Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+license: other
+base_model: google/gemma-7b
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: gemma-7b-sft-full-openhermes-v0
+  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. -->
+
+# gemma-7b-sft-full-openhermes-v0
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- 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: 4
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.99,
+    "train_loss": 1.3370767467730753,
+    "train_runtime": 16871.6289,
+    "train_samples": 1000551,
+    "train_samples_per_second": 44.965,
+    "train_steps_per_second": 0.088
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d922f7d366a1d228bd235b61caaad450f2d1da4dee2e1df7003f419b3fc029
+size 4995496656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb106e7327893d496fc1cbc360528d9b8e3940e6cf737b2c82f6f70cfad5529
+size 4982953168

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83566c307d9a6a80bdc7962e96716ed39c9a472199ed0358a5a5197067e424d1
+size 4982953200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c4bfc291e031bfbebf759e14e33555147c3675ca16fe8e8c1a2edc63e53d9e
+size 2113988336

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 17075361792
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-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.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.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-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.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.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/Feb29_23-32-13_ip-26-0-172-73/events.out.tfevents.1709250419.ip-26-0-172-73.1092806.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5021b01f55c2fc9207a429589dd9a135492df647d6d8b4f39daad487f68cee34
+size 67645

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.99,
+    "train_loss": 1.3370767467730753,
+    "train_runtime": 16871.6289,
+    "train_samples": 1000551,
+    "train_samples_per_second": 44.965,
+    "train_steps_per_second": 0.088
+}

trainer_state.json

@@ -0,0 +1,2109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9946018893387314,
+  "eval_steps": 500,
+  "global_step": 1480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 5172.492790419565,
+      "learning_rate": 6.756756756756757e-08,
+      "loss": 16.2669,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4320.729018206391,
+      "learning_rate": 3.378378378378379e-07,
+      "loss": 15.6969,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 488.5525501221014,
+      "learning_rate": 6.756756756756758e-07,
+      "loss": 12.0521,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 289.24969349599496,
+      "learning_rate": 1.0135135135135136e-06,
+      "loss": 9.2401,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 126.31621322294927,
+      "learning_rate": 1.3513513513513515e-06,
+      "loss": 7.9461,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 71.89469484569835,
+      "learning_rate": 1.6891891891891894e-06,
+      "loss": 7.2699,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 103.51185464247453,
+      "learning_rate": 2.0270270270270273e-06,
+      "loss": 6.9743,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 47.053277376605855,
+      "learning_rate": 2.364864864864865e-06,
+      "loss": 6.7672,
+      "step": 35
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 49.644931428662844,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 6.5877,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 35.00554720125077,
+      "learning_rate": 3.040540540540541e-06,
+      "loss": 6.4428,
+      "step": 45
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 33.14232577992853,
+      "learning_rate": 3.3783783783783788e-06,
+      "loss": 6.2824,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 35.40029424621722,
+      "learning_rate": 3.7162162162162162e-06,
+      "loss": 6.0897,
+      "step": 55
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 40.23393814067933,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 5.8782,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 55.427875975850924,
+      "learning_rate": 4.391891891891892e-06,
+      "loss": 5.5613,
+      "step": 65
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 96.7762735033588,
+      "learning_rate": 4.72972972972973e-06,
+      "loss": 4.8791,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 88.58451501801524,
+      "learning_rate": 5.067567567567568e-06,
+      "loss": 3.2214,
+      "step": 75
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 22.221611879190654,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 1.7005,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 14.404618337150714,
+      "learning_rate": 5.743243243243244e-06,
+      "loss": 1.55,
+      "step": 85
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 14.657001400244646,
+      "learning_rate": 6.081081081081082e-06,
+      "loss": 1.5228,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.295090886362698,
+      "learning_rate": 6.41891891891892e-06,
+      "loss": 1.4585,
+      "step": 95
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 5.24494216356606,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 1.4326,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.440473193782044,
+      "learning_rate": 7.0945945945945946e-06,
+      "loss": 1.3865,
+      "step": 105
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.8147339321014,
+      "learning_rate": 7.4324324324324324e-06,
+      "loss": 1.3655,
+      "step": 110
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.442428248209423,
+      "learning_rate": 7.77027027027027e-06,
+      "loss": 1.3394,
+      "step": 115
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.78770666444895,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 1.3354,
+      "step": 120
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 7.28821915344424,
+      "learning_rate": 8.445945945945948e-06,
+      "loss": 1.3065,
+      "step": 125
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 6.492851696765312,
+      "learning_rate": 8.783783783783785e-06,
+      "loss": 1.2902,
+      "step": 130
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.1773499503060454,
