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 +1,69 @@
+---
+license: gemma
+base_model: google/gemma-7b
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-7b-gemma-sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# zephyr-7b-gemma-sft
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0814
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9991        | 0.9983 | 299  | 1.1125          |
+| 0.732         | 2.0    | 599  | 1.0251          |
+| 0.4257        | 2.9950 | 897  | 1.0814          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.994991652754591,
+    "total_flos": 246978202042368.0,
+    "train_loss": 0.8794620578637224,
+    "train_runtime": 12081.5129,
+    "train_samples": 9500,
+    "train_samples_per_second": 9.517,
+    "train_steps_per_second": 0.074
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_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_activation": null,
+  "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": "4.40.2",
+  "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": "4.40.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cbe752d69e6212a62fe586eebf37f4791ae248c2b13821d89b97482d3b4d7ab
+size 4995496656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d5e2bc8ea81c9c17e809f7bfdcba1f580b90d62fb1888b1743974690962887
+size 4982953168

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026ca11ebc6d14e88d25e0ba1683d902ba767a16f0995dd58edf1555691b0d8e
+size 4982953200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3989a4803fad7896f88ae2bf52817781b8005a5edeeb0bfbc46339f95a93b4
+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"
+  }
+}

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 sha256:322a5f52ab5cab196761ab397a022d6fa3a2e1418585e532bb6efb2fedd2ae94
+size 17477501

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": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ 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 +1,9 @@
+{
+    "epoch": 2.994991652754591,
+    "total_flos": 246978202042368.0,
+    "train_loss": 0.8794620578637224,
+    "train_runtime": 12081.5129,
+    "train_samples": 9500,
+    "train_samples_per_second": 9.517,
+    "train_steps_per_second": 0.074
+}

trainer_state.json

@@ -0,0 +1,1314 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.994991652754591,
+  "eval_steps": 500,
+  "global_step": 897,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00333889816360601,
+      "grad_norm": 1636.1731858645219,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 14.7432,
+      "step": 1
+    },
+    {
+      "epoch": 0.01669449081803005,
+      "grad_norm": 1241.0696113772483,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 13.7623,
+      "step": 5
+    },
+    {
+      "epoch": 0.0333889816360601,
+      "grad_norm": 159.06557930461932,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 6.5961,
+      "step": 10
+    },
+    {
+      "epoch": 0.05008347245409015,
+      "grad_norm": 54.98952826184268,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.4982,
+      "step": 15
+    },
+    {
+      "epoch": 0.0667779632721202,
+      "grad_norm": 15.464982016331927,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.7591,
+      "step": 20
+    },
+    {
+      "epoch": 0.08347245409015025,
+      "grad_norm": 113.55847454938332,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.5909,
+      "step": 25
+    },
+    {
+      "epoch": 0.1001669449081803,
+      "grad_norm": 13.684174796685392,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.4782,
+      "step": 30
+    },
+    {
+      "epoch": 0.11686143572621036,
+      "grad_norm": 18.015145294132687,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.4047,
+      "step": 35
+    },
+    {
+      "epoch": 0.1335559265442404,
+      "grad_norm": 39.03723229354282,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.2649,
+      "step": 40
+    },
+    {
+      "epoch": 0.15025041736227046,
+      "grad_norm": 95.10713656196118,
+      "learning_rate": 1e-05,
+      "loss": 1.2138,
+      "step": 45
+    },
+    {
+      "epoch": 0.1669449081803005,
+      "grad_norm": 23.387914595882737,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.0923,
+      "step": 50
+    },
+    {
+      "epoch": 0.18363939899833054,
+      "grad_norm": 42.989753028654455,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 1.1448,
+      "step": 55
+    },
+    {
+      "epoch": 0.2003338898163606,
