Upload folder using huggingface_hub

added_tokens.json

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

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 0.9880609304240429,
+    "eval_logits/chosen": 9.35390567779541,
+    "eval_logits/rejected": 10.18101692199707,
+    "eval_logps/chosen": -0.37907084822654724,
+    "eval_logps/rejected": -0.3889653980731964,
+    "eval_loss": 1.382422924041748,
+    "eval_rewards/accuracies": 0.5287036895751953,
+    "eval_rewards/chosen": -0.7581416964530945,
+    "eval_rewards/margins": 0.019789105281233788,
+    "eval_rewards/rejected": -0.7779307961463928,
+    "eval_runtime": 152.7821,
+    "eval_samples": 1080,
+    "eval_samples_per_second": 7.069,
+    "eval_steps_per_second": 1.767,
+    "total_flos": 0.0,
+    "train_loss": 1.3895690520604451,
+    "train_runtime": 7857.9562,
+    "train_samples": 9715,
+    "train_samples_per_second": 1.236,
+    "train_steps_per_second": 0.01
+}

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:c029aa0e703f298687e4b5e90e4c3f1341273817a7a638ea9cc006f351b36e14
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714604b4ae0552b0147e18c9d737c0f6dd7f4dbaca43201735a546ec834921bf
+size 2669692552

checkpoint-12/model.safetensors.index.json

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

checkpoint-12/special_tokens_map.json

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

checkpoint-12/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-12/trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.15808974886784685,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.538081705570221,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.038352012634277,
+      "logits/rejected": 10.592904090881348,
+      "logps/chosen": -0.6228358745574951,
+      "logps/rejected": -0.6871199011802673,
+      "loss": 1.342,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -1.2456717491149902,
+      "rewards/margins": 0.12856802344322205,
+      "rewards/rejected": -1.3742398023605347,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.6521235108375549,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.320584297180176,
+      "logits/rejected": 10.721946716308594,
+      "logps/chosen": -0.7115719318389893,
+      "logps/rejected": -0.788784384727478,
+      "loss": 1.3147,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.4231438636779785,
+      "rewards/margins": 0.15442489087581635,
+      "rewards/rejected": -1.577568769454956,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.8797138929367065,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 9.899504661560059,
+      "logits/rejected": 10.505952835083008,
+      "logps/chosen": -0.8225007057189941,
+      "logps/rejected": -0.8832307457923889,
+      "loss": 1.3674,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -1.6450014114379883,
+      "rewards/margins": 0.12146000564098358,
+      "rewards/rejected": -1.7664614915847778,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 1.9139935970306396,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.082985877990723,
+      "logits/rejected": 10.576549530029297,
+      "logps/chosen": -0.6892099976539612,
+      "logps/rejected": -0.7180394530296326,
+      "loss": 1.4038,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.3784199953079224,
+      "rewards/margins": 0.05765870213508606,
+      "rewards/rejected": -1.4360789060592651,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.8647859692573547,
+      "learning_rate": 6.249999999999999e-07,
+      "logits/chosen": 10.318564414978027,
+      "logits/rejected": 11.072587966918945,
+      "logps/chosen": -0.6658570766448975,
+      "logps/rejected": -0.6663312911987305,
+      "loss": 1.4062,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.331714153289795,
+      "rewards/margins": 0.0009482596069574356,
+      "rewards/rejected": -1.332662582397461,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.7906696796417236,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": 10.802580833435059,
+      "logits/rejected": 11.333773612976074,
+      "logps/chosen": -0.7257988452911377,
+      "logps/rejected": -0.7839725017547607,
+      "loss": 1.3781,
+      "rewards/accuracies": 0.6015625,
+      "rewards/chosen": -1.4515976905822754,
+      "rewards/margins": 0.11634734272956848,
+      "rewards/rejected": -1.5679450035095215,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.724219799041748,
+      "learning_rate": 8.75e-07,
+      "logits/chosen": 9.928263664245605,
+      "logits/rejected": 10.422144889831543,
+      "logps/chosen": -0.5926575660705566,
+      "logps/rejected": -0.6688517928123474,
+      "loss": 1.314,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -1.1853151321411133,
+      "rewards/margins": 0.15238842368125916,
+      "rewards/rejected": -1.3377035856246948,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.558660089969635,
+      "learning_rate": 1e-06,
+      "logits/chosen": 10.657012939453125,
+      "logits/rejected": 11.171004295349121,
+      "logps/chosen": -0.6659789681434631,
+      "logps/rejected": -0.7012848258018494,
+      "loss": 1.365,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -1.3319579362869263,
+      "rewards/margins": 0.07061176747083664,
+      "rewards/rejected": -1.4025696516036987,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.7675488591194153,
+      "learning_rate": 9.994504457428556e-07,
+      "logits/chosen": 10.544637680053711,
+      "logits/rejected": 10.839460372924805,
+      "logps/chosen": -0.814159095287323,
+      "logps/rejected": -0.7815468907356262,
+      "loss": 1.4888,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -1.628318190574646,
+      "rewards/margins": -0.0652243047952652,
+      "rewards/rejected": -1.5630937814712524,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 1.1157082319259644,
+      "learning_rate": 9.97802991010949e-07,
+      "logits/chosen": 10.10114574432373,
+      "logits/rejected": 10.555818557739258,
+      "logps/chosen": -0.673196017742157,
+      "logps/rejected": -0.6864349246025085,
+      "loss": 1.4279,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.346392035484314,
+      "rewards/margins": 0.02647773176431656,
+      "rewards/rejected": -1.372869849205017,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 1.2121509313583374,
+      "learning_rate": 9.950612572673255e-07,
+      "logits/chosen": 10.158075332641602,
+      "logits/rejected": 10.813385009765625,
+      "logps/chosen": -0.7734582424163818,
+      "logps/rejected": -0.8254096508026123,
+      "loss": 1.3538,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.5469164848327637,
+      "rewards/margins": 0.10390281677246094,
+      "rewards/rejected": -1.6508193016052246,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.921929657459259,
+      "learning_rate": 9.912312714377879e-07,
+      "logits/chosen": 10.2570161819458,
+      "logits/rejected": 10.633421897888184,
+      "logps/chosen": -0.7107410430908203,
+      "logps/rejected": -0.7390152812004089,
+      "loss": 1.3791,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.4214820861816406,
+      "rewards/margins": 0.056548528373241425,
+      "rewards/rejected": -1.4780305624008179,
+      "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 sha256:4687cf415aee6ada25784317831a2f3da8c4520bb4c264d4107fbca988b8bb82
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9738c06c66837fce5d5992a493765bb5ae9f952e8e1c4c9a4e4da7b9debefb52
+size 2669692552

checkpoint-24/model.safetensors.index.json

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

checkpoint-24/special_tokens_map.json

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

checkpoint-24/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-24/trainer_state.json

