Upload folder using huggingface_hub

added_tokens.json

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

all_results.json

@@ -0,0 +1,24 @@
+{
+    "epoch": 0.9880609304240429,
+    "eval_logits/chosen": 9.158658981323242,
+    "eval_logits/rejected": 9.958081245422363,
+    "eval_logps/chosen": -110.41038513183594,
+    "eval_logps/ref_chosen": -106.16099548339844,
+    "eval_logps/ref_rejected": -119.78473663330078,
+    "eval_logps/rejected": -124.09846496582031,
+    "eval_loss": 0.6929683089256287,
+    "eval_rewards/accuracies": 0.4972222149372101,
+    "eval_rewards/chosen": -0.04249410331249237,
+    "eval_rewards/margins": 0.0006433044327422976,
+    "eval_rewards/rejected": -0.043137405067682266,
+    "eval_runtime": 159.1867,
+    "eval_samples": 1080,
+    "eval_samples_per_second": 6.784,
+    "eval_steps_per_second": 1.696,
+    "total_flos": 0.0,
+    "train_loss": 0.6922952850659688,
+    "train_runtime": 7631.3864,
+    "train_samples": 9715,
+    "train_samples_per_second": 1.273,
+    "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 sha256:54f22084fae392c81cc3d3fb9a382a1dd29526ce63cbdca6f05aff443fcb3655
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf477fb6d46f7596cb0f8b34852dd4598b5798fa0c058d2ed1be95c714f499a
+size 2669692552

checkpoint-12/model.safetensors.index.json

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

checkpoint-12/special_tokens_map.json

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

checkpoint-12/tokenizer_config.json

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

checkpoint-12/trainer_state.json

@@ -0,0 +1,237 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.15808974886784685,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.4815484285354614,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.088521957397461,
+      "logits/rejected": 10.263787269592285,
+      "logps/chosen": -163.12940979003906,
+      "logps/ref_chosen": -163.12940979003906,
+      "logps/ref_rejected": -171.48428344726562,
+      "logps/rejected": -171.48428344726562,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.627070426940918,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.592972755432129,
+      "logits/rejected": 10.720216751098633,
+      "logps/chosen": -155.91574096679688,
+      "logps/ref_chosen": -155.91574096679688,
+      "logps/ref_rejected": -161.34078979492188,
+      "logps/rejected": -161.34078979492188,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.4148138165473938,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.043272972106934,
+      "logits/rejected": 10.398024559020996,
+      "logps/chosen": -158.3568115234375,
+      "logps/ref_chosen": -157.65640258789062,
+      "logps/ref_rejected": -168.5882110595703,
+      "logps/rejected": -168.91085815429688,
+      "loss": 0.6951,
+      "rewards/accuracies": 0.3828125,
+      "rewards/chosen": -0.007004000246524811,
+      "rewards/margins": -0.0037774655502289534,
+      "rewards/rejected": -0.003226534929126501,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.7029770612716675,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.250253677368164,
+      "logits/rejected": 10.45008659362793,
+      "logps/chosen": -164.01119995117188,
+      "logps/ref_chosen": -162.89878845214844,
+      "logps/ref_rejected": -168.30462646484375,
+      "logps/rejected": -169.1818389892578,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.01112416572868824,
+      "rewards/margins": -0.0023521997500211,
+      "rewards/rejected": -0.008771965280175209,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.4063253104686737,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.442557334899902,
+      "logits/rejected": 10.740192413330078,
+      "logps/chosen": -156.1859130859375,
+      "logps/ref_chosen": -156.03257751464844,
+      "logps/ref_rejected": -165.37911987304688,
+      "logps/rejected": -165.6518096923828,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.001533512957394123,
+      "rewards/margins": 0.001193464733660221,
+      "rewards/rejected": -0.002726977691054344,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.4845049977302551,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.906261444091797,
+      "logits/rejected": 11.201122283935547,
+      "logps/chosen": -162.45692443847656,
+      "logps/ref_chosen": -161.98570251464844,
+      "logps/ref_rejected": -169.72560119628906,
+      "logps/rejected": -170.18275451660156,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.004712029360234737,
+      "rewards/margins": -0.00014030117017682642,
+      "rewards/rejected": -0.004571728408336639,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.8172655701637268,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.883949279785156,
+      "logits/rejected": 10.030972480773926,
+      "logps/chosen": -157.43295288085938,
+      "logps/ref_chosen": -157.26968383789062,
+      "logps/ref_rejected": -167.37155151367188,
+      "logps/rejected": -167.53939819335938,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0016327811172232032,
+      "rewards/margins": 4.5756096369586885e-05,
+      "rewards/rejected": -0.0016785369953140616,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.588524341583252,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.633930206298828,
+      "logits/rejected": 10.81590747833252,
+      "logps/chosen": -162.8237762451172,
+      "logps/ref_chosen": -162.2948455810547,
+      "logps/ref_rejected": -172.98866271972656,
+      "logps/rejected": -173.56680297851562,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.005289244465529919,
+      "rewards/margins": 0.0004922347725369036,
+      "rewards/rejected": -0.005781479645520449,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.46077635884284973,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.326555252075195,
+      "logits/rejected": 10.736672401428223,
+      "logps/chosen": -164.5288543701172,
+      "logps/ref_chosen": -163.37091064453125,
+      "logps/ref_rejected": -173.1500701904297,
+      "logps/rejected": -174.08392333984375,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.011579334735870361,
+      "rewards/margins": -0.0022407739888876677,
+      "rewards/rejected": -0.00933856051415205,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.673312783241272,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 10.325155258178711,
+      "logits/rejected": 10.473593711853027,
+      "logps/chosen": -157.8944091796875,
+      "logps/ref_chosen": -156.87838745117188,
+      "logps/ref_rejected": -165.17373657226562,
+      "logps/rejected": -166.20751953125,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.010160216130316257,
+      "rewards/margins": 0.00017760891932994127,
+      "rewards/rejected": -0.010337824933230877,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.6500194668769836,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.476134300231934,
+      "logits/rejected": 10.66375732421875,
+      "logps/chosen": -161.99935913085938,
+      "logps/ref_chosen": -160.73855590820312,
+      "logps/ref_rejected": -173.1862030029297,
+      "logps/rejected": -174.4076385498047,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0126079972833395,
+      "rewards/margins": -0.00039388981531374156,
+      "rewards/rejected": -0.012214107438921928,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.5539909601211548,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.318845748901367,
+      "logits/rejected": 10.355680465698242,
+      "logps/chosen": -167.43121337890625,
+      "logps/ref_chosen": -165.21177673339844,
+      "logps/ref_rejected": -170.47381591796875,
+      "logps/rejected": -172.76483154296875,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.022194450721144676,
+      "rewards/margins": 0.0007156741339713335,
+      "rewards/rejected": -0.02291012369096279,
+      "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 sha256:4032c8b2d51f60ac03135fc0fb65681ee03c17d0546b7d621d9130ba275d3a5b
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf6beb73c331a85cf8e5bea0ab21f3c2b66559ba945ae4b00132c5321ea2ad9
+size 2669692552

