Model save

.gitattributes

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

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: gemma
+base_model: google/gemma-2b
+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-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3544
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 4
+- total_eval_batch_size: 4
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.2658        | 1.0   | 326  | 1.2135          |
+| 0.8841        | 2.0   | 652  | 1.2135          |
+| 0.7012        | 3.0   | 978  | 1.3544          |
+
+
+### Framework versions
+
+- Transformers 4.46.0
+- Pytorch 2.1.2
+- Datasets 3.0.2
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3642602029056.0,
+    "train_loss": 1.0360665048314506,
+    "train_runtime": 586.176,
+    "train_samples": 2023,
+    "train_samples_per_second": 6.674,
+    "train_steps_per_second": 1.668
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "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": "4.46.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f03ed4af2ea91e8b3cbbc4638db271c30b32401880813e3fffa2a20ad9a26c9
+size 4945242264

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3070c72853fac5da48f03f70e9348094fc053d7b892771281116c46eed2ff01
+size 67121608

model.safetensors.index.json

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

runs/Oct27_19-12-03_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730081540.tinkywinky.edc.iee.ucsb.edu.927165.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd5df1f1babe0aaff2ad7bd497d5eed5657c3eb0feb3ff8e897539101d90912
+size 5800

runs/Oct27_19-14-06_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730081665.tinkywinky.edc.iee.ucsb.edu.929915.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68fd46baddaca8bec9522aea4e155cb882ca02d9bede9f4a13f7f4b8c6c4e6df
+size 5800

runs/Oct27_19-50-33_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730083848.tinkywinky.edc.iee.ucsb.edu.953964.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5978029af36d1fbdb987d9557e64d066fcb7563e1070eb604a30131d17eb84e2
+size 5800

runs/Oct27_20-04-09_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730084664.tinkywinky.edc.iee.ucsb.edu.964704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3963fc27ab5c42ba4c87cb92363ce2616d80a1188001ac0826f6fe4a0dddeccc
+size 5800

runs/Oct29_17-38-39_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730248732.tinkywinky.edc.iee.ucsb.edu.1836912.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8276f9a7515c2ebd42ae689fdb16c6c8871d02b62dc92b210fa9c46ba2e5fc99
+size 5800

runs/Oct29_17-41-12_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730248884.tinkywinky.edc.iee.ucsb.edu.1839751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ee5049aee5daabb2c4541b7fb35bf2c3231412b3b8e2040d0a90313e5dc883
+size 5800

runs/Oct29_17-43-56_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730249048.tinkywinky.edc.iee.ucsb.edu.1842529.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e05f74737774af5dbe9cecd47c75abbddbd31866cda957a1a32b253ff9773e4
+size 5800

runs/Oct29_18-11-25_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730250698.tinkywinky.edc.iee.ucsb.edu.1864821.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a64c1d5edde2426ed1c46edcbfe6eb242cd49791bdb9e060785b481f6ea9cbe
+size 5800

runs/Oct29_18-18-33_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730251124.tinkywinky.edc.iee.ucsb.edu.1871884.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f08cfb48a633860c5ca21cc982442957452a79a88ea2dad1093cbd7e482f6a4
+size 5800

runs/Oct29_18-22-00_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730251334.tinkywinky.edc.iee.ucsb.edu.1875484.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16474df016506d71b1d27a1303deb9a947dc0d348e79a710b4a1128e9a90dd4
+size 5800

runs/Oct29_18-22-51_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730251385.tinkywinky.edc.iee.ucsb.edu.1876732.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb4b6885ae0397fec8ec3d472ec3fa90970135336fd636ffd245c53cfaab8c0
+size 5800

runs/Oct29_18-35-45_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730252156.tinkywinky.edc.iee.ucsb.edu.1889157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07b60999c5a0960d09c7b698ccde6c173b557b61d60116d0b17753d70a7e6f0
+size 7870

runs/Oct29_23-40-31_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730270445.tinkywinky.edc.iee.ucsb.edu.2127650.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae69750d635704a4d48c796e1214e4c684d55ecef89a51c7f25bbb80d6a9b6f2
+size 44002

runs/Oct29_23-50-03_tinkywinky.edc.iee.ucsb.edu/events.out.tfevents.1730271015.tinkywinky.edc.iee.ucsb.edu.2137893.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9df8f1699fecd87de0e85d7af28f52fa5372098ea7ace6f667d51951bcb0389
+size 48003

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:c644094fa37d155fce4eccae9d5a12bb1723fe4439b0b6a2ebbe173755b2c218
+size 34315017

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3642602029056.0,
+    "train_loss": 1.0360665048314506,
+    "train_runtime": 586.176,
+    "train_samples": 2023,
+    "train_samples_per_second": 6.674,
+    "train_steps_per_second": 1.668
+}

