Model save

README.md

@@ -0,0 +1,73 @@
+---
+license: llama2
+base_model: epfl-llm/meditron-7b
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: meditron-7b-dpo-full-wo-medication_qa-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. -->
+
+# meditron-7b-dpo-full-wo-medication_qa-ep3
+
+This model is a fine-tuned version of [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6293
+- Rewards/chosen: -0.0145
+- Rewards/rejected: -0.1627
+- Rewards/accuracies: 0.7797
+- Rewards/margins: 0.1482
+- Logps/rejected: -1615.9989
+- Logps/chosen: -955.1961
+- Logits/rejected: -0.8722
+- Logits/chosen: -0.7069
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.592         | 0.55  | 100  | 0.6293          | -0.0145        | -0.1627          | 0.7797             | 0.1482          | -1615.9989     | -955.1961    | -0.8722         | -0.7069       |
+
+
+### 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": 0.5914445311983646,
+    "train_runtime": 2922.1625,
+    "train_samples": 11603,
+    "train_samples_per_second": 3.971,
+    "train_steps_per_second": 0.062
+}

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 sha256:5d7b1dda85ca2de5730cefd566d4331b3b8dae7c4d151488510bf2fece73d467
+size 4939124616

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6801f999037ce86de4dc14dbfd9a881735de7d98b9224e05d289b76fb638a552
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6359ec5024dadaa408bc99c5824c8a73ef4dd47f91f1b9535bf322231c0266e5
+size 3590628080

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13477109760
+  },
+  "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"
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.5914445311983646,
+    "train_runtime": 2922.1625,
+    "train_samples": 11603,
+    "train_samples_per_second": 3.971,
+    "train_steps_per_second": 0.062
+}