checkpoint-24/model.safetensors.index.json

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

checkpoint-24/special_tokens_map.json

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

checkpoint-24/tokenizer_config.json

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

checkpoint-24/trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3161794977356937,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.4815484285354614,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.088521957397461,
+      "logits/rejected": 10.263787269592285,
+      "logps/chosen": -163.12940979003906,
+      "logps/ref_chosen": -163.12940979003906,
+      "logps/ref_rejected": -171.48428344726562,
+      "logps/rejected": -171.48428344726562,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.627070426940918,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.592972755432129,
+      "logits/rejected": 10.720216751098633,
+      "logps/chosen": -155.91574096679688,
+      "logps/ref_chosen": -155.91574096679688,
+      "logps/ref_rejected": -161.34078979492188,
+      "logps/rejected": -161.34078979492188,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.4148138165473938,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.043272972106934,
+      "logits/rejected": 10.398024559020996,
+      "logps/chosen": -158.3568115234375,
+      "logps/ref_chosen": -157.65640258789062,
+      "logps/ref_rejected": -168.5882110595703,
+      "logps/rejected": -168.91085815429688,
+      "loss": 0.6951,
+      "rewards/accuracies": 0.3828125,
+      "rewards/chosen": -0.007004000246524811,
+      "rewards/margins": -0.0037774655502289534,
+      "rewards/rejected": -0.003226534929126501,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.7029770612716675,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.250253677368164,
+      "logits/rejected": 10.45008659362793,
+      "logps/chosen": -164.01119995117188,
+      "logps/ref_chosen": -162.89878845214844,
+      "logps/ref_rejected": -168.30462646484375,
+      "logps/rejected": -169.1818389892578,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.01112416572868824,
+      "rewards/margins": -0.0023521997500211,
+      "rewards/rejected": -0.008771965280175209,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.4063253104686737,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.442557334899902,
+      "logits/rejected": 10.740192413330078,
+      "logps/chosen": -156.1859130859375,
+      "logps/ref_chosen": -156.03257751464844,
+      "logps/ref_rejected": -165.37911987304688,
+      "logps/rejected": -165.6518096923828,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.001533512957394123,
+      "rewards/margins": 0.001193464733660221,
+      "rewards/rejected": -0.002726977691054344,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.4845049977302551,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.906261444091797,
+      "logits/rejected": 11.201122283935547,
+      "logps/chosen": -162.45692443847656,
+      "logps/ref_chosen": -161.98570251464844,
+      "logps/ref_rejected": -169.72560119628906,
+      "logps/rejected": -170.18275451660156,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.004712029360234737,
+      "rewards/margins": -0.00014030117017682642,
+      "rewards/rejected": -0.004571728408336639,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.8172655701637268,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.883949279785156,
+      "logits/rejected": 10.030972480773926,
+      "logps/chosen": -157.43295288085938,
+      "logps/ref_chosen": -157.26968383789062,
+      "logps/ref_rejected": -167.37155151367188,
+      "logps/rejected": -167.53939819335938,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0016327811172232032,
+      "rewards/margins": 4.5756096369586885e-05,
+      "rewards/rejected": -0.0016785369953140616,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.588524341583252,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.633930206298828,
+      "logits/rejected": 10.81590747833252,
+      "logps/chosen": -162.8237762451172,
+      "logps/ref_chosen": -162.2948455810547,
+      "logps/ref_rejected": -172.98866271972656,
+      "logps/rejected": -173.56680297851562,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.005289244465529919,
+      "rewards/margins": 0.0004922347725369036,
+      "rewards/rejected": -0.005781479645520449,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.46077635884284973,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.326555252075195,
+      "logits/rejected": 10.736672401428223,
+      "logps/chosen": -164.5288543701172,
+      "logps/ref_chosen": -163.37091064453125,
+      "logps/ref_rejected": -173.1500701904297,
+      "logps/rejected": -174.08392333984375,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.011579334735870361,
+      "rewards/margins": -0.0022407739888876677,
+      "rewards/rejected": -0.00933856051415205,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.673312783241272,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 10.325155258178711,
+      "logits/rejected": 10.473593711853027,
+      "logps/chosen": -157.8944091796875,
+      "logps/ref_chosen": -156.87838745117188,
+      "logps/ref_rejected": -165.17373657226562,
+      "logps/rejected": -166.20751953125,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.010160216130316257,
+      "rewards/margins": 0.00017760891932994127,
+      "rewards/rejected": -0.010337824933230877,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.6500194668769836,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.476134300231934,
+      "logits/rejected": 10.66375732421875,
+      "logps/chosen": -161.99935913085938,
+      "logps/ref_chosen": -160.73855590820312,
+      "logps/ref_rejected": -173.1862030029297,
+      "logps/rejected": -174.4076385498047,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0126079972833395,
+      "rewards/margins": -0.00039388981531374156,
+      "rewards/rejected": -0.012214107438921928,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.5539909601211548,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.318845748901367,
+      "logits/rejected": 10.355680465698242,
+      "logps/chosen": -167.43121337890625,
+      "logps/ref_chosen": -165.21177673339844,
+      "logps/ref_rejected": -170.47381591796875,
+      "logps/rejected": -172.76483154296875,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.022194450721144676,
+      "rewards/margins": 0.0007156741339713335,
+      "rewards/rejected": -0.02291012369096279,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5150694251060486,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.89578914642334,
