Model save

README.md

@@ -0,0 +1,97 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-7b-sft-safe-hhrlhf
+  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. -->
+
+# zephyr-7b-sft-safe-hhrlhf
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1996
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.4854        | 0.06  | 25   | 1.4540          |
+| 1.43          | 0.12  | 50   | 1.4291          |
+| 1.4188        | 0.18  | 75   | 1.4451          |
+| 1.4465        | 0.25  | 100  | 1.4565          |
+| 1.4499        | 0.31  | 125  | 1.4525          |
+| 1.4387        | 0.37  | 150  | 1.4409          |
+| 1.4368        | 0.43  | 175  | 1.4226          |
+| 1.4095        | 0.49  | 200  | 1.4227          |
+| 1.4065        | 0.55  | 225  | 1.4044          |
+| 1.3747        | 0.62  | 250  | 1.3881          |
+| 1.3847        | 0.68  | 275  | 1.3720          |
+| 1.3526        | 0.74  | 300  | 1.3581          |
+| 1.3072        | 0.8   | 325  | 1.3410          |
+| 1.3146        | 0.86  | 350  | 1.3239          |
+| 1.2783        | 0.92  | 375  | 1.3106          |
+| 1.2773        | 0.99  | 400  | 1.2896          |
+| 0.7303        | 1.05  | 425  | 1.3327          |
+| 0.6911        | 1.11  | 450  | 1.3081          |
+| 0.7044        | 1.17  | 475  | 1.3012          |
+| 0.6597        | 1.23  | 500  | 1.2845          |
+| 0.6717        | 1.29  | 525  | 1.2701          |
+| 0.6538        | 1.35  | 550  | 1.2666          |
+| 0.6484        | 1.42  | 575  | 1.2481          |
+| 0.633         | 1.48  | 600  | 1.2404          |
+| 0.6252        | 1.54  | 625  | 1.2332          |
+| 0.6423        | 1.6   | 650  | 1.2212          |
+| 0.6182        | 1.66  | 675  | 1.2115          |
+| 0.6218        | 1.72  | 700  | 1.2099          |
+| 0.6293        | 1.79  | 725  | 1.2038          |
+| 0.5978        | 1.85  | 750  | 1.2014          |
+| 0.6176        | 1.91  | 775  | 1.1995          |
+| 0.6475        | 1.97  | 800  | 1.1996          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.0263223388218528,
+    "train_runtime": 5267.6103,
+    "train_samples": 50000,
+    "train_samples_per_second": 4.93,
+    "train_steps_per_second": 0.154
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b54fef1ed3493ab89690b717adcfdb71e49428a23b3ee841c2e9f733418792
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e1f61fe08d80fdda763fcaf7ce7654cd6ec98ebf0a4631fecc0b78651fc040
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0c0960e0182b8804a5cb1b675f3faaf8052a4271a7cf432a84e26c54f56886
+size 4540516344

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"
+  }
+}

runs/Jul01_00-26-14_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1719808103.gilbreth-j001.rcac.purdue.edu.42793.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e01c8f337e3e5ad0fa37714ac81e10bb20f8c61847ad5a73ffafa72be78a71
-size 47253
+oid sha256:be6ff0b6eca9224499c71ec8e6fed6d5d69042fe2f4f7ffb17c7b261e4db710a
+size 48029

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.0263223388218528,
+    "train_runtime": 5267.6103,
+    "train_samples": 50000,
+    "train_samples_per_second": 4.93,
+    "train_steps_per_second": 0.154
+}

trainer_state.json

@@ -0,0 +1,1427 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 25,
+  "global_step": 812,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 33.25565995239216,
+      "learning_rate": 2.439024390243903e-07,
+      "loss": 1.8579,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 20.62131418379264,
+      "learning_rate": 1.2195121951219514e-06,
+      "loss": 1.8594,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 9.116745598504249,
+      "learning_rate": 2.4390243902439027e-06,
+      "loss": 1.6368,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.845477457562938,
+      "learning_rate": 3.6585365853658537e-06,
+      "loss": 1.5273,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.064982240065612,
+      "learning_rate": 4.8780487804878055e-06,
+      "loss": 1.4879,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.842051647757176,
+      "learning_rate": 6.0975609756097564e-06,
+      "loss": 1.4854,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.4539871215820312,
+      "eval_runtime": 37.3786,
+      "eval_samples_per_second": 35.047,
+      "eval_steps_per_second": 1.097,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.5736405142429235,
+      "learning_rate": 7.317073170731707e-06,