trainer_state.json

@@ -0,0 +1,1438 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 978,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003067484662576687,
+      "grad_norm": 177.2131714128933,
+      "learning_rate": 2.0408163265306121e-07,
+      "loss": 3.0795,
+      "step": 1
+    },
+    {
+      "epoch": 0.015337423312883436,
+      "grad_norm": 241.89792017630023,
+      "learning_rate": 1.0204081632653063e-06,
+      "loss": 2.738,
+      "step": 5
+    },
+    {
+      "epoch": 0.03067484662576687,
+      "grad_norm": 97.9005821739992,
+      "learning_rate": 2.0408163265306125e-06,
+      "loss": 2.573,
+      "step": 10
+    },
+    {
+      "epoch": 0.046012269938650305,
+      "grad_norm": 29.935305969711827,
+      "learning_rate": 3.0612244897959185e-06,
+      "loss": 2.4113,
+      "step": 15
+    },
+    {
+      "epoch": 0.06134969325153374,
+      "grad_norm": 6.7865011448005985,
+      "learning_rate": 4.081632653061225e-06,
+      "loss": 1.9856,
+      "step": 20
+    },
+    {
+      "epoch": 0.07668711656441718,
+      "grad_norm": 8.264677565869711,
+      "learning_rate": 5.1020408163265315e-06,
+      "loss": 1.8726,
+      "step": 25
+    },
+    {
+      "epoch": 0.09202453987730061,
+      "grad_norm": 19.32485419745683,
+      "learning_rate": 6.122448979591837e-06,
+      "loss": 1.7009,
+      "step": 30
+    },
+    {
+      "epoch": 0.10736196319018405,
+      "grad_norm": 10.162135754390622,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 1.6191,
+      "step": 35
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 3.0916095898500555,
+      "learning_rate": 8.16326530612245e-06,
+      "loss": 1.5164,
+      "step": 40
+    },
+    {
+      "epoch": 0.13803680981595093,
+      "grad_norm": 43.413150705371685,
+      "learning_rate": 9.183673469387756e-06,
+      "loss": 1.5097,
+      "step": 45
+    },
+    {
+      "epoch": 0.15337423312883436,
+      "grad_norm": 49.53965734626817,
+      "learning_rate": 1.0204081632653063e-05,
+      "loss": 1.5785,
+      "step": 50
+    },
+    {
+      "epoch": 0.1687116564417178,
+      "grad_norm": 10.98873172852826,
+      "learning_rate": 1.1224489795918367e-05,
+      "loss": 1.4715,
+      "step": 55
+    },
+    {
+      "epoch": 0.18404907975460122,
+      "grad_norm": 2.7742625393808584,
+      "learning_rate": 1.2244897959183674e-05,
+      "loss": 1.4263,
+      "step": 60
+    },
+    {
+      "epoch": 0.19938650306748465,
+      "grad_norm": 23.101404729255652,
+      "learning_rate": 1.326530612244898e-05,
+      "loss": 1.4043,
+      "step": 65
+    },
+    {
+      "epoch": 0.2147239263803681,
+      "grad_norm": 12.92305440472016,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 1.3793,
+      "step": 70
+    },
+    {
+      "epoch": 0.23006134969325154,
+      "grad_norm": 2.882766144097806,
+      "learning_rate": 1.530612244897959e-05,
+      "loss": 1.4183,
+      "step": 75
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 11.111007796269925,
+      "learning_rate": 1.63265306122449e-05,
+      "loss": 1.4517,
+      "step": 80
+    },
+    {
+      "epoch": 0.2607361963190184,
+      "grad_norm": 2.897394026367856,
+      "learning_rate": 1.7346938775510206e-05,
+      "loss": 1.3393,
+      "step": 85
+    },
+    {
+      "epoch": 0.27607361963190186,
+      "grad_norm": 2.9177477230316566,
+      "learning_rate": 1.836734693877551e-05,
+      "loss": 1.428,
+      "step": 90
+    },
+    {
+      "epoch": 0.29141104294478526,
+      "grad_norm": 2.912560429885746,
+      "learning_rate": 1.9387755102040817e-05,
+      "loss": 1.304,
+      "step": 95
+    },
+    {
+      "epoch": 0.3067484662576687,
+      "grad_norm": 2.5615070520092704,
+      "learning_rate": 1.9999745104274995e-05,
+      "loss": 1.2997,
+      "step": 100
+    },
+    {
+      "epoch": 0.3220858895705521,
+      "grad_norm": 2.9480036513492336,
+      "learning_rate": 1.9996877676598733e-05,
+      "loss": 1.4086,
+      "step": 105
+    },
+    {
+      "epoch": 0.3374233128834356,
+      "grad_norm": 2.5407276803281333,
+      "learning_rate": 1.9990825118233958e-05,
+      "loss": 1.3028,
+      "step": 110
+    },
+    {
+      "epoch": 0.35276073619631904,
+      "grad_norm": 3.239233594777726,
+      "learning_rate": 1.9981589357601727e-05,
+      "loss": 1.4185,
+      "step": 115
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 2.771896819307909,
+      "learning_rate": 1.9969173337331283e-05,
+      "loss": 1.3523,
+      "step": 120
+    },
+    {
+      "epoch": 0.3834355828220859,
+      "grad_norm": 2.7643269799604724,
+      "learning_rate": 1.9953581013322503e-05,
+      "loss": 1.3175,
+      "step": 125
+    },
+    {
+      "epoch": 0.3987730061349693,
+      "grad_norm": 3.508281226717504,
+      "learning_rate": 1.99348173534855e-05,
+      "loss": 1.2981,
+      "step": 130
+    },
+    {
+      "epoch": 0.41411042944785276,
+      "grad_norm": 2.4302828555210025,
+      "learning_rate": 1.9912888336157793e-05,
+      "loss": 1.3109,
+      "step": 135
+    },
+    {
+      "epoch": 0.4294478527607362,