+      "logits/rejected": 10.236948013305664,
+      "logps/chosen": -161.29905700683594,
+      "logps/ref_chosen": -158.68667602539062,
+      "logps/ref_rejected": -168.57968139648438,
+      "logps/rejected": -171.51979064941406,
+      "loss": 0.6916,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.026123855262994766,
+      "rewards/margins": 0.0032772955019026995,
+      "rewards/rejected": -0.029401153326034546,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.6596489548683167,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.484810829162598,
+      "logits/rejected": 10.99763298034668,
+      "logps/chosen": -157.44769287109375,
+      "logps/ref_chosen": -153.92340087890625,
+      "logps/ref_rejected": -167.03564453125,
+      "logps/rejected": -170.4557647705078,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.03524318337440491,
+      "rewards/margins": -0.0010417333105579019,
+      "rewards/rejected": -0.034201446920633316,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.39550018310546875,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 10.189282417297363,
+      "logits/rejected": 10.43722152709961,
+      "logps/chosen": -166.56544494628906,
+      "logps/ref_chosen": -162.66110229492188,
+      "logps/ref_rejected": -168.7485809326172,
+      "logps/rejected": -172.78038024902344,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.03904342278838158,
+      "rewards/margins": 0.0012746157590299845,
+      "rewards/rejected": -0.04031803831458092,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.6276482939720154,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.743437767028809,
+      "logits/rejected": 11.031370162963867,
+      "logps/chosen": -166.45135498046875,
+      "logps/ref_chosen": -163.39239501953125,
+      "logps/ref_rejected": -172.29183959960938,
+      "logps/rejected": -175.4534912109375,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.03058951534330845,
+      "rewards/margins": 0.0010271857026964426,
+      "rewards/rejected": -0.0316167026758194,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.516729474067688,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.332087516784668,
+      "logits/rejected": 10.48865032196045,
+      "logps/chosen": -157.08522033691406,
+      "logps/ref_chosen": -153.6072540283203,
+      "logps/ref_rejected": -161.9541473388672,
+      "logps/rejected": -165.6874542236328,
+      "loss": 0.6919,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.03477972373366356,
+      "rewards/margins": 0.0025533493608236313,
+      "rewards/rejected": -0.03733307495713234,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.70009446144104,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.40684986114502,
+      "logits/rejected": 10.725347518920898,
+      "logps/chosen": -158.2038116455078,
+      "logps/ref_chosen": -154.3197021484375,
+      "logps/ref_rejected": -161.81753540039062,
+      "logps/rejected": -165.58631896972656,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.03884127736091614,
+      "rewards/margins": -0.0011533537181094289,
+      "rewards/rejected": -0.03768792748451233,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.47613224387168884,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.489011764526367,
+      "logits/rejected": 10.455073356628418,
+      "logps/chosen": -171.99160766601562,
+      "logps/ref_chosen": -167.8755340576172,
+      "logps/ref_rejected": -175.09603881835938,
+      "logps/rejected": -179.593994140625,
+      "loss": 0.6913,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.04116089642047882,
+      "rewards/margins": 0.003818710334599018,
+      "rewards/rejected": -0.04497961327433586,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.6483292579650879,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.415058135986328,
+      "logits/rejected": 10.774059295654297,
+      "logps/chosen": -163.5430450439453,
+      "logps/ref_chosen": -159.07583618164062,
+      "logps/ref_rejected": -169.23069763183594,
+      "logps/rejected": -173.73776245117188,
+      "loss": 0.693,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.04467229172587395,
+      "rewards/margins": 0.00039826278225518763,
+      "rewards/rejected": -0.04507055878639221,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.5634174942970276,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 10.342830657958984,
+      "logits/rejected": 10.680377960205078,
+      "logps/chosen": -163.2490997314453,
+      "logps/ref_chosen": -159.25521850585938,
+      "logps/ref_rejected": -169.57681274414062,
+      "logps/rejected": -173.69276428222656,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.03993882238864899,
+      "rewards/margins": 0.0012204290833324194,
+      "rewards/rejected": -0.0411592535674572,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.3794897198677063,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.29517936706543,
+      "logits/rejected": 10.647847175598145,
+      "logps/chosen": -161.54783630371094,
+      "logps/ref_chosen": -157.0568084716797,
+      "logps/ref_rejected": -163.96209716796875,
+      "logps/rejected": -168.51736450195312,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.04491012915968895,
+      "rewards/margins": 0.0006425387691706419,
+      "rewards/rejected": -0.04555266723036766,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4016757607460022,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.357274055480957,
+      "logits/rejected": 10.63122844696045,
+      "logps/chosen": -162.94578552246094,
+      "logps/ref_chosen": -158.10250854492188,
+      "logps/ref_rejected": -169.85250854492188,
+      "logps/rejected": -174.79525756835938,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.04843292012810707,
+      "rewards/margins": 0.0009945080382749438,
+      "rewards/rejected": -0.04942742735147476,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.46131113171577454,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.260627746582031,
+      "logits/rejected": 10.424566268920898,
+      "logps/chosen": -163.2139129638672,
+      "logps/ref_chosen": -158.93540954589844,
+      "logps/ref_rejected": -168.12344360351562,
+      "logps/rejected": -172.52456665039062,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.042785100638866425,
+      "rewards/margins": 0.0012263581156730652,
+      "rewards/rejected": -0.04401145875453949,
+      "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 sha256:00b22060b10f0beab485fa6cbc36baeb3d9957173bd7d34b3b7295082aebd6d2
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b427766e8384119ae16115014422e93ad426e99d775f9a001124258d7dd82e7
+size 2669692552