@@ -0,0 +1,393 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3161794977356937,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.538081705570221,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.038352012634277,
+      "logits/rejected": 10.592904090881348,
+      "logps/chosen": -0.6228358745574951,
+      "logps/rejected": -0.6871199011802673,
+      "loss": 1.342,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -1.2456717491149902,
+      "rewards/margins": 0.12856802344322205,
+      "rewards/rejected": -1.3742398023605347,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.6521235108375549,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.320584297180176,
+      "logits/rejected": 10.721946716308594,
+      "logps/chosen": -0.7115719318389893,
+      "logps/rejected": -0.788784384727478,
+      "loss": 1.3147,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.4231438636779785,
+      "rewards/margins": 0.15442489087581635,
+      "rewards/rejected": -1.577568769454956,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.8797138929367065,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 9.899504661560059,
+      "logits/rejected": 10.505952835083008,
+      "logps/chosen": -0.8225007057189941,
+      "logps/rejected": -0.8832307457923889,
+      "loss": 1.3674,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -1.6450014114379883,
+      "rewards/margins": 0.12146000564098358,
+      "rewards/rejected": -1.7664614915847778,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 1.9139935970306396,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.082985877990723,
+      "logits/rejected": 10.576549530029297,
+      "logps/chosen": -0.6892099976539612,
+      "logps/rejected": -0.7180394530296326,
+      "loss": 1.4038,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.3784199953079224,
+      "rewards/margins": 0.05765870213508606,
+      "rewards/rejected": -1.4360789060592651,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.8647859692573547,
+      "learning_rate": 6.249999999999999e-07,
+      "logits/chosen": 10.318564414978027,
+      "logits/rejected": 11.072587966918945,
+      "logps/chosen": -0.6658570766448975,
+      "logps/rejected": -0.6663312911987305,
+      "loss": 1.4062,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.331714153289795,
+      "rewards/margins": 0.0009482596069574356,
+      "rewards/rejected": -1.332662582397461,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.7906696796417236,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": 10.802580833435059,
+      "logits/rejected": 11.333773612976074,
+      "logps/chosen": -0.7257988452911377,
+      "logps/rejected": -0.7839725017547607,
+      "loss": 1.3781,
+      "rewards/accuracies": 0.6015625,
+      "rewards/chosen": -1.4515976905822754,
+      "rewards/margins": 0.11634734272956848,
+      "rewards/rejected": -1.5679450035095215,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.724219799041748,
+      "learning_rate": 8.75e-07,
+      "logits/chosen": 9.928263664245605,
+      "logits/rejected": 10.422144889831543,
+      "logps/chosen": -0.5926575660705566,
+      "logps/rejected": -0.6688517928123474,
+      "loss": 1.314,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -1.1853151321411133,
+      "rewards/margins": 0.15238842368125916,
+      "rewards/rejected": -1.3377035856246948,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.558660089969635,
+      "learning_rate": 1e-06,
+      "logits/chosen": 10.657012939453125,
+      "logits/rejected": 11.171004295349121,
+      "logps/chosen": -0.6659789681434631,
+      "logps/rejected": -0.7012848258018494,
+      "loss": 1.365,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -1.3319579362869263,
+      "rewards/margins": 0.07061176747083664,
+      "rewards/rejected": -1.4025696516036987,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.7675488591194153,
+      "learning_rate": 9.994504457428556e-07,
+      "logits/chosen": 10.544637680053711,
+      "logits/rejected": 10.839460372924805,
+      "logps/chosen": -0.814159095287323,
+      "logps/rejected": -0.7815468907356262,
+      "loss": 1.4888,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -1.628318190574646,
+      "rewards/margins": -0.0652243047952652,
+      "rewards/rejected": -1.5630937814712524,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 1.1157082319259644,
+      "learning_rate": 9.97802991010949e-07,
+      "logits/chosen": 10.10114574432373,
+      "logits/rejected": 10.555818557739258,
+      "logps/chosen": -0.673196017742157,
+      "logps/rejected": -0.6864349246025085,
+      "loss": 1.4279,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.346392035484314,
+      "rewards/margins": 0.02647773176431656,
+      "rewards/rejected": -1.372869849205017,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 1.2121509313583374,
+      "learning_rate": 9.950612572673255e-07,
+      "logits/chosen": 10.158075332641602,
+      "logits/rejected": 10.813385009765625,
+      "logps/chosen": -0.7734582424163818,
+      "logps/rejected": -0.8254096508026123,
+      "loss": 1.3538,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.5469164848327637,
+      "rewards/margins": 0.10390281677246094,
+      "rewards/rejected": -1.6508193016052246,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.921929657459259,
+      "learning_rate": 9.912312714377879e-07,
+      "logits/chosen": 10.2570161819458,
+      "logits/rejected": 10.633421897888184,
+      "logps/chosen": -0.7107410430908203,
+      "logps/rejected": -0.7390152812004089,
+      "loss": 1.3791,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.4214820861816406,
+      "rewards/margins": 0.056548528373241425,
+      "rewards/rejected": -1.4780305624008179,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 1.0088778734207153,
+      "learning_rate": 9.863214526624063e-07,
+      "logits/chosen": 9.808923721313477,
