Model save

README.md

@@ -0,0 +1,69 @@
+---
+license: other
+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: 0.9732
+
+## 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: 16
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9482        | 1.0   | 299  | 0.9848          |
+| 0.8139        | 2.0   | 599  | 0.9610          |
+| 0.722         | 2.99  | 897  | 0.9732          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.99,
+    "eval_loss": 0.973169207572937,
+    "eval_runtime": 22.1864,
+    "eval_samples": 500,
+    "eval_samples_per_second": 86.224,
+    "eval_steps_per_second": 1.352,
+    "train_loss": 1.0022602648772259,
+    "train_runtime": 5184.357,
+    "train_samples": 9500,
+    "train_samples_per_second": 22.178,
+    "train_steps_per_second": 0.173
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "eval_loss": 0.973169207572937,
+    "eval_runtime": 22.1864,
+    "eval_samples": 500,
+    "eval_samples_per_second": 86.224,
+    "eval_steps_per_second": 1.352
+}

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10276a0f87e08f62e2829230be70ff541d6e234ffe356ddbf25abeb57433c01b
+size 4995496656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad38dd72c60feb83f5f94b7c637f876a74d27a50fc122da30bf35b3213802a41
+size 4982953168

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291250b5d90bd318addab6e1df790bf70cb702814540fbeff26a67d06ee5371c
+size 4982953200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809106cf81c8dfa99d1e3e223e42289fc3b51f1227bfdf9070c4fd113858a448
+size 2113988336

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 17075361792
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/Mar01_09-22-26_ip-26-0-165-24/events.out.tfevents.1709284978.ip-26-0-165-24.1220823.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c6305f097b33203a58255f7c860be608ff35e3366bf162a26397f76c7a5338
+size 43817

runs/Mar01_09-22-26_ip-26-0-165-24/events.out.tfevents.1709290184.ip-26-0-165-24.1220823.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee2478a35515eaf14f48add419945785551e9382ec4eb1f857826a9729a79b2
+size 359

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "train_loss": 1.0022602648772259,
+    "train_runtime": 5184.357,
+    "train_samples": 9500,
+    "train_samples_per_second": 22.178,
+    "train_steps_per_second": 0.173
+}

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": 0.0,
+      "grad_norm": 1554.4859195078177,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 13.9835,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1214.7457310015889,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 13.3423,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 319.25263582700893,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 7.1598,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 101.74884085779856,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 3.257,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 39.750398897218815,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 2.3046,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 39.73415841304385,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 2.0193,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 22.603785465724318,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.803,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 13.57277760359388,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.6723,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 10.745675701951754,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.6164,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 11.48936807248645,
+      "learning_rate": 1e-05,
+      "loss": 1.5651,
+      "step": 45
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 6.759355981336981,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.5031,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 9.542982258251046,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 1.4295,
+      "step": 55
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.960957372064927,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3752,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 65.24876161518675,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 1.3768,
+      "step": 65
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 127.017819160354,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 1.3837,
+      "step": 70
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 66.80311438981465,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2844,
+      "step": 75
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 45.06752723588582,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 1.1568,
+      "step": 80
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 16.607018601484466,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.1208,
+      "step": 85
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.20855793840101,
+      "learning_rate": 2e-05,
+      "loss": 1.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.970187327270322,
+      "learning_rate": 1.9998105699049984e-05,
+      "loss": 1.087,
+      "step": 95
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 9.207660040111582,
+      "learning_rate": 1.9992423513875158e-05,
+      "loss": 1.0611,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 11.032251244972851,
