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": 9.191950798034668,
+    "eval_logits/rejected": 9.997398376464844,
+    "eval_logps/chosen": -115.93839263916016,
+    "eval_logps/ref_chosen": -106.16099548339844,
+    "eval_logps/ref_rejected": -119.78473663330078,
+    "eval_logps/rejected": -130.08287048339844,
+    "eval_loss": 0.6909545063972473,
+    "eval_rewards/accuracies": 0.539814829826355,
+    "eval_rewards/chosen": -0.09777405112981796,
+    "eval_rewards/margins": 0.0052073062397539616,
+    "eval_rewards/rejected": -0.10298136621713638,
+    "eval_runtime": 171.06,
+    "eval_samples": 1080,
+    "eval_samples_per_second": 6.314,
+    "eval_steps_per_second": 1.578,
+    "total_flos": 0.0,
+    "train_loss": 0.6924255990982056,
+    "train_runtime": 7990.9765,
+    "train_samples": 9715,
+    "train_samples_per_second": 1.216,
+    "train_steps_per_second": 0.009
+}

checkpoint-12/added_tokens.json

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

checkpoint-12/config.json

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

checkpoint-12/generation_config.json

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d817980959d699a32d7722bdf4dca75bb458d9e1189510f551057a4845cea273
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14c9c0e83cae49890f87e93a204fe686cdb0803b4e84905f960cf55fc643f04
+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": 0.3937181234359741,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.038352012634277,
+      "logits/rejected": 10.592904090881348,
+      "logps/chosen": -132.56948852539062,
+      "logps/ref_chosen": -132.56948852539062,
+      "logps/ref_rejected": -148.778076171875,
+      "logps/rejected": -148.778076171875,
+      "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": 0.7554967999458313,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.320584297180176,
+      "logits/rejected": 10.721946716308594,
+      "logps/chosen": -132.46385192871094,
+      "logps/ref_chosen": -132.46385192871094,
+      "logps/ref_rejected": -142.69049072265625,
+      "logps/rejected": -142.69049072265625,
+      "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": 0.5059730410575867,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 9.891550064086914,
+      "logits/rejected": 10.499095916748047,
+      "logps/chosen": -136.52415466308594,
+      "logps/ref_chosen": -135.79869079589844,
+      "logps/ref_rejected": -145.69479370117188,
+      "logps/rejected": -146.24124145507812,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.3984375,
+      "rewards/chosen": -0.007254539057612419,
+      "rewards/margins": -0.0017902727704495192,
+      "rewards/rejected": -0.005464266519993544,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.6780113577842712,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.122194290161133,
+      "logits/rejected": 10.64792251586914,
+      "logps/chosen": -137.41903686523438,
+      "logps/ref_chosen": -136.85159301757812,
+      "logps/ref_rejected": -142.64901733398438,
+      "logps/rejected": -142.94912719726562,
+      "loss": 0.6945,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00567453121766448,
+      "rewards/margins": -0.0026732482947409153,
+      "rewards/rejected": -0.0030012831557542086,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.5103796124458313,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.327558517456055,
+      "logits/rejected": 11.079102516174316,
+      "logps/chosen": -130.6144561767578,
+      "logps/ref_chosen": -130.2961883544922,
+      "logps/ref_rejected": -144.1498565673828,
+      "logps/rejected": -144.40802001953125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.0031829699873924255,
+      "rewards/margins": -0.000601244973950088,
+      "rewards/rejected": -0.0025817248970270157,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.7068921327590942,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.794892311096191,
+      "logits/rejected": 11.326902389526367,
+      "logps/chosen": -138.65377807617188,
+      "logps/ref_chosen": -138.59861755371094,
+      "logps/ref_rejected": -151.63775634765625,
+      "logps/rejected": -151.48056030273438,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.0005516067612916231,
+      "rewards/margins": -0.002123636193573475,
+      "rewards/rejected": 0.0015720291994512081,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.4639431834220886,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.949363708496094,
+      "logits/rejected": 10.44249153137207,
+      "logps/chosen": -130.56231689453125,
+      "logps/ref_chosen": -129.5895538330078,
+      "logps/ref_rejected": -139.67816162109375,
+      "logps/rejected": -140.58245849609375,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.009727789089083672,
+      "rewards/margins": -0.000684772094246,
+      "rewards/rejected": -0.009043017402291298,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.5582533478736877,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.655470848083496,
+      "logits/rejected": 11.168412208557129,
+      "logps/chosen": -134.7186737060547,
+      "logps/ref_chosen": -134.24497985839844,
+      "logps/ref_rejected": -147.19009399414062,
+      "logps/rejected": -147.70596313476562,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.0047368621453642845,
+      "rewards/margins": 0.0004215884255245328,
+      "rewards/rejected": -0.0051584504544734955,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.559306263923645,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.525918006896973,
+      "logits/rejected": 10.821675300598145,
+      "logps/chosen": -142.31239318847656,
+      "logps/ref_chosen": -141.59860229492188,
+      "logps/ref_rejected": -149.33889770507812,
+      "logps/rejected": -149.89822387695312,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4140625,
+      "rewards/chosen": -0.007138015236705542,
+      "rewards/margins": -0.001544784870930016,
+      "rewards/rejected": -0.005593230482190847,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6123551726341248,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 10.101277351379395,
+      "logits/rejected": 10.55870246887207,
+      "logps/chosen": -133.06532287597656,
+      "logps/ref_chosen": -132.13449096679688,
+      "logps/ref_rejected": -142.75973510742188,
+      "logps/rejected": -143.90049743652344,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.00930829904973507,
+      "rewards/margins": 0.002099357545375824,
+      "rewards/rejected": -0.011407657526433468,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.6729086637496948,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.170294761657715,
+      "logits/rejected": 10.829442024230957,
+      "logps/chosen": -137.3282012939453,
+      "logps/ref_chosen": -135.85043334960938,
+      "logps/ref_rejected": -152.14999389648438,
+      "logps/rejected": -153.4501953125,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.014777721837162971,
+      "rewards/margins": -0.0017757893074303865,
+      "rewards/rejected": -0.013001934625208378,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.3486435115337372,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.261972427368164,
+      "logits/rejected": 10.63994312286377,
+      "logps/chosen": -141.65684509277344,
+      "logps/ref_chosen": -139.63204956054688,
+      "logps/ref_rejected": -148.03170776367188,
+      "logps/rejected": -150.0493621826172,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.02024805173277855,
+      "rewards/margins": -7.15737696737051e-05,
+      "rewards/rejected": -0.0201764777302742,
+      "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 sha256:213dc2a9b6846290dc8f0f9585441e80491f246025615c7f8220699a2e958ee3
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2baf0f93c9293198c58a6264b901402f9097e7b3f38c119ecd2505f52b96590
+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": 0.3937181234359741,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.038352012634277,
+      "logits/rejected": 10.592904090881348,
+      "logps/chosen": -132.56948852539062,
+      "logps/ref_chosen": -132.56948852539062,
+      "logps/ref_rejected": -148.778076171875,
+      "logps/rejected": -148.778076171875,
+      "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": 0.7554967999458313,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.320584297180176,
+      "logits/rejected": 10.721946716308594,
+      "logps/chosen": -132.46385192871094,
+      "logps/ref_chosen": -132.46385192871094,
