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": 9.238293647766113,
+    "eval_logits/rejected": 10.049151420593262,
+    "eval_logps/chosen": -114.94315338134766,
+    "eval_logps/ref_chosen": -106.16099548339844,
+    "eval_logps/ref_rejected": -119.78473663330078,
+    "eval_logps/rejected": -129.38494873046875,
+    "eval_loss": 0.6894497275352478,
+    "eval_rewards/accuracies": 0.5833333134651184,
+    "eval_rewards/chosen": -0.08782169967889786,
+    "eval_rewards/margins": 0.008180392906069756,
+    "eval_rewards/rejected": -0.09600208699703217,
+    "eval_runtime": 152.328,
+    "eval_samples": 1080,
+    "eval_samples_per_second": 7.09,
+    "eval_steps_per_second": 1.772,
+    "total_flos": 0.0,
+    "train_loss": 0.6920125889778137,
+    "train_runtime": 8059.7946,
+    "train_samples": 9715,
+    "train_samples_per_second": 1.205,
+    "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:c7750ca147640cbe026817393ba508335bd1e7268107cfb044d48d16e3287867
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0e9dda0d4a032e682fbdd0ded41d4b77130ba40c48e886f014f851f7be94f2
+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": 0.39343583583831787,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.071717262268066,
+      "logits/rejected": 10.610974311828613,
+      "logps/chosen": -121.14067077636719,
+      "logps/ref_chosen": -121.14067077636719,
+      "logps/ref_rejected": -137.65684509277344,
+      "logps/rejected": -137.65684509277344,
+      "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": 0.7521647214889526,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.222262382507324,
+      "logits/rejected": 10.754176139831543,
+      "logps/chosen": -116.48068237304688,
+      "logps/ref_chosen": -116.48068237304688,
+      "logps/ref_rejected": -130.27796936035156,
+      "logps/rejected": -130.27796936035156,
+      "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": 0.5880491137504578,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.01984977722168,
+      "logits/rejected": 10.62405776977539,
+      "logps/chosen": -123.36822509765625,
+      "logps/ref_chosen": -122.6683349609375,
+      "logps/ref_rejected": -132.69850158691406,
+      "logps/rejected": -133.207275390625,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.006998830940574408,
+      "rewards/margins": -0.0019110905705019832,
+      "rewards/rejected": -0.005087739787995815,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.4605408310890198,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 9.99990463256836,
+      "logits/rejected": 10.736846923828125,
+      "logps/chosen": -123.02133178710938,
+      "logps/ref_chosen": -122.59739685058594,
+      "logps/ref_rejected": -129.70767211914062,
+      "logps/rejected": -129.98374938964844,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.004239337984472513,
+      "rewards/margins": -0.0014785109087824821,
+      "rewards/rejected": -0.0027608266100287437,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.469856321811676,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.075482368469238,
+      "logits/rejected": 10.892666816711426,
+      "logps/chosen": -117.554931640625,
+      "logps/ref_chosen": -117.5941162109375,
+      "logps/ref_rejected": -132.1708984375,
+      "logps/rejected": -132.1227264404297,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": 0.0003917121794074774,
+      "rewards/margins": -9.010493522509933e-05,
+      "rewards/rejected": 0.0004818170564249158,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.5541566610336304,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.660999298095703,
+      "logits/rejected": 11.290507316589355,
+      "logps/chosen": -127.00320434570312,
+      "logps/ref_chosen": -126.12411499023438,
+      "logps/ref_rejected": -136.9976043701172,
+      "logps/rejected": -137.75950622558594,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00879070907831192,
+      "rewards/margins": -0.0011717069428414106,
+      "rewards/rejected": -0.007619001902639866,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.4422788619995117,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.958097457885742,
+      "logits/rejected": 10.642163276672363,
+      "logps/chosen": -115.61244201660156,
+      "logps/ref_chosen": -115.08863830566406,
+      "logps/ref_rejected": -125.91255187988281,
+      "logps/rejected": -126.15577697753906,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.005238103214651346,
+      "rewards/margins": -0.0028058765456080437,
+      "rewards/rejected": -0.002432226436212659,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.5495327115058899,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.345503807067871,
+      "logits/rejected": 10.97708797454834,
+      "logps/chosen": -121.48406982421875,
+      "logps/ref_chosen": -121.4114761352539,
+      "logps/ref_rejected": -134.62770080566406,
+      "logps/rejected": -134.7586212158203,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.0007259202538989484,
+      "rewards/margins": 0.0005832896567881107,
+      "rewards/rejected": -0.0013092098524793983,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.43922048807144165,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.159126281738281,
