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 +1,24 @@
+{
+    "epoch": 0.9880609304240429,
+    "eval_logits/chosen": 9.252660751342773,
+    "eval_logits/rejected": 10.067312240600586,
+    "eval_logps/chosen": -109.64786529541016,
+    "eval_logps/ref_chosen": -106.16099548339844,
+    "eval_logps/ref_rejected": -119.78473663330078,
+    "eval_logps/rejected": -124.11076354980469,
+    "eval_loss": 0.6891200542449951,
+    "eval_rewards/accuracies": 0.604629635810852,
+    "eval_rewards/chosen": -0.034868817776441574,
+    "eval_rewards/margins": 0.008391385897994041,
+    "eval_rewards/rejected": -0.043260201811790466,
+    "eval_runtime": 161.4409,
+    "eval_samples": 1080,
+    "eval_samples_per_second": 6.69,
+    "eval_steps_per_second": 1.672,
+    "total_flos": 0.0,
+    "train_loss": 0.6916100986798605,
+    "train_runtime": 8570.6786,
+    "train_samples": 9715,
+    "train_samples_per_second": 1.134,
+    "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 sha256:0da4331c450828e3ade9ffce377bab29a84c7c38e9d6b233fda0b5dc96d56d84
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d7c3ae5a376db36d73eaaff94a9b9bb97a9ed5193c98d171ec7b3cbbf18616
+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 +1,237 @@
+{
+  "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": 0.5010076761245728,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 9.988622665405273,
+      "logits/rejected": 10.698101997375488,
+      "logps/chosen": -102.88545989990234,
+      "logps/ref_chosen": -102.88545989990234,
+      "logps/ref_rejected": -121.84871673583984,
+      "logps/rejected": -121.84871673583984,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.7802621126174927,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.208279609680176,
+      "logits/rejected": 11.06594467163086,
+      "logps/chosen": -107.70349884033203,
+      "logps/ref_chosen": -107.70349884033203,
+      "logps/ref_rejected": -121.89966583251953,
+      "logps/rejected": -121.89966583251953,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.5995805859565735,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.029329299926758,
+      "logits/rejected": 11.023927688598633,
+      "logps/chosen": -107.6470947265625,
+      "logps/ref_chosen": -107.98188781738281,
+      "logps/ref_rejected": -124.51527404785156,
+      "logps/rejected": -124.29098510742188,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.0033478327095508575,
+      "rewards/margins": 0.001104944385588169,
+      "rewards/rejected": 0.0022428883239626884,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.5383147597312927,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 9.823471069335938,
+      "logits/rejected": 10.842323303222656,
+      "logps/chosen": -109.73627471923828,
+      "logps/ref_chosen": -109.20836639404297,
+      "logps/ref_rejected": -119.23908996582031,
+      "logps/rejected": -119.65444946289062,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.005279023200273514,
+      "rewards/margins": -0.001125341048464179,
+      "rewards/rejected": -0.004153682850301266,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.5302512645721436,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.209351539611816,
+      "logits/rejected": 10.967523574829102,
+      "logps/chosen": -103.73981475830078,
+      "logps/ref_chosen": -103.87680053710938,
+      "logps/ref_rejected": -118.41618347167969,
+      "logps/rejected": -118.11978149414062,
+      "loss": 0.694,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": 0.0013697518734261394,
+      "rewards/margins": -0.001594369299709797,
+      "rewards/rejected": 0.002964121289551258,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.6919645667076111,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.676691055297852,
+      "logits/rejected": 11.460196495056152,
+      "logps/chosen": -108.08129119873047,
+      "logps/ref_chosen": -107.58968353271484,
+      "logps/ref_rejected": -122.07303619384766,
+      "logps/rejected": -122.37925720214844,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.004916056990623474,
+      "rewards/margins": -0.0018538986332714558,
+      "rewards/rejected": -0.0030621583573520184,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.40329915285110474,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 10.017489433288574,
+      "logits/rejected": 10.722752571105957,
+      "logps/chosen": -107.77075958251953,
+      "logps/ref_chosen": -107.42727661132812,
+      "logps/ref_rejected": -116.87063598632812,
+      "logps/rejected": -116.98759460449219,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4140625,
+      "rewards/chosen": -0.0034348624758422375,
+      "rewards/margins": -0.0022651171311736107,
+      "rewards/rejected": -0.0011697453446686268,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.4481956362724304,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.191514015197754,
+      "logits/rejected": 11.094213485717773,
+      "logps/chosen": -106.06684112548828,
+      "logps/ref_chosen": -105.60282135009766,
+      "logps/ref_rejected": -119.53916931152344,
+      "logps/rejected": -119.9333267211914,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.004640196915715933,
+      "rewards/margins": -0.0006986188236624002,
+      "rewards/rejected": -0.003941578324884176,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.5002302527427673,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.164933204650879,
+      "logits/rejected": 11.139327049255371,
+      "logps/chosen": -106.06144714355469,
+      "logps/ref_chosen": -105.46086120605469,
+      "logps/ref_rejected": -119.00373840332031,
+      "logps/rejected": -119.59027862548828,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.006005657836794853,
+      "rewards/margins": -0.00014029807061888278,
+      "rewards/rejected": -0.005865359678864479,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6467388868331909,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 9.98875904083252,
+      "logits/rejected": 10.815544128417969,
+      "logps/chosen": -105.14952850341797,
+      "logps/ref_chosen": -104.21009826660156,
+      "logps/ref_rejected": -118.9209213256836,
+      "logps/rejected": -119.72019958496094,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.00939436536282301,
+      "rewards/margins": -0.0014015533961355686,
+      "rewards/rejected": -0.007992811501026154,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.8090001344680786,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 9.946345329284668,
+      "logits/rejected": 11.13135814666748,
+      "logps/chosen": -107.09854125976562,
+      "logps/ref_chosen": -105.94319152832031,
+      "logps/ref_rejected": -122.76007843017578,
+      "logps/rejected": -123.9129409790039,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01155336108058691,
+      "rewards/margins": -2.4825334548950195e-05,
+      "rewards/rejected": -0.011528536677360535,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.49643445014953613,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 9.876545906066895,
+      "logits/rejected": 10.567835807800293,
+      "logps/chosen": -109.7830810546875,
+      "logps/ref_chosen": -109.08442687988281,
+      "logps/ref_rejected": -121.41947174072266,
+      "logps/rejected": -122.12468719482422,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.006986413151025772,
+      "rewards/margins": 6.572058191522956e-05,
+      "rewards/rejected": -0.00705213425680995,
+      "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 sha256:3689fa5995edb3614444b13d093593e45588df7fbf40ec3c30cc0c564b96f72b
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811b5ab3c8a8f4286f660428d7cfb8fde5c7d2e7e729f4352b94ece36fb6ac94
+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 +1,441 @@
+{
+  "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": 0.5010076761245728,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 9.988622665405273,
+      "logits/rejected": 10.698101997375488,
+      "logps/chosen": -102.88545989990234,
+      "logps/ref_chosen": -102.88545989990234,
+      "logps/ref_rejected": -121.84871673583984,
+      "logps/rejected": -121.84871673583984,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.7802621126174927,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.208279609680176,
+      "logits/rejected": 11.06594467163086,
+      "logps/chosen": -107.70349884033203,
+      "logps/ref_chosen": -107.70349884033203,
+      "logps/ref_rejected": -121.89966583251953,