+      "logps/ref_rejected": -142.69049072265625,
+      "logps/rejected": -142.69049072265625,
+      "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": 0.5059730410575867,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 9.891550064086914,
+      "logits/rejected": 10.499095916748047,
+      "logps/chosen": -136.52415466308594,
+      "logps/ref_chosen": -135.79869079589844,
+      "logps/ref_rejected": -145.69479370117188,
+      "logps/rejected": -146.24124145507812,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.3984375,
+      "rewards/chosen": -0.007254539057612419,
+      "rewards/margins": -0.0017902727704495192,
+      "rewards/rejected": -0.005464266519993544,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.6780113577842712,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.122194290161133,
+      "logits/rejected": 10.64792251586914,
+      "logps/chosen": -137.41903686523438,
+      "logps/ref_chosen": -136.85159301757812,
+      "logps/ref_rejected": -142.64901733398438,
+      "logps/rejected": -142.94912719726562,
+      "loss": 0.6945,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00567453121766448,
+      "rewards/margins": -0.0026732482947409153,
+      "rewards/rejected": -0.0030012831557542086,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.5103796124458313,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.327558517456055,
+      "logits/rejected": 11.079102516174316,
+      "logps/chosen": -130.6144561767578,
+      "logps/ref_chosen": -130.2961883544922,
+      "logps/ref_rejected": -144.1498565673828,
+      "logps/rejected": -144.40802001953125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.0031829699873924255,
+      "rewards/margins": -0.000601244973950088,
+      "rewards/rejected": -0.0025817248970270157,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.7068921327590942,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.794892311096191,
+      "logits/rejected": 11.326902389526367,
+      "logps/chosen": -138.65377807617188,
+      "logps/ref_chosen": -138.59861755371094,
+      "logps/ref_rejected": -151.63775634765625,
+      "logps/rejected": -151.48056030273438,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.0005516067612916231,
+      "rewards/margins": -0.002123636193573475,
+      "rewards/rejected": 0.0015720291994512081,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.4639431834220886,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.949363708496094,
+      "logits/rejected": 10.44249153137207,
+      "logps/chosen": -130.56231689453125,
+      "logps/ref_chosen": -129.5895538330078,
+      "logps/ref_rejected": -139.67816162109375,
+      "logps/rejected": -140.58245849609375,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.009727789089083672,
+      "rewards/margins": -0.000684772094246,
+      "rewards/rejected": -0.009043017402291298,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.5582533478736877,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.655470848083496,
+      "logits/rejected": 11.168412208557129,
+      "logps/chosen": -134.7186737060547,
+      "logps/ref_chosen": -134.24497985839844,
+      "logps/ref_rejected": -147.19009399414062,
+      "logps/rejected": -147.70596313476562,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.0047368621453642845,
+      "rewards/margins": 0.0004215884255245328,
+      "rewards/rejected": -0.0051584504544734955,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.559306263923645,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.525918006896973,
+      "logits/rejected": 10.821675300598145,
+      "logps/chosen": -142.31239318847656,
+      "logps/ref_chosen": -141.59860229492188,
+      "logps/ref_rejected": -149.33889770507812,
+      "logps/rejected": -149.89822387695312,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4140625,
+      "rewards/chosen": -0.007138015236705542,
+      "rewards/margins": -0.001544784870930016,
+      "rewards/rejected": -0.005593230482190847,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6123551726341248,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 10.101277351379395,
+      "logits/rejected": 10.55870246887207,
+      "logps/chosen": -133.06532287597656,
+      "logps/ref_chosen": -132.13449096679688,
+      "logps/ref_rejected": -142.75973510742188,
+      "logps/rejected": -143.90049743652344,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.00930829904973507,
+      "rewards/margins": 0.002099357545375824,
+      "rewards/rejected": -0.011407657526433468,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.6729086637496948,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.170294761657715,
+      "logits/rejected": 10.829442024230957,
+      "logps/chosen": -137.3282012939453,
+      "logps/ref_chosen": -135.85043334960938,
+      "logps/ref_rejected": -152.14999389648438,
+      "logps/rejected": -153.4501953125,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.014777721837162971,
+      "rewards/margins": -0.0017757893074303865,
+      "rewards/rejected": -0.013001934625208378,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.3486435115337372,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.261972427368164,
+      "logits/rejected": 10.63994312286377,
+      "logps/chosen": -141.65684509277344,
+      "logps/ref_chosen": -139.63204956054688,
+      "logps/ref_rejected": -148.03170776367188,
+      "logps/rejected": -150.0493621826172,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.02024805173277855,
+      "rewards/margins": -7.15737696737051e-05,
+      "rewards/rejected": -0.0201764777302742,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5037537813186646,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.811729431152344,
+      "logits/rejected": 10.610340118408203,
+      "logps/chosen": -131.98635864257812,
+      "logps/ref_chosen": -129.56983947753906,
+      "logps/ref_rejected": -143.01284790039062,
+      "logps/rejected": -145.4197998046875,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.024165067821741104,
+      "rewards/margins": -9.549467358738184e-05,
+      "rewards/rejected": -0.024069571867585182,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 1.0056744813919067,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.571147918701172,
+      "logits/rejected": 11.290738105773926,
+      "logps/chosen": -132.96786499023438,
+      "logps/ref_chosen": -130.44677734375,
+      "logps/ref_rejected": -142.0145721435547,
+      "logps/rejected": -144.57803344726562,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.025210827589035034,
+      "rewards/margins": 0.0004238423425704241,
+      "rewards/rejected": -0.02563466690480709,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.44761258363723755,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.930328369140625,
+      "logits/rejected": 10.632352828979492,
+      "logps/chosen": -137.48495483398438,
+      "logps/ref_chosen": -133.87620544433594,
+      "logps/ref_rejected": -146.4284210205078,
+      "logps/rejected": -150.177490234375,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.036087535321712494,
+      "rewards/margins": 0.0014031402533873916,
+      "rewards/rejected": -0.03749067336320877,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7480736970901489,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.873997688293457,
+      "logits/rejected": 11.219457626342773,
+      "logps/chosen": -138.66485595703125,
+      "logps/ref_chosen": -135.57931518554688,
+      "logps/ref_rejected": -144.543701171875,
+      "logps/rejected": -147.69003295898438,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.0308553334325552,
+      "rewards/margins": 0.0006078272126615047,
+      "rewards/rejected": -0.03146316111087799,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.5350177884101868,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.29094409942627,
+      "logits/rejected": 10.750887870788574,
+      "logps/chosen": -130.87939453125,
+      "logps/ref_chosen": -127.53980255126953,
+      "logps/ref_rejected": -141.44097900390625,
+      "logps/rejected": -144.80685424804688,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.03339584171772003,
+      "rewards/margins": 0.0002629577647894621,
+      "rewards/rejected": -0.03365879878401756,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.6819839477539062,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.341330528259277,
+      "logits/rejected": 10.997025489807129,
+      "logps/chosen": -135.26243591308594,
