Upload folder using huggingface_hub

.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 +1,66 @@
+---
+license: other
+base_model: google/gemma-2b
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrachat_200k
+model-index:
+- name: b128-lr2e-05-s0-e2
+  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. -->
+
+# b128-lr2e-05-s0-e2
+
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the HuggingFaceH4/ultrachat_200k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1860
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.1841        | 1.0   | 966  | 1.1936          |
+| 1.129         | 2.0   | 1932 | 1.1860          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.1860260963439941,
+    "eval_runtime": 712.015,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 19.223,
+    "eval_steps_per_second": 2.403,
+    "train_loss": 1.1706056661487365,
+    "train_runtime": 44868.6505,
+    "train_samples": 207865,
+    "train_samples_per_second": 5.513,
+    "train_steps_per_second": 0.043
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-2b",
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 1.1860260963439941,
+    "eval_runtime": 712.015,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 19.223,
+    "eval_steps_per_second": 2.403
+}

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": "4.38.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07edf9db53867ebca55ee96b233998c4ef08978c9398a85d10f788c6298e240b
+size 4945242264

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6821279c908e23912648c94358297067bacead3b13ab29ba2f89726b9e41353
+size 67121608

model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 5012344832
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "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": 2.0,
+    "train_loss": 1.1706056661487365,
+    "train_runtime": 44868.6505,
+    "train_samples": 207865,
+    "train_samples_per_second": 5.513,
+    "train_steps_per_second": 0.043
+}

trainer_state.json

@@ -0,0 +1,1404 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9994825355756791,
+  "eval_steps": -1932,
+  "global_step": 1932,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 17.643007937527535,
+      "learning_rate": 1.9999986779270796e-05,
+      "loss": 1.7409,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.9197503449441455,
+      "learning_rate": 1.9998677955919127e-05,
+      "loss": 1.4484,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.7374808701002429,
+      "learning_rate": 1.9994712173236604e-05,
+      "loss": 1.3475,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.6899015443647589,
+      "learning_rate": 1.9988103700540345e-05,
+      "loss": 1.2921,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.7237341780111256,
+      "learning_rate": 1.9978854285168784e-05,
+      "loss": 1.2894,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.5922734965135668,
+      "learning_rate": 1.99669663727489e-05,
+      "loss": 1.268,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.5581439767924481,
+      "learning_rate": 1.9952443106549535e-05,
+      "loss": 1.2615,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.5940665797953831,
+      "learning_rate": 1.9935288326650314e-05,
+      "loss": 1.2646,
+      "step": 70
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5959744098368311,
+      "learning_rate": 1.9915506568926283e-05,
+      "loss": 1.2585,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.8144997890397803,
+      "learning_rate": 1.989310306384858e-05,
+      "loss": 1.2584,
+      "step": 90
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.777903617079376,
+      "learning_rate": 1.9868083735101464e-05,
+      "loss": 1.2505,
+      "step": 100
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.6440368370519068,
+      "learning_rate": 1.9840455198016033e-05,
+      "loss": 1.242,
+      "step": 110
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.9925170475214626,
+      "learning_rate": 1.9810224757821063e-05,
+      "loss": 1.2588,
+      "step": 120
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.8103038992058391,
+      "learning_rate": 1.9777400407711467e-05,
+      "loss": 1.2409,
+      "step": 130
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5742872095116479,
+      "learning_rate": 1.9741990826734793e-05,
+      "loss": 1.2399,
+      "step": 140
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5826582249622616,
+      "learning_rate": 1.9704005377496428e-05,
+      "loss": 1.2436,
+      "step": 150
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.001834033758104,
+      "learning_rate": 1.9663454103684043e-05,
+      "loss": 1.2385,
+      "step": 160
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.6116318375090269,
+      "learning_rate": 1.9620347727411933e-05,
+      "loss": 1.2297,
+      "step": 170