+      "logps/rejected": -121.89966583251953,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.5995805859565735,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.029329299926758,
+      "logits/rejected": 11.023927688598633,
+      "logps/chosen": -107.6470947265625,
+      "logps/ref_chosen": -107.98188781738281,
+      "logps/ref_rejected": -124.51527404785156,
+      "logps/rejected": -124.29098510742188,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.0033478327095508575,
+      "rewards/margins": 0.001104944385588169,
+      "rewards/rejected": 0.0022428883239626884,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.5383147597312927,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 9.823471069335938,
+      "logits/rejected": 10.842323303222656,
+      "logps/chosen": -109.73627471923828,
+      "logps/ref_chosen": -109.20836639404297,
+      "logps/ref_rejected": -119.23908996582031,
+      "logps/rejected": -119.65444946289062,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.005279023200273514,
+      "rewards/margins": -0.001125341048464179,
+      "rewards/rejected": -0.004153682850301266,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.5302512645721436,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.209351539611816,
+      "logits/rejected": 10.967523574829102,
+      "logps/chosen": -103.73981475830078,
+      "logps/ref_chosen": -103.87680053710938,
+      "logps/ref_rejected": -118.41618347167969,
+      "logps/rejected": -118.11978149414062,
+      "loss": 0.694,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": 0.0013697518734261394,
+      "rewards/margins": -0.001594369299709797,
+      "rewards/rejected": 0.002964121289551258,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.6919645667076111,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.676691055297852,
+      "logits/rejected": 11.460196495056152,
+      "logps/chosen": -108.08129119873047,
+      "logps/ref_chosen": -107.58968353271484,
+      "logps/ref_rejected": -122.07303619384766,
+      "logps/rejected": -122.37925720214844,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.004916056990623474,
+      "rewards/margins": -0.0018538986332714558,
+      "rewards/rejected": -0.0030621583573520184,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.40329915285110474,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 10.017489433288574,
+      "logits/rejected": 10.722752571105957,
+      "logps/chosen": -107.77075958251953,
+      "logps/ref_chosen": -107.42727661132812,
+      "logps/ref_rejected": -116.87063598632812,
+      "logps/rejected": -116.98759460449219,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4140625,
+      "rewards/chosen": -0.0034348624758422375,
+      "rewards/margins": -0.0022651171311736107,
+      "rewards/rejected": -0.0011697453446686268,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.4481956362724304,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.191514015197754,
+      "logits/rejected": 11.094213485717773,
+      "logps/chosen": -106.06684112548828,
+      "logps/ref_chosen": -105.60282135009766,
+      "logps/ref_rejected": -119.53916931152344,
+      "logps/rejected": -119.9333267211914,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.004640196915715933,
+      "rewards/margins": -0.0006986188236624002,
+      "rewards/rejected": -0.003941578324884176,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.5002302527427673,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.164933204650879,
+      "logits/rejected": 11.139327049255371,
+      "logps/chosen": -106.06144714355469,
+      "logps/ref_chosen": -105.46086120605469,
+      "logps/ref_rejected": -119.00373840332031,
+      "logps/rejected": -119.59027862548828,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.006005657836794853,
+      "rewards/margins": -0.00014029807061888278,
+      "rewards/rejected": -0.005865359678864479,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6467388868331909,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 9.98875904083252,
+      "logits/rejected": 10.815544128417969,
+      "logps/chosen": -105.14952850341797,
+      "logps/ref_chosen": -104.21009826660156,
+      "logps/ref_rejected": -118.9209213256836,
+      "logps/rejected": -119.72019958496094,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.00939436536282301,
+      "rewards/margins": -0.0014015533961355686,
+      "rewards/rejected": -0.007992811501026154,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.8090001344680786,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 9.946345329284668,
+      "logits/rejected": 11.13135814666748,
+      "logps/chosen": -107.09854125976562,
+      "logps/ref_chosen": -105.94319152832031,
+      "logps/ref_rejected": -122.76007843017578,
+      "logps/rejected": -123.9129409790039,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01155336108058691,
+      "rewards/margins": -2.4825334548950195e-05,
+      "rewards/rejected": -0.011528536677360535,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.49643445014953613,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 9.876545906066895,
+      "logits/rejected": 10.567835807800293,
+      "logps/chosen": -109.7830810546875,
+      "logps/ref_chosen": -109.08442687988281,
+      "logps/ref_rejected": -121.41947174072266,
+      "logps/rejected": -122.12468719482422,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.006986413151025772,
+      "rewards/margins": 6.572058191522956e-05,
+      "rewards/rejected": -0.00705213425680995,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5409023761749268,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.916489601135254,
+      "logits/rejected": 10.99366283416748,
+      "logps/chosen": -105.78418731689453,
+      "logps/ref_chosen": -104.62150573730469,
+      "logps/ref_rejected": -119.55384063720703,
+      "logps/rejected": -120.60539245605469,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.011626748368144035,
+      "rewards/margins": -0.0011113437358289957,
+      "rewards/rejected": -0.010515404865145683,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.9010350108146667,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.480968475341797,
+      "logits/rejected": 11.599580764770508,
+      "logps/chosen": -107.57891845703125,
+      "logps/ref_chosen": -106.179443359375,
+      "logps/ref_rejected": -120.73036193847656,
+      "logps/rejected": -122.02151489257812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.013994838111102581,
+      "rewards/margins": -0.0010832665720954537,
+      "rewards/rejected": -0.012911571189761162,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.8957933187484741,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.80737018585205,
+      "logits/rejected": 10.738137245178223,
+      "logps/chosen": -107.41307067871094,
+      "logps/ref_chosen": -105.70547485351562,
+      "logps/ref_rejected": -118.89997863769531,
+      "logps/rejected": -120.64563751220703,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.01707591488957405,
+      "rewards/margins": 0.00038063188549131155,
+      "rewards/rejected": -0.017456548288464546,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7111092805862427,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.634671211242676,
+      "logits/rejected": 11.238730430603027,
+      "logps/chosen": -110.74053955078125,
+      "logps/ref_chosen": -108.86376953125,
+      "logps/ref_rejected": -122.1635513305664,
+      "logps/rejected": -124.17098999023438,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.018767736852169037,
+      "rewards/margins": 0.0013066575629636645,
+      "rewards/rejected": -0.02007439360022545,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.5599011778831482,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.138323783874512,
+      "logits/rejected": 10.76909065246582,
+      "logps/chosen": -104.49694061279297,
+      "logps/ref_chosen": -102.93986511230469,
+      "logps/ref_rejected": -119.43718719482422,
+      "logps/rejected": -121.1658935546875,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.015570812858641148,
+      "rewards/margins": 0.0017161847790703177,
+      "rewards/rejected": -0.0172869972884655,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.7006244659423828,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.374225616455078,
+      "logits/rejected": 11.157809257507324,
+      "logps/chosen": -105.8244400024414,
