Model save

README.md

@@ -0,0 +1,74 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: vicuna-ul15-sft-full
+  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. -->
+
+# vicuna-ul15-sft-full
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4380
+
+## 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: 32
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 512
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0541        | 0.68  | 14   | 1.0341          |
+| 0.9708        | 1.71  | 29   | 1.0142          |
+| 0.9142        | 2.68  | 43   | 1.0111          |
+| 0.8637        | 3.71  | 58   | 1.0239          |
+| 0.8091        | 4.68  | 72   | 1.0363          |
+| 0.7516        | 5.71  | 87   | 1.0780          |
+| 0.6884        | 6.68  | 101  | 1.0987          |
+| 0.6309        | 7.71  | 116  | 1.1394          |
+| 0.5696        | 8.68  | 130  | 1.1820          |
+| 0.4752        | 9.71  | 145  | 1.2695          |
+| 0.448         | 10.68 | 159  | 1.3109          |
+| 0.3955        | 11.71 | 174  | 1.3877          |
+| 0.3579        | 12.68 | 188  | 1.3923          |
+| 0.3228        | 13.71 | 203  | 1.4064          |
+| 0.2914        | 14.68 | 217  | 1.4377          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0a0+32f93b1
+- Datasets 2.14.6
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 14.68,
+    "eval_loss": 1.4379942417144775,
+    "eval_runtime": 379.0519,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 60.968,
+    "eval_steps_per_second": 0.478,
+    "train_loss": 0.6393404012451523,
+    "train_runtime": 14968.9879,
+    "train_samples": 10393,
+    "train_samples_per_second": 10.415,
+    "train_steps_per_second": 0.02
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/data/models/vicuna-7b-v1.3",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 14.68,
+    "eval_loss": 1.4379942417144775,
+    "eval_runtime": 379.0519,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 60.968,
+    "eval_steps_per_second": 0.478
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed2b3bd2e7cfa2e0316fe162dec037c890f15106d2e2bd6429b5b06f047416e
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbce1e16b4d07afdd941f20535646027bbc7969b293cf9c6784c97bc884fa265
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4bc6121ea859afc872f9f894dc8d774a6d8325c0f8b5d4624f3a6f7b4be588
+size 3590488816

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "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-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-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-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-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-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-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/Jan14_05-30-37_c59b1c8aa740/events.out.tfevents.1705210278.c59b1c8aa740.2978.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937c6aca1a8e281f0d3f89d9bc3f317f660849af77b86066d0e03942d64e8c32
+size 15469

runs/Jan14_05-30-37_c59b1c8aa740/events.out.tfevents.1705225626.c59b1c8aa740.2978.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78781443b6eaccd65d520cf253945e332715473e52f4fa1c4ca7e429bb3c749
+size 311

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'USER: ' + message['content'] + ' '}}{% elif message['role'] == 'system' %}{{ message['content'] + ' '}}{% elif message['role'] == 'assistant' %}\n{{ 'ASSISTANT: '  + message['content'] + ' '}}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'ASSISTANT:' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 14.68,
+    "train_loss": 0.6393404012451523,
+    "train_runtime": 14968.9879,
+    "train_samples": 10393,
+    "train_samples_per_second": 10.415,
+    "train_steps_per_second": 0.02
+}