+      "logps/ref_chosen": -130.62847900390625,
+      "logps/ref_rejected": -141.88360595703125,
+      "logps/rejected": -146.40476989746094,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.046339523047208786,
+      "rewards/margins": -0.001128039206378162,
+      "rewards/rejected": -0.045211486518383026,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.5013086199760437,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.433052062988281,
+      "logits/rejected": 10.780852317810059,
+      "logps/chosen": -140.90821838378906,
+      "logps/ref_chosen": -136.1767120361328,
+      "logps/ref_rejected": -148.38580322265625,
+      "logps/rejected": -153.79835510253906,
+      "loss": 0.6898,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.0473150797188282,
+      "rewards/margins": 0.006810260470956564,
+      "rewards/rejected": -0.0541253462433815,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.5322529673576355,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.486635208129883,
+      "logits/rejected": 11.192235946655273,
+      "logps/chosen": -140.9699249267578,
+      "logps/ref_chosen": -134.8175048828125,
+      "logps/ref_rejected": -145.92430114746094,
+      "logps/rejected": -151.58935546875,
+      "loss": 0.6957,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.06152408942580223,
+      "rewards/margins": -0.004873568192124367,
+      "rewards/rejected": -0.056650519371032715,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.426982581615448,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.691137313842773,
+      "logits/rejected": 10.519243240356445,
+      "logps/chosen": -137.68182373046875,
+      "logps/ref_chosen": -131.53555297851562,
+      "logps/ref_rejected": -147.749267578125,
+      "logps/rejected": -154.18560791015625,
+      "loss": 0.6918,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.061462655663490295,
+      "rewards/margins": 0.002900664694607258,
+      "rewards/rejected": -0.06436331570148468,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.39799365401268005,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.019172668457031,
+      "logits/rejected": 10.592238426208496,
+      "logps/chosen": -137.14170837402344,
+      "logps/ref_chosen": -129.1536865234375,
+      "logps/ref_rejected": -138.03895568847656,
+      "logps/rejected": -145.4950714111328,
+      "loss": 0.6959,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.07987993955612183,
+      "rewards/margins": -0.005318798590451479,
+      "rewards/rejected": -0.07456114143133163,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.6805318593978882,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 9.99167251586914,
+      "logits/rejected": 10.793407440185547,
+      "logps/chosen": -139.6283416748047,
+      "logps/ref_chosen": -131.8021240234375,
+      "logps/ref_rejected": -144.97862243652344,
+      "logps/rejected": -152.63169860839844,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.07826196402311325,
+      "rewards/margins": -0.0017311733681708574,
+      "rewards/rejected": -0.07653079926967621,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5804150104522705,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.220123291015625,
+      "logits/rejected": 10.670228958129883,
+      "logps/chosen": -141.5391387939453,
+      "logps/ref_chosen": -134.2378692626953,
+      "logps/ref_rejected": -146.93955993652344,
+      "logps/rejected": -154.45404052734375,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.07301273196935654,
+      "rewards/margins": 0.0021319000516086817,
+      "rewards/rejected": -0.07514464110136032,
+      "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 sha256:83c551480902506b6225fbaa9d027310f28ea00b788601029c5e947cafef2c91
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:214f132f1269c697ec69a285a35e66cdde6008f611aa1a9d83cab06739f393ca
+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": 0.3937181234359741,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.038352012634277,
+      "logits/rejected": 10.592904090881348,
+      "logps/chosen": -132.56948852539062,
+      "logps/ref_chosen": -132.56948852539062,
+      "logps/ref_rejected": -148.778076171875,
+      "logps/rejected": -148.778076171875,
+      "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": 0.7554967999458313,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.320584297180176,
+      "logits/rejected": 10.721946716308594,
+      "logps/chosen": -132.46385192871094,
+      "logps/ref_chosen": -132.46385192871094,
+      "logps/ref_rejected": -142.69049072265625,
+      "logps/rejected": -142.69049072265625,
+      "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": 0.5059730410575867,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 9.891550064086914,
+      "logits/rejected": 10.499095916748047,
+      "logps/chosen": -136.52415466308594,
+      "logps/ref_chosen": -135.79869079589844,
+      "logps/ref_rejected": -145.69479370117188,
+      "logps/rejected": -146.24124145507812,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.3984375,
+      "rewards/chosen": -0.007254539057612419,
+      "rewards/margins": -0.0017902727704495192,
+      "rewards/rejected": -0.005464266519993544,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.6780113577842712,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.122194290161133,
+      "logits/rejected": 10.64792251586914,
+      "logps/chosen": -137.41903686523438,
+      "logps/ref_chosen": -136.85159301757812,
+      "logps/ref_rejected": -142.64901733398438,
+      "logps/rejected": -142.94912719726562,
+      "loss": 0.6945,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00567453121766448,
+      "rewards/margins": -0.0026732482947409153,
+      "rewards/rejected": -0.0030012831557542086,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.5103796124458313,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.327558517456055,
+      "logits/rejected": 11.079102516174316,
+      "logps/chosen": -130.6144561767578,
+      "logps/ref_chosen": -130.2961883544922,
+      "logps/ref_rejected": -144.1498565673828,
+      "logps/rejected": -144.40802001953125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.0031829699873924255,
+      "rewards/margins": -0.000601244973950088,
+      "rewards/rejected": -0.0025817248970270157,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.7068921327590942,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.794892311096191,
+      "logits/rejected": 11.326902389526367,
+      "logps/chosen": -138.65377807617188,
+      "logps/ref_chosen": -138.59861755371094,
+      "logps/ref_rejected": -151.63775634765625,
+      "logps/rejected": -151.48056030273438,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.0005516067612916231,
+      "rewards/margins": -0.002123636193573475,
+      "rewards/rejected": 0.0015720291994512081,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.4639431834220886,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.949363708496094,
+      "logits/rejected": 10.44249153137207,
+      "logps/chosen": -130.56231689453125,
+      "logps/ref_chosen": -129.5895538330078,
+      "logps/ref_rejected": -139.67816162109375,
+      "logps/rejected": -140.58245849609375,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.009727789089083672,
+      "rewards/margins": -0.000684772094246,
+      "rewards/rejected": -0.009043017402291298,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.5582533478736877,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.655470848083496,
+      "logits/rejected": 11.168412208557129,
+      "logps/chosen": -134.7186737060547,
+      "logps/ref_chosen": -134.24497985839844,
+      "logps/ref_rejected": -147.19009399414062,
+      "logps/rejected": -147.70596313476562,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.0047368621453642845,
+      "rewards/margins": 0.0004215884255245328,
+      "rewards/rejected": -0.0051584504544734955,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.559306263923645,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.525918006896973,
+      "logits/rejected": 10.821675300598145,
+      "logps/chosen": -142.31239318847656,
+      "logps/ref_chosen": -141.59860229492188,
+      "logps/ref_rejected": -149.33889770507812,
+      "logps/rejected": -149.89822387695312,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4140625,
+      "rewards/chosen": -0.007138015236705542,
+      "rewards/margins": -0.001544784870930016,
