Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 0.9880609304240429,
+    "eval_logits/chosen": 9.224187850952148,
+    "eval_logits/rejected": 10.039901733398438,
+    "eval_logps/chosen": -0.3674238324165344,
+    "eval_logps/rejected": -0.3802245259284973,
+    "eval_loss": 1.378309726715088,
+    "eval_rewards/accuracies": 0.5407407283782959,
+    "eval_rewards/chosen": -0.7348476648330688,
+    "eval_rewards/margins": 0.025601468980312347,
+    "eval_rewards/rejected": -0.7604490518569946,
+    "eval_runtime": 153.1014,
+    "eval_samples": 1080,
+    "eval_samples_per_second": 7.054,
+    "eval_steps_per_second": 1.764,
+    "total_flos": 0.0,
+    "train_loss": 1.3904367176691692,
+    "train_runtime": 8038.3927,
+    "train_samples": 9715,
+    "train_samples_per_second": 1.209,
+    "train_steps_per_second": 0.009
+}

checkpoint-12/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-12/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/v-liuzichuan/huggingface/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 32064
+}

checkpoint-12/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.45.2"
+}

checkpoint-12/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f425453c2f765cbd57ac3519a2612346220aa745d17407494db9d3ee640736bf
+size 4972489328

checkpoint-12/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f4b9f84e4ef8bb0272909b381037ee8065ab1d6a8904ff8f8ada295e212ec1
+size 2669692552

checkpoint-12/model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 7642159104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-12/special_tokens_map.json

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

checkpoint-12/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-12/trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.15808974886784685,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 1.846787929534912,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 9.988622665405273,
+      "logits/rejected": 10.698101997375488,
+      "logps/chosen": -0.4084107577800751,
+      "logps/rejected": -0.4250854551792145,
+      "loss": 1.3828,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.8168215155601501,
+      "rewards/margins": 0.03334939479827881,
+      "rewards/rejected": -0.850170910358429,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.7274014353752136,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.208279609680176,
+      "logits/rejected": 11.06594467163086,
+      "logps/chosen": -0.4457661509513855,
+      "logps/rejected": -0.4444480836391449,
+      "loss": 1.4032,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.891532301902771,
+      "rewards/margins": -0.0026361620984971523,
+      "rewards/rejected": -0.8888961672782898,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.569585919380188,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.047319412231445,
+      "logits/rejected": 11.040695190429688,
+      "logps/chosen": -0.44595056772232056,
+      "logps/rejected": -0.4271169602870941,
+      "loss": 1.4316,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.8919011354446411,
+      "rewards/margins": -0.037667226046323776,
+      "rewards/rejected": -0.8542339205741882,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.9579747915267944,
+      "learning_rate": 5e-07,
+      "logits/chosen": 9.83576774597168,
+      "logits/rejected": 10.8547945022583,
+      "logps/chosen": -0.4448290169239044,
+      "logps/rejected": -0.43586766719818115,
+      "loss": 1.4147,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.8896580338478088,
+      "rewards/margins": -0.017922835424542427,
+      "rewards/rejected": -0.8717353343963623,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.7575727701187134,
+      "learning_rate": 6.249999999999999e-07,
+      "logits/chosen": 10.199325561523438,
+      "logits/rejected": 10.956421852111816,
+      "logps/chosen": -0.40898576378822327,
+      "logps/rejected": -0.4012777507305145,
+      "loss": 1.4103,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.8179715275764465,
+      "rewards/margins": -0.015416024252772331,
+      "rewards/rejected": -0.802555501461029,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 1.1651052236557007,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": 10.649311065673828,
+      "logits/rejected": 11.438021659851074,
+      "logps/chosen": -0.4362146258354187,
+      "logps/rejected": -0.43107232451438904,
+      "loss": 1.4097,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.8724292516708374,
+      "rewards/margins": -0.01028449460864067,
+      "rewards/rejected": -0.8621446490287781,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.7423586249351501,
+      "learning_rate": 8.75e-07,
+      "logits/chosen": 10.016755104064941,
+      "logits/rejected": 10.720447540283203,
+      "logps/chosen": -0.40585798025131226,
+      "logps/rejected": -0.41537052392959595,
+      "loss": 1.3836,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8117159605026245,
+      "rewards/margins": 0.0190250426530838,
+      "rewards/rejected": -0.8307410478591919,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.6278178095817566,
+      "learning_rate": 1e-06,
+      "logits/chosen": 10.216046333312988,
+      "logits/rejected": 11.114391326904297,
+      "logps/chosen": -0.4205312728881836,
+      "logps/rejected": -0.3968205451965332,
+      "loss": 1.4332,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8410625457763672,
+      "rewards/margins": -0.04742136597633362,
+      "rewards/rejected": -0.7936410903930664,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.7120531797409058,
+      "learning_rate": 9.994504457428556e-07,
+      "logits/chosen": 10.18065071105957,
+      "logits/rejected": 11.15275764465332,
+      "logps/chosen": -0.4227794110774994,
+      "logps/rejected": -0.4355461895465851,
+      "loss": 1.3879,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8455588221549988,
+      "rewards/margins": 0.02553354948759079,
+      "rewards/rejected": -0.8710923790931702,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 1.1985653638839722,
+      "learning_rate": 9.97802991010949e-07,
+      "logits/chosen": 10.042179107666016,
+      "logits/rejected": 10.866905212402344,
+      "logps/chosen": -0.38143518567085266,
+      "logps/rejected": -0.383830189704895,
+      "loss": 1.3934,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.7628703713417053,
+      "rewards/margins": 0.004790017381310463,
+      "rewards/rejected": -0.76766037940979,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.9829190969467163,
+      "learning_rate": 9.950612572673255e-07,
+      "logits/chosen": 9.96993637084961,
+      "logits/rejected": 11.156689643859863,
+      "logps/chosen": -0.4371436536312103,
+      "logps/rejected": -0.4104335606098175,
+      "loss": 1.4388,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.8742873072624207,
+      "rewards/margins": -0.05342020094394684,
+      "rewards/rejected": -0.820867121219635,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.771833062171936,
+      "learning_rate": 9.912312714377879e-07,
+      "logits/chosen": 9.883522033691406,
+      "logits/rejected": 10.568523406982422,
+      "logps/chosen": -0.4180852770805359,
+      "logps/rejected": -0.44434836506843567,
+      "loss": 1.3634,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.8361705541610718,
+      "rewards/margins": 0.05252611264586449,
+      "rewards/rejected": -0.8886967301368713,
+      "step": 12
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 12,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-24/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-24/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/v-liuzichuan/huggingface/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 32064
+}

checkpoint-24/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.45.2"
+}

checkpoint-24/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb92fe1ccb6b59e16b971abdd45222d84c9cdee5ae0f88b6d67d312e6c8e4b3
+size 4972489328

checkpoint-24/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74385700964bfe9f50336e9dd6f2e5a88f25bc298429b2cc4ea1c7eb9ba7a2d
+size 2669692552

checkpoint-24/model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 7642159104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-24/special_tokens_map.json

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

checkpoint-24/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-24/trainer_state.json

