Model save

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2-7B
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-qwen2-7b-sft
+  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-qwen2-7b-sft
+
+This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0646
+
+## 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: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0626        | 1.0   | 956  | 1.0646          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 500925122740224.0,
+    "train_loss": 1.0766646904426638,
+    "train_runtime": 10839.8443,
+    "train_samples": 207864,
+    "train_samples_per_second": 11.286,
+    "train_steps_per_second": 0.088
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6039494ac641d99d13b6f028d2a309d117292be0301ad9e77ccb61d5d09d61
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7907147daaa9fad1b0dd1ccd01bf743294c785fed19b77a288ef3e6cbe91768a
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea1812025c1808c2ebc632f73cad6038809c45373791f1789cf32259447d9d4
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f1bf1dbca8a6fa54c435b5dee8ee34b090850ba9b780c8d6f3083db9d29355
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

runs/Jun10_06-28-29_action-graph-trainer/events.out.tfevents.1718000933.action-graph-trainer.4056328.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bab8873acc8c3491abf5ba9fc96b1a195ed6ceaf465c05a5e6fe04dde707f46
-size 42935
+oid sha256:080a20ece6e0a5f501a0fdfabe67f8205f0d32ba274fea1708f7e41a1e0a098f
+size 45881

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 500925122740224.0,
+    "train_loss": 1.0766646904426638,
+    "train_runtime": 10839.8443,
+    "train_samples": 207864,
+    "train_samples_per_second": 11.286,
+    "train_steps_per_second": 0.088
+}

trainer_state.json

@@ -0,0 +1,1382 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 956,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0010460251046025104,
+      "grad_norm": 4.85831464931585,
+      "learning_rate": 2.0833333333333333e-07,
+      "loss": 1.3092,
+      "step": 1
+    },
+    {
+      "epoch": 0.005230125523012552,
+      "grad_norm": 4.698008970388053,
+      "learning_rate": 1.0416666666666667e-06,
+      "loss": 1.2901,
+      "step": 5
+    },
+    {
+      "epoch": 0.010460251046025104,
+      "grad_norm": 4.048984012433902,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 1.2488,
+      "step": 10
+    },
+    {
+      "epoch": 0.015690376569037656,
+      "grad_norm": 1.2617332917985404,
+      "learning_rate": 3.125e-06,
+      "loss": 1.1403,
+      "step": 15
+    },
+    {
+      "epoch": 0.02092050209205021,
+      "grad_norm": 0.7560157485938099,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.1238,
+      "step": 20
+    },
+    {
+      "epoch": 0.02615062761506276,
+      "grad_norm": 0.6324506842569716,
+      "learning_rate": 5.208333333333334e-06,
+      "loss": 1.0882,
+      "step": 25
+    },
+    {
+      "epoch": 0.03138075313807531,
+      "grad_norm": 0.548469635609847,
+      "learning_rate": 6.25e-06,
+      "loss": 1.0972,
+      "step": 30
+    },
+    {
+      "epoch": 0.036610878661087864,
+      "grad_norm": 0.5552996818029777,
+      "learning_rate": 7.291666666666667e-06,
+      "loss": 1.0967,
+      "step": 35
+    },
+    {
+      "epoch": 0.04184100418410042,
+      "grad_norm": 0.5800275526403403,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.0806,
+      "step": 40
+    },
+    {
+      "epoch": 0.04707112970711297,
+      "grad_norm": 0.6526746495693823,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.0799,
+      "step": 45
+    },
+    {
+      "epoch": 0.05230125523012552,
+      "grad_norm": 0.5908325566513732,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 1.0776,
+      "step": 50
+    },
+    {
+      "epoch": 0.05753138075313807,
+      "grad_norm": 0.5391654191606475,
+      "learning_rate": 1.1458333333333333e-05,
+      "loss": 1.0899,
+      "step": 55
+    },
+    {
+      "epoch": 0.06276150627615062,
+      "grad_norm": 0.5595510219538938,
+      "learning_rate": 1.25e-05,
+      "loss": 1.0764,
+      "step": 60
+    },
+    {
+      "epoch": 0.06799163179916318,
+      "grad_norm": 0.6189231853205227,
+      "learning_rate": 1.3541666666666668e-05,
+      "loss": 1.0822,
+      "step": 65
+    },
+    {
+      "epoch": 0.07322175732217573,
+      "grad_norm": 0.6003927282619645,
+      "learning_rate": 1.4583333333333333e-05,
+      "loss": 1.0677,
+      "step": 70
+    },
+    {
+      "epoch": 0.07845188284518828,
+      "grad_norm": 0.587656104310443,