+      "learning_rate": 9.121621621621622e-06,
+      "loss": 1.2769,
+      "step": 135
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 2.9874866899468238,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 1.266,
+      "step": 140
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 9.94355578144089,
+      "learning_rate": 9.797297297297298e-06,
+      "loss": 1.2624,
+      "step": 145
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.0193035270709077,
+      "learning_rate": 9.999944372378571e-06,
+      "loss": 1.2452,
+      "step": 150
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.139515176735739,
+      "learning_rate": 9.999318575852451e-06,
+      "loss": 1.2341,
+      "step": 155
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.156285780849088,
+      "learning_rate": 9.99799753559161e-06,
+      "loss": 1.2106,
+      "step": 160
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.924005437849429,
+      "learning_rate": 9.995981435310078e-06,
+      "loss": 1.221,
+      "step": 165
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.165437348359594,
+      "learning_rate": 9.993270555382283e-06,
+      "loss": 1.2105,
+      "step": 170
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.342058479511419,
+      "learning_rate": 9.989865272804064e-06,
+      "loss": 1.2067,
+      "step": 175
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 2.6456490809423467,
+      "learning_rate": 9.985766061140233e-06,
+      "loss": 1.196,
+      "step": 180
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.465974100807255,
+      "learning_rate": 9.980973490458728e-06,
+      "loss": 1.1881,
+      "step": 185
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 2.808324774416455,
+      "learning_rate": 9.97548822725133e-06,
+      "loss": 1.1852,
+      "step": 190
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 2.834201027736285,
+      "learning_rate": 9.969311034340977e-06,
+      "loss": 1.1839,
+      "step": 195
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.502666083698819,
+      "learning_rate": 9.962442770775675e-06,
+      "loss": 1.1648,
+      "step": 200
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.780648711057674,
+      "learning_rate": 9.954884391709043e-06,
+      "loss": 1.1619,
+      "step": 205
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.498462904619314,
+      "learning_rate": 9.946636948267468e-06,
+      "loss": 1.1483,
+      "step": 210
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.0642292894829213,
+      "learning_rate": 9.937701587403941e-06,
+      "loss": 1.1412,
+      "step": 215
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.727096769429053,
+      "learning_rate": 9.928079551738542e-06,
+      "loss": 1.1446,
+      "step": 220
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 2.206091891548497,
+      "learning_rate": 9.91777217938564e-06,
+      "loss": 1.1354,
+      "step": 225
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.242676582016566,
+      "learning_rate": 9.906780903767799e-06,
+      "loss": 1.137,
+      "step": 230
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 2.5806553543973396,
+      "learning_rate": 9.895107253416434e-06,
+      "loss": 1.134,
+      "step": 235
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.305243444378998,
+      "learning_rate": 9.882752851759247e-06,
+      "loss": 1.1411,
+      "step": 240
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.911161316221469,
+      "learning_rate": 9.869719416894462e-06,
+      "loss": 1.1144,
+      "step": 245
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 4.2780174060875025,
+      "learning_rate": 9.856008761351882e-06,
+      "loss": 1.109,
+      "step": 250
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 2.3947970947073425,
+      "learning_rate": 9.841622791840839e-06,
+      "loss": 1.1143,
+      "step": 255
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.2640331483926595,
+      "learning_rate": 9.826563508985017e-06,
+      "loss": 1.1158,
+      "step": 260
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.8813671261206033,
+      "learning_rate": 9.810833007044247e-06,
+      "loss": 1.1038,
+      "step": 265
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.7947375217746502,
+      "learning_rate": 9.794433473623249e-06,
+      "loss": 1.1063,
+      "step": 270
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.239529292108957,
+      "learning_rate": 9.777367189367412e-06,
+      "loss": 1.1034,
+      "step": 275
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.8141790841216405,
+      "learning_rate": 9.759636527645633e-06,
+      "loss": 1.094,
+      "step": 280
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.3580672092709722,
+      "learning_rate": 9.74124395422025e-06,
+      "loss": 1.0989,
+      "step": 285
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.116597962727994,
+      "learning_rate": 9.722192026904145e-06,
+      "loss": 1.0927,
+      "step": 290
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 8.108195152123194,
+      "learning_rate": 9.702483395205023e-06,
+      "loss": 1.0785,
+      "step": 295
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 2.4053331358570564,
+      "learning_rate": 9.682120799956961e-06,
+      "loss": 1.0939,
+      "step": 300
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.036700462595253,
+      "learning_rate": 9.661107072939244e-06,
+      "loss": 1.0957,
+      "step": 305
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.9808850854861142,
+      "learning_rate": 9.639445136482549e-06,
+      "loss": 1.0718,
+      "step": 310
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.7199945370090353,
+      "learning_rate": 9.61713800306255e-06,
+      "loss": 1.0908,
+      "step": 315
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.416121355561205,
+      "learning_rate": 9.594188774880981e-06,
+      "loss": 1.0683,
+      "step": 320
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.6221732481646085,
+      "learning_rate": 9.570600643434217e-06,
+      "loss": 1.0812,
+      "step": 325
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.0081014994296655,
+      "learning_rate": 9.546376889069442e-06,