+      "logits/rejected": 10.603569984436035,
+      "logps/chosen": -0.7246454954147339,
+      "logps/rejected": -0.8062013387680054,
+      "loss": 1.3588,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -1.4492909908294678,
+      "rewards/margins": 0.1631116420030594,
+      "rewards/rejected": -1.6124026775360107,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 1.2618002891540527,
+      "learning_rate": 9.8034259378842e-07,
+      "logits/chosen": 10.618194580078125,
+      "logits/rejected": 11.330740928649902,
+      "logps/chosen": -0.6871081590652466,
+      "logps/rejected": -0.752004086971283,
+      "loss": 1.3318,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.3742163181304932,
+      "rewards/margins": 0.1297919750213623,
+      "rewards/rejected": -1.504008173942566,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.3426913917064667,
+      "learning_rate": 9.73307837645217e-07,
+      "logits/chosen": 9.945769309997559,
+      "logits/rejected": 10.648375511169434,
+      "logps/chosen": -0.6394751071929932,
+      "logps/rejected": -0.7090991139411926,
+      "loss": 1.3241,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.2789502143859863,
+      "rewards/margins": 0.13924814760684967,
+      "rewards/rejected": -1.4181982278823853,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 1.1439241170883179,
+      "learning_rate": 9.652326481535433e-07,
+      "logits/chosen": 10.895740509033203,
+      "logits/rejected": 11.243146896362305,
+      "logps/chosen": -0.6249470710754395,
+      "logps/rejected": -0.6594743132591248,
+      "loss": 1.3593,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -1.249894142150879,
+      "rewards/margins": 0.06905444711446762,
+      "rewards/rejected": -1.3189486265182495,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.6084972023963928,
+      "learning_rate": 9.561347763324483e-07,
+      "logits/chosen": 10.294602394104004,
+      "logits/rejected": 10.75848388671875,
+      "logps/chosen": -0.6647714972496033,
+      "logps/rejected": -0.6630449891090393,
+      "loss": 1.4144,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.3295429944992065,
+      "rewards/margins": -0.0034531853161752224,
+      "rewards/rejected": -1.3260899782180786,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 1.20784330368042,
+      "learning_rate": 9.460342212786932e-07,
+      "logits/chosen": 10.368552207946777,
+      "logits/rejected": 11.025596618652344,
+      "logps/chosen": -0.8019055724143982,
+      "logps/rejected": -0.7324545979499817,
+      "loss": 1.5474,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -1.6038111448287964,
+      "rewards/margins": -0.13890185952186584,
+      "rewards/rejected": -1.4649091958999634,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.6674954891204834,
+      "learning_rate": 9.349531862043951e-07,
+      "logits/chosen": 10.525771141052246,
+      "logits/rejected": 10.864877700805664,
+      "logps/chosen": -0.6636431217193604,
+      "logps/rejected": -0.690964937210083,
+      "loss": 1.3837,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -1.3272862434387207,
+      "rewards/margins": 0.05464361608028412,
+      "rewards/rejected": -1.381929874420166,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.9430455565452576,
+      "learning_rate": 9.229160296295487e-07,
+      "logits/chosen": 10.509737014770508,
+      "logits/rejected": 11.218311309814453,
+      "logps/chosen": -0.7572717666625977,
+      "logps/rejected": -0.7445338368415833,
+      "loss": 1.4599,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.5145435333251953,
+      "rewards/margins": -0.02547581121325493,
+      "rewards/rejected": -1.4890676736831665,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.5352253317832947,
+      "learning_rate": 9.099492118367122e-07,
+      "logits/chosen": 9.723971366882324,
+      "logits/rejected": 10.554994583129883,
+      "logps/chosen": -0.706066906452179,
+      "logps/rejected": -0.7981133460998535,
+      "loss": 1.3079,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.412133812904358,
+      "rewards/margins": 0.18409286439418793,
+      "rewards/rejected": -1.596226692199707,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 1.4943097829818726,
+      "learning_rate": 8.960812367055646e-07,
+      "logits/chosen": 10.025705337524414,
+      "logits/rejected": 10.595457077026367,
+      "logps/chosen": -0.7785383462905884,
+      "logps/rejected": -0.7879722118377686,
+      "loss": 1.4168,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.5570766925811768,
+      "rewards/margins": 0.01886790432035923,
+      "rewards/rejected": -1.575944423675537,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4453490972518921,
+      "learning_rate": 8.813425890551909e-07,
+      "logits/chosen": 10.01511001586914,
+      "logits/rejected": 10.817825317382812,
+      "logps/chosen": -0.7974975109100342,
+      "logps/rejected": -0.7531540393829346,
+      "loss": 1.5107,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -1.5949950218200684,
+      "rewards/margins": -0.08868695795536041,
+      "rewards/rejected": -1.5063080787658691,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.8292773962020874,
+      "learning_rate": 8.657656676318345e-07,
+      "logits/chosen": 10.253622055053711,
+      "logits/rejected": 10.707040786743164,
+      "logps/chosen": -0.6545951962471008,
+      "logps/rejected": -0.6871030330657959,
+      "loss": 1.3837,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.3091903924942017,
+      "rewards/margins": 0.06501554697751999,
+      "rewards/rejected": -1.3742060661315918,
+      "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 sha256:6e0c71c2ff58f2960595e73dc0e7cd4f1fe4f993865d884d9433aa1bae32a39a
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e35caf2c96315d9710759918a1f4d1776f48bc7adadde118a3209465ff4893
+size 2669692552

