Model save

.gitattributes

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

README.md

@@ -0,0 +1,62 @@
+---
+license: other
+base_model: google/gemma-7b
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: gemma-7b-sft-full-deita-10k-v0
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gemma-7b-sft-full-deita-10k-v0
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 128
+- 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
+
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "train_loss": 1.0102584746104553,
+    "train_runtime": 5029.5541,
+    "train_samples": 9500,
+    "train_samples_per_second": 22.861,
+    "train_steps_per_second": 0.178
+}

config.json

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

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd7c1a97e7fce0e4c931e5b71a56375c5177f88f56df74fa914458fed3dab67
+size 4995496656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af2d45d1afc3f1aa1109b194f97afb3ec1c0da3bf5bb4808c076657d0890b17
+size 4982953168

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f7bd6ce0aac24da11e0d16ecff0c43572d39be9782b03a956e27d8e9d8efde
+size 4982953200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6760ea6ed166c1286837dd36ed8675aa1f900f69905a3b7a8002e14f660efc83
+size 2113988336

model.safetensors.index.json

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

runs/Feb29_14-35-38_ip-26-0-166-244/events.out.tfevents.1709217561.ip-26-0-166-244.3503402.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e94801fda6f4c941cd46f4bd55cd122c3d9b8e29f94ab1c37e7a8c685bcb1a
+size 4933

runs/Feb29_14-40-22_ip-26-0-166-244/events.out.tfevents.1709217651.ip-26-0-166-244.3505275.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e65ff7e088bd456f847ca03823fa8a44462667d2763dd4c2fcda31e5e06f9c
+size 42956

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.99,
+    "train_loss": 1.0102584746104553,
+    "train_runtime": 5029.5541,
+    "train_samples": 9500,
+    "train_samples_per_second": 22.861,
+    "train_steps_per_second": 0.178
+}