@@ -0,0 +1,393 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3161794977356937,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 1.846787929534912,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 9.988622665405273,
+      "logits/rejected": 10.698101997375488,
+      "logps/chosen": -0.4084107577800751,
+      "logps/rejected": -0.4250854551792145,
+      "loss": 1.3828,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.8168215155601501,
+      "rewards/margins": 0.03334939479827881,
+      "rewards/rejected": -0.850170910358429,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.7274014353752136,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.208279609680176,
+      "logits/rejected": 11.06594467163086,
+      "logps/chosen": -0.4457661509513855,
+      "logps/rejected": -0.4444480836391449,
+      "loss": 1.4032,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.891532301902771,
+      "rewards/margins": -0.0026361620984971523,
+      "rewards/rejected": -0.8888961672782898,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.569585919380188,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.047319412231445,
+      "logits/rejected": 11.040695190429688,
+      "logps/chosen": -0.44595056772232056,
+      "logps/rejected": -0.4271169602870941,
+      "loss": 1.4316,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.8919011354446411,
+      "rewards/margins": -0.037667226046323776,
+      "rewards/rejected": -0.8542339205741882,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.9579747915267944,
+      "learning_rate": 5e-07,
+      "logits/chosen": 9.83576774597168,
+      "logits/rejected": 10.8547945022583,
+      "logps/chosen": -0.4448290169239044,
+      "logps/rejected": -0.43586766719818115,
+      "loss": 1.4147,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.8896580338478088,
+      "rewards/margins": -0.017922835424542427,
+      "rewards/rejected": -0.8717353343963623,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.7575727701187134,
+      "learning_rate": 6.249999999999999e-07,
+      "logits/chosen": 10.199325561523438,
+      "logits/rejected": 10.956421852111816,
+      "logps/chosen": -0.40898576378822327,
+      "logps/rejected": -0.4012777507305145,
+      "loss": 1.4103,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.8179715275764465,
+      "rewards/margins": -0.015416024252772331,
+      "rewards/rejected": -0.802555501461029,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 1.1651052236557007,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": 10.649311065673828,
+      "logits/rejected": 11.438021659851074,
+      "logps/chosen": -0.4362146258354187,
+      "logps/rejected": -0.43107232451438904,
+      "loss": 1.4097,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.8724292516708374,
+      "rewards/margins": -0.01028449460864067,
+      "rewards/rejected": -0.8621446490287781,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.7423586249351501,
+      "learning_rate": 8.75e-07,
+      "logits/chosen": 10.016755104064941,
+      "logits/rejected": 10.720447540283203,
+      "logps/chosen": -0.40585798025131226,
+      "logps/rejected": -0.41537052392959595,
+      "loss": 1.3836,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8117159605026245,
+      "rewards/margins": 0.0190250426530838,
+      "rewards/rejected": -0.8307410478591919,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.6278178095817566,
+      "learning_rate": 1e-06,
+      "logits/chosen": 10.216046333312988,
+      "logits/rejected": 11.114391326904297,
+      "logps/chosen": -0.4205312728881836,
+      "logps/rejected": -0.3968205451965332,
+      "loss": 1.4332,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8410625457763672,
+      "rewards/margins": -0.04742136597633362,
+      "rewards/rejected": -0.7936410903930664,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.7120531797409058,
+      "learning_rate": 9.994504457428556e-07,
+      "logits/chosen": 10.18065071105957,
+      "logits/rejected": 11.15275764465332,
+      "logps/chosen": -0.4227794110774994,
+      "logps/rejected": -0.4355461895465851,
+      "loss": 1.3879,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8455588221549988,
+      "rewards/margins": 0.02553354948759079,
+      "rewards/rejected": -0.8710923790931702,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 1.1985653638839722,
+      "learning_rate": 9.97802991010949e-07,
+      "logits/chosen": 10.042179107666016,
+      "logits/rejected": 10.866905212402344,
+      "logps/chosen": -0.38143518567085266,
+      "logps/rejected": -0.383830189704895,
+      "loss": 1.3934,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.7628703713417053,
+      "rewards/margins": 0.004790017381310463,
+      "rewards/rejected": -0.76766037940979,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.9829190969467163,
+      "learning_rate": 9.950612572673255e-07,
+      "logits/chosen": 9.96993637084961,
+      "logits/rejected": 11.156689643859863,
+      "logps/chosen": -0.4371436536312103,
+      "logps/rejected": -0.4104335606098175,
+      "loss": 1.4388,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.8742873072624207,
+      "rewards/margins": -0.05342020094394684,
+      "rewards/rejected": -0.820867121219635,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.771833062171936,
+      "learning_rate": 9.912312714377879e-07,
+      "logits/chosen": 9.883522033691406,
+      "logits/rejected": 10.568523406982422,
+      "logps/chosen": -0.4180852770805359,
+      "logps/rejected": -0.44434836506843567,
+      "loss": 1.3634,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.8361705541610718,
+      "rewards/margins": 0.05252611264586449,
+      "rewards/rejected": -0.8886967301368713,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5779662728309631,
+      "learning_rate": 9.863214526624063e-07,
+      "logits/chosen": 9.908037185668945,
+      "logits/rejected": 10.980252265930176,