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.7383765635051086,
+      "learning_rate": 1.9574697646386027e-05,
+      "loss": 1.2355,
+      "step": 180
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.7300866971988723,
+      "learning_rate": 1.9526515930890203e-05,
+      "loss": 1.2359,
+      "step": 190
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.616652810626178,
+      "learning_rate": 1.947581532059481e-05,
+      "loss": 1.2279,
+      "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.7043435155790823,
+      "learning_rate": 1.9422609221188208e-05,
+      "loss": 1.2376,
+      "step": 210
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.582186147373243,
+      "learning_rate": 1.9366911700832146e-05,
+      "loss": 1.2067,
+      "step": 220
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.5325118176004562,
+      "learning_rate": 1.9308737486442045e-05,
+      "loss": 1.2211,
+      "step": 230
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.2786931118214846,
+      "learning_rate": 1.9248101959793066e-05,
+      "loss": 1.2308,
+      "step": 240
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.8059420699070421,
+      "learning_rate": 1.918502115345303e-05,
+      "loss": 1.2275,
+      "step": 250
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.0151484537313564,
+      "learning_rate": 1.9119511746543265e-05,
+      "loss": 1.2194,
+      "step": 260
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6394385159074882,
+      "learning_rate": 1.9051591060328496e-05,
+      "loss": 1.2199,
+      "step": 270
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.1135335849941765,
+      "learning_rate": 1.8981277053636963e-05,
+      "loss": 1.2035,
+      "step": 280
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2945894820873338,
+      "learning_rate": 1.8908588318111932e-05,
+      "loss": 1.2067,
+      "step": 290
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.7098012376621641,
+      "learning_rate": 1.8833544073295918e-05,
+      "loss": 1.2095,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.053415846088335,
+      "learning_rate": 1.8756164161548848e-05,
+      "loss": 1.2135,
+      "step": 310
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.5430734273349764,
+      "learning_rate": 1.867646904280159e-05,
+      "loss": 1.2263,
+      "step": 320
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.7828549270150109,
+      "learning_rate": 1.859447978914614e-05,
+      "loss": 1.2164,
+      "step": 330
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5580407435562567,
+      "learning_rate": 1.8510218079263995e-05,
+      "loss": 1.2215,
+      "step": 340
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.604581236096349,
+      "learning_rate": 1.8423706192694118e-05,
+      "loss": 1.2056,
+      "step": 350
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.6909532249212962,
+      "learning_rate": 1.833496700394202e-05,
+      "loss": 1.2167,
+      "step": 360
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.3577994836194605,
+      "learning_rate": 1.824402397643155e-05,
+      "loss": 1.2158,
+      "step": 370
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.9441385325830896,
+      "learning_rate": 1.8150901156300956e-05,
+      "loss": 1.2112,
+      "step": 380
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7267919462491368,
+      "learning_rate": 1.8055623166044855e-05,
+      "loss": 1.2075,
+      "step": 390
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.072921001675868,
+      "learning_rate": 1.7958215198003866e-05,
+      "loss": 1.2086,
+      "step": 400
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.6898746674574788,
+      "learning_rate": 1.78587030077035e-05,
+      "loss": 1.2055,
+      "step": 410
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.9590944345354587,
+      "learning_rate": 1.77571129070442e-05,
+      "loss": 1.2133,
+      "step": 420
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.025412064694876,
+      "learning_rate": 1.7653471757344203e-05,
+      "loss": 1.2111,
+      "step": 430
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.7709425585870252,
+      "learning_rate": 1.7547806962237222e-05,
+      "loss": 1.2225,
+      "step": 440
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.9387702182387361,
+      "learning_rate": 1.744014646042663e-05,
+      "loss": 1.2118,
+      "step": 450
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3353541510148834,
+      "learning_rate": 1.7330518718298263e-05,
+      "loss": 1.2027,
+      "step": 460
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.727639267424137,
+      "learning_rate": 1.7218952722393646e-05,
+      "loss": 1.2006,
+      "step": 470
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5674850292979883,