checkpoint-36/model.safetensors.index.json

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

checkpoint-36/special_tokens_map.json

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

checkpoint-36/tokenizer_config.json

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

checkpoint-36/trainer_state.json

@@ -0,0 +1,645 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.47426924660354053,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.4815484285354614,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.088521957397461,
+      "logits/rejected": 10.263787269592285,
+      "logps/chosen": -163.12940979003906,
+      "logps/ref_chosen": -163.12940979003906,
+      "logps/ref_rejected": -171.48428344726562,
+      "logps/rejected": -171.48428344726562,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.627070426940918,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.592972755432129,
+      "logits/rejected": 10.720216751098633,
+      "logps/chosen": -155.91574096679688,
+      "logps/ref_chosen": -155.91574096679688,
+      "logps/ref_rejected": -161.34078979492188,
+      "logps/rejected": -161.34078979492188,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.4148138165473938,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.043272972106934,
+      "logits/rejected": 10.398024559020996,
+      "logps/chosen": -158.3568115234375,
+      "logps/ref_chosen": -157.65640258789062,
+      "logps/ref_rejected": -168.5882110595703,
+      "logps/rejected": -168.91085815429688,
+      "loss": 0.6951,
+      "rewards/accuracies": 0.3828125,
+      "rewards/chosen": -0.007004000246524811,
+      "rewards/margins": -0.0037774655502289534,
+      "rewards/rejected": -0.003226534929126501,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.7029770612716675,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.250253677368164,
+      "logits/rejected": 10.45008659362793,
+      "logps/chosen": -164.01119995117188,
+      "logps/ref_chosen": -162.89878845214844,
+      "logps/ref_rejected": -168.30462646484375,
+      "logps/rejected": -169.1818389892578,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.01112416572868824,
+      "rewards/margins": -0.0023521997500211,
+      "rewards/rejected": -0.008771965280175209,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.4063253104686737,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.442557334899902,
+      "logits/rejected": 10.740192413330078,
+      "logps/chosen": -156.1859130859375,
+      "logps/ref_chosen": -156.03257751464844,
+      "logps/ref_rejected": -165.37911987304688,
+      "logps/rejected": -165.6518096923828,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.001533512957394123,
+      "rewards/margins": 0.001193464733660221,
+      "rewards/rejected": -0.002726977691054344,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.4845049977302551,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.906261444091797,
+      "logits/rejected": 11.201122283935547,
+      "logps/chosen": -162.45692443847656,
+      "logps/ref_chosen": -161.98570251464844,
+      "logps/ref_rejected": -169.72560119628906,
+      "logps/rejected": -170.18275451660156,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.004712029360234737,
+      "rewards/margins": -0.00014030117017682642,
+      "rewards/rejected": -0.004571728408336639,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.8172655701637268,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.883949279785156,
+      "logits/rejected": 10.030972480773926,
+      "logps/chosen": -157.43295288085938,
+      "logps/ref_chosen": -157.26968383789062,
+      "logps/ref_rejected": -167.37155151367188,
+      "logps/rejected": -167.53939819335938,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0016327811172232032,
+      "rewards/margins": 4.5756096369586885e-05,
+      "rewards/rejected": -0.0016785369953140616,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.588524341583252,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.633930206298828,
+      "logits/rejected": 10.81590747833252,
+      "logps/chosen": -162.8237762451172,
+      "logps/ref_chosen": -162.2948455810547,
+      "logps/ref_rejected": -172.98866271972656,
+      "logps/rejected": -173.56680297851562,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.005289244465529919,
+      "rewards/margins": 0.0004922347725369036,
+      "rewards/rejected": -0.005781479645520449,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.46077635884284973,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.326555252075195,
+      "logits/rejected": 10.736672401428223,
+      "logps/chosen": -164.5288543701172,
+      "logps/ref_chosen": -163.37091064453125,
+      "logps/ref_rejected": -173.1500701904297,
+      "logps/rejected": -174.08392333984375,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.011579334735870361,
+      "rewards/margins": -0.0022407739888876677,
+      "rewards/rejected": -0.00933856051415205,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.673312783241272,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 10.325155258178711,
+      "logits/rejected": 10.473593711853027,
+      "logps/chosen": -157.8944091796875,
+      "logps/ref_chosen": -156.87838745117188,
+      "logps/ref_rejected": -165.17373657226562,
+      "logps/rejected": -166.20751953125,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.010160216130316257,
+      "rewards/margins": 0.00017760891932994127,
+      "rewards/rejected": -0.010337824933230877,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.6500194668769836,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.476134300231934,
+      "logits/rejected": 10.66375732421875,
+      "logps/chosen": -161.99935913085938,
+      "logps/ref_chosen": -160.73855590820312,
+      "logps/ref_rejected": -173.1862030029297,
+      "logps/rejected": -174.4076385498047,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0126079972833395,
+      "rewards/margins": -0.00039388981531374156,
+      "rewards/rejected": -0.012214107438921928,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.5539909601211548,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.318845748901367,
+      "logits/rejected": 10.355680465698242,
+      "logps/chosen": -167.43121337890625,
+      "logps/ref_chosen": -165.21177673339844,
+      "logps/ref_rejected": -170.47381591796875,
+      "logps/rejected": -172.76483154296875,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.022194450721144676,
+      "rewards/margins": 0.0007156741339713335,
+      "rewards/rejected": -0.02291012369096279,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5150694251060486,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.89578914642334,
+      "logits/rejected": 10.236948013305664,
+      "logps/chosen": -161.29905700683594,
+      "logps/ref_chosen": -158.68667602539062,
+      "logps/ref_rejected": -168.57968139648438,
+      "logps/rejected": -171.51979064941406,
+      "loss": 0.6916,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.026123855262994766,
+      "rewards/margins": 0.0032772955019026995,
+      "rewards/rejected": -0.029401153326034546,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.6596489548683167,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.484810829162598,
+      "logits/rejected": 10.99763298034668,
+      "logps/chosen": -157.44769287109375,
+      "logps/ref_chosen": -153.92340087890625,
+      "logps/ref_rejected": -167.03564453125,
+      "logps/rejected": -170.4557647705078,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.03524318337440491,
+      "rewards/margins": -0.0010417333105579019,
+      "rewards/rejected": -0.034201446920633316,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.39550018310546875,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 10.189282417297363,
+      "logits/rejected": 10.43722152709961,
+      "logps/chosen": -166.56544494628906,
+      "logps/ref_chosen": -162.66110229492188,
+      "logps/ref_rejected": -168.7485809326172,
+      "logps/rejected": -172.78038024902344,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.03904342278838158,
+      "rewards/margins": 0.0012746157590299845,
+      "rewards/rejected": -0.04031803831458092,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.6276482939720154,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.743437767028809,
+      "logits/rejected": 11.031370162963867,
+      "logps/chosen": -166.45135498046875,
+      "logps/ref_chosen": -163.39239501953125,
+      "logps/ref_rejected": -172.29183959960938,
+      "logps/rejected": -175.4534912109375,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.03058951534330845,
+      "rewards/margins": 0.0010271857026964426,
+      "rewards/rejected": -0.0316167026758194,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.516729474067688,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.332087516784668,
+      "logits/rejected": 10.48865032196045,
+      "logps/chosen": -157.08522033691406,
+      "logps/ref_chosen": -153.6072540283203,
+      "logps/ref_rejected": -161.9541473388672,
+      "logps/rejected": -165.6874542236328,
+      "loss": 0.6919,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.03477972373366356,
+      "rewards/margins": 0.0025533493608236313,
+      "rewards/rejected": -0.03733307495713234,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.70009446144104,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.40684986114502,
+      "logits/rejected": 10.725347518920898,
+      "logps/chosen": -158.2038116455078,
+      "logps/ref_chosen": -154.3197021484375,
+      "logps/ref_rejected": -161.81753540039062,
+      "logps/rejected": -165.58631896972656,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.03884127736091614,
+      "rewards/margins": -0.0011533537181094289,
+      "rewards/rejected": -0.03768792748451233,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.47613224387168884,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.489011764526367,
+      "logits/rejected": 10.455073356628418,
+      "logps/chosen": -171.99160766601562,