trainer_state.json

@@ -0,0 +1,1290 @@
+{
+  "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": 1611.325982263448,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 14.3706,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1203.709045070288,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 14.0095,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 317.62260508814944,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 7.0245,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 140.7698798601618,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 3.2406,
+      "step": 15
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 53.214014098542116,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 2.3518,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 32.80877069708861,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.9155,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 18.406728342109837,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.7744,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 15.70206361537138,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.6662,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 9.680796676938787,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.5805,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 9.949620133147931,
+      "learning_rate": 1e-05,
+      "loss": 1.5108,
+      "step": 45
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 17.89818156462526,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.4516,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 9.463874703914655,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 1.386,
+      "step": 55
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 16.600372205018896,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3472,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.591121067230071,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 1.3051,
+      "step": 65
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 17.026560958812688,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 1.2846,
+      "step": 70
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 11.244332052116006,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2202,
+      "step": 75
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 21.171092249623154,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 1.1422,
+      "step": 80
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 79.69525524449374,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.2502,
+      "step": 85
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 48.3592163956308,
+      "learning_rate": 2e-05,
+      "loss": 1.3437,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 31.60366391829559,
+      "learning_rate": 1.9998105699049984e-05,
+      "loss": 1.2415,
+      "step": 95
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 14.941685751929072,
+      "learning_rate": 1.9992423513875158e-05,
+      "loss": 1.1521,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 10.723912828129833,
+      "learning_rate": 1.9982955597229275e-05,
+      "loss": 1.1428,
+      "step": 105
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.661132660781078,
+      "learning_rate": 1.9969705536129033e-05,
+      "loss": 1.1019,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 11.84763200258169,
+      "learning_rate": 1.9952678350495104e-05,
+      "loss": 1.0693,
+      "step": 115
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.584094081913566,
+      "learning_rate": 1.9931880491250263e-05,
+      "loss": 1.06,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.687346480648606,
+      "learning_rate": 1.990731983787542e-05,
+      "loss": 1.0754,
+      "step": 125
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 8.02176533763531,
+      "learning_rate": 1.987900569542438e-05,
+      "loss": 1.0656,
+      "step": 130
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.890194579215236,
+      "learning_rate": 1.9846948790998532e-05,
+      "loss": 1.0494,
+      "step": 135
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.573476232049487,
+      "learning_rate": 1.9811161269682776e-05,
+      "loss": 1.0246,
+      "step": 140
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.9288708942568094,
+      "learning_rate": 1.9771656689944238e-05,
+      "loss": 1.031,
+      "step": 145
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.4500277726115267,
+      "learning_rate": 1.9728450018495506e-05,
+      "loss": 1.0133,
+      "step": 150
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.717186694916964,
+      "learning_rate": 1.968155762462433e-05,
+      "loss": 0.9788,
+      "step": 155
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 5.124236034673133,
+      "learning_rate": 1.9630997273991964e-05,
+      "loss": 1.0098,
+      "step": 160
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 6.845307185570511,
+      "learning_rate": 1.9576788121902457e-05,
+      "loss": 1.0105,
+      "step": 165
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 4.010533684726192,
+      "learning_rate": 1.951895070604547e-05,
+      "loss": 1.0024,
+      "step": 170
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.096428764017947,
+      "learning_rate": 1.9457506938715357e-05,
+      "loss": 0.9934,
+      "step": 175
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 12.29708093689668,
+      "learning_rate": 1.9392480098509488e-05,
+      "loss": 0.9722,
+      "step": 180
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.10527746898357,
+      "learning_rate": 1.93238948215089e-05,
+      "loss": 1.005,
+      "step": 185
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 8.993111720295193,
+      "learning_rate": 1.9251777091944665e-05,