+      "logps/chosen": -0.4335843622684479,
+      "logps/rejected": -0.4193909764289856,
+      "loss": 1.4188,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.8671687245368958,
+      "rewards/margins": -0.028386807069182396,
+      "rewards/rejected": -0.8387819528579712,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.755972146987915,
+      "learning_rate": 9.8034259378842e-07,
+      "logits/chosen": 10.47681999206543,
+      "logits/rejected": 11.599574089050293,
+      "logps/chosen": -0.40058645606040955,
+      "logps/rejected": -0.41547441482543945,
+      "loss": 1.3776,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8011729121208191,
+      "rewards/margins": 0.02977588400244713,
+      "rewards/rejected": -0.8309488296508789,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 1.2080482244491577,
+      "learning_rate": 9.73307837645217e-07,
+      "logits/chosen": 9.785813331604004,
+      "logits/rejected": 10.71661376953125,
+      "logps/chosen": -0.4059077799320221,
+      "logps/rejected": -0.3964956998825073,
+      "loss": 1.4115,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.8118155598640442,
+      "rewards/margins": -0.018824119120836258,
+      "rewards/rejected": -0.7929913997650146,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 1.0530983209609985,
+      "learning_rate": 9.652326481535433e-07,
+      "logits/chosen": 10.606256484985352,
+      "logits/rejected": 11.221076965332031,
+      "logps/chosen": -0.43960413336753845,
+      "logps/rejected": -0.43556928634643555,
+      "loss": 1.4054,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.8792082667350769,
+      "rewards/margins": -0.008069731295108795,
+      "rewards/rejected": -0.8711385726928711,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.8931649327278137,
+      "learning_rate": 9.561347763324483e-07,
+      "logits/chosen": 10.093276977539062,
+      "logits/rejected": 10.721864700317383,
+      "logps/chosen": -0.46352270245552063,
+      "logps/rejected": -0.47664591670036316,
+      "loss": 1.398,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.9270454049110413,
+      "rewards/margins": 0.026246393099427223,
+      "rewards/rejected": -0.9532918334007263,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.5987163782119751,
+      "learning_rate": 9.460342212786932e-07,
+      "logits/chosen": 10.340713500976562,
+      "logits/rejected": 11.121424674987793,
+      "logps/chosen": -0.4333910644054413,
+      "logps/rejected": -0.4210299551486969,
+      "loss": 1.4189,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.8667821288108826,
+      "rewards/margins": -0.024722211062908173,
+      "rewards/rejected": -0.8420599102973938,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.7226627469062805,
+      "learning_rate": 9.349531862043951e-07,
+      "logits/chosen": 10.257181167602539,
+      "logits/rejected": 10.92556095123291,
+      "logps/chosen": -0.4293927550315857,
+      "logps/rejected": -0.4481368064880371,
+      "loss": 1.3801,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.8587855100631714,
+      "rewards/margins": 0.03748808801174164,
+      "rewards/rejected": -0.8962736129760742,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.7743024826049805,
+      "learning_rate": 9.229160296295487e-07,
+      "logits/chosen": 10.641219139099121,
+      "logits/rejected": 11.451465606689453,
+      "logps/chosen": -0.40963226556777954,
+      "logps/rejected": -0.42823317646980286,
+      "loss": 1.3718,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.8192645311355591,
+      "rewards/margins": 0.03720181807875633,
+      "rewards/rejected": -0.8564663529396057,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 1.043879747390747,
+      "learning_rate": 9.099492118367122e-07,
+      "logits/chosen": 9.668081283569336,
+      "logits/rejected": 10.759317398071289,
+      "logps/chosen": -0.41088593006134033,
+      "logps/rejected": -0.44134727120399475,
+      "loss": 1.3653,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.8217718601226807,
+      "rewards/margins": 0.06092273071408272,
+      "rewards/rejected": -0.8826945424079895,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 1.8495320081710815,
+      "learning_rate": 8.960812367055646e-07,
+      "logits/chosen": 10.094249725341797,
+      "logits/rejected": 10.969901084899902,
+      "logps/chosen": -0.43626973032951355,
+      "logps/rejected": -0.44013574719429016,
+      "loss": 1.4045,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.8725394606590271,
+      "rewards/margins": 0.00773210171610117,
+      "rewards/rejected": -0.8802714943885803,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4824877977371216,
+      "learning_rate": 8.813425890551909e-07,
+      "logits/chosen": 10.012961387634277,
+      "logits/rejected": 11.028541564941406,
+      "logps/chosen": -0.4449196755886078,
+      "logps/rejected": -0.43216580152511597,
+      "loss": 1.424,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.8898393511772156,
+      "rewards/margins": -0.025507748126983643,
+      "rewards/rejected": -0.8643316030502319,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 1.0434041023254395,
+      "learning_rate": 8.657656676318345e-07,
+      "logits/chosen": 10.089515686035156,
+      "logits/rejected": 10.921834945678711,
+      "logps/chosen": -0.4228805899620056,
+      "logps/rejected": -0.44924959540367126,
+      "loss": 1.3654,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.8457611799240112,
+      "rewards/margins": 0.05273808538913727,
+      "rewards/rejected": -0.8984991908073425,
+      "step": 24
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 12,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-36/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-36/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/v-liuzichuan/huggingface/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 32064
+}