+      "learning_rate": 1.7105477971745668e-05,
+      "loss": 1.208,
+      "step": 480
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.7282760631852704,
+      "learning_rate": 1.699012447007882e-05,
+      "loss": 1.1933,
+      "step": 490
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.5061673744005348,
+      "learning_rate": 1.6872922717875923e-05,
+      "loss": 1.1954,
+      "step": 500
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 2.129316814510312,
+      "learning_rate": 1.6753903704313527e-05,
+      "loss": 1.1948,
+      "step": 510
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.562747770369411,
+      "learning_rate": 1.6633098899068112e-05,
+      "loss": 1.2116,
+      "step": 520
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.4038904472553382,
+      "learning_rate": 1.6510540243995216e-05,
+      "loss": 1.2069,
+      "step": 530
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.9891488942684802,
+      "learning_rate": 1.6386260144683744e-05,
+      "loss": 1.1841,
+      "step": 540
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.674516959054479,
+      "learning_rate": 1.6260291461887628e-05,
+      "loss": 1.2092,
+      "step": 550
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.8101178930200521,
+      "learning_rate": 1.6132667502837164e-05,
+      "loss": 1.1898,
+      "step": 560
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.6229432949885818,
+      "learning_rate": 1.6003422012432275e-05,
+      "loss": 1.2033,
+      "step": 570
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7465954888391386,
+      "learning_rate": 1.587258916432008e-05,
+      "loss": 1.1889,
+      "step": 580
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.5512571394145237,
+      "learning_rate": 1.574020355185906e-05,
+      "loss": 1.2108,
+      "step": 590
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.6230914377601484,
+      "learning_rate": 1.560630017897229e-05,
+      "loss": 1.1947,
+      "step": 600
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.842968187484418,
+      "learning_rate": 1.5470914450892066e-05,
+      "loss": 1.1959,
+      "step": 610
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5710889771223773,
+      "learning_rate": 1.533408216479849e-05,
+      "loss": 1.209,
+      "step": 620
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.6384265788966181,
+      "learning_rate": 1.5195839500354337e-05,
+      "loss": 1.2034,
+      "step": 630
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.1199276334985704,
+      "learning_rate": 1.5056223010138857e-05,
+      "loss": 1.1945,
+      "step": 640
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.6533817452915996,
+      "learning_rate": 1.491526960998295e-05,
+      "loss": 1.2137,
+      "step": 650
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.8685960014206779,
+      "learning_rate": 1.4773016569208283e-05,
+      "loss": 1.2111,
+      "step": 660
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.5953668304650684,
+      "learning_rate": 1.4629501500772962e-05,
+      "loss": 1.199,
+      "step": 670
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.6749225480684463,
+      "learning_rate": 1.4484762351326344e-05,
+      "loss": 1.2084,
+      "step": 680
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.904182741829073,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 1.1945,
+      "step": 690
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5508295579907717,
+      "learning_rate": 1.4191765204166643e-05,
+      "loss": 1.1939,
+      "step": 700
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.6866787996093148,
+      "learning_rate": 1.4043584677482383e-05,
+      "loss": 1.1909,
+      "step": 710
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.8835327853377292,
+      "learning_rate": 1.3894334991360448e-05,
+      "loss": 1.1948,
+      "step": 720
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8315517331576922,
+      "learning_rate": 1.3744055608733654e-05,
+      "loss": 1.1808,
+      "step": 730
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.8656141990305095,
+      "learning_rate": 1.3592786264795659e-05,
+      "loss": 1.1887,
+      "step": 740
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0324451071242036,
+      "learning_rate": 1.344056695649462e-05,
+      "loss": 1.1884,
+      "step": 750
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.3534158770353415,
+      "learning_rate": 1.3287437931957642e-05,
+      "loss": 1.1992,
+      "step": 760
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7244302821509494,
+      "learning_rate": 1.3133439679848824e-05,
+      "loss": 1.1873,
+      "step": 770
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.7298798990304196,
+      "learning_rate": 1.2978612918663702e-05,