+      "logps/ref_chosen": -167.8755340576172,
+      "logps/ref_rejected": -175.09603881835938,
+      "logps/rejected": -179.593994140625,
+      "loss": 0.6913,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.04116089642047882,
+      "rewards/margins": 0.003818710334599018,
+      "rewards/rejected": -0.04497961327433586,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.6483292579650879,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.415058135986328,
+      "logits/rejected": 10.774059295654297,
+      "logps/chosen": -163.5430450439453,
+      "logps/ref_chosen": -159.07583618164062,
+      "logps/ref_rejected": -169.23069763183594,
+      "logps/rejected": -173.73776245117188,
+      "loss": 0.693,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.04467229172587395,
+      "rewards/margins": 0.00039826278225518763,
+      "rewards/rejected": -0.04507055878639221,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.5634174942970276,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 10.342830657958984,
+      "logits/rejected": 10.680377960205078,
+      "logps/chosen": -163.2490997314453,
+      "logps/ref_chosen": -159.25521850585938,
+      "logps/ref_rejected": -169.57681274414062,
+      "logps/rejected": -173.69276428222656,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.03993882238864899,
+      "rewards/margins": 0.0012204290833324194,
+      "rewards/rejected": -0.0411592535674572,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.3794897198677063,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.29517936706543,
+      "logits/rejected": 10.647847175598145,
+      "logps/chosen": -161.54783630371094,
+      "logps/ref_chosen": -157.0568084716797,
+      "logps/ref_rejected": -163.96209716796875,
+      "logps/rejected": -168.51736450195312,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.04491012915968895,
+      "rewards/margins": 0.0006425387691706419,
+      "rewards/rejected": -0.04555266723036766,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4016757607460022,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.357274055480957,
+      "logits/rejected": 10.63122844696045,
+      "logps/chosen": -162.94578552246094,
+      "logps/ref_chosen": -158.10250854492188,
+      "logps/ref_rejected": -169.85250854492188,
+      "logps/rejected": -174.79525756835938,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.04843292012810707,
+      "rewards/margins": 0.0009945080382749438,
+      "rewards/rejected": -0.04942742735147476,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.46131113171577454,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.260627746582031,
+      "logits/rejected": 10.424566268920898,
+      "logps/chosen": -163.2139129638672,
+      "logps/ref_chosen": -158.93540954589844,
+      "logps/ref_rejected": -168.12344360351562,
+      "logps/rejected": -172.52456665039062,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.042785100638866425,
+      "rewards/margins": 0.0012263581156730652,
+      "rewards/rejected": -0.04401145875453949,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.4610799252986908,
+      "learning_rate": 4.246923569447104e-07,
+      "logits/chosen": 10.461551666259766,
+      "logits/rejected": 10.855925559997559,
+      "logps/chosen": -165.60084533691406,
+      "logps/ref_chosen": -161.0833740234375,
+      "logps/ref_rejected": -174.85760498046875,
+      "logps/rejected": -179.20965576171875,
+      "loss": 0.694,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.0451747290790081,
+      "rewards/margins": -0.0016541833756491542,
+      "rewards/rejected": -0.043520547449588776,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 0.41953545808792114,
+      "learning_rate": 4.161178683597054e-07,
+      "logits/chosen": 10.611435890197754,
+      "logits/rejected": 10.745625495910645,
+      "logps/chosen": -160.7465057373047,
+      "logps/ref_chosen": -156.07315063476562,
+      "logps/ref_rejected": -161.84292602539062,
+      "logps/rejected": -166.85279846191406,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.046733610332012177,
+      "rewards/margins": 0.0033648861572146416,
+      "rewards/rejected": -0.05009850114583969,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.3880956470966339,
+      "learning_rate": 4.0717821664772124e-07,
+      "logits/chosen": 10.590215682983398,
+      "logits/rejected": 10.893061637878418,
+      "logps/chosen": -168.67279052734375,
+      "logps/ref_chosen": -163.2271728515625,
+      "logps/ref_rejected": -171.53738403320312,
+      "logps/rejected": -176.9310302734375,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.05445636808872223,
+      "rewards/margins": -0.00051975465612486,
+      "rewards/rejected": -0.05393661558628082,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.5345169901847839,
+      "learning_rate": 3.978930531033806e-07,
+      "logits/chosen": 9.953861236572266,
+      "logits/rejected": 10.416406631469727,
+      "logps/chosen": -162.322021484375,
+      "logps/ref_chosen": -157.08795166015625,
+      "logps/ref_rejected": -167.1195068359375,
+      "logps/rejected": -172.4853973388672,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.0523407980799675,
+      "rewards/margins": 0.001318173250183463,
+      "rewards/rejected": -0.053658969700336456,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.5297831296920776,
+      "learning_rate": 3.882827885312998e-07,
+      "logits/chosen": 10.323142051696777,
+      "logits/rejected": 10.501938819885254,
+      "logps/chosen": -168.2061004638672,
+      "logps/ref_chosen": -163.59707641601562,
+      "logps/ref_rejected": -171.89508056640625,
+      "logps/rejected": -176.55738830566406,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.04609035328030586,
+      "rewards/margins": 0.0005328265833668411,
+      "rewards/rejected": -0.04662318155169487,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.35810208320617676,
+      "learning_rate": 3.7836854837871044e-07,
+      "logits/chosen": 10.40945053100586,
+      "logits/rejected": 10.931025505065918,
+      "logps/chosen": -169.71910095214844,
+      "logps/ref_chosen": -164.91160583496094,
+      "logps/ref_rejected": -176.66453552246094,
+      "logps/rejected": -181.69285583496094,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.04807499051094055,
+      "rewards/margins": 0.0022084712982177734,
+      "rewards/rejected": -0.050283461809158325,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.44152358174324036,
+      "learning_rate": 3.681721262971413e-07,
+      "logits/chosen": 10.004611015319824,
+      "logits/rejected": 10.491472244262695,
+      "logps/chosen": -161.24798583984375,
+      "logps/ref_chosen": -155.95877075195312,
+      "logps/ref_rejected": -166.5852508544922,
+      "logps/rejected": -172.22703552246094,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.052892111241817474,
+      "rewards/margins": 0.003525771899148822,
+      "rewards/rejected": -0.05641787871718407,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.5185390114784241,
+      "learning_rate": 3.577159362352426e-07,
+      "logits/chosen": 10.27377986907959,
+      "logits/rejected": 10.56481647491455,
+      "logps/chosen": -167.19921875,
+      "logps/ref_chosen": -161.83575439453125,
+      "logps/ref_rejected": -169.53759765625,
+      "logps/rejected": -174.91342163085938,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.05363469570875168,
+      "rewards/margins": 0.00012344191782176495,
+      "rewards/rejected": -0.05375813692808151,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 1.1196942329406738,
+      "learning_rate": 3.470229631680624e-07,
+      "logits/chosen": 10.063702583312988,
+      "logits/rejected": 10.693009376525879,
+      "logps/chosen": -164.40225219726562,
+      "logps/ref_chosen": -158.7517547607422,
+      "logps/ref_rejected": -168.51002502441406,
+      "logps/rejected": -174.00901794433594,
+      "loss": 0.694,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.056504976004362106,
+      "rewards/margins": -0.0015149968676269054,
+      "rewards/rejected": -0.054989978671073914,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.593383252620697,
+      "learning_rate": 3.361167125710832e-07,
+      "logits/chosen": 9.993782043457031,
+      "logits/rejected": 10.380085945129395,
+      "logps/chosen": -170.81832885742188,
+      "logps/ref_chosen": -165.12754821777344,
+      "logps/ref_rejected": -177.654296875,
+      "logps/rejected": -183.54998779296875,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.05690779164433479,
+      "rewards/margins": 0.0020490488968789577,
+      "rewards/rejected": -0.05895683914422989,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.4870688319206238,
+      "learning_rate": 3.2502115875008516e-07,
+      "logits/chosen": 10.418455123901367,
+      "logits/rejected": 10.655467987060547,
+      "logps/chosen": -165.74551391601562,
+      "logps/ref_chosen": -159.895751953125,
+      "logps/ref_rejected": -167.39785766601562,
+      "logps/rejected": -173.5540008544922,
+      "loss": 0.6917,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.058497510850429535,
+      "rewards/margins": 0.0030638885218650103,
+      "rewards/rejected": -0.06156139820814133,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.9538622498512268,
+      "learning_rate": 3.137606921404191e-07,
+      "logits/chosen": 10.286083221435547,
+      "logits/rejected": 10.6614408493042,
+      "logps/chosen": -170.4355926513672,
+      "logps/ref_chosen": -165.02023315429688,
+      "logps/ref_rejected": -172.28997802734375,
+      "logps/rejected": -177.64358520507812,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.05415371432900429,
+      "rewards/margins": -0.0006177356699481606,
+      "rewards/rejected": -0.053535979241132736,
+      "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 sha256:1166c80f648ef40fe6ed4c132ae6f557f582574db2c74bb034b9b718d5c35592
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b05e739009c567816d5bcea3d2ebe5ce9cbc8ec2350650c6e3207480da16e8a
+size 2669692552