+      "learning_rate": 1.5625e-05,
+      "loss": 1.094,
+      "step": 75
+    },
+    {
+      "epoch": 0.08368200836820083,
+      "grad_norm": 0.6752900460018412,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.0929,
+      "step": 80
+    },
+    {
+      "epoch": 0.08891213389121339,
+      "grad_norm": 0.584358866439279,
+      "learning_rate": 1.7708333333333335e-05,
+      "loss": 1.1021,
+      "step": 85
+    },
+    {
+      "epoch": 0.09414225941422594,
+      "grad_norm": 0.6938741353728844,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.0856,
+      "step": 90
+    },
+    {
+      "epoch": 0.09937238493723849,
+      "grad_norm": 0.5937738979114767,
+      "learning_rate": 1.979166666666667e-05,
+      "loss": 1.0862,
+      "step": 95
+    },
+    {
+      "epoch": 0.10460251046025104,
+      "grad_norm": 0.6710102145171454,
+      "learning_rate": 1.9998932457674904e-05,
+      "loss": 1.0933,
+      "step": 100
+    },
+    {
+      "epoch": 0.1098326359832636,
+      "grad_norm": 0.5541556578263152,
+      "learning_rate": 1.999459595761682e-05,
+      "loss": 1.1147,
+      "step": 105
+    },
+    {
+      "epoch": 0.11506276150627615,
+      "grad_norm": 0.7295308103628182,
+      "learning_rate": 1.9986925223989665e-05,
+      "loss": 1.093,
+      "step": 110
+    },
+    {
+      "epoch": 0.1202928870292887,
+      "grad_norm": 0.5550755397232149,
+      "learning_rate": 1.9975922815778082e-05,
+      "loss": 1.0831,
+      "step": 115
+    },
+    {
+      "epoch": 0.12552301255230125,
+      "grad_norm": 0.6906078000000908,
+      "learning_rate": 1.996159240342547e-05,
+      "loss": 1.0825,
+      "step": 120
+    },
+    {
+      "epoch": 0.1307531380753138,
+      "grad_norm": 0.6064322930924732,
+      "learning_rate": 1.9943938767609515e-05,
+      "loss": 1.0831,
+      "step": 125
+    },
+    {
+      "epoch": 0.13598326359832635,
+      "grad_norm": 0.5759088665056421,
+      "learning_rate": 1.9922967797647357e-05,
+      "loss": 1.0905,
+      "step": 130
+    },
+    {
+      "epoch": 0.1412133891213389,
+      "grad_norm": 0.5922048567597843,
+      "learning_rate": 1.9898686489530852e-05,
+      "loss": 1.0974,
+      "step": 135
+    },
+    {
+      "epoch": 0.14644351464435146,
+      "grad_norm": 0.582760629154959,
+      "learning_rate": 1.9871102943592717e-05,
+      "loss": 1.0731,
+      "step": 140
+    },
+    {
+      "epoch": 0.151673640167364,
+      "grad_norm": 0.5685111043758668,
+      "learning_rate": 1.9840226361804223e-05,
+      "loss": 1.1055,
+      "step": 145
+    },
+    {
+      "epoch": 0.15690376569037656,
+      "grad_norm": 0.5443024454296611,
+      "learning_rate": 1.9806067044705375e-05,
+      "loss": 1.076,
+      "step": 150
+    },
+    {
+      "epoch": 0.16213389121338911,
+      "grad_norm": 0.624292985384766,
+      "learning_rate": 1.9768636387968616e-05,
+      "loss": 1.1064,
+      "step": 155
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 0.6240829821198746,
+      "learning_rate": 1.9727946878597193e-05,
+      "loss": 1.0791,
+      "step": 160
+    },
+    {
+      "epoch": 0.17259414225941422,
+      "grad_norm": 0.5276766638385988,
+      "learning_rate": 1.968401209075946e-05,
+      "loss": 1.0839,
+      "step": 165
+    },
+    {
+      "epoch": 0.17782426778242677,
+      "grad_norm": 0.5836785578453231,
+      "learning_rate": 1.963684668126046e-05,
+      "loss": 1.1019,
+      "step": 170
+    },
+    {
+      "epoch": 0.18305439330543932,
+      "grad_norm": 0.635087703249428,
+      "learning_rate": 1.9586466384652366e-05,
+      "loss": 1.0847,
+      "step": 175
+    },
+    {
+      "epoch": 0.18828451882845187,
+      "grad_norm": 0.6401066654821815,
+      "learning_rate": 1.9532888007985408e-05,
+      "loss": 1.0956,
+      "step": 180
+    },
+    {
+      "epoch": 0.19351464435146443,
+      "grad_norm": 0.6003213599436353,
+      "learning_rate": 1.9476129425200935e-05,
+      "loss": 1.0937,
+      "step": 185
+    },
+    {
+      "epoch": 0.19874476987447698,
+      "grad_norm": 0.6459057767600639,
+      "learning_rate": 1.9416209571168648e-05,
+      "loss": 1.089,
+      "step": 190
+    },
+    {
+      "epoch": 0.20397489539748953,
+      "grad_norm": 0.5793932824335415,
+      "learning_rate": 1.9353148435369816e-05,
+      "loss": 1.0906,
+      "step": 195
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "grad_norm": 0.5669130898905272,
+      "learning_rate": 1.9286967055228744e-05,
+      "loss": 1.093,
+      "step": 200
+    },
+    {
+      "epoch": 0.21443514644351463,
+      "grad_norm": 0.6665999257578469,