+      "loss": 1.4689,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 3.601301646883329,
+      "learning_rate": 8.536585365853658e-06,
+      "loss": 1.4492,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.5795153985197454,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 1.4464,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.547211967993725,
+      "learning_rate": 1.0975609756097562e-05,
+      "loss": 1.4118,
+      "step": 45
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.8241967984903127,
+      "learning_rate": 1.2195121951219513e-05,
+      "loss": 1.43,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4291119575500488,
+      "eval_runtime": 37.1035,
+      "eval_samples_per_second": 35.307,
+      "eval_steps_per_second": 1.105,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.65980179405396,
+      "learning_rate": 1.3414634146341466e-05,
+      "loss": 1.4254,
+      "step": 55
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.155175626685716,
+      "learning_rate": 1.4634146341463415e-05,
+      "loss": 1.4337,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.6031251352197695,
+      "learning_rate": 1.585365853658537e-05,
+      "loss": 1.4482,
+      "step": 65
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.9000471804568297,
+      "learning_rate": 1.7073170731707317e-05,
+      "loss": 1.452,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.6748440024674487,
+      "learning_rate": 1.829268292682927e-05,
+      "loss": 1.4188,
+      "step": 75
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 1.4451020956039429,
+      "eval_runtime": 36.3992,
+      "eval_samples_per_second": 35.99,
+      "eval_steps_per_second": 1.126,
+      "step": 75
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.784684166408002,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 1.422,
+      "step": 80
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.777533605838261,
+      "learning_rate": 1.9999166586547382e-05,
+      "loss": 1.4567,
+      "step": 85
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.551321168481626,
+      "learning_rate": 1.999407400739705e-05,
+      "loss": 1.4674,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.625908306378223,
+      "learning_rate": 1.9984354211555646e-05,
+      "loss": 1.4554,
+      "step": 95
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.243745995028721,
+      "learning_rate": 1.997001169925015e-05,
+      "loss": 1.4465,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.4564708471298218,
+      "eval_runtime": 35.8982,
+      "eval_samples_per_second": 36.492,
+      "eval_steps_per_second": 1.142,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.7056910011856434,
+      "learning_rate": 1.995105311100698e-05,
+      "loss": 1.435,
+      "step": 105
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 4.028708939881987,
+      "learning_rate": 1.9927487224577402e-05,
+      "loss": 1.4554,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.4936872675120205,
+      "learning_rate": 1.9899324950873532e-05,
+      "loss": 1.4371,
+      "step": 115
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.446138884571553,
+      "learning_rate": 1.986657932891657e-05,
+      "loss": 1.4213,
+      "step": 120
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 3.5762471286009836,
+      "learning_rate": 1.9829265519799824e-05,
+      "loss": 1.4499,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 1.4525413513183594,
+      "eval_runtime": 36.7696,
+      "eval_samples_per_second": 35.627,
+      "eval_steps_per_second": 1.115,
+      "step": 125
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.651881589784425,
+      "learning_rate": 1.9787400799669155e-05,
+      "loss": 1.4406,
+      "step": 130
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.5390077509830626,
+      "learning_rate": 1.9741004551724208e-05,
+      "loss": 1.4683,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.654802825210285,
+      "learning_rate": 1.9690098257244063e-05,
+      "loss": 1.46,
+      "step": 140
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.828779092366187,
+      "learning_rate": 1.963470548564149e-05,
+      "loss": 1.457,
+      "step": 145
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.221793591458839,
+      "learning_rate": 1.9574851883550395e-05,
+      "loss": 1.4387,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 1.4409288167953491,
+      "eval_runtime": 36.7378,