checkpoint-36/model.safetensors.index.json

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

checkpoint-36/special_tokens_map.json

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

checkpoint-36/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-36/trainer_state.json

@@ -0,0 +1,573 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.47426924660354053,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.538081705570221,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.038352012634277,
+      "logits/rejected": 10.592904090881348,
+      "logps/chosen": -0.6228358745574951,
+      "logps/rejected": -0.6871199011802673,
+      "loss": 1.342,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -1.2456717491149902,
+      "rewards/margins": 0.12856802344322205,
+      "rewards/rejected": -1.3742398023605347,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.6521235108375549,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.320584297180176,
+      "logits/rejected": 10.721946716308594,
+      "logps/chosen": -0.7115719318389893,
+      "logps/rejected": -0.788784384727478,
+      "loss": 1.3147,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.4231438636779785,
+      "rewards/margins": 0.15442489087581635,
+      "rewards/rejected": -1.577568769454956,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.8797138929367065,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 9.899504661560059,
+      "logits/rejected": 10.505952835083008,
+      "logps/chosen": -0.8225007057189941,
+      "logps/rejected": -0.8832307457923889,
+      "loss": 1.3674,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -1.6450014114379883,
+      "rewards/margins": 0.12146000564098358,
+      "rewards/rejected": -1.7664614915847778,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 1.9139935970306396,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.082985877990723,
+      "logits/rejected": 10.576549530029297,
+      "logps/chosen": -0.6892099976539612,
+      "logps/rejected": -0.7180394530296326,
+      "loss": 1.4038,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.3784199953079224,
+      "rewards/margins": 0.05765870213508606,
+      "rewards/rejected": -1.4360789060592651,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.8647859692573547,
+      "learning_rate": 6.249999999999999e-07,
+      "logits/chosen": 10.318564414978027,
+      "logits/rejected": 11.072587966918945,
+      "logps/chosen": -0.6658570766448975,
+      "logps/rejected": -0.6663312911987305,
+      "loss": 1.4062,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.331714153289795,
+      "rewards/margins": 0.0009482596069574356,
+      "rewards/rejected": -1.332662582397461,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.7906696796417236,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": 10.802580833435059,
+      "logits/rejected": 11.333773612976074,
+      "logps/chosen": -0.7257988452911377,
+      "logps/rejected": -0.7839725017547607,
+      "loss": 1.3781,
+      "rewards/accuracies": 0.6015625,
+      "rewards/chosen": -1.4515976905822754,
+      "rewards/margins": 0.11634734272956848,
+      "rewards/rejected": -1.5679450035095215,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.724219799041748,
+      "learning_rate": 8.75e-07,
+      "logits/chosen": 9.928263664245605,
+      "logits/rejected": 10.422144889831543,
+      "logps/chosen": -0.5926575660705566,
+      "logps/rejected": -0.6688517928123474,
+      "loss": 1.314,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -1.1853151321411133,
+      "rewards/margins": 0.15238842368125916,
+      "rewards/rejected": -1.3377035856246948,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.558660089969635,
+      "learning_rate": 1e-06,
+      "logits/chosen": 10.657012939453125,
+      "logits/rejected": 11.171004295349121,
+      "logps/chosen": -0.6659789681434631,
+      "logps/rejected": -0.7012848258018494,
+      "loss": 1.365,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -1.3319579362869263,
+      "rewards/margins": 0.07061176747083664,
+      "rewards/rejected": -1.4025696516036987,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.7675488591194153,
+      "learning_rate": 9.994504457428556e-07,
+      "logits/chosen": 10.544637680053711,
+      "logits/rejected": 10.839460372924805,
+      "logps/chosen": -0.814159095287323,
+      "logps/rejected": -0.7815468907356262,
+      "loss": 1.4888,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -1.628318190574646,
+      "rewards/margins": -0.0652243047952652,
+      "rewards/rejected": -1.5630937814712524,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 1.1157082319259644,
+      "learning_rate": 9.97802991010949e-07,
+      "logits/chosen": 10.10114574432373,
+      "logits/rejected": 10.555818557739258,
+      "logps/chosen": -0.673196017742157,
+      "logps/rejected": -0.6864349246025085,
+      "loss": 1.4279,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.346392035484314,
+      "rewards/margins": 0.02647773176431656,
+      "rewards/rejected": -1.372869849205017,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 1.2121509313583374,
+      "learning_rate": 9.950612572673255e-07,
+      "logits/chosen": 10.158075332641602,
+      "logits/rejected": 10.813385009765625,
+      "logps/chosen": -0.7734582424163818,
+      "logps/rejected": -0.8254096508026123,
+      "loss": 1.3538,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.5469164848327637,
+      "rewards/margins": 0.10390281677246094,
+      "rewards/rejected": -1.6508193016052246,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.921929657459259,
+      "learning_rate": 9.912312714377879e-07,
+      "logits/chosen": 10.2570161819458,
+      "logits/rejected": 10.633421897888184,
+      "logps/chosen": -0.7107410430908203,
+      "logps/rejected": -0.7390152812004089,
+      "loss": 1.3791,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.4214820861816406,
+      "rewards/margins": 0.056548528373241425,
+      "rewards/rejected": -1.4780305624008179,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 1.0088778734207153,
+      "learning_rate": 9.863214526624063e-07,
+      "logits/chosen": 9.808923721313477,
+      "logits/rejected": 10.603569984436035,
+      "logps/chosen": -0.7246454954147339,
+      "logps/rejected": -0.8062013387680054,
+      "loss": 1.3588,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -1.4492909908294678,
+      "rewards/margins": 0.1631116420030594,
+      "rewards/rejected": -1.6124026775360107,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 1.2618002891540527,
+      "learning_rate": 9.8034259378842e-07,
+      "logits/chosen": 10.618194580078125,
+      "logits/rejected": 11.330740928649902,
+      "logps/chosen": -0.6871081590652466,
+      "logps/rejected": -0.752004086971283,
+      "loss": 1.3318,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.3742163181304932,
+      "rewards/margins": 0.1297919750213623,
+      "rewards/rejected": -1.504008173942566,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.3426913917064667,
+      "learning_rate": 9.73307837645217e-07,
+      "logits/chosen": 9.945769309997559,
+      "logits/rejected": 10.648375511169434,
+      "logps/chosen": -0.6394751071929932,
+      "logps/rejected": -0.7090991139411926,
+      "loss": 1.3241,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.2789502143859863,
+      "rewards/margins": 0.13924814760684967,
+      "rewards/rejected": -1.4181982278823853,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 1.1439241170883179,
+      "learning_rate": 9.652326481535433e-07,
+      "logits/chosen": 10.895740509033203,
+      "logits/rejected": 11.243146896362305,
+      "logps/chosen": -0.6249470710754395,
+      "logps/rejected": -0.6594743132591248,
+      "loss": 1.3593,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -1.249894142150879,
+      "rewards/margins": 0.06905444711446762,
+      "rewards/rejected": -1.3189486265182495,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.6084972023963928,
+      "learning_rate": 9.561347763324483e-07,
+      "logits/chosen": 10.294602394104004,
+      "logits/rejected": 10.75848388671875,
+      "logps/chosen": -0.6647714972496033,
+      "logps/rejected": -0.6630449891090393,
+      "loss": 1.4144,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.3295429944992065,
+      "rewards/margins": -0.0034531853161752224,
+      "rewards/rejected": -1.3260899782180786,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 1.20784330368042,
+      "learning_rate": 9.460342212786932e-07,
+      "logits/chosen": 10.368552207946777,
+      "logits/rejected": 11.025596618652344,
+      "logps/chosen": -0.8019055724143982,
+      "logps/rejected": -0.7324545979499817,
+      "loss": 1.5474,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -1.6038111448287964,
+      "rewards/margins": -0.13890185952186584,
+      "rewards/rejected": -1.4649091958999634,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.6674954891204834,
