Model save

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-7b-sft-full-10ep
+  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-sft-full-10ep
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0485
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.203         | 1.0   | 23   | 0.1086          |
+| 0.0942        | 2.0   | 46   | 0.0702          |
+| 0.064         | 3.0   | 69   | 0.0579          |
+| 0.055         | 4.0   | 92   | 0.0539          |
+| 0.0533        | 5.0   | 115  | 0.0529          |
+| 0.0525        | 6.0   | 138  | 0.0515          |
+| 0.0519        | 7.0   | 161  | 0.0505          |
+| 0.0505        | 8.0   | 184  | 0.0496          |
+| 0.0494        | 9.0   | 207  | 0.0487          |
+| 0.0484        | 10.0  | 230  | 0.0485          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 48157320806400.0,
+    "train_loss": 0.1130801611620447,
+    "train_runtime": 3471.4646,
+    "train_samples": 62967,
+    "train_samples_per_second": 4.137,
+    "train_steps_per_second": 0.066
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9884b5fe63b001cbcbe617917f46a07fd2fb26dba9f70d0a7bdae9d92e7a60fb
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b975a2fb699d3c97d72420cc405bd6827c97ac18032622086fa452abbb2006
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c3eafda30d2eee7ccaba35f3163a84673b2187b85147a9686e71eff37bcd421
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

runs/May07_10-26-26_e54ca48fff8845e4ad8a0f635d61b311000000/events.out.tfevents.1715077758.e54ca48fff8845e4ad8a0f635d61b311000000.347.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34697e9df71e7048f38ba27024cd6eaa15a256114a0954b10c07bcd7c08ca8ec
-size 15495
+oid sha256:cc11b59a0241a736878f175631d4d7e548587930df66aaf1ac869c57fd579f00
+size 17657

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 48157320806400.0,
+    "train_loss": 0.1130801611620447,
+    "train_runtime": 3471.4646,
+    "train_samples": 62967,
+    "train_samples_per_second": 4.137,
+    "train_steps_per_second": 0.066
+}

