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-hinge-listsize_8-beta_0.05-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/7sup87og)
+# mistral-7b-base-hinge-listsize_8-beta_0.05-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: 0.4086
+- Logps: -310.0013
+- Logits: -2.2096
+
+## 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  |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
+| 0.431         | 0.4275 | 200  | 0.4315          | -301.7860 | -2.3264 |
+| 0.4118        | 0.8549 | 400  | 0.4086          | -310.0013 | -2.2096 |
+
+
+### 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": 0.4667486662017201,
+    "train_runtime": 41187.6602,
+    "train_samples": 59880,
+    "train_samples_per_second": 1.454,
+    "train_steps_per_second": 0.011
+}

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 sha256:44d74e4d578a33bf601bd8bd6195c914ad69a8a88d6ca521d7668c65c206294c
+size 4943162240

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60235f1dba7c9134747c68ea6231055a6542252321b265eb0594fd97f31c8240
+size 4999819232

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f51780a8ba362bd89003efa4eeadca13dd4932a6a774a7a41d947a035036c3d
+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": 0.4667486662017201,
+    "train_runtime": 41187.6602,
+    "train_samples": 59880,
+    "train_samples_per_second": 1.454,
+    "train_steps_per_second": 0.011
+}

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": 1.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.010686615014694095,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "logits": -2.8715224266052246,
+      "logps": -234.59034729003906,
+      "loss": 1.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.02137323002938819,
+      "grad_norm": 48.2801432920563,
+      "learning_rate": 5.3191489361702123e-08,
+      "logits": -2.8460676670074463,
+      "logps": -248.16787719726562,
+      "loss": 0.9998,
+      "step": 10
+    },
+    {
+      "epoch": 0.03205984504408229,
+      "grad_norm": 50.29241141091707,
+      "learning_rate": 9.574468085106382e-08,
+      "logits": -2.7791006565093994,
+      "logps": -229.27816772460938,
+      "loss": 0.9874,
+      "step": 15
+    },
+    {
+      "epoch": 0.04274646005877638,
+      "grad_norm": 46.57864781408822,
+      "learning_rate": 1.3829787234042553e-07,
+      "logits": -2.7698864936828613,
+      "logps": -204.43753051757812,
+      "loss": 0.9444,
+      "step": 20
+    },
+    {
+      "epoch": 0.053433075073470476,
+      "grad_norm": 36.984896584442474,
+      "learning_rate": 1.9148936170212765e-07,
+      "logits": -2.9412951469421387,
+      "logps": -291.7972717285156,
+      "loss": 0.795,
+      "step": 25
+    },
+    {
+      "epoch": 0.06411969008816458,
+      "grad_norm": 25.64585807242414,
+      "learning_rate": 2.4468085106382976e-07,
+      "logits": -2.913182258605957,
+      "logps": -280.78009033203125,
+      "loss": 0.6761,
+      "step": 30
+    },
+    {
+      "epoch": 0.07480630510285867,
+      "grad_norm": 22.189719283428744,
+      "learning_rate": 2.978723404255319e-07,
+      "logits": -2.8854992389678955,
+      "logps": -233.5765380859375,
+      "loss": 0.6236,
+      "step": 35
+    },
+    {
+      "epoch": 0.08549292011755276,
+      "grad_norm": 22.990475128782094,
+      "learning_rate": 3.5106382978723405e-07,
+      "logits": -2.8781936168670654,
+      "logps": -233.80117797851562,
+      "loss": 0.5835,
+      "step": 40
+    },
+    {
+      "epoch": 0.09617953513224686,
+      "grad_norm": 21.917107832657997,
+      "learning_rate": 4.0425531914893614e-07,
+      "logits": -2.7908034324645996,
+      "logps": -257.6076965332031,
+      "loss": 0.5822,