checkpoint-36/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.45.2"
+}

checkpoint-36/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a57c2f0c8df0f33edc786b9b65abbdeb89def2207ed8a540d07209da14c0b9f
+size 4972489328

checkpoint-36/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3689caa7329af2f14bcc3fb47a94facbf7f973d96e03504c425189da801c0442
+size 2669692552

checkpoint-36/model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 7642159104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-36/special_tokens_map.json

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

checkpoint-36/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-36/trainer_state.json

@@ -0,0 +1,573 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.47426924660354053,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 1.846787929534912,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 9.988622665405273,
+      "logits/rejected": 10.698101997375488,
+      "logps/chosen": -0.4084107577800751,
+      "logps/rejected": -0.4250854551792145,
+      "loss": 1.3828,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.8168215155601501,
+      "rewards/margins": 0.03334939479827881,
+      "rewards/rejected": -0.850170910358429,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.7274014353752136,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.208279609680176,
+      "logits/rejected": 11.06594467163086,
+      "logps/chosen": -0.4457661509513855,
+      "logps/rejected": -0.4444480836391449,
+      "loss": 1.4032,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.891532301902771,
+      "rewards/margins": -0.0026361620984971523,
+      "rewards/rejected": -0.8888961672782898,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.569585919380188,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.047319412231445,
+      "logits/rejected": 11.040695190429688,
+      "logps/chosen": -0.44595056772232056,
+      "logps/rejected": -0.4271169602870941,
+      "loss": 1.4316,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.8919011354446411,
+      "rewards/margins": -0.037667226046323776,
+      "rewards/rejected": -0.8542339205741882,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.9579747915267944,
+      "learning_rate": 5e-07,
+      "logits/chosen": 9.83576774597168,
+      "logits/rejected": 10.8547945022583,
+      "logps/chosen": -0.4448290169239044,
+      "logps/rejected": -0.43586766719818115,
+      "loss": 1.4147,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.8896580338478088,
+      "rewards/margins": -0.017922835424542427,
+      "rewards/rejected": -0.8717353343963623,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.7575727701187134,
+      "learning_rate": 6.249999999999999e-07,
+      "logits/chosen": 10.199325561523438,
+      "logits/rejected": 10.956421852111816,
+      "logps/chosen": -0.40898576378822327,
+      "logps/rejected": -0.4012777507305145,
+      "loss": 1.4103,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.8179715275764465,
+      "rewards/margins": -0.015416024252772331,
+      "rewards/rejected": -0.802555501461029,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 1.1651052236557007,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": 10.649311065673828,
+      "logits/rejected": 11.438021659851074,
+      "logps/chosen": -0.4362146258354187,
+      "logps/rejected": -0.43107232451438904,
+      "loss": 1.4097,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.8724292516708374,
+      "rewards/margins": -0.01028449460864067,
+      "rewards/rejected": -0.8621446490287781,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.7423586249351501,
+      "learning_rate": 8.75e-07,
+      "logits/chosen": 10.016755104064941,
+      "logits/rejected": 10.720447540283203,
+      "logps/chosen": -0.40585798025131226,
+      "logps/rejected": -0.41537052392959595,
+      "loss": 1.3836,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8117159605026245,
+      "rewards/margins": 0.0190250426530838,
+      "rewards/rejected": -0.8307410478591919,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.6278178095817566,
+      "learning_rate": 1e-06,
+      "logits/chosen": 10.216046333312988,
+      "logits/rejected": 11.114391326904297,
+      "logps/chosen": -0.4205312728881836,
+      "logps/rejected": -0.3968205451965332,
+      "loss": 1.4332,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8410625457763672,
+      "rewards/margins": -0.04742136597633362,
+      "rewards/rejected": -0.7936410903930664,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.7120531797409058,
+      "learning_rate": 9.994504457428556e-07,
+      "logits/chosen": 10.18065071105957,
+      "logits/rejected": 11.15275764465332,
+      "logps/chosen": -0.4227794110774994,
+      "logps/rejected": -0.4355461895465851,
+      "loss": 1.3879,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8455588221549988,
+      "rewards/margins": 0.02553354948759079,
+      "rewards/rejected": -0.8710923790931702,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 1.1985653638839722,
+      "learning_rate": 9.97802991010949e-07,
+      "logits/chosen": 10.042179107666016,
+      "logits/rejected": 10.866905212402344,
+      "logps/chosen": -0.38143518567085266,
+      "logps/rejected": -0.383830189704895,
+      "loss": 1.3934,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.7628703713417053,
+      "rewards/margins": 0.004790017381310463,
+      "rewards/rejected": -0.76766037940979,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.9829190969467163,
+      "learning_rate": 9.950612572673255e-07,
+      "logits/chosen": 9.96993637084961,
+      "logits/rejected": 11.156689643859863,
+      "logps/chosen": -0.4371436536312103,
+      "logps/rejected": -0.4104335606098175,
+      "loss": 1.4388,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.8742873072624207,
+      "rewards/margins": -0.05342020094394684,
+      "rewards/rejected": -0.820867121219635,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.771833062171936,
+      "learning_rate": 9.912312714377879e-07,
+      "logits/chosen": 9.883522033691406,
+      "logits/rejected": 10.568523406982422,
+      "logps/chosen": -0.4180852770805359,
+      "logps/rejected": -0.44434836506843567,
+      "loss": 1.3634,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.8361705541610718,
+      "rewards/margins": 0.05252611264586449,
+      "rewards/rejected": -0.8886967301368713,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5779662728309631,
+      "learning_rate": 9.863214526624063e-07,
+      "logits/chosen": 9.908037185668945,
+      "logits/rejected": 10.980252265930176,
+      "logps/chosen": -0.4335843622684479,
+      "logps/rejected": -0.4193909764289856,
+      "loss": 1.4188,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.8671687245368958,
+      "rewards/margins": -0.028386807069182396,
+      "rewards/rejected": -0.8387819528579712,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.755972146987915,
+      "learning_rate": 9.8034259378842e-07,
+      "logits/chosen": 10.47681999206543,
+      "logits/rejected": 11.599574089050293,
+      "logps/chosen": -0.40058645606040955,
+      "logps/rejected": -0.41547441482543945,
+      "loss": 1.3776,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8011729121208191,
+      "rewards/margins": 0.02977588400244713,
+      "rewards/rejected": -0.8309488296508789,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 1.2080482244491577,
+      "learning_rate": 9.73307837645217e-07,
+      "logits/chosen": 9.785813331604004,
+      "logits/rejected": 10.71661376953125,
+      "logps/chosen": -0.4059077799320221,
+      "logps/rejected": -0.3964956998825073,
+      "loss": 1.4115,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.8118155598640442,
+      "rewards/margins": -0.018824119120836258,
+      "rewards/rejected": -0.7929913997650146,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 1.0530983209609985,
+      "learning_rate": 9.652326481535433e-07,
+      "logits/chosen": 10.606256484985352,
+      "logits/rejected": 11.221076965332031,
+      "logps/chosen": -0.43960413336753845,
+      "logps/rejected": -0.43556928634643555,
+      "loss": 1.4054,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.8792082667350769,
+      "rewards/margins": -0.008069731295108795,
+      "rewards/rejected": -0.8711385726928711,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.8931649327278137,
+      "learning_rate": 9.561347763324483e-07,
+      "logits/chosen": 10.093276977539062,
+      "logits/rejected": 10.721864700317383,
+      "logps/chosen": -0.46352270245552063,
+      "logps/rejected": -0.47664591670036316,
+      "loss": 1.398,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.9270454049110413,
+      "rewards/margins": 0.026246393099427223,
+      "rewards/rejected": -0.9532918334007263,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.5987163782119751,
+      "learning_rate": 9.460342212786932e-07,
+      "logits/chosen": 10.340713500976562,
+      "logits/rejected": 11.121424674987793,
+      "logps/chosen": -0.4333910644054413,
+      "logps/rejected": -0.4210299551486969,