+      "loss": 1.0672,
+      "step": 330
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.928715018400264,
+      "learning_rate": 9.521520880528453e-06,
+      "loss": 1.0696,
+      "step": 335
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.510557690197284,
+      "learning_rate": 9.496036074479184e-06,
+      "loss": 1.0748,
+      "step": 340
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 2.1531622758856206,
+      "learning_rate": 9.46992601503499e-06,
+      "loss": 1.072,
+      "step": 345
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.5600473945363453,
+      "learning_rate": 9.44319433326178e-06,
+      "loss": 1.0674,
+      "step": 350
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.9316399234342516,
+      "learning_rate": 9.415844746673047e-06,
+      "loss": 1.0715,
+      "step": 355
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 3.1641780363359624,
+      "learning_rate": 9.387881058712888e-06,
+      "loss": 1.0607,
+      "step": 360
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 2.5389167608685477,
+      "learning_rate": 9.359307158227067e-06,
+      "loss": 1.0571,
+      "step": 365
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.209876430466923,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.0656,
+      "step": 370
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 2.0112001074770856,
+      "learning_rate": 9.300344698813124e-06,
+      "loss": 1.0473,
+      "step": 375
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 2.3621990368530037,
+      "learning_rate": 9.269964339658605e-06,
+      "loss": 1.0479,
+      "step": 380
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.9555447312938368,
+      "learning_rate": 9.238990166385304e-06,
+      "loss": 1.0481,
+      "step": 385
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 1.9979169106404795,
+      "learning_rate": 9.207426486500252e-06,
+      "loss": 1.0489,
+      "step": 390
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 2.7432607054958145,
+      "learning_rate": 9.175277689491804e-06,
+      "loss": 1.0553,
+      "step": 395
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.9273849661076683,
+      "learning_rate": 9.142548246219212e-06,
+      "loss": 1.0398,
+      "step": 400
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 2.0451128390125235,
+      "learning_rate": 9.109242708290864e-06,
+      "loss": 1.0417,
+      "step": 405
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 4.496881794147535,
+      "learning_rate": 9.075365707431311e-06,
+      "loss": 1.0348,
+      "step": 410
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.7112676473960327,
+      "learning_rate": 9.040921954837139e-06,
+      "loss": 1.0475,
+      "step": 415
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 1.7843942716305177,
+      "learning_rate": 9.005916240521788e-06,
+      "loss": 1.0435,
+      "step": 420
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 3.688231246483607,
+      "learning_rate": 8.97035343264943e-06,
+      "loss": 1.0316,
+      "step": 425
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.0133406140771672,
+      "learning_rate": 8.93423847685795e-06,
+      "loss": 1.0363,
+      "step": 430
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 3.65260559397669,
+      "learning_rate": 8.89757639557118e-06,
+      "loss": 1.0295,
+      "step": 435
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 2.0183294533927083,
+      "learning_rate": 8.860372287300432e-06,
+      "loss": 1.033,
+      "step": 440
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.8479490054275187,
+      "learning_rate": 8.822631325935463e-06,
+      "loss": 1.0472,
+      "step": 445
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 2.114757094329874,
+      "learning_rate": 8.78435876002496e-06,
+      "loss": 1.0295,
+      "step": 450
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 1.9082626009926926,
+      "learning_rate": 8.745559912046625e-06,
+      "loss": 1.033,
+      "step": 455
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.730783726030946,
+      "learning_rate": 8.706240177667003e-06,
+      "loss": 1.0385,
+      "step": 460
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 2.5320093097552614,
+      "learning_rate": 8.666405024991105e-06,
+      "loss": 1.0375,
+      "step": 465
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 3.400617294472977,
+      "learning_rate": 8.626059993801988e-06,
+      "loss": 1.0253,
+      "step": 470
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.7269138208449157,
+      "learning_rate": 8.585210694790333e-06,
+      "loss": 1.0191,
+      "step": 475
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.943069131491427,
+      "learning_rate": 8.543862808774193e-06,
+      "loss": 1.021,
+      "step": 480
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 1.8339225500743817,
+      "learning_rate": 8.502022085908963e-06,
+      "loss": 1.0164,
+      "step": 485
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.137449239722819,
+      "learning_rate": 8.459694344887732e-06,
+      "loss": 1.0367,
+      "step": 490
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 2.581812285540177,
+      "learning_rate": 8.416885472132077e-06,
+      "loss": 1.0283,
+      "step": 495
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.8160848127506812,
+      "learning_rate": 8.373601420973464e-06,
+      "loss": 1.017,
+      "step": 500
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 2.346923224689188,
+      "learning_rate": 8.329848210825322e-06,
+      "loss": 1.0237,
+      "step": 505
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 2.024470398972999,
+      "learning_rate": 8.285631926345943e-06,
+      "loss": 1.028,
+      "step": 510
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.382418457888275,
+      "learning_rate": 8.240958716592304e-06,
+      "loss": 1.0103,
+      "step": 515
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.754061139243149,
+      "learning_rate": 8.195834794164925e-06,
+      "loss": 1.0179,
+      "step": 520
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.6884398821609177,
+      "learning_rate": 8.150266434343904e-06,
+      "loss": 1.0218,
+      "step": 525