+      "rewards/rejected": -0.005593230482190847,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6123551726341248,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 10.101277351379395,
+      "logits/rejected": 10.55870246887207,
+      "logps/chosen": -133.06532287597656,
+      "logps/ref_chosen": -132.13449096679688,
+      "logps/ref_rejected": -142.75973510742188,
+      "logps/rejected": -143.90049743652344,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.00930829904973507,
+      "rewards/margins": 0.002099357545375824,
+      "rewards/rejected": -0.011407657526433468,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.6729086637496948,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.170294761657715,
+      "logits/rejected": 10.829442024230957,
+      "logps/chosen": -137.3282012939453,
+      "logps/ref_chosen": -135.85043334960938,
+      "logps/ref_rejected": -152.14999389648438,
+      "logps/rejected": -153.4501953125,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.014777721837162971,
+      "rewards/margins": -0.0017757893074303865,
+      "rewards/rejected": -0.013001934625208378,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.3486435115337372,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.261972427368164,
+      "logits/rejected": 10.63994312286377,
+      "logps/chosen": -141.65684509277344,
+      "logps/ref_chosen": -139.63204956054688,
+      "logps/ref_rejected": -148.03170776367188,
+      "logps/rejected": -150.0493621826172,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.02024805173277855,
+      "rewards/margins": -7.15737696737051e-05,
+      "rewards/rejected": -0.0201764777302742,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5037537813186646,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.811729431152344,
+      "logits/rejected": 10.610340118408203,
+      "logps/chosen": -131.98635864257812,
+      "logps/ref_chosen": -129.56983947753906,
+      "logps/ref_rejected": -143.01284790039062,
+      "logps/rejected": -145.4197998046875,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.024165067821741104,
+      "rewards/margins": -9.549467358738184e-05,
+      "rewards/rejected": -0.024069571867585182,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 1.0056744813919067,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.571147918701172,
+      "logits/rejected": 11.290738105773926,
+      "logps/chosen": -132.96786499023438,
+      "logps/ref_chosen": -130.44677734375,
+      "logps/ref_rejected": -142.0145721435547,
+      "logps/rejected": -144.57803344726562,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.025210827589035034,
+      "rewards/margins": 0.0004238423425704241,
+      "rewards/rejected": -0.02563466690480709,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.44761258363723755,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.930328369140625,
+      "logits/rejected": 10.632352828979492,
+      "logps/chosen": -137.48495483398438,
+      "logps/ref_chosen": -133.87620544433594,
+      "logps/ref_rejected": -146.4284210205078,
+      "logps/rejected": -150.177490234375,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.036087535321712494,
+      "rewards/margins": 0.0014031402533873916,
+      "rewards/rejected": -0.03749067336320877,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7480736970901489,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.873997688293457,
+      "logits/rejected": 11.219457626342773,
+      "logps/chosen": -138.66485595703125,
+      "logps/ref_chosen": -135.57931518554688,
+      "logps/ref_rejected": -144.543701171875,
+      "logps/rejected": -147.69003295898438,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.0308553334325552,
+      "rewards/margins": 0.0006078272126615047,
+      "rewards/rejected": -0.03146316111087799,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.5350177884101868,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.29094409942627,
+      "logits/rejected": 10.750887870788574,
+      "logps/chosen": -130.87939453125,
+      "logps/ref_chosen": -127.53980255126953,
+      "logps/ref_rejected": -141.44097900390625,
+      "logps/rejected": -144.80685424804688,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.03339584171772003,
+      "rewards/margins": 0.0002629577647894621,
+      "rewards/rejected": -0.03365879878401756,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.6819839477539062,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.341330528259277,
+      "logits/rejected": 10.997025489807129,
+      "logps/chosen": -135.26243591308594,
+      "logps/ref_chosen": -130.62847900390625,
+      "logps/ref_rejected": -141.88360595703125,
+      "logps/rejected": -146.40476989746094,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.046339523047208786,
+      "rewards/margins": -0.001128039206378162,
+      "rewards/rejected": -0.045211486518383026,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.5013086199760437,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.433052062988281,
+      "logits/rejected": 10.780852317810059,
+      "logps/chosen": -140.90821838378906,
+      "logps/ref_chosen": -136.1767120361328,
+      "logps/ref_rejected": -148.38580322265625,
+      "logps/rejected": -153.79835510253906,
+      "loss": 0.6898,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.0473150797188282,
+      "rewards/margins": 0.006810260470956564,
+      "rewards/rejected": -0.0541253462433815,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.5322529673576355,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.486635208129883,
+      "logits/rejected": 11.192235946655273,
+      "logps/chosen": -140.9699249267578,
+      "logps/ref_chosen": -134.8175048828125,
+      "logps/ref_rejected": -145.92430114746094,
+      "logps/rejected": -151.58935546875,
+      "loss": 0.6957,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.06152408942580223,
+      "rewards/margins": -0.004873568192124367,
+      "rewards/rejected": -0.056650519371032715,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.426982581615448,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.691137313842773,
+      "logits/rejected": 10.519243240356445,
+      "logps/chosen": -137.68182373046875,
+      "logps/ref_chosen": -131.53555297851562,
+      "logps/ref_rejected": -147.749267578125,
+      "logps/rejected": -154.18560791015625,
+      "loss": 0.6918,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.061462655663490295,
+      "rewards/margins": 0.002900664694607258,
+      "rewards/rejected": -0.06436331570148468,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.39799365401268005,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.019172668457031,
+      "logits/rejected": 10.592238426208496,
+      "logps/chosen": -137.14170837402344,
+      "logps/ref_chosen": -129.1536865234375,
+      "logps/ref_rejected": -138.03895568847656,
+      "logps/rejected": -145.4950714111328,
+      "loss": 0.6959,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.07987993955612183,
+      "rewards/margins": -0.005318798590451479,
+      "rewards/rejected": -0.07456114143133163,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.6805318593978882,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 9.99167251586914,
+      "logits/rejected": 10.793407440185547,
+      "logps/chosen": -139.6283416748047,
+      "logps/ref_chosen": -131.8021240234375,
+      "logps/ref_rejected": -144.97862243652344,
+      "logps/rejected": -152.63169860839844,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.07826196402311325,
+      "rewards/margins": -0.0017311733681708574,
+      "rewards/rejected": -0.07653079926967621,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5804150104522705,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.220123291015625,
+      "logits/rejected": 10.670228958129883,
+      "logps/chosen": -141.5391387939453,
+      "logps/ref_chosen": -134.2378692626953,
+      "logps/ref_rejected": -146.93955993652344,
+      "logps/rejected": -154.45404052734375,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.07301273196935654,
+      "rewards/margins": 0.0021319000516086817,
+      "rewards/rejected": -0.07514464110136032,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.5388622283935547,
+      "learning_rate": 4.246923569447104e-07,
+      "logits/chosen": 10.13163948059082,
+      "logits/rejected": 10.671570777893066,
+      "logps/chosen": -143.1488037109375,
+      "logps/ref_chosen": -134.34185791015625,
+      "logps/ref_rejected": -152.0093231201172,