+      "learning_rate": 1.9982955597229275e-05,
+      "loss": 1.055,
+      "step": 105
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 7.70794959419036,
+      "learning_rate": 1.9969705536129033e-05,
+      "loss": 1.0494,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.115775243109966,
+      "learning_rate": 1.9952678350495104e-05,
+      "loss": 1.03,
+      "step": 115
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.185703416946629,
+      "learning_rate": 1.9931880491250263e-05,
+      "loss": 1.0341,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.719162959123087,
+      "learning_rate": 1.990731983787542e-05,
+      "loss": 1.0433,
+      "step": 125
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 12.405446493626323,
+      "learning_rate": 1.987900569542438e-05,
+      "loss": 1.0496,
+      "step": 130
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 13.49655125076312,
+      "learning_rate": 1.9846948790998532e-05,
+      "loss": 1.0155,
+      "step": 135
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 7.942566346935867,
+      "learning_rate": 1.9811161269682776e-05,
+      "loss": 1.0249,
+      "step": 140
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.540779868090953,
+      "learning_rate": 1.9771656689944238e-05,
+      "loss": 1.0094,
+      "step": 145
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.71935614128467,
+      "learning_rate": 1.9728450018495506e-05,
+      "loss": 1.0363,
+      "step": 150
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 8.301612111722024,
+      "learning_rate": 1.968155762462433e-05,
+      "loss": 0.9804,
+      "step": 155
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 4.611128256903672,
+      "learning_rate": 1.9630997273991964e-05,
+      "loss": 0.99,
+      "step": 160
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 6.349166471933137,
+      "learning_rate": 1.9576788121902457e-05,
+      "loss": 0.974,
+      "step": 165
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 4.709847602929964,
+      "learning_rate": 1.951895070604547e-05,
+      "loss": 0.9771,
+      "step": 170
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.952845884539213,
+      "learning_rate": 1.9457506938715357e-05,
+      "loss": 1.0052,
+      "step": 175
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.4487385859558914,
+      "learning_rate": 1.9392480098509488e-05,
+      "loss": 0.9863,
+      "step": 180
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.258252581584813,
+      "learning_rate": 1.93238948215089e-05,
+      "loss": 0.9766,
+      "step": 185
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 4.480190590593033,
+      "learning_rate": 1.9251777091944665e-05,
+      "loss": 0.9981,
+      "step": 190
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 7.433883383226472,
+      "learning_rate": 1.9176154232353513e-05,
+      "loss": 0.9985,
+      "step": 195
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 4.227680033826242,
+      "learning_rate": 1.9097054893226395e-05,
+      "loss": 0.9709,
+      "step": 200
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.5498806463564025,
+      "learning_rate": 1.9014509042153964e-05,
+      "loss": 1.0064,
+      "step": 205
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.8662258274644032,
+      "learning_rate": 1.8928547952473037e-05,
+      "loss": 0.9557,
+      "step": 210
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 6.516418186408566,
+      "learning_rate": 1.8839204191418386e-05,
+      "loss": 0.9499,
+      "step": 215
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 6.638325575394558,
+      "learning_rate": 1.8746511607784298e-05,
+      "loss": 0.9832,
+      "step": 220
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 7.49893501725385,
+      "learning_rate": 1.865050531910062e-05,
+      "loss": 0.9535,
+      "step": 225
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 6.04469353811688,
+      "learning_rate": 1.855122169832813e-05,
+      "loss": 0.947,
+      "step": 230
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.3984302418422536,
+      "learning_rate": 1.844869836007825e-05,
+      "loss": 0.9592,
+      "step": 235
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.599537518194927,
+      "learning_rate": 1.8342974146362397e-05,
+      "loss": 0.9938,
+      "step": 240
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.5743133672120875,
+      "learning_rate": 1.8234089111876256e-05,
+      "loss": 0.9375,
+      "step": 245
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.153578666049746,
+      "learning_rate": 1.8122084508824692e-05,
+      "loss": 0.9503,
+      "step": 250
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.358976477421789,
+      "learning_rate": 1.80070027712929e-05,
+      "loss": 0.9405,
+      "step": 255
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.715023563708574,
+      "learning_rate": 1.7888887499169816e-05,
+      "loss": 0.9448,
+      "step": 260
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.540308197945189,
+      "learning_rate": 1.7767783441629883e-05,
+      "loss": 0.9518,
+      "step": 265
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.61899118162512,
+      "learning_rate": 1.7643736480179353e-05,
+      "loss": 0.9331,
+      "step": 270