+      "logps/ref_chosen": -103.81341552734375,
+      "logps/ref_rejected": -117.45123291015625,
+      "logps/rejected": -119.37814331054688,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.020110249519348145,
+      "rewards/margins": -0.0008410783484578133,
+      "rewards/rejected": -0.019269172102212906,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.49562451243400574,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.303974151611328,
+      "logits/rejected": 10.965604782104492,
+      "logps/chosen": -109.81462860107422,
+      "logps/ref_chosen": -107.85797119140625,
+      "logps/ref_rejected": -121.88042449951172,
+      "logps/rejected": -124.41007232666016,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.019566601142287254,
+      "rewards/margins": 0.005729879252612591,
+      "rewards/rejected": -0.02529647946357727,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.48442593216896057,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.682939529418945,
+      "logits/rejected": 11.487958908081055,
+      "logps/chosen": -105.8414077758789,
+      "logps/ref_chosen": -103.42721557617188,
+      "logps/ref_rejected": -116.7796630859375,
+      "logps/rejected": -119.14535522460938,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.024141818284988403,
+      "rewards/margins": -0.00048486533341929317,
+      "rewards/rejected": -0.023656953126192093,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.6605204343795776,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.703460693359375,
+      "logits/rejected": 10.792010307312012,
+      "logps/chosen": -109.3312759399414,
+      "logps/ref_chosen": -106.60163879394531,
+      "logps/ref_rejected": -124.56562805175781,
+      "logps/rejected": -127.45460510253906,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.027296334505081177,
+      "rewards/margins": 0.0015935557894408703,
+      "rewards/rejected": -0.028889887034893036,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.8831092715263367,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.168815612792969,
+      "logits/rejected": 11.040711402893066,
+      "logps/chosen": -107.1961669921875,
+      "logps/ref_chosen": -103.77696228027344,
+      "logps/ref_rejected": -118.73616027832031,
+      "logps/rejected": -121.80266571044922,
+      "loss": 0.695,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.03419206291437149,
+      "rewards/margins": -0.0035268948413431644,
+      "rewards/rejected": -0.030665166676044464,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.37249696254730225,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.050610542297363,
+      "logits/rejected": 11.06921100616455,
+      "logps/chosen": -108.137451171875,
+      "logps/ref_chosen": -104.72956085205078,
+      "logps/ref_rejected": -121.35556030273438,
+      "logps/rejected": -124.6715316772461,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.03407883644104004,
+      "rewards/margins": -0.0009191110148094594,
+      "rewards/rejected": -0.03315972909331322,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5831263661384583,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.146599769592285,
+      "logits/rejected": 10.979142189025879,
+      "logps/chosen": -109.36030578613281,
+      "logps/ref_chosen": -105.88758087158203,
+      "logps/ref_rejected": -125.69054412841797,
+      "logps/rejected": -129.528076171875,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.034727297723293304,
+      "rewards/margins": 0.003648004261776805,
+      "rewards/rejected": -0.03837530314922333,
+      "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 sha256:10f40d4e1b9377ff9c6c2eb887fe07bb44e76e083df02e176879c9fafd3a824a
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9008ffc21c5c0fedcd78556c9d60ba24b57b1610842f4e82d550e7d68d2bc23
+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 +1,645 @@
+{
+  "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": 0.5010076761245728,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 9.988622665405273,
+      "logits/rejected": 10.698101997375488,
+      "logps/chosen": -102.88545989990234,
+      "logps/ref_chosen": -102.88545989990234,
+      "logps/ref_rejected": -121.84871673583984,
+      "logps/rejected": -121.84871673583984,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.7802621126174927,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.208279609680176,
+      "logits/rejected": 11.06594467163086,
+      "logps/chosen": -107.70349884033203,
+      "logps/ref_chosen": -107.70349884033203,
+      "logps/ref_rejected": -121.89966583251953,
+      "logps/rejected": -121.89966583251953,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.5995805859565735,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.029329299926758,
+      "logits/rejected": 11.023927688598633,
+      "logps/chosen": -107.6470947265625,
+      "logps/ref_chosen": -107.98188781738281,
+      "logps/ref_rejected": -124.51527404785156,
+      "logps/rejected": -124.29098510742188,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.0033478327095508575,
+      "rewards/margins": 0.001104944385588169,
+      "rewards/rejected": 0.0022428883239626884,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.5383147597312927,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 9.823471069335938,
+      "logits/rejected": 10.842323303222656,
+      "logps/chosen": -109.73627471923828,
+      "logps/ref_chosen": -109.20836639404297,
+      "logps/ref_rejected": -119.23908996582031,
+      "logps/rejected": -119.65444946289062,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.005279023200273514,
+      "rewards/margins": -0.001125341048464179,
+      "rewards/rejected": -0.004153682850301266,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.5302512645721436,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.209351539611816,
+      "logits/rejected": 10.967523574829102,
+      "logps/chosen": -103.73981475830078,
+      "logps/ref_chosen": -103.87680053710938,
+      "logps/ref_rejected": -118.41618347167969,
+      "logps/rejected": -118.11978149414062,
+      "loss": 0.694,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": 0.0013697518734261394,
+      "rewards/margins": -0.001594369299709797,
+      "rewards/rejected": 0.002964121289551258,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.6919645667076111,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.676691055297852,
+      "logits/rejected": 11.460196495056152,
+      "logps/chosen": -108.08129119873047,
+      "logps/ref_chosen": -107.58968353271484,
+      "logps/ref_rejected": -122.07303619384766,
+      "logps/rejected": -122.37925720214844,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.004916056990623474,
+      "rewards/margins": -0.0018538986332714558,
+      "rewards/rejected": -0.0030621583573520184,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.40329915285110474,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 10.017489433288574,
+      "logits/rejected": 10.722752571105957,
+      "logps/chosen": -107.77075958251953,
+      "logps/ref_chosen": -107.42727661132812,
+      "logps/ref_rejected": -116.87063598632812,
+      "logps/rejected": -116.98759460449219,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4140625,
+      "rewards/chosen": -0.0034348624758422375,
+      "rewards/margins": -0.0022651171311736107,
+      "rewards/rejected": -0.0011697453446686268,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.4481956362724304,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.191514015197754,
+      "logits/rejected": 11.094213485717773,
+      "logps/chosen": -106.06684112548828,
+      "logps/ref_chosen": -105.60282135009766,
+      "logps/ref_rejected": -119.53916931152344,
+      "logps/rejected": -119.9333267211914,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.004640196915715933,
+      "rewards/margins": -0.0006986188236624002,
+      "rewards/rejected": -0.003941578324884176,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.5002302527427673,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.164933204650879,
+      "logits/rejected": 11.139327049255371,
+      "logps/chosen": -106.06144714355469,
+      "logps/ref_chosen": -105.46086120605469,
+      "logps/ref_rejected": -119.00373840332031,
+      "logps/rejected": -119.59027862548828,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.006005657836794853,
+      "rewards/margins": -0.00014029807061888278,