trainer_state.json

@@ -0,0 +1,439 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 175.07723361554483,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.9054,
+      "step": 1
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 62.962929820729734,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 1.4576,
+      "step": 5
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 8.648281883873826,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.6132,
+      "step": 10
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 16.239431113601718,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 0.3115,
+      "step": 15
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 3.450808311744288,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.203,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.10863249748945236,
+      "eval_runtime": 67.8349,
+      "eval_samples_per_second": 21.169,
+      "eval_steps_per_second": 0.663,
+      "step": 23
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 34.3749757818615,
+      "learning_rate": 1.9995393663024054e-05,
+      "loss": 0.1339,
+      "step": 25
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 2.3841429135265555,
+      "learning_rate": 1.9943621095573588e-05,
+      "loss": 0.1249,
+      "step": 30
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 1.2759644316371075,
+      "learning_rate": 1.9834617016337424e-05,
+      "loss": 0.088,
+      "step": 35
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 34.92728113964099,
+      "learning_rate": 1.9669008809262064e-05,
+      "loss": 0.0829,
+      "step": 40
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 2.0028289380489945,
+      "learning_rate": 1.944774964904754e-05,
+      "loss": 0.0942,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.07020141929388046,
+      "eval_runtime": 67.1251,
+      "eval_samples_per_second": 21.393,
+      "eval_steps_per_second": 0.67,
+      "step": 46
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 1.3438276529586066,
+      "learning_rate": 1.917211301505453e-05,
+      "loss": 0.0674,
+      "step": 50
+    },
+    {
+      "epoch": 2.391304347826087,
+      "grad_norm": 1142.7739612838905,
+      "learning_rate": 1.8843685361665724e-05,
+      "loss": 0.0668,
+      "step": 55
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 2.660687233406025,
+      "learning_rate": 1.8464356987288012e-05,
+      "loss": 0.065,
+      "step": 60
+    },
+    {
+      "epoch": 2.8260869565217392,
+      "grad_norm": 6.723586538182285,
+      "learning_rate": 1.8036311154549783e-05,
+      "loss": 0.064,
+      "step": 65
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.057872917503118515,
+      "eval_runtime": 67.6569,
+      "eval_samples_per_second": 21.225,
+      "eval_steps_per_second": 0.665,
+      "step": 69
+    },
+    {
+      "epoch": 3.0434782608695654,
+      "grad_norm": 0.7827050845032839,
+      "learning_rate": 1.7562011524313187e-05,
+      "loss": 0.0604,
+      "step": 70
+    },
+    {
+      "epoch": 3.260869565217391,
+      "grad_norm": 1.2639368123822572,
+      "learning_rate": 1.7044187975826126e-05,
+      "loss": 0.0755,
+      "step": 75
+    },
+    {
+      "epoch": 3.4782608695652173,
+      "grad_norm": 0.9047997047917037,
+      "learning_rate": 1.648582089462756e-05,
+      "loss": 0.0569,
+      "step": 80
+    },
+    {
+      "epoch": 3.6956521739130435,
+      "grad_norm": 0.5428178712369748,
+      "learning_rate": 1.589012401863864e-05,
+      "loss": 0.0577,
+      "step": 85
+    },
+    {
+      "epoch": 3.9130434782608696,
+      "grad_norm": 0.6450527453899985,
+      "learning_rate": 1.526052594117071e-05,
+      "loss": 0.055,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.05387277901172638,
+      "eval_runtime": 67.296,
+      "eval_samples_per_second": 21.339,
+      "eval_steps_per_second": 0.669,
+      "step": 92
+    },
+    {
+      "epoch": 4.130434782608695,
+      "grad_norm": 0.6167289429330038,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.0549,
+      "step": 95
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 0.5274268025844417,
+      "learning_rate": 1.3914295307268396e-05,
+      "loss": 0.0535,
+      "step": 100
+    },
+    {
+      "epoch": 4.565217391304348,
+      "grad_norm": 4.645394192055986,
+      "learning_rate": 1.3205411116710973e-05,
+      "loss": 0.0558,
+      "step": 105
+    },
+    {
+      "epoch": 4.782608695652174,
+      "grad_norm": 0.44016634132559596,
+      "learning_rate": 1.2478077859929e-05,
+      "loss": 0.0557,
+      "step": 110
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.37871781752696215,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.0533,
+      "step": 115
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.05291759595274925,
+      "eval_runtime": 67.622,
+      "eval_samples_per_second": 21.236,
+      "eval_steps_per_second": 0.665,
+      "step": 115
+    },
+    {
+      "epoch": 5.217391304347826,
+      "grad_norm": 0.4605215085179153,
+      "learning_rate": 1.0984891197811686e-05,
+      "loss": 0.0526,
+      "step": 120
+    },
+    {
+      "epoch": 5.434782608695652,