+      "learning_rate": 9.349531862043951e-07,
+      "logits/chosen": 10.525771141052246,
+      "logits/rejected": 10.864877700805664,
+      "logps/chosen": -0.6636431217193604,
+      "logps/rejected": -0.690964937210083,
+      "loss": 1.3837,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -1.3272862434387207,
+      "rewards/margins": 0.05464361608028412,
+      "rewards/rejected": -1.381929874420166,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.9430455565452576,
+      "learning_rate": 9.229160296295487e-07,
+      "logits/chosen": 10.509737014770508,
+      "logits/rejected": 11.218311309814453,
+      "logps/chosen": -0.7572717666625977,
+      "logps/rejected": -0.7445338368415833,
+      "loss": 1.4599,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.5145435333251953,
+      "rewards/margins": -0.02547581121325493,
+      "rewards/rejected": -1.4890676736831665,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.5352253317832947,
+      "learning_rate": 9.099492118367122e-07,
+      "logits/chosen": 9.723971366882324,
+      "logits/rejected": 10.554994583129883,
+      "logps/chosen": -0.706066906452179,
+      "logps/rejected": -0.7981133460998535,
+      "loss": 1.3079,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.412133812904358,
+      "rewards/margins": 0.18409286439418793,
+      "rewards/rejected": -1.596226692199707,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 1.4943097829818726,
+      "learning_rate": 8.960812367055646e-07,
+      "logits/chosen": 10.025705337524414,
+      "logits/rejected": 10.595457077026367,
+      "logps/chosen": -0.7785383462905884,
+      "logps/rejected": -0.7879722118377686,
+      "loss": 1.4168,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.5570766925811768,
+      "rewards/margins": 0.01886790432035923,
+      "rewards/rejected": -1.575944423675537,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4453490972518921,
+      "learning_rate": 8.813425890551909e-07,
+      "logits/chosen": 10.01511001586914,
+      "logits/rejected": 10.817825317382812,
+      "logps/chosen": -0.7974975109100342,
+      "logps/rejected": -0.7531540393829346,
+      "loss": 1.5107,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -1.5949950218200684,
+      "rewards/margins": -0.08868695795536041,
+      "rewards/rejected": -1.5063080787658691,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.8292773962020874,
+      "learning_rate": 8.657656676318345e-07,
+      "logits/chosen": 10.253622055053711,
+      "logits/rejected": 10.707040786743164,
+      "logps/chosen": -0.6545951962471008,
+      "logps/rejected": -0.6871030330657959,
+      "loss": 1.3837,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.3091903924942017,
+      "rewards/margins": 0.06501554697751999,
+      "rewards/rejected": -1.3742060661315918,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 3.5230870246887207,
+      "learning_rate": 8.493847138894208e-07,
+      "logits/chosen": 10.166427612304688,
+      "logits/rejected": 10.720212936401367,
+      "logps/chosen": -0.6964614391326904,
+      "logps/rejected": -0.7443124055862427,
+      "loss": 1.3755,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.3929228782653809,
+      "rewards/margins": 0.09570197016000748,
+      "rewards/rejected": -1.4886248111724854,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 1.1598762273788452,
+      "learning_rate": 8.322357367194108e-07,
+      "logits/chosen": 10.49393367767334,
+      "logits/rejected": 11.039409637451172,
+      "logps/chosen": -0.7815979719161987,
+      "logps/rejected": -0.8116061687469482,
+      "loss": 1.3981,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.5631959438323975,
+      "rewards/margins": 0.06001615524291992,
+      "rewards/rejected": -1.6232123374938965,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 2.6781487464904785,
+      "learning_rate": 8.143564332954425e-07,
+      "logits/chosen": 10.239036560058594,
+      "logits/rejected": 11.069831848144531,
+      "logps/chosen": -0.7489575147628784,
+      "logps/rejected": -0.7497468590736389,
+      "loss": 1.4293,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -1.4979150295257568,
+      "rewards/margins": 0.0015787146985530853,
+      "rewards/rejected": -1.4994937181472778,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.4053559899330139,
+      "learning_rate": 7.957861062067612e-07,
+      "logits/chosen": 9.529670715332031,
+      "logits/rejected": 10.38549518585205,
+      "logps/chosen": -0.7035645246505737,
+      "logps/rejected": -0.7123870253562927,
+      "loss": 1.4258,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.4071290493011475,
+      "rewards/margins": 0.017645111307501793,
+      "rewards/rejected": -1.4247740507125854,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.6468765735626221,
+      "learning_rate": 7.765655770625996e-07,
+      "logits/chosen": 10.515686988830566,
+      "logits/rejected": 10.88726806640625,
+      "logps/chosen": -0.6611747145652771,
+      "logps/rejected": -0.7040727734565735,
+      "loss": 1.368,
+      "rewards/accuracies": 0.6328125,
+      "rewards/chosen": -1.3223494291305542,
+      "rewards/margins": 0.08579609543085098,
+      "rewards/rejected": -1.408145546913147,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.6986653208732605,
+      "learning_rate": 7.567370967574209e-07,
+      "logits/chosen": 10.111821174621582,
+      "logits/rejected": 11.31137466430664,
+      "logps/chosen": -0.6936085820198059,
+      "logps/rejected": -0.6943917274475098,
+      "loss": 1.4297,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -1.3872171640396118,
+      "rewards/margins": 0.0015661753714084625,
+      "rewards/rejected": -1.3887834548950195,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.4217478334903717,
+      "learning_rate": 7.363442525942826e-07,
+      "logits/chosen": 9.911711692810059,
+      "logits/rejected": 10.704763412475586,
+      "logps/chosen": -0.6641364097595215,
+      "logps/rejected": -0.6581347584724426,
+      "loss": 1.4344,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.328272819519043,
+      "rewards/margins": -0.012003323063254356,
+      "rewards/rejected": -1.3162695169448853,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.6227706670761108,
+      "learning_rate": 7.154318724704851e-07,
+      "logits/chosen": 9.962979316711426,
+      "logits/rejected": 10.975818634033203,
+      "logps/chosen": -0.6416503190994263,
+      "logps/rejected": -0.6450206637382507,
+      "loss": 1.4274,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -1.2833006381988525,
+      "rewards/margins": 0.006740846671164036,
+      "rewards/rejected": -1.2900413274765015,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 0.9526137709617615,
+      "learning_rate": 6.940459263361248e-07,
+      "logits/chosen": 10.01764965057373,
+      "logits/rejected": 10.877232551574707,
+      "logps/chosen": -0.7044752836227417,
+      "logps/rejected": -0.6560808420181274,
+      "loss": 1.5103,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -1.4089505672454834,
+      "rewards/margins": -0.09678899496793747,
+      "rewards/rejected": -1.3121616840362549,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.7180893421173096,
+      "learning_rate": 6.722334251421664e-07,
+      "logits/chosen": 9.873922348022461,
+      "logits/rejected": 10.598325729370117,
+      "logps/chosen": -0.7634012699127197,
+      "logps/rejected": -0.7632129192352295,
+      "loss": 1.4281,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -1.5268025398254395,
+      "rewards/margins": -0.00037665292620658875,
+      "rewards/rejected": -1.526425838470459,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 1.9519481658935547,
+      "learning_rate": 6.500423175001703e-07,
+      "logits/chosen": 10.66737174987793,
+      "logits/rejected": 11.170511245727539,
+      "logps/chosen": -0.7307225465774536,
+      "logps/rejected": -0.7907586097717285,
+      "loss": 1.3918,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -1.4614450931549072,
+      "rewards/margins": 0.12007206678390503,
+      "rewards/rejected": -1.581517219543457,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.7991163730621338,
+      "learning_rate": 6.275213842808382e-07,
+      "logits/chosen": 10.241875648498535,
+      "logits/rejected": 10.639405250549316,
+      "logps/chosen": -0.6178256869316101,
+      "logps/rejected": -0.6322227120399475,
+      "loss": 1.3976,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -1.2356513738632202,
+      "rewards/margins": 0.028794117271900177,
+      "rewards/rejected": -1.264445424079895,
+      "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:f401a8ca155f8f815cc3297414409f59ddddff9c24a822423e57ec3bbd49257e
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079f213c88eedc5979b242c2bb581319755a2b82d8441348338e8c685c30359b
+size 2669692552

