Model save

README.md

@@ -0,0 +1,57 @@
+---
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: llama3-8b-sft-full
+  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. -->
+
+# llama3-8b-sft-full
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown 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-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9978431433840766,
+    "total_flos": 1.9278929080237425e+18,
+    "train_loss": 0.3424536967062735,
+    "train_runtime": 31340.7737,
+    "train_samples": 63982,
+    "train_samples_per_second": 6.124,
+    "train_steps_per_second": 0.096
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505ba7a6efd48a1c69b36d34d7040eb0284e0956fee384ee644cb440679faf61
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a60a37c499ee6074fb03d31bb32cf2c0cd8825bdaf7bd3880725e90f451329b
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82713ee0706a3b2a17dd1e025746881b9dff19647606a48e3896b17953ba184e
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6a6710e3f24bdd76400a572a7cb42badb26b96992540e1a68783b91e957944
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9978431433840766,
+    "total_flos": 1.9278929080237425e+18,
+    "train_loss": 0.3424536967062735,
+    "train_runtime": 31340.7737,
+    "train_samples": 63982,
+    "train_samples_per_second": 6.124,
+    "train_steps_per_second": 0.096
+}

trainer_state.json

@@ -0,0 +1,450 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9978431433840766,
+  "eval_steps": 500,
+  "global_step": 2997,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001000281329123816,
+      "grad_norm": 62.25,
+      "learning_rate": 6.666666666666668e-08,
+      "loss": 2.3405,
+      "step": 1
+    },
+    {
+      "epoch": 0.0500140664561908,
+      "grad_norm": 6.875,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.3787,
+      "step": 50
+    },
+    {
+      "epoch": 0.1000281329123816,
+      "grad_norm": 3.9375,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6171,
+      "step": 100
+    },
+    {
+      "epoch": 0.1500421993685724,
+      "grad_norm": 3.703125,
+      "learning_rate": 1e-05,
+      "loss": 0.5743,
+      "step": 150
+    },
+    {
+      "epoch": 0.2000562658247632,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.5609,
+      "step": 200
+    },
+    {
+      "epoch": 0.25007033228095404,
+      "grad_norm": 3.171875,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6189,
+      "step": 250
+    },
+    {
+      "epoch": 0.3000843987371448,
+      "grad_norm": 5.90625,
+      "learning_rate": 2e-05,
+      "loss": 0.5975,
+      "step": 300
+    },
+    {
+      "epoch": 0.35009846519333565,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.9983043934122208e-05,
+      "loss": 0.5851,
+      "step": 350
+    },
+    {
+      "epoch": 0.4001125316495264,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.9932233238122834e-05,
+      "loss": 0.567,
+      "step": 400
+    },
+    {
+      "epoch": 0.45012659810571726,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.984774022190361e-05,
+      "loss": 0.5503,
+      "step": 450
+    },
+    {
+      "epoch": 0.5001406645619081,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.972985141929439e-05,
+      "loss": 0.5386,
+      "step": 500
+    },
+    {
+      "epoch": 0.5501547310180989,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.9578966616355823e-05,
+      "loss": 0.5262,
+      "step": 550
+    },
+    {
+      "epoch": 0.6001687974742896,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.9395597495619634e-05,
+      "loss": 0.5219,
+      "step": 600
+    },
+    {
+      "epoch": 0.6501828639304804,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.918036590086405e-05,
+      "loss": 0.5065,
+      "step": 650
+    },
+    {
+      "epoch": 0.7001969303866713,
+      "grad_norm": 1.703125,
+      "learning_rate": 1.8934001728309003e-05,
+      "loss": 0.5041,
+      "step": 700
+    },
+    {