+      "eval_samples_per_second": 35.658,
+      "eval_steps_per_second": 1.116,
+      "step": 150
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.429483358899047,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 1.4227,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.3883915102781494,
+      "learning_rate": 1.9441875088342e-05,
+      "loss": 1.4335,
+      "step": 160
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 3.4947168397325368,
+      "learning_rate": 1.9368813462954316e-05,
+      "loss": 1.4165,
+      "step": 165
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.498600082458413,
+      "learning_rate": 1.9291414114031744e-05,
+      "loss": 1.411,
+      "step": 170
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.540671355408263,
+      "learning_rate": 1.9209712877166347e-05,
+      "loss": 1.4368,
+      "step": 175
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 1.4226408004760742,
+      "eval_runtime": 36.4019,
+      "eval_samples_per_second": 35.987,
+      "eval_steps_per_second": 1.126,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 324.64947934206117,
+      "learning_rate": 1.9123747579707275e-05,
+      "loss": 1.3938,
+      "step": 180
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 9.509687913297793,
+      "learning_rate": 1.9033558023246845e-05,
+      "loss": 1.4201,
+      "step": 185
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.133252955012539,
+      "learning_rate": 1.8939185965192572e-05,
+      "loss": 1.413,
+      "step": 190
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.023875370016508,
+      "learning_rate": 1.8840675099433637e-05,
+      "loss": 1.4426,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.144939646556894,
+      "learning_rate": 1.873807103611081e-05,
+      "loss": 1.4095,
+      "step": 200
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.422728419303894,
+      "eval_runtime": 36.3022,
+      "eval_samples_per_second": 36.086,
+      "eval_steps_per_second": 1.129,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.8094743377142,
+      "learning_rate": 1.8631421280499114e-05,
+      "loss": 1.4219,
+      "step": 205
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.6484435225782885,
+      "learning_rate": 1.8520775211013094e-05,
+      "loss": 1.399,
+      "step": 210
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 3.8418704373836454,
+      "learning_rate": 1.8406184056344784e-05,
+      "loss": 1.424,
+      "step": 215
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.5369039139594354,
+      "learning_rate": 1.8287700871745036e-05,
+      "loss": 1.3809,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 4.306679118424655,
+      "learning_rate": 1.816538051445916e-05,
+      "loss": 1.4065,
+      "step": 225
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 1.4043676853179932,
+      "eval_runtime": 36.1499,
+      "eval_samples_per_second": 36.238,
+      "eval_steps_per_second": 1.134,
+      "step": 225
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.793497887600387,
+      "learning_rate": 1.8039279618328215e-05,
+      "loss": 1.4393,
+      "step": 230
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.5806655996080217,
+      "learning_rate": 1.7909456567567774e-05,
+      "loss": 1.3877,
+      "step": 235
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.335034005215255,
+      "learning_rate": 1.777597146973627e-05,
+      "loss": 1.3992,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.5829112355976407,
+      "learning_rate": 1.7638886127905427e-05,
+      "loss": 1.3966,
+      "step": 245
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.380252848613958,
+      "learning_rate": 1.7498264012045686e-05,
+      "loss": 1.3747,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 1.3881479501724243,
+      "eval_runtime": 36.7171,
+      "eval_samples_per_second": 35.678,
+      "eval_steps_per_second": 1.117,
+      "step": 250
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.610102942308515,
+      "learning_rate": 1.7354170229639856e-05,
+      "loss": 1.3726,
+      "step": 255
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.3439020430777155,
+      "learning_rate": 1.720667149553861e-05,
+      "loss": 1.3682,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.4956412955508402,
+      "learning_rate": 1.705583610107178e-05,
+      "loss": 1.3552,
+      "step": 265