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.8408143701714872,
+      "learning_rate": 8.104259974216219e-06,
+      "loss": 1.0109,
+      "step": 530
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.8898424458167393,
+      "learning_rate": 8.057821811794457e-06,
+      "loss": 1.0113,
+      "step": 535
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 2.0040005987182923,
+      "learning_rate": 8.010958405127048e-06,
+      "loss": 1.0205,
+      "step": 540
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.8031516449231006,
+      "learning_rate": 7.963676271400158e-06,
+      "loss": 1.0102,
+      "step": 545
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.0776879759963798,
+      "learning_rate": 7.915981986031367e-06,
+      "loss": 1.0089,
+      "step": 550
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.4545184199390695,
+      "learning_rate": 7.86788218175523e-06,
+      "loss": 1.021,
+      "step": 555
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 1.9664285212166526,
+      "learning_rate": 7.819383547700889e-06,
+      "loss": 1.008,
+      "step": 560
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.7035372351508404,
+      "learning_rate": 7.770492828461824e-06,
+      "loss": 1.013,
+      "step": 565
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 2.737641626508961,
+      "learning_rate": 7.721216823157896e-06,
+      "loss": 1.0125,
+      "step": 570
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.7709332048302728,
+      "learning_rate": 7.671562384489819e-06,
+      "loss": 1.0197,
+      "step": 575
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.592514417019854,
+      "learning_rate": 7.621536417786159e-06,
+      "loss": 1.006,
+      "step": 580
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 1.8116371870435586,
+      "learning_rate": 7.571145880043036e-06,
+      "loss": 1.0021,
+      "step": 585
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 2.742484137764987,
+      "learning_rate": 7.520397778956623e-06,
+      "loss": 0.9942,
+      "step": 590
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 1.8390385024848412,
+      "learning_rate": 7.469299171948608e-06,
+      "loss": 1.0085,
+      "step": 595
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.8627501795637935,
+      "learning_rate": 7.417857165184723e-06,
+      "loss": 1.0065,
+      "step": 600
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 1.8662148392820241,
+      "learning_rate": 7.366078912586523e-06,
+      "loss": 1.0069,
+      "step": 605
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.9898176799731553,
+      "learning_rate": 7.313971614836496e-06,
+      "loss": 1.0075,
+      "step": 610
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 1.6374351854744644,
+      "learning_rate": 7.261542518376677e-06,
+      "loss": 0.9954,
+      "step": 615
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 2.3713553804160554,
+      "learning_rate": 7.208798914400916e-06,
+      "loss": 1.0041,
+      "step": 620
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 2.43390000834423,
+      "learning_rate": 7.155748137840892e-06,
+      "loss": 1.0043,
+      "step": 625
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.9046613363144396,
+      "learning_rate": 7.102397566346073e-06,
+      "loss": 0.9984,
+      "step": 630
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.667190267378518,
+      "learning_rate": 7.048754619257716e-06,
+      "loss": 1.0029,
+      "step": 635
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.638081070696857,
+      "learning_rate": 6.994826756577082e-06,
+      "loss": 1.0032,
+      "step": 640
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 2.2506476935835407,
+      "learning_rate": 6.940621477927988e-06,
+      "loss": 1.0023,
+      "step": 645
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.0559944356090116,
+      "learning_rate": 6.88614632151385e-06,
+      "loss": 1.0036,
+      "step": 650
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.7722705407021138,
+      "learning_rate": 6.831408863069364e-06,
+      "loss": 0.9981,
+      "step": 655
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 1.510560677423063,
+      "learning_rate": 6.7764167148069695e-06,
+      "loss": 0.9845,
+      "step": 660
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.6159682830961077,
+      "learning_rate": 6.721177524358226e-06,
+      "loss": 1.0014,
+      "step": 665
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 2.547134856734226,
+      "learning_rate": 6.665698973710289e-06,
+      "loss": 0.9955,
+      "step": 670
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 2.6937900779118524,
+      "learning_rate": 6.609988778137582e-06,
+      "loss": 0.9856,
+      "step": 675
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 2.0660116621981937,
+      "learning_rate": 6.554054685128857e-06,
+      "loss": 0.987,
+      "step": 680
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 1.7256065453185816,
+      "learning_rate": 6.497904473309766e-06,
+      "loss": 0.9907,
+      "step": 685
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 1.9848736194116567,
+      "learning_rate": 6.44154595136111e-06,
+      "loss": 0.9938,
+      "step": 690
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 2.226796297825019,
+      "learning_rate": 6.384986956932897e-06,
+      "loss": 0.9891,
+      "step": 695
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.7756206272082837,
+      "learning_rate": 6.328235355554382e-06,
+      "loss": 0.989,
+      "step": 700
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 2.055029436503266,
+      "learning_rate": 6.271299039540228e-06,
+      "loss": 0.9854,
+      "step": 705
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.1572868944232733,
+      "learning_rate": 6.214185926892936e-06,
+      "loss": 0.991,
+      "step": 710
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 1.705088008506106,
+      "learning_rate": 6.156903960201709e-06,
+      "loss": 0.99,
+      "step": 715
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 2.394966448163764,
+      "learning_rate": 6.099461105537889e-06,
+      "loss": 0.9866,
+      "step": 720