+      "grad_norm": 21.574525631481794,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.0929,
+      "step": 60
+    },
+    {
+      "epoch": 0.21702838063439064,
+      "grad_norm": 19.62417675516016,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 1.0565,
+      "step": 65
+    },
+    {
+      "epoch": 0.2337228714524207,
+      "grad_norm": 18.48635867600005,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 1.0676,
+      "step": 70
+    },
+    {
+      "epoch": 0.25041736227045075,
+      "grad_norm": 56.269945581410674,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.0468,
+      "step": 75
+    },
+    {
+      "epoch": 0.2671118530884808,
+      "grad_norm": 92.06608057852377,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 1.0886,
+      "step": 80
+    },
+    {
+      "epoch": 0.2838063439065108,
+      "grad_norm": 9.25817849729028,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.0923,
+      "step": 85
+    },
+    {
+      "epoch": 0.3005008347245409,
+      "grad_norm": 42.001132789001005,
+      "learning_rate": 2e-05,
+      "loss": 1.1971,
+      "step": 90
+    },
+    {
+      "epoch": 0.31719532554257096,
+      "grad_norm": 32.33157331317634,
+      "learning_rate": 1.9998105699049984e-05,
+      "loss": 1.1355,
+      "step": 95
+    },
+    {
+      "epoch": 0.333889816360601,
+      "grad_norm": 39.74167678661768,
+      "learning_rate": 1.9992423513875158e-05,
+      "loss": 1.1301,
+      "step": 100
+    },
+    {
+      "epoch": 0.35058430717863104,
+      "grad_norm": 67.18243692938607,
+      "learning_rate": 1.9982955597229275e-05,
+      "loss": 1.1313,
+      "step": 105
+    },
+    {
+      "epoch": 0.3672787979966611,
+      "grad_norm": 19.404632003387977,
+      "learning_rate": 1.9969705536129033e-05,
+      "loss": 1.0945,
+      "step": 110
+    },
+    {
+      "epoch": 0.38397328881469117,
+      "grad_norm": 27.47292619482353,
+      "learning_rate": 1.9952678350495104e-05,
+      "loss": 1.0579,
+      "step": 115
+    },
+    {
+      "epoch": 0.4006677796327212,
+      "grad_norm": 16.321517177338055,
+      "learning_rate": 1.9931880491250263e-05,
+      "loss": 1.0929,
+      "step": 120
+    },
+    {
+      "epoch": 0.41736227045075125,
+      "grad_norm": 41.445947552770555,
+      "learning_rate": 1.990731983787542e-05,
+      "loss": 1.075,
+      "step": 125
+    },
+    {
+      "epoch": 0.4340567612687813,
+      "grad_norm": 40.404151604564895,
+      "learning_rate": 1.987900569542438e-05,
+      "loss": 1.055,
+      "step": 130
+    },
+    {
+      "epoch": 0.4507512520868113,
+      "grad_norm": 42.80864271129836,
+      "learning_rate": 1.9846948790998532e-05,
+      "loss": 1.0148,
+      "step": 135
+    },
+    {
+      "epoch": 0.4674457429048414,
+      "grad_norm": 29.906791369261654,
+      "learning_rate": 1.9811161269682776e-05,
+      "loss": 1.019,
+      "step": 140
+    },
+    {
+      "epoch": 0.48414023372287146,
+      "grad_norm": 45.64979239247701,
+      "learning_rate": 1.9771656689944238e-05,
+      "loss": 1.0167,
+      "step": 145
+    },
+    {
+      "epoch": 0.5008347245409015,
+      "grad_norm": 41.489381367872696,
+      "learning_rate": 1.9728450018495506e-05,
+      "loss": 0.9916,
+      "step": 150
+    },
+    {
+      "epoch": 0.5175292153589316,
+      "grad_norm": 28.13085318824674,
+      "learning_rate": 1.968155762462433e-05,
+      "loss": 0.9901,
+      "step": 155
+    },
+    {
+      "epoch": 0.5342237061769616,
+      "grad_norm": 28.96110814252046,
+      "learning_rate": 1.9630997273991964e-05,
+      "loss": 1.0022,
+      "step": 160
+    },
+    {
+      "epoch": 0.5509181969949917,
+      "grad_norm": 30.254621993184756,
+      "learning_rate": 1.9576788121902457e-05,
+      "loss": 0.9955,
+      "step": 165
+    },
+    {
+      "epoch": 0.5676126878130217,
+      "grad_norm": 23.80583469366122,
+      "learning_rate": 1.951895070604547e-05,
+      "loss": 0.9863,
+      "step": 170
+    },
+    {
+      "epoch": 0.5843071786310517,
+      "grad_norm": 30.76534972341624,
+      "learning_rate": 1.9457506938715357e-05,
+      "loss": 0.974,
+      "step": 175
+    },
+    {
+      "epoch": 0.6010016694490818,
+      "grad_norm": 23.682111890096746,
+      "learning_rate": 1.9392480098509488e-05,
+      "loss": 0.9608,
+      "step": 180
+    },
+    {
+      "epoch": 0.6176961602671118,
+      "grad_norm": 40.932765589134476,