checkpoint-48/model.safetensors.index.json

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

checkpoint-48/special_tokens_map.json

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

checkpoint-48/tokenizer_config.json

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

checkpoint-48/trainer_state.json

@@ -0,0 +1,849 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6323589954713874,
+  "eval_steps": 500,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.4815484285354614,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.088521957397461,
+      "logits/rejected": 10.263787269592285,
+      "logps/chosen": -163.12940979003906,
+      "logps/ref_chosen": -163.12940979003906,
+      "logps/ref_rejected": -171.48428344726562,
+      "logps/rejected": -171.48428344726562,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.627070426940918,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.592972755432129,
+      "logits/rejected": 10.720216751098633,
+      "logps/chosen": -155.91574096679688,
+      "logps/ref_chosen": -155.91574096679688,
+      "logps/ref_rejected": -161.34078979492188,
+      "logps/rejected": -161.34078979492188,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.4148138165473938,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.043272972106934,
+      "logits/rejected": 10.398024559020996,
+      "logps/chosen": -158.3568115234375,
+      "logps/ref_chosen": -157.65640258789062,
+      "logps/ref_rejected": -168.5882110595703,
+      "logps/rejected": -168.91085815429688,
+      "loss": 0.6951,
+      "rewards/accuracies": 0.3828125,
+      "rewards/chosen": -0.007004000246524811,
+      "rewards/margins": -0.0037774655502289534,
+      "rewards/rejected": -0.003226534929126501,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.7029770612716675,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.250253677368164,
+      "logits/rejected": 10.45008659362793,
+      "logps/chosen": -164.01119995117188,
+      "logps/ref_chosen": -162.89878845214844,
+      "logps/ref_rejected": -168.30462646484375,
+      "logps/rejected": -169.1818389892578,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.01112416572868824,
+      "rewards/margins": -0.0023521997500211,
+      "rewards/rejected": -0.008771965280175209,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.4063253104686737,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.442557334899902,
+      "logits/rejected": 10.740192413330078,
+      "logps/chosen": -156.1859130859375,
+      "logps/ref_chosen": -156.03257751464844,
+      "logps/ref_rejected": -165.37911987304688,
+      "logps/rejected": -165.6518096923828,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.001533512957394123,
+      "rewards/margins": 0.001193464733660221,
+      "rewards/rejected": -0.002726977691054344,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.4845049977302551,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.906261444091797,
+      "logits/rejected": 11.201122283935547,
+      "logps/chosen": -162.45692443847656,
+      "logps/ref_chosen": -161.98570251464844,
+      "logps/ref_rejected": -169.72560119628906,
+      "logps/rejected": -170.18275451660156,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.004712029360234737,
+      "rewards/margins": -0.00014030117017682642,
+      "rewards/rejected": -0.004571728408336639,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.8172655701637268,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.883949279785156,
+      "logits/rejected": 10.030972480773926,
+      "logps/chosen": -157.43295288085938,
+      "logps/ref_chosen": -157.26968383789062,
+      "logps/ref_rejected": -167.37155151367188,
+      "logps/rejected": -167.53939819335938,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0016327811172232032,
+      "rewards/margins": 4.5756096369586885e-05,
+      "rewards/rejected": -0.0016785369953140616,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.588524341583252,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.633930206298828,
+      "logits/rejected": 10.81590747833252,
+      "logps/chosen": -162.8237762451172,
+      "logps/ref_chosen": -162.2948455810547,
+      "logps/ref_rejected": -172.98866271972656,
+      "logps/rejected": -173.56680297851562,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.005289244465529919,
+      "rewards/margins": 0.0004922347725369036,
+      "rewards/rejected": -0.005781479645520449,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.46077635884284973,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.326555252075195,
+      "logits/rejected": 10.736672401428223,
+      "logps/chosen": -164.5288543701172,
+      "logps/ref_chosen": -163.37091064453125,
+      "logps/ref_rejected": -173.1500701904297,
+      "logps/rejected": -174.08392333984375,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.011579334735870361,
+      "rewards/margins": -0.0022407739888876677,
+      "rewards/rejected": -0.00933856051415205,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.673312783241272,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 10.325155258178711,
+      "logits/rejected": 10.473593711853027,
+      "logps/chosen": -157.8944091796875,
+      "logps/ref_chosen": -156.87838745117188,
+      "logps/ref_rejected": -165.17373657226562,
+      "logps/rejected": -166.20751953125,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.010160216130316257,
+      "rewards/margins": 0.00017760891932994127,
+      "rewards/rejected": -0.010337824933230877,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.6500194668769836,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.476134300231934,
+      "logits/rejected": 10.66375732421875,
+      "logps/chosen": -161.99935913085938,
+      "logps/ref_chosen": -160.73855590820312,
+      "logps/ref_rejected": -173.1862030029297,
+      "logps/rejected": -174.4076385498047,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0126079972833395,
+      "rewards/margins": -0.00039388981531374156,
+      "rewards/rejected": -0.012214107438921928,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.5539909601211548,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.318845748901367,
+      "logits/rejected": 10.355680465698242,
+      "logps/chosen": -167.43121337890625,
+      "logps/ref_chosen": -165.21177673339844,
+      "logps/ref_rejected": -170.47381591796875,
+      "logps/rejected": -172.76483154296875,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.022194450721144676,
+      "rewards/margins": 0.0007156741339713335,
+      "rewards/rejected": -0.02291012369096279,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5150694251060486,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.89578914642334,
+      "logits/rejected": 10.236948013305664,
+      "logps/chosen": -161.29905700683594,
+      "logps/ref_chosen": -158.68667602539062,
+      "logps/ref_rejected": -168.57968139648438,
+      "logps/rejected": -171.51979064941406,
+      "loss": 0.6916,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.026123855262994766,
+      "rewards/margins": 0.0032772955019026995,
+      "rewards/rejected": -0.029401153326034546,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.6596489548683167,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.484810829162598,
+      "logits/rejected": 10.99763298034668,
+      "logps/chosen": -157.44769287109375,
+      "logps/ref_chosen": -153.92340087890625,
+      "logps/ref_rejected": -167.03564453125,
+      "logps/rejected": -170.4557647705078,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.03524318337440491,
+      "rewards/margins": -0.0010417333105579019,
+      "rewards/rejected": -0.034201446920633316,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.39550018310546875,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 10.189282417297363,
+      "logits/rejected": 10.43722152709961,
+      "logps/chosen": -166.56544494628906,
+      "logps/ref_chosen": -162.66110229492188,
+      "logps/ref_rejected": -168.7485809326172,
+      "logps/rejected": -172.78038024902344,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.03904342278838158,
+      "rewards/margins": 0.0012746157590299845,
+      "rewards/rejected": -0.04031803831458092,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.6276482939720154,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.743437767028809,
+      "logits/rejected": 11.031370162963867,
+      "logps/chosen": -166.45135498046875,
+      "logps/ref_chosen": -163.39239501953125,
+      "logps/ref_rejected": -172.29183959960938,
+      "logps/rejected": -175.4534912109375,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.03058951534330845,
+      "rewards/margins": 0.0010271857026964426,
+      "rewards/rejected": -0.0316167026758194,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.516729474067688,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.332087516784668,
+      "logits/rejected": 10.48865032196045,
+      "logps/chosen": -157.08522033691406,
+      "logps/ref_chosen": -153.6072540283203,
+      "logps/ref_rejected": -161.9541473388672,
+      "logps/rejected": -165.6874542236328,
