Model save

README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+base_model: weijie210/mistral_gsm8k_sft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: mistral_gsm8k_dpo_0
+  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_gsm8k_dpo_0
+
+This model is a fine-tuned version of [weijie210/mistral_gsm8k_sft](https://huggingface.co/weijie210/mistral_gsm8k_sft) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0108
+- Rewards/chosen: -1.6999
+- Rewards/rejected: -22.5187
+- Rewards/accuracies: 0.9957
+- Rewards/margins: 20.8188
+- Logps/rejected: -238.0359
+- Logps/chosen: -48.7549
+- Logits/rejected: -2.6146
+- Logits/chosen: -2.6687
+
+## 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
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.36.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 2.0,
+    "eval_logits/chosen": -2.668743848800659,
+    "eval_logits/rejected": -2.614588499069214,
+    "eval_logps/chosen": -48.75492858886719,
+    "eval_logps/rejected": -238.03585815429688,
+    "eval_loss": 0.010777823626995087,
+    "eval_rewards/accuracies": 0.9956896305084229,
+    "eval_rewards/chosen": -1.6998504400253296,
+    "eval_rewards/margins": 20.81882667541504,
+    "eval_rewards/rejected": -22.5186767578125,
+    "eval_runtime": 231.3578,
+    "eval_samples": 905,
+    "eval_samples_per_second": 3.912,
+    "eval_steps_per_second": 0.125,
+    "train_loss": 0.06552632141962543,
+    "train_runtime": 3687.7187,
+    "train_samples": 4570,
+    "train_samples_per_second": 2.478,
+    "train_steps_per_second": 0.078
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "weijie210/mistral_gsm8k_sft",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 2.0,
+    "eval_logits/chosen": -2.668743848800659,
+    "eval_logits/rejected": -2.614588499069214,
+    "eval_logps/chosen": -48.75492858886719,
+    "eval_logps/rejected": -238.03585815429688,
+    "eval_loss": 0.010777823626995087,
+    "eval_rewards/accuracies": 0.9956896305084229,
+    "eval_rewards/chosen": -1.6998504400253296,
+    "eval_rewards/margins": 20.81882667541504,
+    "eval_rewards/rejected": -22.5186767578125,
+    "eval_runtime": 231.3578,
+    "eval_samples": 905,
+    "eval_samples_per_second": 3.912,
+    "eval_steps_per_second": 0.125
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fc4ae69f0657ea215db6e5e9e12ac0bc3c89237fe4ad55907e57c6d333781d
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cca397186b414340bf11e0e97b31da81a39d7360906409f0ecdd05568167285
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a8172879d63ccfe57f48341c65c1644ab15cd1220f2ab8396334cd0262cdbda
+size 4540516344

model.safetensors.index.json

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

runs/Feb09_01-36-34_node01/events.out.tfevents.1707414076.node01.399158.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee60cddfb1ac1820c072d6bdc496cbcc48b7f81d92b6a922dc7acc5f40fc90a9
+size 17330

runs/Feb09_01-36-34_node01/events.out.tfevents.1707416827.node01.399158.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d1be9fb48069a55da6b4117006b2648f68d4c77c66b5aeb09fbff2ec281c8b
+size 828

runs/Feb09_09-39-43_node01/events.out.tfevents.1707442937.node01.450204.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1620b5311503f983bb4e73f4079a205b24f0325e119d8b9a509153e2f65eac4d
+size 6308

runs/Feb09_10-55-15_node01/events.out.tfevents.1707447447.node01.464573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce1ffabb1c82c213970d9e6a0a2e9aaa20480ecc433ef92e0808bda1867d905
+size 15708

runs/Feb10_10-59-01_node01/events.out.tfevents.1707534108.node01.620006.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:713ebec4324a203229690878836683a6027e05826aff9b595ff0eb4ec022b143
+size 23036

runs/Feb10_10-59-01_node01/events.out.tfevents.1707537988.node01.620006.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16467635a65d859117f4fceedccc16d0fb4c25d977e82fe3f8bdfada4c23f12b
+size 828

runs/Feb12_11-33-36_node01/events.out.tfevents.1707709012.node01.922658.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5856e57efa9759fa827209b1d10dcca1e9e25a635172d1558511cbef92aef294
+size 23036

runs/Feb12_11-33-36_node01/events.out.tfevents.1707712931.node01.922658.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ae926f1a1dbe008d1a4a01f20c64f38d6aa2489ce5c8fbe34a2807e2e6b0c3
+size 828