checkpoint-48/model.safetensors.index.json

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

checkpoint-48/special_tokens_map.json

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

checkpoint-48/tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-48/trainer_state.json

@@ -0,0 +1,753 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6323589954713874,
+  "eval_steps": 500,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.538081705570221,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.038352012634277,
+      "logits/rejected": 10.592904090881348,
+      "logps/chosen": -0.6228358745574951,
+      "logps/rejected": -0.6871199011802673,
+      "loss": 1.342,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -1.2456717491149902,
+      "rewards/margins": 0.12856802344322205,
+      "rewards/rejected": -1.3742398023605347,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.6521235108375549,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.320584297180176,
+      "logits/rejected": 10.721946716308594,
+      "logps/chosen": -0.7115719318389893,
+      "logps/rejected": -0.788784384727478,
+      "loss": 1.3147,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.4231438636779785,
+      "rewards/margins": 0.15442489087581635,
+      "rewards/rejected": -1.577568769454956,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.8797138929367065,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 9.899504661560059,
+      "logits/rejected": 10.505952835083008,
+      "logps/chosen": -0.8225007057189941,
+      "logps/rejected": -0.8832307457923889,
+      "loss": 1.3674,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -1.6450014114379883,
+      "rewards/margins": 0.12146000564098358,
+      "rewards/rejected": -1.7664614915847778,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 1.9139935970306396,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.082985877990723,
+      "logits/rejected": 10.576549530029297,
+      "logps/chosen": -0.6892099976539612,
+      "logps/rejected": -0.7180394530296326,
+      "loss": 1.4038,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.3784199953079224,
+      "rewards/margins": 0.05765870213508606,
+      "rewards/rejected": -1.4360789060592651,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.8647859692573547,
+      "learning_rate": 6.249999999999999e-07,
+      "logits/chosen": 10.318564414978027,
+      "logits/rejected": 11.072587966918945,
+      "logps/chosen": -0.6658570766448975,
+      "logps/rejected": -0.6663312911987305,
+      "loss": 1.4062,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.331714153289795,
+      "rewards/margins": 0.0009482596069574356,
+      "rewards/rejected": -1.332662582397461,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.7906696796417236,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": 10.802580833435059,
+      "logits/rejected": 11.333773612976074,
+      "logps/chosen": -0.7257988452911377,
+      "logps/rejected": -0.7839725017547607,
+      "loss": 1.3781,
+      "rewards/accuracies": 0.6015625,
+      "rewards/chosen": -1.4515976905822754,
+      "rewards/margins": 0.11634734272956848,
+      "rewards/rejected": -1.5679450035095215,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.724219799041748,
+      "learning_rate": 8.75e-07,
+      "logits/chosen": 9.928263664245605,
+      "logits/rejected": 10.422144889831543,
+      "logps/chosen": -0.5926575660705566,
+      "logps/rejected": -0.6688517928123474,
+      "loss": 1.314,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -1.1853151321411133,
+      "rewards/margins": 0.15238842368125916,
+      "rewards/rejected": -1.3377035856246948,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.558660089969635,
+      "learning_rate": 1e-06,
+      "logits/chosen": 10.657012939453125,
+      "logits/rejected": 11.171004295349121,
+      "logps/chosen": -0.6659789681434631,
+      "logps/rejected": -0.7012848258018494,
+      "loss": 1.365,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -1.3319579362869263,
+      "rewards/margins": 0.07061176747083664,
+      "rewards/rejected": -1.4025696516036987,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.7675488591194153,
+      "learning_rate": 9.994504457428556e-07,
+      "logits/chosen": 10.544637680053711,
+      "logits/rejected": 10.839460372924805,
+      "logps/chosen": -0.814159095287323,
+      "logps/rejected": -0.7815468907356262,
+      "loss": 1.4888,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -1.628318190574646,
+      "rewards/margins": -0.0652243047952652,
+      "rewards/rejected": -1.5630937814712524,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 1.1157082319259644,
+      "learning_rate": 9.97802991010949e-07,
+      "logits/chosen": 10.10114574432373,
+      "logits/rejected": 10.555818557739258,
+      "logps/chosen": -0.673196017742157,
+      "logps/rejected": -0.6864349246025085,
+      "loss": 1.4279,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.346392035484314,
+      "rewards/margins": 0.02647773176431656,
+      "rewards/rejected": -1.372869849205017,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 1.2121509313583374,
+      "learning_rate": 9.950612572673255e-07,
+      "logits/chosen": 10.158075332641602,
+      "logits/rejected": 10.813385009765625,
+      "logps/chosen": -0.7734582424163818,
+      "logps/rejected": -0.8254096508026123,
+      "loss": 1.3538,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.5469164848327637,
+      "rewards/margins": 0.10390281677246094,
+      "rewards/rejected": -1.6508193016052246,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.921929657459259,
+      "learning_rate": 9.912312714377879e-07,
+      "logits/chosen": 10.2570161819458,
+      "logits/rejected": 10.633421897888184,
+      "logps/chosen": -0.7107410430908203,
+      "logps/rejected": -0.7390152812004089,
+      "loss": 1.3791,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.4214820861816406,
+      "rewards/margins": 0.056548528373241425,
+      "rewards/rejected": -1.4780305624008179,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 1.0088778734207153,
+      "learning_rate": 9.863214526624063e-07,
+      "logits/chosen": 9.808923721313477,
+      "logits/rejected": 10.603569984436035,
+      "logps/chosen": -0.7246454954147339,
+      "logps/rejected": -0.8062013387680054,
+      "loss": 1.3588,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -1.4492909908294678,
+      "rewards/margins": 0.1631116420030594,
+      "rewards/rejected": -1.6124026775360107,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 1.2618002891540527,
+      "learning_rate": 9.8034259378842e-07,
+      "logits/chosen": 10.618194580078125,
+      "logits/rejected": 11.330740928649902,
+      "logps/chosen": -0.6871081590652466,
+      "logps/rejected": -0.752004086971283,
+      "loss": 1.3318,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": -1.3742163181304932,
+      "rewards/margins": 0.1297919750213623,
+      "rewards/rejected": -1.504008173942566,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.3426913917064667,
+      "learning_rate": 9.73307837645217e-07,
+      "logits/chosen": 9.945769309997559,
+      "logits/rejected": 10.648375511169434,
+      "logps/chosen": -0.6394751071929932,
+      "logps/rejected": -0.7090991139411926,
+      "loss": 1.3241,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.2789502143859863,
+      "rewards/margins": 0.13924814760684967,
+      "rewards/rejected": -1.4181982278823853,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 1.1439241170883179,
+      "learning_rate": 9.652326481535433e-07,
+      "logits/chosen": 10.895740509033203,
+      "logits/rejected": 11.243146896362305,
+      "logps/chosen": -0.6249470710754395,
+      "logps/rejected": -0.6594743132591248,
+      "loss": 1.3593,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -1.249894142150879,
+      "rewards/margins": 0.06905444711446762,
+      "rewards/rejected": -1.3189486265182495,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.6084972023963928,