+      "step": 45
+    },
+    {
+      "epoch": 0.10686615014694095,
+      "grad_norm": 22.029695238746953,
+      "learning_rate": 4.574468085106383e-07,
+      "logits": -2.614025592803955,
+      "logps": -270.81671142578125,
+      "loss": 0.5573,
+      "step": 50
+    },
+    {
+      "epoch": 0.11755276516163506,
+      "grad_norm": 21.89479772573872,
+      "learning_rate": 4.999930062653174e-07,
+      "logits": -2.7972469329833984,
+      "logps": -286.5457458496094,
+      "loss": 0.5318,
+      "step": 55
+    },
+    {
+      "epoch": 0.12823938017632916,
+      "grad_norm": 21.44902343753467,
+      "learning_rate": 4.997482666353286e-07,
+      "logits": -2.690673828125,
+      "logps": -253.75869750976562,
+      "loss": 0.5219,
+      "step": 60
+    },
+    {
+      "epoch": 0.13892599519102325,
+      "grad_norm": 21.630693894892058,
+      "learning_rate": 4.991542314714122e-07,
+      "logits": -2.73010516166687,
+      "logps": -293.25762939453125,
+      "loss": 0.5026,
+      "step": 65
+    },
+    {
+      "epoch": 0.14961261020571734,
+      "grad_norm": 25.306412397060555,
+      "learning_rate": 4.982117315854593e-07,
+      "logits": -2.5588488578796387,
+      "logps": -263.66851806640625,
+      "loss": 0.5258,
+      "step": 70
+    },
+    {
+      "epoch": 0.16029922522041143,
+      "grad_norm": 22.279892008137498,
+      "learning_rate": 4.969220851487844e-07,
+      "logits": -2.401634693145752,
+      "logps": -262.5799255371094,
+      "loss": 0.4803,
+      "step": 75
+    },
+    {
+      "epoch": 0.17098584023510552,
+      "grad_norm": 23.85473503890347,
+      "learning_rate": 4.952870958485431e-07,
+      "logits": -2.7048754692077637,
+      "logps": -305.823486328125,
+      "loss": 0.4825,
+      "step": 80
+    },
+    {
+      "epoch": 0.18167245524979964,
+      "grad_norm": 26.91529025786325,
+      "learning_rate": 4.933090503651128e-07,
+      "logits": -2.3958709239959717,
+      "logps": -296.0675964355469,
+      "loss": 0.4779,
+      "step": 85
+    },
+    {
+      "epoch": 0.19235907026449373,
+      "grad_norm": 23.370663292540115,
+      "learning_rate": 4.909907151739633e-07,
+      "logits": -2.552422046661377,
+      "logps": -235.0645751953125,
+      "loss": 0.479,
+      "step": 90
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 24.61367431074327,
+      "learning_rate": 4.883353326764906e-07,
+      "logits": -2.3946549892425537,
+      "logps": -295.76959228515625,
+      "loss": 0.4708,
+      "step": 95
+    },
+    {
+      "epoch": 0.2137323002938819,
+      "grad_norm": 25.53290336307927,
+      "learning_rate": 4.853466166652258e-07,
+      "logits": -2.442629098892212,
+      "logps": -241.5957794189453,
+      "loss": 0.4609,
+      "step": 100
+    },
+    {
+      "epoch": 0.224418915308576,
+      "grad_norm": 22.113276785856915,
+      "learning_rate": 4.820287471297597e-07,
+      "logits": -2.474640369415283,
+      "logps": -290.6409912109375,
+      "loss": 0.4479,
+      "step": 105
+    },
+    {
+      "epoch": 0.2351055303232701,
+      "grad_norm": 21.079178522203513,
+      "learning_rate": 4.783863644106502e-07,
+      "logits": -2.515345335006714,
+      "logps": -306.5741882324219,
+      "loss": 0.4529,
+      "step": 110
+    },
+    {
+      "epoch": 0.2457921453379642,
+      "grad_norm": 21.06551183306965,
+      "learning_rate": 4.752422169756047e-07,
+      "logits": -2.4756886959075928,
+      "logps": -281.9891662597656,
+      "loss": 0.4696,
+      "step": 115
+    },
+    {
+      "epoch": 0.2564787603526583,
+      "grad_norm": 22.63241646221903,
+      "learning_rate": 4.710288483761524e-07,
+      "logits": -2.4553544521331787,