+      "loss": 0.9962,
+      "step": 190
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.4437270374749556,
+      "learning_rate": 1.9176154232353513e-05,
+      "loss": 0.9868,
+      "step": 195
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.771850755773128,
+      "learning_rate": 1.9097054893226395e-05,
+      "loss": 0.9851,
+      "step": 200
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.049218130758563,
+      "learning_rate": 1.9014509042153964e-05,
+      "loss": 0.9738,
+      "step": 205
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.7715704988491385,
+      "learning_rate": 1.8928547952473037e-05,
+      "loss": 1.005,
+      "step": 210
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 6.146573303594628,
+      "learning_rate": 1.8839204191418386e-05,
+      "loss": 0.9586,
+      "step": 215
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 8.160744647991924,
+      "learning_rate": 1.8746511607784298e-05,
+      "loss": 0.9808,
+      "step": 220
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 7.706895037397381,
+      "learning_rate": 1.865050531910062e-05,
+      "loss": 1.0017,
+      "step": 225
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 11.758878906059278,
+      "learning_rate": 1.855122169832813e-05,
+      "loss": 0.9999,
+      "step": 230
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 6.613719964629243,
+      "learning_rate": 1.844869836007825e-05,
+      "loss": 0.9546,
+      "step": 235
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.5628300646011075,
+      "learning_rate": 1.8342974146362397e-05,
+      "loss": 0.952,
+      "step": 240
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 8.005725339426444,
+      "learning_rate": 1.8234089111876256e-05,
+      "loss": 0.9721,
+      "step": 245
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 3.8142262373421842,
+      "learning_rate": 1.8122084508824692e-05,
+      "loss": 0.9466,
+      "step": 250
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.9283785698082263,
+      "learning_rate": 1.80070027712929e-05,
+      "loss": 0.9714,
+      "step": 255
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.77851405459744,
+      "learning_rate": 1.7888887499169816e-05,
+      "loss": 0.9499,
+      "step": 260
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.591252723643397,
+      "learning_rate": 1.7767783441629883e-05,
+      "loss": 0.9912,
+      "step": 265
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.016605910673708,
+      "learning_rate": 1.7643736480179353e-05,
+      "loss": 0.9566,
+      "step": 270
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 6.373102607823453,
+      "learning_rate": 1.7516793611273614e-05,
+      "loss": 0.9308,
+      "step": 275
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.834120929511878,
+      "learning_rate": 1.7387002928512093e-05,
+      "loss": 0.9524,
+      "step": 280
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.634655228348776,
+      "learning_rate": 1.725441360441752e-05,
+      "loss": 0.9392,
+      "step": 285
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 6.620105860028147,
+      "learning_rate": 1.711907587180642e-05,
+      "loss": 0.9351,
+      "step": 290
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.670289326633902,
+      "learning_rate": 1.698104100475788e-05,
+      "loss": 0.9693,
+      "step": 295
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.39460086399978,
+      "learning_rate": 1.684036129918786e-05,
+      "loss": 0.951,
+      "step": 300
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 4.585629392068035,
+      "learning_rate": 1.6697090053036344e-05,
+      "loss": 0.8574,
+      "step": 305
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 3.7164245648143464,
+      "learning_rate": 1.6551281546074863e-05,
+      "loss": 0.8819,
+      "step": 310
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 5.697457454364852,
+      "learning_rate": 1.6402991019342073e-05,
+      "loss": 0.8602,
+      "step": 315
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 4.644169677070983,
+      "learning_rate": 1.625227465421511e-05,
+      "loss": 0.8301,
+      "step": 320
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 4.037165905809593,
+      "learning_rate": 1.60991895511247e-05,
+      "loss": 0.8698,
+      "step": 325
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.742488771494794,
+      "learning_rate": 1.5943793707922086e-05,
+      "loss": 0.8465,
+      "step": 330
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 4.112214119398294,
+      "learning_rate": 1.5786145997905952e-05,
+      "loss": 0.8612,
+      "step": 335
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 9.430841344870588,
+      "learning_rate": 1.5626306147517665e-05,
+      "loss": 0.8798,
+      "step": 340
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 10.376642310954942,
+      "learning_rate": 1.5464334713713312e-05,
+      "loss": 0.8482,
+      "step": 345
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 4.046603696090184,
+      "learning_rate": 1.5300293061021084e-05,
+      "loss": 0.8383,
+      "step": 350
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 5.823206738990728,
+      "learning_rate": 1.5134243338292686e-05,
+      "loss": 0.8734,
+      "step": 355
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.736067876795748,
+      "learning_rate": 1.4966248455157622e-05,
+      "loss": 0.8449,
+      "step": 360
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 3.810954674146249,
+      "learning_rate": 1.4796372058189235e-05,
+      "loss": 0.8302,
+      "step": 365
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 4.844425691427299,
+      "learning_rate": 1.4624678506791556e-05,
+      "loss": 0.8437,