+      "loss": 0.6919,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.03477972373366356,
+      "rewards/margins": 0.0025533493608236313,
+      "rewards/rejected": -0.03733307495713234,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.70009446144104,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.40684986114502,
+      "logits/rejected": 10.725347518920898,
+      "logps/chosen": -158.2038116455078,
+      "logps/ref_chosen": -154.3197021484375,
+      "logps/ref_rejected": -161.81753540039062,
+      "logps/rejected": -165.58631896972656,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.03884127736091614,
+      "rewards/margins": -0.0011533537181094289,
+      "rewards/rejected": -0.03768792748451233,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.47613224387168884,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.489011764526367,
+      "logits/rejected": 10.455073356628418,
+      "logps/chosen": -171.99160766601562,
+      "logps/ref_chosen": -167.8755340576172,
+      "logps/ref_rejected": -175.09603881835938,
+      "logps/rejected": -179.593994140625,
+      "loss": 0.6913,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.04116089642047882,
+      "rewards/margins": 0.003818710334599018,
+      "rewards/rejected": -0.04497961327433586,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.6483292579650879,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.415058135986328,
+      "logits/rejected": 10.774059295654297,
+      "logps/chosen": -163.5430450439453,
+      "logps/ref_chosen": -159.07583618164062,
+      "logps/ref_rejected": -169.23069763183594,
+      "logps/rejected": -173.73776245117188,
+      "loss": 0.693,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.04467229172587395,
+      "rewards/margins": 0.00039826278225518763,
+      "rewards/rejected": -0.04507055878639221,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.5634174942970276,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 10.342830657958984,
+      "logits/rejected": 10.680377960205078,
+      "logps/chosen": -163.2490997314453,
+      "logps/ref_chosen": -159.25521850585938,
+      "logps/ref_rejected": -169.57681274414062,
+      "logps/rejected": -173.69276428222656,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.03993882238864899,
+      "rewards/margins": 0.0012204290833324194,
+      "rewards/rejected": -0.0411592535674572,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.3794897198677063,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.29517936706543,
+      "logits/rejected": 10.647847175598145,
+      "logps/chosen": -161.54783630371094,
+      "logps/ref_chosen": -157.0568084716797,
+      "logps/ref_rejected": -163.96209716796875,
+      "logps/rejected": -168.51736450195312,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.04491012915968895,
+      "rewards/margins": 0.0006425387691706419,
+      "rewards/rejected": -0.04555266723036766,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.4016757607460022,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.357274055480957,
+      "logits/rejected": 10.63122844696045,
+      "logps/chosen": -162.94578552246094,
+      "logps/ref_chosen": -158.10250854492188,
+      "logps/ref_rejected": -169.85250854492188,
+      "logps/rejected": -174.79525756835938,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.04843292012810707,
+      "rewards/margins": 0.0009945080382749438,
+      "rewards/rejected": -0.04942742735147476,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.46131113171577454,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.260627746582031,
+      "logits/rejected": 10.424566268920898,
+      "logps/chosen": -163.2139129638672,
+      "logps/ref_chosen": -158.93540954589844,
+      "logps/ref_rejected": -168.12344360351562,
+      "logps/rejected": -172.52456665039062,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.042785100638866425,
+      "rewards/margins": 0.0012263581156730652,
+      "rewards/rejected": -0.04401145875453949,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.4610799252986908,
+      "learning_rate": 4.246923569447104e-07,
+      "logits/chosen": 10.461551666259766,
+      "logits/rejected": 10.855925559997559,
+      "logps/chosen": -165.60084533691406,
+      "logps/ref_chosen": -161.0833740234375,
+      "logps/ref_rejected": -174.85760498046875,
+      "logps/rejected": -179.20965576171875,
+      "loss": 0.694,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.0451747290790081,
+      "rewards/margins": -0.0016541833756491542,
+      "rewards/rejected": -0.043520547449588776,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 0.41953545808792114,
+      "learning_rate": 4.161178683597054e-07,
+      "logits/chosen": 10.611435890197754,
+      "logits/rejected": 10.745625495910645,
+      "logps/chosen": -160.7465057373047,
+      "logps/ref_chosen": -156.07315063476562,
+      "logps/ref_rejected": -161.84292602539062,
+      "logps/rejected": -166.85279846191406,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.046733610332012177,
+      "rewards/margins": 0.0033648861572146416,
+      "rewards/rejected": -0.05009850114583969,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.3880956470966339,
+      "learning_rate": 4.0717821664772124e-07,
+      "logits/chosen": 10.590215682983398,
+      "logits/rejected": 10.893061637878418,
+      "logps/chosen": -168.67279052734375,
+      "logps/ref_chosen": -163.2271728515625,
+      "logps/ref_rejected": -171.53738403320312,
+      "logps/rejected": -176.9310302734375,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.05445636808872223,
+      "rewards/margins": -0.00051975465612486,
+      "rewards/rejected": -0.05393661558628082,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.5345169901847839,
+      "learning_rate": 3.978930531033806e-07,
+      "logits/chosen": 9.953861236572266,
+      "logits/rejected": 10.416406631469727,
+      "logps/chosen": -162.322021484375,
+      "logps/ref_chosen": -157.08795166015625,
+      "logps/ref_rejected": -167.1195068359375,
+      "logps/rejected": -172.4853973388672,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.0523407980799675,
+      "rewards/margins": 0.001318173250183463,
+      "rewards/rejected": -0.053658969700336456,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.5297831296920776,
+      "learning_rate": 3.882827885312998e-07,
+      "logits/chosen": 10.323142051696777,
+      "logits/rejected": 10.501938819885254,
+      "logps/chosen": -168.2061004638672,
+      "logps/ref_chosen": -163.59707641601562,
+      "logps/ref_rejected": -171.89508056640625,
+      "logps/rejected": -176.55738830566406,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.04609035328030586,
+      "rewards/margins": 0.0005328265833668411,
+      "rewards/rejected": -0.04662318155169487,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.35810208320617676,
+      "learning_rate": 3.7836854837871044e-07,
+      "logits/chosen": 10.40945053100586,
+      "logits/rejected": 10.931025505065918,
+      "logps/chosen": -169.71910095214844,
+      "logps/ref_chosen": -164.91160583496094,
+      "logps/ref_rejected": -176.66453552246094,
+      "logps/rejected": -181.69285583496094,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.04807499051094055,
+      "rewards/margins": 0.0022084712982177734,
+      "rewards/rejected": -0.050283461809158325,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.44152358174324036,
+      "learning_rate": 3.681721262971413e-07,
+      "logits/chosen": 10.004611015319824,
+      "logits/rejected": 10.491472244262695,
+      "logps/chosen": -161.24798583984375,
+      "logps/ref_chosen": -155.95877075195312,
+      "logps/ref_rejected": -166.5852508544922,
+      "logps/rejected": -172.22703552246094,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.052892111241817474,
+      "rewards/margins": 0.003525771899148822,
+      "rewards/rejected": -0.05641787871718407,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.5185390114784241,
+      "learning_rate": 3.577159362352426e-07,
+      "logits/chosen": 10.27377986907959,
+      "logits/rejected": 10.56481647491455,
+      "logps/chosen": -167.19921875,
+      "logps/ref_chosen": -161.83575439453125,
+      "logps/ref_rejected": -169.53759765625,
+      "logps/rejected": -174.91342163085938,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.05363469570875168,
+      "rewards/margins": 0.00012344191782176495,
+      "rewards/rejected": -0.05375813692808151,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 1.1196942329406738,
+      "learning_rate": 3.470229631680624e-07,
+      "logits/chosen": 10.063702583312988,
+      "logits/rejected": 10.693009376525879,
+      "logps/chosen": -164.40225219726562,
+      "logps/ref_chosen": -158.7517547607422,
+      "logps/ref_rejected": -168.51002502441406,
+      "logps/rejected": -174.00901794433594,
+      "loss": 0.694,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.056504976004362106,
+      "rewards/margins": -0.0015149968676269054,
+      "rewards/rejected": -0.054989978671073914,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.593383252620697,
+      "learning_rate": 3.361167125710832e-07,
+      "logits/chosen": 9.993782043457031,