+      "loss": 1.4189,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.8667821288108826,
+      "rewards/margins": -0.024722211062908173,
+      "rewards/rejected": -0.8420599102973938,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.7226627469062805,
+      "learning_rate": 9.349531862043951e-07,
+      "logits/chosen": 10.257181167602539,
+      "logits/rejected": 10.92556095123291,
+      "logps/chosen": -0.4293927550315857,
+      "logps/rejected": -0.4481368064880371,
+      "loss": 1.3801,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.8587855100631714,
+      "rewards/margins": 0.03748808801174164,
+      "rewards/rejected": -0.8962736129760742,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.7743024826049805,
+      "learning_rate": 9.229160296295487e-07,
+      "logits/chosen": 10.641219139099121,
+      "logits/rejected": 11.451465606689453,
+      "logps/chosen": -0.40963226556777954,
+      "logps/rejected": -0.42823317646980286,
+      "loss": 1.3718,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.8192645311355591,
+      "rewards/margins": 0.03720181807875633,
+      "rewards/rejected": -0.8564663529396057,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 1.043879747390747,
+      "learning_rate": 9.099492118367122e-07,
+      "logits/chosen": 9.668081283569336,
+      "logits/rejected": 10.759317398071289,
+      "logps/chosen": -0.41088593006134033,
+      "logps/rejected": -0.44134727120399475,
+      "loss": 1.3653,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.8217718601226807,
+      "rewards/margins": 0.06092273071408272,
+      "rewards/rejected": -0.8826945424079895,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 1.8495320081710815,
+      "learning_rate": 8.960812367055646e-07,
+      "logits/chosen": 10.094249725341797,
+      "logits/rejected": 10.969901084899902,
+      "logps/chosen": -0.43626973032951355,
+      "logps/rejected": -0.44013574719429016,
+      "loss": 1.4045,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.8725394606590271,
+      "rewards/margins": 0.00773210171610117,
+      "rewards/rejected": -0.8802714943885803,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4824877977371216,
+      "learning_rate": 8.813425890551909e-07,
+      "logits/chosen": 10.012961387634277,
+      "logits/rejected": 11.028541564941406,
+      "logps/chosen": -0.4449196755886078,
+      "logps/rejected": -0.43216580152511597,
+      "loss": 1.424,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.8898393511772156,
+      "rewards/margins": -0.025507748126983643,
+      "rewards/rejected": -0.8643316030502319,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 1.0434041023254395,
+      "learning_rate": 8.657656676318345e-07,
+      "logits/chosen": 10.089515686035156,
+      "logits/rejected": 10.921834945678711,
+      "logps/chosen": -0.4228805899620056,
+      "logps/rejected": -0.44924959540367126,
+      "loss": 1.3654,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.8457611799240112,
+      "rewards/margins": 0.05273808538913727,
+      "rewards/rejected": -0.8984991908073425,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.8496569991111755,
+      "learning_rate": 8.493847138894208e-07,
+      "logits/chosen": 10.220051765441895,
+      "logits/rejected": 10.924245834350586,
+      "logps/chosen": -0.4278189241886139,
+      "logps/rejected": -0.45087143778800964,
+      "loss": 1.3771,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.8556378483772278,
+      "rewards/margins": 0.046104975044727325,
+      "rewards/rejected": -0.9017428755760193,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 1.1707934141159058,
+      "learning_rate": 8.322357367194108e-07,
+      "logits/chosen": 10.33618450164795,
+      "logits/rejected": 11.42149829864502,
+      "logps/chosen": -0.4403349757194519,
+      "logps/rejected": -0.4506159722805023,
+      "loss": 1.3831,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8806699514389038,
+      "rewards/margins": 0.020561927929520607,
+      "rewards/rejected": -0.9012319445610046,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.9727609753608704,
+      "learning_rate": 8.143564332954425e-07,
+      "logits/chosen": 9.973875999450684,
+      "logits/rejected": 11.174227714538574,
+      "logps/chosen": -0.48110640048980713,
+      "logps/rejected": -0.46264228224754333,
+      "loss": 1.4375,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.9622128009796143,
+      "rewards/margins": -0.03692828118801117,
+      "rewards/rejected": -0.9252845644950867,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.4669955372810364,
+      "learning_rate": 7.957861062067612e-07,
+      "logits/chosen": 9.494720458984375,
+      "logits/rejected": 10.64975357055664,
+      "logps/chosen": -0.4049557149410248,
+      "logps/rejected": -0.41160064935684204,
+      "loss": 1.3949,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.8099114298820496,
+      "rewards/margins": 0.01328977383673191,
+      "rewards/rejected": -0.8232012987136841,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.6599685549736023,
+      "learning_rate": 7.765655770625996e-07,
+      "logits/chosen": 9.987813949584961,
+      "logits/rejected": 11.066561698913574,
+      "logps/chosen": -0.4204758107662201,
+      "logps/rejected": -0.4215814769268036,
+      "loss": 1.4024,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.8409516215324402,
+      "rewards/margins": 0.002211294136941433,
+      "rewards/rejected": -0.8431629538536072,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.4469655156135559,
+      "learning_rate": 7.567370967574209e-07,
+      "logits/chosen": 10.159306526184082,
+      "logits/rejected": 11.529789924621582,
+      "logps/chosen": -0.44582635164260864,
+      "logps/rejected": -0.4426492154598236,
+      "loss": 1.4042,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8916527032852173,
+      "rewards/margins": -0.006354227662086487,
+      "rewards/rejected": -0.8852984309196472,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.46628981828689575,
+      "learning_rate": 7.363442525942826e-07,
+      "logits/chosen": 9.731393814086914,
+      "logits/rejected": 10.743117332458496,
+      "logps/chosen": -0.4495592713356018,
+      "logps/rejected": -0.41725438833236694,
+      "loss": 1.4528,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.8991185426712036,
+      "rewards/margins": -0.06460972875356674,
+      "rewards/rejected": -0.8345087766647339,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.6232314109802246,
+      "learning_rate": 7.154318724704851e-07,
+      "logits/chosen": 9.956490516662598,
+      "logits/rejected": 11.324994087219238,
+      "logps/chosen": -0.42140334844589233,
+      "logps/rejected": -0.3955790102481842,
+      "loss": 1.4406,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8428066968917847,
+      "rewards/margins": -0.05164865404367447,
+      "rewards/rejected": -0.7911580204963684,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 1.1314888000488281,
+      "learning_rate": 6.940459263361248e-07,
+      "logits/chosen": 9.897272109985352,
+      "logits/rejected": 10.727909088134766,
+      "logps/chosen": -0.38281309604644775,
+      "logps/rejected": -0.4067748188972473,
+      "loss": 1.3728,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.7656261920928955,
+      "rewards/margins": 0.04792340472340584,
+      "rewards/rejected": -0.8135496377944946,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.9336860179901123,
+      "learning_rate": 6.722334251421664e-07,
+      "logits/chosen": 10.045162200927734,
+      "logits/rejected": 10.88832950592041,
+      "logps/chosen": -0.424130380153656,
+      "logps/rejected": -0.44961968064308167,
+      "loss": 1.3642,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.848260760307312,
+      "rewards/margins": 0.050978533923625946,
+      "rewards/rejected": -0.8992393612861633,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.6091923117637634,
+      "learning_rate": 6.500423175001703e-07,
+      "logits/chosen": 10.366498947143555,
+      "logits/rejected": 11.302865028381348,
+      "logps/chosen": -0.38435739278793335,
+      "logps/rejected": -0.40687644481658936,
+      "loss": 1.3686,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.7687147855758667,
+      "rewards/margins": 0.04503808170557022,
+      "rewards/rejected": -0.8137528896331787,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 1.436123251914978,
+      "learning_rate": 6.275213842808382e-07,
+      "logits/chosen": 9.993330955505371,
+      "logits/rejected": 10.635811805725098,
+      "logps/chosen": -0.41794323921203613,
+      "logps/rejected": -0.416820764541626,
+      "loss": 1.4028,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.8358864784240723,
+      "rewards/margins": -0.0022448617964982986,
+      "rewards/rejected": -0.833641529083252,
+      "step": 36
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 12,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-48/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-48/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/v-liuzichuan/huggingface/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 32064
+}