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.8933823492498987,
+      "learning_rate": 1.7516793611273614e-05,
+      "loss": 0.9402,
+      "step": 275
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.402077716843347,
+      "learning_rate": 1.7387002928512093e-05,
+      "loss": 0.9427,
+      "step": 280
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.439064477908216,
+      "learning_rate": 1.725441360441752e-05,
+      "loss": 0.9689,
+      "step": 285
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 4.228994650655801,
+      "learning_rate": 1.711907587180642e-05,
+      "loss": 0.922,
+      "step": 290
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.352694277486445,
+      "learning_rate": 1.698104100475788e-05,
+      "loss": 0.9482,
+      "step": 295
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9848138093948364,
+      "eval_runtime": 21.922,
+      "eval_samples_per_second": 87.264,
+      "eval_steps_per_second": 1.368,
+      "step": 299
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.7344611256762605,
+      "learning_rate": 1.684036129918786e-05,
+      "loss": 0.9147,
+      "step": 300
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 7.808442765171335,
+      "learning_rate": 1.6697090053036344e-05,
+      "loss": 0.872,
+      "step": 305
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 4.265041320808819,
+      "learning_rate": 1.6551281546074863e-05,
+      "loss": 0.8276,
+      "step": 310
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 11.609187861418906,
+      "learning_rate": 1.6402991019342073e-05,
+      "loss": 0.8501,
+      "step": 315
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 6.4050483054707765,
+      "learning_rate": 1.625227465421511e-05,
+      "loss": 0.8722,
+      "step": 320
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 4.007163655718817,
+      "learning_rate": 1.60991895511247e-05,
+      "loss": 0.8791,
+      "step": 325
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 6.169584899822902,
+      "learning_rate": 1.5943793707922086e-05,
+      "loss": 0.8378,
+      "step": 330
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 5.702556304345057,
+      "learning_rate": 1.5786145997905952e-05,
+      "loss": 0.8529,
+      "step": 335
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 3.666829882865862,
+      "learning_rate": 1.5626306147517665e-05,
+      "loss": 0.8625,
+      "step": 340
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 7.196219177199569,
+      "learning_rate": 1.5464334713713312e-05,
+      "loss": 0.846,
+      "step": 345
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 4.360948957874904,
+      "learning_rate": 1.5300293061021084e-05,
+      "loss": 0.8504,
+      "step": 350
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 3.985490385252694,
+      "learning_rate": 1.5134243338292686e-05,
+      "loss": 0.8722,
+      "step": 355
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.45100120259278,
+      "learning_rate": 1.4966248455157622e-05,
+      "loss": 0.8322,
+      "step": 360
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 5.266623346917125,
+      "learning_rate": 1.4796372058189235e-05,
+      "loss": 0.8284,
+      "step": 365
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 3.8641643965703647,
+      "learning_rate": 1.4624678506791556e-05,
+      "loss": 0.8482,
+      "step": 370
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 5.041022068055208,
+      "learning_rate": 1.445123284881609e-05,
+      "loss": 0.8301,
+      "step": 375
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 3.3180915430698654,
+      "learning_rate": 1.4276100795917777e-05,
+      "loss": 0.8208,
+      "step": 380
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 6.201419840904921,
+      "learning_rate": 1.409934869865945e-05,
+      "loss": 0.8571,
+      "step": 385
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 7.459788747214111,
+      "learning_rate": 1.392104352137426e-05,
+      "loss": 0.8569,
+      "step": 390
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 6.709652163052175,
+      "learning_rate": 1.3741252816795552e-05,
+      "loss": 0.8622,
+      "step": 395
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 3.473788351536053,
+      "learning_rate": 1.3560044700463824e-05,
+      "loss": 0.8577,
+      "step": 400
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 3.5872538636448805,
+      "learning_rate": 1.3377487824920459e-05,
+      "loss": 0.86,
+      "step": 405
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 5.307258675746272,
+      "learning_rate": 1.3193651353698012e-05,
+      "loss": 0.8229,
+      "step": 410
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 4.804376190916538,
+      "learning_rate": 1.30086049351169e-05,
+      "loss": 0.8249,
+      "step": 415
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 4.476642767728941,
+      "learning_rate": 1.2822418675898428e-05,
+      "loss": 0.815,
+      "step": 420
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 3.662676271025836,
+      "learning_rate": 1.2635163114604131e-05,
+      "loss": 0.8322,
+      "step": 425
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 5.33760518542071,
+      "learning_rate": 1.2446909194911552e-05,
+      "loss": 0.8283,