+      "rewards/rejected": -0.005865359678864479,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6467388868331909,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 9.98875904083252,
+      "logits/rejected": 10.815544128417969,
+      "logps/chosen": -105.14952850341797,
+      "logps/ref_chosen": -104.21009826660156,
+      "logps/ref_rejected": -118.9209213256836,
+      "logps/rejected": -119.72019958496094,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.00939436536282301,
+      "rewards/margins": -0.0014015533961355686,
+      "rewards/rejected": -0.007992811501026154,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.8090001344680786,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 9.946345329284668,
+      "logits/rejected": 11.13135814666748,
+      "logps/chosen": -107.09854125976562,
+      "logps/ref_chosen": -105.94319152832031,
+      "logps/ref_rejected": -122.76007843017578,
+      "logps/rejected": -123.9129409790039,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01155336108058691,
+      "rewards/margins": -2.4825334548950195e-05,
+      "rewards/rejected": -0.011528536677360535,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.49643445014953613,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 9.876545906066895,
+      "logits/rejected": 10.567835807800293,
+      "logps/chosen": -109.7830810546875,
+      "logps/ref_chosen": -109.08442687988281,
+      "logps/ref_rejected": -121.41947174072266,
+      "logps/rejected": -122.12468719482422,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.006986413151025772,
+      "rewards/margins": 6.572058191522956e-05,
+      "rewards/rejected": -0.00705213425680995,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5409023761749268,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.916489601135254,
+      "logits/rejected": 10.99366283416748,
+      "logps/chosen": -105.78418731689453,
+      "logps/ref_chosen": -104.62150573730469,
+      "logps/ref_rejected": -119.55384063720703,
+      "logps/rejected": -120.60539245605469,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.011626748368144035,
+      "rewards/margins": -0.0011113437358289957,
+      "rewards/rejected": -0.010515404865145683,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.9010350108146667,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.480968475341797,
+      "logits/rejected": 11.599580764770508,
+      "logps/chosen": -107.57891845703125,
+      "logps/ref_chosen": -106.179443359375,
+      "logps/ref_rejected": -120.73036193847656,
+      "logps/rejected": -122.02151489257812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.013994838111102581,
+      "rewards/margins": -0.0010832665720954537,
+      "rewards/rejected": -0.012911571189761162,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.8957933187484741,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.80737018585205,
+      "logits/rejected": 10.738137245178223,
+      "logps/chosen": -107.41307067871094,
+      "logps/ref_chosen": -105.70547485351562,
+      "logps/ref_rejected": -118.89997863769531,
+      "logps/rejected": -120.64563751220703,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.01707591488957405,
+      "rewards/margins": 0.00038063188549131155,
+      "rewards/rejected": -0.017456548288464546,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7111092805862427,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.634671211242676,
+      "logits/rejected": 11.238730430603027,
+      "logps/chosen": -110.74053955078125,
+      "logps/ref_chosen": -108.86376953125,
+      "logps/ref_rejected": -122.1635513305664,
+      "logps/rejected": -124.17098999023438,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.018767736852169037,
+      "rewards/margins": 0.0013066575629636645,
+      "rewards/rejected": -0.02007439360022545,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.5599011778831482,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.138323783874512,
+      "logits/rejected": 10.76909065246582,
+      "logps/chosen": -104.49694061279297,
+      "logps/ref_chosen": -102.93986511230469,
+      "logps/ref_rejected": -119.43718719482422,
+      "logps/rejected": -121.1658935546875,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.015570812858641148,
+      "rewards/margins": 0.0017161847790703177,
+      "rewards/rejected": -0.0172869972884655,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.7006244659423828,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.374225616455078,
+      "logits/rejected": 11.157809257507324,
+      "logps/chosen": -105.8244400024414,
+      "logps/ref_chosen": -103.81341552734375,
+      "logps/ref_rejected": -117.45123291015625,
+      "logps/rejected": -119.37814331054688,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.020110249519348145,
+      "rewards/margins": -0.0008410783484578133,
+      "rewards/rejected": -0.019269172102212906,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.49562451243400574,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.303974151611328,
+      "logits/rejected": 10.965604782104492,
+      "logps/chosen": -109.81462860107422,
+      "logps/ref_chosen": -107.85797119140625,
+      "logps/ref_rejected": -121.88042449951172,
+      "logps/rejected": -124.41007232666016,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.019566601142287254,
+      "rewards/margins": 0.005729879252612591,
+      "rewards/rejected": -0.02529647946357727,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.48442593216896057,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.682939529418945,
+      "logits/rejected": 11.487958908081055,
+      "logps/chosen": -105.8414077758789,
+      "logps/ref_chosen": -103.42721557617188,
+      "logps/ref_rejected": -116.7796630859375,
+      "logps/rejected": -119.14535522460938,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.024141818284988403,
+      "rewards/margins": -0.00048486533341929317,
+      "rewards/rejected": -0.023656953126192093,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.6605204343795776,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.703460693359375,
+      "logits/rejected": 10.792010307312012,
+      "logps/chosen": -109.3312759399414,
+      "logps/ref_chosen": -106.60163879394531,
+      "logps/ref_rejected": -124.56562805175781,
+      "logps/rejected": -127.45460510253906,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.027296334505081177,
+      "rewards/margins": 0.0015935557894408703,
+      "rewards/rejected": -0.028889887034893036,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.8831092715263367,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.168815612792969,
+      "logits/rejected": 11.040711402893066,
+      "logps/chosen": -107.1961669921875,
+      "logps/ref_chosen": -103.77696228027344,
+      "logps/ref_rejected": -118.73616027832031,
+      "logps/rejected": -121.80266571044922,
+      "loss": 0.695,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.03419206291437149,
+      "rewards/margins": -0.0035268948413431644,
+      "rewards/rejected": -0.030665166676044464,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.37249696254730225,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.050610542297363,
+      "logits/rejected": 11.06921100616455,
+      "logps/chosen": -108.137451171875,
+      "logps/ref_chosen": -104.72956085205078,
+      "logps/ref_rejected": -121.35556030273438,
+      "logps/rejected": -124.6715316772461,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.03407883644104004,
+      "rewards/margins": -0.0009191110148094594,
+      "rewards/rejected": -0.03315972909331322,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5831263661384583,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.146599769592285,
+      "logits/rejected": 10.979142189025879,
+      "logps/chosen": -109.36030578613281,
+      "logps/ref_chosen": -105.88758087158203,
+      "logps/ref_rejected": -125.69054412841797,
+      "logps/rejected": -129.528076171875,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.034727297723293304,
+      "rewards/margins": 0.003648004261776805,
+      "rewards/rejected": -0.03837530314922333,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.574914276599884,
+      "learning_rate": 4.246923569447104e-07,
+      "logits/chosen": 10.25512409210205,
+      "logits/rejected": 10.956289291381836,
+      "logps/chosen": -113.96874237060547,
+      "logps/ref_chosen": -110.0761489868164,
+      "logps/ref_rejected": -129.10540771484375,