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.4985126593068165,
+      "learning_rate": 1.690173388242972e-05,
+      "loss": 1.3895,
+      "step": 270
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.7382334626759746,
+      "learning_rate": 1.6744436188329455e-05,
+      "loss": 1.3847,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 1.3719505071640015,
+      "eval_runtime": 36.7391,
+      "eval_samples_per_second": 35.657,
+      "eval_steps_per_second": 1.116,
+      "step": 275
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 3.7522691462559363,
+      "learning_rate": 1.658401584698049e-05,
+      "loss": 1.3954,
+      "step": 280
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.599034550869163,
+      "learning_rate": 1.6420547132365637e-05,
+      "loss": 1.3558,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.780355027101858,
+      "learning_rate": 1.6254105729852466e-05,
+      "loss": 1.3836,
+      "step": 290
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.723697013821863,
+      "learning_rate": 1.6084768701151263e-05,
+      "loss": 1.3753,
+      "step": 295
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.285217439584574,
+      "learning_rate": 1.5912614448635784e-05,
+      "loss": 1.3526,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 1.358110785484314,
+      "eval_runtime": 36.5535,
+      "eval_samples_per_second": 35.838,
+      "eval_steps_per_second": 1.122,
+      "step": 300
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.389266580261243,
+      "learning_rate": 1.573772267904325e-05,
+      "loss": 1.3432,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.562805344105124,
+      "learning_rate": 1.5560174366570448e-05,
+      "loss": 1.3479,
+      "step": 310
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.557282541178432,
+      "learning_rate": 1.5380051715383e-05,
+      "loss": 1.3482,
+      "step": 315
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 3.171518329728872,
+      "learning_rate": 1.5197438121555159e-05,
+      "loss": 1.3627,
+      "step": 320
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.4241008103077006,
+      "learning_rate": 1.5012418134457756e-05,
+      "loss": 1.3072,
+      "step": 325
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.3410331010818481,
+      "eval_runtime": 36.5162,
+      "eval_samples_per_second": 35.874,
+      "eval_steps_per_second": 1.123,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 3.4417136894356077,
+      "learning_rate": 1.4825077417612187e-05,
+      "loss": 1.3713,
+      "step": 330
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.55225659028301,
+      "learning_rate": 1.4635502709028511e-05,
+      "loss": 1.3492,
+      "step": 335
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.864004021362561,
+      "learning_rate": 1.4443781781046135e-05,
+      "loss": 1.3297,
+      "step": 340
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.714231728878515,
+      "learning_rate": 1.425000339969554e-05,
+      "loss": 1.292,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.499541537796859,
+      "learning_rate": 1.4054257283599974e-05,
+      "loss": 1.3146,
+      "step": 350
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 1.3238551616668701,
+      "eval_runtime": 35.9276,
+      "eval_samples_per_second": 36.462,
+      "eval_steps_per_second": 1.141,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 3.3766322552695374,
+      "learning_rate": 1.3856634062436073e-05,
+      "loss": 1.2782,
+      "step": 355
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.430094949177884,
+      "learning_rate": 1.3657225234972695e-05,
+      "loss": 1.291,
+      "step": 360
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.7053693958311964,
+      "learning_rate": 1.3456123126707334e-05,
+      "loss": 1.3275,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 3.528099228472523,
+      "learning_rate": 1.3253420847119804e-05,
+      "loss": 1.2867,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.6078436890974706,
+      "learning_rate": 1.304921224656289e-05,
+      "loss": 1.2783,
+      "step": 375
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 1.310630440711975,
+      "eval_runtime": 36.5504,
+      "eval_samples_per_second": 35.841,
+      "eval_steps_per_second": 1.122,
+      "step": 375
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.523684230098565,