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 2.016768798949277,
+      "learning_rate": 6.041865351347146e-06,
+      "loss": 0.9919,
+      "step": 725
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.8476093711911672,
+      "learning_rate": 5.984124707338528e-06,
+      "loss": 0.9932,
+      "step": 730
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.9896940215311267,
+      "learning_rate": 5.926247203370583e-06,
+      "loss": 0.9958,
+      "step": 735
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.5258042306430637,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.9915,
+      "step": 740
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 2.300171514270174,
+      "learning_rate": 5.810113829035544e-06,
+      "loss": 0.9681,
+      "step": 745
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 1.9721303641863295,
+      "learning_rate": 5.751874109069685e-06,
+      "loss": 0.9597,
+      "step": 750
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 2.2390559024844086,
+      "learning_rate": 5.693529827700967e-06,
+      "loss": 0.9578,
+      "step": 755
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 2.0408626045391167,
+      "learning_rate": 5.635089098734394e-06,
+      "loss": 0.9759,
+      "step": 760
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 2.3474388556665353,
+      "learning_rate": 5.576560049387717e-06,
+      "loss": 0.9692,
+      "step": 765
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.577362362698819,
+      "learning_rate": 5.517950819161196e-06,
+      "loss": 0.9693,
+      "step": 770
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.798565847037349,
+      "learning_rate": 5.459269558705667e-06,
+      "loss": 0.9583,
+      "step": 775
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 1.9304589279981041,
+      "learning_rate": 5.400524428689035e-06,
+      "loss": 0.9717,
+      "step": 780
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 1.721891020322892,
+      "learning_rate": 5.341723598661409e-06,
+      "loss": 0.9639,
+      "step": 785
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 1.7487840479558292,
+      "learning_rate": 5.282875245918963e-06,
+      "loss": 0.9705,
+      "step": 790
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 1.8716448470255413,
+      "learning_rate": 5.2239875543667465e-06,
+      "loss": 0.9714,
+      "step": 795
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.5692767824863278,
+      "learning_rate": 5.165068713380568e-06,
+      "loss": 0.9728,
+      "step": 800
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 1.6666960593346472,
+      "learning_rate": 5.106126916668118e-06,
+      "loss": 0.9634,
+      "step": 805
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 1.6602656394819693,
+      "learning_rate": 5.047170361129484e-06,
+      "loss": 0.9665,
+      "step": 810
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.5606922426383971,
+      "learning_rate": 4.988207245717232e-06,
+      "loss": 0.9615,
+      "step": 815
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 1.8903502303369755,
+      "learning_rate": 4.929245770296191e-06,
+      "loss": 0.9517,
+      "step": 820
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 2.0904161072997076,
+      "learning_rate": 4.870294134503123e-06,
+      "loss": 0.9578,
+      "step": 825
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.8320825036562747,
+      "learning_rate": 4.811360536606416e-06,
+      "loss": 0.9695,
+      "step": 830
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 1.9133665529378556,
+      "learning_rate": 4.752453172365966e-06,
+      "loss": 0.9585,
+      "step": 835
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 1.8758941343800197,
+      "learning_rate": 4.69358023389342e-06,
+      "loss": 0.9608,
+      "step": 840
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 2.133289277786595,
+      "learning_rate": 4.634749908512907e-06,
+      "loss": 0.9619,
+      "step": 845
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 1.8131410749776957,
+      "learning_rate": 4.575970377622456e-06,
+      "loss": 0.9623,
+      "step": 850
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 2.0361433234498514,
+      "learning_rate": 4.517249815556219e-06,
+      "loss": 0.9572,
+      "step": 855
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.8450224454341402,
+      "learning_rate": 4.458596388447691e-06,
+      "loss": 0.9588,
+      "step": 860
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 1.5855628731202065,
+      "learning_rate": 4.400018253094065e-06,
+      "loss": 0.9544,
+      "step": 865
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 1.7015227109739095,
+      "learning_rate": 4.341523555821882e-06,
+      "loss": 0.9629,
+      "step": 870
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.533925044445312,
+      "learning_rate": 4.283120431354137e-06,
+      "loss": 0.9571,
+      "step": 875
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.5138597264361546,
+      "learning_rate": 4.224817001679011e-06,
+      "loss": 0.9642,
+      "step": 880
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 2.3034815379141795,
+      "learning_rate": 4.1666213749203545e-06,
+      "loss": 0.9562,
+      "step": 885
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.6982866609702905,
+      "learning_rate": 4.1085416442101205e-06,
+      "loss": 0.9628,
+      "step": 890
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 1.8780386107869884,
+      "learning_rate": 4.050585886562858e-06,
+      "loss": 0.9549,
+      "step": 895
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 1.683670163601615,
+      "learning_rate": 3.992762161752474e-06,
+      "loss": 0.9615,
+      "step": 900
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 2.001515746557216,
+      "learning_rate": 3.935078511191368e-06,
+      "loss": 0.9617,
+      "step": 905
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 2.4485180814449925,
+      "learning_rate": 3.877542956812137e-06,
+      "loss": 0.9599,
+      "step": 910
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 2.2535920157325373,
+      "learning_rate": 3.820163499951984e-06,
+      "loss": 0.9485,
+      "step": 915