+      "logps/rejected": -133.20553588867188,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.03892593830823898,
+      "rewards/margins": 0.0020754451397806406,
+      "rewards/rejected": -0.04100137948989868,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 0.42842620611190796,
+      "learning_rate": 4.161178683597054e-07,
+      "logits/chosen": 10.368014335632324,
+      "logits/rejected": 11.450322151184082,
+      "logps/chosen": -108.39615631103516,
+      "logps/ref_chosen": -103.74571990966797,
+      "logps/ref_rejected": -120.73832702636719,
+      "logps/rejected": -125.09370422363281,
+      "loss": 0.6947,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.046504296362400055,
+      "rewards/margins": -0.002950500464066863,
+      "rewards/rejected": -0.04355379566550255,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.5645923018455505,
+      "learning_rate": 4.0717821664772124e-07,
+      "logits/chosen": 10.042550086975098,
+      "logits/rejected": 11.243234634399414,
+      "logps/chosen": -110.1788330078125,
+      "logps/ref_chosen": -105.47428131103516,
+      "logps/ref_rejected": -120.5193099975586,
+      "logps/rejected": -125.00762939453125,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.04704552888870239,
+      "rewards/margins": -0.0021622537169605494,
+      "rewards/rejected": -0.044883277267217636,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.680381178855896,
+      "learning_rate": 3.978930531033806e-07,
+      "logits/chosen": 9.559943199157715,
+      "logits/rejected": 10.705163955688477,
+      "logps/chosen": -107.98367309570312,
+      "logps/ref_chosen": -103.72540283203125,
+      "logps/ref_rejected": -119.79557800292969,
+      "logps/rejected": -124.30613708496094,
+      "loss": 0.692,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.04258278012275696,
+      "rewards/margins": 0.0025227584410458803,
+      "rewards/rejected": -0.04510553926229477,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.569850504398346,
+      "learning_rate": 3.882827885312998e-07,
+      "logits/chosen": 10.065170288085938,
+      "logits/rejected": 11.1397123336792,
+      "logps/chosen": -112.4742431640625,
+      "logps/ref_chosen": -108.65434265136719,
+      "logps/ref_rejected": -121.46784973144531,
+      "logps/rejected": -125.24649047851562,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.03819899260997772,
+      "rewards/margins": -0.0004125672858208418,
+      "rewards/rejected": -0.03778642416000366,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.5246622562408447,
+      "learning_rate": 3.7836854837871044e-07,
+      "logits/chosen": 10.21100902557373,
+      "logits/rejected": 11.58244800567627,
+      "logps/chosen": -108.34341430664062,
+      "logps/ref_chosen": -103.62174224853516,
+      "logps/ref_rejected": -126.73807525634766,
+      "logps/rejected": -131.23304748535156,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.04721669480204582,
+      "rewards/margins": -0.0022669308818876743,
+      "rewards/rejected": -0.044949766248464584,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.37346869707107544,
+      "learning_rate": 3.681721262971413e-07,
+      "logits/chosen": 9.762397766113281,
+      "logits/rejected": 10.784234046936035,
+      "logps/chosen": -110.99979400634766,
+      "logps/ref_chosen": -106.10479736328125,
+      "logps/ref_rejected": -120.6382827758789,
+      "logps/rejected": -125.51140594482422,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.04894987493753433,
+      "rewards/margins": -0.00021872523939236999,
+      "rewards/rejected": -0.04873115196824074,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.4927314221858978,
+      "learning_rate": 3.577159362352426e-07,
+      "logits/chosen": 10.023344993591309,
+      "logits/rejected": 11.392967224121094,
+      "logps/chosen": -110.29427337646484,
+      "logps/ref_chosen": -105.99569702148438,
+      "logps/ref_rejected": -128.34303283691406,
+      "logps/rejected": -132.72604370117188,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.04298572242259979,
+      "rewards/margins": 0.0008442200487479568,
+      "rewards/rejected": -0.04382994398474693,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 0.9654183983802795,
+      "learning_rate": 3.470229631680624e-07,
+      "logits/chosen": 9.917928695678711,
+      "logits/rejected": 10.762564659118652,
+      "logps/chosen": -110.05650329589844,
+      "logps/ref_chosen": -105.72196197509766,
+      "logps/ref_rejected": -121.59507751464844,
+      "logps/rejected": -126.74140167236328,
+      "loss": 0.6892,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.04334544017910957,
+      "rewards/margins": 0.008117962628602982,
+      "rewards/rejected": -0.05146340653300285,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.5439296960830688,
+      "learning_rate": 3.361167125710832e-07,
+      "logits/chosen": 10.135066032409668,
+      "logits/rejected": 10.976527214050293,
+      "logps/chosen": -115.52051544189453,
+      "logps/ref_chosen": -111.4834976196289,
+      "logps/ref_rejected": -130.48089599609375,
+      "logps/rejected": -135.11973571777344,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.04037024453282356,
+      "rewards/margins": 0.0060182418674230576,
+      "rewards/rejected": -0.04638848453760147,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.6634539365768433,
+      "learning_rate": 3.2502115875008516e-07,
+      "logits/chosen": 10.4329252243042,
+      "logits/rejected": 11.376739501953125,
+      "logps/chosen": -112.54086303710938,
+      "logps/ref_chosen": -108.9183349609375,
+      "logps/ref_rejected": -121.32493591308594,
+      "logps/rejected": -125.75639343261719,
+      "loss": 0.6893,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.03622515872120857,
+      "rewards/margins": 0.008089457638561726,
+      "rewards/rejected": -0.04431461915373802,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.6542326807975769,
+      "learning_rate": 3.137606921404191e-07,
+      "logits/chosen": 10.058025360107422,
+      "logits/rejected": 10.712655067443848,
+      "logps/chosen": -111.80799865722656,
+      "logps/ref_chosen": -107.1411361694336,
+      "logps/ref_rejected": -118.66165161132812,
+      "logps/rejected": -123.4068832397461,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.046668585389852524,
+      "rewards/margins": 0.000783862778916955,
+      "rewards/rejected": -0.047452446073293686,
+      "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:dd3ca45781e83bebafc34e762d2edb6aeb1096eecd24991fe2430d6119be59f9
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1b5892ecf5904aaf5bb13c6f71b7e23ac0bbdc9d8a24eda82efa332e73db1a
+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 +1,849 @@
+{
+  "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": 0.5010076761245728,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 9.988622665405273,
+      "logits/rejected": 10.698101997375488,
+      "logps/chosen": -102.88545989990234,
+      "logps/ref_chosen": -102.88545989990234,
+      "logps/ref_rejected": -121.84871673583984,
+      "logps/rejected": -121.84871673583984,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.7802621126174927,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.208279609680176,
+      "logits/rejected": 11.06594467163086,
+      "logps/chosen": -107.70349884033203,
+      "logps/ref_chosen": -107.70349884033203,
+      "logps/ref_rejected": -121.89966583251953,
+      "logps/rejected": -121.89966583251953,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.5995805859565735,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.029329299926758,
+      "logits/rejected": 11.023927688598633,
+      "logps/chosen": -107.6470947265625,
+      "logps/ref_chosen": -107.98188781738281,
+      "logps/ref_rejected": -124.51527404785156,
+      "logps/rejected": -124.29098510742188,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.0033478327095508575,
+      "rewards/margins": 0.001104944385588169,
+      "rewards/rejected": 0.0022428883239626884,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.5383147597312927,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 9.823471069335938,
+      "logits/rejected": 10.842323303222656,
+      "logps/chosen": -109.73627471923828,
+      "logps/ref_chosen": -109.20836639404297,
+      "logps/ref_rejected": -119.23908996582031,
+      "logps/rejected": -119.65444946289062,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.005279023200273514,
