Model save

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- ndcg
+- generated_from_trainer
+model-index:
+- name: mistral-7b-base-approx_ndcg_1-listsize_8-alpha_25.0-batchsize_128
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhaoyang1/huggingface/runs/13nrxem0)
+# mistral-7b-base-approx_ndcg_1-listsize_8-alpha_25.0-batchsize_128
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: -0.9810
+- Logps: -291.1517
+- Logits: -2.9495
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Logps     | Logits  |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
+| -0.9788       | 0.4275 | 200  | -0.9776         | -289.3082 | -3.0493 |
+| -0.9812       | 0.8549 | 400  | -0.9810         | -291.1517 | -2.9495 |
+
+
+### Framework versions
+
+- Transformers 4.42.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9981298423724285,
+    "total_flos": 0.0,
+    "train_loss": -0.9702747563733789,
+    "train_runtime": 45631.769,
+    "train_samples": 59880,
+    "train_samples_per_second": 1.312,
+    "train_steps_per_second": 0.01
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.42.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e13ca6930fe75d694bde2201b96694802eb17a72fc1e7527a6fb46fa20f96cb
+size 4943162240

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc2b6261613135930fb4ec6a3d2d1ae32db5b217dd8045b56751a1feb2d2fbc
+size 4999819232

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d0bb1787a6731ce1ccd2a0ff687943088bb244d8f02c7616358b976e32f0a0
+size 4540516256

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "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"
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9981298423724285,
+    "total_flos": 0.0,
+    "train_loss": -0.9702747563733789,
+    "train_runtime": 45631.769,
+    "train_samples": 59880,
+    "train_samples_per_second": 1.312,
+    "train_steps_per_second": 0.01
+}

trainer_state.json

@@ -0,0 +1,908 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9981298423724285,
+  "eval_steps": 200,
+  "global_step": 467,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0021373230029388193,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "logits": -2.7276527881622314,
+      "logps": -123.19757843017578,
+      "loss": -0.7819,
+      "step": 1
+    },
+    {
+      "epoch": 0.010686615014694095,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "logits": -2.8715224266052246,
+      "logps": -234.59034729003906,
+      "loss": -0.7834,
+      "step": 5
+    },
+    {
+      "epoch": 0.02137323002938819,
+      "grad_norm": 62.58979166531292,
+      "learning_rate": 3.191489361702127e-08,
+      "logits": -2.846045732498169,
+      "logps": -248.165771484375,
+      "loss": -0.7829,
+      "step": 10
+    },
+    {
+      "epoch": 0.03205984504408229,
+      "grad_norm": 165.21106318043798,
+      "learning_rate": 7.446808510638298e-08,
+      "logits": -2.777956485748291,
+      "logps": -229.2180938720703,
+      "loss": -0.7878,
+      "step": 15
+    },
+    {
+      "epoch": 0.04274646005877638,
+      "grad_norm": 73.29436509866687,
+      "learning_rate": 1.2765957446808508e-07,
+      "logits": -2.769435405731201,
+      "logps": -204.04058837890625,
+      "loss": -0.86,
+      "step": 20
+    },
+    {
+      "epoch": 0.053433075073470476,
+      "grad_norm": 43.89267095591359,
+      "learning_rate": 1.8085106382978725e-07,
+      "logits": -2.9436452388763428,
+      "logps": -289.7768859863281,
+      "loss": -0.939,
+      "step": 25
+    },
+    {
+      "epoch": 0.06411969008816458,
+      "grad_norm": 29.65124187980817,
+      "learning_rate": 2.3404255319148937e-07,
+      "logits": -2.9300923347473145,
+      "logps": -277.5953674316406,
+      "loss": -0.9585,
+      "step": 30
+    },
+    {
+      "epoch": 0.07480630510285867,