+      "grad_norm": 2.3273613141747975,
+      "learning_rate": 1.9887800948199496e-05,
+      "loss": 1.2887,
+      "step": 140
+    },
+    {
+      "epoch": 0.4447852760736196,
+      "grad_norm": 2.502367541877984,
+      "learning_rate": 1.9859563182767268e-05,
+      "loss": 1.2735,
+      "step": 145
+    },
+    {
+      "epoch": 0.4601226993865031,
+      "grad_norm": 2.8584207562233113,
+      "learning_rate": 1.9828184036767556e-05,
+      "loss": 1.2271,
+      "step": 150
+    },
+    {
+      "epoch": 0.4754601226993865,
+      "grad_norm": 2.190347531165954,
+      "learning_rate": 1.9793673507990086e-05,
+      "loss": 1.2896,
+      "step": 155
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 2.2761435625476545,
+      "learning_rate": 1.9756042591922436e-05,
+      "loss": 1.3294,
+      "step": 160
+    },
+    {
+      "epoch": 0.5061349693251533,
+      "grad_norm": 2.220138706256322,
+      "learning_rate": 1.9715303278246724e-05,
+      "loss": 1.3188,
+      "step": 165
+    },
+    {
+      "epoch": 0.5214723926380368,
+      "grad_norm": 2.294310010674355,
+      "learning_rate": 1.9671468547019575e-05,
+      "loss": 1.2199,
+      "step": 170
+    },
+    {
+      "epoch": 0.5368098159509203,
+      "grad_norm": 2.513372192362633,
+      "learning_rate": 1.9624552364536472e-05,
+      "loss": 1.3106,
+      "step": 175
+    },
+    {
+      "epoch": 0.5521472392638037,
+      "grad_norm": 2.510468468716461,
+      "learning_rate": 1.9574569678881965e-05,
+      "loss": 1.3708,
+      "step": 180
+    },
+    {
+      "epoch": 0.5674846625766872,
+      "grad_norm": 2.041921641107936,
+      "learning_rate": 1.952153641516698e-05,
+      "loss": 1.1784,
+      "step": 185
+    },
+    {
+      "epoch": 0.5828220858895705,
+      "grad_norm": 2.27820722339295,
+      "learning_rate": 1.94654694704549e-05,
+      "loss": 1.1902,
+      "step": 190
+    },
+    {
+      "epoch": 0.598159509202454,
+      "grad_norm": 2.328841014102968,
+      "learning_rate": 1.9406386708377956e-05,
+      "loss": 1.316,
+      "step": 195
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 2.2926147060214066,
+      "learning_rate": 1.9344306953445632e-05,
+      "loss": 1.3843,
+      "step": 200
+    },
+    {
+      "epoch": 0.6288343558282209,
+      "grad_norm": 3.113673918623077,
+      "learning_rate": 1.9279249985046948e-05,
+      "loss": 1.3199,
+      "step": 205
+    },
+    {
+      "epoch": 0.6441717791411042,
+      "grad_norm": 2.105413236829464,
+      "learning_rate": 1.92112365311485e-05,
+      "loss": 1.2593,
+      "step": 210
+    },
+    {
+      "epoch": 0.6595092024539877,
+      "grad_norm": 2.2971282506758204,
+      "learning_rate": 1.9140288261690278e-05,
+      "loss": 1.2316,
+      "step": 215
+    },
+    {
+      "epoch": 0.6748466257668712,
+      "grad_norm": 3.060568400530995,
+      "learning_rate": 1.9066427781681314e-05,
+      "loss": 1.1986,
+      "step": 220
+    },
+    {
+      "epoch": 0.6901840490797546,
+      "grad_norm": 2.0851577530985663,
+      "learning_rate": 1.8989678623997506e-05,
+      "loss": 1.2465,
+      "step": 225
+    },
+    {
+      "epoch": 0.7055214723926381,
+      "grad_norm": 2.34599375716676,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 1.3111,
+      "step": 230
+    },
+    {
+      "epoch": 0.7208588957055214,
+      "grad_norm": 2.0045103451147352,
+      "learning_rate": 1.8827613001162534e-05,
+      "loss": 1.2048,
+      "step": 235
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 2.0865280550933663,
+      "learning_rate": 1.8742348172152728e-05,
+      "loss": 1.3875,
+      "step": 240
+    },
+    {
+      "epoch": 0.7515337423312883,
+      "grad_norm": 2.1899054440028602,
+      "learning_rate": 1.8654297921298862e-05,
+      "loss": 1.2177,
+      "step": 245
+    },
+    {
+      "epoch": 0.7668711656441718,
+      "grad_norm": 2.146615168451316,
+      "learning_rate": 1.856349030251589e-05,
+      "loss": 1.2302,
+      "step": 250
+    },
+    {
+      "epoch": 0.7822085889570553,
+      "grad_norm": 5.215245761172734,
+      "learning_rate": 1.846995424825079e-05,
+      "loss": 1.1558,
+      "step": 255
+    },
+    {
+      "epoch": 0.7975460122699386,
+      "grad_norm": 2.1303631206592253,
+      "learning_rate": 1.837371956026433e-05,
+      "loss": 1.2666,
+      "step": 260
+    },
+    {
+      "epoch": 0.8128834355828221,
+      "grad_norm": 3.324267620281515,
+      "learning_rate": 1.8274816900135842e-05,
+      "loss": 1.2796,
+      "step": 265
+    },
+    {
+      "epoch": 0.8282208588957055,
+      "grad_norm": 2.0369143733640174,
+      "learning_rate": 1.817327777949407e-05,
+      "loss": 1.2191,
+      "step": 270
+    },
+    {
+      "epoch": 0.843558282208589,
+      "grad_norm": 2.268965846881571,
+      "learning_rate": 1.806913454997717e-05,
+      "loss": 1.2382,
+      "step": 275
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 1.9534994546311044,
+      "learning_rate": 1.7962420392925066e-05,
+      "loss": 1.3029,
+      "step": 280
+    },
+    {
+      "epoch": 0.8742331288343558,