+      "learning_rate": 1.9217687509094596e-05,
+      "loss": 1.0759,
+      "step": 205
+    },
+    {
+      "epoch": 0.2196652719665272,
+      "grad_norm": 0.6045661696203776,
+      "learning_rate": 1.9145332908875984e-05,
+      "loss": 1.0911,
+      "step": 210
+    },
+    {
+      "epoch": 0.22489539748953974,
+      "grad_norm": 0.603921012093451,
+      "learning_rate": 1.9069927392330742e-05,
+      "loss": 1.1017,
+      "step": 215
+    },
+    {
+      "epoch": 0.2301255230125523,
+      "grad_norm": 0.6981633005799726,
+      "learning_rate": 1.89914961150135e-05,
+      "loss": 1.082,
+      "step": 220
+    },
+    {
+      "epoch": 0.23535564853556484,
+      "grad_norm": 0.5312778797944372,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 1.0797,
+      "step": 225
+    },
+    {
+      "epoch": 0.2405857740585774,
+      "grad_norm": 0.6185885471490489,
+      "learning_rate": 1.8825661938576784e-05,
+      "loss": 1.085,
+      "step": 230
+    },
+    {
+      "epoch": 0.24581589958158995,
+      "grad_norm": 0.6020254222541368,
+      "learning_rate": 1.8738314362341828e-05,
+      "loss": 1.0849,
+      "step": 235
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "grad_norm": 0.5477699753630808,
+      "learning_rate": 1.864805165264799e-05,
+      "loss": 1.0953,
+      "step": 240
+    },
+    {
+      "epoch": 0.25627615062761505,
+      "grad_norm": 0.6850363564163309,
+      "learning_rate": 1.8554903921463578e-05,
+      "loss": 1.0889,
+      "step": 245
+    },
+    {
+      "epoch": 0.2615062761506276,
+      "grad_norm": 0.5908540938126509,
+      "learning_rate": 1.8458902243210558e-05,
+      "loss": 1.0822,
+      "step": 250
+    },
+    {
+      "epoch": 0.26673640167364016,
+      "grad_norm": 0.6783907257016317,
+      "learning_rate": 1.8360078644398028e-05,
+      "loss": 1.0788,
+      "step": 255
+    },
+    {
+      "epoch": 0.2719665271966527,
+      "grad_norm": 0.5917684668235483,
+      "learning_rate": 1.8258466092938042e-05,
+      "loss": 1.101,
+      "step": 260
+    },
+    {
+      "epoch": 0.27719665271966526,
+      "grad_norm": 0.5760642704541414,
+      "learning_rate": 1.8154098487147405e-05,
+      "loss": 1.0776,
+      "step": 265
+    },
+    {
+      "epoch": 0.2824267782426778,
+      "grad_norm": 0.7830659265090936,
+      "learning_rate": 1.8047010644439074e-05,
+      "loss": 1.0838,
+      "step": 270
+    },
+    {
+      "epoch": 0.28765690376569036,
+      "grad_norm": 0.5624324029328165,
+      "learning_rate": 1.7937238289706927e-05,
+      "loss": 1.0821,
+      "step": 275
+    },
+    {
+      "epoch": 0.2928870292887029,
+      "grad_norm": 0.6142016239039022,
+      "learning_rate": 1.7824818043407828e-05,
+      "loss": 1.064,
+      "step": 280
+    },
+    {
+      "epoch": 0.29811715481171547,
+      "grad_norm": 0.5924790097587224,
+      "learning_rate": 1.7709787409344893e-05,
+      "loss": 1.0749,
+      "step": 285
+    },
+    {
+      "epoch": 0.303347280334728,
+      "grad_norm": 0.6228874527190459,
+      "learning_rate": 1.75921847621561e-05,
+      "loss": 1.0863,
+      "step": 290
+    },
+    {
+      "epoch": 0.30857740585774057,
+      "grad_norm": 0.6526952399454782,
+      "learning_rate": 1.7472049334512354e-05,
+      "loss": 1.0752,
+      "step": 295
+    },
+    {
+      "epoch": 0.3138075313807531,
+      "grad_norm": 0.5460673752687526,
+      "learning_rate": 1.7349421204029343e-05,
+      "loss": 1.0838,
+      "step": 300
+    },
+    {
+      "epoch": 0.3190376569037657,
+      "grad_norm": 0.5952113239646497,
+      "learning_rate": 1.7224341279897473e-05,
+      "loss": 1.0937,
+      "step": 305
+    },
+    {
+      "epoch": 0.32426778242677823,
+      "grad_norm": 0.6159873510239029,
+      "learning_rate": 1.7096851289234448e-05,
+      "loss": 1.0861,
+      "step": 310
+    },
+    {
+      "epoch": 0.3294979079497908,
+      "grad_norm": 0.6664129454325257,
+      "learning_rate": 1.6966993763164928e-05,
+      "loss": 1.0863,
+      "step": 315
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 0.5500624646942581,
+      "learning_rate": 1.6834812022632e-05,
+      "loss": 1.0915,
+      "step": 320
+    },
+    {
+      "epoch": 0.3399581589958159,
+      "grad_norm": 0.5592633657451478,
+      "learning_rate": 1.670035016394513e-05,
+      "loss": 1.0875,
+      "step": 325
+    },
+    {
+      "epoch": 0.34518828451882844,
+      "grad_norm": 0.5766618518095256,
+      "learning_rate": 1.656365304406953e-05,
+      "loss": 1.0813,
+      "step": 330
+    },
+    {
