Training in progress, step 100

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: mistral-7b-dpo-full-wo-kqa_golden-ep3
+  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. -->
+
+# mistral-7b-dpo-full-wo-kqa_golden-ep3
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2889
+- Rewards/chosen: -0.9091
+- Rewards/rejected: -3.8737
+- Rewards/accuracies: 0.8250
+- Rewards/margins: 2.9646
+- Logps/rejected: -1290.0824
+- Logps/chosen: -656.5975
+- Logits/rejected: -2.9198
+- Logits/chosen: -3.1186
+
+## 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: 5e-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- 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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.1851        | 0.53  | 100  | 0.2889          | -0.9091        | -3.8737          | 0.8250             | 2.9646          | -1290.0824     | -656.5975    | -2.9198         | -3.1186       |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.27576306701343967,
+    "train_runtime": 3082.9663,
+    "train_samples": 11996,
+    "train_samples_per_second": 3.891,
+    "train_steps_per_second": 0.061
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267f7e96c3a254a09f752a3256ac512b2e248b9cfe7fa3017005c580906977d2
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493c8e696fb4bdba9978b1cb053a743fe75c8954129d62aaec43baaa987cd934
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc8ff93ae161def1d5859043c3dc04f83ca0519c89c4a8b0f846dd7572f64e8
+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"
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.27576306701343967,
+    "train_runtime": 3082.9663,
+    "train_samples": 11996,
+    "train_samples_per_second": 3.891,
+    "train_steps_per_second": 0.061
+}