+      "learning_rate": 1.2843591872810039e-05,
+      "loss": 1.2782,
+      "step": 380
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.7267322056062144,
+      "learning_rate": 1.2636654927280074e-05,
+      "loss": 1.2761,
+      "step": 385
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.65799573792828,
+      "learning_rate": 1.2428497220959359e-05,
+      "loss": 1.2864,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 3.520887899492278,
+      "learning_rate": 1.2219215130041656e-05,
+      "loss": 1.2936,
+      "step": 395
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.878015265725218,
+      "learning_rate": 1.2008905551306356e-05,
+      "loss": 1.2773,
+      "step": 400
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.2895601987838745,
+      "eval_runtime": 36.4176,
+      "eval_samples_per_second": 35.972,
+      "eval_steps_per_second": 1.126,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.1260498556243155,
+      "learning_rate": 1.1797665857255622e-05,
+      "loss": 1.2861,
+      "step": 405
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 4.466084749533314,
+      "learning_rate": 1.1585593851031346e-05,
+      "loss": 0.8568,
+      "step": 410
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 4.230541766753645,
+      "learning_rate": 1.1372787721132648e-05,
+      "loss": 0.7304,
+      "step": 415
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 4.050955020609926,
+      "learning_rate": 1.1159345995955007e-05,
+      "loss": 0.7438,
+      "step": 420
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 3.8978479248153,
+      "learning_rate": 1.0945367498171992e-05,
+      "loss": 0.7303,
+      "step": 425
+    },
+    {
+      "epoch": 1.05,
+      "eval_loss": 1.3326823711395264,
+      "eval_runtime": 37.9893,
+      "eval_samples_per_second": 34.483,
+      "eval_steps_per_second": 1.079,
+      "step": 425
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 3.7185440445464963,
+      "learning_rate": 1.0730951298980776e-05,
+      "loss": 0.7407,
+      "step": 430
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 3.7568671101121303,
+      "learning_rate": 1.0516196672232538e-05,
+      "loss": 0.7147,
+      "step": 435
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 4.175956955241419,
+      "learning_rate": 1.0301203048469084e-05,
+      "loss": 0.7187,
+      "step": 440
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 3.5713973562394794,
+      "learning_rate": 1.0086069968886885e-05,
+      "loss": 0.6899,
+      "step": 445
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 3.926229796886718,
+      "learning_rate": 9.87089703924991e-06,
+      "loss": 0.6911,
+      "step": 450
+    },
+    {
+      "epoch": 1.11,
+      "eval_loss": 1.3080617189407349,
+      "eval_runtime": 36.6218,
+      "eval_samples_per_second": 35.771,
+      "eval_steps_per_second": 1.12,
+      "step": 450
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 4.041765832088674,
+      "learning_rate": 9.655783883772546e-06,
+      "loss": 0.6783,
+      "step": 455
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 3.822198052373504,
+      "learning_rate": 9.440830098993969e-06,
+      "loss": 0.7047,
+      "step": 460
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 3.74103783619035,
+      "learning_rate": 9.22613520766537e-06,
+      "loss": 0.7148,
+      "step": 465
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.863229052811563,
+      "learning_rate": 9.011798612671286e-06,
+      "loss": 0.6882,
+      "step": 470
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.7184780256426233,
+      "learning_rate": 8.797919551006477e-06,
+      "loss": 0.7044,
+      "step": 475
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 1.3011983633041382,
+      "eval_runtime": 36.1296,
+      "eval_samples_per_second": 36.258,
+      "eval_steps_per_second": 1.135,
+      "step": 475
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 3.61644498812297,
+      "learning_rate": 8.58459704782957e-06,
+      "loss": 0.7014,
+      "step": 480
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.7252005213479427,
+      "learning_rate": 8.371929870614834e-06,
+      "loss": 0.689,
+      "step": 485
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 3.6457105180525105,
+      "learning_rate": 8.1600164834232e-06,
+      "loss": 0.6913,
+      "step": 490
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 7.856843188311362,