+      "epoch": 0.350418410041841,
+      "grad_norm": 0.5879084875352091,
+      "learning_rate": 1.6424766265661648e-05,
+      "loss": 1.084,
+      "step": 335
+    },
+    {
+      "epoch": 0.35564853556485354,
+      "grad_norm": 0.6329467200832875,
+      "learning_rate": 1.6283736161855995e-05,
+      "loss": 1.0772,
+      "step": 340
+    },
+    {
+      "epoch": 0.3608786610878661,
+      "grad_norm": 0.5327051525622571,
+      "learning_rate": 1.614060978080823e-05,
+      "loss": 1.0927,
+      "step": 345
+    },
+    {
+      "epoch": 0.36610878661087864,
+      "grad_norm": 0.5576373339458268,
+      "learning_rate": 1.5995434869999723e-05,
+      "loss": 1.079,
+      "step": 350
+    },
+    {
+      "epoch": 0.3713389121338912,
+      "grad_norm": 0.5657380130894529,
+      "learning_rate": 1.584825986030883e-05,
+      "loss": 1.0876,
+      "step": 355
+    },
+    {
+      "epoch": 0.37656903765690375,
+      "grad_norm": 0.5680127150496128,
+      "learning_rate": 1.5699133849854164e-05,
+      "loss": 1.0888,
+      "step": 360
+    },
+    {
+      "epoch": 0.3817991631799163,
+      "grad_norm": 0.5721025801861312,
+      "learning_rate": 1.5548106587615295e-05,
+      "loss": 1.0669,
+      "step": 365
+    },
+    {
+      "epoch": 0.38702928870292885,
+      "grad_norm": 0.5558402829959199,
+      "learning_rate": 1.5395228456836298e-05,
+      "loss": 1.084,
+      "step": 370
+    },
+    {
+      "epoch": 0.3922594142259414,
+      "grad_norm": 0.6799222607741628,
+      "learning_rate": 1.524055045821773e-05,
+      "loss": 1.0915,
+      "step": 375
+    },
+    {
+      "epoch": 0.39748953974895396,
+      "grad_norm": 0.6425506459433847,
+      "learning_rate": 1.5084124192902612e-05,
+      "loss": 1.0788,
+      "step": 380
+    },
+    {
+      "epoch": 0.4027196652719665,
+      "grad_norm": 0.5897131592885358,
+      "learning_rate": 1.4926001845262081e-05,
+      "loss": 1.0831,
+      "step": 385
+    },
+    {
+      "epoch": 0.40794979079497906,
+      "grad_norm": 0.5398425974996183,
+      "learning_rate": 1.4766236165486526e-05,
+      "loss": 1.0798,
+      "step": 390
+    },
+    {
+      "epoch": 0.4131799163179916,
+      "grad_norm": 0.562078925489584,
+      "learning_rate": 1.4604880451987895e-05,
+      "loss": 1.0763,
+      "step": 395
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "grad_norm": 0.5164729530296905,
+      "learning_rate": 1.4441988533619182e-05,
+      "loss": 1.0735,
+      "step": 400
+    },
+    {
+      "epoch": 0.4236401673640167,
+      "grad_norm": 0.5832567739541322,
+      "learning_rate": 1.4277614751716911e-05,
+      "loss": 1.0821,
+      "step": 405
+    },
+    {
+      "epoch": 0.42887029288702927,
+      "grad_norm": 0.5652212930411926,
+      "learning_rate": 1.4111813941972672e-05,
+      "loss": 1.0961,
+      "step": 410
+    },
+    {
+      "epoch": 0.4341004184100418,
+      "grad_norm": 0.6010203451282251,
+      "learning_rate": 1.3944641416139737e-05,
+      "loss": 1.0816,
+      "step": 415
+    },
+    {
+      "epoch": 0.4393305439330544,
+      "grad_norm": 0.5630993268496297,
+      "learning_rate": 1.3776152943580846e-05,
+      "loss": 1.0914,
+      "step": 420
+    },
+    {
+      "epoch": 0.4445606694560669,
+      "grad_norm": 0.5502230295962955,
+      "learning_rate": 1.3606404732663365e-05,
+      "loss": 1.0697,
+      "step": 425
+    },
+    {
+      "epoch": 0.4497907949790795,
+      "grad_norm": 0.6076500784198701,
+      "learning_rate": 1.3435453412007949e-05,
+      "loss": 1.068,
+      "step": 430
+    },
+    {
+      "epoch": 0.45502092050209203,
+      "grad_norm": 0.5106137967418161,
+      "learning_rate": 1.3263356011597045e-05,
+      "loss": 1.0758,
+      "step": 435
+    },
+    {
+      "epoch": 0.4602510460251046,
+      "grad_norm": 0.5461351720790467,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 1.0788,
+      "step": 440
+    },
+    {
+      "epoch": 0.46548117154811713,
+      "grad_norm": 0.5139632832447684,
+      "learning_rate": 1.2915952983967477e-05,
+      "loss": 1.0876,
+      "step": 445
+    },
+    {
+      "epoch": 0.4707112970711297,
+      "grad_norm": 0.551036425577886,
+      "learning_rate": 1.2740763251662585e-05,
+      "loss": 1.1003,
+      "step": 450
+    },
+    {
+      "epoch": 0.47594142259414224,
+      "grad_norm": 0.6151223670580791,
+      "learning_rate": 1.2564659190766788e-05,
+      "loss": 1.0764,
+      "step": 455
+    },
+    {
+      "epoch": 0.4811715481171548,
+      "grad_norm": 0.5552173831481524,
+      "learning_rate": 1.2387699550235419e-05,