+      "grad_norm": 27.17018222606885,
+      "learning_rate": 2.872340425531915e-07,
+      "logits": -2.9261233806610107,
+      "logps": -234.77285766601562,
+      "loss": -0.9666,
+      "step": 35
+    },
+    {
+      "epoch": 0.08549292011755276,
+      "grad_norm": 23.213967474767983,
+      "learning_rate": 3.404255319148936e-07,
+      "logits": -2.960068464279175,
+      "logps": -236.64358520507812,
+      "loss": -0.9697,
+      "step": 40
+    },
+    {
+      "epoch": 0.09617953513224686,
+      "grad_norm": 21.820617838068017,
+      "learning_rate": 3.9361702127659574e-07,
+      "logits": -2.910217046737671,
+      "logps": -254.3408203125,
+      "loss": -0.9706,
+      "step": 45
+    },
+    {
+      "epoch": 0.10686615014694095,
+      "grad_norm": 19.42383634052037,
+      "learning_rate": 4.4680851063829783e-07,
+      "logits": -2.80342960357666,
+      "logps": -266.91448974609375,
+      "loss": -0.9712,
+      "step": 50
+    },
+    {
+      "epoch": 0.11755276516163506,
+      "grad_norm": 19.073870329982725,
+      "learning_rate": 5e-07,
+      "logits": -3.0574581623077393,
+      "logps": -278.97833251953125,
+      "loss": -0.9752,
+      "step": 55
+    },
+    {
+      "epoch": 0.12823938017632916,
+      "grad_norm": 22.140537506897275,
+      "learning_rate": 4.998251761970996e-07,
+      "logits": -2.982924699783325,
+      "logps": -246.08999633789062,
+      "loss": -0.9711,
+      "step": 60
+    },
+    {
+      "epoch": 0.13892599519102325,
+      "grad_norm": 22.027187117031247,
+      "learning_rate": 4.993009492952949e-07,
+      "logits": -3.066633939743042,
+      "logps": -287.9792175292969,
+      "loss": -0.9739,
+      "step": 65
+    },
+    {
+      "epoch": 0.14961261020571734,
+      "grad_norm": 28.360950734285428,
+      "learning_rate": 4.984280524733107e-07,
+      "logits": -2.9325830936431885,
+      "logps": -254.9385528564453,
+      "loss": -0.969,
+      "step": 70
+    },
+    {
+      "epoch": 0.16029922522041143,
+      "grad_norm": 26.470079510381215,
+      "learning_rate": 4.972077065562821e-07,
+      "logits": -2.8176350593566895,
+      "logps": -247.518798828125,
+      "loss": -0.9746,
+      "step": 75
+    },
+    {
+      "epoch": 0.17098584023510552,
+      "grad_norm": 19.869439451969985,
+      "learning_rate": 4.956416183083221e-07,
+      "logits": -3.0621449947357178,
+      "logps": -289.036376953125,
+      "loss": -0.974,
+      "step": 80
+    },
+    {
+      "epoch": 0.18167245524979964,
+      "grad_norm": 18.092489458888704,
+      "learning_rate": 4.937319780454559e-07,
+      "logits": -2.8688838481903076,
+      "logps": -279.94183349609375,
+      "loss": -0.9776,
+      "step": 85
+    },
+    {
+      "epoch": 0.19235907026449373,
+      "grad_norm": 23.563928671841666,
+      "learning_rate": 4.91481456572267e-07,
+      "logits": -3.0502922534942627,
+      "logps": -219.67733764648438,
+      "loss": -0.9768,
+      "step": 90
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 18.6682864992676,
+      "learning_rate": 4.888932014465352e-07,
+      "logits": -2.9103236198425293,
+      "logps": -270.4436340332031,
+      "loss": -0.9753,
+      "step": 95
+    },
+    {
+      "epoch": 0.2137323002938819,
+      "grad_norm": 18.181568458747662,
+      "learning_rate": 4.859708325770919e-07,
+      "logits": -2.9558568000793457,
+      "logps": -222.9886932373047,
+      "loss": -0.9758,
+      "step": 100
+    },
+    {
+      "epoch": 0.224418915308576,
+      "grad_norm": 22.1137260269499,
+      "learning_rate": 4.82718437161051e-07,
+      "logits": -3.025911808013916,
+      "logps": -265.393310546875,
+      "loss": -0.9784,
+      "step": 105
+    },
+    {
+      "epoch": 0.2351055303232701,
+      "grad_norm": 18.34089290810698,
+      "learning_rate": 4.79140563967494e-07,