+      "step": 370
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 3.1753997442211954,
+      "learning_rate": 1.445123284881609e-05,
+      "loss": 0.8671,
+      "step": 375
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 4.573612034944129,
+      "learning_rate": 1.4276100795917777e-05,
+      "loss": 0.8126,
+      "step": 380
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 3.6271701232281752,
+      "learning_rate": 1.409934869865945e-05,
+      "loss": 0.8423,
+      "step": 385
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 4.384171797308968,
+      "learning_rate": 1.392104352137426e-05,
+      "loss": 0.8348,
+      "step": 390
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.572132246822777,
+      "learning_rate": 1.3741252816795552e-05,
+      "loss": 0.8685,
+      "step": 395
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 7.154463900691466,
+      "learning_rate": 1.3560044700463824e-05,
+      "loss": 0.8234,
+      "step": 400
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 5.1445903649483355,
+      "learning_rate": 1.3377487824920459e-05,
+      "loss": 0.8603,
+      "step": 405
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 3.417578210350955,
+      "learning_rate": 1.3193651353698012e-05,
+      "loss": 0.846,
+      "step": 410
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 2.89568583566464,
+      "learning_rate": 1.30086049351169e-05,
+      "loss": 0.8396,
+      "step": 415
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.7362473425942007,
+      "learning_rate": 1.2822418675898428e-05,
+      "loss": 0.8758,
+      "step": 420
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 4.330928362220086,
+      "learning_rate": 1.2635163114604131e-05,
+      "loss": 0.8616,
+      "step": 425
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 3.7106724475482826,
+      "learning_rate": 1.2446909194911552e-05,
+      "loss": 0.8373,
+      "step": 430
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 3.926542815570075,
+      "learning_rate": 1.2257728238736468e-05,
+      "loss": 0.8383,
+      "step": 435
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 4.47693007964662,
+      "learning_rate": 1.2067691919211879e-05,
+      "loss": 0.8547,
+      "step": 440
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 3.990520695042587,
+      "learning_rate": 1.1876872233533909e-05,
+      "loss": 0.8288,
+      "step": 445
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 3.9073482540862754,
+      "learning_rate": 1.1685341475684935e-05,
+      "loss": 0.8506,
+      "step": 450
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 4.0981061235737295,
+      "learning_rate": 1.1493172209044259e-05,
+      "loss": 0.8181,
+      "step": 455
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 3.6983475788184945,
+      "learning_rate": 1.1300437238896758e-05,
+      "loss": 0.8339,
+      "step": 460
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 3.214152827379248,
+      "learning_rate": 1.1107209584849845e-05,
+      "loss": 0.851,
+      "step": 465
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 3.350988754839917,
+      "learning_rate": 1.0913562453169241e-05,
+      "loss": 0.8266,
+      "step": 470
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 7.847759662798763,
+      "learning_rate": 1.0719569209044047e-05,
+      "loss": 0.8429,
+      "step": 475
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 4.0207776210716215,
+      "learning_rate": 1.0525303348791599e-05,
+      "loss": 0.8498,
+      "step": 480
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 2.7225943916928963,
+      "learning_rate": 1.0330838472012617e-05,
+      "loss": 0.8215,
+      "step": 485
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 3.6576366170765597,
+      "learning_rate": 1.0136248253707267e-05,
+      "loss": 0.8307,
+      "step": 490
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 3.4227860041960665,
+      "learning_rate": 9.94160641636263e-06,
+      "loss": 0.8148,
+      "step": 495
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 3.111038433143253,
+      "learning_rate": 9.74698670202218e-06,
+      "loss": 0.8443,
+      "step": 500
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 3.252772592031176,
+      "learning_rate": 9.552462844347883e-06,
+      "loss": 0.8438,
+      "step": 505
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 4.718741450931272,
+      "learning_rate": 9.358108540685406e-06,
+      "loss": 0.832,
+      "step": 510
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 3.839793400271427,
+      "learning_rate": 9.163997424143167e-06,
+      "loss": 0.8159,
+      "step": 515
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 3.0905029907583432,
+      "learning_rate": 8.970203035695662e-06,
+      "loss": 0.8561,
+      "step": 520
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.9454863037823777,
+      "learning_rate": 8.776798796321715e-06,
+      "loss": 0.8482,
+      "step": 525
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 4.171404088039613,
+      "learning_rate": 8.583857979188203e-06,
+      "loss": 0.8027,
+      "step": 530
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 2.8741497032915415,
+      "learning_rate": 8.391453681889772e-06,
+      "loss": 0.8452,
+      "step": 535
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 3.618045180794514,
+      "learning_rate": 8.199658798755048e-06,
+      "loss": 0.846,
+      "step": 540
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 4.5919678070450445,
+      "learning_rate": 8.008545993229897e-06,
+      "loss": 0.8259,
+      "step": 545
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 3.286397180719563,
+      "learning_rate": 7.818187670348133e-06,