+      "learning_rate": 1.93238948215089e-05,
+      "loss": 0.9886,
+      "step": 185
+    },
+    {
+      "epoch": 0.6343906510851419,
+      "grad_norm": 24.22268491501868,
+      "learning_rate": 1.9251777091944665e-05,
+      "loss": 0.9818,
+      "step": 190
+    },
+    {
+      "epoch": 0.6510851419031719,
+      "grad_norm": 31.497106387949316,
+      "learning_rate": 1.9176154232353513e-05,
+      "loss": 0.9896,
+      "step": 195
+    },
+    {
+      "epoch": 0.667779632721202,
+      "grad_norm": 27.472535439999113,
+      "learning_rate": 1.9097054893226395e-05,
+      "loss": 0.9498,
+      "step": 200
+    },
+    {
+      "epoch": 0.6844741235392321,
+      "grad_norm": 37.827441038916966,
+      "learning_rate": 1.9014509042153964e-05,
+      "loss": 0.9633,
+      "step": 205
+    },
+    {
+      "epoch": 0.7011686143572621,
+      "grad_norm": 33.73411466957624,
+      "learning_rate": 1.8928547952473037e-05,
+      "loss": 0.9749,
+      "step": 210
+    },
+    {
+      "epoch": 0.7178631051752922,
+      "grad_norm": 27.49850413211882,
+      "learning_rate": 1.8839204191418386e-05,
+      "loss": 0.9446,
+      "step": 215
+    },
+    {
+      "epoch": 0.7345575959933222,
+      "grad_norm": 27.552863205682964,
+      "learning_rate": 1.8746511607784298e-05,
+      "loss": 0.9529,
+      "step": 220
+    },
+    {
+      "epoch": 0.7512520868113522,
+      "grad_norm": 32.118943766221065,
+      "learning_rate": 1.865050531910062e-05,
+      "loss": 0.9671,
+      "step": 225
+    },
+    {
+      "epoch": 0.7679465776293823,
+      "grad_norm": 21.270564236998155,
+      "learning_rate": 1.855122169832813e-05,
+      "loss": 0.9609,
+      "step": 230
+    },
+    {
+      "epoch": 0.7846410684474123,
+      "grad_norm": 28.392651654223076,
+      "learning_rate": 1.844869836007825e-05,
+      "loss": 0.9695,
+      "step": 235
+    },
+    {
+      "epoch": 0.8013355592654424,
+      "grad_norm": 24.77881281961339,
+      "learning_rate": 1.8342974146362397e-05,
+      "loss": 0.9522,
+      "step": 240
+    },
+    {
+      "epoch": 0.8180300500834724,
+      "grad_norm": 44.290831285889865,
+      "learning_rate": 1.8234089111876256e-05,
+      "loss": 0.94,
+      "step": 245
+    },
+    {
+      "epoch": 0.8347245409015025,
+      "grad_norm": 28.426449603459353,
+      "learning_rate": 1.8122084508824692e-05,
+      "loss": 0.9237,
+      "step": 250
+    },
+    {
+      "epoch": 0.8514190317195326,
+      "grad_norm": 18.50017000873142,
+      "learning_rate": 1.80070027712929e-05,
+      "loss": 0.9213,
+      "step": 255
+    },
+    {
+      "epoch": 0.8681135225375626,
+      "grad_norm": 6.074609944113466,
+      "learning_rate": 1.7888887499169816e-05,
+      "loss": 0.9705,
+      "step": 260
+    },
+    {
+      "epoch": 0.8848080133555927,
+      "grad_norm": 50.118804464161194,
+      "learning_rate": 1.7767783441629883e-05,
+      "loss": 0.9985,
+      "step": 265
+    },
+    {
+      "epoch": 0.9015025041736227,
+      "grad_norm": 13.585608342741851,
+      "learning_rate": 1.7643736480179353e-05,
+      "loss": 1.0247,
+      "step": 270
+    },
+    {
+      "epoch": 0.9181969949916527,
+      "grad_norm": 48.90372434538966,
+      "learning_rate": 1.7516793611273614e-05,
+      "loss": 1.058,
+      "step": 275
+    },
+    {
+      "epoch": 0.9348914858096828,
+      "grad_norm": 13.845686747415364,
+      "learning_rate": 1.7387002928512093e-05,
+      "loss": 1.2477,
+      "step": 280
+    },
+    {
+      "epoch": 0.9515859766277128,
+      "grad_norm": 30.457372642079424,
+      "learning_rate": 1.725441360441752e-05,
+      "loss": 1.1773,
+      "step": 285
+    },
+    {
+      "epoch": 0.9682804674457429,
+      "grad_norm": 17.834289286231748,
+      "learning_rate": 1.711907587180642e-05,
+      "loss": 1.0797,
+      "step": 290
+    },
+    {
+      "epoch": 0.9849749582637729,
+      "grad_norm": 16.139198517107467,
+      "learning_rate": 1.698104100475788e-05,
+      "loss": 0.9991,
+      "step": 295
+    },
+    {
+      "epoch": 0.998330550918197,
+      "eval_loss": 1.1124651432037354,
+      "eval_runtime": 51.5404,
+      "eval_samples_per_second": 37.117,
+      "eval_steps_per_second": 1.164,
+      "step": 299
+    },
+    {
+      "epoch": 1.001669449081803,
+      "grad_norm": 10.399808410370275,
+      "learning_rate": 1.684036129918786e-05,
+      "loss": 1.0245,
+      "step": 300
+    },
+    {