+      "logps": -262.58184814453125,
+      "loss": 0.4712,
+      "step": 120
+    },
+    {
+      "epoch": 0.2671653753673524,
+      "grad_norm": 24.782221235525792,
+      "learning_rate": 4.6650635094610966e-07,
+      "logits": -2.3455586433410645,
+      "logps": -286.12481689453125,
+      "loss": 0.439,
+      "step": 125
+    },
+    {
+      "epoch": 0.2778519903820465,
+      "grad_norm": 22.240996330864814,
+      "learning_rate": 4.6168104980707103e-07,
+      "logits": -2.454857349395752,
+      "logps": -278.26177978515625,
+      "loss": 0.4606,
+      "step": 130
+    },
+    {
+      "epoch": 0.2885386053967406,
+      "grad_norm": 23.029344848112892,
+      "learning_rate": 4.565596935789987e-07,
+      "logits": -2.5119175910949707,
+      "logps": -271.8935546875,
+      "loss": 0.4583,
+      "step": 135
+    },
+    {
+      "epoch": 0.2992252204114347,
+      "grad_norm": 23.114231775090644,
+      "learning_rate": 4.511494449416671e-07,
+      "logits": -2.4763400554656982,
+      "logps": -305.2304992675781,
+      "loss": 0.4444,
+      "step": 140
+    },
+    {
+      "epoch": 0.30991183542612877,
+      "grad_norm": 22.307052406807973,
+      "learning_rate": 4.4545787061700746e-07,
+      "logits": -2.279383659362793,
+      "logps": -314.3868103027344,
+      "loss": 0.4433,
+      "step": 145
+    },
+    {
+      "epoch": 0.32059845044082286,
+      "grad_norm": 22.621940716026984,
+      "learning_rate": 4.394929307863632e-07,
+      "logits": -2.4016177654266357,
+      "logps": -280.4060363769531,
+      "loss": 0.4603,
+      "step": 150
+    },
+    {
+      "epoch": 0.33128506545551695,
+      "grad_norm": 27.05574310923442,
+      "learning_rate": 4.332629679574565e-07,
+      "logits": -2.4656858444213867,
+      "logps": -310.09173583984375,
+      "loss": 0.4505,
+      "step": 155
+    },
+    {
+      "epoch": 0.34197168047021104,
+      "grad_norm": 23.53583613618808,
+      "learning_rate": 4.2677669529663686e-07,
+      "logits": -2.337423801422119,
+      "logps": -317.040771484375,
+      "loss": 0.4395,
+      "step": 160
+    },
+    {
+      "epoch": 0.3526582954849052,
+      "grad_norm": 23.875484303552483,
+      "learning_rate": 4.200431844427298e-07,
+      "logits": -2.5105397701263428,
+      "logps": -305.39630126953125,
+      "loss": 0.4456,
+      "step": 165
+    },
+    {
+      "epoch": 0.36334491049959927,
+      "grad_norm": 22.450514799974165,
+      "learning_rate": 4.130718528195303e-07,
+      "logits": -2.3933465480804443,
+      "logps": -275.6124267578125,
+      "loss": 0.443,
+      "step": 170
+    },
+    {
+      "epoch": 0.37403152551429336,
+      "grad_norm": 23.74049455633747,
+      "learning_rate": 4.058724504646834e-07,
+      "logits": -2.3835606575012207,
+      "logps": -277.36956787109375,
+      "loss": 0.4339,
+      "step": 175
+    },
+    {
+      "epoch": 0.38471814052898745,
+      "grad_norm": 23.64677950778481,
+      "learning_rate": 3.9845504639337535e-07,
+      "logits": -2.4487411975860596,
+      "logps": -290.956298828125,
+      "loss": 0.4573,
+      "step": 180
+    },
+    {
+      "epoch": 0.39540475554368154,
+      "grad_norm": 21.598937457276417,
+      "learning_rate": 3.908300145159055e-07,
+      "logits": -2.413297176361084,
+      "logps": -235.90109252929688,
+      "loss": 0.4279,
+      "step": 185
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 23.712081510750036,
+      "learning_rate": 3.8300801912883414e-07,
+      "logits": -2.4640491008758545,
+      "logps": -287.1435546875,
+      "loss": 0.4354,
+      "step": 190
+    },
+    {
+      "epoch": 0.4167779855730697,