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.6920809388339335,
+      "learning_rate": 3.7629481202399886e-06,
+      "loss": 0.9464,
+      "step": 920
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.9251860711568731,
+      "learning_rate": 3.705904774487396e-06,
+      "loss": 0.9565,
+      "step": 925
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 1.6963234663767837,
+      "learning_rate": 3.64904139558109e-06,
+      "loss": 0.9657,
+      "step": 930
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 1.723192642702987,
+      "learning_rate": 3.5923658913803726e-06,
+      "loss": 0.9545,
+      "step": 935
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 1.857223252079437,
+      "learning_rate": 3.5358861436172487e-06,
+      "loss": 0.951,
+      "step": 940
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 1.9463652794821473,
+      "learning_rate": 3.47961000680032e-06,
+      "loss": 0.9545,
+      "step": 945
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.6275095264739814,
+      "learning_rate": 3.4235453071224882e-06,
+      "loss": 0.956,
+      "step": 950
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 2.132166681197278,
+      "learning_rate": 3.3676998413725726e-06,
+      "loss": 0.9597,
+      "step": 955
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 2.389342012426533,
+      "learning_rate": 3.3120813758510385e-06,
+      "loss": 0.9444,
+      "step": 960
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 2.1360938817924424,
+      "learning_rate": 3.2566976452899507e-06,
+      "loss": 0.9488,
+      "step": 965
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 2.1039499268212323,
+      "learning_rate": 3.2015563517773214e-06,
+      "loss": 0.953,
+      "step": 970
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 2.310285226796488,
+      "learning_rate": 3.1466651636860025e-06,
+      "loss": 0.9617,
+      "step": 975
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 2.0128464455024817,
+      "learning_rate": 3.0920317146072577e-06,
+      "loss": 0.9516,
+      "step": 980
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 1.4735182975439758,
+      "learning_rate": 3.0376636022891813e-06,
+      "loss": 0.9575,
+      "step": 985
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 2.318196631109318,
+      "learning_rate": 2.983568387580094e-06,
+      "loss": 0.9536,
+      "step": 990
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 1.616843986566008,
+      "learning_rate": 2.9297535933770732e-06,
+      "loss": 0.9474,
+      "step": 995
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 1.7693581907423008,
+      "learning_rate": 2.8762267035797607e-06,
+      "loss": 0.95,
+      "step": 1000
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 2.122336403201617,
+      "learning_rate": 2.822995162049599e-06,
+      "loss": 0.9505,
+      "step": 1005
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 1.5679869228768337,
+      "learning_rate": 2.7700663715746213e-06,
+      "loss": 0.9474,
+      "step": 1010
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 1.5424846799708574,
+      "learning_rate": 2.7174476928399685e-06,
+      "loss": 0.9483,
+      "step": 1015
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.654933401000696,
+      "learning_rate": 2.66514644340426e-06,
+      "loss": 0.9521,
+      "step": 1020
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 1.5993372025284307,
+      "learning_rate": 2.613169896681949e-06,
+      "loss": 0.9597,
+      "step": 1025
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.780666444469016,
+      "learning_rate": 2.5615252809318287e-06,
+      "loss": 0.9488,
+      "step": 1030
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 1.5279733243149005,
+      "learning_rate": 2.5102197782518145e-06,
+      "loss": 0.9438,
+      "step": 1035
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 1.8194536821858915,
+      "learning_rate": 2.4592605235801544e-06,
+      "loss": 0.943,
+      "step": 1040
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 1.6480818333921619,
+      "learning_rate": 2.4086546037031734e-06,
+      "loss": 0.9437,
+      "step": 1045
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 1.9968939308919122,
+      "learning_rate": 2.3584090562697427e-06,
+      "loss": 0.949,
+      "step": 1050
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.712960437774201,
+      "learning_rate": 2.3085308688125695e-06,
+      "loss": 0.9522,
+      "step": 1055
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 1.7812514943208981,
+      "learning_rate": 2.2590269777764516e-06,
+      "loss": 0.9503,
+      "step": 1060
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 1.4783532304720237,
+      "learning_rate": 2.2099042675536437e-06,
+      "loss": 0.9565,
+      "step": 1065
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 1.4892687284353463,
+      "learning_rate": 2.161169569526461e-06,
+      "loss": 0.9481,
+      "step": 1070
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.5738512766968247,
+      "learning_rate": 2.1128296611172593e-06,
+      "loss": 0.9483,
+      "step": 1075
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 1.7245957459593824,
+      "learning_rate": 2.0648912648459072e-06,
+      "loss": 0.9424,
+      "step": 1080
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 1.6116002624575987,
+      "learning_rate": 2.0173610473949048e-06,
+      "loss": 0.9462,
+      "step": 1085
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.5813885175238174,
+      "learning_rate": 1.9702456186822595e-06,
+      "loss": 0.9443,
+      "step": 1090
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.6220303849517923,
+      "learning_rate": 1.9235515309422685e-06,
+      "loss": 0.9428,
+      "step": 1095
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 1.847653265677833,
+      "learning_rate": 1.8772852778143064e-06,
+      "loss": 0.9431,
+      "step": 1100
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 1.7766441613041704,
+      "learning_rate": 1.831453293439771e-06,
+      "loss": 0.9371,
+      "step": 1105
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7572717020990576,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.9455,
+      "step": 1110