+      "epoch": 1.018363939899833,
+      "grad_norm": 22.312983524170857,
+      "learning_rate": 1.6697090053036344e-05,
+      "loss": 0.8376,
+      "step": 305
+    },
+    {
+      "epoch": 1.0350584307178632,
+      "grad_norm": 10.23946947372752,
+      "learning_rate": 1.6551281546074863e-05,
+      "loss": 0.8381,
+      "step": 310
+    },
+    {
+      "epoch": 1.0517529215358932,
+      "grad_norm": 10.822249366036935,
+      "learning_rate": 1.6402991019342073e-05,
+      "loss": 0.7963,
+      "step": 315
+    },
+    {
+      "epoch": 1.0684474123539232,
+      "grad_norm": 23.353805364118337,
+      "learning_rate": 1.625227465421511e-05,
+      "loss": 0.8458,
+      "step": 320
+    },
+    {
+      "epoch": 1.0851419031719534,
+      "grad_norm": 35.132703592046234,
+      "learning_rate": 1.60991895511247e-05,
+      "loss": 0.8504,
+      "step": 325
+    },
+    {
+      "epoch": 1.1018363939899833,
+      "grad_norm": 12.778026589965993,
+      "learning_rate": 1.5943793707922086e-05,
+      "loss": 0.8158,
+      "step": 330
+    },
+    {
+      "epoch": 1.1185308848080133,
+      "grad_norm": 10.675434539871876,
+      "learning_rate": 1.5786145997905952e-05,
+      "loss": 0.845,
+      "step": 335
+    },
+    {
+      "epoch": 1.1352253756260433,
+      "grad_norm": 7.2516130782939685,
+      "learning_rate": 1.5626306147517665e-05,
+      "loss": 0.8119,
+      "step": 340
+    },
+    {
+      "epoch": 1.1519198664440735,
+      "grad_norm": 11.563033540745929,
+      "learning_rate": 1.5464334713713312e-05,
+      "loss": 0.8162,
+      "step": 345
+    },
+    {
+      "epoch": 1.1686143572621035,
+      "grad_norm": 4.678107369657476,
+      "learning_rate": 1.5300293061021084e-05,
+      "loss": 0.8441,
+      "step": 350
+    },
+    {
+      "epoch": 1.1853088480801335,
+      "grad_norm": 13.53721264062237,
+      "learning_rate": 1.5134243338292686e-05,
+      "loss": 0.8365,
+      "step": 355
+    },
+    {
+      "epoch": 1.2020033388981637,
+      "grad_norm": 10.368076427426205,
+      "learning_rate": 1.4966248455157622e-05,
+      "loss": 0.8318,
+      "step": 360
+    },
+    {
+      "epoch": 1.2186978297161937,
+      "grad_norm": 30.650511145751103,
+      "learning_rate": 1.4796372058189235e-05,
+      "loss": 0.8069,
+      "step": 365
+    },
+    {
+      "epoch": 1.2353923205342237,
+      "grad_norm": 12.33430302707372,
+      "learning_rate": 1.4624678506791556e-05,
+      "loss": 0.8394,
+      "step": 370
+    },
+    {
+      "epoch": 1.2520868113522536,
+      "grad_norm": 15.813506313324618,
+      "learning_rate": 1.445123284881609e-05,
+      "loss": 0.8065,
+      "step": 375
+    },
+    {
+      "epoch": 1.2687813021702838,
+      "grad_norm": 17.421613932726007,
+      "learning_rate": 1.4276100795917777e-05,
+      "loss": 0.7969,
+      "step": 380
+    },
+    {
+      "epoch": 1.2854757929883138,
+      "grad_norm": 25.591747341293413,
+      "learning_rate": 1.409934869865945e-05,
+      "loss": 0.8187,
+      "step": 385
+    },
+    {
+      "epoch": 1.302170283806344,
+      "grad_norm": 17.823730817956918,
+      "learning_rate": 1.392104352137426e-05,
+      "loss": 0.7874,
+      "step": 390
+    },
+    {
+      "epoch": 1.318864774624374,
+      "grad_norm": 19.683521817273643,
+      "learning_rate": 1.3741252816795552e-05,
+      "loss": 0.7827,
+      "step": 395
+    },
+    {
+      "epoch": 1.335559265442404,
+      "grad_norm": 11.92479858052398,
+      "learning_rate": 1.3560044700463824e-05,
+      "loss": 0.7802,
+      "step": 400
+    },
+    {
+      "epoch": 1.352253756260434,
+      "grad_norm": 16.848294314739636,
+      "learning_rate": 1.3377487824920459e-05,
+      "loss": 0.7937,
+      "step": 405
+    },
+    {
+      "epoch": 1.3689482470784642,
+      "grad_norm": 22.682558611391517,
+      "learning_rate": 1.3193651353698012e-05,
+      "loss": 0.7671,
+      "step": 410
+    },
+    {
+      "epoch": 1.3856427378964942,
+      "grad_norm": 16.087113575747633,
+      "learning_rate": 1.30086049351169e-05,
+      "loss": 0.7831,
+      "step": 415
+    },
+    {
+      "epoch": 1.4023372287145242,
+      "grad_norm": 16.405925048155012,
+      "learning_rate": 1.2822418675898428e-05,
+      "loss": 0.7665,
+      "step": 420
+    },
+    {
+      "epoch": 1.4190317195325544,
+      "grad_norm": 14.602601903009484,
+      "learning_rate": 1.2635163114604131e-05,
+      "loss": 0.7558,