+      "logits/rejected": 11.002123832702637,
+      "logps/chosen": -122.51399230957031,
+      "logps/ref_chosen": -121.59207153320312,
+      "logps/ref_rejected": -134.70025634765625,
+      "logps/rejected": -135.55740356445312,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.00921926274895668,
+      "rewards/margins": -0.0006479143630713224,
+      "rewards/rejected": -0.008571348153054714,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6643485426902771,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 9.9464111328125,
+      "logits/rejected": 10.739057540893555,
+      "logps/chosen": -117.91310119628906,
+      "logps/ref_chosen": -117.16349029541016,
+      "logps/ref_rejected": -129.98167419433594,
+      "logps/rejected": -130.65924072265625,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.007496046833693981,
+      "rewards/margins": -0.0007203805143944919,
+      "rewards/rejected": -0.00677566509693861,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.4432956576347351,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.095781326293945,
+      "logits/rejected": 11.001167297363281,
+      "logps/chosen": -123.26506042480469,
+      "logps/ref_chosen": -121.95927429199219,
+      "logps/ref_rejected": -136.18655395507812,
+      "logps/rejected": -137.39865112304688,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01305788941681385,
+      "rewards/margins": -0.0009369202307425439,
+      "rewards/rejected": -0.012120969593524933,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.3955974280834198,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.129995346069336,
+      "logits/rejected": 10.673677444458008,
+      "logps/chosen": -126.05357360839844,
+      "logps/ref_chosen": -124.12315368652344,
+      "logps/ref_rejected": -134.275390625,
+      "logps/rejected": -136.24940490722656,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.01930420845746994,
+      "rewards/margins": 0.00043603626545518637,
+      "rewards/rejected": -0.01974024437367916,
+      "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 sha256:607c81351a37ec995fb0a6a7311f9b469ffdaa114ea874f8608e452070b2eb68
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba14374acf82bd8338ba7f58ac7f237a36334cee0b0fad4a9d796700f5607d3
+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": 0.39343583583831787,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.071717262268066,
+      "logits/rejected": 10.610974311828613,
+      "logps/chosen": -121.14067077636719,
+      "logps/ref_chosen": -121.14067077636719,
+      "logps/ref_rejected": -137.65684509277344,
+      "logps/rejected": -137.65684509277344,
+      "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": 0.7521647214889526,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.222262382507324,
+      "logits/rejected": 10.754176139831543,
+      "logps/chosen": -116.48068237304688,
+      "logps/ref_chosen": -116.48068237304688,
+      "logps/ref_rejected": -130.27796936035156,
+      "logps/rejected": -130.27796936035156,
+      "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": 0.5880491137504578,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.01984977722168,
+      "logits/rejected": 10.62405776977539,
+      "logps/chosen": -123.36822509765625,
+      "logps/ref_chosen": -122.6683349609375,
+      "logps/ref_rejected": -132.69850158691406,
+      "logps/rejected": -133.207275390625,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.006998830940574408,
+      "rewards/margins": -0.0019110905705019832,
+      "rewards/rejected": -0.005087739787995815,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.4605408310890198,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 9.99990463256836,
+      "logits/rejected": 10.736846923828125,
+      "logps/chosen": -123.02133178710938,
+      "logps/ref_chosen": -122.59739685058594,
+      "logps/ref_rejected": -129.70767211914062,
+      "logps/rejected": -129.98374938964844,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.004239337984472513,
+      "rewards/margins": -0.0014785109087824821,
+      "rewards/rejected": -0.0027608266100287437,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.469856321811676,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.075482368469238,
+      "logits/rejected": 10.892666816711426,
+      "logps/chosen": -117.554931640625,
+      "logps/ref_chosen": -117.5941162109375,
+      "logps/ref_rejected": -132.1708984375,
+      "logps/rejected": -132.1227264404297,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": 0.0003917121794074774,
+      "rewards/margins": -9.010493522509933e-05,
+      "rewards/rejected": 0.0004818170564249158,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.5541566610336304,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.660999298095703,
+      "logits/rejected": 11.290507316589355,
+      "logps/chosen": -127.00320434570312,
+      "logps/ref_chosen": -126.12411499023438,
+      "logps/ref_rejected": -136.9976043701172,
+      "logps/rejected": -137.75950622558594,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00879070907831192,
+      "rewards/margins": -0.0011717069428414106,
+      "rewards/rejected": -0.007619001902639866,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.4422788619995117,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.958097457885742,