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 2.0366564271261396,
+      "learning_rate": 1.7411175646664103e-06,
+      "loss": 0.9415,
+      "step": 1115
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 1.641890714375309,
+      "learning_rate": 1.6966263830495939e-06,
+      "loss": 0.9245,
+      "step": 1120
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 1.7389532361568043,
+      "learning_rate": 1.6525945940031407e-06,
+      "loss": 0.9387,
+      "step": 1125
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 1.6927577102388072,
+      "learning_rate": 1.6090283209266682e-06,
+      "loss": 0.9358,
+      "step": 1130
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 1.6810193706370176,
+      "learning_rate": 1.5659336224815642e-06,
+      "loss": 0.9302,
+      "step": 1135
+    },
+    {
+      "epoch": 3.08,
+      "grad_norm": 1.5836446992301734,
+      "learning_rate": 1.5233164917484117e-06,
+      "loss": 0.9339,
+      "step": 1140
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 1.4925374056585887,
+      "learning_rate": 1.4811828553935498e-06,
+      "loss": 0.9359,
+      "step": 1145
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 1.562133820438609,
+      "learning_rate": 1.439538572844873e-06,
+      "loss": 0.9265,
+      "step": 1150
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 1.508715392161331,
+      "learning_rate": 1.3983894354769616e-06,
+      "loss": 0.94,
+      "step": 1155
+    },
+    {
+      "epoch": 3.13,
+      "grad_norm": 1.4833918032553421,
+      "learning_rate": 1.3577411658056965e-06,
+      "loss": 0.9359,
+      "step": 1160
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 1.7381479633485923,
+      "learning_rate": 1.3175994166924394e-06,
+      "loss": 0.9292,
+      "step": 1165
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 2.4773729170453276,
+      "learning_rate": 1.2779697705579058e-06,
+      "loss": 0.935,
+      "step": 1170
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 1.6423953500818698,
+      "learning_rate": 1.2388577386058248e-06,
+      "loss": 0.9281,
+      "step": 1175
+    },
+    {
+      "epoch": 3.18,
+      "grad_norm": 1.5747180314126341,
+      "learning_rate": 1.2002687600565138e-06,
+      "loss": 0.9251,
+      "step": 1180
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.4796953478538386,
+      "learning_rate": 1.1622082013904535e-06,
+      "loss": 0.9309,
+      "step": 1185
+    },
+    {
+      "epoch": 3.21,
+      "grad_norm": 1.9087071208773028,
+      "learning_rate": 1.1246813556019925e-06,
+      "loss": 0.9302,
+      "step": 1190
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 1.441416955211069,
+      "learning_rate": 1.0876934414632523e-06,
+      "loss": 0.9222,
+      "step": 1195
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 1.4528421452118758,
+      "learning_rate": 1.0512496027983715e-06,
+      "loss": 0.9358,
+      "step": 1200
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 1.4391309054269417,
+      "learning_rate": 1.0153549077681617e-06,
+      "loss": 0.9294,
+      "step": 1205
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 1.5484810522299401,
+      "learning_rate": 9.80014348165298e-07,
+      "loss": 0.9258,
+      "step": 1210
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 1.5093687112295802,
+      "learning_rate": 9.452328387201104e-07,
+      "loss": 0.9294,
+      "step": 1215
+    },
+    {
+      "epoch": 3.29,
+      "grad_norm": 1.4811632926742155,
+      "learning_rate": 9.110152164171127e-07,
+      "loss": 0.9291,
+      "step": 1220
+    },
+    {
+      "epoch": 3.31,
+      "grad_norm": 1.6851965695398232,
+      "learning_rate": 8.773662398223276e-07,
+      "loss": 0.9315,
+      "step": 1225
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 1.5680181843321963,
+      "learning_rate": 8.44290588421533e-07,
+      "loss": 0.9245,
+      "step": 1230
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 1.501501151688511,
+      "learning_rate": 8.117928619694848e-07,
+      "loss": 0.9312,
+      "step": 1235
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 1.5069447398439229,
+      "learning_rate": 7.798775798502484e-07,
+      "loss": 0.9256,
+      "step": 1240
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 1.4179041700918098,
+      "learning_rate": 7.485491804486972e-07,
+      "loss": 0.9209,
+      "step": 1245
+    },
+    {
+      "epoch": 3.37,
+      "grad_norm": 1.388023240525021,
+      "learning_rate": 7.178120205332717e-07,
+      "loss": 0.9311,
+      "step": 1250
+    },
+    {
+      "epoch": 3.39,
+      "grad_norm": 1.6540883448168693,
+      "learning_rate": 6.876703746500984e-07,
+      "loss": 0.9398,
+      "step": 1255
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 1.3848004961206983,
+      "learning_rate": 6.581284345285371e-07,
+      "loss": 0.9316,
+      "step": 1260
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 1.3665324107772734,
+      "learning_rate": 6.291903084982481e-07,
+      "loss": 0.9301,
+      "step": 1265
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 1.4952001545175686,
+      "learning_rate": 6.008600209178539e-07,
+      "loss": 0.9375,
+      "step": 1270
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 1.4437175986820594,
+      "learning_rate": 5.7314151161528e-07,
+      "loss": 0.9324,
+      "step": 1275
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 1.3632138123352606,
+      "learning_rate": 5.460386353398583e-07,
+      "loss": 0.9355,
+      "step": 1280
+    },
+    {
+      "epoch": 3.47,
+      "grad_norm": 1.4355913142058574,
+      "learning_rate": 5.195551612262478e-07,
+      "loss": 0.9369,
+      "step": 1285
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 1.3593932016675367,
+      "learning_rate": 4.936947722702762e-07,
+      "loss": 0.9248,
+      "step": 1290
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 1.5313367509871634,
+      "learning_rate": 4.6846106481675035e-07,
+      "loss": 0.9313,
+      "step": 1295
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 1.5679931446767343,
+      "learning_rate": 4.43857548059321e-07,
+      "loss": 0.9241,
+      "step": 1300
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 1.4231649052268165,