+      "logits": -3.0452187061309814,
+      "logps": -291.10003662109375,
+      "loss": -0.977,
+      "step": 110
+    },
+    {
+      "epoch": 0.2457921453379642,
+      "grad_norm": 24.000868485282172,
+      "learning_rate": 4.752422169756047e-07,
+      "logits": -2.9980249404907227,
+      "logps": -270.8134765625,
+      "loss": -0.9769,
+      "step": 115
+    },
+    {
+      "epoch": 0.2564787603526583,
+      "grad_norm": 22.432824006478324,
+      "learning_rate": 4.710288483761524e-07,
+      "logits": -3.0276284217834473,
+      "logps": -242.854248046875,
+      "loss": -0.9781,
+      "step": 120
+    },
+    {
+      "epoch": 0.2671653753673524,
+      "grad_norm": 19.623943572874033,
+      "learning_rate": 4.6650635094610966e-07,
+      "logits": -2.9869930744171143,
+      "logps": -264.6936340332031,
+      "loss": -0.9784,
+      "step": 125
+    },
+    {
+      "epoch": 0.2778519903820465,
+      "grad_norm": 16.514800564439714,
+      "learning_rate": 4.6168104980707103e-07,
+      "logits": -3.074154853820801,
+      "logps": -254.39559936523438,
+      "loss": -0.9789,
+      "step": 130
+    },
+    {
+      "epoch": 0.2885386053967406,
+      "grad_norm": 17.940806695880376,
+      "learning_rate": 4.565596935789987e-07,
+      "logits": -3.064635753631592,
+      "logps": -253.6359405517578,
+      "loss": -0.9772,
+      "step": 135
+    },
+    {
+      "epoch": 0.2992252204114347,
+      "grad_norm": 15.99587855831518,
+      "learning_rate": 4.511494449416671e-07,
+      "logits": -3.021132707595825,
+      "logps": -291.09625244140625,
+      "loss": -0.9776,
+      "step": 140
+    },
+    {
+      "epoch": 0.30991183542612877,
+      "grad_norm": 15.5792510590759,
+      "learning_rate": 4.4545787061700746e-07,
+      "logits": -2.853203296661377,
+      "logps": -281.72210693359375,
+      "loss": -0.9771,
+      "step": 145
+    },
+    {
+      "epoch": 0.32059845044082286,
+      "grad_norm": 17.480990084091566,
+      "learning_rate": 4.394929307863632e-07,
+      "logits": -2.993375539779663,
+      "logps": -265.2592468261719,
+      "loss": -0.9753,
+      "step": 150
+    },
+    {
+      "epoch": 0.33128506545551695,
+      "grad_norm": 17.70526730878467,
+      "learning_rate": 4.332629679574565e-07,
+      "logits": -3.0605502128601074,
+      "logps": -305.0889587402344,
+      "loss": -0.9766,
+      "step": 155
+    },
+    {
+      "epoch": 0.34197168047021104,
+      "grad_norm": 18.40262893823541,
+      "learning_rate": 4.2677669529663686e-07,
+      "logits": -2.9697351455688477,
+      "logps": -306.7701721191406,
+      "loss": -0.9792,
+      "step": 160
+    },
+    {
+      "epoch": 0.3526582954849052,
+      "grad_norm": 20.54973812877713,
+      "learning_rate": 4.200431844427298e-07,
+      "logits": -3.0495619773864746,
+      "logps": -295.7186279296875,
+      "loss": -0.9785,
+      "step": 165
+    },
+    {
+      "epoch": 0.36334491049959927,
+      "grad_norm": 23.008419291973887,
+      "learning_rate": 4.130718528195303e-07,
+      "logits": -2.997997283935547,
+      "logps": -275.9290466308594,
+      "loss": -0.9772,
+      "step": 170
+    },
+    {
+      "epoch": 0.37403152551429336,
+      "grad_norm": 22.007125412303857,
+      "learning_rate": 4.058724504646834e-07,
+      "logits": -2.998748779296875,
+      "logps": -276.2112731933594,
+      "loss": -0.9773,
+      "step": 175
+    },
+    {
+      "epoch": 0.38471814052898745,
+      "grad_norm": 14.558828760504346,
+      "learning_rate": 3.9845504639337535e-07,
+      "logits": -3.035895586013794,
+      "logps": -280.32708740234375,
+      "loss": -0.9778,
+      "step": 180
+    },
+    {
+      "epoch": 0.39540475554368154,
+      "grad_norm": 15.094528036756223,
+      "learning_rate": 3.908300145159055e-07,