+      "grad_norm": 44.372947453047885,
+      "learning_rate": 3.75e-07,
+      "logits": -2.3341147899627686,
+      "logps": -343.4080505371094,
+      "loss": 0.4329,
+      "step": 195
+    },
+    {
+      "epoch": 0.4274646005877638,
+      "grad_norm": 23.012230002196524,
+      "learning_rate": 3.668171570682655e-07,
+      "logits": -2.340860366821289,
+      "logps": -262.5423889160156,
+      "loss": 0.431,
+      "step": 200
+    },
+    {
+      "epoch": 0.4274646005877638,
+      "eval_logits": -2.3263635635375977,
+      "eval_logps": -301.7860412597656,
+      "eval_loss": 0.4314996898174286,
+      "eval_runtime": 507.0323,
+      "eval_samples_per_second": 3.881,
+      "eval_steps_per_second": 0.243,
+      "step": 200
+    },
+    {
+      "epoch": 0.4381512156024579,
+      "grad_norm": 22.412220925103565,
+      "learning_rate": 3.584709347793895e-07,
+      "logits": -2.2411904335021973,
+      "logps": -277.8357849121094,
+      "loss": 0.4425,
+      "step": 205
+    },
+    {
+      "epoch": 0.448837830617152,
+      "grad_norm": 23.021158257266347,
+      "learning_rate": 3.499730060799352e-07,
+      "logits": -2.1322011947631836,
+      "logps": -289.6743469238281,
+      "loss": 0.4292,
+      "step": 210
+    },
+    {
+      "epoch": 0.45952444563184613,
+      "grad_norm": 23.724850433619796,
+      "learning_rate": 3.413352560915988e-07,
+      "logits": -2.0033411979675293,
+      "logps": -272.5525207519531,
+      "loss": 0.4121,
+      "step": 215
+    },
+    {
+      "epoch": 0.4702110606465402,
+      "grad_norm": 21.651299269242514,
+      "learning_rate": 3.325697654887918e-07,
+      "logits": -2.051339626312256,
+      "logps": -235.84262084960938,
+      "loss": 0.4222,
+      "step": 220
+    },
+    {
+      "epoch": 0.4808976756612343,
+      "grad_norm": 25.440752125826293,
+      "learning_rate": 3.2368879360272606e-07,
+      "logits": -2.34849214553833,
+      "logps": -312.7589111328125,
+      "loss": 0.424,
+      "step": 225
+    },
+    {
+      "epoch": 0.4915842906759284,
+      "grad_norm": 21.05394354899474,
+      "learning_rate": 3.147047612756302e-07,
+      "logits": -2.335400104522705,
+      "logps": -325.1053161621094,
+      "loss": 0.4261,
+      "step": 230
+    },
+    {
+      "epoch": 0.5022709056906225,
+      "grad_norm": 22.293568633261653,
+      "learning_rate": 3.056302334890786e-07,
+      "logits": -2.2490334510803223,
+      "logps": -266.56219482421875,
+      "loss": 0.4322,
+      "step": 235
+    },
+    {
+      "epoch": 0.5129575207053166,
+      "grad_norm": 22.256364087698653,
+      "learning_rate": 2.964779017907287e-07,
+      "logits": -2.16744065284729,
+      "logps": -309.4420471191406,
+      "loss": 0.4222,
+      "step": 240
+    },
+    {
+      "epoch": 0.5236441357200107,
+      "grad_norm": 25.954148860680444,
+      "learning_rate": 2.872605665440436e-07,
+      "logits": -2.451477527618408,
+      "logps": -282.71319580078125,
+      "loss": 0.4096,
+      "step": 245
+    },
+    {
+      "epoch": 0.5343307507347048,
+      "grad_norm": 21.39918862577877,
+      "learning_rate": 2.7799111902582693e-07,
+      "logits": -2.6052417755126953,
+      "logps": -273.9092102050781,
+      "loss": 0.4155,
+      "step": 250
+    },
+    {
+      "epoch": 0.5450173657493989,
+      "grad_norm": 24.967131244901736,
+      "learning_rate": 2.6868252339660607e-07,
+      "logits": -2.225090503692627,
+      "logps": -280.70782470703125,
+      "loss": 0.416,
+      "step": 255
+    },
+    {
+      "epoch": 0.555703980764093,
+      "grad_norm": 24.077110482464793,
+      "learning_rate": 2.593477985690815e-07,
+      "logits": -2.2254879474639893,