+      "grad_norm": 1.9407859425510332,
+      "learning_rate": 1.785316930880745e-05,
+      "loss": 1.183,
+      "step": 285
+    },
+    {
+      "epoch": 0.8895705521472392,
+      "grad_norm": 1.9539166093233689,
+      "learning_rate": 1.7741416106390828e-05,
+      "loss": 1.1725,
+      "step": 290
+    },
+    {
+      "epoch": 0.9049079754601227,
+      "grad_norm": 2.2999481127748216,
+      "learning_rate": 1.7627196391647982e-05,
+      "loss": 1.2114,
+      "step": 295
+    },
+    {
+      "epoch": 0.9202453987730062,
+      "grad_norm": 1.9126415566238704,
+      "learning_rate": 1.75105465564135e-05,
+      "loss": 1.2206,
+      "step": 300
+    },
+    {
+      "epoch": 0.9355828220858896,
+      "grad_norm": 2.3510054432341887,
+      "learning_rate": 1.739150376678883e-05,
+      "loss": 1.301,
+      "step": 305
+    },
+    {
+      "epoch": 0.950920245398773,
+      "grad_norm": 2.5269459534002596,
+      "learning_rate": 1.727010595130074e-05,
+      "loss": 1.3914,
+      "step": 310
+    },
+    {
+      "epoch": 0.9662576687116564,
+      "grad_norm": 2.045224623846914,
+      "learning_rate": 1.714639178881678e-05,
+      "loss": 1.2722,
+      "step": 315
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 2.0917960158205107,
+      "learning_rate": 1.7020400696221737e-05,
+      "loss": 1.2093,
+      "step": 320
+    },
+    {
+      "epoch": 0.9969325153374233,
+      "grad_norm": 2.017009094857716,
+      "learning_rate": 1.6892172815858896e-05,
+      "loss": 1.2658,
+      "step": 325
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.2135429382324219,
+      "eval_runtime": 6.9064,
+      "eval_samples_per_second": 23.022,
+      "eval_steps_per_second": 5.792,
+      "step": 326
+    },
+    {
+      "epoch": 1.0122699386503067,
+      "grad_norm": 2.1076821373912433,
+      "learning_rate": 1.6761749002740195e-05,
+      "loss": 1.126,
+      "step": 330
+    },
+    {
+      "epoch": 1.0276073619631902,
+      "grad_norm": 2.532948886360268,
+      "learning_rate": 1.662917081152932e-05,
+      "loss": 1.0517,
+      "step": 335
+    },
+    {
+      "epoch": 1.0429447852760736,
+      "grad_norm": 2.159362066124978,
+      "learning_rate": 1.6494480483301836e-05,
+      "loss": 0.9849,
+      "step": 340
+    },
+    {
+      "epoch": 1.058282208588957,
+      "grad_norm": 1.9634133830158156,
+      "learning_rate": 1.635772093208669e-05,
+      "loss": 0.961,
+      "step": 345
+    },
+    {
+      "epoch": 1.0736196319018405,
+      "grad_norm": 2.643597563770428,
+      "learning_rate": 1.6218935731193223e-05,
+      "loss": 0.929,
+      "step": 350
+    },
+    {
+      "epoch": 1.0889570552147239,
+      "grad_norm": 2.2336296848587986,
+      "learning_rate": 1.6078169099328196e-05,
+      "loss": 0.9695,
+      "step": 355
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 2.5120125840182803,
+      "learning_rate": 1.5935465886507143e-05,
+      "loss": 1.1179,
+      "step": 360
+    },
+    {
+      "epoch": 1.1196319018404908,
+      "grad_norm": 2.0896191655801735,
+      "learning_rate": 1.579087155976459e-05,
+      "loss": 1.1294,
+      "step": 365
+    },
+    {
+      "epoch": 1.1349693251533743,
+      "grad_norm": 2.325319374896529,
+      "learning_rate": 1.5644432188667695e-05,
+      "loss": 0.9826,
+      "step": 370
+    },
+    {
+      "epoch": 1.1503067484662577,
+      "grad_norm": 2.1728488841214095,
+      "learning_rate": 1.5496194430637903e-05,
+      "loss": 0.9251,
+      "step": 375
+    },
+    {
+      "epoch": 1.165644171779141,
+      "grad_norm": 2.424880159324192,
+      "learning_rate": 1.5346205516085305e-05,
+      "loss": 1.0463,
+      "step": 380
+    },
+    {
+      "epoch": 1.1809815950920246,
+      "grad_norm": 3.026265515790728,
+      "learning_rate": 1.5194513233360439e-05,
+      "loss": 0.9217,
+      "step": 385
+    },
+    {
+      "epoch": 1.196319018404908,
+      "grad_norm": 3.1617293471411654,
+      "learning_rate": 1.504116591352832e-05,
+      "loss": 1.1437,
+      "step": 390
+    },
+    {
+      "epoch": 1.2116564417177913,
+      "grad_norm": 2.2307237557720003,
+      "learning_rate": 1.4886212414969551e-05,
+      "loss": 0.967,
+      "step": 395
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 2.430911245376782,
+      "learning_rate": 1.4729702107813438e-05,
+      "loss": 0.999,
+      "step": 400
+    },
+    {
+      "epoch": 1.2423312883435582,
+      "grad_norm": 2.1612231748678896,
+      "learning_rate": 1.4571684858208045e-05,
+      "loss": 1.004,
+      "step": 405
+    },
+    {
+      "epoch": 1.2576687116564418,
+      "grad_norm": 2.6596296516845563,
+      "learning_rate": 1.4412211012432213e-05,
+      "loss": 1.0454,
+      "step": 410
+    },
+    {
+      "epoch": 1.2730061349693251,
+      "grad_norm": 2.093932365865954,
+      "learning_rate": 1.4251331380854602e-05,
+      "loss": 1.0569,
+      "step": 415
+    },
+    {
+      "epoch": 1.2883435582822087,
+      "grad_norm": 2.72153245614344,
+      "learning_rate": 1.408909722174487e-05,
+      "loss": 0.9593,
+      "step": 420