+      "step": 430
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 3.6241603881416093,
+      "learning_rate": 1.2257728238736468e-05,
+      "loss": 0.8419,
+      "step": 435
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 8.345200463380893,
+      "learning_rate": 1.2067691919211879e-05,
+      "loss": 0.8431,
+      "step": 440
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 5.157020256989829,
+      "learning_rate": 1.1876872233533909e-05,
+      "loss": 0.8341,
+      "step": 445
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.22959672388336,
+      "learning_rate": 1.1685341475684935e-05,
+      "loss": 0.8238,
+      "step": 450
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 4.075617092942542,
+      "learning_rate": 1.1493172209044259e-05,
+      "loss": 0.8246,
+      "step": 455
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 4.130669786993403,
+      "learning_rate": 1.1300437238896758e-05,
+      "loss": 0.8587,
+      "step": 460
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.8344057909806653,
+      "learning_rate": 1.1107209584849845e-05,
+      "loss": 0.8405,
+      "step": 465
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 4.419191495305873,
+      "learning_rate": 1.0913562453169241e-05,
+      "loss": 0.8513,
+      "step": 470
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 3.639847517010915,
+      "learning_rate": 1.0719569209044047e-05,
+      "loss": 0.8268,
+      "step": 475
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 6.0850406807943695,
+      "learning_rate": 1.0525303348791599e-05,
+      "loss": 0.835,
+      "step": 480
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 4.663234575938155,
+      "learning_rate": 1.0330838472012617e-05,
+      "loss": 0.8297,
+      "step": 485
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 2.952245938431757,
+      "learning_rate": 1.0136248253707267e-05,
+      "loss": 0.8435,
+      "step": 490
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 3.1679752592105435,
+      "learning_rate": 9.94160641636263e-06,
+      "loss": 0.8409,
+      "step": 495
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.2886951326936753,
+      "learning_rate": 9.74698670202218e-06,
+      "loss": 0.811,
+      "step": 500
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 3.114045037749334,
+      "learning_rate": 9.552462844347883e-06,
+      "loss": 0.847,
+      "step": 505
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 3.537647563076529,
+      "learning_rate": 9.358108540685406e-06,
+      "loss": 0.8272,
+      "step": 510
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 3.41342205194864,
+      "learning_rate": 9.163997424143167e-06,
+      "loss": 0.8435,
+      "step": 515
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 4.382615756695022,
+      "learning_rate": 8.970203035695662e-06,
+      "loss": 0.8241,
+      "step": 520
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 6.06775300616703,
+      "learning_rate": 8.776798796321715e-06,
+      "loss": 0.8328,
+      "step": 525
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 6.410082659319438,
+      "learning_rate": 8.583857979188203e-06,
+      "loss": 0.832,
+      "step": 530
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 5.6018541648497715,
+      "learning_rate": 8.391453681889772e-06,
+      "loss": 0.8477,
+      "step": 535
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.110209003561718,
+      "learning_rate": 8.199658798755048e-06,
+      "loss": 0.8365,
+      "step": 540
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 3.2444930006535078,
+      "learning_rate": 8.008545993229897e-06,
+      "loss": 0.8519,
+      "step": 545
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 3.25930172152866,
+      "learning_rate": 7.818187670348133e-06,
+      "loss": 0.8455,
+      "step": 550
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 3.1738586241269706,
+      "learning_rate": 7.628655949300133e-06,
+      "loss": 0.8451,
+      "step": 555
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.1977554967249144,
+      "learning_rate": 7.440022636109742e-06,
+      "loss": 0.8263,
+      "step": 560
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 5.738948608123997,
+      "learning_rate": 7.2523591964298345e-06,
+      "loss": 0.8246,
+      "step": 565
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.650496523890181,
+      "learning_rate": 7.065736728466832e-06,
+      "loss": 0.821,
+      "step": 570
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 3.3610021866091073,
+      "learning_rate": 6.880225936044402e-06,
+      "loss": 0.8039,
+      "step": 575
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 3.4144579406106996,
+      "learning_rate": 6.695897101816606e-06,
+      "loss": 0.8081,
+      "step": 580
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 4.538437452063136,
+      "learning_rate": 6.512820060640608e-06,
+      "loss": 0.8334,
+      "step": 585
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 4.895649774301149,
+      "learning_rate": 6.331064173119008e-06,
+      "loss": 0.8063,
+      "step": 590
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 3.373177420856697,
+      "learning_rate": 6.150698299321889e-06,
+      "loss": 0.8139,
+      "step": 595