+      "logps": -286.8822937011719,
+      "loss": 0.4099,
+      "step": 260
+    },
+    {
+      "epoch": 0.566390595778787,
+      "grad_norm": 22.910756064363806,
+      "learning_rate": 2.5e-07,
+      "logits": -2.3557419776916504,
+      "logps": -280.0397033691406,
+      "loss": 0.4125,
+      "step": 265
+    },
+    {
+      "epoch": 0.5770772107934812,
+      "grad_norm": 27.974836628803857,
+      "learning_rate": 2.406522014309186e-07,
+      "logits": -2.041544198989868,
+      "logps": -273.45318603515625,
+      "loss": 0.4291,
+      "step": 270
+    },
+    {
+      "epoch": 0.5877638258081752,
+      "grad_norm": 22.765553156216026,
+      "learning_rate": 2.3131747660339394e-07,
+      "logits": -2.3228344917297363,
+      "logps": -282.9244079589844,
+      "loss": 0.4141,
+      "step": 275
+    },
+    {
+      "epoch": 0.5984504408228694,
+      "grad_norm": 22.498986802146685,
+      "learning_rate": 2.2200888097417302e-07,
+      "logits": -1.89029061794281,
+      "logps": -315.2174072265625,
+      "loss": 0.42,
+      "step": 280
+    },
+    {
+      "epoch": 0.6091370558375635,
+      "grad_norm": 23.58891369147268,
+      "learning_rate": 2.1273943345595635e-07,
+      "logits": -1.903066873550415,
+      "logps": -261.4866638183594,
+      "loss": 0.4062,
+      "step": 285
+    },
+    {
+      "epoch": 0.6198236708522575,
+      "grad_norm": 21.26751900271618,
+      "learning_rate": 2.0352209820927135e-07,
+      "logits": -2.048973560333252,
+      "logps": -312.31048583984375,
+      "loss": 0.4142,
+      "step": 290
+    },
+    {
+      "epoch": 0.6305102858669517,
+      "grad_norm": 22.071346201309105,
+      "learning_rate": 1.9436976651092142e-07,
+      "logits": -1.7636706829071045,
+      "logps": -257.8403625488281,
+      "loss": 0.4124,
+      "step": 295
+    },
+    {
+      "epoch": 0.6411969008816457,
+      "grad_norm": 21.12974848393809,
+      "learning_rate": 1.8529523872436977e-07,
+      "logits": -2.014808177947998,
+      "logps": -279.1208190917969,
+      "loss": 0.4112,
+      "step": 300
+    },
+    {
+      "epoch": 0.6518835158963399,
+      "grad_norm": 23.594905022803008,
+      "learning_rate": 1.763112063972739e-07,
+      "logits": -2.050807237625122,
+      "logps": -296.3996887207031,
+      "loss": 0.4112,
+      "step": 305
+    },
+    {
+      "epoch": 0.6625701309110339,
+      "grad_norm": 21.591511525006933,
+      "learning_rate": 1.674302345112083e-07,
+      "logits": -1.986161470413208,
+      "logps": -275.21893310546875,
+      "loss": 0.419,
+      "step": 310
+    },
+    {
+      "epoch": 0.673256745925728,
+      "grad_norm": 20.6885856376684,
+      "learning_rate": 1.5866474390840124e-07,
+      "logits": -2.2522599697113037,
+      "logps": -319.27911376953125,
+      "loss": 0.4106,
+      "step": 315
+    },
+    {
+      "epoch": 0.6839433609404221,
+      "grad_norm": 22.909433086566732,
+      "learning_rate": 1.500269939200648e-07,
+      "logits": -2.207468032836914,
+      "logps": -266.585205078125,
+      "loss": 0.3909,
+      "step": 320
+    },
+    {
+      "epoch": 0.6946299759551162,
+      "grad_norm": 22.282735602270293,
+      "learning_rate": 1.4152906522061047e-07,
+      "logits": -2.35794997215271,
+      "logps": -316.83807373046875,
+      "loss": 0.4048,
+      "step": 325
+    },
+    {
+      "epoch": 0.7053165909698104,
+      "grad_norm": 23.16656248515272,
+      "learning_rate": 1.3318284293173449e-07,
+      "logits": -2.242034912109375,
+      "logps": -307.3307189941406,
+      "loss": 0.4042,
+      "step": 330
+    },
+    {
+      "epoch": 0.7160032059845044,
+      "grad_norm": 21.510083315851972,