+      "learning_rate": 7.948955001313812e-06,
+      "loss": 0.6851,
+      "step": 495
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 3.583455067918794,
+      "learning_rate": 7.738843144917119e-06,
+      "loss": 0.6597,
+      "step": 500
+    },
+    {
+      "epoch": 1.23,
+      "eval_loss": 1.2844963073730469,
+      "eval_runtime": 36.2065,
+      "eval_samples_per_second": 36.181,
+      "eval_steps_per_second": 1.132,
+      "step": 500
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 6.459020130486219,
+      "learning_rate": 7.529778195190644e-06,
+      "loss": 0.6643,
+      "step": 505
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 3.8211583260556905,
+      "learning_rate": 7.321856948378259e-06,
+      "loss": 0.6848,
+      "step": 510
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 3.7126647718977095,
+      "learning_rate": 7.115175671193913e-06,
+      "loss": 0.6894,
+      "step": 515
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 3.659148206814036,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.6846,
+      "step": 520
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 3.5912318784335757,
+      "learning_rate": 6.7059151777547e-06,
+      "loss": 0.6717,
+      "step": 525
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 1.2701396942138672,
+      "eval_runtime": 36.3576,
+      "eval_samples_per_second": 36.031,
+      "eval_steps_per_second": 1.128,
+      "step": 525
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 4.43495688718006,
+      "learning_rate": 6.503525447487717e-06,
+      "loss": 0.6644,
+      "step": 530
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.754517876550191,
+      "learning_rate": 6.3027545710932715e-06,
+      "loss": 0.6531,
+      "step": 535
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 3.745749569347864,
+      "learning_rate": 6.103695504692122e-06,
+      "loss": 0.6528,
+      "step": 540
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 3.724963177872727,
+      "learning_rate": 5.906440411843787e-06,
+      "loss": 0.6679,
+      "step": 545
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.5172682214444926,
+      "learning_rate": 5.711080620875165e-06,
+      "loss": 0.6538,
+      "step": 550
+    },
+    {
+      "epoch": 1.35,
+      "eval_loss": 1.2666361331939697,
+      "eval_runtime": 36.5896,
+      "eval_samples_per_second": 35.802,
+      "eval_steps_per_second": 1.121,
+      "step": 550
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 3.6339406360777096,
+      "learning_rate": 5.517706582595896e-06,
+      "loss": 0.6794,
+      "step": 555
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 3.7173322180156116,
+      "learning_rate": 5.32640782841998e-06,
+      "loss": 0.6479,
+      "step": 560
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 3.661315456496335,
+      "learning_rate": 5.137272928913097e-06,
+      "loss": 0.6582,
+      "step": 565
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 4.487184920335217,
+      "learning_rate": 4.950389452784796e-06,
+      "loss": 0.6697,
+      "step": 570
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.5318063600935776,
+      "learning_rate": 4.7658439263445015e-06,
+      "loss": 0.6484,
+      "step": 575
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 1.2480911016464233,
+      "eval_runtime": 36.7469,
+      "eval_samples_per_second": 35.649,
+      "eval_steps_per_second": 1.116,
+      "step": 575
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 3.6935613568961463,
+      "learning_rate": 4.583721793440188e-06,
+      "loss": 0.6621,
+      "step": 580
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.6221958065559203,
+      "learning_rate": 4.404107375898234e-06,
+      "loss": 0.6633,
+      "step": 585
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 3.9034034514689533,
+      "learning_rate": 4.2270838344827285e-06,
+      "loss": 0.6561,
+      "step": 590
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 3.7752277109004733,
+      "learning_rate": 4.052733130392367e-06,
+      "loss": 0.65,
+      "step": 595
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 3.63792060813426,
+      "learning_rate": 3.881135987312758e-06,
+      "loss": 0.633,
+      "step": 600
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 1.2404245138168335,
+      "eval_runtime": 36.9,
+      "eval_samples_per_second": 35.501,