+      "logits": -2.99044132232666,
+      "logps": -231.31869506835938,
+      "loss": -0.9782,
+      "step": 185
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 19.931751129133623,
+      "learning_rate": 3.8300801912883414e-07,
+      "logits": -3.1248080730438232,
+      "logps": -272.81658935546875,
+      "loss": -0.9794,
+      "step": 190
+    },
+    {
+      "epoch": 0.4167779855730697,
+      "grad_norm": 19.163508181353045,
+      "learning_rate": 3.75e-07,
+      "logits": -3.047405242919922,
+      "logps": -332.17578125,
+      "loss": -0.979,
+      "step": 195
+    },
+    {
+      "epoch": 0.4274646005877638,
+      "grad_norm": 16.407530767721205,
+      "learning_rate": 3.668171570682655e-07,
+      "logits": -3.0323641300201416,
+      "logps": -251.59506225585938,
+      "loss": -0.9788,
+      "step": 200
+    },
+    {
+      "epoch": 0.4274646005877638,
+      "eval_logits": -3.0493266582489014,
+      "eval_logps": -289.3082275390625,
+      "eval_loss": -0.9775694608688354,
+      "eval_runtime": 586.0302,
+      "eval_samples_per_second": 3.358,
+      "eval_steps_per_second": 0.21,
+      "step": 200
+    },
+    {
+      "epoch": 0.4381512156024579,
+      "grad_norm": 18.72596941199976,
+      "learning_rate": 3.584709347793895e-07,
+      "logits": -2.9899675846099854,
+      "logps": -264.5972595214844,
+      "loss": -0.9774,
+      "step": 205
+    },
+    {
+      "epoch": 0.448837830617152,
+      "grad_norm": 14.684631204607477,
+      "learning_rate": 3.499730060799352e-07,
+      "logits": -2.9389395713806152,
+      "logps": -270.917236328125,
+      "loss": -0.977,
+      "step": 210
+    },
+    {
+      "epoch": 0.45952444563184613,
+      "grad_norm": 19.60342980482045,
+      "learning_rate": 3.413352560915988e-07,
+      "logits": -2.9131505489349365,
+      "logps": -250.50747680664062,
+      "loss": -0.9779,
+      "step": 215
+    },
+    {
+      "epoch": 0.4702110606465402,
+      "grad_norm": 12.44502702657658,
+      "learning_rate": 3.325697654887918e-07,
+      "logits": -2.8331167697906494,
+      "logps": -209.47265625,
+      "loss": -0.9759,
+      "step": 220
+    },
+    {
+      "epoch": 0.4808976756612343,
+      "grad_norm": 19.223731552060446,
+      "learning_rate": 3.2368879360272606e-07,
+      "logits": -3.003699779510498,
+      "logps": -293.6314392089844,
+      "loss": -0.9776,
+      "step": 225
+    },
+    {
+      "epoch": 0.4915842906759284,
+      "grad_norm": 18.20205804125661,
+      "learning_rate": 3.147047612756302e-07,
+      "logits": -3.0232555866241455,
+      "logps": -305.18316650390625,
+      "loss": -0.9783,
+      "step": 230
+    },
+    {
+      "epoch": 0.5022709056906225,
+      "grad_norm": 16.46859278231364,
+      "learning_rate": 3.056302334890786e-07,
+      "logits": -2.9345574378967285,
+      "logps": -237.68637084960938,
+      "loss": -0.9797,
+      "step": 235
+    },
+    {
+      "epoch": 0.5129575207053166,
+      "grad_norm": 16.465984487681027,
+      "learning_rate": 2.964779017907287e-07,
+      "logits": -2.9307010173797607,
+      "logps": -286.076171875,
+      "loss": -0.9805,
+      "step": 240
+    },
+    {
+      "epoch": 0.5236441357200107,
+      "grad_norm": 17.54623610211809,
+      "learning_rate": 2.872605665440436e-07,
+      "logits": -2.974175453186035,
+      "logps": -262.3833312988281,
+      "loss": -0.9787,
+      "step": 245
+    },
+    {
+      "epoch": 0.5343307507347048,
+      "grad_norm": 18.88275216616494,
+      "learning_rate": 2.7799111902582693e-07,
+      "logits": -3.046766996383667,
+      "logps": -251.1654052734375,
+      "loss": -0.9818,
+      "step": 250
+    },
+    {
+      "epoch": 0.5450173657493989,
+      "grad_norm": 16.60487185722242,
+      "learning_rate": 2.6868252339660607e-07,