trainer_state.json

@@ -0,0 +1,331 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9973333333333333,
+  "eval_steps": 100,
+  "global_step": 187,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 19.110474755913092,
+      "learning_rate": 2.6315789473684208e-08,
+      "logits/chosen": -2.964515209197998,
+      "logits/rejected": -2.865140914916992,
+      "logps/chosen": -485.6763916015625,
+      "logps/rejected": -1249.7501220703125,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 18.87772208802828,
+      "learning_rate": 2.631578947368421e-07,
+      "logits/chosen": -2.773491859436035,
+      "logits/rejected": -2.7407619953155518,
+      "logps/chosen": -604.6580810546875,
+      "logps/rejected": -1056.211181640625,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5069444179534912,
+      "rewards/chosen": 0.0016368491342291236,
+      "rewards/margins": 0.001945263589732349,
+      "rewards/rejected": -0.00030841471743769944,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 19.583298204247857,
+      "learning_rate": 4.999562902281866e-07,
+      "logits/chosen": -2.7963502407073975,
+      "logits/rejected": -2.827116012573242,
+      "logps/chosen": -571.3228759765625,
+      "logps/rejected": -971.4885864257812,
+      "loss": 0.675,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": 0.03118445910513401,
+      "rewards/margins": 0.03232298418879509,
+      "rewards/rejected": -0.0011385272955521941,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 23.803330324477223,
+      "learning_rate": 4.947295864744121e-07,
+      "logits/chosen": -2.8588290214538574,
+      "logits/rejected": -2.8853542804718018,
+      "logps/chosen": -529.5823974609375,
+      "logps/rejected": -1093.4755859375,
+      "loss": 0.6299,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.04894017428159714,
+      "rewards/margins": 0.15211351215839386,
+      "rewards/rejected": -0.10317333787679672,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 73.67534704558324,
+      "learning_rate": 4.809698831278217e-07,
+      "logits/chosen": -3.104024648666382,
+      "logits/rejected": -3.1031734943389893,
+      "logps/chosen": -630.6378173828125,
+      "logps/rejected": -1098.404541015625,
+      "loss": 0.5082,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -0.45488986372947693,
+      "rewards/margins": 0.6105720400810242,
+      "rewards/rejected": -1.0654619932174683,
+      "step": 40
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 70.45752193577601,
+      "learning_rate": 4.591569405016049e-07,
+      "logits/chosen": -3.1391983032226562,
+      "logits/rejected": -3.341365098953247,
+      "logps/chosen": -616.8588256835938,
+      "logps/rejected": -1329.1591796875,
+      "loss": 0.3004,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.7416905164718628,
+      "rewards/margins": 2.4845588207244873,
+      "rewards/rejected": -3.2262492179870605,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 39.13638850853986,
+      "learning_rate": 4.3005131163403164e-07,
+      "logits/chosen": -3.2234439849853516,
+      "logits/rejected": -3.387814998626709,
+      "logps/chosen": -613.5189208984375,
+      "logps/rejected": -1566.4166259765625,
+      "loss": 0.2494,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.7437312006950378,
+      "rewards/margins": 4.0797834396362305,
+      "rewards/rejected": -4.823514938354492,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 64.03359322882075,
+      "learning_rate": 3.946678240449515e-07,
+      "logits/chosen": -2.9871840476989746,
+      "logits/rejected": -3.163975715637207,
+      "logps/chosen": -617.3074340820312,
+      "logps/rejected": -1532.427978515625,
+      "loss": 0.2231,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -0.8076885938644409,
+      "rewards/margins": 4.495209693908691,
+      "rewards/rejected": -5.302898406982422,
+      "step": 70
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 30.339221409943534,
+      "learning_rate": 3.5424019569033206e-07,
+      "logits/chosen": -2.9922754764556885,
+      "logits/rejected": -3.0162343978881836,
+      "logps/chosen": -707.5257568359375,
+      "logps/rejected": -1704.016357421875,
+      "loss": 0.2364,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -1.1326261758804321,
+      "rewards/margins": 5.4823126792907715,
+      "rewards/rejected": -6.614939212799072,
+      "step": 80
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 29.449732213039997,
+      "learning_rate": 3.1017801885224326e-07,
+      "logits/chosen": -3.0152523517608643,
+      "logits/rejected": -3.0497183799743652,
+      "logps/chosen": -653.091552734375,
+      "logps/rejected": -1524.4569091796875,
+      "loss": 0.2151,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -0.900044322013855,
+      "rewards/margins": 4.4186201095581055,
+      "rewards/rejected": -5.318665027618408,
+      "step": 90
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 30.099525435462873,
+      "learning_rate": 2.640176118092979e-07,
+      "logits/chosen": -2.930925130844116,
+      "logits/rejected": -3.0645267963409424,
+      "logps/chosen": -727.9111938476562,
+      "logps/rejected": -1594.2391357421875,
+      "loss": 0.1851,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": -0.967258632183075,
+      "rewards/margins": 4.204586505889893,
+      "rewards/rejected": -5.171844482421875,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "eval_logits/chosen": -3.1186375617980957,
+      "eval_logits/rejected": -2.9198145866394043,
+      "eval_logps/chosen": -656.5974731445312,
+      "eval_logps/rejected": -1290.0823974609375,
+      "eval_loss": 0.288867712020874,
+      "eval_rewards/accuracies": 0.824999988079071,
+      "eval_rewards/chosen": -0.9091285467147827,
+      "eval_rewards/margins": 2.96455717086792,
+      "eval_rewards/rejected": -3.873685836791992,
+      "eval_runtime": 78.3784,
+      "eval_samples_per_second": 7.859,
+      "eval_steps_per_second": 0.255,
+      "step": 100
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 44.578131376508864,
+      "learning_rate": 2.1736845194498716e-07,
+      "logits/chosen": -2.9603259563446045,
+      "logits/rejected": -3.03521466255188,
+      "logps/chosen": -594.0872802734375,
+      "logps/rejected": -1612.428466796875,
+      "loss": 0.1691,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.8532097935676575,
+      "rewards/margins": 5.7642388343811035,
+      "rewards/rejected": -6.6174492835998535,
+      "step": 110
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 45.452576155560585,
+      "learning_rate": 1.718570580135889e-07,
+      "logits/chosen": -2.975057363510132,
+      "logits/rejected": -3.041111707687378,
+      "logps/chosen": -633.195068359375,
+      "logps/rejected": -1821.9937744140625,
+      "loss": 0.1416,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -1.0681055784225464,
+      "rewards/margins": 6.503140926361084,
+      "rewards/rejected": -7.571246147155762,
+      "step": 120
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 44.49014668597494,
+      "learning_rate": 1.2907027822369005e-07,
+      "logits/chosen": -2.963229179382324,
+      "logits/rejected": -3.067150831222534,
+      "logps/chosen": -721.2030029296875,
+      "logps/rejected": -1949.7958984375,
+      "loss": 0.1515,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -1.216491937637329,
+      "rewards/margins": 7.717434883117676,
+      "rewards/rejected": -8.93392562866211,
+      "step": 130
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 24.238718650060004,
+      "learning_rate": 9.049996151674788e-08,
+      "logits/chosen": -3.040541172027588,
+      "logits/rejected": -3.041283130645752,
+      "logps/chosen": -626.3173828125,
+      "logps/rejected": -1778.029541015625,
+      "loss": 0.185,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -0.9689780473709106,
+      "rewards/margins": 6.321756362915039,
+      "rewards/rejected": -7.29073429107666,
+      "step": 140
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 25.38260287029375,
+      "learning_rate": 5.74909411901843e-08,
+      "logits/chosen": -2.9344351291656494,
+      "logits/rejected": -2.9482829570770264,
+      "logps/chosen": -602.518798828125,
+      "logps/rejected": -1676.466796875,
+      "loss": 0.141,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": -0.8014429807662964,
+      "rewards/margins": 5.64138126373291,
+      "rewards/rejected": -6.442823886871338,
+      "step": 150
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 37.72257002210603,
+      "learning_rate": 3.119414452281158e-08,
+      "logits/chosen": -2.971004009246826,
+      "logits/rejected": -3.0024333000183105,
+      "logps/chosen": -657.559326171875,
+      "logps/rejected": -1856.759033203125,
+      "loss": 0.1321,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": -0.8327785730361938,
+      "rewards/margins": 7.157062530517578,
+      "rewards/rejected": -7.989840507507324,
+      "step": 160
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 23.531414397024523,
+      "learning_rate": 1.2526463331788501e-08,
+      "logits/chosen": -3.06162428855896,
+      "logits/rejected": -2.9571709632873535,
+      "logps/chosen": -637.3997192382812,
+      "logps/rejected": -1728.625732421875,
+      "loss": 0.133,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -0.9682890772819519,
+      "rewards/margins": 6.160744667053223,
+      "rewards/rejected": -7.129033088684082,
+      "step": 170
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 29.678702291223654,
+      "learning_rate": 2.1387846565474044e-09,
+      "logits/chosen": -3.0236430168151855,
+      "logits/rejected": -2.9661448001861572,
+      "logps/chosen": -605.8822021484375,
+      "logps/rejected": -1746.495849609375,
+      "loss": 0.1363,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -1.0128748416900635,
+      "rewards/margins": 6.32363224029541,
+      "rewards/rejected": -7.3365068435668945,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "step": 187,
+      "total_flos": 0.0,
+      "train_loss": 0.27576306701343967,
+      "train_runtime": 3082.9663,
+      "train_samples_per_second": 3.891,
+      "train_steps_per_second": 0.061
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 187,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b34439d43a41df0df2fdc8d0f54841616e4d938247ddc878dd22053f8648b21f
+oid sha256:6b86d9878fe7e0d391962486a7eca8073fa11d7828e83631aaa0e4006b79289f
 size 6200