+      "logps/rejected": -160.7644500732422,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.08806941658258438,
+      "rewards/margins": -0.0005181076703593135,
+      "rewards/rejected": -0.0875513106584549,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 0.620239794254303,
+      "learning_rate": 4.161178683597054e-07,
+      "logits/chosen": 10.47970962524414,
+      "logits/rejected": 11.029216766357422,
+      "logps/chosen": -143.7899932861328,
+      "logps/ref_chosen": -134.17701721191406,
+      "logps/ref_rejected": -144.4202880859375,
+      "logps/rejected": -153.90005493164062,
+      "loss": 0.694,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.09613002091646194,
+      "rewards/margins": -0.0013323710300028324,
+      "rewards/rejected": -0.09479765594005585,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.5931733250617981,
+      "learning_rate": 4.0717821664772124e-07,
+      "logits/chosen": 10.175558090209961,
+      "logits/rejected": 10.997458457946777,
+      "logps/chosen": -140.18865966796875,
+      "logps/ref_chosen": -130.59686279296875,
+      "logps/ref_rejected": -142.52255249023438,
+      "logps/rejected": -152.0471954345703,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.09591788053512573,
+      "rewards/margins": -0.0006713568000122905,
+      "rewards/rejected": -0.09524651616811752,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.5717474222183228,
+      "learning_rate": 3.978930531033806e-07,
+      "logits/chosen": 9.4828519821167,
+      "logits/rejected": 10.328558921813965,
+      "logps/chosen": -143.23362731933594,
+      "logps/ref_chosen": -133.38320922851562,
+      "logps/ref_rejected": -145.3930206298828,
+      "logps/rejected": -155.37828063964844,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.0985042154788971,
+      "rewards/margins": 0.0013483850052580237,
+      "rewards/rejected": -0.09985260665416718,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.4360070526599884,
+      "learning_rate": 3.882827885312998e-07,
+      "logits/chosen": 10.448491096496582,
+      "logits/rejected": 10.812265396118164,
+      "logps/chosen": -153.20803833007812,
+      "logps/ref_chosen": -143.988037109375,
+      "logps/ref_rejected": -152.1568603515625,
+      "logps/rejected": -161.3251953125,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.09220016002655029,
+      "rewards/margins": -0.0005166500341147184,
+      "rewards/rejected": -0.09168350696563721,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.4402547776699066,
+      "learning_rate": 3.7836854837871044e-07,
+      "logits/chosen": 10.051721572875977,
+      "logits/rejected": 11.249682426452637,
+      "logps/chosen": -142.13824462890625,
+      "logps/ref_chosen": -132.1126251220703,
+      "logps/ref_rejected": -152.75811767578125,
+      "logps/rejected": -162.65602111816406,
+      "loss": 0.694,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.10025617480278015,
+      "rewards/margins": -0.0012769806198775768,
+      "rewards/rejected": -0.09897918999195099,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.48144519329071045,
+      "learning_rate": 3.681721262971413e-07,
+      "logits/chosen": 9.837646484375,
+      "logits/rejected": 10.622282981872559,
+      "logps/chosen": -138.56285095214844,
+      "logps/ref_chosen": -128.07298278808594,
+      "logps/ref_rejected": -143.27847290039062,
+      "logps/rejected": -153.86830139160156,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.10489849746227264,
+      "rewards/margins": 0.000999803887680173,
+      "rewards/rejected": -0.10589830577373505,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.577687680721283,
+      "learning_rate": 3.577159362352426e-07,
+      "logits/chosen": 9.869830131530762,
+      "logits/rejected": 10.881388664245605,
+      "logps/chosen": -138.81886291503906,
+      "logps/ref_chosen": -128.7156982421875,
+      "logps/ref_rejected": -145.83937072753906,
+      "logps/rejected": -155.76939392089844,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.10103171318769455,
+      "rewards/margins": -0.0017315337900072336,
+      "rewards/rejected": -0.09930018335580826,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 1.0172251462936401,
+      "learning_rate": 3.470229631680624e-07,
+      "logits/chosen": 9.960894584655762,
+      "logits/rejected": 10.816852569580078,
+      "logps/chosen": -147.22015380859375,
+      "logps/ref_chosen": -135.9361572265625,
+      "logps/ref_rejected": -147.2296600341797,
+      "logps/rejected": -158.244873046875,
+      "loss": 0.6947,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.1128399446606636,
+      "rewards/margins": -0.002687737811356783,
+      "rewards/rejected": -0.11015220731496811,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.6145241856575012,
+      "learning_rate": 3.361167125710832e-07,
+      "logits/chosen": 9.720129013061523,
+      "logits/rejected": 10.441550254821777,
+      "logps/chosen": -151.5580291748047,
+      "logps/ref_chosen": -140.27676391601562,
+      "logps/ref_rejected": -155.95626831054688,
+      "logps/rejected": -167.70098876953125,
+      "loss": 0.691,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.11281266808509827,
+      "rewards/margins": 0.004634363576769829,
+      "rewards/rejected": -0.11744703352451324,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.6173374652862549,
+      "learning_rate": 3.2502115875008516e-07,
+      "logits/chosen": 10.506845474243164,
+      "logits/rejected": 10.996613502502441,
+      "logps/chosen": -150.4586944580078,
+      "logps/ref_chosen": -140.04530334472656,
+      "logps/ref_rejected": -149.5904083251953,
+      "logps/rejected": -160.94920349121094,
+      "loss": 0.6887,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.10413391143083572,
+      "rewards/margins": 0.009454021230340004,
+      "rewards/rejected": -0.11358792334794998,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.5631862878799438,
+      "learning_rate": 3.137606921404191e-07,
+      "logits/chosen": 10.14232063293457,
+      "logits/rejected": 10.531699180603027,
+      "logps/chosen": -146.30441284179688,
+      "logps/ref_chosen": -135.6486053466797,
+      "logps/ref_rejected": -141.86065673828125,
+      "logps/rejected": -151.99014282226562,
+      "loss": 0.696,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.10655791312456131,
+      "rewards/margins": -0.005262960214167833,
+      "rewards/rejected": -0.10129496455192566,
+      "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 sha256:2671a61b13f263736b985e317ef79bc2d19c6059b573ef7ec514b72a0f9165a2
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b6c6ac69d7e4f1bd1bab25c4c2443ff2e0ab5861121fa5c37cd31bdfee5315c
+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": 0.3937181234359741,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.038352012634277,
+      "logits/rejected": 10.592904090881348,
+      "logps/chosen": -132.56948852539062,
+      "logps/ref_chosen": -132.56948852539062,
+      "logps/ref_rejected": -148.778076171875,
+      "logps/rejected": -148.778076171875,
+      "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": 0.7554967999458313,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.320584297180176,
+      "logits/rejected": 10.721946716308594,
+      "logps/chosen": -132.46385192871094,
+      "logps/ref_chosen": -132.46385192871094,
+      "logps/ref_rejected": -142.69049072265625,
+      "logps/rejected": -142.69049072265625,
+      "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": 0.5059730410575867,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 9.891550064086914,
+      "logits/rejected": 10.499095916748047,
+      "logps/chosen": -136.52415466308594,
+      "logps/ref_chosen": -135.79869079589844,
+      "logps/ref_rejected": -145.69479370117188,
+      "logps/rejected": -146.24124145507812,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.3984375,
+      "rewards/chosen": -0.007254539057612419,
+      "rewards/margins": -0.0017902727704495192,
+      "rewards/rejected": -0.005464266519993544,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.6780113577842712,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 10.122194290161133,
+      "logits/rejected": 10.64792251586914,
+      "logps/chosen": -137.41903686523438,
+      "logps/ref_chosen": -136.85159301757812,
+      "logps/ref_rejected": -142.64901733398438,
+      "logps/rejected": -142.94912719726562,
+      "loss": 0.6945,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00567453121766448,