+      "epoch": 0.7502109968428621,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.865734045138245e-05,
+      "loss": 0.4946,
+      "step": 750
+    },
+    {
+      "epoch": 0.8002250632990529,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.8351320287451865e-05,
+      "loss": 0.4906,
+      "step": 800
+    },
+    {
+      "epoch": 0.8502391297552436,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.8016979016129164e-05,
+      "loss": 0.4824,
+      "step": 850
+    },
+    {
+      "epoch": 0.9002531962114345,
+      "grad_norm": 1.4375,
+      "learning_rate": 1.7655450459938786e-05,
+      "loss": 0.4736,
+      "step": 900
+    },
+    {
+      "epoch": 0.9502672626676253,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.726796063928382e-05,
+      "loss": 0.4677,
+      "step": 950
+    },
+    {
+      "epoch": 1.0002813291238162,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.6855823614749474e-05,
+      "loss": 0.4654,
+      "step": 1000
+    },
+    {
+      "epoch": 1.050295395580007,
+      "grad_norm": 1.453125,
+      "learning_rate": 1.6420437030843482e-05,
+      "loss": 0.3223,
+      "step": 1050
+    },
+    {
+      "epoch": 1.1003094620361977,
+      "grad_norm": 1.375,
+      "learning_rate": 1.5963277376285646e-05,
+      "loss": 0.319,
+      "step": 1100
+    },
+    {
+      "epoch": 1.1503235284923885,
+      "grad_norm": 1.2578125,
+      "learning_rate": 1.5485894976919836e-05,
+      "loss": 0.3218,
+      "step": 1150
+    },
+    {
+      "epoch": 1.2003375949485793,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.4989908738228567e-05,
+      "loss": 0.3174,
+      "step": 1200
+    },
+    {
+      "epoch": 1.25035166140477,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.4477000655279376e-05,
+      "loss": 0.3185,
+      "step": 1250
+    },
+    {
+      "epoch": 1.3003657278609608,
+      "grad_norm": 1.5625,
+      "learning_rate": 1.394891010872102e-05,
+      "loss": 0.3153,
+      "step": 1300
+    },
+    {
+      "epoch": 1.3503797943171518,
+      "grad_norm": 1.4375,
+      "learning_rate": 1.3407427966172866e-05,
+      "loss": 0.3161,
+      "step": 1350
+    },
+    {
+      "epoch": 1.4003938607733426,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.2854390509011061e-05,
+      "loss": 0.3117,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4504079272295334,
+      "grad_norm": 1.375,
+      "learning_rate": 1.2291673205146908e-05,
+      "loss": 0.307,
+      "step": 1450
+    },
+    {
+      "epoch": 1.5004219936857242,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.1721184348915384e-05,
+      "loss": 0.3057,
+      "step": 1500
+    },
+    {
+      "epoch": 1.550436060141915,
+      "grad_norm": 1.2890625,
+      "learning_rate": 1.1144858589642251e-05,
+      "loss": 0.3023,
+      "step": 1550
+    },
+    {
+      "epoch": 1.6004501265981057,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.0564650370835772e-05,
+      "loss": 0.2997,
+      "step": 1600
+    },
+    {
+      "epoch": 1.6504641930542965,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.982527302252135e-06,
+      "loss": 0.2989,
+      "step": 1650
+    },
+    {
+      "epoch": 1.7004782595104873,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.40046348731131e-06,
+      "loss": 0.2947,
+      "step": 1700
+    },
+    {
+      "epoch": 1.750492325966678,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.820432828491542e-06,
+      "loss": 0.2935,
+      "step": 1750
+    },
+    {
+      "epoch": 1.8005063924228688,
+      "grad_norm": 1.359375,
+      "learning_rate": 8.244402333405252e-06,
+      "loss": 0.289,
+      "step": 1800
+    },
+    {
+      "epoch": 1.8505204588790596,
+      "grad_norm": 1.40625,
+      "learning_rate": 7.674325444256899e-06,
+      "loss": 0.2874,
+      "step": 1850
+    },
+    {
+      "epoch": 1.9005345253352506,
+      "grad_norm": 1.40625,
+      "learning_rate": 7.112135413304042e-06,
+      "loss": 0.2839,
+      "step": 1900
+    },
+    {