+      "grad_norm": 0.5874492251340868,
+      "learning_rate": 1.0227631978561057e-05,
+      "loss": 0.0531,
+      "step": 125
+    },
+    {
+      "epoch": 5.6521739130434785,
+      "grad_norm": 0.29510087532653284,
+      "learning_rate": 9.469062600552509e-06,
+      "loss": 0.0525,
+      "step": 130
+    },
+    {
+      "epoch": 5.869565217391305,
+      "grad_norm": 0.344906161076209,
+      "learning_rate": 8.71354908617169e-06,
+      "loss": 0.0525,
+      "step": 135
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.0515441857278347,
+      "eval_runtime": 67.5553,
+      "eval_samples_per_second": 21.257,
+      "eval_steps_per_second": 0.666,
+      "step": 138
+    },
+    {
+      "epoch": 6.086956521739131,
+      "grad_norm": 0.36354029610859134,
+      "learning_rate": 7.965439869473664e-06,
+      "loss": 0.0514,
+      "step": 140
+    },
+    {
+      "epoch": 6.304347826086957,
+      "grad_norm": 0.26428382375759113,
+      "learning_rate": 7.2290407683331154e-06,
+      "loss": 0.0515,
+      "step": 145
+    },
+    {
+      "epoch": 6.521739130434782,
+      "grad_norm": 0.22822648732081055,
+      "learning_rate": 6.508590201876317e-06,
+      "loss": 0.0512,
+      "step": 150
+    },
+    {
+      "epoch": 6.739130434782608,
+      "grad_norm": 0.25828737593751994,
+      "learning_rate": 5.8082347958333625e-06,
+      "loss": 0.0513,
+      "step": 155
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 0.2285799063924952,
+      "learning_rate": 5.132005516216512e-06,
+      "loss": 0.0519,
+      "step": 160
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.05051277205348015,
+      "eval_runtime": 67.5123,
+      "eval_samples_per_second": 21.27,
+      "eval_steps_per_second": 0.667,
+      "step": 161
+    },
+    {
+      "epoch": 7.173913043478261,
+      "grad_norm": 0.24475626828923558,
+      "learning_rate": 4.483794468689728e-06,
+      "loss": 0.0508,
+      "step": 165
+    },
+    {
+      "epoch": 7.391304347826087,
+      "grad_norm": 0.2520072015362384,
+      "learning_rate": 3.867332497162836e-06,
+      "loss": 0.0504,
+      "step": 170
+    },
+    {
+      "epoch": 7.608695652173913,
+      "grad_norm": 0.27382520169651525,
+      "learning_rate": 3.2861677105440335e-06,
+      "loss": 0.0504,
+      "step": 175
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 0.2716287514584957,
+      "learning_rate": 2.7436450612420098e-06,
+      "loss": 0.0505,
+      "step": 180
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.04957514628767967,
+      "eval_runtime": 67.276,
+      "eval_samples_per_second": 21.345,
+      "eval_steps_per_second": 0.669,
+      "step": 184
+    },
+    {
+      "epoch": 8.043478260869565,
+      "grad_norm": 0.21787711573464694,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.0496,
+      "step": 185
+    },
+    {
+      "epoch": 8.26086956521739,
+      "grad_norm": 0.21445383159071862,
+      "learning_rate": 1.7867759685603115e-06,
+      "loss": 0.0494,
+      "step": 190
+    },
+    {
+      "epoch": 8.478260869565217,
+      "grad_norm": 0.24405861737397047,
+      "learning_rate": 1.3779368815278648e-06,
+      "loss": 0.0491,
+      "step": 195
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 0.2697463930100617,
+      "learning_rate": 1.01872294636304e-06,
+      "loss": 0.0495,
+      "step": 200
+    },
+    {
+      "epoch": 8.91304347826087,
+      "grad_norm": 0.21112878071345867,
+      "learning_rate": 7.1120165501533e-07,
+      "loss": 0.0494,
+      "step": 205
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.048730239272117615,
+      "eval_runtime": 66.913,
+      "eval_samples_per_second": 21.461,
+      "eval_steps_per_second": 0.673,
+      "step": 207
+    },
+    {
+      "epoch": 9.130434782608695,
+      "grad_norm": 0.19010353057716406,
+      "learning_rate": 4.5714297722121105e-07,
+      "loss": 0.049,
+      "step": 210
+    },
+    {
+      "epoch": 9.347826086956522,
+      "grad_norm": 0.17948234694281104,
+      "learning_rate": 2.5800917326521013e-07,
+      "loss": 0.0491,
+      "step": 215
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 0.19343675188279383,
+      "learning_rate": 1.1494637779369766e-07,
+      "loss": 0.0489,
+      "step": 220
+    },
+    {
+      "epoch": 9.782608695652174,
+      "grad_norm": 0.21072621537133224,
+      "learning_rate": 2.8778003121607834e-08,
+      "loss": 0.0483,
+      "step": 225
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.18309652115048786,
+      "learning_rate": 0.0,
+      "loss": 0.0484,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.0484623983502388,
+      "eval_runtime": 67.5159,
+      "eval_samples_per_second": 21.269,
+      "eval_steps_per_second": 0.667,
+      "step": 230
+    },
+    {
+      "epoch": 10.0,
+      "step": 230,
+      "total_flos": 48157320806400.0,
+      "train_loss": 0.1130801611620447,
+      "train_runtime": 3471.4646,
+      "train_samples_per_second": 4.137,
+      "train_steps_per_second": 0.066
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 48157320806400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}