+      "logits/rejected": 10.380085945129395,
+      "logps/chosen": -170.81832885742188,
+      "logps/ref_chosen": -165.12754821777344,
+      "logps/ref_rejected": -177.654296875,
+      "logps/rejected": -183.54998779296875,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.05690779164433479,
+      "rewards/margins": 0.0020490488968789577,
+      "rewards/rejected": -0.05895683914422989,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.4870688319206238,
+      "learning_rate": 3.2502115875008516e-07,
+      "logits/chosen": 10.418455123901367,
+      "logits/rejected": 10.655467987060547,
+      "logps/chosen": -165.74551391601562,
+      "logps/ref_chosen": -159.895751953125,
+      "logps/ref_rejected": -167.39785766601562,
+      "logps/rejected": -173.5540008544922,
+      "loss": 0.6917,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.058497510850429535,
+      "rewards/margins": 0.0030638885218650103,
+      "rewards/rejected": -0.06156139820814133,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.9538622498512268,
+      "learning_rate": 3.137606921404191e-07,
+      "logits/chosen": 10.286083221435547,
+      "logits/rejected": 10.6614408493042,
+      "logps/chosen": -170.4355926513672,
+      "logps/ref_chosen": -165.02023315429688,
+      "logps/ref_rejected": -172.28997802734375,
+      "logps/rejected": -177.64358520507812,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.05415371432900429,
+      "rewards/margins": -0.0006177356699481606,
+      "rewards/rejected": -0.053535979241132736,
+      "step": 36
+    },
+    {
+      "epoch": 0.4874433923425278,
+      "grad_norm": 0.6481872200965881,
+      "learning_rate": 3.0236006569153616e-07,
+      "logits/chosen": 10.281628608703613,
+      "logits/rejected": 10.485464096069336,
+      "logps/chosen": -167.83177185058594,
+      "logps/ref_chosen": -162.57997131347656,
+      "logps/ref_rejected": -174.94447326660156,
+      "logps/rejected": -180.6204833984375,
+      "loss": 0.6911,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.05251805856823921,
+      "rewards/margins": 0.004242150578647852,
+      "rewards/rejected": -0.056760210543870926,
+      "step": 37
+    },
+    {
+      "epoch": 0.500617538081515,
+      "grad_norm": 0.6258410215377808,
+      "learning_rate": 2.9084434045463254e-07,
+      "logits/chosen": 10.348075866699219,
+      "logits/rejected": 10.585733413696289,
+      "logps/chosen": -170.00047302246094,
+      "logps/ref_chosen": -164.2234649658203,
+      "logps/ref_rejected": -170.92135620117188,
+      "logps/rejected": -177.09783935546875,
+      "loss": 0.6912,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.05776997655630112,
+      "rewards/margins": 0.003995058126747608,
+      "rewards/rejected": -0.06176503747701645,
+      "step": 38
+    },
+    {
+      "epoch": 0.5137916838205022,
+      "grad_norm": 0.45227017998695374,
+      "learning_rate": 2.7923883049302066e-07,
+      "logits/chosen": 10.290374755859375,
+      "logits/rejected": 10.424775123596191,
+      "logps/chosen": -172.98834228515625,
+      "logps/ref_chosen": -166.5240478515625,
+      "logps/ref_rejected": -174.45970153808594,
+      "logps/rejected": -180.691162109375,
+      "loss": 0.6944,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.0646430104970932,
+      "rewards/margins": -0.002328395377844572,
+      "rewards/rejected": -0.06231461465358734,
+      "step": 39
+    },
+    {
+      "epoch": 0.5269658295594895,
+      "grad_norm": 0.7223658561706543,
+      "learning_rate": 2.6756904723632324e-07,
+      "logits/chosen": 10.33895492553711,
+      "logits/rejected": 10.744306564331055,
+      "logps/chosen": -162.80517578125,
+      "logps/ref_chosen": -156.39364624023438,
+      "logps/ref_rejected": -172.6676483154297,
+      "logps/rejected": -178.97576904296875,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.06411512196063995,
+      "rewards/margins": -0.0010338453575968742,
+      "rewards/rejected": -0.0630812719464302,
+      "step": 40
+    },
+    {
+      "epoch": 0.5401399752984768,
+      "grad_norm": 0.9710007905960083,
+      "learning_rate": 2.5586064340081516e-07,
+      "logits/chosen": 10.650144577026367,
+      "logits/rejected": 10.64175796508789,
+      "logps/chosen": -164.384765625,
+      "logps/ref_chosen": -158.60899353027344,
+      "logps/ref_rejected": -167.36000061035156,
+      "logps/rejected": -173.48138427734375,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.057757824659347534,
+      "rewards/margins": 0.0034558887127786875,
+      "rewards/rejected": -0.061213716864585876,
+      "step": 41
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": 1.060659408569336,
+      "learning_rate": 2.4413935659918487e-07,
+      "logits/chosen": 9.889198303222656,
+      "logits/rejected": 10.20853042602539,
+      "logps/chosen": -161.29913330078125,
+      "logps/ref_chosen": -155.86929321289062,
+      "logps/ref_rejected": -164.31619262695312,
+      "logps/rejected": -170.2007598876953,
+      "loss": 0.691,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.05429830774664879,
+      "rewards/margins": 0.004547302611172199,
+      "rewards/rejected": -0.05884561315178871,
+      "step": 42
+    },
+    {
+      "epoch": 0.5664882667764513,
+      "grad_norm": 0.5962560176849365,
+      "learning_rate": 2.3243095276367684e-07,
+      "logits/chosen": 9.809310913085938,
+      "logits/rejected": 10.134492874145508,
+      "logps/chosen": -155.75411987304688,
+      "logps/ref_chosen": -149.69866943359375,
+      "logps/ref_rejected": -163.860107421875,
+      "logps/rejected": -170.56063842773438,
+      "loss": 0.69,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.06055447459220886,
+      "rewards/margins": 0.006450990214943886,
+      "rewards/rejected": -0.0670054703950882,
+      "step": 43
+    },
+    {
+      "epoch": 0.5796624125154385,
+      "grad_norm": 0.38942375779151917,
+      "learning_rate": 2.2076116950697937e-07,
+      "logits/chosen": 10.249410629272461,
+      "logits/rejected": 10.454606056213379,
+      "logps/chosen": -161.172119140625,
+      "logps/ref_chosen": -155.06076049804688,
+      "logps/ref_rejected": -161.446044921875,
+      "logps/rejected": -167.66583251953125,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.06111355125904083,
+      "rewards/margins": 0.0010843212949112058,
+      "rewards/rejected": -0.06219786778092384,
+      "step": 44
+    },
+    {
+      "epoch": 0.5928365582544257,
+      "grad_norm": 0.3398829996585846,
+      "learning_rate": 2.091556595453674e-07,
+      "logits/chosen": 10.017583847045898,
+      "logits/rejected": 10.271501541137695,
+      "logps/chosen": -169.4973907470703,
+      "logps/ref_chosen": -163.5751190185547,
+      "logps/ref_rejected": -176.65078735351562,
+      "logps/rejected": -183.13449096679688,
+      "loss": 0.6904,
+      "rewards/accuracies": 0.6015625,
+      "rewards/chosen": -0.059222809970378876,
+      "rewards/margins": 0.005614194553345442,
+      "rewards/rejected": -0.0648370012640953,
+      "step": 45
+    },
+    {
+      "epoch": 0.606010703993413,
+      "grad_norm": 0.5492353439331055,
+      "learning_rate": 1.9763993430846392e-07,
+      "logits/chosen": 10.156986236572266,
+      "logits/rejected": 10.36589241027832,
+      "logps/chosen": -168.26568603515625,
+      "logps/ref_chosen": -162.17233276367188,
+      "logps/ref_rejected": -169.48728942871094,
+      "logps/rejected": -176.28375244140625,
+      "loss": 0.6897,
+      "rewards/accuracies": 0.6015625,
+      "rewards/chosen": -0.06093353033065796,
+      "rewards/margins": 0.007031145039945841,
+      "rewards/rejected": -0.06796467304229736,
+      "step": 46
+    },
+    {
+      "epoch": 0.6191848497324002,
+      "grad_norm": 0.361573725938797,
+      "learning_rate": 1.862393078595809e-07,
+      "logits/chosen": 10.36301040649414,
+      "logits/rejected": 10.790814399719238,
+      "logps/chosen": -164.67152404785156,
+      "logps/ref_chosen": -158.01217651367188,
+      "logps/ref_rejected": -170.02401733398438,
+      "logps/rejected": -177.1544189453125,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.06659334897994995,
+      "rewards/margins": 0.004710891284048557,
+      "rewards/rejected": -0.07130423933267593,
+      "step": 47
+    },
+    {
+      "epoch": 0.6323589954713874,
+      "grad_norm": 0.49494439363479614,
+      "learning_rate": 1.7497884124991485e-07,
+      "logits/chosen": 10.640326499938965,
+      "logits/rejected": 10.784747123718262,
+      "logps/chosen": -170.2487335205078,
+      "logps/ref_chosen": -163.1754608154297,
+      "logps/ref_rejected": -171.04629516601562,
+      "logps/rejected": -178.30601501464844,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.07073251903057098,
+      "rewards/margins": 0.0018647168762981892,
+      "rewards/rejected": -0.07259723544120789,
+      "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 sha256:943aba53589edd9d99ac81ea6697d5edece074bcd9108c5ff0d149ce3b34fcd3
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61747e67dd22f0c41802ce10d9a89f9e4bd09f442c230efa2aa8841093348889
+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
+  }
+}