+      "learning_rate": 1.2500000000000005e-07,
+      "logits": -1.9815715551376343,
+      "logps": -338.7240905761719,
+      "loss": 0.3934,
+      "step": 335
+    },
+    {
+      "epoch": 0.7266898209991985,
+      "grad_norm": 21.492689286630217,
+      "learning_rate": 1.1699198087116588e-07,
+      "logits": -2.1296348571777344,
+      "logps": -271.06878662109375,
+      "loss": 0.4011,
+      "step": 340
+    },
+    {
+      "epoch": 0.7373764360138926,
+      "grad_norm": 23.01568750995505,
+      "learning_rate": 1.0916998548409447e-07,
+      "logits": -2.244135618209839,
+      "logps": -310.14501953125,
+      "loss": 0.412,
+      "step": 345
+    },
+    {
+      "epoch": 0.7480630510285867,
+      "grad_norm": 22.53687051047034,
+      "learning_rate": 1.0154495360662463e-07,
+      "logits": -2.1778364181518555,
+      "logps": -269.3367614746094,
+      "loss": 0.3901,
+      "step": 350
+    },
+    {
+      "epoch": 0.7587496660432808,
+      "grad_norm": 23.184829487659847,
+      "learning_rate": 9.412754953531663e-08,
+      "logits": -2.286181926727295,
+      "logps": -271.3564453125,
+      "loss": 0.4172,
+      "step": 355
+    },
+    {
+      "epoch": 0.7694362810579749,
+      "grad_norm": 21.040610617000496,
+      "learning_rate": 8.692814718046978e-08,
+      "logits": -2.055994987487793,
+      "logps": -304.63885498046875,
+      "loss": 0.4083,
+      "step": 360
+    },
+    {
+      "epoch": 0.7801228960726689,
+      "grad_norm": 23.09698562414689,
+      "learning_rate": 7.99568155572701e-08,
+      "logits": -2.213494062423706,
+      "logps": -277.4697570800781,
+      "loss": 0.4155,
+      "step": 365
+    },
+    {
+      "epoch": 0.7908095110873631,
+      "grad_norm": 21.236358981933506,
+      "learning_rate": 7.322330470336313e-08,
+      "logits": -2.0819058418273926,
+      "logps": -281.2724914550781,
+      "loss": 0.4037,
+      "step": 370
+    },
+    {
+      "epoch": 0.8014961261020572,
+      "grad_norm": 26.06067361683024,
+      "learning_rate": 6.673703204254347e-08,
+      "logits": -2.030791997909546,
+      "logps": -284.4011535644531,
+      "loss": 0.4121,
+      "step": 375
+    },
+    {
+      "epoch": 0.8121827411167513,
+      "grad_norm": 20.224636468750884,
+      "learning_rate": 6.050706921363672e-08,
+      "logits": -1.9256960153579712,
+      "logps": -294.9930725097656,
+      "loss": 0.4027,
+      "step": 380
+    },
+    {
+      "epoch": 0.8228693561314454,
+      "grad_norm": 24.14425420434055,
+      "learning_rate": 5.454212938299255e-08,
+      "logits": -1.7693021297454834,
+      "logps": -286.45452880859375,
+      "loss": 0.4136,
+      "step": 385
+    },
+    {
+      "epoch": 0.8335559711461394,
+      "grad_norm": 22.762479440937984,
+      "learning_rate": 4.885055505833291e-08,
+      "logits": -1.9304530620574951,
+      "logps": -291.02880859375,
+      "loss": 0.3988,
+      "step": 390
+    },
+    {
+      "epoch": 0.8442425861608336,
+      "grad_norm": 21.312231537009946,
+      "learning_rate": 4.3440306421001324e-08,
+      "logits": -2.025493860244751,
+      "logps": -268.2240905761719,
+      "loss": 0.4083,
+      "step": 395
+    },
+    {
+      "epoch": 0.8549292011755276,
+      "grad_norm": 23.03482969018928,
+      "learning_rate": 3.831895019292897e-08,
+      "logits": -2.1968250274658203,
+      "logps": -294.18292236328125,
+      "loss": 0.4118,
+      "step": 400
+    },
+    {
+      "epoch": 0.8549292011755276,
+      "eval_logits": -2.2095947265625,
+      "eval_logps": -310.0013122558594,
+      "eval_loss": 0.40863949060440063,
+      "eval_runtime": 537.6528,
+      "eval_samples_per_second": 3.66,
+      "eval_steps_per_second": 0.229,