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% 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,
+  "max_length": 2048,
+  "model_max_length": 4096,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.06552632141962543,
+    "train_runtime": 3687.7187,
+    "train_samples": 4570,
+    "train_samples_per_second": 2.478,
+    "train_steps_per_second": 0.078
+}

trainer_state.json

@@ -0,0 +1,436 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 286,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7241379310344825e-08,
+      "logits/chosen": -2.46767258644104,
+      "logits/rejected": -2.4595911502838135,
+      "logps/chosen": -22.810455322265625,
+      "logps/rejected": -22.677112579345703,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.7241379310344828e-07,
+      "logits/chosen": -2.815382719039917,
+      "logits/rejected": -2.7576191425323486,
+      "logps/chosen": -19.62689971923828,
+      "logps/rejected": -11.512568473815918,
+      "loss": 0.6817,
+      "rewards/accuracies": 0.6944444179534912,
+      "rewards/chosen": -0.002836173167452216,
+      "rewards/margins": 0.020304910838603973,
+      "rewards/rejected": -0.023141082376241684,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.4482758620689656e-07,
+      "logits/chosen": -2.760253429412842,
+      "logits/rejected": -2.776731014251709,
+      "logps/chosen": -18.500263214111328,
+      "logps/rejected": -24.879409790039062,
+      "loss": 0.3663,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.05979099124670029,
+      "rewards/margins": 1.2453944683074951,
+      "rewards/rejected": -1.3051855564117432,
+      "step": 20
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.980544747081712e-07,
+      "logits/chosen": -2.8509573936462402,
+      "logits/rejected": -2.8971199989318848,
+      "logps/chosen": -20.137048721313477,
+      "logps/rejected": -61.92778778076172,
+      "loss": 0.1236,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -0.16065621376037598,
+      "rewards/margins": 4.86615514755249,
+      "rewards/rejected": -5.026811599731445,
+      "step": 30
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.785992217898833e-07,
+      "logits/chosen": -2.792508602142334,
+      "logits/rejected": -2.8558077812194824,
+      "logps/chosen": -23.098939895629883,
+      "logps/rejected": -88.87196350097656,
+      "loss": 0.0921,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -0.44465622305870056,
+      "rewards/margins": 7.166872978210449,
+      "rewards/rejected": -7.611530303955078,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.591439688715953e-07,
+      "logits/chosen": -2.8872122764587402,
+      "logits/rejected": -2.8914027214050293,
+      "logps/chosen": -21.817670822143555,
+      "logps/rejected": -82.24397277832031,
+      "loss": 0.0947,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -0.6026766896247864,
+      "rewards/margins": 6.256636619567871,
+      "rewards/rejected": -6.85931396484375,
+      "step": 50
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.3968871595330735e-07,
+      "logits/chosen": -2.8102235794067383,
+      "logits/rejected": -2.867000102996826,
+      "logps/chosen": -22.098957061767578,
+      "logps/rejected": -106.98995208740234,
+      "loss": 0.0684,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.6044292449951172,
+      "rewards/margins": 8.731573104858398,
+      "rewards/rejected": -9.336004257202148,
+      "step": 60
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.202334630350194e-07,
+      "logits/chosen": -2.838426113128662,
+      "logits/rejected": -2.8441996574401855,
+      "logps/chosen": -32.25341033935547,
+      "logps/rejected": -112.56993103027344,
+      "loss": 0.0467,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.9181193113327026,
+      "rewards/margins": 8.931884765625,
+      "rewards/rejected": -9.850004196166992,
+      "step": 70
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.007782101167315e-07,
+      "logits/chosen": -2.7943294048309326,
+      "logits/rejected": -2.81146240234375,
+      "logps/chosen": -28.41353416442871,
+      "logps/rejected": -115.3572769165039,
+      "loss": 0.0531,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -0.8534424901008606,
+      "rewards/margins": 9.425840377807617,
+      "rewards/rejected": -10.27928352355957,
+      "step": 80
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.813229571984435e-07,
+      "logits/chosen": -2.6642768383026123,
+      "logits/rejected": -2.695777416229248,
+      "logps/chosen": -30.20281410217285,
+      "logps/rejected": -115.2649917602539,