+      "loss": 0.8292,
+      "step": 550
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 3.273535359111842,
+      "learning_rate": 7.628655949300133e-06,
+      "loss": 0.8338,
+      "step": 555
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 3.15565303365465,
+      "learning_rate": 7.440022636109742e-06,
+      "loss": 0.818,
+      "step": 560
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 3.1548763199568035,
+      "learning_rate": 7.2523591964298345e-06,
+      "loss": 0.8485,
+      "step": 565
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.1540649270721524,
+      "learning_rate": 7.065736728466832e-06,
+      "loss": 0.819,
+      "step": 570
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 4.373590862563539,
+      "learning_rate": 6.880225936044402e-06,
+      "loss": 0.8031,
+      "step": 575
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 3.1586070204270467,
+      "learning_rate": 6.695897101816606e-06,
+      "loss": 0.8406,
+      "step": 580
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 2.9568635260100127,
+      "learning_rate": 6.512820060640608e-06,
+      "loss": 0.835,
+      "step": 585
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 3.0203617695232663,
+      "learning_rate": 6.331064173119008e-06,
+      "loss": 0.8494,
+      "step": 590
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 3.1117798744102574,
+      "learning_rate": 6.150698299321889e-06,
+      "loss": 0.8308,
+      "step": 595
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.55872308952704,
+      "learning_rate": 5.971790772698467e-06,
+      "loss": 0.8035,
+      "step": 600
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 4.2821019574649535,
+      "learning_rate": 5.794409374188272e-06,
+      "loss": 0.7114,
+      "step": 605
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 3.707456621907476,
+      "learning_rate": 5.61862130654165e-06,
+      "loss": 0.7153,
+      "step": 610
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 3.2111867758546278,
+      "learning_rate": 5.444493168859304e-06,
+      "loss": 0.7127,
+      "step": 615
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 2.981834951561055,
+      "learning_rate": 5.272090931360564e-06,
+      "loss": 0.7152,
+      "step": 620
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 3.261244591092665,
+      "learning_rate": 5.101479910389888e-06,
+      "loss": 0.7187,
+      "step": 625
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.572508474876337,
+      "learning_rate": 4.932724743671089e-06,
+      "loss": 0.6839,
+      "step": 630
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 4.094077691261136,
+      "learning_rate": 4.765889365818708e-06,
+      "loss": 0.6999,
+      "step": 635
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 3.1272831710472118,
+      "learning_rate": 4.601036984115684e-06,
+      "loss": 0.7086,
+      "step": 640
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 2.923329574215811,
+      "learning_rate": 4.438230054566678e-06,
+      "loss": 0.7085,
+      "step": 645
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 3.0901398496943226,
+      "learning_rate": 4.277530258235955e-06,
+      "loss": 0.701,
+      "step": 650
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 3.4929443326902465,
+      "learning_rate": 4.118998477878879e-06,
+      "loss": 0.7049,
+      "step": 655
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 3.6504428413222376,
+      "learning_rate": 3.96269477487588e-06,
+      "loss": 0.7214,
+      "step": 660
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 3.2341076651772975,
+      "learning_rate": 3.8086783664775827e-06,
+      "loss": 0.7085,
+      "step": 665
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 3.092474822298113,
+      "learning_rate": 3.657007603369728e-06,
+      "loss": 0.6767,
+      "step": 670
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 2.947080196219785,
+      "learning_rate": 3.5077399475664474e-06,
+      "loss": 0.7076,
+      "step": 675
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 3.6087538594951662,
+      "learning_rate": 3.360931950640185e-06,
+      "loss": 0.6975,
+      "step": 680
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 2.929061678667629,
+      "learning_rate": 3.2166392322965423e-06,
+      "loss": 0.708,
+      "step": 685
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 2.8841689757419875,
+      "learning_rate": 3.074916459302211e-06,
+      "loss": 0.6923,
+      "step": 690
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 2.9696900618191338,
+      "learning_rate": 2.935817324773893e-06,
+      "loss": 0.7001,
+      "step": 695
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 2.6611962094828363,
+      "learning_rate": 2.799394527836129e-06,
+      "loss": 0.7017,
+      "step": 700
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 3.454056655854251,
+      "learning_rate": 2.665699753655684e-06,
+      "loss": 0.7036,
+      "step": 705
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 2.951382811612529,
+      "learning_rate": 2.5347836538601113e-06,
+      "loss": 0.7128,
+      "step": 710
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 2.720458967552173,
+      "learning_rate": 2.406695827347848e-06,
+      "loss": 0.6813,
+      "step": 715
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 3.2947724618805436,
+      "learning_rate": 2.281484801497186e-06,
+      "loss": 0.701,
+      "step": 720
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 3.3925114406979,
+      "learning_rate": 2.1591980137811684e-06,
+      "loss": 0.7131,
+      "step": 725
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 2.762867665401941,
+      "learning_rate": 2.0398817937954275e-06,