+      "loss": 1.0858,
+      "step": 460
+    },
+    {
+      "epoch": 0.48640167364016734,
+      "grad_norm": 0.4951589610620449,
+      "learning_rate": 1.2209943364448298e-05,
+      "loss": 1.0584,
+      "step": 465
+    },
+    {
+      "epoch": 0.4916317991631799,
+      "grad_norm": 0.5475474226252068,
+      "learning_rate": 1.2031449933515625e-05,
+      "loss": 1.0687,
+      "step": 470
+    },
+    {
+      "epoch": 0.49686192468619245,
+      "grad_norm": 0.5486935313880071,
+      "learning_rate": 1.1852278803495267e-05,
+      "loss": 1.0573,
+      "step": 475
+    },
+    {
+      "epoch": 0.502092050209205,
+      "grad_norm": 0.6521150028759091,
+      "learning_rate": 1.1672489746527979e-05,
+      "loss": 1.0758,
+      "step": 480
+    },
+    {
+      "epoch": 0.5073221757322176,
+      "grad_norm": 0.6367797364958308,
+      "learning_rate": 1.1492142740897188e-05,
+      "loss": 1.0677,
+      "step": 485
+    },
+    {
+      "epoch": 0.5125523012552301,
+      "grad_norm": 0.5492169886313175,
+      "learning_rate": 1.1311297951020028e-05,
+      "loss": 1.0652,
+      "step": 490
+    },
+    {
+      "epoch": 0.5177824267782427,
+      "grad_norm": 0.7238966917771047,
+      "learning_rate": 1.1130015707376262e-05,
+      "loss": 1.0715,
+      "step": 495
+    },
+    {
+      "epoch": 0.5230125523012552,
+      "grad_norm": 0.5393341980142385,
+      "learning_rate": 1.0948356486381829e-05,
+      "loss": 1.0769,
+      "step": 500
+    },
+    {
+      "epoch": 0.5282426778242678,
+      "grad_norm": 0.5559622163553696,
+      "learning_rate": 1.0766380890213675e-05,
+      "loss": 1.0806,
+      "step": 505
+    },
+    {
+      "epoch": 0.5334728033472803,
+      "grad_norm": 0.5765233869935052,
+      "learning_rate": 1.0584149626592662e-05,
+      "loss": 1.056,
+      "step": 510
+    },
+    {
+      "epoch": 0.5387029288702929,
+      "grad_norm": 0.6006558028355857,
+      "learning_rate": 1.0401723488531238e-05,
+      "loss": 1.0682,
+      "step": 515
+    },
+    {
+      "epoch": 0.5439330543933054,
+      "grad_norm": 0.5396974095022056,
+      "learning_rate": 1.0219163334052682e-05,
+      "loss": 1.0817,
+      "step": 520
+    },
+    {
+      "epoch": 0.549163179916318,
+      "grad_norm": 0.6140554510099683,
+      "learning_rate": 1.003653006588863e-05,
+      "loss": 1.0757,
+      "step": 525
+    },
+    {
+      "epoch": 0.5543933054393305,
+      "grad_norm": 0.5087617662738954,
+      "learning_rate": 9.853884611161709e-06,
+      "loss": 1.047,
+      "step": 530
+    },
+    {
+      "epoch": 0.5596234309623431,
+      "grad_norm": 0.5112466701463289,
+      "learning_rate": 9.671287901060035e-06,
+      "loss": 1.064,
+      "step": 535
+    },
+    {
+      "epoch": 0.5648535564853556,
+      "grad_norm": 0.5633974067279639,
+      "learning_rate": 9.48880085051033e-06,
+      "loss": 1.0734,
+      "step": 540
+    },
+    {
+      "epoch": 0.5700836820083682,
+      "grad_norm": 0.5557468531733452,
+      "learning_rate": 9.306484337856497e-06,
+      "loss": 1.0777,
+      "step": 545
+    },
+    {
+      "epoch": 0.5753138075313807,
+      "grad_norm": 0.5271151067730627,
+      "learning_rate": 9.124399184550377e-06,
+      "loss": 1.0817,
+      "step": 550
+    },
+    {
+      "epoch": 0.5805439330543933,
+      "grad_norm": 0.5448740669834791,
+      "learning_rate": 8.94260613486149e-06,
+      "loss": 1.0757,
+      "step": 555
+    },
+    {
+      "epoch": 0.5857740585774058,
+      "grad_norm": 0.5155325719909827,
+      "learning_rate": 8.76116583561252e-06,
+      "loss": 1.0589,
+      "step": 560
+    },
+    {
+      "epoch": 0.5910041841004184,
+      "grad_norm": 0.5378614772721012,
+      "learning_rate": 8.580138815947336e-06,
+      "loss": 1.0651,
+      "step": 565
+    },
+    {
+      "epoch": 0.5962343096234309,
+      "grad_norm": 0.6326045695053654,
+      "learning_rate": 8.399585467138215e-06,
+      "loss": 1.0763,
+      "step": 570
+    },
+    {
+      "epoch": 0.6014644351464435,
+      "grad_norm": 0.6213989271242717,
+      "learning_rate": 8.219566022439128e-06,
+      "loss": 1.0792,
+      "step": 575
+    },
+    {
+      "epoch": 0.606694560669456,
+      "grad_norm": 0.5547238276934333,
+      "learning_rate": 8.040140536991688e-06,
+      "loss": 1.0767,
+      "step": 580
+    },
+    {
+      "epoch": 0.6119246861924686,
+      "grad_norm": 0.6071589445644577,
+      "learning_rate": 7.861368867790541e-06,
+      "loss": 1.0792,
+      "step": 585
+    },
+    {
+      "epoch": 0.6171548117154811,