+      "rewards/margins": -0.001125341048464179,
+      "rewards/rejected": -0.004153682850301266,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.5302512645721436,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.209351539611816,
+      "logits/rejected": 10.967523574829102,
+      "logps/chosen": -103.73981475830078,
+      "logps/ref_chosen": -103.87680053710938,
+      "logps/ref_rejected": -118.41618347167969,
+      "logps/rejected": -118.11978149414062,
+      "loss": 0.694,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": 0.0013697518734261394,
+      "rewards/margins": -0.001594369299709797,
+      "rewards/rejected": 0.002964121289551258,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.6919645667076111,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.676691055297852,
+      "logits/rejected": 11.460196495056152,
+      "logps/chosen": -108.08129119873047,
+      "logps/ref_chosen": -107.58968353271484,
+      "logps/ref_rejected": -122.07303619384766,
+      "logps/rejected": -122.37925720214844,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.421875,
+      "rewards/chosen": -0.004916056990623474,
+      "rewards/margins": -0.0018538986332714558,
+      "rewards/rejected": -0.0030621583573520184,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.40329915285110474,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 10.017489433288574,
+      "logits/rejected": 10.722752571105957,
+      "logps/chosen": -107.77075958251953,
+      "logps/ref_chosen": -107.42727661132812,
+      "logps/ref_rejected": -116.87063598632812,
+      "logps/rejected": -116.98759460449219,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4140625,
+      "rewards/chosen": -0.0034348624758422375,
+      "rewards/margins": -0.0022651171311736107,
+      "rewards/rejected": -0.0011697453446686268,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.4481956362724304,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.191514015197754,
+      "logits/rejected": 11.094213485717773,
+      "logps/chosen": -106.06684112548828,
+      "logps/ref_chosen": -105.60282135009766,
+      "logps/ref_rejected": -119.53916931152344,
+      "logps/rejected": -119.9333267211914,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.004640196915715933,
+      "rewards/margins": -0.0006986188236624002,
+      "rewards/rejected": -0.003941578324884176,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.5002302527427673,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.164933204650879,
+      "logits/rejected": 11.139327049255371,
+      "logps/chosen": -106.06144714355469,
+      "logps/ref_chosen": -105.46086120605469,
+      "logps/ref_rejected": -119.00373840332031,
+      "logps/rejected": -119.59027862548828,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.006005657836794853,
+      "rewards/margins": -0.00014029807061888278,
+      "rewards/rejected": -0.005865359678864479,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6467388868331909,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 9.98875904083252,
+      "logits/rejected": 10.815544128417969,
+      "logps/chosen": -105.14952850341797,
+      "logps/ref_chosen": -104.21009826660156,
+      "logps/ref_rejected": -118.9209213256836,
+      "logps/rejected": -119.72019958496094,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.00939436536282301,
+      "rewards/margins": -0.0014015533961355686,
+      "rewards/rejected": -0.007992811501026154,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.8090001344680786,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 9.946345329284668,
+      "logits/rejected": 11.13135814666748,
+      "logps/chosen": -107.09854125976562,
+      "logps/ref_chosen": -105.94319152832031,
+      "logps/ref_rejected": -122.76007843017578,
+      "logps/rejected": -123.9129409790039,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01155336108058691,
+      "rewards/margins": -2.4825334548950195e-05,
+      "rewards/rejected": -0.011528536677360535,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.49643445014953613,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 9.876545906066895,
+      "logits/rejected": 10.567835807800293,
+      "logps/chosen": -109.7830810546875,
+      "logps/ref_chosen": -109.08442687988281,
+      "logps/ref_rejected": -121.41947174072266,
+      "logps/rejected": -122.12468719482422,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.006986413151025772,
+      "rewards/margins": 6.572058191522956e-05,
+      "rewards/rejected": -0.00705213425680995,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5409023761749268,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.916489601135254,
+      "logits/rejected": 10.99366283416748,
+      "logps/chosen": -105.78418731689453,
+      "logps/ref_chosen": -104.62150573730469,
+      "logps/ref_rejected": -119.55384063720703,
+      "logps/rejected": -120.60539245605469,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.011626748368144035,
+      "rewards/margins": -0.0011113437358289957,
+      "rewards/rejected": -0.010515404865145683,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.9010350108146667,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.480968475341797,
+      "logits/rejected": 11.599580764770508,
+      "logps/chosen": -107.57891845703125,
+      "logps/ref_chosen": -106.179443359375,
+      "logps/ref_rejected": -120.73036193847656,
+      "logps/rejected": -122.02151489257812,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.013994838111102581,
+      "rewards/margins": -0.0010832665720954537,
+      "rewards/rejected": -0.012911571189761162,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.8957933187484741,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.80737018585205,
+      "logits/rejected": 10.738137245178223,
+      "logps/chosen": -107.41307067871094,
+      "logps/ref_chosen": -105.70547485351562,
+      "logps/ref_rejected": -118.89997863769531,
+      "logps/rejected": -120.64563751220703,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.01707591488957405,
+      "rewards/margins": 0.00038063188549131155,
+      "rewards/rejected": -0.017456548288464546,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7111092805862427,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.634671211242676,
+      "logits/rejected": 11.238730430603027,
+      "logps/chosen": -110.74053955078125,
+      "logps/ref_chosen": -108.86376953125,
+      "logps/ref_rejected": -122.1635513305664,
+      "logps/rejected": -124.17098999023438,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.018767736852169037,
+      "rewards/margins": 0.0013066575629636645,
+      "rewards/rejected": -0.02007439360022545,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.5599011778831482,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.138323783874512,
+      "logits/rejected": 10.76909065246582,
+      "logps/chosen": -104.49694061279297,
+      "logps/ref_chosen": -102.93986511230469,
+      "logps/ref_rejected": -119.43718719482422,
+      "logps/rejected": -121.1658935546875,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.015570812858641148,
+      "rewards/margins": 0.0017161847790703177,
+      "rewards/rejected": -0.0172869972884655,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.7006244659423828,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.374225616455078,
+      "logits/rejected": 11.157809257507324,
+      "logps/chosen": -105.8244400024414,
+      "logps/ref_chosen": -103.81341552734375,
+      "logps/ref_rejected": -117.45123291015625,
+      "logps/rejected": -119.37814331054688,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.020110249519348145,
+      "rewards/margins": -0.0008410783484578133,
+      "rewards/rejected": -0.019269172102212906,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.49562451243400574,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.303974151611328,
+      "logits/rejected": 10.965604782104492,
+      "logps/chosen": -109.81462860107422,
+      "logps/ref_chosen": -107.85797119140625,
+      "logps/ref_rejected": -121.88042449951172,
+      "logps/rejected": -124.41007232666016,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.019566601142287254,
+      "rewards/margins": 0.005729879252612591,
+      "rewards/rejected": -0.02529647946357727,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.48442593216896057,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.682939529418945,