+      "learning_rate": 9.561347763324483e-07,
+      "logits/chosen": 10.294602394104004,
+      "logits/rejected": 10.75848388671875,
+      "logps/chosen": -0.6647714972496033,
+      "logps/rejected": -0.6630449891090393,
+      "loss": 1.4144,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.3295429944992065,
+      "rewards/margins": -0.0034531853161752224,
+      "rewards/rejected": -1.3260899782180786,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 1.20784330368042,
+      "learning_rate": 9.460342212786932e-07,
+      "logits/chosen": 10.368552207946777,
+      "logits/rejected": 11.025596618652344,
+      "logps/chosen": -0.8019055724143982,
+      "logps/rejected": -0.7324545979499817,
+      "loss": 1.5474,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -1.6038111448287964,
+      "rewards/margins": -0.13890185952186584,
+      "rewards/rejected": -1.4649091958999634,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.6674954891204834,
+      "learning_rate": 9.349531862043951e-07,
+      "logits/chosen": 10.525771141052246,
+      "logits/rejected": 10.864877700805664,
+      "logps/chosen": -0.6636431217193604,
+      "logps/rejected": -0.690964937210083,
+      "loss": 1.3837,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -1.3272862434387207,
+      "rewards/margins": 0.05464361608028412,
+      "rewards/rejected": -1.381929874420166,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.9430455565452576,
+      "learning_rate": 9.229160296295487e-07,
+      "logits/chosen": 10.509737014770508,
+      "logits/rejected": 11.218311309814453,
+      "logps/chosen": -0.7572717666625977,
+      "logps/rejected": -0.7445338368415833,
+      "loss": 1.4599,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.5145435333251953,
+      "rewards/margins": -0.02547581121325493,
+      "rewards/rejected": -1.4890676736831665,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.5352253317832947,
+      "learning_rate": 9.099492118367122e-07,
+      "logits/chosen": 9.723971366882324,
+      "logits/rejected": 10.554994583129883,
+      "logps/chosen": -0.706066906452179,
+      "logps/rejected": -0.7981133460998535,
+      "loss": 1.3079,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.412133812904358,
+      "rewards/margins": 0.18409286439418793,
+      "rewards/rejected": -1.596226692199707,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 1.4943097829818726,
+      "learning_rate": 8.960812367055646e-07,
+      "logits/chosen": 10.025705337524414,
+      "logits/rejected": 10.595457077026367,
+      "logps/chosen": -0.7785383462905884,
+      "logps/rejected": -0.7879722118377686,
+      "loss": 1.4168,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.5570766925811768,
+      "rewards/margins": 0.01886790432035923,
+      "rewards/rejected": -1.575944423675537,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4453490972518921,
+      "learning_rate": 8.813425890551909e-07,
+      "logits/chosen": 10.01511001586914,
+      "logits/rejected": 10.817825317382812,
+      "logps/chosen": -0.7974975109100342,
+      "logps/rejected": -0.7531540393829346,
+      "loss": 1.5107,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -1.5949950218200684,
+      "rewards/margins": -0.08868695795536041,
+      "rewards/rejected": -1.5063080787658691,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.8292773962020874,
+      "learning_rate": 8.657656676318345e-07,
+      "logits/chosen": 10.253622055053711,
+      "logits/rejected": 10.707040786743164,
+      "logps/chosen": -0.6545951962471008,
+      "logps/rejected": -0.6871030330657959,
+      "loss": 1.3837,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.3091903924942017,
+      "rewards/margins": 0.06501554697751999,
+      "rewards/rejected": -1.3742060661315918,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 3.5230870246887207,
+      "learning_rate": 8.493847138894208e-07,
+      "logits/chosen": 10.166427612304688,
+      "logits/rejected": 10.720212936401367,
+      "logps/chosen": -0.6964614391326904,
+      "logps/rejected": -0.7443124055862427,
+      "loss": 1.3755,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -1.3929228782653809,
+      "rewards/margins": 0.09570197016000748,
+      "rewards/rejected": -1.4886248111724854,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 1.1598762273788452,
+      "learning_rate": 8.322357367194108e-07,
+      "logits/chosen": 10.49393367767334,
+      "logits/rejected": 11.039409637451172,
+      "logps/chosen": -0.7815979719161987,
+      "logps/rejected": -0.8116061687469482,
+      "loss": 1.3981,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -1.5631959438323975,
+      "rewards/margins": 0.06001615524291992,
+      "rewards/rejected": -1.6232123374938965,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 2.6781487464904785,
+      "learning_rate": 8.143564332954425e-07,
+      "logits/chosen": 10.239036560058594,
+      "logits/rejected": 11.069831848144531,
+      "logps/chosen": -0.7489575147628784,
+      "logps/rejected": -0.7497468590736389,
+      "loss": 1.4293,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -1.4979150295257568,
+      "rewards/margins": 0.0015787146985530853,
+      "rewards/rejected": -1.4994937181472778,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.4053559899330139,
+      "learning_rate": 7.957861062067612e-07,
+      "logits/chosen": 9.529670715332031,
+      "logits/rejected": 10.38549518585205,
+      "logps/chosen": -0.7035645246505737,
+      "logps/rejected": -0.7123870253562927,
+      "loss": 1.4258,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.4071290493011475,
+      "rewards/margins": 0.017645111307501793,
+      "rewards/rejected": -1.4247740507125854,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.6468765735626221,
+      "learning_rate": 7.765655770625996e-07,
+      "logits/chosen": 10.515686988830566,
+      "logits/rejected": 10.88726806640625,
+      "logps/chosen": -0.6611747145652771,
+      "logps/rejected": -0.7040727734565735,
+      "loss": 1.368,
+      "rewards/accuracies": 0.6328125,
+      "rewards/chosen": -1.3223494291305542,
+      "rewards/margins": 0.08579609543085098,
+      "rewards/rejected": -1.408145546913147,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.6986653208732605,
+      "learning_rate": 7.567370967574209e-07,
+      "logits/chosen": 10.111821174621582,
+      "logits/rejected": 11.31137466430664,
+      "logps/chosen": -0.6936085820198059,
+      "logps/rejected": -0.6943917274475098,
+      "loss": 1.4297,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -1.3872171640396118,
+      "rewards/margins": 0.0015661753714084625,
+      "rewards/rejected": -1.3887834548950195,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.4217478334903717,
+      "learning_rate": 7.363442525942826e-07,
+      "logits/chosen": 9.911711692810059,
+      "logits/rejected": 10.704763412475586,
+      "logps/chosen": -0.6641364097595215,
+      "logps/rejected": -0.6581347584724426,
+      "loss": 1.4344,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -1.328272819519043,
+      "rewards/margins": -0.012003323063254356,
+      "rewards/rejected": -1.3162695169448853,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.6227706670761108,
+      "learning_rate": 7.154318724704851e-07,
+      "logits/chosen": 9.962979316711426,
+      "logits/rejected": 10.975818634033203,
+      "logps/chosen": -0.6416503190994263,
+      "logps/rejected": -0.6450206637382507,
+      "loss": 1.4274,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -1.2833006381988525,
+      "rewards/margins": 0.006740846671164036,
+      "rewards/rejected": -1.2900413274765015,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 0.9526137709617615,
+      "learning_rate": 6.940459263361248e-07,
+      "logits/chosen": 10.01764965057373,
+      "logits/rejected": 10.877232551574707,
+      "logps/chosen": -0.7044752836227417,
+      "logps/rejected": -0.6560808420181274,
+      "loss": 1.5103,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -1.4089505672454834,
+      "rewards/margins": -0.09678899496793747,