+      "loss": 1.1884,
+      "step": 780
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.413179744039514,
+      "learning_rate": 1.2822998585962909e-05,
+      "loss": 1.1909,
+      "step": 790
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.0358455016123018,
+      "learning_rate": 1.2666637827547935e-05,
+      "loss": 1.1987,
+      "step": 800
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.6031288230702698,
+      "learning_rate": 1.2509571986581814e-05,
+      "loss": 1.1902,
+      "step": 810
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.7093558444620996,
+      "learning_rate": 1.2351842592657612e-05,
+      "loss": 1.199,
+      "step": 820
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.5974126496122436,
+      "learning_rate": 1.2193491350817657e-05,
+      "loss": 1.1928,
+      "step": 830
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.0993091833167254,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 1.1894,
+      "step": 840
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.0436299996205698,
+      "learning_rate": 1.1875090954599472e-05,
+      "loss": 1.1845,
+      "step": 850
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.005963688677739,
+      "learning_rate": 1.1715125988093075e-05,
+      "loss": 1.1881,
+      "step": 860
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8352354026650106,
+      "learning_rate": 1.155470752715458e-05,
+      "loss": 1.1871,
+      "step": 870
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.7899077951054885,
+      "learning_rate": 1.1393877987839329e-05,
+      "loss": 1.1903,
+      "step": 880
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5922501845943217,
+      "learning_rate": 1.1232679894895417e-05,
+      "loss": 1.1826,
+      "step": 890
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.048795193828536,
+      "learning_rate": 1.1071155870519777e-05,
+      "loss": 1.1782,
+      "step": 900
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.7362075773775668,
+      "learning_rate": 1.0909348623088472e-05,
+      "loss": 1.2019,
+      "step": 910
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.6013600464653039,
+      "learning_rate": 1.0747300935864245e-05,
+      "loss": 1.18,
+      "step": 920
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5456484078106916,
+      "learning_rate": 1.058505565568424e-05,
+      "loss": 1.1897,
+      "step": 930
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 2.5478758461886337,
+      "learning_rate": 1.0422655681630917e-05,
+      "loss": 1.1842,
+      "step": 940
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.589047830040976,
+      "learning_rate": 1.0260143953689165e-05,
+      "loss": 1.1668,
+      "step": 950
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.8101184986963358,
+      "learning_rate": 1.0097563441392582e-05,
+      "loss": 1.1841,
+      "step": 960
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1935690641403198,
+      "eval_runtime": 713.5459,
+      "eval_samples_per_second": 19.182,
+      "eval_steps_per_second": 2.398,
+      "step": 966
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7266564378737855,
+      "learning_rate": 9.93495713246196e-06,
+      "loss": 1.158,
+      "step": 970
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.5811606746061891,
+      "learning_rate": 9.772368021438943e-06,
+      "loss": 1.137,
+      "step": 980
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.9020508561679803,
+      "learning_rate": 9.609839098317902e-06,
+      "loss": 1.1431,
+      "step": 990
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 1.18508535225423,
+      "learning_rate": 9.447413337178994e-06,
+      "loss": 1.1321,
+      "step": 1000
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.8495084821410501,
+      "learning_rate": 9.285133684825435e-06,
+      "loss": 1.1348,
+      "step": 1010
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.552216080899871,
+      "learning_rate": 9.123043049427996e-06,
+      "loss": 1.1334,
+      "step": 1020
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.9043855104169688,
+      "learning_rate": 8.961184289179695e-06,
+      "loss": 1.118,
+      "step": 1030
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.7622936476724878,
+      "learning_rate": 8.799600200963716e-06,
+      "loss": 1.1352,
+      "step": 1040
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.8035628121141856,
+      "learning_rate": 8.638333509037537e-06,
+      "loss": 1.1313,
+      "step": 1050
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.8605002053318102,
+      "learning_rate": 8.477426853736257e-06,
+      "loss": 1.122,
+      "step": 1060
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.8384089217871873,
+      "learning_rate": 8.316922780198126e-06,
+      "loss": 1.1298,