+      "step": 425
+    },
+    {
+      "epoch": 1.4357262103505843,
+      "grad_norm": 18.515025497243688,
+      "learning_rate": 1.2446909194911552e-05,
+      "loss": 0.7791,
+      "step": 430
+    },
+    {
+      "epoch": 1.4524207011686143,
+      "grad_norm": 15.622061871111407,
+      "learning_rate": 1.2257728238736468e-05,
+      "loss": 0.7533,
+      "step": 435
+    },
+    {
+      "epoch": 1.4691151919866443,
+      "grad_norm": 15.421378645200017,
+      "learning_rate": 1.2067691919211879e-05,
+      "loss": 0.7446,
+      "step": 440
+    },
+    {
+      "epoch": 1.4858096828046745,
+      "grad_norm": 13.076444596991138,
+      "learning_rate": 1.1876872233533909e-05,
+      "loss": 0.7692,
+      "step": 445
+    },
+    {
+      "epoch": 1.5025041736227045,
+      "grad_norm": 15.097766901980801,
+      "learning_rate": 1.1685341475684935e-05,
+      "loss": 0.7533,
+      "step": 450
+    },
+    {
+      "epoch": 1.5191986644407347,
+      "grad_norm": 9.610701692201411,
+      "learning_rate": 1.1493172209044259e-05,
+      "loss": 0.7341,
+      "step": 455
+    },
+    {
+      "epoch": 1.5358931552587647,
+      "grad_norm": 14.24181191980203,
+      "learning_rate": 1.1300437238896758e-05,
+      "loss": 0.7486,
+      "step": 460
+    },
+    {
+      "epoch": 1.5525876460767947,
+      "grad_norm": 15.636653785170678,
+      "learning_rate": 1.1107209584849845e-05,
+      "loss": 0.747,
+      "step": 465
+    },
+    {
+      "epoch": 1.5692821368948247,
+      "grad_norm": 13.323220831047744,
+      "learning_rate": 1.0913562453169241e-05,
+      "loss": 0.77,
+      "step": 470
+    },
+    {
+      "epoch": 1.5859766277128546,
+      "grad_norm": 32.63260067379098,
+      "learning_rate": 1.0719569209044047e-05,
+      "loss": 1.0936,
+      "step": 475
+    },
+    {
+      "epoch": 1.6026711185308848,
+      "grad_norm": 10.450602758643768,
+      "learning_rate": 1.0525303348791599e-05,
+      "loss": 0.9183,
+      "step": 480
+    },
+    {
+      "epoch": 1.6193656093489148,
+      "grad_norm": 20.4536544538245,
+      "learning_rate": 1.0330838472012617e-05,
+      "loss": 0.8361,
+      "step": 485
+    },
+    {
+      "epoch": 1.636060100166945,
+      "grad_norm": 16.69213477924267,
+      "learning_rate": 1.0136248253707267e-05,
+      "loss": 0.7915,
+      "step": 490
+    },
+    {
+      "epoch": 1.652754590984975,
+      "grad_norm": 13.995256639718455,
+      "learning_rate": 9.94160641636263e-06,
+      "loss": 0.7643,
+      "step": 495
+    },
+    {
+      "epoch": 1.669449081803005,
+      "grad_norm": 13.608901583624743,
+      "learning_rate": 9.74698670202218e-06,
+      "loss": 0.771,
+      "step": 500
+    },
+    {
+      "epoch": 1.686143572621035,
+      "grad_norm": 13.753503798553933,
+      "learning_rate": 9.552462844347883e-06,
+      "loss": 0.7614,
+      "step": 505
+    },
+    {
+      "epoch": 1.702838063439065,
+      "grad_norm": 9.957240880648195,
+      "learning_rate": 9.358108540685406e-06,
+      "loss": 0.7312,
+      "step": 510
+    },
+    {
+      "epoch": 1.7195325542570952,
+      "grad_norm": 14.904981953953694,
+      "learning_rate": 9.163997424143167e-06,
+      "loss": 0.7388,
+      "step": 515
+    },
+    {
+      "epoch": 1.7362270450751254,
+      "grad_norm": 9.75471131334925,
+      "learning_rate": 8.970203035695662e-06,
+      "loss": 0.7502,
+      "step": 520
+    },
+    {
+      "epoch": 1.7529215358931554,
+      "grad_norm": 12.411472312082738,
+      "learning_rate": 8.776798796321715e-06,
+      "loss": 0.7348,
+      "step": 525
+    },
+    {
+      "epoch": 1.7696160267111853,
+      "grad_norm": 9.523945053556687,
+      "learning_rate": 8.583857979188203e-06,
+      "loss": 0.7361,
+      "step": 530
+    },
+    {
+      "epoch": 1.7863105175292153,
+      "grad_norm": 9.855371100134114,
+      "learning_rate": 8.391453681889772e-06,
+      "loss": 0.7532,
+      "step": 535
+    },
+    {
+      "epoch": 1.8030050083472453,
+      "grad_norm": 8.692313461538896,
+      "learning_rate": 8.199658798755048e-06,
+      "loss": 0.7855,
+      "step": 540
+    },
+    {
+      "epoch": 1.8196994991652755,
+      "grad_norm": 10.08176119888539,
+      "learning_rate": 8.008545993229897e-06,
+      "loss": 0.7381,
+      "step": 545
+    },
+    {
+      "epoch": 1.8363939899833055,
+      "grad_norm": 8.944907231752433,
+      "learning_rate": 7.818187670348133e-06,