+      "step": 400
+    },
+    {
+      "epoch": 0.8656158161902218,
+      "grad_norm": 21.5208583380133,
+      "learning_rate": 3.349364905389032e-08,
+      "logits": -2.188328981399536,
+      "logps": -306.3011169433594,
+      "loss": 0.4113,
+      "step": 405
+    },
+    {
+      "epoch": 0.8763024312049158,
+      "grad_norm": 20.54362762134308,
+      "learning_rate": 2.8971151623847584e-08,
+      "logits": -1.99441659450531,
+      "logps": -286.16876220703125,
+      "loss": 0.4171,
+      "step": 410
+    },
+    {
+      "epoch": 0.88698904621961,
+      "grad_norm": 22.86656655422917,
+      "learning_rate": 2.475778302439524e-08,
+      "logits": -2.1187539100646973,
+      "logps": -266.64959716796875,
+      "loss": 0.4053,
+      "step": 415
+    },
+    {
+      "epoch": 0.897675661234304,
+      "grad_norm": 22.18589761074244,
+      "learning_rate": 2.085943603250595e-08,
+      "logits": -2.3276543617248535,
+      "logps": -284.54974365234375,
+      "loss": 0.4153,
+      "step": 420
+    },
+    {
+      "epoch": 0.9083622762489981,
+      "grad_norm": 20.63324288656286,
+      "learning_rate": 1.7281562838948966e-08,
+      "logits": -2.1507515907287598,
+      "logps": -281.44158935546875,
+      "loss": 0.4074,
+      "step": 425
+    },
+    {
+      "epoch": 0.9190488912636923,
+      "grad_norm": 20.358726620730323,
+      "learning_rate": 1.4029167422908105e-08,
+      "logits": -2.1837050914764404,
+      "logps": -310.3664245605469,
+      "loss": 0.3928,
+      "step": 430
+    },
+    {
+      "epoch": 0.9297355062783863,
+      "grad_norm": 21.126634047747054,
+      "learning_rate": 1.1106798553464802e-08,
+      "logits": -2.260655164718628,
+      "logps": -281.1075439453125,
+      "loss": 0.413,
+      "step": 435
+    },
+    {
+      "epoch": 0.9404221212930804,
+      "grad_norm": 23.274529002886094,
+      "learning_rate": 8.518543427732949e-09,
+      "logits": -2.16852068901062,
+      "logps": -262.402099609375,
+      "loss": 0.3922,
+      "step": 440
+    },
+    {
+      "epoch": 0.9511087363077745,
+      "grad_norm": 26.435895904221407,
+      "learning_rate": 6.268021954544095e-09,
+      "logits": -2.1322624683380127,
+      "logps": -324.4895324707031,
+      "loss": 0.4172,
+      "step": 445
+    },
+    {
+      "epoch": 0.9617953513224686,
+      "grad_norm": 24.896799022635523,
+      "learning_rate": 4.358381691677931e-09,
+      "logits": -2.1141066551208496,
+      "logps": -289.3265380859375,
+      "loss": 0.4068,
+      "step": 450
+    },
+    {
+      "epoch": 0.9724819663371627,
+      "grad_norm": 21.21043979653372,
+      "learning_rate": 2.7922934437178692e-09,
+      "logits": -1.9867866039276123,
+      "logps": -283.8013000488281,
+      "loss": 0.391,
+      "step": 455
+    },
+    {
+      "epoch": 0.9831685813518568,
+      "grad_norm": 21.01754870372027,
+      "learning_rate": 1.5719475266893489e-09,
+      "logits": -2.012530565261841,
+      "logps": -245.16806030273438,
+      "loss": 0.4041,
+      "step": 460
+    },
+    {
+      "epoch": 0.9938551963665508,
+      "grad_norm": 22.43911437197679,
+      "learning_rate": 6.990507047049676e-10,
+      "logits": -2.1750540733337402,
+      "logps": -284.3227233886719,
+      "loss": 0.4094,
+      "step": 465
+    },
+    {
+      "epoch": 0.9981298423724285,
+      "step": 467,
+      "total_flos": 0.0,
+      "train_loss": 0.4667486662017201,
+      "train_runtime": 41187.6602,
+      "train_samples_per_second": 1.454,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 467,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "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
+}