+      "logits": -2.889235496520996,
+      "logps": -254.0398712158203,
+      "loss": -0.9779,
+      "step": 255
+    },
+    {
+      "epoch": 0.555703980764093,
+      "grad_norm": 19.312080394342164,
+      "learning_rate": 2.593477985690815e-07,
+      "logits": -2.904877185821533,
+      "logps": -260.0421142578125,
+      "loss": -0.9792,
+      "step": 260
+    },
+    {
+      "epoch": 0.566390595778787,
+      "grad_norm": 17.837317168454984,
+      "learning_rate": 2.5e-07,
+      "logits": -3.0580921173095703,
+      "logps": -253.33425903320312,
+      "loss": -0.9783,
+      "step": 265
+    },
+    {
+      "epoch": 0.5770772107934812,
+      "grad_norm": 19.59229912598117,
+      "learning_rate": 2.406522014309186e-07,
+      "logits": -2.8213086128234863,
+      "logps": -248.05899047851562,
+      "loss": -0.9789,
+      "step": 270
+    },
+    {
+      "epoch": 0.5877638258081752,
+      "grad_norm": 19.31749257546076,
+      "learning_rate": 2.3131747660339394e-07,
+      "logits": -3.022545576095581,
+      "logps": -261.65911865234375,
+      "loss": -0.9795,
+      "step": 275
+    },
+    {
+      "epoch": 0.5984504408228694,
+      "grad_norm": 18.893405028741554,
+      "learning_rate": 2.2200888097417302e-07,
+      "logits": -2.8628716468811035,
+      "logps": -276.71771240234375,
+      "loss": -0.9787,
+      "step": 280
+    },
+    {
+      "epoch": 0.6091370558375635,
+      "grad_norm": 12.031725724871942,
+      "learning_rate": 2.1273943345595635e-07,
+      "logits": -2.8501031398773193,
+      "logps": -225.07083129882812,
+      "loss": -0.9802,
+      "step": 285
+    },
+    {
+      "epoch": 0.6198236708522575,
+      "grad_norm": 17.440618788817403,
+      "learning_rate": 2.0352209820927135e-07,
+      "logits": -2.9809391498565674,
+      "logps": -279.31085205078125,
+      "loss": -0.98,
+      "step": 290
+    },
+    {
+      "epoch": 0.6305102858669517,
+      "grad_norm": 17.533312297864594,
+      "learning_rate": 1.9436976651092142e-07,
+      "logits": -2.8259799480438232,
+      "logps": -233.43637084960938,
+      "loss": -0.9791,
+      "step": 295
+    },
+    {
+      "epoch": 0.6411969008816457,
+      "grad_norm": 19.09114013567347,
+      "learning_rate": 1.8529523872436977e-07,
+      "logits": -2.877838134765625,
+      "logps": -250.38919067382812,
+      "loss": -0.979,
+      "step": 300
+    },
+    {
+      "epoch": 0.6518835158963399,
+      "grad_norm": 14.469325828491328,
+      "learning_rate": 1.763112063972739e-07,
+      "logits": -2.9694724082946777,
+      "logps": -265.880615234375,
+      "loss": -0.9795,
+      "step": 305
+    },
+    {
+      "epoch": 0.6625701309110339,
+      "grad_norm": 13.892022212321942,
+      "learning_rate": 1.674302345112083e-07,
+      "logits": -2.8365535736083984,
+      "logps": -249.2300567626953,
+      "loss": -0.9815,
+      "step": 310
+    },
+    {
+      "epoch": 0.673256745925728,
+      "grad_norm": 16.882467097549785,
+      "learning_rate": 1.5866474390840124e-07,
+      "logits": -3.010043144226074,
+      "logps": -297.1403503417969,
+      "loss": -0.9803,
+      "step": 315
+    },
+    {
+      "epoch": 0.6839433609404221,
+      "grad_norm": 16.561775281344463,
+      "learning_rate": 1.500269939200648e-07,
+      "logits": -2.910022735595703,
+      "logps": -245.9589080810547,
+      "loss": -0.981,
+      "step": 320
+    },
+    {
+      "epoch": 0.6946299759551162,
+      "grad_norm": 11.956009192905249,
+      "learning_rate": 1.4152906522061047e-07,
+      "logits": -3.090505599975586,
+      "logps": -297.404052734375,
+      "loss": -0.9801,
+      "step": 325
+    },
+    {
+      "epoch": 0.7053165909698104,
+      "grad_norm": 20.558342213046632,
+      "learning_rate": 1.3318284293173449e-07,