+    },
+    {
+      "epoch": 1.303680981595092,
+      "grad_norm": 2.6462362091450515,
+      "learning_rate": 1.3925560224942145e-05,
+      "loss": 0.9271,
+      "step": 425
+    },
+    {
+      "epoch": 1.3190184049079754,
+      "grad_norm": 2.267205865998314,
+      "learning_rate": 1.3760772495385998e-05,
+      "loss": 0.9582,
+      "step": 430
+    },
+    {
+      "epoch": 1.334355828220859,
+      "grad_norm": 14.299415996684987,
+      "learning_rate": 1.3594786536515154e-05,
+      "loss": 0.9659,
+      "step": 435
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 2.8919289960885157,
+      "learning_rate": 1.3427655233539227e-05,
+      "loss": 0.922,
+      "step": 440
+    },
+    {
+      "epoch": 1.3650306748466257,
+      "grad_norm": 2.0424273794301344,
+      "learning_rate": 1.3259431836588843e-05,
+      "loss": 0.9932,
+      "step": 445
+    },
+    {
+      "epoch": 1.3803680981595092,
+      "grad_norm": 6.610636759407049,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.9837,
+      "step": 450
+    },
+    {
+      "epoch": 1.3957055214723926,
+      "grad_norm": 2.2497868172019357,
+      "learning_rate": 1.2919923483984415e-05,
+      "loss": 0.9149,
+      "step": 455
+    },
+    {
+      "epoch": 1.4110429447852761,
+      "grad_norm": 2.2842331908069125,
+      "learning_rate": 1.2748746699952338e-05,
+      "loss": 1.0342,
+      "step": 460
+    },
+    {
+      "epoch": 1.4263803680981595,
+      "grad_norm": 2.1102577421193085,
+      "learning_rate": 1.2576694130724905e-05,
+      "loss": 1.1568,
+      "step": 465
+    },
+    {
+      "epoch": 1.441717791411043,
+      "grad_norm": 2.127882920435348,
+      "learning_rate": 1.2403820594409926e-05,
+      "loss": 0.9638,
+      "step": 470
+    },
+    {
+      "epoch": 1.4570552147239264,
+      "grad_norm": 2.584359793762212,
+      "learning_rate": 1.2230181170685636e-05,
+      "loss": 0.9673,
+      "step": 475
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 2.264911154520169,
+      "learning_rate": 1.2055831183251608e-05,
+      "loss": 1.0154,
+      "step": 480
+    },
+    {
+      "epoch": 1.4877300613496933,
+      "grad_norm": 2.0087330179243335,
+      "learning_rate": 1.1880826182201926e-05,
+      "loss": 0.8973,
+      "step": 485
+    },
+    {
+      "epoch": 1.5030674846625767,
+      "grad_norm": 1.9321511470889676,
+      "learning_rate": 1.170522192632624e-05,
+      "loss": 0.9371,
+      "step": 490
+    },
+    {
+      "epoch": 1.51840490797546,
+      "grad_norm": 2.121122226050571,
+      "learning_rate": 1.1529074365344302e-05,
+      "loss": 1.033,
+      "step": 495
+    },
+    {
+      "epoch": 1.5337423312883436,
+      "grad_norm": 2.029011447995027,
+      "learning_rate": 1.1352439622079689e-05,
+      "loss": 0.9768,
+      "step": 500
+    },
+    {
+      "epoch": 1.5490797546012272,
+      "grad_norm": 2.108744801443365,
+      "learning_rate": 1.1175373974578378e-05,
+      "loss": 0.9089,
+      "step": 505
+    },
+    {
+      "epoch": 1.5644171779141103,
+      "grad_norm": 2.2204587915399876,
+      "learning_rate": 1.0997933838177828e-05,
+      "loss": 1.0449,
+      "step": 510
+    },
+    {
+      "epoch": 1.5797546012269938,
+      "grad_norm": 2.1535325181232294,
+      "learning_rate": 1.0820175747532373e-05,
+      "loss": 1.0172,
+      "step": 515
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 21.819229878115912,
+      "learning_rate": 1.064215633860055e-05,
+      "loss": 0.9769,
+      "step": 520
+    },
+    {
+      "epoch": 1.6104294478527608,
+      "grad_norm": 2.1296751297142897,
+      "learning_rate": 1.0463932330600197e-05,
+      "loss": 0.9483,
+      "step": 525
+    },
+    {
+      "epoch": 1.6257668711656441,
+      "grad_norm": 2.1616752600527134,
+      "learning_rate": 1.0285560507936962e-05,
+      "loss": 4.3216,
+      "step": 530
+    },
+    {
+      "epoch": 1.6411042944785277,
+      "grad_norm": 3.2786842755698795,
+      "learning_rate": 1.010709770211212e-05,
+      "loss": 1.1255,
+      "step": 535
+    },
+    {
+      "epoch": 1.656441717791411,
+      "grad_norm": 2.4763448399092147,
+      "learning_rate": 9.928600773615306e-06,
+      "loss": 1.0498,
+      "step": 540
+    },
+    {
+      "epoch": 1.6717791411042944,
+      "grad_norm": 2.006782735936947,
+      "learning_rate": 9.750126593808083e-06,
+      "loss": 0.927,
+      "step": 545
+    },
+    {
+      "epoch": 1.687116564417178,
+      "grad_norm": 2.2437759465461777,
+      "learning_rate": 9.571732026803978e-06,
+      "loss": 0.906,
+      "step": 550
+    },
+    {
+      "epoch": 1.7024539877300615,
+      "grad_norm": 1.9556898555009257,
+      "learning_rate": 9.393473911350895e-06,
+      "loss": 0.9715,
+      "step": 555
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 2.082737830638052,
+      "learning_rate": 9.215409042721553e-06,
+      "loss": 1.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.7331288343558282,
+      "grad_norm": 2.3756819460619534,
+      "learning_rate": 9.037594154617811e-06,
+      "loss": 0.9755,
+      "step": 565