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9609715938568115,
+      "eval_runtime": 23.563,
+      "eval_samples_per_second": 81.187,
+      "eval_steps_per_second": 1.273,
+      "step": 599
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.9256303288824705,
+      "learning_rate": 5.971790772698467e-06,
+      "loss": 0.7915,
+      "step": 600
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 4.385016578281952,
+      "learning_rate": 5.794409374188272e-06,
+      "loss": 0.7106,
+      "step": 605
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 4.602412318513612,
+      "learning_rate": 5.61862130654165e-06,
+      "loss": 0.701,
+      "step": 610
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 4.466214253217951,
+      "learning_rate": 5.444493168859304e-06,
+      "loss": 0.7118,
+      "step": 615
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 3.3100514145049678,
+      "learning_rate": 5.272090931360564e-06,
+      "loss": 0.7004,
+      "step": 620
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 2.9902764365530023,
+      "learning_rate": 5.101479910389888e-06,
+      "loss": 0.7177,
+      "step": 625
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 2.960756149194766,
+      "learning_rate": 4.932724743671089e-06,
+      "loss": 0.7061,
+      "step": 630
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 3.3796322175614093,
+      "learning_rate": 4.765889365818708e-06,
+      "loss": 0.7243,
+      "step": 635
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 3.068706242207435,
+      "learning_rate": 4.601036984115684e-06,
+      "loss": 0.7138,
+      "step": 640
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 2.949462217015265,
+      "learning_rate": 4.438230054566678e-06,
+      "loss": 0.6921,
+      "step": 645
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 2.9285837942249935,
+      "learning_rate": 4.277530258235955e-06,
+      "loss": 0.7087,
+      "step": 650
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 2.8241960382183517,
+      "learning_rate": 4.118998477878879e-06,
+      "loss": 0.692,
+      "step": 655
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 3.754111606827016,
+      "learning_rate": 3.96269477487588e-06,
+      "loss": 0.7036,
+      "step": 660
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 2.801260790695992,
+      "learning_rate": 3.8086783664775827e-06,
+      "loss": 0.703,
+      "step": 665
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 3.5205014160146484,
+      "learning_rate": 3.657007603369728e-06,
+      "loss": 0.6837,
+      "step": 670
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 2.957347255235954,
+      "learning_rate": 3.5077399475664474e-06,
+      "loss": 0.716,
+      "step": 675
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 3.0699352110382394,
+      "learning_rate": 3.360931950640185e-06,
+      "loss": 0.7159,
+      "step": 680
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 2.8837481146108077,
+      "learning_rate": 3.2166392322965423e-06,
+      "loss": 0.688,
+      "step": 685
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 2.763237253733171,
+      "learning_rate": 3.074916459302211e-06,
+      "loss": 0.7158,
+      "step": 690
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 3.355328029300809,
+      "learning_rate": 2.935817324773893e-06,
+      "loss": 0.7046,
+      "step": 695
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 2.8914814523547587,
+      "learning_rate": 2.799394527836129e-06,
+      "loss": 0.7096,
+      "step": 700
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 3.5718163510342014,
+      "learning_rate": 2.665699753655684e-06,
+      "loss": 0.6984,
+      "step": 705
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 3.2223677480030157,
+      "learning_rate": 2.5347836538601113e-06,
+      "loss": 0.6906,
+      "step": 710
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 2.7101631013279373,
+      "learning_rate": 2.406695827347848e-06,
+      "loss": 0.7229,
+      "step": 715
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.9181738000190482,
+      "learning_rate": 2.281484801497186e-06,
+      "loss": 0.7161,
+      "step": 720
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 2.7148342264509067,
+      "learning_rate": 2.1591980137811684e-06,
+      "loss": 0.6911,
+      "step": 725
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 2.645866837308739,
+      "learning_rate": 2.0398817937954275e-06,
+      "loss": 0.6935,
+      "step": 730
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 2.923721171986238,
+      "learning_rate": 1.923581345705736e-06,
+      "loss": 0.7012,
+      "step": 735
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 2.5730130782483767,
+      "learning_rate": 1.8103407311219523e-06,
+      "loss": 0.7001,
+      "step": 740
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 3.1294946465675535,
+      "learning_rate": 1.7002028524048354e-06,
+      "loss": 0.6849,
+      "step": 745
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.9432875746786955,
+      "learning_rate": 1.5932094364120453e-06,
+      "loss": 0.6834,
+      "step": 750
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 2.951328262763639,
+      "learning_rate": 1.489401018689488e-06,
+      "loss": 0.6893,