trainer_state.json

@@ -0,0 +1,331 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9972451790633609,
+  "eval_steps": 100,
+  "global_step": 181,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.4602671481986516,
+      "learning_rate": 2.6315789473684208e-08,
+      "logits/chosen": -0.7853389978408813,
+      "logits/rejected": -0.651086151599884,
+      "logps/chosen": -1158.1322021484375,
+      "logps/rejected": -1143.569091796875,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.676508624329794,
+      "learning_rate": 2.631578947368421e-07,
+      "logits/chosen": -0.709392786026001,
+      "logits/rejected": -0.8101767897605896,
+      "logps/chosen": -995.121826171875,
+      "logps/rejected": -1316.8297119140625,
+      "loss": 0.693,
+      "rewards/accuracies": 0.4305555522441864,
+      "rewards/chosen": -0.0007655912195332348,
+      "rewards/margins": -0.00027954205870628357,
+      "rewards/rejected": -0.0004860491317231208,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.611380190345714,
+      "learning_rate": 4.999529926121253e-07,
+      "logits/chosen": -0.7076992988586426,
+      "logits/rejected": -0.826177716255188,
+      "logps/chosen": -942.4779052734375,
+      "logps/rejected": -1303.2080078125,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.581250011920929,
+      "rewards/chosen": 0.0009432749939151108,
+      "rewards/margins": 0.002406059531494975,
+      "rewards/rejected": -0.0014627845957875252,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.545137388238839,
+      "learning_rate": 4.943334645626589e-07,
+      "logits/chosen": -0.7218513488769531,
+      "logits/rejected": -0.8190325498580933,
+      "logps/chosen": -986.5565185546875,
+      "logps/rejected": -1347.8033447265625,
+      "loss": 0.6883,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.004364156164228916,
+      "rewards/margins": 0.008785699494183064,
+      "rewards/rejected": -0.004421542398631573,
+      "step": 30
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.401192871872299,
+      "learning_rate": 4.795540267200686e-07,
+      "logits/chosen": -0.7325557470321655,
+      "logits/rejected": -0.7795466184616089,
+      "logps/chosen": -1022.5738525390625,
+      "logps/rejected": -1272.192626953125,
+      "loss": 0.6826,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.01184375025331974,
+      "rewards/margins": 0.019737884402275085,
+      "rewards/rejected": -0.007894134148955345,
+      "step": 40
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.67072465163404,
+      "learning_rate": 4.561687510272767e-07,
+      "logits/chosen": -0.7071916460990906,
+      "logits/rejected": -0.7952053546905518,
+      "logps/chosen": -973.41259765625,
+      "logps/rejected": -1254.411376953125,
+      "loss": 0.6759,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 0.010998593643307686,
+      "rewards/margins": 0.031063910573720932,
+      "rewards/rejected": -0.020065316930413246,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.340731797997725,
+      "learning_rate": 4.2505433694179213e-07,
+      "logits/chosen": -0.7227746248245239,
+      "logits/rejected": -0.8140878677368164,
+      "logps/chosen": -1035.677734375,
+      "logps/rejected": -1306.7808837890625,
+      "loss": 0.6642,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": 0.017496155574917793,
+      "rewards/margins": 0.06553898006677628,
+      "rewards/rejected": -0.04804282635450363,
+      "step": 60
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.496628183792233,
+      "learning_rate": 3.873772445177015e-07,
+      "logits/chosen": -0.7832368612289429,
+      "logits/rejected": -0.7676926851272583,
+      "logps/chosen": -1028.62890625,
+      "logps/rejected": -1254.6610107421875,
+      "loss": 0.6538,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.01262822188436985,
+      "rewards/margins": 0.07675839215517044,
+      "rewards/rejected": -0.06413016468286514,
+      "step": 70
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.939508062028092,
+      "learning_rate": 3.445499645429106e-07,
+      "logits/chosen": -0.7500189542770386,
+      "logits/rejected": -0.8156210780143738,
+      "logps/chosen": -1028.065185546875,
+      "logps/rejected": -1316.736328125,
+      "loss": 0.6433,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": 0.0009801089763641357,
+      "rewards/margins": 0.0968375876545906,
+      "rewards/rejected": -0.09585747867822647,
+      "step": 80
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.7399950008550205,
+      "learning_rate": 2.981780651370224e-07,
+      "logits/chosen": -0.7468028664588928,
+      "logits/rejected": -0.7884877920150757,
+      "logps/chosen": -996.8697509765625,
+      "logps/rejected": -1192.45654296875,
+      "loss": 0.6079,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.004719099495559931,
+      "rewards/margins": 0.21119482815265656,
+      "rewards/rejected": -0.20647573471069336,
+      "step": 90
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.466151335512206,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": -0.7582017183303833,
+      "logits/rejected": -0.8466933369636536,
+      "logps/chosen": -979.6242065429688,