+      "logits/rejected": 11.487958908081055,
+      "logps/chosen": -105.8414077758789,
+      "logps/ref_chosen": -103.42721557617188,
+      "logps/ref_rejected": -116.7796630859375,
+      "logps/rejected": -119.14535522460938,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.024141818284988403,
+      "rewards/margins": -0.00048486533341929317,
+      "rewards/rejected": -0.023656953126192093,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.6605204343795776,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.703460693359375,
+      "logits/rejected": 10.792010307312012,
+      "logps/chosen": -109.3312759399414,
+      "logps/ref_chosen": -106.60163879394531,
+      "logps/ref_rejected": -124.56562805175781,
+      "logps/rejected": -127.45460510253906,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.027296334505081177,
+      "rewards/margins": 0.0015935557894408703,
+      "rewards/rejected": -0.028889887034893036,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.8831092715263367,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.168815612792969,
+      "logits/rejected": 11.040711402893066,
+      "logps/chosen": -107.1961669921875,
+      "logps/ref_chosen": -103.77696228027344,
+      "logps/ref_rejected": -118.73616027832031,
+      "logps/rejected": -121.80266571044922,
+      "loss": 0.695,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.03419206291437149,
+      "rewards/margins": -0.0035268948413431644,
+      "rewards/rejected": -0.030665166676044464,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.37249696254730225,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.050610542297363,
+      "logits/rejected": 11.06921100616455,
+      "logps/chosen": -108.137451171875,
+      "logps/ref_chosen": -104.72956085205078,
+      "logps/ref_rejected": -121.35556030273438,
+      "logps/rejected": -124.6715316772461,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.03407883644104004,
+      "rewards/margins": -0.0009191110148094594,
+      "rewards/rejected": -0.03315972909331322,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5831263661384583,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.146599769592285,
+      "logits/rejected": 10.979142189025879,
+      "logps/chosen": -109.36030578613281,
+      "logps/ref_chosen": -105.88758087158203,
+      "logps/ref_rejected": -125.69054412841797,
+      "logps/rejected": -129.528076171875,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.034727297723293304,
+      "rewards/margins": 0.003648004261776805,
+      "rewards/rejected": -0.03837530314922333,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.574914276599884,
+      "learning_rate": 4.246923569447104e-07,
+      "logits/chosen": 10.25512409210205,
+      "logits/rejected": 10.956289291381836,
+      "logps/chosen": -113.96874237060547,
+      "logps/ref_chosen": -110.0761489868164,
+      "logps/ref_rejected": -129.10540771484375,
+      "logps/rejected": -133.20553588867188,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.03892593830823898,
+      "rewards/margins": 0.0020754451397806406,
+      "rewards/rejected": -0.04100137948989868,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 0.42842620611190796,
+      "learning_rate": 4.161178683597054e-07,
+      "logits/chosen": 10.368014335632324,
+      "logits/rejected": 11.450322151184082,
+      "logps/chosen": -108.39615631103516,
+      "logps/ref_chosen": -103.74571990966797,
+      "logps/ref_rejected": -120.73832702636719,
+      "logps/rejected": -125.09370422363281,
+      "loss": 0.6947,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.046504296362400055,
+      "rewards/margins": -0.002950500464066863,
+      "rewards/rejected": -0.04355379566550255,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.5645923018455505,
+      "learning_rate": 4.0717821664772124e-07,
+      "logits/chosen": 10.042550086975098,
+      "logits/rejected": 11.243234634399414,
+      "logps/chosen": -110.1788330078125,
+      "logps/ref_chosen": -105.47428131103516,
+      "logps/ref_rejected": -120.5193099975586,
+      "logps/rejected": -125.00762939453125,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.04704552888870239,
+      "rewards/margins": -0.0021622537169605494,
+      "rewards/rejected": -0.044883277267217636,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.680381178855896,
+      "learning_rate": 3.978930531033806e-07,
+      "logits/chosen": 9.559943199157715,
+      "logits/rejected": 10.705163955688477,
+      "logps/chosen": -107.98367309570312,
+      "logps/ref_chosen": -103.72540283203125,
+      "logps/ref_rejected": -119.79557800292969,
+      "logps/rejected": -124.30613708496094,
+      "loss": 0.692,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.04258278012275696,
+      "rewards/margins": 0.0025227584410458803,
+      "rewards/rejected": -0.04510553926229477,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.569850504398346,
+      "learning_rate": 3.882827885312998e-07,
+      "logits/chosen": 10.065170288085938,
+      "logits/rejected": 11.1397123336792,
+      "logps/chosen": -112.4742431640625,
+      "logps/ref_chosen": -108.65434265136719,
+      "logps/ref_rejected": -121.46784973144531,
+      "logps/rejected": -125.24649047851562,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.03819899260997772,
+      "rewards/margins": -0.0004125672858208418,
+      "rewards/rejected": -0.03778642416000366,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.5246622562408447,
+      "learning_rate": 3.7836854837871044e-07,
+      "logits/chosen": 10.21100902557373,
+      "logits/rejected": 11.58244800567627,
+      "logps/chosen": -108.34341430664062,
+      "logps/ref_chosen": -103.62174224853516,
+      "logps/ref_rejected": -126.73807525634766,
+      "logps/rejected": -131.23304748535156,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.04721669480204582,
+      "rewards/margins": -0.0022669308818876743,
+      "rewards/rejected": -0.044949766248464584,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.37346869707107544,
+      "learning_rate": 3.681721262971413e-07,
+      "logits/chosen": 9.762397766113281,
+      "logits/rejected": 10.784234046936035,
+      "logps/chosen": -110.99979400634766,
+      "logps/ref_chosen": -106.10479736328125,
+      "logps/ref_rejected": -120.6382827758789,
+      "logps/rejected": -125.51140594482422,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.04894987493753433,
+      "rewards/margins": -0.00021872523939236999,
+      "rewards/rejected": -0.04873115196824074,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.4927314221858978,
+      "learning_rate": 3.577159362352426e-07,
+      "logits/chosen": 10.023344993591309,
+      "logits/rejected": 11.392967224121094,
+      "logps/chosen": -110.29427337646484,
+      "logps/ref_chosen": -105.99569702148438,
+      "logps/ref_rejected": -128.34303283691406,
+      "logps/rejected": -132.72604370117188,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.04298572242259979,
+      "rewards/margins": 0.0008442200487479568,
+      "rewards/rejected": -0.04382994398474693,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 0.9654183983802795,
+      "learning_rate": 3.470229631680624e-07,
+      "logits/chosen": 9.917928695678711,
+      "logits/rejected": 10.762564659118652,
+      "logps/chosen": -110.05650329589844,
+      "logps/ref_chosen": -105.72196197509766,
+      "logps/ref_rejected": -121.59507751464844,
+      "logps/rejected": -126.74140167236328,
+      "loss": 0.6892,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.04334544017910957,
+      "rewards/margins": 0.008117962628602982,
+      "rewards/rejected": -0.05146340653300285,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.5439296960830688,
+      "learning_rate": 3.361167125710832e-07,
+      "logits/chosen": 10.135066032409668,
+      "logits/rejected": 10.976527214050293,
+      "logps/chosen": -115.52051544189453,
+      "logps/ref_chosen": -111.4834976196289,
+      "logps/ref_rejected": -130.48089599609375,
+      "logps/rejected": -135.11973571777344,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -0.04037024453282356,
+      "rewards/margins": 0.0060182418674230576,
+      "rewards/rejected": -0.04638848453760147,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.6634539365768433,
+      "learning_rate": 3.2502115875008516e-07,
+      "logits/chosen": 10.4329252243042,
+      "logits/rejected": 11.376739501953125,
+      "logps/chosen": -112.54086303710938,