+      "epoch": 1.9505485917914414,
+      "grad_norm": 1.2421875,
+      "learning_rate": 6.55973874678682e-06,
+      "loss": 0.2832,
+      "step": 1950
+    },
+    {
+      "epoch": 2.0005626582476324,
+      "grad_norm": 1.15625,
+      "learning_rate": 6.0190087395588596e-06,
+      "loss": 0.2765,
+      "step": 2000
+    },
+    {
+      "epoch": 2.050576724703823,
+      "grad_norm": 1.2578125,
+      "learning_rate": 5.491779122345093e-06,
+      "loss": 0.1509,
+      "step": 2050
+    },
+    {
+      "epoch": 2.100590791160014,
+      "grad_norm": 1.203125,
+      "learning_rate": 4.979837843169959e-06,
+      "loss": 0.1491,
+      "step": 2100
+    },
+    {
+      "epoch": 2.1506048576162047,
+      "grad_norm": 1.296875,
+      "learning_rate": 4.484921004044509e-06,
+      "loss": 0.149,
+      "step": 2150
+    },
+    {
+      "epoch": 2.2006189240723955,
+      "grad_norm": 1.1875,
+      "learning_rate": 4.008706973474391e-06,
+      "loss": 0.1492,
+      "step": 2200
+    },
+    {
+      "epoch": 2.2506329905285862,
+      "grad_norm": 1.1640625,
+      "learning_rate": 3.5528106947544626e-06,
+      "loss": 0.1477,
+      "step": 2250
+    },
+    {
+      "epoch": 2.300647056984777,
+      "grad_norm": 1.2421875,
+      "learning_rate": 3.118778209351808e-06,
+      "loss": 0.1478,
+      "step": 2300
+    },
+    {
+      "epoch": 2.350661123440968,
+      "grad_norm": 1.3046875,
+      "learning_rate": 2.7080814139495402e-06,
+      "loss": 0.1471,
+      "step": 2350
+    },
+    {
+      "epoch": 2.4006751898971586,
+      "grad_norm": 1.265625,
+      "learning_rate": 2.322113068931391e-06,
+      "loss": 0.1472,
+      "step": 2400
+    },
+    {
+      "epoch": 2.4506892563533493,
+      "grad_norm": 1.2421875,
+      "learning_rate": 1.9621820752343324e-06,
+      "loss": 0.1467,
+      "step": 2450
+    },
+    {
+      "epoch": 2.50070332280954,
+      "grad_norm": 1.1875,
+      "learning_rate": 1.629509035586484e-06,
+      "loss": 0.1449,
+      "step": 2500
+    },
+    {
+      "epoch": 2.550717389265731,
+      "grad_norm": 1.28125,
+      "learning_rate": 1.3252221151830513e-06,
+      "loss": 0.1457,
+      "step": 2550
+    },
+    {
+      "epoch": 2.6007314557219217,
+      "grad_norm": 1.2890625,
+      "learning_rate": 1.0503532158376584e-06,
+      "loss": 0.1447,
+      "step": 2600
+    },
+    {
+      "epoch": 2.6507455221781124,
+      "grad_norm": 1.28125,
+      "learning_rate": 8.058344765833171e-07,
+      "loss": 0.146,
+      "step": 2650
+    },
+    {
+      "epoch": 2.7007595886343037,
+      "grad_norm": 1.3359375,
+      "learning_rate": 5.924951125902545e-07,
+      "loss": 0.1461,
+      "step": 2700
+    },
+    {
+      "epoch": 2.7507736550904944,
+      "grad_norm": 1.1875,
+      "learning_rate": 4.11058603120511e-07,
+      "loss": 0.144,
+      "step": 2750
+    },
+    {
+      "epoch": 2.800787721546685,
+      "grad_norm": 1.171875,
+      "learning_rate": 2.6214023805552826e-07,
+      "loss": 0.1447,
+      "step": 2800
+    },
+    {
+      "epoch": 2.850801788002876,
+      "grad_norm": 1.28125,
+      "learning_rate": 1.462450313169983e-07,
+      "loss": 0.1443,
+      "step": 2850
+    },
+    {
+      "epoch": 2.9008158544590668,
+      "grad_norm": 1.2421875,
+      "learning_rate": 6.376600825699463e-08,
+      "loss": 0.1443,
+      "step": 2900
+    },
+    {
+      "epoch": 2.9508299209152575,
+      "grad_norm": 1.21875,
+      "learning_rate": 1.49828728252277e-08,
+      "loss": 0.1456,
+      "step": 2950
+    },
+    {
+      "epoch": 2.9978431433840766,
+      "step": 2997,
+      "total_flos": 1.9278929080237425e+18,
+      "train_loss": 0.3424536967062735,
+      "train_runtime": 31340.7737,
+      "train_samples_per_second": 6.124,
+      "train_steps_per_second": 0.096
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2997,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1.9278929080237425e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}