+      "logits": -3.017181396484375,
+      "logps": -282.6482238769531,
+      "loss": -0.9807,
+      "step": 330
+    },
+    {
+      "epoch": 0.7160032059845044,
+      "grad_norm": 13.386951582952191,
+      "learning_rate": 1.2500000000000005e-07,
+      "logits": -2.884382963180542,
+      "logps": -307.8055419921875,
+      "loss": -0.982,
+      "step": 335
+    },
+    {
+      "epoch": 0.7266898209991985,
+      "grad_norm": 20.886776560670956,
+      "learning_rate": 1.1699198087116588e-07,
+      "logits": -2.919635057449341,
+      "logps": -249.56100463867188,
+      "loss": -0.9798,
+      "step": 340
+    },
+    {
+      "epoch": 0.7373764360138926,
+      "grad_norm": 18.641185325431465,
+      "learning_rate": 1.0916998548409447e-07,
+      "logits": -2.8742291927337646,
+      "logps": -281.08062744140625,
+      "loss": -0.9797,
+      "step": 345
+    },
+    {
+      "epoch": 0.7480630510285867,
+      "grad_norm": 12.516321612741994,
+      "learning_rate": 1.0154495360662463e-07,
+      "logits": -2.859714984893799,
+      "logps": -246.27450561523438,
+      "loss": -0.9812,
+      "step": 350
+    },
+    {
+      "epoch": 0.7587496660432808,
+      "grad_norm": 15.783450182742786,
+      "learning_rate": 9.412754953531663e-08,
+      "logits": -2.9711270332336426,
+      "logps": -252.8061981201172,
+      "loss": -0.9806,
+      "step": 355
+    },
+    {
+      "epoch": 0.7694362810579749,
+      "grad_norm": 16.203610890848484,
+      "learning_rate": 8.692814718046978e-08,
+      "logits": -2.942884683609009,
+      "logps": -284.9074401855469,
+      "loss": -0.9813,
+      "step": 360
+    },
+    {
+      "epoch": 0.7801228960726689,
+      "grad_norm": 15.344868690260943,
+      "learning_rate": 7.99568155572701e-08,
+      "logits": -2.9541680812835693,
+      "logps": -254.73123168945312,
+      "loss": -0.9793,
+      "step": 365
+    },
+    {
+      "epoch": 0.7908095110873631,
+      "grad_norm": 15.263546884716034,
+      "learning_rate": 7.322330470336313e-08,
+      "logits": -2.816589832305908,
+      "logps": -258.56964111328125,
+      "loss": -0.9813,
+      "step": 370
+    },
+    {
+      "epoch": 0.8014961261020572,
+      "grad_norm": 15.150826166868379,
+      "learning_rate": 6.673703204254347e-08,
+      "logits": -2.874589681625366,
+      "logps": -264.58929443359375,
+      "loss": -0.9818,
+      "step": 375
+    },
+    {
+      "epoch": 0.8121827411167513,
+      "grad_norm": 17.746820632954226,
+      "learning_rate": 6.050706921363672e-08,
+      "logits": -2.811462879180908,
+      "logps": -274.1175842285156,
+      "loss": -0.9821,
+      "step": 380
+    },
+    {
+      "epoch": 0.8228693561314454,
+      "grad_norm": 17.866909167465558,
+      "learning_rate": 5.454212938299255e-08,
+      "logits": -2.751802444458008,
+      "logps": -265.1951904296875,
+      "loss": -0.981,
+      "step": 385
+    },
+    {
+      "epoch": 0.8335559711461394,
+      "grad_norm": 19.146717420675806,
+      "learning_rate": 4.885055505833291e-08,
+      "logits": -2.872286319732666,
+      "logps": -271.44451904296875,
+      "loss": -0.9816,
+      "step": 390
+    },
+    {
+      "epoch": 0.8442425861608336,
+      "grad_norm": 16.977738077995557,
+      "learning_rate": 4.3440306421001324e-08,
+      "logits": -2.9000906944274902,
+      "logps": -246.639892578125,
+      "loss": -0.9818,
+      "step": 395
+    },
+    {
+      "epoch": 0.8549292011755276,
+      "grad_norm": 15.148125130733664,
+      "learning_rate": 3.831895019292897e-08,
+      "logits": -2.962857723236084,
+      "logps": -276.59356689453125,
+      "loss": -0.9812,
+      "step": 400
+    },
+    {
+      "epoch": 0.8549292011755276,
+      "eval_logits": -2.9494612216949463,
+      "eval_logps": -291.1517028808594,