+      "logps/ref_chosen": -108.9183349609375,
+      "logps/ref_rejected": -121.32493591308594,
+      "logps/rejected": -125.75639343261719,
+      "loss": 0.6893,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.03622515872120857,
+      "rewards/margins": 0.008089457638561726,
+      "rewards/rejected": -0.04431461915373802,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.6542326807975769,
+      "learning_rate": 3.137606921404191e-07,
+      "logits/chosen": 10.058025360107422,
+      "logits/rejected": 10.712655067443848,
+      "logps/chosen": -111.80799865722656,
+      "logps/ref_chosen": -107.1411361694336,
+      "logps/ref_rejected": -118.66165161132812,
+      "logps/rejected": -123.4068832397461,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.046668585389852524,
+      "rewards/margins": 0.000783862778916955,
+      "rewards/rejected": -0.047452446073293686,
+      "step": 36
+    },
+    {
+      "epoch": 0.4874433923425278,
+      "grad_norm": 0.4339970350265503,
+      "learning_rate": 3.0236006569153616e-07,
+      "logits/chosen": 10.282718658447266,
+      "logits/rejected": 11.08802604675293,
+      "logps/chosen": -110.58891296386719,
+      "logps/ref_chosen": -106.6348876953125,
+      "logps/ref_rejected": -121.37834167480469,
+      "logps/rejected": -125.47262573242188,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.03954017534852028,
+      "rewards/margins": 0.0014026057906448841,
+      "rewards/rejected": -0.040942780673503876,
+      "step": 37
+    },
+    {
+      "epoch": 0.500617538081515,
+      "grad_norm": 0.6856023073196411,
+      "learning_rate": 2.9084434045463254e-07,
+      "logits/chosen": 9.826108932495117,
+      "logits/rejected": 10.918371200561523,
+      "logps/chosen": -107.96115112304688,
+      "logps/ref_chosen": -104.01033782958984,
+      "logps/ref_rejected": -119.02666473388672,
+      "logps/rejected": -123.3695068359375,
+      "loss": 0.6913,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.039508119225502014,
+      "rewards/margins": 0.003920318093150854,
+      "rewards/rejected": -0.043428435921669006,
+      "step": 38
+    },
+    {
+      "epoch": 0.5137916838205022,
+      "grad_norm": 0.5166105628013611,
+      "learning_rate": 2.7923883049302066e-07,
+      "logits/chosen": 10.282295227050781,
+      "logits/rejected": 11.047395706176758,
+      "logps/chosen": -113.61396026611328,
+      "logps/ref_chosen": -109.76485443115234,
+      "logps/ref_rejected": -122.25163269042969,
+      "logps/rejected": -126.30699157714844,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.038491036742925644,
+      "rewards/margins": 0.002062497427687049,
+      "rewards/rejected": -0.040553539991378784,
+      "step": 39
+    },
+    {
+      "epoch": 0.5269658295594895,
+      "grad_norm": 0.7613899111747742,
+      "learning_rate": 2.6756904723632324e-07,
+      "logits/chosen": 10.10784912109375,
+      "logits/rejected": 11.276141166687012,
+      "logps/chosen": -111.32815551757812,
+      "logps/ref_chosen": -107.18782806396484,
+      "logps/ref_rejected": -124.24542236328125,
+      "logps/rejected": -128.5751495361328,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.04140327125787735,
+      "rewards/margins": 0.001893932232633233,
+      "rewards/rejected": -0.04329720139503479,
+      "step": 40
+    },
+    {
+      "epoch": 0.5401399752984768,
+      "grad_norm": 0.5243136882781982,
+      "learning_rate": 2.5586064340081516e-07,
+      "logits/chosen": 10.432905197143555,
+      "logits/rejected": 11.059402465820312,
+      "logps/chosen": -109.8786849975586,
+      "logps/ref_chosen": -106.42051696777344,
+      "logps/ref_rejected": -122.25247192382812,
+      "logps/rejected": -126.91265106201172,
+      "loss": 0.6873,
+      "rewards/accuracies": 0.6171875,
+      "rewards/chosen": -0.034581609070301056,
+      "rewards/margins": 0.012020176276564598,
+      "rewards/rejected": -0.0466017909348011,
+      "step": 41
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": 0.6438937187194824,
+      "learning_rate": 2.4413935659918487e-07,
+      "logits/chosen": 9.422279357910156,
+      "logits/rejected": 10.50160026550293,
+      "logps/chosen": -106.31170654296875,
+      "logps/ref_chosen": -103.1148452758789,
+      "logps/ref_rejected": -116.55464935302734,
+      "logps/rejected": -120.24292755126953,
+      "loss": 0.6908,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.03196856006979942,
+      "rewards/margins": 0.004914162214845419,
+      "rewards/rejected": -0.03688272088766098,
+      "step": 42
+    },
+    {
+      "epoch": 0.5664882667764513,
+      "grad_norm": 0.5491278171539307,
+      "learning_rate": 2.3243095276367684e-07,
+      "logits/chosen": 9.590739250183105,
+      "logits/rejected": 10.710611343383789,
+      "logps/chosen": -107.79342651367188,
+      "logps/ref_chosen": -104.21064758300781,
+      "logps/ref_rejected": -118.7614974975586,
+      "logps/rejected": -122.59417724609375,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.03582778573036194,
+      "rewards/margins": 0.002499072812497616,
+      "rewards/rejected": -0.03832685574889183,
+      "step": 43
+    },
+    {
+      "epoch": 0.5796624125154385,
+      "grad_norm": 0.39058002829551697,
+      "learning_rate": 2.2076116950697937e-07,
+      "logits/chosen": 9.714144706726074,
+      "logits/rejected": 10.525476455688477,
+      "logps/chosen": -104.20186614990234,
+      "logps/ref_chosen": -100.59449005126953,
+      "logps/ref_rejected": -115.95166778564453,
+      "logps/rejected": -120.36408233642578,
+      "loss": 0.6893,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.03607375919818878,
+      "rewards/margins": 0.008050307631492615,
+      "rewards/rejected": -0.044124066829681396,
+      "step": 44
+    },
+    {
+      "epoch": 0.5928365582544257,
+      "grad_norm": 0.49462494254112244,
+      "learning_rate": 2.091556595453674e-07,
+      "logits/chosen": 9.886950492858887,
+      "logits/rejected": 10.70908260345459,
+      "logps/chosen": -110.35658264160156,
+      "logps/ref_chosen": -106.96060943603516,
+      "logps/ref_rejected": -125.49449157714844,
+      "logps/rejected": -129.1283416748047,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.033959683030843735,
+      "rewards/margins": 0.0023788013495504856,
+      "rewards/rejected": -0.03633848577737808,
+      "step": 45
+    },
+    {
+      "epoch": 0.606010703993413,
+      "grad_norm": 0.5809131860733032,
+      "learning_rate": 1.9763993430846392e-07,
+      "logits/chosen": 9.98457145690918,
+      "logits/rejected": 10.643254280090332,
+      "logps/chosen": -110.51849365234375,
+      "logps/ref_chosen": -107.08544158935547,
+      "logps/ref_rejected": -120.38542175292969,
+      "logps/rejected": -124.85211944580078,
+      "loss": 0.6881,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.034330543130636215,
+      "rewards/margins": 0.010336533188819885,
+      "rewards/rejected": -0.0446670763194561,
+      "step": 46
+    },
+    {
+      "epoch": 0.6191848497324002,
+      "grad_norm": 0.6774134039878845,
+      "learning_rate": 1.862393078595809e-07,
+      "logits/chosen": 9.864917755126953,
+      "logits/rejected": 11.103195190429688,
+      "logps/chosen": -109.32252502441406,
+      "logps/ref_chosen": -105.74787902832031,
+      "logps/ref_rejected": -122.93606567382812,
+      "logps/rejected": -126.75948333740234,
+      "loss": 0.692,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.03574639558792114,
+      "rewards/margins": 0.0024877344258129597,
+      "rewards/rejected": -0.038234129548072815,
+      "step": 47
+    },
+    {
+      "epoch": 0.6323589954713874,
+      "grad_norm": 0.6952683925628662,
+      "learning_rate": 1.7497884124991485e-07,
+      "logits/chosen": 10.426509857177734,
+      "logits/rejected": 11.333501815795898,
+      "logps/chosen": -108.989013671875,
+      "logps/ref_chosen": -105.3005599975586,
+      "logps/ref_rejected": -123.93569946289062,
+      "logps/rejected": -127.78026580810547,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.036884430795907974,
+      "rewards/margins": 0.001561243087053299,
+      "rewards/rejected": -0.03844567388296127,
+      "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:a7c6b68742e1dfdea9f9d1d3289819239e7150f3dfee2dfb241d7cf192564cce
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a310a4e09c172055132b12059797ecfd9ed470f01d2b7b9e0fe49ad9e4a3745
+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
+  }
+}