+      "logits/rejected": 10.642163276672363,
+      "logps/chosen": -115.61244201660156,
+      "logps/ref_chosen": -115.08863830566406,
+      "logps/ref_rejected": -125.91255187988281,
+      "logps/rejected": -126.15577697753906,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.005238103214651346,
+      "rewards/margins": -0.0028058765456080437,
+      "rewards/rejected": -0.002432226436212659,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.5495327115058899,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.345503807067871,
+      "logits/rejected": 10.97708797454834,
+      "logps/chosen": -121.48406982421875,
+      "logps/ref_chosen": -121.4114761352539,
+      "logps/ref_rejected": -134.62770080566406,
+      "logps/rejected": -134.7586212158203,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.0007259202538989484,
+      "rewards/margins": 0.0005832896567881107,
+      "rewards/rejected": -0.0013092098524793983,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.43922048807144165,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.159126281738281,
+      "logits/rejected": 11.002123832702637,
+      "logps/chosen": -122.51399230957031,
+      "logps/ref_chosen": -121.59207153320312,
+      "logps/ref_rejected": -134.70025634765625,
+      "logps/rejected": -135.55740356445312,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.00921926274895668,
+      "rewards/margins": -0.0006479143630713224,
+      "rewards/rejected": -0.008571348153054714,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6643485426902771,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 9.9464111328125,
+      "logits/rejected": 10.739057540893555,
+      "logps/chosen": -117.91310119628906,
+      "logps/ref_chosen": -117.16349029541016,
+      "logps/ref_rejected": -129.98167419433594,
+      "logps/rejected": -130.65924072265625,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.007496046833693981,
+      "rewards/margins": -0.0007203805143944919,
+      "rewards/rejected": -0.00677566509693861,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.4432956576347351,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.095781326293945,
+      "logits/rejected": 11.001167297363281,
+      "logps/chosen": -123.26506042480469,
+      "logps/ref_chosen": -121.95927429199219,
+      "logps/ref_rejected": -136.18655395507812,
+      "logps/rejected": -137.39865112304688,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01305788941681385,
+      "rewards/margins": -0.0009369202307425439,
+      "rewards/rejected": -0.012120969593524933,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.3955974280834198,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.129995346069336,
+      "logits/rejected": 10.673677444458008,
+      "logps/chosen": -126.05357360839844,
+      "logps/ref_chosen": -124.12315368652344,
+      "logps/ref_rejected": -134.275390625,
+      "logps/rejected": -136.24940490722656,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.01930420845746994,
+      "rewards/margins": 0.00043603626545518637,
+      "rewards/rejected": -0.01974024437367916,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.4873650074005127,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.8243989944458,
+      "logits/rejected": 10.843228340148926,
+      "logps/chosen": -119.30509185791016,
+      "logps/ref_chosen": -116.83765411376953,
+      "logps/ref_rejected": -130.78997802734375,
+      "logps/rejected": -133.15672302246094,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.024674497544765472,
+      "rewards/margins": -0.0010069820564240217,
+      "rewards/rejected": -0.02366751804947853,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.8769639134407043,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.427848815917969,
+      "logits/rejected": 11.37716293334961,
+      "logps/chosen": -120.9067611694336,
+      "logps/ref_chosen": -118.43791961669922,
+      "logps/ref_rejected": -132.5309600830078,
+      "logps/rejected": -134.91236877441406,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.02468838170170784,
+      "rewards/margins": -0.0008744060760363936,
+      "rewards/rejected": -0.023813974112272263,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.8736073970794678,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.956391334533691,
+      "logits/rejected": 10.684510231018066,
+      "logps/chosen": -128.198486328125,
+      "logps/ref_chosen": -124.82101440429688,
+      "logps/ref_rejected": -135.32565307617188,
+      "logps/rejected": -138.8860626220703,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.033774565905332565,
+      "rewards/margins": 0.0018295131158083677,
+      "rewards/rejected": -0.0356040820479393,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7293412089347839,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.677412033081055,
+      "logits/rejected": 11.254134178161621,
+      "logps/chosen": -122.79344940185547,
+      "logps/ref_chosen": -119.69990539550781,
+      "logps/ref_rejected": -130.34449768066406,
+      "logps/rejected": -133.39932250976562,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.030935294926166534,
+      "rewards/margins": -0.0003869622596539557,