+    },
+    {
+      "epoch": 1.7484662576687118,
+      "grad_norm": 2.7832428710692265,
+      "learning_rate": 8.860085901094595e-06,
+      "loss": 0.9694,
+      "step": 570
+    },
+    {
+      "epoch": 1.7638036809815951,
+      "grad_norm": 2.299830262573217,
+      "learning_rate": 8.682940838509206e-06,
+      "loss": 0.8829,
+      "step": 575
+    },
+    {
+      "epoch": 1.7791411042944785,
+      "grad_norm": 1.9164299833335463,
+      "learning_rate": 8.50621540750175e-06,
+      "loss": 0.9634,
+      "step": 580
+    },
+    {
+      "epoch": 1.794478527607362,
+      "grad_norm": 2.0803428687947023,
+      "learning_rate": 8.329965915012451e-06,
+      "loss": 1.0047,
+      "step": 585
+    },
+    {
+      "epoch": 1.8098159509202454,
+      "grad_norm": 1.961542308344144,
+      "learning_rate": 8.154248516341547e-06,
+      "loss": 0.9783,
+      "step": 590
+    },
+    {
+      "epoch": 1.8251533742331287,
+      "grad_norm": 1.98951654932812,
+      "learning_rate": 7.979119197257505e-06,
+      "loss": 1.0009,
+      "step": 595
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 2.1181463512012653,
+      "learning_rate": 7.804633756159258e-06,
+      "loss": 0.9263,
+      "step": 600
+    },
+    {
+      "epoch": 1.8558282208588959,
+      "grad_norm": 2.017971907316727,
+      "learning_rate": 7.63084778629813e-06,
+      "loss": 0.9933,
+      "step": 605
+    },
+    {
+      "epoch": 1.871165644171779,
+      "grad_norm": 2.1164163856970135,
+      "learning_rate": 7.4578166580651335e-06,
+      "loss": 0.9392,
+      "step": 610
+    },
+    {
+      "epoch": 1.8865030674846626,
+      "grad_norm": 2.118557747327772,
+      "learning_rate": 7.285595501349259e-06,
+      "loss": 0.9537,
+      "step": 615
+    },
+    {
+      "epoch": 1.9018404907975461,
+      "grad_norm": 2.087163676278093,
+      "learning_rate": 7.114239187972416e-06,
+      "loss": 0.8722,
+      "step": 620
+    },
+    {
+      "epoch": 1.9171779141104295,
+      "grad_norm": 2.222443842922782,
+      "learning_rate": 6.94380231420656e-06,
+      "loss": 0.9518,
+      "step": 625
+    },
+    {
+      "epoch": 1.9325153374233128,
+      "grad_norm": 2.0519691059771503,
+      "learning_rate": 6.774339183378663e-06,
+      "loss": 0.9595,
+      "step": 630
+    },
+    {
+      "epoch": 1.9478527607361964,
+      "grad_norm": 2.395088570054642,
+      "learning_rate": 6.605903788568962e-06,
+      "loss": 0.9082,
+      "step": 635
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 4.89604575465679,
+      "learning_rate": 6.438549795408107e-06,
+      "loss": 0.9101,
+      "step": 640
+    },
+    {
+      "epoch": 1.978527607361963,
+      "grad_norm": 2.1171931357011236,
+      "learning_rate": 6.272330524978613e-06,
+      "loss": 0.9687,
+      "step": 645
+    },
+    {
+      "epoch": 1.9938650306748467,
+      "grad_norm": 2.0986919385384137,
+      "learning_rate": 6.107298936826086e-06,
+      "loss": 0.8841,
+      "step": 650
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.2134720087051392,
+      "eval_runtime": 7.1411,
+      "eval_samples_per_second": 22.266,
+      "eval_steps_per_second": 5.601,
+      "step": 652
+    },
+    {
+      "epoch": 2.0092024539877302,
+      "grad_norm": 2.1628044565671556,
+      "learning_rate": 5.943507612085661e-06,
+      "loss": 0.8251,
+      "step": 655
+    },
+    {
+      "epoch": 2.0245398773006134,
+      "grad_norm": 1.980162767088004,
+      "learning_rate": 5.781008736728975e-06,
+      "loss": 0.6487,
+      "step": 660
+    },
+    {
+      "epoch": 2.039877300613497,
+      "grad_norm": 2.862228737237209,
+      "learning_rate": 5.619854084937085e-06,
+      "loss": 0.6706,
+      "step": 665
+    },
+    {
+      "epoch": 2.0552147239263805,
+      "grad_norm": 2.2439249118077136,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.6652,
+      "step": 670
+    },
+    {
+      "epoch": 2.0705521472392636,
+      "grad_norm": 2.254257809075137,
+      "learning_rate": 5.3017823909799295e-06,
+      "loss": 0.7293,
+      "step": 675
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 2.223082549239095,
+      "learning_rate": 5.144966690448159e-06,
+      "loss": 0.755,
+      "step": 680
+    },
+    {
+      "epoch": 2.1012269938650308,
+      "grad_norm": 2.0645657168776617,
+      "learning_rate": 4.9896978644594516e-06,
+      "loss": 0.5896,
+      "step": 685
+    },
+    {
+      "epoch": 2.116564417177914,
+      "grad_norm": 2.543974903041173,
+      "learning_rate": 4.836025383610382e-06,
+      "loss": 0.7457,
+      "step": 690
+    },
+    {
+      "epoch": 2.1319018404907975,
+      "grad_norm": 2.1096988101915524,
+      "learning_rate": 4.683998209881943e-06,
+      "loss": 0.6847,
+      "step": 695
+    },
+    {
+      "epoch": 2.147239263803681,
+      "grad_norm": 2.36099194700885,
+      "learning_rate": 4.533664781039622e-06,
+      "loss": 0.715,
+      "step": 700
+    },
+    {
+      "epoch": 2.1625766871165646,
+      "grad_norm": 2.633833128566785,
+      "learning_rate": 4.385072995200532e-06,
+      "loss": 0.626,