+      "eval_loss": -0.9810261130332947,
+      "eval_runtime": 560.2713,
+      "eval_samples_per_second": 3.513,
+      "eval_steps_per_second": 0.22,
+      "step": 400
+    },
+    {
+      "epoch": 0.8656158161902218,
+      "grad_norm": 17.51200256618434,
+      "learning_rate": 3.349364905389032e-08,
+      "logits": -2.8892321586608887,
+      "logps": -291.7529296875,
+      "loss": -0.9807,
+      "step": 405
+    },
+    {
+      "epoch": 0.8763024312049158,
+      "grad_norm": 22.832692473414674,
+      "learning_rate": 2.8971151623847584e-08,
+      "logits": -2.803345203399658,
+      "logps": -268.4388122558594,
+      "loss": -0.9811,
+      "step": 410
+    },
+    {
+      "epoch": 0.88698904621961,
+      "grad_norm": 17.595837977158578,
+      "learning_rate": 2.475778302439524e-08,
+      "logits": -2.8722121715545654,
+      "logps": -251.7541961669922,
+      "loss": -0.9823,
+      "step": 415
+    },
+    {
+      "epoch": 0.897675661234304,
+      "grad_norm": 18.312171813693368,
+      "learning_rate": 2.085943603250595e-08,
+      "logits": -2.9985263347625732,
+      "logps": -270.0942077636719,
+      "loss": -0.9802,
+      "step": 420
+    },
+    {
+      "epoch": 0.9083622762489981,
+      "grad_norm": 16.517443174199403,
+      "learning_rate": 1.7281562838948966e-08,
+      "logits": -2.8859758377075195,
+      "logps": -265.142578125,
+      "loss": -0.9812,
+      "step": 425
+    },
+    {
+      "epoch": 0.9190488912636923,
+      "grad_norm": 19.65350536281161,
+      "learning_rate": 1.4029167422908105e-08,
+      "logits": -2.95444393157959,
+      "logps": -290.2696228027344,
+      "loss": -0.9818,
+      "step": 430
+    },
+    {
+      "epoch": 0.9297355062783863,
+      "grad_norm": 15.855089650199325,
+      "learning_rate": 1.1106798553464802e-08,
+      "logits": -2.9999821186065674,
+      "logps": -269.6681213378906,
+      "loss": -0.9815,
+      "step": 435
+    },
+    {
+      "epoch": 0.9404221212930804,
+      "grad_norm": 17.34381390762727,
+      "learning_rate": 8.518543427732949e-09,
+      "logits": -2.989065647125244,
+      "logps": -246.51412963867188,
+      "loss": -0.9808,
+      "step": 440
+    },
+    {
+      "epoch": 0.9511087363077745,
+      "grad_norm": 16.16955244150207,
+      "learning_rate": 6.268021954544095e-09,
+      "logits": -2.859179973602295,
+      "logps": -305.86053466796875,
+      "loss": -0.9795,
+      "step": 445
+    },
+    {
+      "epoch": 0.9617953513224686,
+      "grad_norm": 14.813287522652269,
+      "learning_rate": 4.358381691677931e-09,
+      "logits": -2.835251808166504,
+      "logps": -273.0709533691406,
+      "loss": -0.9813,
+      "step": 450
+    },
+    {
+      "epoch": 0.9724819663371627,
+      "grad_norm": 18.12603626613458,
+      "learning_rate": 2.7922934437178692e-09,
+      "logits": -2.8190817832946777,
+      "logps": -264.83544921875,
+      "loss": -0.981,
+      "step": 455
+    },
+    {
+      "epoch": 0.9831685813518568,
+      "grad_norm": 17.624270425975272,
+      "learning_rate": 1.5719475266893489e-09,
+      "logits": -2.793806552886963,
+      "logps": -224.26779174804688,
+      "loss": -0.9821,
+      "step": 460
+    },
+    {
+      "epoch": 0.9938551963665508,
+      "grad_norm": 17.165545325823846,
+      "learning_rate": 6.990507047049676e-10,
+      "logits": -2.9348580837249756,
+      "logps": -265.0174255371094,
+      "loss": -0.9799,
+      "step": 465
+    },
+    {
+      "epoch": 0.9981298423724285,
+      "step": 467,
+      "total_flos": 0.0,
+      "train_loss": -0.9702747563733789,
+      "train_runtime": 45631.769,
+      "train_samples_per_second": 1.312,
+      "train_steps_per_second": 0.01
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 467,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}