+      "rewards/rejected": -0.030548332259058952,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.6406402587890625,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.172043800354004,
+      "logits/rejected": 10.859190940856934,
+      "logps/chosen": -118.11813354492188,
+      "logps/ref_chosen": -114.52975463867188,
+      "logps/ref_rejected": -129.5846405029297,
+      "logps/rejected": -133.20779418945312,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.035883828997612,
+      "rewards/margins": 0.00034771906211972237,
+      "rewards/rejected": -0.036231543868780136,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.7559142708778381,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.747884750366211,
+      "logits/rejected": 11.173224449157715,
+      "logps/chosen": -121.89351654052734,
+      "logps/ref_chosen": -117.67997741699219,
+      "logps/ref_rejected": -128.00650024414062,
+      "logps/rejected": -132.31655883789062,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.042135339230298996,
+      "rewards/margins": 0.0009651560103520751,
+      "rewards/rejected": -0.043100498616695404,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.49808746576309204,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.380050659179688,
+      "logits/rejected": 10.91146469116211,
+      "logps/chosen": -125.04395294189453,
+      "logps/ref_chosen": -120.92308044433594,
+      "logps/ref_rejected": -133.8301544189453,
+      "logps/rejected": -138.79052734375,
+      "loss": 0.689,
+      "rewards/accuracies": 0.6328125,
+      "rewards/chosen": -0.0412086620926857,
+      "rewards/margins": 0.008395083248615265,
+      "rewards/rejected": -0.04960374906659126,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.5601547956466675,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.563058853149414,
+      "logits/rejected": 11.37236499786377,
+      "logps/chosen": -126.93672180175781,
+      "logps/ref_chosen": -121.84554290771484,
+      "logps/ref_rejected": -133.343017578125,
+      "logps/rejected": -138.12808227539062,
+      "loss": 0.6948,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.050911907106637955,
+      "rewards/margins": -0.0030612414702773094,
+      "rewards/rejected": -0.04785066470503807,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.41351014375686646,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.687071800231934,
+      "logits/rejected": 10.572582244873047,
+      "logps/chosen": -124.77998352050781,
+      "logps/ref_chosen": -119.20828247070312,
+      "logps/ref_rejected": -134.38436889648438,
+      "logps/rejected": -140.02293395996094,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.055717017501592636,
+      "rewards/margins": 0.0006685962434858084,
+      "rewards/rejected": -0.056385621428489685,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.6027271747589111,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.03482437133789,
+      "logits/rejected": 10.820859909057617,
+      "logps/chosen": -121.17003631591797,
+      "logps/ref_chosen": -114.62059020996094,
+      "logps/ref_rejected": -128.0896759033203,
+      "logps/rejected": -134.1069793701172,
+      "loss": 0.6959,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.06549445539712906,
+      "rewards/margins": -0.005321440752595663,
+      "rewards/rejected": -0.06017300859093666,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.5877695083618164,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.00536060333252,
+      "logits/rejected": 10.877461433410645,
+      "logps/chosen": -124.2905044555664,
+      "logps/ref_chosen": -117.84042358398438,
+      "logps/ref_rejected": -131.79171752929688,
+      "logps/rejected": -137.91160583496094,
+      "loss": 0.6949,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.06450086086988449,
+      "rewards/margins": -0.0033018956892192364,
+      "rewards/rejected": -0.061198972165584564,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5177574157714844,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.104101181030273,
+      "logits/rejected": 10.70304012298584,
+      "logps/chosen": -129.96224975585938,
+      "logps/ref_chosen": -123.75523376464844,
+      "logps/ref_rejected": -138.6237030029297,
+      "logps/rejected": -144.98983764648438,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.062070075422525406,
+      "rewards/margins": 0.0015914504183456302,
+      "rewards/rejected": -0.06366152316331863,
+      "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:ee6e417d669e8449a2627edc7cc788ab939043a4f1fd1dcbf0751661de451c1b
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b28a1f60fc94e11d835ed75dee3439ba5ac7f0bb26be01d96b5df081fe3ccf
+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": 0.39343583583831787,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.071717262268066,
+      "logits/rejected": 10.610974311828613,
+      "logps/chosen": -121.14067077636719,
+      "logps/ref_chosen": -121.14067077636719,
+      "logps/ref_rejected": -137.65684509277344,
+      "logps/rejected": -137.65684509277344,
+      "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": 0.7521647214889526,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.222262382507324,
+      "logits/rejected": 10.754176139831543,