checkpoint-48/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.45.2"
+}

checkpoint-48/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002a14a82d7cedaf8e046111f595c7cb1d9e446e63f548bc7ee2a82a8e003652
+size 4972489328

checkpoint-48/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23de17a6b8ee0d1b3f598bbc5d87cde49db85051eeb3f33b3b0589f852253c7d
+size 2669692552

checkpoint-48/model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 7642159104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-48/special_tokens_map.json

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

checkpoint-48/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-48/trainer_state.json

@@ -0,0 +1,753 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6323589954713874,
+  "eval_steps": 500,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 1.846787929534912,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 9.988622665405273,
+      "logits/rejected": 10.698101997375488,
+      "logps/chosen": -0.4084107577800751,
+      "logps/rejected": -0.4250854551792145,
+      "loss": 1.3828,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.8168215155601501,
+      "rewards/margins": 0.03334939479827881,
+      "rewards/rejected": -0.850170910358429,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.7274014353752136,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.208279609680176,
+      "logits/rejected": 11.06594467163086,
+      "logps/chosen": -0.4457661509513855,
+      "logps/rejected": -0.4444480836391449,
+      "loss": 1.4032,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.891532301902771,
+      "rewards/margins": -0.0026361620984971523,
+      "rewards/rejected": -0.8888961672782898,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.569585919380188,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.047319412231445,
+      "logits/rejected": 11.040695190429688,
+      "logps/chosen": -0.44595056772232056,
+      "logps/rejected": -0.4271169602870941,
+      "loss": 1.4316,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.8919011354446411,
+      "rewards/margins": -0.037667226046323776,
+      "rewards/rejected": -0.8542339205741882,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.9579747915267944,
+      "learning_rate": 5e-07,
+      "logits/chosen": 9.83576774597168,
+      "logits/rejected": 10.8547945022583,
+      "logps/chosen": -0.4448290169239044,
+      "logps/rejected": -0.43586766719818115,
+      "loss": 1.4147,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.8896580338478088,
+      "rewards/margins": -0.017922835424542427,
+      "rewards/rejected": -0.8717353343963623,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.7575727701187134,
+      "learning_rate": 6.249999999999999e-07,
+      "logits/chosen": 10.199325561523438,
+      "logits/rejected": 10.956421852111816,
+      "logps/chosen": -0.40898576378822327,
+      "logps/rejected": -0.4012777507305145,
+      "loss": 1.4103,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.8179715275764465,
+      "rewards/margins": -0.015416024252772331,
+      "rewards/rejected": -0.802555501461029,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 1.1651052236557007,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": 10.649311065673828,
+      "logits/rejected": 11.438021659851074,
+      "logps/chosen": -0.4362146258354187,
+      "logps/rejected": -0.43107232451438904,
+      "loss": 1.4097,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.8724292516708374,
+      "rewards/margins": -0.01028449460864067,
+      "rewards/rejected": -0.8621446490287781,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.7423586249351501,
+      "learning_rate": 8.75e-07,
+      "logits/chosen": 10.016755104064941,
+      "logits/rejected": 10.720447540283203,
+      "logps/chosen": -0.40585798025131226,
+      "logps/rejected": -0.41537052392959595,
+      "loss": 1.3836,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8117159605026245,
+      "rewards/margins": 0.0190250426530838,
+      "rewards/rejected": -0.8307410478591919,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.6278178095817566,
+      "learning_rate": 1e-06,
+      "logits/chosen": 10.216046333312988,
+      "logits/rejected": 11.114391326904297,
+      "logps/chosen": -0.4205312728881836,
+      "logps/rejected": -0.3968205451965332,
+      "loss": 1.4332,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8410625457763672,
+      "rewards/margins": -0.04742136597633362,
+      "rewards/rejected": -0.7936410903930664,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.7120531797409058,
+      "learning_rate": 9.994504457428556e-07,
+      "logits/chosen": 10.18065071105957,
+      "logits/rejected": 11.15275764465332,
+      "logps/chosen": -0.4227794110774994,
+      "logps/rejected": -0.4355461895465851,
+      "loss": 1.3879,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8455588221549988,
+      "rewards/margins": 0.02553354948759079,
+      "rewards/rejected": -0.8710923790931702,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 1.1985653638839722,
+      "learning_rate": 9.97802991010949e-07,
+      "logits/chosen": 10.042179107666016,
+      "logits/rejected": 10.866905212402344,
+      "logps/chosen": -0.38143518567085266,
+      "logps/rejected": -0.383830189704895,
+      "loss": 1.3934,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.7628703713417053,
+      "rewards/margins": 0.004790017381310463,
+      "rewards/rejected": -0.76766037940979,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.9829190969467163,
+      "learning_rate": 9.950612572673255e-07,
+      "logits/chosen": 9.96993637084961,
+      "logits/rejected": 11.156689643859863,
+      "logps/chosen": -0.4371436536312103,
+      "logps/rejected": -0.4104335606098175,
+      "loss": 1.4388,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.8742873072624207,
+      "rewards/margins": -0.05342020094394684,
+      "rewards/rejected": -0.820867121219635,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.771833062171936,
+      "learning_rate": 9.912312714377879e-07,
+      "logits/chosen": 9.883522033691406,
+      "logits/rejected": 10.568523406982422,
+      "logps/chosen": -0.4180852770805359,
+      "logps/rejected": -0.44434836506843567,
+      "loss": 1.3634,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.8361705541610718,
+      "rewards/margins": 0.05252611264586449,
+      "rewards/rejected": -0.8886967301368713,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5779662728309631,
+      "learning_rate": 9.863214526624063e-07,
+      "logits/chosen": 9.908037185668945,
+      "logits/rejected": 10.980252265930176,
+      "logps/chosen": -0.4335843622684479,
+      "logps/rejected": -0.4193909764289856,
+      "loss": 1.4188,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.8671687245368958,
+      "rewards/margins": -0.028386807069182396,
+      "rewards/rejected": -0.8387819528579712,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.755972146987915,
+      "learning_rate": 9.8034259378842e-07,
+      "logits/chosen": 10.47681999206543,
+      "logits/rejected": 11.599574089050293,
+      "logps/chosen": -0.40058645606040955,
+      "logps/rejected": -0.41547441482543945,
+      "loss": 1.3776,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8011729121208191,
+      "rewards/margins": 0.02977588400244713,
+      "rewards/rejected": -0.8309488296508789,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 1.2080482244491577,
+      "learning_rate": 9.73307837645217e-07,
+      "logits/chosen": 9.785813331604004,
+      "logits/rejected": 10.71661376953125,
+      "logps/chosen": -0.4059077799320221,
+      "logps/rejected": -0.3964956998825073,
+      "loss": 1.4115,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.8118155598640442,
+      "rewards/margins": -0.018824119120836258,
+      "rewards/rejected": -0.7929913997650146,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 1.0530983209609985,
+      "learning_rate": 9.652326481535433e-07,
+      "logits/chosen": 10.606256484985352,
+      "logits/rejected": 11.221076965332031,
+      "logps/chosen": -0.43960413336753845,
+      "logps/rejected": -0.43556928634643555,
+      "loss": 1.4054,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.8792082667350769,
+      "rewards/margins": -0.008069731295108795,
+      "rewards/rejected": -0.8711385726928711,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.8931649327278137,