+      "grad_norm": 0.5293708637565184,
+      "learning_rate": 7.683310653714857e-06,
+      "loss": 1.0723,
+      "step": 590
+    },
+    {
+      "epoch": 0.6223849372384938,
+      "grad_norm": 0.6845571370634647,
+      "learning_rate": 7.506025295632577e-06,
+      "loss": 1.0646,
+      "step": 595
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "grad_norm": 0.5398870120099946,
+      "learning_rate": 7.329571936584072e-06,
+      "loss": 1.0566,
+      "step": 600
+    },
+    {
+      "epoch": 0.6328451882845189,
+      "grad_norm": 0.5549729687939188,
+      "learning_rate": 7.154009442051813e-06,
+      "loss": 1.0562,
+      "step": 605
+    },
+    {
+      "epoch": 0.6380753138075314,
+      "grad_norm": 0.5739399359103224,
+      "learning_rate": 6.979396380322621e-06,
+      "loss": 1.0744,
+      "step": 610
+    },
+    {
+      "epoch": 0.643305439330544,
+      "grad_norm": 0.5432529949624418,
+      "learning_rate": 6.805791002949085e-06,
+      "loss": 1.0688,
+      "step": 615
+    },
+    {
+      "epoch": 0.6485355648535565,
+      "grad_norm": 0.5014458185904755,
+      "learning_rate": 6.63325122531663e-06,
+      "loss": 1.0541,
+      "step": 620
+    },
+    {
+      "epoch": 0.6537656903765691,
+      "grad_norm": 0.5197776266160257,
+      "learning_rate": 6.461834607322719e-06,
+      "loss": 1.0547,
+      "step": 625
+    },
+    {
+      "epoch": 0.6589958158995816,
+      "grad_norm": 0.5327187159562262,
+      "learning_rate": 6.291598334174685e-06,
+      "loss": 1.0572,
+      "step": 630
+    },
+    {
+      "epoch": 0.6642259414225942,
+      "grad_norm": 0.4979473409535948,
+      "learning_rate": 6.122599197312525e-06,
+      "loss": 1.0858,
+      "step": 635
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 0.5036476989509128,
+      "learning_rate": 5.954893575463064e-06,
+      "loss": 1.0637,
+      "step": 640
+    },
+    {
+      "epoch": 0.6746861924686193,
+      "grad_norm": 0.5228587745934291,
+      "learning_rate": 5.788537415831825e-06,
+      "loss": 1.055,
+      "step": 645
+    },
+    {
+      "epoch": 0.6799163179916318,
+      "grad_norm": 0.501253029293146,
+      "learning_rate": 5.623586215438813e-06,
+      "loss": 1.0641,
+      "step": 650
+    },
+    {
+      "epoch": 0.6851464435146444,
+      "grad_norm": 0.5050457318096031,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 1.0477,
+      "step": 655
+    },
+    {
+      "epoch": 0.6903765690376569,
+      "grad_norm": 0.5360440296456983,
+      "learning_rate": 5.298118318592316e-06,
+      "loss": 1.0654,
+      "step": 660
+    },
+    {
+      "epoch": 0.6956066945606695,
+      "grad_norm": 0.50207454781218,
+      "learning_rate": 5.137710199413182e-06,
+      "loss": 1.0685,
+      "step": 665
+    },
+    {
+      "epoch": 0.700836820083682,
+      "grad_norm": 0.558550005312336,
+      "learning_rate": 4.978924157799208e-06,
+      "loss": 1.06,
+      "step": 670
+    },
+    {
+      "epoch": 0.7060669456066946,
+      "grad_norm": 0.48483916829543067,
+      "learning_rate": 4.821813165351495e-06,
+      "loss": 1.0581,
+      "step": 675
+    },
+    {
+      "epoch": 0.7112970711297071,
+      "grad_norm": 0.49927440612478785,
+      "learning_rate": 4.666429634868651e-06,
+      "loss": 1.0851,
+      "step": 680
+    },
+    {
+      "epoch": 0.7165271966527197,
+      "grad_norm": 0.48707052941667256,
+      "learning_rate": 4.512825402861686e-06,
+      "loss": 1.0552,
+      "step": 685
+    },
+    {
+      "epoch": 0.7217573221757322,
+      "grad_norm": 0.5683679089994613,
+      "learning_rate": 4.361051712261173e-06,
+      "loss": 1.0596,
+      "step": 690
+    },
+    {
+      "epoch": 0.7269874476987448,
+      "grad_norm": 0.5340603274742174,
+      "learning_rate": 4.211159195322404e-06,
+      "loss": 1.0501,
+      "step": 695
+    },
+    {
+      "epoch": 0.7322175732217573,
+      "grad_norm": 0.5206965463042575,
+      "learning_rate": 4.063197856734295e-06,
+      "loss": 1.0783,
+      "step": 700
+    },
+    {
+      "epoch": 0.7374476987447699,
+      "grad_norm": 0.5029185927153098,
+      "learning_rate": 3.917217056937649e-06,
+      "loss": 1.0636,
+      "step": 705
+    },
+    {
+      "epoch": 0.7426778242677824,
+      "grad_norm": 0.5154613274025447,
+      "learning_rate": 3.773265495658309e-06,
+      "loss": 1.0655,
+      "step": 710
+    },
+    {
+      "epoch": 0.747907949790795,
+      "grad_norm": 0.4955231762184273,
+      "learning_rate": 3.6313911956607827e-06,
+      "loss": 1.0853,
+      "step": 715
+    },
+    {