+      "rewards/margins": -0.0026732482947409153,
+      "rewards/rejected": -0.0030012831557542086,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.5103796124458313,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.327558517456055,
+      "logits/rejected": 11.079102516174316,
+      "logps/chosen": -130.6144561767578,
+      "logps/ref_chosen": -130.2961883544922,
+      "logps/ref_rejected": -144.1498565673828,
+      "logps/rejected": -144.40802001953125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.0031829699873924255,
+      "rewards/margins": -0.000601244973950088,
+      "rewards/rejected": -0.0025817248970270157,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.7068921327590942,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.794892311096191,
+      "logits/rejected": 11.326902389526367,
+      "logps/chosen": -138.65377807617188,
+      "logps/ref_chosen": -138.59861755371094,
+      "logps/ref_rejected": -151.63775634765625,
+      "logps/rejected": -151.48056030273438,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.0005516067612916231,
+      "rewards/margins": -0.002123636193573475,
+      "rewards/rejected": 0.0015720291994512081,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.4639431834220886,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.949363708496094,
+      "logits/rejected": 10.44249153137207,
+      "logps/chosen": -130.56231689453125,
+      "logps/ref_chosen": -129.5895538330078,
+      "logps/ref_rejected": -139.67816162109375,
+      "logps/rejected": -140.58245849609375,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.009727789089083672,
+      "rewards/margins": -0.000684772094246,
+      "rewards/rejected": -0.009043017402291298,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.5582533478736877,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.655470848083496,
+      "logits/rejected": 11.168412208557129,
+      "logps/chosen": -134.7186737060547,
+      "logps/ref_chosen": -134.24497985839844,
+      "logps/ref_rejected": -147.19009399414062,
+      "logps/rejected": -147.70596313476562,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.0047368621453642845,
+      "rewards/margins": 0.0004215884255245328,
+      "rewards/rejected": -0.0051584504544734955,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.559306263923645,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.525918006896973,
+      "logits/rejected": 10.821675300598145,
+      "logps/chosen": -142.31239318847656,
+      "logps/ref_chosen": -141.59860229492188,
+      "logps/ref_rejected": -149.33889770507812,
+      "logps/rejected": -149.89822387695312,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4140625,
+      "rewards/chosen": -0.007138015236705542,
+      "rewards/margins": -0.001544784870930016,
+      "rewards/rejected": -0.005593230482190847,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6123551726341248,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 10.101277351379395,
+      "logits/rejected": 10.55870246887207,
+      "logps/chosen": -133.06532287597656,
+      "logps/ref_chosen": -132.13449096679688,
+      "logps/ref_rejected": -142.75973510742188,
+      "logps/rejected": -143.90049743652344,
+      "loss": 0.6921,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.00930829904973507,
+      "rewards/margins": 0.002099357545375824,
+      "rewards/rejected": -0.011407657526433468,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.6729086637496948,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.170294761657715,
+      "logits/rejected": 10.829442024230957,
+      "logps/chosen": -137.3282012939453,
+      "logps/ref_chosen": -135.85043334960938,
+      "logps/ref_rejected": -152.14999389648438,
+      "logps/rejected": -153.4501953125,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.014777721837162971,
+      "rewards/margins": -0.0017757893074303865,
+      "rewards/rejected": -0.013001934625208378,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.3486435115337372,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.261972427368164,
+      "logits/rejected": 10.63994312286377,
+      "logps/chosen": -141.65684509277344,
+      "logps/ref_chosen": -139.63204956054688,
+      "logps/ref_rejected": -148.03170776367188,
+      "logps/rejected": -150.0493621826172,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.02024805173277855,
+      "rewards/margins": -7.15737696737051e-05,
+      "rewards/rejected": -0.0201764777302742,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.5037537813186646,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.811729431152344,
+      "logits/rejected": 10.610340118408203,
+      "logps/chosen": -131.98635864257812,
+      "logps/ref_chosen": -129.56983947753906,
+      "logps/ref_rejected": -143.01284790039062,
+      "logps/rejected": -145.4197998046875,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.024165067821741104,
+      "rewards/margins": -9.549467358738184e-05,
+      "rewards/rejected": -0.024069571867585182,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 1.0056744813919067,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.571147918701172,
+      "logits/rejected": 11.290738105773926,
+      "logps/chosen": -132.96786499023438,
+      "logps/ref_chosen": -130.44677734375,
+      "logps/ref_rejected": -142.0145721435547,
+      "logps/rejected": -144.57803344726562,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.025210827589035034,
+      "rewards/margins": 0.0004238423425704241,
+      "rewards/rejected": -0.02563466690480709,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.44761258363723755,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.930328369140625,
+      "logits/rejected": 10.632352828979492,
+      "logps/chosen": -137.48495483398438,
+      "logps/ref_chosen": -133.87620544433594,
+      "logps/ref_rejected": -146.4284210205078,
+      "logps/rejected": -150.177490234375,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.036087535321712494,
+      "rewards/margins": 0.0014031402533873916,
+      "rewards/rejected": -0.03749067336320877,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7480736970901489,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.873997688293457,
+      "logits/rejected": 11.219457626342773,
+      "logps/chosen": -138.66485595703125,
+      "logps/ref_chosen": -135.57931518554688,
+      "logps/ref_rejected": -144.543701171875,
+      "logps/rejected": -147.69003295898438,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.0308553334325552,
+      "rewards/margins": 0.0006078272126615047,
+      "rewards/rejected": -0.03146316111087799,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.5350177884101868,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.29094409942627,
+      "logits/rejected": 10.750887870788574,
+      "logps/chosen": -130.87939453125,
+      "logps/ref_chosen": -127.53980255126953,
+      "logps/ref_rejected": -141.44097900390625,
+      "logps/rejected": -144.80685424804688,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.03339584171772003,
+      "rewards/margins": 0.0002629577647894621,
+      "rewards/rejected": -0.03365879878401756,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.6819839477539062,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.341330528259277,
+      "logits/rejected": 10.997025489807129,
+      "logps/chosen": -135.26243591308594,
+      "logps/ref_chosen": -130.62847900390625,
+      "logps/ref_rejected": -141.88360595703125,
+      "logps/rejected": -146.40476989746094,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.046339523047208786,
+      "rewards/margins": -0.001128039206378162,
+      "rewards/rejected": -0.045211486518383026,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.5013086199760437,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.433052062988281,
+      "logits/rejected": 10.780852317810059,
+      "logps/chosen": -140.90821838378906,
+      "logps/ref_chosen": -136.1767120361328,
+      "logps/ref_rejected": -148.38580322265625,
+      "logps/rejected": -153.79835510253906,
+      "loss": 0.6898,
+      "rewards/accuracies": 0.578125,
+      "rewards/chosen": -0.0473150797188282,
+      "rewards/margins": 0.006810260470956564,
+      "rewards/rejected": -0.0541253462433815,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.5322529673576355,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.486635208129883,
+      "logits/rejected": 11.192235946655273,
+      "logps/chosen": -140.9699249267578,