+      "step": 705
+    },
+    {
+      "epoch": 2.1779141104294477,
+      "grad_norm": 2.506530086487105,
+      "learning_rate": 4.2382701955724724e-06,
+      "loss": 0.7172,
+      "step": 710
+    },
+    {
+      "epoch": 2.1932515337423313,
+      "grad_norm": 2.3802287660865553,
+      "learning_rate": 4.093303155369771e-06,
+      "loss": 0.6839,
+      "step": 715
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 2.24220538972355,
+      "learning_rate": 3.950218062910776e-06,
+      "loss": 0.5827,
+      "step": 720
+    },
+    {
+      "epoch": 2.223926380368098,
+      "grad_norm": 2.2370918425887267,
+      "learning_rate": 3.8090605069016596e-06,
+      "loss": 0.6599,
+      "step": 725
+    },
+    {
+      "epoch": 2.2392638036809815,
+      "grad_norm": 2.1088652822907448,
+      "learning_rate": 3.6698754619112974e-06,
+      "loss": 0.7594,
+      "step": 730
+    },
+    {
+      "epoch": 2.254601226993865,
+      "grad_norm": 2.083592158309122,
+      "learning_rate": 3.53270727404179e-06,
+      "loss": 0.6702,
+      "step": 735
+    },
+    {
+      "epoch": 2.2699386503067487,
+      "grad_norm": 2.567792989862267,
+      "learning_rate": 3.3975996467992557e-06,
+      "loss": 0.6419,
+      "step": 740
+    },
+    {
+      "epoch": 2.285276073619632,
+      "grad_norm": 2.334913734729685,
+      "learning_rate": 3.2645956271693257e-06,
+      "loss": 0.6634,
+      "step": 745
+    },
+    {
+      "epoch": 2.3006134969325154,
+      "grad_norm": 2.3429523817504716,
+      "learning_rate": 3.133737591901864e-06,
+      "loss": 0.6939,
+      "step": 750
+    },
+    {
+      "epoch": 2.315950920245399,
+      "grad_norm": 2.2619584916199615,
+      "learning_rate": 3.0050672340091723e-06,
+      "loss": 0.6678,
+      "step": 755
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 2.6296479257995777,
+      "learning_rate": 2.878625549482084e-06,
+      "loss": 0.7031,
+      "step": 760
+    },
+    {
+      "epoch": 2.3466257668711656,
+      "grad_norm": 2.8130762384906864,
+      "learning_rate": 2.7544528242281323e-06,
+      "loss": 0.5788,
+      "step": 765
+    },
+    {
+      "epoch": 2.361963190184049,
+      "grad_norm": 2.150686530040835,
+      "learning_rate": 2.6325886212359496e-06,
+      "loss": 0.6077,
+      "step": 770
+    },
+    {
+      "epoch": 2.3773006134969323,
+      "grad_norm": 2.2806678502354476,
+      "learning_rate": 2.51307176797001e-06,
+      "loss": 0.7225,
+      "step": 775
+    },
+    {
+      "epoch": 2.392638036809816,
+      "grad_norm": 2.257367372279919,
+      "learning_rate": 2.395940343999691e-06,
+      "loss": 0.66,
+      "step": 780
+    },
+    {
+      "epoch": 2.4079754601226995,
+      "grad_norm": 2.105998185034246,
+      "learning_rate": 2.2812316688666735e-06,
+      "loss": 0.5642,
+      "step": 785
+    },
+    {
+      "epoch": 2.4233128834355826,
+      "grad_norm": 2.6751693267999164,
+      "learning_rate": 2.1689822901944456e-06,
+      "loss": 0.6999,
+      "step": 790
+    },
+    {
+      "epoch": 2.438650306748466,
+      "grad_norm": 2.337986334515246,
+      "learning_rate": 2.0592279720437856e-06,
+      "loss": 0.6405,
+      "step": 795
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 2.5090481285811026,
+      "learning_rate": 1.9520036835178667e-06,
+      "loss": 0.7335,
+      "step": 800
+    },
+    {
+      "epoch": 2.4693251533742333,
+      "grad_norm": 2.222070003754594,
+      "learning_rate": 1.8473435876206792e-06,
+      "loss": 0.6446,
+      "step": 805
+    },
+    {
+      "epoch": 2.4846625766871164,
+      "grad_norm": 2.3534318368821467,
+      "learning_rate": 1.74528103037226e-06,
+      "loss": 0.7604,
+      "step": 810
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.1957922076650225,
+      "learning_rate": 1.645848530184233e-06,
+      "loss": 0.6602,
+      "step": 815
+    },
+    {
+      "epoch": 2.5153374233128836,
+      "grad_norm": 2.248469614521019,
+      "learning_rate": 1.5490777674990376e-06,
+      "loss": 0.7518,
+      "step": 820
+    },
+    {
+      "epoch": 2.530674846625767,
+      "grad_norm": 2.358970858496667,
+      "learning_rate": 1.4549995746961332e-06,
+      "loss": 0.6974,
+      "step": 825
+    },
+    {
+      "epoch": 2.5460122699386503,
+      "grad_norm": 2.409137169378918,
+      "learning_rate": 1.3636439262684299e-06,
+      "loss": 0.6054,
+      "step": 830
+    },
+    {
+      "epoch": 2.561349693251534,
+      "grad_norm": 2.3008344145258275,
+      "learning_rate": 1.2750399292720284e-06,
+      "loss": 0.6626,
+      "step": 835
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 2.2498393839801403,
+      "learning_rate": 1.1892158140523546e-06,
+      "loss": 0.6923,
+      "step": 840
+    },
+    {
+      "epoch": 2.5920245398773005,
+      "grad_norm": 2.287309751844316,
+      "learning_rate": 1.1061989252496053e-06,
+      "loss": 0.6596,
+      "step": 845
+    },
+    {
+      "epoch": 2.607361963190184,
+      "grad_norm": 3.2190551280360937,
+      "learning_rate": 1.0260157130864178e-06,
+      "loss": 0.6771,