+      "learning_rate": 9.561347763324483e-07,
+      "logits/chosen": 10.093276977539062,
+      "logits/rejected": 10.721864700317383,
+      "logps/chosen": -0.46352270245552063,
+      "logps/rejected": -0.47664591670036316,
+      "loss": 1.398,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.9270454049110413,
+      "rewards/margins": 0.026246393099427223,
+      "rewards/rejected": -0.9532918334007263,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.5987163782119751,
+      "learning_rate": 9.460342212786932e-07,
+      "logits/chosen": 10.340713500976562,
+      "logits/rejected": 11.121424674987793,
+      "logps/chosen": -0.4333910644054413,
+      "logps/rejected": -0.4210299551486969,
+      "loss": 1.4189,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.8667821288108826,
+      "rewards/margins": -0.024722211062908173,
+      "rewards/rejected": -0.8420599102973938,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.7226627469062805,
+      "learning_rate": 9.349531862043951e-07,
+      "logits/chosen": 10.257181167602539,
+      "logits/rejected": 10.92556095123291,
+      "logps/chosen": -0.4293927550315857,
+      "logps/rejected": -0.4481368064880371,
+      "loss": 1.3801,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.8587855100631714,
+      "rewards/margins": 0.03748808801174164,
+      "rewards/rejected": -0.8962736129760742,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.7743024826049805,
+      "learning_rate": 9.229160296295487e-07,
+      "logits/chosen": 10.641219139099121,
+      "logits/rejected": 11.451465606689453,
+      "logps/chosen": -0.40963226556777954,
+      "logps/rejected": -0.42823317646980286,
+      "loss": 1.3718,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.8192645311355591,
+      "rewards/margins": 0.03720181807875633,
+      "rewards/rejected": -0.8564663529396057,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 1.043879747390747,
+      "learning_rate": 9.099492118367122e-07,
+      "logits/chosen": 9.668081283569336,
+      "logits/rejected": 10.759317398071289,
+      "logps/chosen": -0.41088593006134033,
+      "logps/rejected": -0.44134727120399475,
+      "loss": 1.3653,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.8217718601226807,
+      "rewards/margins": 0.06092273071408272,
+      "rewards/rejected": -0.8826945424079895,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 1.8495320081710815,
+      "learning_rate": 8.960812367055646e-07,
+      "logits/chosen": 10.094249725341797,
+      "logits/rejected": 10.969901084899902,
+      "logps/chosen": -0.43626973032951355,
+      "logps/rejected": -0.44013574719429016,
+      "loss": 1.4045,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.8725394606590271,
+      "rewards/margins": 0.00773210171610117,
+      "rewards/rejected": -0.8802714943885803,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4824877977371216,
+      "learning_rate": 8.813425890551909e-07,
+      "logits/chosen": 10.012961387634277,
+      "logits/rejected": 11.028541564941406,
+      "logps/chosen": -0.4449196755886078,
+      "logps/rejected": -0.43216580152511597,
+      "loss": 1.424,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.8898393511772156,
+      "rewards/margins": -0.025507748126983643,
+      "rewards/rejected": -0.8643316030502319,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 1.0434041023254395,
+      "learning_rate": 8.657656676318345e-07,
+      "logits/chosen": 10.089515686035156,
+      "logits/rejected": 10.921834945678711,
+      "logps/chosen": -0.4228805899620056,
+      "logps/rejected": -0.44924959540367126,
+      "loss": 1.3654,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.8457611799240112,
+      "rewards/margins": 0.05273808538913727,
+      "rewards/rejected": -0.8984991908073425,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.8496569991111755,
+      "learning_rate": 8.493847138894208e-07,
+      "logits/chosen": 10.220051765441895,
+      "logits/rejected": 10.924245834350586,
+      "logps/chosen": -0.4278189241886139,
+      "logps/rejected": -0.45087143778800964,
+      "loss": 1.3771,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.8556378483772278,
+      "rewards/margins": 0.046104975044727325,
+      "rewards/rejected": -0.9017428755760193,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 1.1707934141159058,
+      "learning_rate": 8.322357367194108e-07,
+      "logits/chosen": 10.33618450164795,
+      "logits/rejected": 11.42149829864502,
+      "logps/chosen": -0.4403349757194519,
+      "logps/rejected": -0.4506159722805023,
+      "loss": 1.3831,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8806699514389038,
+      "rewards/margins": 0.020561927929520607,
+      "rewards/rejected": -0.9012319445610046,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.9727609753608704,
+      "learning_rate": 8.143564332954425e-07,
+      "logits/chosen": 9.973875999450684,
+      "logits/rejected": 11.174227714538574,
+      "logps/chosen": -0.48110640048980713,
+      "logps/rejected": -0.46264228224754333,
+      "loss": 1.4375,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.9622128009796143,
+      "rewards/margins": -0.03692828118801117,
+      "rewards/rejected": -0.9252845644950867,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.4669955372810364,
+      "learning_rate": 7.957861062067612e-07,
+      "logits/chosen": 9.494720458984375,
+      "logits/rejected": 10.64975357055664,
+      "logps/chosen": -0.4049557149410248,
+      "logps/rejected": -0.41160064935684204,
+      "loss": 1.3949,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.8099114298820496,
+      "rewards/margins": 0.01328977383673191,
+      "rewards/rejected": -0.8232012987136841,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.6599685549736023,
+      "learning_rate": 7.765655770625996e-07,
+      "logits/chosen": 9.987813949584961,
+      "logits/rejected": 11.066561698913574,
+      "logps/chosen": -0.4204758107662201,
+      "logps/rejected": -0.4215814769268036,
+      "loss": 1.4024,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.8409516215324402,
+      "rewards/margins": 0.002211294136941433,
+      "rewards/rejected": -0.8431629538536072,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.4469655156135559,
+      "learning_rate": 7.567370967574209e-07,
+      "logits/chosen": 10.159306526184082,
+      "logits/rejected": 11.529789924621582,
+      "logps/chosen": -0.44582635164260864,
+      "logps/rejected": -0.4426492154598236,
+      "loss": 1.4042,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.8916527032852173,
+      "rewards/margins": -0.006354227662086487,
+      "rewards/rejected": -0.8852984309196472,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.46628981828689575,
+      "learning_rate": 7.363442525942826e-07,
+      "logits/chosen": 9.731393814086914,
+      "logits/rejected": 10.743117332458496,
+      "logps/chosen": -0.4495592713356018,
+      "logps/rejected": -0.41725438833236694,
+      "loss": 1.4528,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.8991185426712036,
+      "rewards/margins": -0.06460972875356674,
+      "rewards/rejected": -0.8345087766647339,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.6232314109802246,
+      "learning_rate": 7.154318724704851e-07,
+      "logits/chosen": 9.956490516662598,
+      "logits/rejected": 11.324994087219238,
+      "logps/chosen": -0.42140334844589233,
+      "logps/rejected": -0.3955790102481842,
+      "loss": 1.4406,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.8428066968917847,
+      "rewards/margins": -0.05164865404367447,
+      "rewards/rejected": -0.7911580204963684,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 1.1314888000488281,
+      "learning_rate": 6.940459263361248e-07,
+      "logits/chosen": 9.897272109985352,
+      "logits/rejected": 10.727909088134766,
+      "logps/chosen": -0.38281309604644775,
+      "logps/rejected": -0.4067748188972473,
+      "loss": 1.3728,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.7656261920928955,
+      "rewards/margins": 0.04792340472340584,
+      "rewards/rejected": -0.8135496377944946,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.9336860179901123,
+      "learning_rate": 6.722334251421664e-07,
+      "logits/chosen": 10.045162200927734,
+      "logits/rejected": 10.88832950592041,