+      "step": 1070
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5528220558144542,
+      "learning_rate": 8.15686372711521e-06,
+      "loss": 1.1235,
+      "step": 1080
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.6970307225205526,
+      "learning_rate": 7.997292015512257e-06,
+      "loss": 1.1321,
+      "step": 1090
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.7347197055541482,
+      "learning_rate": 7.83824983755663e-06,
+      "loss": 1.1294,
+      "step": 1100
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.5059154997147504,
+      "learning_rate": 7.679779245402321e-06,
+      "loss": 1.1094,
+      "step": 1110
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.884265369908016,
+      "learning_rate": 7.521922140071003e-06,
+      "loss": 1.1241,
+      "step": 1120
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.6033143868426079,
+      "learning_rate": 7.364720260373017e-06,
+      "loss": 1.1268,
+      "step": 1130
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.0148548766319452,
+      "learning_rate": 7.208215171871277e-06,
+      "loss": 1.1285,
+      "step": 1140
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.618997247973023,
+      "learning_rate": 7.052448255890958e-06,
+      "loss": 1.1298,
+      "step": 1150
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.8657773774435762,
+      "learning_rate": 6.897460698577918e-06,
+      "loss": 1.1207,
+      "step": 1160
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.7115128067386574,
+      "learning_rate": 6.743293480008703e-06,
+      "loss": 1.1309,
+      "step": 1170
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.7183269888324105,
+      "learning_rate": 6.589987363355068e-06,
+      "loss": 1.1218,
+      "step": 1180
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.5703913996302657,
+      "learning_rate": 6.437582884105835e-06,
+      "loss": 1.1289,
+      "step": 1190
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.7815346714791873,
+      "learning_rate": 6.286120339348935e-06,
+      "loss": 1.1388,
+      "step": 1200
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.5219064361079887,
+      "learning_rate": 6.135639777116526e-06,
+      "loss": 1.1321,
+      "step": 1210
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.6957441921997511,
+      "learning_rate": 5.986180985795927e-06,
+      "loss": 1.1344,
+      "step": 1220
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.5281652316634469,
+      "learning_rate": 5.837783483609214e-06,
+      "loss": 1.1378,
+      "step": 1230
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.6339946135976855,
+      "learning_rate": 5.690486508164268e-06,
+      "loss": 1.1234,
+      "step": 1240
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.6527823541816111,
+      "learning_rate": 5.544329006079987e-06,
+      "loss": 1.1273,
+      "step": 1250
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.5301541402833422,
+      "learning_rate": 5.399349622688479e-06,
+      "loss": 1.1135,
+      "step": 1260
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.5178611686388369,
+      "learning_rate": 5.255586691816874e-06,
+      "loss": 1.1257,
+      "step": 1270
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.5477723564080109,
+      "learning_rate": 5.113078225651529e-06,
+      "loss": 1.1267,
+      "step": 1280
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.5638053300059095,
+      "learning_rate": 4.971861904687283e-06,
+      "loss": 1.1331,
+      "step": 1290
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.5721584413593953,
+      "learning_rate": 4.831975067764387e-06,
+      "loss": 1.1107,
+      "step": 1300
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.9007471246680614,
+      "learning_rate": 4.693454702195784e-06,
+      "loss": 1.121,
+      "step": 1310
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.7273372669798455,
+      "learning_rate": 4.556337433987359e-06,
+      "loss": 1.1275,
+      "step": 1320
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.488613514692357,
+      "learning_rate": 4.420659518153667e-06,
+      "loss": 1.1274,
+      "step": 1330
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.578443583469973,
+      "learning_rate": 4.286456829131821e-06,
+      "loss": 1.124,
+      "step": 1340
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.6326996663378455,
+      "learning_rate": 4.153764851295954e-06,
+      "loss": 1.1376,
+      "step": 1350
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.5965643189554584,
+      "learning_rate": 4.022618669574839e-06,
+      "loss": 1.1219,
+      "step": 1360
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.5659365610817053,
+      "learning_rate": 3.893052960175128e-06,
+      "loss": 1.1172,
+      "step": 1370