+      "epoch": 0.7531380753138075,
+      "grad_norm": 0.513151209360854,
+      "learning_rate": 3.491641486727645e-06,
+      "loss": 1.0684,
+      "step": 720
+    },
+    {
+      "epoch": 0.7583682008368201,
+      "grad_norm": 0.5327297461286351,
+      "learning_rate": 3.354062989870166e-06,
+      "loss": 1.0504,
+      "step": 725
+    },
+    {
+      "epoch": 0.7635983263598326,
+      "grad_norm": 0.5121990852058834,
+      "learning_rate": 3.2187016017753714e-06,
+      "loss": 1.066,
+      "step": 730
+    },
+    {
+      "epoch": 0.7688284518828452,
+      "grad_norm": 0.5203341394376972,
+      "learning_rate": 3.085602479494735e-06,
+      "loss": 1.0602,
+      "step": 735
+    },
+    {
+      "epoch": 0.7740585774058577,
+      "grad_norm": 0.5005436050566201,
+      "learning_rate": 2.954810025379633e-06,
+      "loss": 1.071,
+      "step": 740
+    },
+    {
+      "epoch": 0.7792887029288703,
+      "grad_norm": 0.502346137505219,
+      "learning_rate": 2.826367872268543e-06,
+      "loss": 1.0517,
+      "step": 745
+    },
+    {
+      "epoch": 0.7845188284518828,
+      "grad_norm": 0.5272314894368499,
+      "learning_rate": 2.700318868930977e-06,
+      "loss": 1.0683,
+      "step": 750
+    },
+    {
+      "epoch": 0.7897489539748954,
+      "grad_norm": 0.5292107880965233,
+      "learning_rate": 2.576705065772985e-06,
+      "loss": 1.0543,
+      "step": 755
+    },
+    {
+      "epoch": 0.7949790794979079,
+      "grad_norm": 0.4869311193186611,
+      "learning_rate": 2.455567700808974e-06,
+      "loss": 1.0437,
+      "step": 760
+    },
+    {
+      "epoch": 0.8002092050209205,
+      "grad_norm": 0.5199956099665775,
+      "learning_rate": 2.3369471859045558e-06,
+      "loss": 1.0637,
+      "step": 765
+    },
+    {
+      "epoch": 0.805439330543933,
+      "grad_norm": 0.5041918826572614,
+      "learning_rate": 2.2208830932950175e-06,
+      "loss": 1.0557,
+      "step": 770
+    },
+    {
+      "epoch": 0.8106694560669456,
+      "grad_norm": 0.4992808348206519,
+      "learning_rate": 2.107414142383857e-06,
+      "loss": 1.0636,
+      "step": 775
+    },
+    {
+      "epoch": 0.8158995815899581,
+      "grad_norm": 0.5351058053191133,
+      "learning_rate": 1.996578186825876e-06,
+      "loss": 1.0652,
+      "step": 780
+    },
+    {
+      "epoch": 0.8211297071129707,
+      "grad_norm": 0.5071325680716784,
+      "learning_rate": 1.8884122018990292e-06,
+      "loss": 1.0575,
+      "step": 785
+    },
+    {
+      "epoch": 0.8263598326359832,
+      "grad_norm": 0.5070573073765244,
+      "learning_rate": 1.7829522721693738e-06,
+      "loss": 1.0476,
+      "step": 790
+    },
+    {
+      "epoch": 0.8315899581589958,
+      "grad_norm": 0.5283232962970443,
+      "learning_rate": 1.680233579453101e-06,
+      "loss": 1.0604,
+      "step": 795
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 0.500454736041983,
+      "learning_rate": 1.5802903910797584e-06,
+      "loss": 1.0623,
+      "step": 800
+    },
+    {
+      "epoch": 0.8420502092050209,
+      "grad_norm": 0.4991364513451987,
+      "learning_rate": 1.483156048460561e-06,
+      "loss": 1.0702,
+      "step": 805
+    },
+    {
+      "epoch": 0.8472803347280334,
+      "grad_norm": 0.5156696669086099,
+      "learning_rate": 1.3888629559655497e-06,
+      "loss": 1.065,
+      "step": 810
+    },
+    {
+      "epoch": 0.852510460251046,
+      "grad_norm": 0.495859957636518,
+      "learning_rate": 1.2974425701133941e-06,
+      "loss": 1.0519,
+      "step": 815
+    },
+    {
+      "epoch": 0.8577405857740585,
+      "grad_norm": 0.506274711437886,
+      "learning_rate": 1.2089253890773789e-06,
+      "loss": 1.0592,
+      "step": 820
+    },
+    {
+      "epoch": 0.8629707112970711,
+      "grad_norm": 0.49088086705348327,
+      "learning_rate": 1.1233409425110952e-06,
+      "loss": 1.0562,
+      "step": 825
+    },
+    {
+      "epoch": 0.8682008368200836,
+      "grad_norm": 0.4880905900442435,
+      "learning_rate": 1.0407177816972558e-06,
+      "loss": 1.0469,
+      "step": 830
+    },
+    {
+      "epoch": 0.8734309623430963,
+      "grad_norm": 0.5013767019673636,
+      "learning_rate": 9.610834700228654e-07,
+      "loss": 1.0776,
+      "step": 835
+    },
+    {
+      "epoch": 0.8786610878661087,
+      "grad_norm": 0.5040841468024664,
+      "learning_rate": 8.844645737839874e-07,
+      "loss": 1.0568,
+      "step": 840
+    },
+    {
+      "epoch": 0.8838912133891214,
+      "grad_norm": 0.4758757276308106,
+      "learning_rate": 8.108866533231252e-07,
+      "loss": 1.0427,