+      "rewards/rejected": -1.3121616840362549,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.7180893421173096,
+      "learning_rate": 6.722334251421664e-07,
+      "logits/chosen": 9.873922348022461,
+      "logits/rejected": 10.598325729370117,
+      "logps/chosen": -0.7634012699127197,
+      "logps/rejected": -0.7632129192352295,
+      "loss": 1.4281,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -1.5268025398254395,
+      "rewards/margins": -0.00037665292620658875,
+      "rewards/rejected": -1.526425838470459,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 1.9519481658935547,
+      "learning_rate": 6.500423175001703e-07,
+      "logits/chosen": 10.66737174987793,
+      "logits/rejected": 11.170511245727539,
+      "logps/chosen": -0.7307225465774536,
+      "logps/rejected": -0.7907586097717285,
+      "loss": 1.3918,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -1.4614450931549072,
+      "rewards/margins": 0.12007206678390503,
+      "rewards/rejected": -1.581517219543457,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.7991163730621338,
+      "learning_rate": 6.275213842808382e-07,
+      "logits/chosen": 10.241875648498535,
+      "logits/rejected": 10.639405250549316,
+      "logps/chosen": -0.6178256869316101,
+      "logps/rejected": -0.6322227120399475,
+      "loss": 1.3976,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -1.2356513738632202,
+      "rewards/margins": 0.028794117271900177,
+      "rewards/rejected": -1.264445424079895,
+      "step": 36
+    },
+    {
+      "epoch": 0.4874433923425278,
+      "grad_norm": 0.6113852262496948,
+      "learning_rate": 6.047201313830723e-07,
+      "logits/chosen": 10.230165481567383,
+      "logits/rejected": 10.763371467590332,
+      "logps/chosen": -0.6862261295318604,
+      "logps/rejected": -0.7486332654953003,
+      "loss": 1.3326,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -1.3724522590637207,
+      "rewards/margins": 0.12481416761875153,
+      "rewards/rejected": -1.4972665309906006,
+      "step": 37
+    },
+    {
+      "epoch": 0.500617538081515,
+      "grad_norm": 1.0607084035873413,
+      "learning_rate": 5.816886809092651e-07,
+      "logits/chosen": 10.049585342407227,
+      "logits/rejected": 10.759794235229492,
+      "logps/chosen": -0.6145029067993164,
+      "logps/rejected": -0.6638337969779968,
+      "loss": 1.3483,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -1.2290058135986328,
+      "rewards/margins": 0.0986616313457489,
+      "rewards/rejected": -1.3276675939559937,
+      "step": 38
+    },
+    {
+      "epoch": 0.5137916838205022,
+      "grad_norm": 1.5060722827911377,
+      "learning_rate": 5.584776609860413e-07,
+      "logits/chosen": 10.381738662719727,
+      "logits/rejected": 10.864119529724121,
+      "logps/chosen": -0.7063203454017639,
+      "logps/rejected": -0.6916000247001648,
+      "loss": 1.4498,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -1.4126406908035278,
+      "rewards/margins": -0.029440607875585556,
+      "rewards/rejected": -1.3832000494003296,
+      "step": 39
+    },
+    {
+      "epoch": 0.5269658295594895,
+      "grad_norm": 2.536262273788452,
+      "learning_rate": 5.351380944726465e-07,
+      "logits/chosen": 10.201406478881836,
+      "logits/rejected": 11.195016860961914,
+      "logps/chosen": -0.6529728174209595,
+      "logps/rejected": -0.695421576499939,
+      "loss": 1.3726,
+      "rewards/accuracies": 0.640625,
+      "rewards/chosen": -1.305945634841919,
+      "rewards/margins": 0.08489762991666794,
+      "rewards/rejected": -1.390843152999878,
+      "step": 40
+    },
+    {
+      "epoch": 0.5401399752984768,
+      "grad_norm": 3.44834303855896,
+      "learning_rate": 5.117212868016303e-07,
+      "logits/chosen": 10.57003402709961,
+      "logits/rejected": 10.89995288848877,
+      "logps/chosen": -0.6615808606147766,
+      "logps/rejected": -0.6666579842567444,
+      "loss": 1.4101,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -1.3231617212295532,
+      "rewards/margins": 0.010154157876968384,
+      "rewards/rejected": -1.3333159685134888,
+      "step": 41
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": 0.3262707591056824,
+      "learning_rate": 4.882787131983697e-07,
+      "logits/chosen": 9.684130668640137,
+      "logits/rejected": 10.468993186950684,
+      "logps/chosen": -0.6019183993339539,
+      "logps/rejected": -0.6411232948303223,
+      "loss": 1.3798,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -1.2038367986679077,
+      "rewards/margins": 0.07840971648693085,
+      "rewards/rejected": -1.2822465896606445,
+      "step": 42
+    },
+    {
+      "epoch": 0.5664882667764513,
+      "grad_norm": 1.150577187538147,
+      "learning_rate": 4.648619055273537e-07,
+      "logits/chosen": 9.844969749450684,
+      "logits/rejected": 10.612713813781738,
+      "logps/chosen": -0.5501813292503357,
+      "logps/rejected": -0.591031551361084,
+      "loss": 1.3513,
+      "rewards/accuracies": 0.6171875,
+      "rewards/chosen": -1.1003626585006714,
+      "rewards/margins": 0.08170032501220703,
+      "rewards/rejected": -1.182063102722168,
+      "step": 43
+    },
+    {
+      "epoch": 0.5796624125154385,
+      "grad_norm": 0.3965461850166321,
+      "learning_rate": 4.4152233901395875e-07,
+      "logits/chosen": 9.765134811401367,
+      "logits/rejected": 10.664865493774414,
+      "logps/chosen": -0.689943253993988,
+      "logps/rejected": -0.6770355701446533,
+      "loss": 1.4345,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.379886507987976,
+      "rewards/margins": -0.025815514847636223,
+      "rewards/rejected": -1.3540711402893066,
+      "step": 44
+    },
+    {
+      "epoch": 0.5928365582544257,
+      "grad_norm": 0.5376319289207458,
+      "learning_rate": 4.183113190907348e-07,
+      "logits/chosen": 10.018446922302246,
+      "logits/rejected": 10.538941383361816,
+      "logps/chosen": -0.6233353614807129,
+      "logps/rejected": -0.633882999420166,
+      "loss": 1.4166,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -1.2466707229614258,
+      "rewards/margins": 0.02109522372484207,
+      "rewards/rejected": -1.267765998840332,
+      "step": 45
+    },
+    {
+      "epoch": 0.606010703993413,
+      "grad_norm": 3.684044122695923,
+      "learning_rate": 3.9527986861692785e-07,
+      "logits/chosen": 10.023819923400879,
+      "logits/rejected": 10.466320037841797,
+      "logps/chosen": -0.644775927066803,
+      "logps/rejected": -0.6808078289031982,
+      "loss": 1.3706,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -1.289551854133606,
+      "rewards/margins": 0.07206393778324127,
+      "rewards/rejected": -1.3616156578063965,
+      "step": 46
+    },
+    {
+      "epoch": 0.6191848497324002,
+      "grad_norm": 0.5732494592666626,
+      "learning_rate": 3.724786157191618e-07,
+      "logits/chosen": 10.115565299987793,
+      "logits/rejected": 10.92066764831543,
+      "logps/chosen": -0.7901978492736816,
+      "logps/rejected": -0.7942913174629211,
+      "loss": 1.4251,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -1.5803956985473633,
+      "rewards/margins": 0.008186978287994862,
+      "rewards/rejected": -1.5885826349258423,
+      "step": 47
+    },
+    {
+      "epoch": 0.6323589954713874,
+      "grad_norm": 0.6679599285125732,
+      "learning_rate": 3.499576824998297e-07,
+      "logits/chosen": 10.542475700378418,
+      "logits/rejected": 11.161402702331543,
+      "logps/chosen": -0.6402223706245422,
+      "logps/rejected": -0.6876631379127502,
+      "loss": 1.3518,
+      "rewards/accuracies": 0.6328125,
+      "rewards/chosen": -1.2804447412490845,
+      "rewards/margins": 0.09488136321306229,
+      "rewards/rejected": -1.3753262758255005,
+      "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 sha256:3a1038a82f5011c4f7eb41a4d0c82bfbeadc8254400987029a5f9b99caafa32d
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6ae750e71a60ddc831866803942cd5dff86cb52f6a83f1066ab401172f5056
+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
+  }
+}