+      "logps/ref_chosen": -134.8175048828125,
+      "logps/ref_rejected": -145.92430114746094,
+      "logps/rejected": -151.58935546875,
+      "loss": 0.6957,
+      "rewards/accuracies": 0.40625,
+      "rewards/chosen": -0.06152408942580223,
+      "rewards/margins": -0.004873568192124367,
+      "rewards/rejected": -0.056650519371032715,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.426982581615448,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.691137313842773,
+      "logits/rejected": 10.519243240356445,
+      "logps/chosen": -137.68182373046875,
+      "logps/ref_chosen": -131.53555297851562,
+      "logps/ref_rejected": -147.749267578125,
+      "logps/rejected": -154.18560791015625,
+      "loss": 0.6918,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.061462655663490295,
+      "rewards/margins": 0.002900664694607258,
+      "rewards/rejected": -0.06436331570148468,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.39799365401268005,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.019172668457031,
+      "logits/rejected": 10.592238426208496,
+      "logps/chosen": -137.14170837402344,
+      "logps/ref_chosen": -129.1536865234375,
+      "logps/ref_rejected": -138.03895568847656,
+      "logps/rejected": -145.4950714111328,
+      "loss": 0.6959,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.07987993955612183,
+      "rewards/margins": -0.005318798590451479,
+      "rewards/rejected": -0.07456114143133163,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.6805318593978882,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 9.99167251586914,
+      "logits/rejected": 10.793407440185547,
+      "logps/chosen": -139.6283416748047,
+      "logps/ref_chosen": -131.8021240234375,
+      "logps/ref_rejected": -144.97862243652344,
+      "logps/rejected": -152.63169860839844,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.07826196402311325,
+      "rewards/margins": -0.0017311733681708574,
+      "rewards/rejected": -0.07653079926967621,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5804150104522705,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.220123291015625,
+      "logits/rejected": 10.670228958129883,
+      "logps/chosen": -141.5391387939453,
+      "logps/ref_chosen": -134.2378692626953,
+      "logps/ref_rejected": -146.93955993652344,
+      "logps/rejected": -154.45404052734375,
+      "loss": 0.6922,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.07301273196935654,
+      "rewards/margins": 0.0021319000516086817,
+      "rewards/rejected": -0.07514464110136032,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.5388622283935547,
+      "learning_rate": 4.246923569447104e-07,
+      "logits/chosen": 10.13163948059082,
+      "logits/rejected": 10.671570777893066,
+      "logps/chosen": -143.1488037109375,
+      "logps/ref_chosen": -134.34185791015625,
+      "logps/ref_rejected": -152.0093231201172,
+      "logps/rejected": -160.7644500732422,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.08806941658258438,
+      "rewards/margins": -0.0005181076703593135,
+      "rewards/rejected": -0.0875513106584549,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 0.620239794254303,
+      "learning_rate": 4.161178683597054e-07,
+      "logits/chosen": 10.47970962524414,
+      "logits/rejected": 11.029216766357422,
+      "logps/chosen": -143.7899932861328,
+      "logps/ref_chosen": -134.17701721191406,
+      "logps/ref_rejected": -144.4202880859375,
+      "logps/rejected": -153.90005493164062,
+      "loss": 0.694,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.09613002091646194,
+      "rewards/margins": -0.0013323710300028324,
+      "rewards/rejected": -0.09479765594005585,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.5931733250617981,
+      "learning_rate": 4.0717821664772124e-07,
+      "logits/chosen": 10.175558090209961,
+      "logits/rejected": 10.997458457946777,
+      "logps/chosen": -140.18865966796875,
+      "logps/ref_chosen": -130.59686279296875,
+      "logps/ref_rejected": -142.52255249023438,
+      "logps/rejected": -152.0471954345703,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.09591788053512573,
+      "rewards/margins": -0.0006713568000122905,
+      "rewards/rejected": -0.09524651616811752,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.5717474222183228,
+      "learning_rate": 3.978930531033806e-07,
+      "logits/chosen": 9.4828519821167,
+      "logits/rejected": 10.328558921813965,
+      "logps/chosen": -143.23362731933594,
+      "logps/ref_chosen": -133.38320922851562,
+      "logps/ref_rejected": -145.3930206298828,
+      "logps/rejected": -155.37828063964844,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.0985042154788971,
+      "rewards/margins": 0.0013483850052580237,
+      "rewards/rejected": -0.09985260665416718,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.4360070526599884,
+      "learning_rate": 3.882827885312998e-07,
+      "logits/chosen": 10.448491096496582,
+      "logits/rejected": 10.812265396118164,
+      "logps/chosen": -153.20803833007812,
+      "logps/ref_chosen": -143.988037109375,
+      "logps/ref_rejected": -152.1568603515625,
+      "logps/rejected": -161.3251953125,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.09220016002655029,
+      "rewards/margins": -0.0005166500341147184,
+      "rewards/rejected": -0.09168350696563721,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.4402547776699066,
+      "learning_rate": 3.7836854837871044e-07,
+      "logits/chosen": 10.051721572875977,
+      "logits/rejected": 11.249682426452637,
+      "logps/chosen": -142.13824462890625,
+      "logps/ref_chosen": -132.1126251220703,
+      "logps/ref_rejected": -152.75811767578125,
+      "logps/rejected": -162.65602111816406,
+      "loss": 0.694,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.10025617480278015,
+      "rewards/margins": -0.0012769806198775768,
+      "rewards/rejected": -0.09897918999195099,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.48144519329071045,
+      "learning_rate": 3.681721262971413e-07,
+      "logits/chosen": 9.837646484375,
+      "logits/rejected": 10.622282981872559,
+      "logps/chosen": -138.56285095214844,
+      "logps/ref_chosen": -128.07298278808594,
+      "logps/ref_rejected": -143.27847290039062,
+      "logps/rejected": -153.86830139160156,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.10489849746227264,
+      "rewards/margins": 0.000999803887680173,
+      "rewards/rejected": -0.10589830577373505,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.577687680721283,
+      "learning_rate": 3.577159362352426e-07,
+      "logits/chosen": 9.869830131530762,
+      "logits/rejected": 10.881388664245605,
+      "logps/chosen": -138.81886291503906,
+      "logps/ref_chosen": -128.7156982421875,
+      "logps/ref_rejected": -145.83937072753906,
+      "logps/rejected": -155.76939392089844,
+      "loss": 0.6943,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.10103171318769455,
+      "rewards/margins": -0.0017315337900072336,
+      "rewards/rejected": -0.09930018335580826,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 1.0172251462936401,
+      "learning_rate": 3.470229631680624e-07,
+      "logits/chosen": 9.960894584655762,
+      "logits/rejected": 10.816852569580078,
+      "logps/chosen": -147.22015380859375,
+      "logps/ref_chosen": -135.9361572265625,
+      "logps/ref_rejected": -147.2296600341797,
+      "logps/rejected": -158.244873046875,
+      "loss": 0.6947,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.1128399446606636,
+      "rewards/margins": -0.002687737811356783,
+      "rewards/rejected": -0.11015220731496811,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.6145241856575012,
+      "learning_rate": 3.361167125710832e-07,
+      "logits/chosen": 9.720129013061523,
+      "logits/rejected": 10.441550254821777,
+      "logps/chosen": -151.5580291748047,
+      "logps/ref_chosen": -140.27676391601562,
+      "logps/ref_rejected": -155.95626831054688,
+      "logps/rejected": -167.70098876953125,
+      "loss": 0.691,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.11281266808509827,
+      "rewards/margins": 0.004634363576769829,
+      "rewards/rejected": -0.11744703352451324,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.6173374652862549,
+      "learning_rate": 3.2502115875008516e-07,
+      "logits/chosen": 10.506845474243164,
+      "logits/rejected": 10.996613502502441,
+      "logps/chosen": -150.4586944580078,
