0.4989,
+      "step": 770
+    },
+    {
+      "epoch": 3.0,
+      "step": 774,
+      "total_flos": 2591282618695680.0,
+      "train_loss": 0.5476873404603904,
+      "train_runtime": 11104.4038,
+      "train_samples_per_second": 71.315,
+      "train_steps_per_second": 0.07
+    }
+  ],
+  "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:c846defce8df2f680b04d6dc308d6a18da5d03fc36db1577fdf42a587ec35697
+size 7672