+      "loss": 0.0493,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -0.9560843706130981,
+      "rewards/margins": 9.298072814941406,
+      "rewards/rejected": -10.254158020019531,
+      "step": 90
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.618677042801556e-07,
+      "logits/chosen": -2.61277437210083,
+      "logits/rejected": -2.7204833030700684,
+      "logps/chosen": -33.576595306396484,
+      "logps/rejected": -150.16848754882812,
+      "loss": 0.0391,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -1.3517389297485352,
+      "rewards/margins": 12.079813003540039,
+      "rewards/rejected": -13.431551933288574,
+      "step": 100
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.4241245136186767e-07,
+      "logits/chosen": -2.7867584228515625,
+      "logits/rejected": -2.7667887210845947,
+      "logps/chosen": -24.368350982666016,
+      "logps/rejected": -107.03987884521484,
+      "loss": 0.0492,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -0.7897183895111084,
+      "rewards/margins": 8.651564598083496,
+      "rewards/rejected": -9.441283226013184,
+      "step": 110
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.2295719844357975e-07,
+      "logits/chosen": -2.6104767322540283,
+      "logits/rejected": -2.675987482070923,
+      "logps/chosen": -33.704322814941406,
+      "logps/rejected": -135.02169799804688,
+      "loss": 0.023,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -1.1443722248077393,
+      "rewards/margins": 11.034332275390625,
+      "rewards/rejected": -12.178705215454102,
+      "step": 120
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.0350194552529177e-07,
+      "logits/chosen": -2.568190574645996,
+      "logits/rejected": -2.6318023204803467,
+      "logps/chosen": -30.85686683654785,
+      "logps/rejected": -167.8513946533203,
+      "loss": 0.0389,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -1.3852249383926392,
+      "rewards/margins": 14.069249153137207,
+      "rewards/rejected": -15.454473495483398,
+      "step": 130
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.8404669260700384e-07,
+      "logits/chosen": -2.5317270755767822,
+      "logits/rejected": -2.593646764755249,
+      "logps/chosen": -33.05012512207031,
+      "logps/rejected": -199.79788208007812,
+      "loss": 0.0281,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.1634151935577393,
+      "rewards/margins": 17.322010040283203,
+      "rewards/rejected": -18.485424041748047,
+      "step": 140
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.645914396887159e-07,
+      "logits/chosen": -2.6736645698547363,
+      "logits/rejected": -2.65024995803833,
+      "logps/chosen": -32.11931610107422,
+      "logps/rejected": -172.3567352294922,
+      "loss": 0.011,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.398026704788208,
+      "rewards/margins": 14.626693725585938,
+      "rewards/rejected": -16.02471923828125,
+      "step": 150
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.45136186770428e-07,
+      "logits/chosen": -2.6248397827148438,
+      "logits/rejected": -2.6503357887268066,
+      "logps/chosen": -35.05925369262695,
+      "logps/rejected": -219.28378295898438,
+      "loss": 0.0095,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.4844539165496826,
+      "rewards/margins": 19.174663543701172,
+      "rewards/rejected": -20.659120559692383,
+      "step": 160
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.2568093385214007e-07,
+      "logits/chosen": -2.6490864753723145,
+      "logits/rejected": -2.6252989768981934,
+      "logps/chosen": -31.650588989257812,
+      "logps/rejected": -194.4810333251953,
+      "loss": 0.0158,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.9476087689399719,
+      "rewards/margins": 17.060314178466797,
+      "rewards/rejected": -18.007923126220703,
+      "step": 170
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.0622568093385212e-07,
+      "logits/chosen": -2.7093279361724854,
+      "logits/rejected": -2.638579845428467,
+      "logps/chosen": -32.82453155517578,
+      "logps/rejected": -185.39230346679688,
+      "loss": 0.0104,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.2247194051742554,
+      "rewards/margins": 15.979866027832031,
+      "rewards/rejected": -17.204586029052734,
+      "step": 180
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.867704280155642e-07,
+      "logits/chosen": -2.6887717247009277,
+      "logits/rejected": -2.6667675971984863,
+      "logps/chosen": -34.072509765625,
+      "logps/rejected": -194.00869750976562,
+      "loss": 0.0099,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.21720290184021,