+      "logps/chosen": -0.424130380153656,
+      "logps/rejected": -0.44961968064308167,
+      "loss": 1.3642,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.848260760307312,
+      "rewards/margins": 0.050978533923625946,
+      "rewards/rejected": -0.8992393612861633,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.6091923117637634,
+      "learning_rate": 6.500423175001703e-07,
+      "logits/chosen": 10.366498947143555,
+      "logits/rejected": 11.302865028381348,
+      "logps/chosen": -0.38435739278793335,
+      "logps/rejected": -0.40687644481658936,
+      "loss": 1.3686,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.7687147855758667,
+      "rewards/margins": 0.04503808170557022,
+      "rewards/rejected": -0.8137528896331787,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 1.436123251914978,
+      "learning_rate": 6.275213842808382e-07,
+      "logits/chosen": 9.993330955505371,
+      "logits/rejected": 10.635811805725098,
+      "logps/chosen": -0.41794323921203613,
+      "logps/rejected": -0.416820764541626,
+      "loss": 1.4028,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.8358864784240723,
+      "rewards/margins": -0.0022448617964982986,
+      "rewards/rejected": -0.833641529083252,
+      "step": 36
+    },
+    {
+      "epoch": 0.4874433923425278,
+      "grad_norm": 0.4129350483417511,
+      "learning_rate": 6.047201313830723e-07,
+      "logits/chosen": 10.213558197021484,
+      "logits/rejected": 11.014687538146973,
+      "logps/chosen": -0.4101608991622925,
+      "logps/rejected": -0.40530481934547424,
+      "loss": 1.409,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.820321798324585,
+      "rewards/margins": -0.00971211027354002,
+      "rewards/rejected": -0.8106096386909485,
+      "step": 37
+    },
+    {
+      "epoch": 0.500617538081515,
+      "grad_norm": 1.0162944793701172,
+      "learning_rate": 5.816886809092651e-07,
+      "logits/chosen": 9.751138687133789,
+      "logits/rejected": 10.836737632751465,
+      "logps/chosen": -0.4359847605228424,
+      "logps/rejected": -0.42434683442115784,
+      "loss": 1.4272,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.8719695210456848,
+      "rewards/margins": -0.02327585220336914,
+      "rewards/rejected": -0.8486936688423157,
+      "step": 38
+    },
+    {
+      "epoch": 0.5137916838205022,
+      "grad_norm": 1.3473665714263916,
+      "learning_rate": 5.584776609860413e-07,
+      "logits/chosen": 10.200762748718262,
+      "logits/rejected": 10.96191692352295,
+      "logps/chosen": -0.40851840376853943,
+      "logps/rejected": -0.38918375968933105,
+      "loss": 1.4273,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.8170368075370789,
+      "rewards/margins": -0.03866923972964287,
+      "rewards/rejected": -0.7783675193786621,
+      "step": 39
+    },
+    {
+      "epoch": 0.5269658295594895,
+      "grad_norm": 3.9734771251678467,
+      "learning_rate": 5.351380944726465e-07,
+      "logits/chosen": 10.102203369140625,
+      "logits/rejected": 11.253116607666016,
+      "logps/chosen": -0.40019893646240234,
+      "logps/rejected": -0.40543556213378906,
+      "loss": 1.3934,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.8003978729248047,
+      "rewards/margins": 0.010473249480128288,
+      "rewards/rejected": -0.8108711242675781,
+      "step": 40
+    },
+    {
+      "epoch": 0.5401399752984768,
+      "grad_norm": 1.0061744451522827,
+      "learning_rate": 5.117212868016303e-07,
+      "logits/chosen": 10.42828369140625,
+      "logits/rejected": 11.038559913635254,
+      "logps/chosen": -0.39824292063713074,
+      "logps/rejected": -0.41535234451293945,
+      "loss": 1.3724,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.7964858412742615,
+      "rewards/margins": 0.03421883285045624,
+      "rewards/rejected": -0.8307046890258789,
+      "step": 41
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": 1.7842886447906494,
+      "learning_rate": 4.882787131983697e-07,
+      "logits/chosen": 9.360157012939453,
+      "logits/rejected": 10.43077278137207,
+      "logps/chosen": -0.3668302893638611,
+      "logps/rejected": -0.3597845435142517,
+      "loss": 1.4068,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.7336605787277222,
+      "rewards/margins": -0.014091495424509048,
+      "rewards/rejected": -0.7195690870285034,
+      "step": 42
+    },
+    {
+      "epoch": 0.5664882667764513,
+      "grad_norm": 0.7694165706634521,
+      "learning_rate": 4.648619055273537e-07,
+      "logits/chosen": 9.549002647399902,
+      "logits/rejected": 10.662269592285156,
+      "logps/chosen": -0.3708702325820923,
+      "logps/rejected": -0.3596724271774292,
+      "loss": 1.4136,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.7417404651641846,
+      "rewards/margins": -0.022395702078938484,
+      "rewards/rejected": -0.7193448543548584,
+      "step": 43
+    },
+    {
+      "epoch": 0.5796624125154385,
+      "grad_norm": 0.31465020775794983,
+      "learning_rate": 4.4152233901395875e-07,
+      "logits/chosen": 9.66249942779541,
+      "logits/rejected": 10.4733247756958,
+      "logps/chosen": -0.3584354817867279,
+      "logps/rejected": -0.3858814835548401,
+      "loss": 1.3559,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.7168709635734558,
+      "rewards/margins": 0.05489201098680496,
+      "rewards/rejected": -0.7717629671096802,
+      "step": 44
+    },
+    {
+      "epoch": 0.5928365582544257,
+      "grad_norm": 0.9510380029678345,
+      "learning_rate": 4.183113190907348e-07,
+      "logits/chosen": 9.850863456726074,
+      "logits/rejected": 10.66943359375,
+      "logps/chosen": -0.371550589799881,
+      "logps/rejected": -0.37234315276145935,
+      "loss": 1.3984,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.743101179599762,
+      "rewards/margins": 0.0015851231291890144,
+      "rewards/rejected": -0.7446863055229187,
+      "step": 45
+    },
+    {
+      "epoch": 0.606010703993413,
+      "grad_norm": 0.7652634382247925,
+      "learning_rate": 3.9527986861692785e-07,
+      "logits/chosen": 9.94843864440918,
+      "logits/rejected": 10.614623069763184,
+      "logps/chosen": -0.3755650222301483,
+      "logps/rejected": -0.3979741632938385,
+      "loss": 1.3633,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.7511300444602966,
+      "rewards/margins": 0.044818248599767685,
+      "rewards/rejected": -0.795948326587677,
+      "step": 46
+    },
+    {
+      "epoch": 0.6191848497324002,
+      "grad_norm": 0.40572136640548706,
+      "learning_rate": 3.724786157191618e-07,
+      "logits/chosen": 9.853185653686523,
+      "logits/rejected": 11.088766098022461,
+      "logps/chosen": -0.3570285439491272,
+      "logps/rejected": -0.3574231266975403,
+      "loss": 1.3937,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.7140570878982544,
+      "rewards/margins": 0.0007891724817454815,
+      "rewards/rejected": -0.7148462533950806,
+      "step": 47
+    },
+    {
+      "epoch": 0.6323589954713874,
+      "grad_norm": 0.8276376724243164,
+      "learning_rate": 3.499576824998297e-07,
+      "logits/chosen": 10.390812873840332,
+      "logits/rejected": 11.2942476272583,
+      "logps/chosen": -0.3813317120075226,
+      "logps/rejected": -0.40014880895614624,
+      "loss": 1.37,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.7626634240150452,
+      "rewards/margins": 0.03763421252369881,
+      "rewards/rejected": -0.8002976179122925,
+      "step": 48
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 12,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-60/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

checkpoint-60/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/v-liuzichuan/huggingface/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 32064
+}

checkpoint-60/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.45.2"
+}

checkpoint-60/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8a018cbdbb3469fc14e93f7c3ff0b139336f521e029630a5ee06d63d8ad871
+size 4972489328

checkpoint-60/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15df8c21893b1eaef68d06d63af1c7fbd80c8825b4683d501ae1395ce93e7d2
+size 2669692552

checkpoint-60/model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 7642159104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-60/special_tokens_map.json

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