+      "loss": 0.7195,
+      "step": 550
+    },
+    {
+      "epoch": 1.8530884808013357,
+      "grad_norm": 12.330352353476183,
+      "learning_rate": 7.628655949300133e-06,
+      "loss": 0.7542,
+      "step": 555
+    },
+    {
+      "epoch": 1.8697829716193657,
+      "grad_norm": 5.577454872729604,
+      "learning_rate": 7.440022636109742e-06,
+      "loss": 0.7504,
+      "step": 560
+    },
+    {
+      "epoch": 1.8864774624373957,
+      "grad_norm": 10.34792226158881,
+      "learning_rate": 7.2523591964298345e-06,
+      "loss": 0.7077,
+      "step": 565
+    },
+    {
+      "epoch": 1.9031719532554257,
+      "grad_norm": 12.209499576214666,
+      "learning_rate": 7.065736728466832e-06,
+      "loss": 0.7341,
+      "step": 570
+    },
+    {
+      "epoch": 1.9198664440734556,
+      "grad_norm": 9.887351733832002,
+      "learning_rate": 6.880225936044402e-06,
+      "loss": 0.733,
+      "step": 575
+    },
+    {
+      "epoch": 1.9365609348914858,
+      "grad_norm": 6.9361947084341224,
+      "learning_rate": 6.695897101816606e-06,
+      "loss": 0.7234,
+      "step": 580
+    },
+    {
+      "epoch": 1.9532554257095158,
+      "grad_norm": 5.155988536277592,
+      "learning_rate": 6.512820060640608e-06,
+      "loss": 0.7548,
+      "step": 585
+    },
+    {
+      "epoch": 1.969949916527546,
+      "grad_norm": 3.2935220347482312,
+      "learning_rate": 6.331064173119008e-06,
+      "loss": 0.7236,
+      "step": 590
+    },
+    {
+      "epoch": 1.986644407345576,
+      "grad_norm": 4.894307755407556,
+      "learning_rate": 6.150698299321889e-06,
+      "loss": 0.732,
+      "step": 595
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.025130271911621,
+      "eval_runtime": 51.5123,
+      "eval_samples_per_second": 37.137,
+      "eval_steps_per_second": 1.165,
+      "step": 599
+    },
+    {
+      "epoch": 2.003338898163606,
+      "grad_norm": 5.572538387405579,
+      "learning_rate": 5.971790772698467e-06,
+      "loss": 0.6828,
+      "step": 600
+    },
+    {
+      "epoch": 2.020033388981636,
+      "grad_norm": 10.00384584169959,
+      "learning_rate": 5.794409374188272e-06,
+      "loss": 0.4778,
+      "step": 605
+    },
+    {
+      "epoch": 2.036727879799666,
+      "grad_norm": 4.457469590156071,
+      "learning_rate": 5.61862130654165e-06,
+      "loss": 0.4757,
+      "step": 610
+    },
+    {
+      "epoch": 2.053422370617696,
+      "grad_norm": 5.015853492813808,
+      "learning_rate": 5.444493168859304e-06,
+      "loss": 0.4492,
+      "step": 615
+    },
+    {
+      "epoch": 2.0701168614357264,
+      "grad_norm": 4.283685547555074,
+      "learning_rate": 5.272090931360564e-06,
+      "loss": 0.4621,
+      "step": 620
+    },
+    {
+      "epoch": 2.0868113522537564,
+      "grad_norm": 3.0474708502514845,
+      "learning_rate": 5.101479910389888e-06,
+      "loss": 0.4749,
+      "step": 625
+    },
+    {
+      "epoch": 2.1035058430717863,
+      "grad_norm": 3.6032459713343465,
+      "learning_rate": 4.932724743671089e-06,
+      "loss": 0.4918,
+      "step": 630
+    },
+    {
+      "epoch": 2.1202003338898163,
+      "grad_norm": 3.422191932371061,
+      "learning_rate": 4.765889365818708e-06,
+      "loss": 0.463,
+      "step": 635
+    },
+    {
+      "epoch": 2.1368948247078463,
+      "grad_norm": 4.893888701972754,
+      "learning_rate": 4.601036984115684e-06,
+      "loss": 0.4729,
+      "step": 640
+    },
+    {
+      "epoch": 2.1535893155258763,
+      "grad_norm": 7.072549276322734,
+      "learning_rate": 4.438230054566678e-06,
+      "loss": 0.4597,
+      "step": 645
+    },
+    {
+      "epoch": 2.1702838063439067,
+      "grad_norm": 2.863464952941035,
+      "learning_rate": 4.277530258235955e-06,
+      "loss": 0.4733,
+      "step": 650
+    },
+    {
+      "epoch": 2.1869782971619367,
+      "grad_norm": 5.646193751997582,
+      "learning_rate": 4.118998477878879e-06,
+      "loss": 0.4729,
+      "step": 655
+    },
+    {
+      "epoch": 2.2036727879799667,
+      "grad_norm": 4.15359578652878,
+      "learning_rate": 3.96269477487588e-06,
+      "loss": 0.4885,
+      "step": 660
+    },
+    {
+      "epoch": 2.2203672787979967,
+      "grad_norm": 2.236298306259915,
+      "learning_rate": 3.8086783664775827e-06,
+      "loss": 0.443,
+      "step": 665
+    },
+    {
+      "epoch": 2.2370617696160267,
+      "grad_norm": 7.93104553530229,