+      "rewards/margins": 16.749324798583984,
+      "rewards/rejected": -17.96652603149414,
+      "step": 190
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.6731517509727624e-07,
+      "logits/chosen": -2.6063685417175293,
+      "logits/rejected": -2.5614001750946045,
+      "logps/chosen": -41.58473587036133,
+      "logps/rejected": -219.73104858398438,
+      "loss": 0.0121,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/chosen": -1.829288125038147,
+      "rewards/margins": 18.672809600830078,
+      "rewards/rejected": -20.502098083496094,
+      "step": 200
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.4785992217898832e-07,
+      "logits/chosen": -2.7379167079925537,
+      "logits/rejected": -2.674070119857788,
+      "logps/chosen": -35.14494323730469,
+      "logps/rejected": -182.973388671875,
+      "loss": 0.0093,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.3816758394241333,
+      "rewards/margins": 15.531547546386719,
+      "rewards/rejected": -16.913225173950195,
+      "step": 210
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.2840466926070036e-07,
+      "logits/chosen": -2.7067456245422363,
+      "logits/rejected": -2.632633686065674,
+      "logps/chosen": -34.483577728271484,
+      "logps/rejected": -222.17990112304688,
+      "loss": 0.0054,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.9836966395378113,
+      "rewards/margins": 19.769222259521484,
+      "rewards/rejected": -20.752918243408203,
+      "step": 220
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.0894941634241245e-07,
+      "logits/chosen": -2.608846664428711,
+      "logits/rejected": -2.604660749435425,
+      "logps/chosen": -32.35722732543945,
+      "logps/rejected": -246.7973175048828,
+      "loss": 0.0076,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.2495921850204468,
+      "rewards/margins": 22.08835220336914,
+      "rewards/rejected": -23.33794403076172,
+      "step": 230
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.949416342412451e-08,
+      "logits/chosen": -2.607797622680664,
+      "logits/rejected": -2.566305637359619,
+      "logps/chosen": -27.041118621826172,
+      "logps/rejected": -209.3827667236328,
+      "loss": 0.0122,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.9218173027038574,
+      "rewards/margins": 18.870208740234375,
+      "rewards/rejected": -19.79202651977539,
+      "step": 240
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.003891050583658e-08,
+      "logits/chosen": -2.518440008163452,
+      "logits/rejected": -2.5331220626831055,
+      "logps/chosen": -31.538745880126953,
+      "logps/rejected": -247.35238647460938,
+      "loss": 0.004,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.2074544429779053,
+      "rewards/margins": 22.2752742767334,
+      "rewards/rejected": -23.48272705078125,
+      "step": 250
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 5.058365758754864e-08,
+      "logits/chosen": -2.5735764503479004,
+      "logits/rejected": -2.52424693107605,
+      "logps/chosen": -28.21148681640625,
+      "logps/rejected": -196.92958068847656,
+      "loss": 0.0018,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.0159205198287964,
+      "rewards/margins": 17.290904998779297,
+      "rewards/rejected": -18.306825637817383,
+      "step": 260
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.11284046692607e-08,
+      "logits/chosen": -2.643744945526123,
+      "logits/rejected": -2.626131772994995,
+      "logps/chosen": -29.778423309326172,
+      "logps/rejected": -234.2376251220703,
+      "loss": 0.0074,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.0768438577651978,
+      "rewards/margins": 20.66169548034668,
+      "rewards/rejected": -21.738544464111328,
+      "step": 270
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.1673151750972762e-08,
+      "logits/chosen": -2.467341899871826,
+      "logits/rejected": -2.524524211883545,
+      "logps/chosen": -29.820302963256836,
+      "logps/rejected": -301.8487243652344,
+      "loss": 0.0019,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.9357167482376099,
+      "rewards/margins": 27.8673152923584,
+      "rewards/rejected": -28.80303382873535,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "step": 286,
+      "total_flos": 0.0,
+      "train_loss": 0.06552632141962543,
+      "train_runtime": 3687.7187,
+      "train_samples_per_second": 2.478,
+      "train_steps_per_second": 0.078
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 286,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8f95b6a65812eada38d9e7e87e8e68d0988e75cacd5214d60fdee95413b15e
+size 5371