+      "logps/ref_chosen": -140.04530334472656,
+      "logps/ref_rejected": -149.5904083251953,
+      "logps/rejected": -160.94920349121094,
+      "loss": 0.6887,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.10413391143083572,
+      "rewards/margins": 0.009454021230340004,
+      "rewards/rejected": -0.11358792334794998,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.5631862878799438,
+      "learning_rate": 3.137606921404191e-07,
+      "logits/chosen": 10.14232063293457,
+      "logits/rejected": 10.531699180603027,
+      "logps/chosen": -146.30441284179688,
+      "logps/ref_chosen": -135.6486053466797,
+      "logps/ref_rejected": -141.86065673828125,
+      "logps/rejected": -151.99014282226562,
+      "loss": 0.696,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.10655791312456131,
+      "rewards/margins": -0.005262960214167833,
+      "rewards/rejected": -0.10129496455192566,
+      "step": 36
+    },
+    {
+      "epoch": 0.4874433923425278,
+      "grad_norm": 0.39251431822776794,
+      "learning_rate": 3.0236006569153616e-07,
+      "logits/chosen": 10.132379531860352,
+      "logits/rejected": 10.665701866149902,
+      "logps/chosen": -143.94390869140625,
+      "logps/ref_chosen": -133.20074462890625,
+      "logps/ref_rejected": -147.91590881347656,
+      "logps/rejected": -158.85093688964844,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.10743152350187302,
+      "rewards/margins": 0.0019188999431207776,
+      "rewards/rejected": -0.10935042798519135,
+      "step": 37
+    },
+    {
+      "epoch": 0.500617538081515,
+      "grad_norm": 0.7656453847885132,
+      "learning_rate": 2.9084434045463254e-07,
+      "logits/chosen": 9.960819244384766,
+      "logits/rejected": 10.67172622680664,
+      "logps/chosen": -137.5731658935547,
+      "logps/ref_chosen": -127.76959228515625,
+      "logps/ref_rejected": -141.39682006835938,
+      "logps/rejected": -151.8663330078125,
+      "loss": 0.69,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.09803567081689835,
+      "rewards/margins": 0.00665951706469059,
+      "rewards/rejected": -0.10469517856836319,
+      "step": 38
+    },
+    {
+      "epoch": 0.5137916838205022,
+      "grad_norm": 0.5559167861938477,
+      "learning_rate": 2.7923883049302066e-07,
+      "logits/chosen": 10.277292251586914,
+      "logits/rejected": 10.739974975585938,
+      "logps/chosen": -154.29446411132812,
+      "logps/ref_chosen": -143.0114288330078,
+      "logps/ref_rejected": -152.31521606445312,
+      "logps/rejected": -163.67828369140625,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.1128302812576294,
+      "rewards/margins": 0.0008003946859389544,
+      "rewards/rejected": -0.11363067477941513,
+      "step": 39
+    },
+    {
+      "epoch": 0.5269658295594895,
+      "grad_norm": 0.7704273462295532,
+      "learning_rate": 2.6756904723632324e-07,
+      "logits/chosen": 10.08700942993164,
+      "logits/rejected": 11.070208549499512,
+      "logps/chosen": -145.0982666015625,
+      "logps/ref_chosen": -133.50540161132812,
+      "logps/ref_rejected": -153.46780395507812,
+      "logps/rejected": -164.51731872558594,
+      "loss": 0.6962,
+      "rewards/accuracies": 0.4296875,
+      "rewards/chosen": -0.11592855304479599,
+      "rewards/margins": -0.005433396901935339,
+      "rewards/rejected": -0.11049516499042511,
+      "step": 40
+    },
+    {
+      "epoch": 0.5401399752984768,
+      "grad_norm": 0.804985761642456,
+      "learning_rate": 2.5586064340081516e-07,
+      "logits/chosen": 10.431921005249023,
+      "logits/rejected": 10.745326042175293,
+      "logps/chosen": -141.06336975097656,
+      "logps/ref_chosen": -130.76077270507812,
+      "logps/ref_rejected": -141.3428497314453,
+      "logps/rejected": -152.6197052001953,
+      "loss": 0.6885,
+      "rewards/accuracies": 0.5859375,
+      "rewards/chosen": -0.10302580147981644,
+      "rewards/margins": 0.009742637164890766,
+      "rewards/rejected": -0.11276843398809433,
+      "step": 41
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": 0.39167729020118713,
+      "learning_rate": 2.4413935659918487e-07,
+      "logits/chosen": 9.522839546203613,
+      "logits/rejected": 10.306070327758789,
+      "logps/chosen": -139.82749938964844,
+      "logps/ref_chosen": -129.22003173828125,
+      "logps/ref_rejected": -143.66864013671875,
+      "logps/rejected": -154.94313049316406,
+      "loss": 0.6901,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.10607446730136871,
+      "rewards/margins": 0.006670599337667227,
+      "rewards/rejected": -0.11274506151676178,
+      "step": 42
+    },
+    {
+      "epoch": 0.5664882667764513,
+      "grad_norm": 0.5384664535522461,
+      "learning_rate": 2.3243095276367684e-07,
+      "logits/chosen": 9.664013862609863,
+      "logits/rejected": 10.42688274383545,
+      "logps/chosen": -134.9727325439453,
+      "logps/ref_chosen": -124.54762268066406,
+      "logps/ref_rejected": -139.1492156982422,
+      "logps/rejected": -149.46144104003906,
+      "loss": 0.694,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.1042512059211731,
+      "rewards/margins": -0.0011289024259895086,
+      "rewards/rejected": -0.10312230885028839,
+      "step": 43
+    },
+    {
+      "epoch": 0.5796624125154385,
+      "grad_norm": 0.5131722688674927,
+      "learning_rate": 2.2076116950697937e-07,
+      "logits/chosen": 9.627304077148438,
+      "logits/rejected": 10.516542434692383,
+      "logps/chosen": -143.17015075683594,
+      "logps/ref_chosen": -131.923095703125,
+      "logps/ref_rejected": -145.09170532226562,
+      "logps/rejected": -156.09776306152344,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.11247052252292633,
+      "rewards/margins": -0.002409988548606634,
+      "rewards/rejected": -0.11006053537130356,
+      "step": 44
+    },
+    {
+      "epoch": 0.5928365582544257,
+      "grad_norm": 0.4406370222568512,
+      "learning_rate": 2.091556595453674e-07,
+      "logits/chosen": 9.869440078735352,
+      "logits/rejected": 10.380814552307129,
+      "logps/chosen": -138.8632049560547,
+      "logps/ref_chosen": -128.74046325683594,
+      "logps/ref_rejected": -144.51145935058594,
+      "logps/rejected": -154.9576416015625,
+      "loss": 0.6918,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.1012275293469429,
+      "rewards/margins": 0.00323441531509161,
+      "rewards/rejected": -0.10446193069219589,
+      "step": 45
+    },
+    {
+      "epoch": 0.606010703993413,
+      "grad_norm": 0.7753900289535522,
+      "learning_rate": 1.9763993430846392e-07,
+      "logits/chosen": 9.825464248657227,
+      "logits/rejected": 10.249982833862305,
+      "logps/chosen": -138.25758361816406,
+      "logps/ref_chosen": -127.67835998535156,
+      "logps/ref_rejected": -139.95693969726562,
+      "logps/rejected": -151.13128662109375,
+      "loss": 0.6904,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.10579212754964828,
+      "rewards/margins": 0.00595143111422658,
+      "rewards/rejected": -0.11174355447292328,
+      "step": 46
+    },
+    {
+      "epoch": 0.6191848497324002,
+      "grad_norm": 0.5868674516677856,
+      "learning_rate": 1.862393078595809e-07,
+      "logits/chosen": 9.929595947265625,
+      "logits/rejected": 10.724593162536621,
+      "logps/chosen": -150.34271240234375,
+      "logps/ref_chosen": -139.08160400390625,
+      "logps/ref_rejected": -153.37371826171875,
+      "logps/rejected": -165.11471557617188,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": -0.11261098831892014,
+      "rewards/margins": 0.004799033515155315,
+      "rewards/rejected": -0.11741001904010773,
+      "step": 47
+    },
+    {
+      "epoch": 0.6323589954713874,
+      "grad_norm": 0.8715807795524597,
+      "learning_rate": 1.7497884124991485e-07,
+      "logits/chosen": 10.29124641418457,
+      "logits/rejected": 10.894004821777344,
+      "logps/chosen": -143.96966552734375,
+      "logps/ref_chosen": -132.76876831054688,
+      "logps/ref_rejected": -147.2455596923828,
+      "logps/rejected": -158.60287475585938,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.11200893670320511,
+      "rewards/margins": 0.0015640957280993462,
+      "rewards/rejected": -0.11357302963733673,
+      "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:b2a021f78342ebefe300f4ef8091ea2457447a4cf934ca0e9579a808d70da3ae
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084695f9a94f6669eb0c6b15a3ce1e7d9d091da7a44e0b189393035c1d5da899
+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
+  }
+}