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.600973182084687,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 1.121,
+      "step": 1380
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.5982641636650878,
+      "learning_rate": 3.6387995646542727e-06,
+      "loss": 1.1287,
+      "step": 1390
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.5031147841111573,
+      "learning_rate": 3.5141791053724405e-06,
+      "loss": 1.1339,
+      "step": 1400
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.5426031516616974,
+      "learning_rate": 3.3912735543152864e-06,
+      "loss": 1.1288,
+      "step": 1410
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.5392907866642725,
+      "learning_rate": 3.27011540879406e-06,
+      "loss": 1.1271,
+      "step": 1420
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.5386770630525428,
+      "learning_rate": 3.1507367040905943e-06,
+      "loss": 1.1334,
+      "step": 1430
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.5085556091485328,
+      "learning_rate": 3.0331690049868733e-06,
+      "loss": 1.1297,
+      "step": 1440
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5633636269166687,
+      "learning_rate": 2.9174433974190365e-06,
+      "loss": 1.1243,
+      "step": 1450
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.48764993266916146,
+      "learning_rate": 2.803590480257985e-06,
+      "loss": 1.1281,
+      "step": 1460
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.9169861978820425,
+      "learning_rate": 2.691640357218759e-06,
+      "loss": 1.1239,
+      "step": 1470
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.516479662678479,
+      "learning_rate": 2.581622628900868e-06,
+      "loss": 1.1228,
+      "step": 1480
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.6193601635552117,
+      "learning_rate": 2.4735663849616098e-06,
+      "loss": 1.1202,
+      "step": 1490
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.49498823489992116,
+      "learning_rate": 2.367500196424529e-06,
+      "loss": 1.1279,
+      "step": 1500
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.6290761419202775,
+      "learning_rate": 2.263452108124968e-06,
+      "loss": 1.1192,
+      "step": 1510
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.5701593566889765,
+      "learning_rate": 2.161449631294785e-06,
+      "loss": 1.1227,
+      "step": 1520
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.4691807510199917,
+      "learning_rate": 2.0615197362881234e-06,
+      "loss": 1.117,
+      "step": 1530
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.926057066254184,
+      "learning_rate": 1.963688845450218e-06,
+      "loss": 1.1177,
+      "step": 1540
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7383468808391309,
+      "learning_rate": 1.8679828261311073e-06,
+      "loss": 1.1299,
+      "step": 1550
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.49356910651083413,
+      "learning_rate": 1.774426983846058e-06,
+      "loss": 1.1167,
+      "step": 1560
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.5403947993978422,
+      "learning_rate": 1.6830460555845719e-06,
+      "loss": 1.1324,
+      "step": 1570
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.5254533594635142,
+      "learning_rate": 1.593864203269716e-06,
+      "loss": 1.1288,
+      "step": 1580
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.4750626069678938,
+      "learning_rate": 1.5069050073694813e-06,
+      "loss": 1.127,
+      "step": 1590
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.4803355102824248,
+      "learning_rate": 1.4221914606619135e-06,
+      "loss": 1.1253,
+      "step": 1600
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.5023769646064918,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 1.1362,
+      "step": 1610
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.4750107387465944,
+      "learning_rate": 1.259590311167238e-06,
+      "loss": 1.1196,
+      "step": 1620
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.49120491276877826,
+      "learning_rate": 1.181745701557574e-06,
+      "loss": 1.1163,
+      "step": 1630
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.523266756507014,
+      "learning_rate": 1.1062327161276965e-06,
+      "loss": 1.1133,
+      "step": 1640
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.48201400455042975,
+      "learning_rate": 1.0330713211766864e-06,
+      "loss": 1.128,
+      "step": 1650
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.6814324481203446,
+      "learning_rate": 9.622808612223722e-07,
+      "loss": 1.1441,
+      "step": 1660
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.4529669002867237,
+      "learning_rate": 8.9388005388647e-07,
+      "loss": 1.132,
+      "step": 1670