+      "learning_rate": 4.198876435524718e-07,
+      "loss": 0.9288,
+      "step": 1305
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 1.5147664043720925,
+      "learning_rate": 3.9655468473568436e-07,
+      "loss": 0.937,
+      "step": 1310
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 1.505384912577037,
+      "learning_rate": 3.7386191646987094e-07,
+      "loss": 0.9362,
+      "step": 1315
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 1.7241739930760707,
+      "learning_rate": 3.51812494586114e-07,
+      "loss": 0.9209,
+      "step": 1320
+    },
+    {
+      "epoch": 3.58,
+      "grad_norm": 1.498479993175917,
+      "learning_rate": 3.3040948544679817e-07,
+      "loss": 0.9323,
+      "step": 1325
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 1.464257082461974,
+      "learning_rate": 3.096558655191706e-07,
+      "loss": 0.9365,
+      "step": 1330
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.4384497143831931,
+      "learning_rate": 2.895545209614176e-07,
+      "loss": 0.939,
+      "step": 1335
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 1.4541548130541968,
+      "learning_rate": 2.701082472212879e-07,
+      "loss": 0.9277,
+      "step": 1340
+    },
+    {
+      "epoch": 3.63,
+      "grad_norm": 1.5175629961859558,
+      "learning_rate": 2.5131974864734063e-07,
+      "loss": 0.9279,
+      "step": 1345
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 1.4611673173663144,
+      "learning_rate": 2.331916381128535e-07,
+      "loss": 0.9268,
+      "step": 1350
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 1.3907174934591902,
+      "learning_rate": 2.157264366524603e-07,
+      "loss": 0.9297,
+      "step": 1355
+    },
+    {
+      "epoch": 3.67,
+      "grad_norm": 1.6602489752653944,
+      "learning_rate": 1.989265731115525e-07,
+      "loss": 0.9279,
+      "step": 1360
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 1.4335900513136002,
+      "learning_rate": 1.827943838085111e-07,
+      "loss": 0.9261,
+      "step": 1365
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 1.4382877939912813,
+      "learning_rate": 1.6733211220979316e-07,
+      "loss": 0.9286,
+      "step": 1370
+    },
+    {
+      "epoch": 3.71,
+      "grad_norm": 1.5442925793363935,
+      "learning_rate": 1.5254190861794415e-07,
+      "loss": 0.931,
+      "step": 1375
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 1.474749185950876,
+      "learning_rate": 1.3842582987255494e-07,
+      "loss": 0.9237,
+      "step": 1380
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 1.3949775304121632,
+      "learning_rate": 1.2498583906422779e-07,
+      "loss": 0.9264,
+      "step": 1385
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 1.4864944753529736,
+      "learning_rate": 1.1222380526156929e-07,
+      "loss": 0.9337,
+      "step": 1390
+    },
+    {
+      "epoch": 3.77,
+      "grad_norm": 1.4352950913827418,
+      "learning_rate": 1.0014150325126315e-07,
+      "loss": 0.9296,
+      "step": 1395
+    },
+    {
+      "epoch": 3.78,
+      "grad_norm": 1.54647479187705,
+      "learning_rate": 8.874061329125939e-08,
+      "loss": 0.9284,
+      "step": 1400
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 1.5426799677559493,
+      "learning_rate": 7.802272087709951e-08,
+      "loss": 0.9267,
+      "step": 1405
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 1.4345720592945528,
+      "learning_rate": 6.798931652142738e-08,
+      "loss": 0.9412,
+      "step": 1410
+    },
+    {
+      "epoch": 3.82,
+      "grad_norm": 1.4666166802740588,
+      "learning_rate": 5.864179554670724e-08,
+      "loss": 0.9274,
+      "step": 1415
+    },
+    {
+      "epoch": 3.83,
+      "grad_norm": 1.37454276267336,
+      "learning_rate": 4.998145789118114e-08,
+      "loss": 0.9347,
+      "step": 1420
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 1.3537939594957207,
+      "learning_rate": 4.2009507928084116e-08,
+      "loss": 0.9374,
+      "step": 1425
+    },
+    {
+      "epoch": 3.86,
+      "grad_norm": 1.5201092358761166,
+      "learning_rate": 3.4727054298161475e-08,
+      "loss": 0.9278,
+      "step": 1430
+    },
+    {
+      "epoch": 3.87,
+      "grad_norm": 1.3548157698669074,
+      "learning_rate": 2.8135109755487723e-08,
+      "loss": 0.9229,
+      "step": 1435
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 1.413302347919726,
+      "learning_rate": 2.223459102662695e-08,
+      "loss": 0.9341,
+      "step": 1440
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 1.3765482397349185,
+      "learning_rate": 1.7026318683147082e-08,
+      "loss": 0.9289,
+      "step": 1445
+    },
+    {
+      "epoch": 3.91,
+      "grad_norm": 1.3538302103790776,
+      "learning_rate": 1.2511017027501682e-08,
+      "loss": 0.9233,
+      "step": 1450
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 1.466960745073582,
+      "learning_rate": 8.689313992306104e-09,
+      "loss": 0.9303,
+      "step": 1455
+    },
+    {
+      "epoch": 3.94,
+      "grad_norm": 1.3714566713014886,
+      "learning_rate": 5.561741053010661e-09,
+      "loss": 0.936,
+      "step": 1460
+    },
+    {
+      "epoch": 3.95,
+      "grad_norm": 1.4859645171436624,
+      "learning_rate": 3.1287331539903155e-09,
+      "loss": 0.9247,
+      "step": 1465
+    },
+    {
+      "epoch": 3.97,
+      "grad_norm": 1.386772570990769,
+      "learning_rate": 1.3906286480563913e-09,
+      "loss": 0.9195,
+      "step": 1470
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 1.3873824123701393,
+      "learning_rate": 3.4766924940476954e-10,
+      "loss": 0.9374,
+      "step": 1475
+    },
+    {
+      "epoch": 3.99,
+      "grad_norm": 1.492034850579766,
+      "learning_rate": 0.0,
+      "loss": 0.9213,
+      "step": 1480
+    },
+    {
+      "epoch": 3.99,
+      "step": 1480,
+      "total_flos": 1630317777518592.0,
+      "train_loss": 1.3370767467730753,
+      "train_runtime": 16871.6289,
+      "train_samples_per_second": 44.965,
+      "train_steps_per_second": 0.088
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1630317777518592.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee114a93a6227495b2e198efefb90dcb64281dfc4537f4154d7cbe0d7984f73
+size 6072