+      "learning_rate": 3.657007603369728e-06,
+      "loss": 0.4665,
+      "step": 670
+    },
+    {
+      "epoch": 2.2537562604340566,
+      "grad_norm": 3.419578306650183,
+      "learning_rate": 3.5077399475664474e-06,
+      "loss": 0.4627,
+      "step": 675
+    },
+    {
+      "epoch": 2.2704507512520866,
+      "grad_norm": 2.4698290658247384,
+      "learning_rate": 3.360931950640185e-06,
+      "loss": 0.4825,
+      "step": 680
+    },
+    {
+      "epoch": 2.287145242070117,
+      "grad_norm": 2.7390623799111937,
+      "learning_rate": 3.2166392322965423e-06,
+      "loss": 0.4646,
+      "step": 685
+    },
+    {
+      "epoch": 2.303839732888147,
+      "grad_norm": 2.2546947544210107,
+      "learning_rate": 3.074916459302211e-06,
+      "loss": 0.4448,
+      "step": 690
+    },
+    {
+      "epoch": 2.320534223706177,
+      "grad_norm": 5.131657089417796,
+      "learning_rate": 2.935817324773893e-06,
+      "loss": 0.4541,
+      "step": 695
+    },
+    {
+      "epoch": 2.337228714524207,
+      "grad_norm": 2.268641469209863,
+      "learning_rate": 2.799394527836129e-06,
+      "loss": 0.4626,
+      "step": 700
+    },
+    {
+      "epoch": 2.353923205342237,
+      "grad_norm": 2.4065765494216573,
+      "learning_rate": 2.665699753655684e-06,
+      "loss": 0.455,
+      "step": 705
+    },
+    {
+      "epoch": 2.370617696160267,
+      "grad_norm": 3.1609792969658823,
+      "learning_rate": 2.5347836538601113e-06,
+      "loss": 0.4539,
+      "step": 710
+    },
+    {
+      "epoch": 2.3873121869782974,
+      "grad_norm": 2.163005176181913,
+      "learning_rate": 2.406695827347848e-06,
+      "loss": 0.4465,
+      "step": 715
+    },
+    {
+      "epoch": 2.4040066777963274,
+      "grad_norm": 2.3200939066770507,
+      "learning_rate": 2.281484801497186e-06,
+      "loss": 0.4434,
+      "step": 720
+    },
+    {
+      "epoch": 2.4207011686143574,
+      "grad_norm": 3.12558657263236,
+      "learning_rate": 2.1591980137811684e-06,
+      "loss": 0.4615,
+      "step": 725
+    },
+    {
+      "epoch": 2.4373956594323873,
+      "grad_norm": 2.379596526225785,
+      "learning_rate": 2.0398817937954275e-06,
+      "loss": 0.4438,
+      "step": 730
+    },
+    {
+      "epoch": 2.4540901502504173,
+      "grad_norm": 4.2220069539946685,
+      "learning_rate": 1.923581345705736e-06,
+      "loss": 0.4323,
+      "step": 735
+    },
+    {
+      "epoch": 2.4707846410684473,
+      "grad_norm": 2.0670454701693695,
+      "learning_rate": 1.8103407311219523e-06,
+      "loss": 0.4566,
+      "step": 740
+    },
+    {
+      "epoch": 2.4874791318864773,
+      "grad_norm": 4.378258400253472,
+      "learning_rate": 1.7002028524048354e-06,
+      "loss": 0.4343,
+      "step": 745
+    },
+    {
+      "epoch": 2.5041736227045073,
+      "grad_norm": 1.9839908799803745,
+      "learning_rate": 1.5932094364120453e-06,
+      "loss": 0.4498,
+      "step": 750
+    },
+    {
+      "epoch": 2.5208681135225377,
+      "grad_norm": 2.712434366093587,
+      "learning_rate": 1.489401018689488e-06,
+      "loss": 0.4367,
+      "step": 755
+    },
+    {
+      "epoch": 2.5375626043405677,
+      "grad_norm": 2.1865310419981996,
+      "learning_rate": 1.3888169281140284e-06,
+      "loss": 0.4425,
+      "step": 760
+    },
+    {
+      "epoch": 2.5542570951585977,
+      "grad_norm": 1.8978613598908045,
+      "learning_rate": 1.291495271993337e-06,
+      "loss": 0.445,
+      "step": 765
+    },
+    {
+      "epoch": 2.5709515859766277,
+      "grad_norm": 2.5804068184452884,
+      "learning_rate": 1.1974729216285386e-06,
+      "loss": 0.4423,
+      "step": 770
+    },
+    {
+      "epoch": 2.5876460767946576,
+      "grad_norm": 2.747544186566795,
+      "learning_rate": 1.1067854983451575e-06,
+      "loss": 0.4271,
+      "step": 775
+    },
+    {
+      "epoch": 2.604340567612688,
+      "grad_norm": 2.921731104304227,
+      "learning_rate": 1.0194673599976134e-06,
+      "loss": 0.4285,
+      "step": 780
+    },
+    {
+      "epoch": 2.621035058430718,
+      "grad_norm": 2.681611805642079,
+      "learning_rate": 9.355515879523858e-07,
+      "loss": 0.4216,
+      "step": 785
+    },
+    {
+      "epoch": 2.637729549248748,
+      "grad_norm": 2.3013460333352733,
+      "learning_rate": 8.550699745548196e-07,
+      "loss": 0.4427,
+      "step": 790
+    },
+    {
+      "epoch": 2.654424040066778,
+      "grad_norm": 2.1241926442770183,