trainer_state.json

@@ -0,0 +1,412 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.682926829268293,
+  "eval_steps": 500,
+  "global_step": 217,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9999451693655125e-05,
+      "loss": 1.3914,
+      "step": 1
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9986295347545738e-05,
+      "loss": 1.1489,
+      "step": 5
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9945218953682736e-05,
+      "loss": 1.0541,
+      "step": 10
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 1.0341095924377441,
+      "eval_runtime": 379.2893,
+      "eval_samples_per_second": 60.93,
+      "eval_steps_per_second": 0.477,
+      "step": 14
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 1.0441,
+      "step": 15
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.9858,
+      "step": 20
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.9708,
+      "step": 25
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 1.0142368078231812,
+      "eval_runtime": 378.349,
+      "eval_samples_per_second": 61.081,
+      "eval_steps_per_second": 0.478,
+      "step": 29
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.9679,
+      "step": 30
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.9335804264972018e-05,
+      "loss": 0.9274,
+      "step": 35
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.9142,
+      "step": 40
+    },
+    {
+      "epoch": 2.68,
+      "eval_loss": 1.0111455917358398,
+      "eval_runtime": 378.1977,
+      "eval_samples_per_second": 61.106,
+      "eval_steps_per_second": 0.479,
+      "step": 43
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.8994,
+      "step": 45
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.8775,
+      "step": 50
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.8386705679454243e-05,
+      "loss": 0.8637,
+      "step": 55
+    },
+    {
+      "epoch": 3.71,
+      "eval_loss": 1.023858666419983,
+      "eval_runtime": 378.3558,
+      "eval_samples_per_second": 61.08,
+      "eval_steps_per_second": 0.478,
+      "step": 58
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.8323,
+      "step": 60
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 1.777145961456971e-05,
+      "loss": 0.8209,
+      "step": 65
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 1.7431448254773943e-05,
+      "loss": 0.8091,
+      "step": 70
+    },
+    {
+      "epoch": 4.68,
+      "eval_loss": 1.0362672805786133,
+      "eval_runtime": 378.1433,
+      "eval_samples_per_second": 61.114,
+      "eval_steps_per_second": 0.479,
+      "step": 72
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.7588,
+      "step": 75
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.7629,
+      "step": 80
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 1.6293203910498375e-05,
+      "loss": 0.7516,
+      "step": 85
+    },
+    {
+      "epoch": 5.71,
+      "eval_loss": 1.0779954195022583,
+      "eval_runtime": 378.7856,
+      "eval_samples_per_second": 61.011,
+      "eval_steps_per_second": 0.478,
+      "step": 87
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.6866,
+      "step": 90
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.5446390350150272e-05,
+      "loss": 0.6993,
+      "step": 95
+    },
+    {
+      "epoch": 6.63,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.6884,
+      "step": 100
+    },
+    {
+      "epoch": 6.68,
+      "eval_loss": 1.0987329483032227,
+      "eval_runtime": 378.7519,
+      "eval_samples_per_second": 61.016,
+      "eval_steps_per_second": 0.478,
+      "step": 101
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.6135,
+      "step": 105
+    },
+    {
+      "epoch": 7.41,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 0.6301,
+      "step": 110
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 1.3583679495453e-05,
+      "loss": 0.6309,
+      "step": 115
+    },
+    {
+      "epoch": 7.71,
+      "eval_loss": 1.1394284963607788,
+      "eval_runtime": 378.7271,
+      "eval_samples_per_second": 61.02,
+      "eval_steps_per_second": 0.478,
+      "step": 116
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.5431,
+      "step": 120
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.5686,
+      "step": 125
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 0.5696,
+      "step": 130
+    },
+    {
+      "epoch": 8.68,
+      "eval_loss": 1.1820148229599,
+      "eval_runtime": 378.7544,
+      "eval_samples_per_second": 61.016,
+      "eval_steps_per_second": 0.478,
+      "step": 130
+    },
+    {
+      "epoch": 9.22,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.489,
+      "step": 135
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.5067,
+      "step": 140
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 1.0523359562429441e-05,
+      "loss": 0.4752,
+      "step": 145
+    },
+    {
+      "epoch": 9.71,
+      "eval_loss": 1.2695468664169312,
+      "eval_runtime": 379.3356,
+      "eval_samples_per_second": 60.922,
+      "eval_steps_per_second": 0.477,
+      "step": 145
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 1e-05,
+      "loss": 0.4579,
+      "step": 150
+    },
+    {
+      "epoch": 10.49,
+      "learning_rate": 9.476640437570562e-06,
+      "loss": 0.448,
+      "step": 155
+    },
+    {
+      "epoch": 10.68,
+      "eval_loss": 1.3108839988708496,
+      "eval_runtime": 379.098,
+      "eval_samples_per_second": 60.96,
+      "eval_steps_per_second": 0.477,
+      "step": 159
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.4175,
+      "step": 160
+    },
+    {
+      "epoch": 11.27,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.4065,
+      "step": 165
+    },
+    {
+      "epoch": 11.51,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 0.3955,
+      "step": 170
+    },
+    {
+      "epoch": 11.71,
+      "eval_loss": 1.387709379196167,
+      "eval_runtime": 379.1872,
+      "eval_samples_per_second": 60.946,
+      "eval_steps_per_second": 0.477,
+      "step": 174
+    },
+    {
+      "epoch": 12.05,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.3736,
+      "step": 175
+    },
+    {
+      "epoch": 12.29,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.3623,
+      "step": 180
+    },
+    {
+      "epoch": 12.54,
+      "learning_rate": 6.4163205045469975e-06,
+      "loss": 0.3579,
+      "step": 185
+    },
+    {
+      "epoch": 12.68,
+      "eval_loss": 1.3922604322433472,
+      "eval_runtime": 378.9155,
+      "eval_samples_per_second": 60.99,
+      "eval_steps_per_second": 0.478,
+      "step": 188
+    },
+    {
+      "epoch": 13.07,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 0.3336,
+      "step": 190
+    },
+    {
+      "epoch": 13.32,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.3216,
+      "step": 195
+    },
+    {
+      "epoch": 13.56,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3228,
+      "step": 200
+    },
+    {
+      "epoch": 13.71,
+      "eval_loss": 1.4064093828201294,
+      "eval_runtime": 378.8946,
+      "eval_samples_per_second": 60.993,
+      "eval_steps_per_second": 0.478,
+      "step": 203
+    },
+    {
+      "epoch": 14.1,
+      "learning_rate": 4.5536096498497295e-06,
+      "loss": 0.2974,
+      "step": 205
+    },
+    {
+      "epoch": 14.34,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.29,
+      "step": 210
+    },
+    {
+      "epoch": 14.59,
+      "learning_rate": 3.7067960895016277e-06,
+      "loss": 0.2914,
+      "step": 215
+    },
+    {
+      "epoch": 14.68,
+      "eval_loss": 1.4377079010009766,
+      "eval_runtime": 378.9608,
+      "eval_samples_per_second": 60.983,
+      "eval_steps_per_second": 0.478,
+      "step": 217
+    },
+    {
+      "epoch": 14.68,
+      "step": 217,
+      "total_flos": 353275824046080.0,
+      "train_loss": 0.6393404012451523,
+      "train_runtime": 14968.9879,
+      "train_samples_per_second": 10.415,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 353275824046080.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb939e8ece3b50f614eb1fcc6f5dd1b0568106186966d71243988a776b9bd3f
+size 5624