+      "loss": 0.6984,
+      "step": 730
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 2.7010469113237434,
+      "learning_rate": 1.923581345705736e-06,
+      "loss": 0.7096,
+      "step": 735
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 2.852400843485154,
+      "learning_rate": 1.8103407311219523e-06,
+      "loss": 0.7032,
+      "step": 740
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 2.86250818820308,
+      "learning_rate": 1.7002028524048354e-06,
+      "loss": 0.7293,
+      "step": 745
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.51712023734419,
+      "learning_rate": 1.5932094364120453e-06,
+      "loss": 0.7012,
+      "step": 750
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 2.7437779027345215,
+      "learning_rate": 1.489401018689488e-06,
+      "loss": 0.6839,
+      "step": 755
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 2.661627012464701,
+      "learning_rate": 1.3888169281140284e-06,
+      "loss": 0.6939,
+      "step": 760
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 2.732001611716385,
+      "learning_rate": 1.291495271993337e-06,
+      "loss": 0.688,
+      "step": 765
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 2.6615007947383553,
+      "learning_rate": 1.1974729216285386e-06,
+      "loss": 0.7018,
+      "step": 770
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 2.924733067359529,
+      "learning_rate": 1.1067854983451575e-06,
+      "loss": 0.7067,
+      "step": 775
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 2.6258772657245557,
+      "learning_rate": 1.0194673599976134e-06,
+      "loss": 0.7105,
+      "step": 780
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 2.516616483442641,
+      "learning_rate": 9.355515879523858e-07,
+      "loss": 0.7135,
+      "step": 785
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 2.7835305971129163,
+      "learning_rate": 8.550699745548196e-07,
+      "loss": 0.6885,
+      "step": 790
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 2.615176282326374,
+      "learning_rate": 7.780530110842566e-07,
+      "loss": 0.6819,
+      "step": 795
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 2.654709241244524,
+      "learning_rate": 7.045298762021125e-07,
+      "loss": 0.7008,
+      "step": 800
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 2.7964338501174395,
+      "learning_rate": 6.345284248972383e-07,
+      "loss": 0.6944,
+      "step": 805
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 2.6124049003030243,
+      "learning_rate": 5.680751779327742e-07,
+      "loss": 0.709,
+      "step": 810
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 2.798593198334347,
+      "learning_rate": 5.05195311798491e-07,
+      "loss": 0.7001,
+      "step": 815
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 2.6899441693791037,
+      "learning_rate": 4.4591264917242195e-07,
+      "loss": 0.6996,
+      "step": 820
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 2.4467811439684475,
+      "learning_rate": 3.9024964989539227e-07,
+      "loss": 0.7111,
+      "step": 825
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 2.642511218648128,
+      "learning_rate": 3.3822740246188477e-07,
+      "loss": 0.7003,
+      "step": 830
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 2.5965636823764444,
+      "learning_rate": 2.8986561603044694e-07,
+      "loss": 0.6972,
+      "step": 835
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.531198285866803,
+      "learning_rate": 2.4518261295667255e-07,
+      "loss": 0.7094,
+      "step": 840
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 2.4502750845690455,
+      "learning_rate": 2.0419532185159796e-07,
+      "loss": 0.6844,
+      "step": 845
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 2.6177312094207346,
+      "learning_rate": 1.6691927116812002e-07,
+      "loss": 0.6924,
+      "step": 850
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 2.7461025264636763,
+      "learning_rate": 1.3336858331787993e-07,
+      "loss": 0.6944,
+      "step": 855
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 2.5081604238233237,
+      "learning_rate": 1.0355596932085432e-07,
+      "loss": 0.7123,
+      "step": 860
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 2.4841520023484462,
+      "learning_rate": 7.749272398964613e-08,
+      "loss": 0.6777,
+      "step": 865
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 2.5778856215526447,
+      "learning_rate": 5.518872165033329e-08,
+      "loss": 0.695,
+      "step": 870
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 2.572814592379813,
+      "learning_rate": 3.6652412401478875e-08,
+      "loss": 0.6948,
+      "step": 875
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 2.4573450802780363,
+      "learning_rate": 2.1890818912728706e-08,
+      "loss": 0.6865,
+      "step": 880
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 2.5566553348831174,
+      "learning_rate": 1.0909533764194013e-08,
+      "loss": 0.6825,
+      "step": 885
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 2.429805674481568,
+      "learning_rate": 3.7127173276563234e-09,
+      "loss": 0.7116,
+      "step": 890
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 2.6137017455070115,
+      "learning_rate": 3.0309619035495675e-10,
+      "loss": 0.7018,
+      "step": 895
+    },
+    {
+      "epoch": 2.99,
+      "step": 897,
+      "total_flos": 246978202042368.0,
+      "train_loss": 1.0102584746104553,
+      "train_runtime": 5029.5541,
+      "train_samples_per_second": 22.861,
+      "train_steps_per_second": 0.178
+    }
+  ],
+  "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 sha256:20455c14bb18364ee0b09ffd051e0d137b2dc2b681ae5c0ede649f7aa5dfa708
+size 6072