+      "eval_steps_per_second": 1.111,
+      "step": 600
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 3.629431521288044,
+      "learning_rate": 3.712371854041654e-06,
+      "loss": 0.6252,
+      "step": 605
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.7538748748698962,
+      "learning_rate": 3.546518867704499e-06,
+      "loss": 0.6549,
+      "step": 610
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 3.5943200372390676,
+      "learning_rate": 3.383653817577216e-06,
+      "loss": 0.6365,
+      "step": 615
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 3.7988035352394673,
+      "learning_rate": 3.223852109533112e-06,
+      "loss": 0.6157,
+      "step": 620
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 3.7396973266303886,
+      "learning_rate": 3.0671877311302247e-06,
+      "loss": 0.6252,
+      "step": 625
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 1.2332385778427124,
+      "eval_runtime": 36.3217,
+      "eval_samples_per_second": 36.067,
+      "eval_steps_per_second": 1.129,
+      "step": 625
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.6119019240279258,
+      "learning_rate": 2.9137332173554043e-06,
+      "loss": 0.6215,
+      "step": 630
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 3.561248255506443,
+      "learning_rate": 2.763559617040876e-06,
+      "loss": 0.6364,
+      "step": 635
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 4.068465368690645,
+      "learning_rate": 2.616736459968936e-06,
+      "loss": 0.6193,
+      "step": 640
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 3.808522974597512,
+      "learning_rate": 2.473331724679917e-06,
+      "loss": 0.6622,
+      "step": 645
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.743484183877061,
+      "learning_rate": 2.3334118069984102e-06,
+      "loss": 0.6423,
+      "step": 650
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.2212291955947876,
+      "eval_runtime": 36.995,
+      "eval_samples_per_second": 35.41,
+      "eval_steps_per_second": 1.108,
+      "step": 650
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 3.7762899770508453,
+      "learning_rate": 2.197041489292244e-06,
+      "loss": 0.64,
+      "step": 655
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 3.7440789835416575,
+      "learning_rate": 2.064283910478527e-06,
+      "loss": 0.6627,
+      "step": 660
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 3.53490892439879,
+      "learning_rate": 1.9352005367905536e-06,
+      "loss": 0.6253,
+      "step": 665
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 3.743044691468231,
+      "learning_rate": 1.8098511333192026e-06,
+      "loss": 0.6248,
+      "step": 670
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 3.508178112989742,
+      "learning_rate": 1.6882937363419205e-06,
+      "loss": 0.6182,
+      "step": 675
+    },
+    {
+      "epoch": 1.66,
+      "eval_loss": 1.2115447521209717,
+      "eval_runtime": 36.7342,
+      "eval_samples_per_second": 35.662,
+      "eval_steps_per_second": 1.116,
+      "step": 675
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.82584115413825,
+      "learning_rate": 1.5705846264521728e-06,
+      "loss": 0.6159,
+      "step": 680
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 3.805908154584629,
+      "learning_rate": 1.45677830250173e-06,
+      "loss": 0.5992,
+      "step": 685
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 3.6691587173463174,
+      "learning_rate": 1.3469274563679401e-06,
+      "loss": 0.6379,
+      "step": 690
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 3.6099414977809534,
+      "learning_rate": 1.2410829485575703e-06,
+      "loss": 0.6217,
+      "step": 695
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 3.6351646415567833,
+      "learning_rate": 1.1392937846586216e-06,
+      "loss": 0.6218,
+      "step": 700
+    },
+    {
+      "epoch": 1.72,
+      "eval_loss": 1.2099106311798096,
+      "eval_runtime": 37.2149,
+      "eval_samples_per_second": 35.201,
+      "eval_steps_per_second": 1.102,
+      "step": 700
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 3.5759017601516625,
+      "learning_rate": 1.0416070926509114e-06,
+      "loss": 0.625,
+      "step": 705
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 4.079216714693347,
+      "learning_rate": 9.48068101086026e-07,
+      "loss": 0.6503,
+      "step": 710