+      "step": 845
+    },
+    {
+      "epoch": 0.8891213389121339,
+      "grad_norm": 0.5126814725002861,
+      "learning_rate": 7.403742545021986e-07,
+      "loss": 1.0559,
+      "step": 850
+    },
+    {
+      "epoch": 0.8943514644351465,
+      "grad_norm": 0.4987765646224313,
+      "learning_rate": 6.729509005139634e-07,
+      "loss": 1.0415,
+      "step": 855
+    },
+    {
+      "epoch": 0.899581589958159,
+      "grad_norm": 0.5014454129425115,
+      "learning_rate": 6.086390840345758e-07,
+      "loss": 1.05,
+      "step": 860
+    },
+    {
+      "epoch": 0.9048117154811716,
+      "grad_norm": 0.48975109580877996,
+      "learning_rate": 5.474602597199607e-07,
+      "loss": 1.0704,
+      "step": 865
+    },
+    {
+      "epoch": 0.9100418410041841,
+      "grad_norm": 0.4994701501642807,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 1.0691,
+      "step": 870
+    },
+    {
+      "epoch": 0.9152719665271967,
+      "grad_norm": 0.521731055642247,
+      "learning_rate": 4.34582173512168e-07,
+      "loss": 1.0677,
+      "step": 875
+    },
+    {
+      "epoch": 0.9205020920502092,
+      "grad_norm": 0.4885441287488048,
+      "learning_rate": 3.8292056815916965e-07,
+      "loss": 1.059,
+      "step": 880
+    },
+    {
+      "epoch": 0.9257322175732218,
+      "grad_norm": 0.5068844610447545,
+      "learning_rate": 3.344672554889428e-07,
+      "loss": 1.0691,
+      "step": 885
+    },
+    {
+      "epoch": 0.9309623430962343,
+      "grad_norm": 0.49577008576644055,
+      "learning_rate": 2.8923839970285473e-07,
+      "loss": 1.0592,
+      "step": 890
+    },
+    {
+      "epoch": 0.9361924686192469,
+      "grad_norm": 0.4907561902253791,
+      "learning_rate": 2.472490893117274e-07,
+      "loss": 1.0458,
+      "step": 895
+    },
+    {
+      "epoch": 0.9414225941422594,
+      "grad_norm": 0.5000871009012277,
+      "learning_rate": 2.0851333210225032e-07,
+      "loss": 1.0608,
+      "step": 900
+    },
+    {
+      "epoch": 0.946652719665272,
+      "grad_norm": 0.48247289512404495,
+      "learning_rate": 1.730440504639408e-07,
+      "loss": 1.058,
+      "step": 905
+    },
+    {
+      "epoch": 0.9518828451882845,
+      "grad_norm": 0.48826128008832265,
+      "learning_rate": 1.408530770781813e-07,
+      "loss": 1.0526,
+      "step": 910
+    },
+    {
+      "epoch": 0.9571129707112971,
+      "grad_norm": 0.4969532853804826,
+      "learning_rate": 1.1195115097079268e-07,
+      "loss": 1.0685,
+      "step": 915
+    },
+    {
+      "epoch": 0.9623430962343096,
+      "grad_norm": 0.48920579432423383,
+      "learning_rate": 8.634791392946429e-08,
+      "loss": 1.0676,
+      "step": 920
+    },
+    {
+      "epoch": 0.9675732217573222,
+      "grad_norm": 0.49070804064035406,
+      "learning_rate": 6.405190728721033e-08,
+      "loss": 1.0455,
+      "step": 925
+    },
+    {
+      "epoch": 0.9728033472803347,
+      "grad_norm": 0.47721070672447036,
+      "learning_rate": 4.5070569072952485e-08,
+      "loss": 1.061,
+      "step": 930
+    },
+    {
+      "epoch": 0.9780334728033473,
+      "grad_norm": 0.4960618241854113,
+      "learning_rate": 2.9410231530168087e-08,
+      "loss": 1.0499,
+      "step": 935
+    },
+    {
+      "epoch": 0.9832635983263598,
+      "grad_norm": 0.4727473862892527,
+      "learning_rate": 1.7076119004429958e-08,
+      "loss": 1.0763,
+      "step": 940
+    },
+    {
+      "epoch": 0.9884937238493724,
+      "grad_norm": 0.4932911494908516,
+      "learning_rate": 8.072346200544979e-09,
+      "loss": 1.0672,
+      "step": 945
+    },
+    {
+      "epoch": 0.9937238493723849,
+      "grad_norm": 0.48937555835484964,
+      "learning_rate": 2.401916809872118e-09,
+      "loss": 1.0629,
+      "step": 950
+    },
+    {
+      "epoch": 0.9989539748953975,
+      "grad_norm": 0.47678060880513334,
+      "learning_rate": 6.672250828620996e-11,
+      "loss": 1.0626,
+      "step": 955
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0645579099655151,
+      "eval_runtime": 287.2685,
+      "eval_samples_per_second": 47.13,
+      "eval_steps_per_second": 0.738,
+      "step": 956
+    },
+    {
+      "epoch": 1.0,
+      "step": 956,
+      "total_flos": 500925122740224.0,
+      "train_loss": 1.0766646904426638,
+      "train_runtime": 10839.8443,
+      "train_samples_per_second": 11.286,
+      "train_steps_per_second": 0.088
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 956,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 500925122740224.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}