+      "step": 755
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 3.0873225694591886,
+      "learning_rate": 1.3888169281140284e-06,
+      "loss": 0.6672,
+      "step": 760
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 2.9951086396524285,
+      "learning_rate": 1.291495271993337e-06,
+      "loss": 0.7005,
+      "step": 765
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 2.6961455349482057,
+      "learning_rate": 1.1974729216285386e-06,
+      "loss": 0.7047,
+      "step": 770
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 2.7063424423455777,
+      "learning_rate": 1.1067854983451575e-06,
+      "loss": 0.6874,
+      "step": 775
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 2.969350173180754,
+      "learning_rate": 1.0194673599976134e-06,
+      "loss": 0.6954,
+      "step": 780
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 2.8241124873176804,
+      "learning_rate": 9.355515879523858e-07,
+      "loss": 0.7151,
+      "step": 785
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 2.703842291084545,
+      "learning_rate": 8.550699745548196e-07,
+      "loss": 0.7051,
+      "step": 790
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 2.52014475737678,
+      "learning_rate": 7.780530110842566e-07,
+      "loss": 0.7032,
+      "step": 795
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 2.8940329465111967,
+      "learning_rate": 7.045298762021125e-07,
+      "loss": 0.696,
+      "step": 800
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 2.715730102462268,
+      "learning_rate": 6.345284248972383e-07,
+      "loss": 0.6594,
+      "step": 805
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 2.562152086335658,
+      "learning_rate": 5.680751779327742e-07,
+      "loss": 0.6882,
+      "step": 810
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 2.753866693209901,
+      "learning_rate": 5.05195311798491e-07,
+      "loss": 0.6929,
+      "step": 815
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 2.5848331829143225,
+      "learning_rate": 4.4591264917242195e-07,
+      "loss": 0.6914,
+      "step": 820
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 2.656019725897738,
+      "learning_rate": 3.9024964989539227e-07,
+      "loss": 0.6997,
+      "step": 825
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 2.6710040716803927,
+      "learning_rate": 3.3822740246188477e-07,
+      "loss": 0.7042,
+      "step": 830
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 2.797959120368719,
+      "learning_rate": 2.8986561603044694e-07,
+      "loss": 0.717,
+      "step": 835
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.6446312241054803,
+      "learning_rate": 2.4518261295667255e-07,
+      "loss": 0.6838,
+      "step": 840
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 2.6673940520178836,
+      "learning_rate": 2.0419532185159796e-07,
+      "loss": 0.7003,
+      "step": 845
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 2.697047820136764,
+      "learning_rate": 1.6691927116812002e-07,
+      "loss": 0.6936,
+      "step": 850
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 2.5372070358560843,
+      "learning_rate": 1.3336858331787993e-07,
+      "loss": 0.6913,
+      "step": 855
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 2.5976068799798187,
+      "learning_rate": 1.0355596932085432e-07,
+      "loss": 0.694,
+      "step": 860
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 2.922996849182434,
+      "learning_rate": 7.749272398964613e-08,
+      "loss": 0.703,
+      "step": 865
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 2.53597875366406,
+      "learning_rate": 5.518872165033329e-08,
+      "loss": 0.6936,
+      "step": 870
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 2.7025680089043584,
+      "learning_rate": 3.6652412401478875e-08,
+      "loss": 0.6911,
+      "step": 875
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 2.6197435490839873,
+      "learning_rate": 2.1890818912728706e-08,
+      "loss": 0.7137,
+      "step": 880
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 2.6370913398207825,
+      "learning_rate": 1.0909533764194013e-08,
+      "loss": 0.7064,
+      "step": 885
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 2.7175545973145687,
+      "learning_rate": 3.7127173276563234e-09,
+      "loss": 0.7116,
+      "step": 890
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 2.796693677065229,
+      "learning_rate": 3.0309619035495675e-10,
+      "loss": 0.722,
+      "step": 895
+    },
+    {
+      "epoch": 2.99,
+      "eval_loss": 0.973169207572937,
+      "eval_runtime": 24.5227,
+      "eval_samples_per_second": 78.009,
+      "eval_steps_per_second": 1.223,
+      "step": 897
+    },
+    {
+      "epoch": 2.99,
+      "step": 897,
+      "total_flos": 246909348347904.0,
+      "train_loss": 1.0022602648772259,
+      "train_runtime": 5184.357,
+      "train_samples_per_second": 22.178,
+      "train_steps_per_second": 0.173
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 897,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 246909348347904.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b5a27b6cd0df95bd2ace06a78a88778f8b435939eb4809c5c95fed96373791b
+oid sha256:d0a06e56d184015f335160e8faa60d328056eb5ec077b25524ae96311c4b8019
 size 6136