+      "step": 850
+    },
+    {
+      "epoch": 2.6226993865030677,
+      "grad_norm": 2.1948501519870782,
+      "learning_rate": 9.486917249404815e-07,
+      "loss": 0.6886,
+      "step": 855
+    },
+    {
+      "epoch": 2.638036809815951,
+      "grad_norm": 2.1803684507178955,
+      "learning_rate": 8.742515972048404e-07,
+      "loss": 0.7121,
+      "step": 860
+    },
+    {
+      "epoch": 2.6533742331288344,
+      "grad_norm": 2.089857540368277,
+      "learning_rate": 8.027190474384127e-07,
+      "loss": 0.5654,
+      "step": 865
+    },
+    {
+      "epoch": 2.668711656441718,
+      "grad_norm": 2.900973015953986,
+      "learning_rate": 7.341168668092857e-07,
+      "loss": 0.5899,
+      "step": 870
+    },
+    {
+      "epoch": 2.684049079754601,
+      "grad_norm": 2.269220220981122,
+      "learning_rate": 6.684669128331655e-07,
+      "loss": 0.7626,
+      "step": 875
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 2.177246970471886,
+      "learning_rate": 6.057901024092949e-07,
+      "loss": 0.6272,
+      "step": 880
+    },
+    {
+      "epoch": 2.714723926380368,
+      "grad_norm": 2.265583420009415,
+      "learning_rate": 5.461064051560705e-07,
+      "loss": 0.7539,
+      "step": 885
+    },
+    {
+      "epoch": 2.7300613496932513,
+      "grad_norm": 2.097337573364251,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.6404,
+      "step": 890
+    },
+    {
+      "epoch": 2.745398773006135,
+      "grad_norm": 2.6099811023622483,
+      "learning_rate": 4.3579345435930454e-07,
+      "loss": 0.781,
+      "step": 895
+    },
+    {
+      "epoch": 2.7607361963190185,
+      "grad_norm": 2.2217027523814155,
+      "learning_rate": 3.851993479063154e-07,
+      "loss": 0.7015,
+      "step": 900
+    },
+    {
+      "epoch": 2.7760736196319016,
+      "grad_norm": 2.325907671442105,
+      "learning_rate": 3.3766863760676947e-07,
+      "loss": 0.6844,
+      "step": 905
+    },
+    {
+      "epoch": 2.791411042944785,
+      "grad_norm": 2.264535197628352,
+      "learning_rate": 2.93216467341475e-07,
+      "loss": 0.6508,
+      "step": 910
+    },
+    {
+      "epoch": 2.8067484662576687,
+      "grad_norm": 2.4713808636104533,
+      "learning_rate": 2.5185700012975603e-07,
+      "loss": 0.7762,
+      "step": 915
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 2.402679896607673,
+      "learning_rate": 2.1360341361692517e-07,
+      "loss": 0.6639,
+      "step": 920
+    },
+    {
+      "epoch": 2.837423312883436,
+      "grad_norm": 2.179790948612016,
+      "learning_rate": 1.784678958757291e-07,
+      "loss": 0.65,
+      "step": 925
+    },
+    {
+      "epoch": 2.852760736196319,
+      "grad_norm": 2.076797574324857,
+      "learning_rate": 1.464616415230702e-07,
+      "loss": 0.6342,
+      "step": 930
+    },
+    {
+      "epoch": 2.8680981595092025,
+      "grad_norm": 2.1047162156910804,
+      "learning_rate": 1.1759484815326294e-07,
+      "loss": 0.6047,
+      "step": 935
+    },
+    {
+      "epoch": 2.883435582822086,
+      "grad_norm": 2.1660216273789237,
+      "learning_rate": 9.187671308895418e-08,
+      "loss": 0.6571,
+      "step": 940
+    },
+    {
+      "epoch": 2.8987730061349692,
+      "grad_norm": 2.713364435220778,
+      "learning_rate": 6.931543045073708e-08,
+      "loss": 0.8338,
+      "step": 945
+    },
+    {
+      "epoch": 2.914110429447853,
+      "grad_norm": 2.6713007123159724,
+      "learning_rate": 4.991818854640396e-08,
+      "loss": 0.6373,
+      "step": 950
+    },
+    {
+      "epoch": 2.9294478527607364,
+      "grad_norm": 2.1069338794602723,
+      "learning_rate": 3.369116758066171e-08,
+      "loss": 0.6385,
+      "step": 955
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 2.312520932069723,
+      "learning_rate": 2.063953768603799e-08,
+      "loss": 0.7596,
+      "step": 960
+    },
+    {
+      "epoch": 2.960122699386503,
+      "grad_norm": 2.1046770032748077,
+      "learning_rate": 1.0767457275615567e-08,
+      "loss": 0.634,
+      "step": 965
+    },
+    {
+      "epoch": 2.9754601226993866,
+      "grad_norm": 2.207645312141143,
+      "learning_rate": 4.0780717181077015e-09,
+      "loss": 0.7555,
+      "step": 970
+    },
+    {
+      "epoch": 2.9907975460122698,
+      "grad_norm": 2.457929371194042,
+      "learning_rate": 5.735123357042405e-10,
+      "loss": 0.7012,
+      "step": 975
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.3543522357940674,
+      "eval_runtime": 6.5158,
+      "eval_samples_per_second": 24.402,
+      "eval_steps_per_second": 6.139,
+      "step": 978
+    },
+    {
+      "epoch": 3.0,
+      "step": 978,
+      "total_flos": 3642602029056.0,
+      "train_loss": 1.0360665048314506,
+      "train_runtime": 586.176,
+      "train_samples_per_second": 6.674,
+      "train_steps_per_second": 1.668
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 978,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3642602029056.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53624d092600031a396068be5c97cc3df1725958186d1ebe3846858ecc969c0e
+size 6968