+      "learning_rate": 7.780530110842566e-07,
+      "loss": 0.4564,
+      "step": 795
+    },
+    {
+      "epoch": 2.671118530884808,
+      "grad_norm": 2.1094322480698446,
+      "learning_rate": 7.045298762021125e-07,
+      "loss": 0.4212,
+      "step": 800
+    },
+    {
+      "epoch": 2.687813021702838,
+      "grad_norm": 2.065126476385816,
+      "learning_rate": 6.345284248972383e-07,
+      "loss": 0.4343,
+      "step": 805
+    },
+    {
+      "epoch": 2.704507512520868,
+      "grad_norm": 2.111310955387196,
+      "learning_rate": 5.680751779327742e-07,
+      "loss": 0.4303,
+      "step": 810
+    },
+    {
+      "epoch": 2.721202003338898,
+      "grad_norm": 1.8695554654021782,
+      "learning_rate": 5.05195311798491e-07,
+      "loss": 0.4273,
+      "step": 815
+    },
+    {
+      "epoch": 2.7378964941569284,
+      "grad_norm": 1.7653322997367364,
+      "learning_rate": 4.4591264917242195e-07,
+      "loss": 0.4194,
+      "step": 820
+    },
+    {
+      "epoch": 2.7545909849749584,
+      "grad_norm": 2.580982327606043,
+      "learning_rate": 3.9024964989539227e-07,
+      "loss": 0.4364,
+      "step": 825
+    },
+    {
+      "epoch": 2.7712854757929883,
+      "grad_norm": 2.3745636013022393,
+      "learning_rate": 3.3822740246188477e-07,
+      "loss": 0.4221,
+      "step": 830
+    },
+    {
+      "epoch": 2.7879799666110183,
+      "grad_norm": 1.7954651271213284,
+      "learning_rate": 2.8986561603044694e-07,
+      "loss": 0.4419,
+      "step": 835
+    },
+    {
+      "epoch": 2.8046744574290483,
+      "grad_norm": 1.7817436931187334,
+      "learning_rate": 2.4518261295667255e-07,
+      "loss": 0.4256,
+      "step": 840
+    },
+    {
+      "epoch": 2.8213689482470787,
+      "grad_norm": 1.9832033151678319,
+      "learning_rate": 2.0419532185159796e-07,
+      "loss": 0.4377,
+      "step": 845
+    },
+    {
+      "epoch": 2.8380634390651087,
+      "grad_norm": 2.1044988631805936,
+      "learning_rate": 1.6691927116812002e-07,
+      "loss": 0.4227,
+      "step": 850
+    },
+    {
+      "epoch": 2.8547579298831387,
+      "grad_norm": 1.7105569326916548,
+      "learning_rate": 1.3336858331787993e-07,
+      "loss": 0.4348,
+      "step": 855
+    },
+    {
+      "epoch": 2.8714524207011687,
+      "grad_norm": 1.8507017140571933,
+      "learning_rate": 1.0355596932085432e-07,
+      "loss": 0.4409,
+      "step": 860
+    },
+    {
+      "epoch": 2.8881469115191987,
+      "grad_norm": 2.064062762183687,
+      "learning_rate": 7.749272398964613e-08,
+      "loss": 0.4144,
+      "step": 865
+    },
+    {
+      "epoch": 2.9048414023372287,
+      "grad_norm": 1.719486823729206,
+      "learning_rate": 5.518872165033329e-08,
+      "loss": 0.4111,
+      "step": 870
+    },
+    {
+      "epoch": 2.9215358931552586,
+      "grad_norm": 1.8799918395529704,
+      "learning_rate": 3.6652412401478875e-08,
+      "loss": 0.4193,
+      "step": 875
+    },
+    {
+      "epoch": 2.9382303839732886,
+      "grad_norm": 1.8770289189731946,
+      "learning_rate": 2.1890818912728706e-08,
+      "loss": 0.4236,
+      "step": 880
+    },
+    {
+      "epoch": 2.9549248747913186,
+      "grad_norm": 1.7627043794208022,
+      "learning_rate": 1.0909533764194013e-08,
+      "loss": 0.4139,
+      "step": 885
+    },
+    {
+      "epoch": 2.971619365609349,
+      "grad_norm": 1.734409436675283,
+      "learning_rate": 3.7127173276563234e-09,
+      "loss": 0.4253,
+      "step": 890
+    },
+    {
+      "epoch": 2.988313856427379,
+      "grad_norm": 1.7460091881103872,
+      "learning_rate": 3.0309619035495675e-10,
+      "loss": 0.4257,
+      "step": 895
+    },
+    {
+      "epoch": 2.994991652754591,
+      "eval_loss": 1.0814331769943237,
+      "eval_runtime": 51.3381,
+      "eval_samples_per_second": 37.263,
+      "eval_steps_per_second": 1.169,
+      "step": 897
+    },
+    {
+      "epoch": 2.994991652754591,
+      "step": 897,
+      "total_flos": 246978202042368.0,
+      "train_loss": 0.8794620578637224,
+      "train_runtime": 12081.5129,
+      "train_samples_per_second": 9.517,
+      "train_steps_per_second": 0.074
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 897,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 246978202042368.0,
+  "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:de5f0d42053febd7b4e3d55e5da1c30a7ae96f95423d9aca9d7e192ad1920a07
+size 6264