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.5488831178907686,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 1.1373,
+      "step": 1680
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.46046446784548656,
+      "learning_rate": 7.643191035486086e-07,
+      "loss": 1.1147,
+      "step": 1690
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.48574840186097173,
+      "learning_rate": 7.031932176041522e-07,
+      "loss": 1.1283,
+      "step": 1700
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.614025528461565,
+      "learning_rate": 6.445254893352381e-07,
+      "loss": 1.1147,
+      "step": 1710
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.46356093239410984,
+      "learning_rate": 5.883314310064492e-07,
+      "loss": 1.1353,
+      "step": 1720
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.5695243032656638,
+      "learning_rate": 5.346259008222243e-07,
+      "loss": 1.1206,
+      "step": 1730
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.5116195400283284,
+      "learning_rate": 4.834230989982214e-07,
+      "loss": 1.1123,
+      "step": 1740
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.4727612452244113,
+      "learning_rate": 4.3473656400665256e-07,
+      "loss": 1.1258,
+      "step": 1750
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.0498570469876018,
+      "learning_rate": 3.885791689966023e-07,
+      "loss": 1.129,
+      "step": 1760
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.5474571870293417,
+      "learning_rate": 3.4496311839024133e-07,
+      "loss": 1.1246,
+      "step": 1770
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.46259219613163566,
+      "learning_rate": 3.038999446558755e-07,
+      "loss": 1.1249,
+      "step": 1780
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.5077623062630557,
+      "learning_rate": 2.654005052586628e-07,
+      "loss": 1.1344,
+      "step": 1790
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.7073531796619889,
+      "learning_rate": 2.294749797897955e-07,
+      "loss": 1.1075,
+      "step": 1800
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.48237877829197745,
+      "learning_rate": 1.961328672749352e-07,
+      "loss": 1.1219,
+      "step": 1810
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.456598123312511,
+      "learning_rate": 1.6538298366257975e-07,
+      "loss": 1.1109,
+      "step": 1820
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.4764383587717983,
+      "learning_rate": 1.3723345949305245e-07,
+      "loss": 1.1238,
+      "step": 1830
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.4611156020653585,
+      "learning_rate": 1.1169173774871478e-07,
+      "loss": 1.1229,
+      "step": 1840
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.4560163397865408,
+      "learning_rate": 8.876457188597642e-08,
+      "loss": 1.1325,
+      "step": 1850
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.5219948547290205,
+      "learning_rate": 6.845802404962243e-08,
+      "loss": 1.1177,
+      "step": 1860
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.4510998317003041,
+      "learning_rate": 5.0777463469925406e-08,
+      "loss": 1.125,
+      "step": 1870
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.48962561357722584,
+      "learning_rate": 3.572756504297892e-08,
+      "loss": 1.1399,
+      "step": 1880
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.5094047679112849,
+      "learning_rate": 2.3312308094607382e-08,
+      "loss": 1.1209,
+      "step": 1890
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.48754364841280406,
+      "learning_rate": 1.3534975328205468e-08,
+      "loss": 1.1311,
+      "step": 1900
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.48361438379969285,
+      "learning_rate": 6.398151956754639e-09,
+      "loss": 1.123,
+      "step": 1910
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.5170334599385726,
+      "learning_rate": 1.9037250192732728e-09,
+      "loss": 1.1228,
+      "step": 1920
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8343836947757891,
+      "learning_rate": 5.288288186688917e-11,
+      "loss": 1.129,
+      "step": 1930
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1860260963439941,
+      "eval_runtime": 713.2766,
+      "eval_samples_per_second": 19.189,
+      "eval_steps_per_second": 2.399,
+      "step": 1932
+    },
+    {
+      "epoch": 2.0,
+      "step": 1932,
+      "total_flos": 230258632556544.0,
+      "train_loss": 1.1706056661487365,
+      "train_runtime": 44868.6505,
+      "train_samples_per_second": 5.513,
+      "train_steps_per_second": 0.043
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1932,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 230258632556544.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542c00bd70203b99f544c7881c12f8dea4f49f66f8aec3d0d7d21eb818382067
+size 6136