+      "logps/rejected": -1357.511962890625,
+      "loss": 0.592,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -0.00921861082315445,
+      "rewards/margins": 0.2683759033679962,
+      "rewards/rejected": -0.27759450674057007,
+      "step": 100
+    },
+    {
+      "epoch": 0.55,
+      "eval_logits/chosen": -0.7069126963615417,
+      "eval_logits/rejected": -0.8721536993980408,
+      "eval_logps/chosen": -955.1961059570312,
+      "eval_logps/rejected": -1615.9989013671875,
+      "eval_loss": 0.6292956471443176,
+      "eval_rewards/accuracies": 0.7796609997749329,
+      "eval_rewards/chosen": -0.0145129868760705,
+      "eval_rewards/margins": 0.14818498492240906,
+      "eval_rewards/rejected": -0.16269797086715698,
+      "eval_runtime": 214.9002,
+      "eval_samples_per_second": 8.674,
+      "eval_steps_per_second": 0.275,
+      "step": 100
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 4.779970412172738,
+      "learning_rate": 2.018219348629775e-07,
+      "logits/chosen": -0.779070258140564,
+      "logits/rejected": -0.8311734199523926,
+      "logps/chosen": -992.7100830078125,
+      "logps/rejected": -1354.688720703125,
+      "loss": 0.5575,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.0526651069521904,
+      "rewards/margins": 0.4234324097633362,
+      "rewards/rejected": -0.4760975241661072,
+      "step": 110
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.9180549707398695,
+      "learning_rate": 1.554500354570894e-07,
+      "logits/chosen": -0.7683907747268677,
+      "logits/rejected": -0.8335941433906555,
+      "logps/chosen": -1003.9620971679688,
+      "logps/rejected": -1312.5740966796875,
+      "loss": 0.5428,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": -0.06494404375553131,
+      "rewards/margins": 0.5937026739120483,
+      "rewards/rejected": -0.6586467623710632,
+      "step": 120
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.7132927229572354,
+      "learning_rate": 1.126227554822985e-07,
+      "logits/chosen": -0.798209011554718,
+      "logits/rejected": -0.8723245859146118,
+      "logps/chosen": -1054.9263916015625,
+      "logps/rejected": -1349.2750244140625,
+      "loss": 0.5312,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.15924784541130066,
+      "rewards/margins": 0.5923423767089844,
+      "rewards/rejected": -0.7515901923179626,
+      "step": 130
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 10.497632384133095,
+      "learning_rate": 7.494566305820788e-08,
+      "logits/chosen": -0.8022674322128296,
+      "logits/rejected": -0.882843017578125,
+      "logps/chosen": -1055.48974609375,
+      "logps/rejected": -1417.170654296875,
+      "loss": 0.4988,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -0.17785976827144623,
+      "rewards/margins": 1.1309340000152588,
+      "rewards/rejected": -1.3087936639785767,
+      "step": 140
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 6.590111680094942,
+      "learning_rate": 4.38312489727233e-08,
+      "logits/chosen": -0.7941451668739319,
+      "logits/rejected": -0.8360635042190552,
+      "logps/chosen": -994.5494384765625,
+      "logps/rejected": -1374.3560791015625,
+      "loss": 0.4917,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": -0.2062647044658661,
+      "rewards/margins": 0.8967850804328918,
+      "rewards/rejected": -1.1030497550964355,
+      "step": 150
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 8.361359149599993,
+      "learning_rate": 2.044597327993153e-08,
+      "logits/chosen": -0.7812503576278687,
+      "logits/rejected": -0.8671078681945801,
+      "logps/chosen": -1042.375244140625,
+      "logps/rejected": -1443.9189453125,
+      "loss": 0.4813,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.2346261441707611,
+      "rewards/margins": 0.8702405095100403,
+      "rewards/rejected": -1.104866623878479,
+      "step": 160
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 7.649602408833162,
+      "learning_rate": 5.666535437341108e-09,
+      "logits/chosen": -0.792350172996521,
+      "logits/rejected": -0.8578357696533203,
+      "logps/chosen": -1057.263427734375,
+      "logps/rejected": -1363.985107421875,
+      "loss": 0.4843,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -0.292695015668869,
+      "rewards/margins": 1.1091253757476807,
+      "rewards/rejected": -1.401820421218872,
+      "step": 170
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 8.116244988839705,
+      "learning_rate": 4.700738787466463e-11,
+      "logits/chosen": -0.7855504751205444,
+      "logits/rejected": -0.8505135774612427,
+      "logps/chosen": -952.7326049804688,
+      "logps/rejected": -1447.79541015625,
+      "loss": 0.4771,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.23469653725624084,
+      "rewards/margins": 0.9054014086723328,
+      "rewards/rejected": -1.140097975730896,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "step": 181,
+      "total_flos": 0.0,
+      "train_loss": 0.5914445311983646,
+      "train_runtime": 2922.1625,
+      "train_samples_per_second": 3.971,
+      "train_steps_per_second": 0.062
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 181,
+  "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
+}