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 3.690374175674403,
+      "learning_rate": 8.58720118146662e-07,
+      "loss": 0.6279,
+      "step": 715
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 3.653451951807952,
+      "learning_rate": 7.736045115951252e-07,
+      "loss": 0.6214,
+      "step": 720
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 3.9843182779544253,
+      "learning_rate": 6.927606896202066e-07,
+      "loss": 0.6293,
+      "step": 725
+    },
+    {
+      "epoch": 1.79,
+      "eval_loss": 1.2038028240203857,
+      "eval_runtime": 36.8911,
+      "eval_samples_per_second": 35.51,
+      "eval_steps_per_second": 1.111,
+      "step": 725
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 3.625232494017856,
+      "learning_rate": 6.162260825913591e-07,
+      "loss": 0.6138,
+      "step": 730
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 3.438461239374458,
+      "learning_rate": 5.440361257285742e-07,
+      "loss": 0.6035,
+      "step": 735
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 3.468914334826838,
+      "learning_rate": 4.762242426960262e-07,
+      "loss": 0.6123,
+      "step": 740
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 3.4298511965711214,
+      "learning_rate": 4.128218301270359e-07,
+      "loss": 0.5911,
+      "step": 745
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 3.648217807793934,
+      "learning_rate": 3.538582430875659e-07,
+      "loss": 0.5978,
+      "step": 750
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 1.20143461227417,
+      "eval_runtime": 36.7633,
+      "eval_samples_per_second": 35.633,
+      "eval_steps_per_second": 1.115,
+      "step": 750
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 3.6847453856191597,
+      "learning_rate": 2.9936078148492973e-07,
+      "loss": 0.6013,
+      "step": 755
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.6349536920444874,
+      "learning_rate": 2.493546774280531e-07,
+      "loss": 0.6004,
+      "step": 760
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 3.5351570751944594,
+      "learning_rate": 2.0386308354509944e-07,
+      "loss": 0.5957,
+      "step": 765
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.623279846120391,
+      "learning_rate": 1.6290706226390286e-07,
+      "loss": 0.5953,
+      "step": 770
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 3.6727168784725897,
+      "learning_rate": 1.2650557606013635e-07,
+      "loss": 0.6176,
+      "step": 775
+    },
+    {
+      "epoch": 1.91,
+      "eval_loss": 1.19950532913208,
+      "eval_runtime": 36.6969,
+      "eval_samples_per_second": 35.698,
+      "eval_steps_per_second": 1.117,
+      "step": 775
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 3.873849616801828,
+      "learning_rate": 9.467547867777261e-08,
+      "loss": 0.5817,
+      "step": 780
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 3.554084353387301,
+      "learning_rate": 6.74315073258569e-08,
+      "loss": 0.6145,
+      "step": 785
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 7.330372861717701,
+      "learning_rate": 4.478627585524753e-08,
+      "loss": 0.6256,
+      "step": 790
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 3.617776301851038,
+      "learning_rate": 2.675026891844512e-08,
+      "loss": 0.6224,
+      "step": 795
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 3.5902020548965763,
+      "learning_rate": 1.3331837115241331e-08,
+      "loss": 0.6475,
+      "step": 800
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 1.199601411819458,
+      "eval_runtime": 36.7572,
+      "eval_samples_per_second": 35.639,
+      "eval_steps_per_second": 1.115,
+      "step": 800
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 3.5573953568277306,
+      "learning_rate": 4.537193126427086e-09,
+      "loss": 0.5941,
+      "step": 805
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.684445766409529,
+      "learning_rate": 3.7040883734462685e-10,
+      "loss": 0.6021,
+      "step": 810
+    },
+    {
+      "epoch": 2.0,
+      "step": 812,
+      "total_flos": 42504070103040.0,
+      "train_loss": 1.0263223388218528,
+      "train_runtime": 5267.6103,
+      "train_samples_per_second": 4.93,
+      "train_steps_per_second": 0.154
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 812,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 42504070103040.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}