+      "logps/chosen": -116.48068237304688,
+      "logps/ref_chosen": -116.48068237304688,
+      "logps/ref_rejected": -130.27796936035156,
+      "logps/rejected": -130.27796936035156,
+      "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": 0.5880491137504578,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.01984977722168,
+      "logits/rejected": 10.62405776977539,
+      "logps/chosen": -123.36822509765625,
+      "logps/ref_chosen": -122.6683349609375,
+      "logps/ref_rejected": -132.69850158691406,
+      "logps/rejected": -133.207275390625,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.006998830940574408,
+      "rewards/margins": -0.0019110905705019832,
+      "rewards/rejected": -0.005087739787995815,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.4605408310890198,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 9.99990463256836,
+      "logits/rejected": 10.736846923828125,
+      "logps/chosen": -123.02133178710938,
+      "logps/ref_chosen": -122.59739685058594,
+      "logps/ref_rejected": -129.70767211914062,
+      "logps/rejected": -129.98374938964844,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.004239337984472513,
+      "rewards/margins": -0.0014785109087824821,
+      "rewards/rejected": -0.0027608266100287437,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.469856321811676,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.075482368469238,
+      "logits/rejected": 10.892666816711426,
+      "logps/chosen": -117.554931640625,
+      "logps/ref_chosen": -117.5941162109375,
+      "logps/ref_rejected": -132.1708984375,
+      "logps/rejected": -132.1227264404297,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": 0.0003917121794074774,
+      "rewards/margins": -9.010493522509933e-05,
+      "rewards/rejected": 0.0004818170564249158,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.5541566610336304,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.660999298095703,
+      "logits/rejected": 11.290507316589355,
+      "logps/chosen": -127.00320434570312,
+      "logps/ref_chosen": -126.12411499023438,
+      "logps/ref_rejected": -136.9976043701172,
+      "logps/rejected": -137.75950622558594,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00879070907831192,
+      "rewards/margins": -0.0011717069428414106,
+      "rewards/rejected": -0.007619001902639866,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.4422788619995117,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.958097457885742,
+      "logits/rejected": 10.642163276672363,
+      "logps/chosen": -115.61244201660156,
+      "logps/ref_chosen": -115.08863830566406,
+      "logps/ref_rejected": -125.91255187988281,
+      "logps/rejected": -126.15577697753906,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.005238103214651346,
+      "rewards/margins": -0.0028058765456080437,
+      "rewards/rejected": -0.002432226436212659,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.5495327115058899,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.345503807067871,
+      "logits/rejected": 10.97708797454834,
+      "logps/chosen": -121.48406982421875,
+      "logps/ref_chosen": -121.4114761352539,
+      "logps/ref_rejected": -134.62770080566406,
+      "logps/rejected": -134.7586212158203,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.0007259202538989484,
+      "rewards/margins": 0.0005832896567881107,
+      "rewards/rejected": -0.0013092098524793983,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.43922048807144165,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.159126281738281,
+      "logits/rejected": 11.002123832702637,
+      "logps/chosen": -122.51399230957031,
+      "logps/ref_chosen": -121.59207153320312,
+      "logps/ref_rejected": -134.70025634765625,
+      "logps/rejected": -135.55740356445312,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.00921926274895668,
+      "rewards/margins": -0.0006479143630713224,
+      "rewards/rejected": -0.008571348153054714,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6643485426902771,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 9.9464111328125,
+      "logits/rejected": 10.739057540893555,
+      "logps/chosen": -117.91310119628906,
+      "logps/ref_chosen": -117.16349029541016,
+      "logps/ref_rejected": -129.98167419433594,
+      "logps/rejected": -130.65924072265625,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.007496046833693981,
+      "rewards/margins": -0.0007203805143944919,
+      "rewards/rejected": -0.00677566509693861,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.4432956576347351,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.095781326293945,
+      "logits/rejected": 11.001167297363281,
+      "logps/chosen": -123.26506042480469,
+      "logps/ref_chosen": -121.95927429199219,
+      "logps/ref_rejected": -136.18655395507812,
+      "logps/rejected": -137.39865112304688,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01305788941681385,
+      "rewards/margins": -0.0009369202307425439,
+      "rewards/rejected": -0.012120969593524933,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.3955974280834198,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.129995346069336,
+      "logits/rejected": 10.673677444458008,
+      "logps/chosen": -126.05357360839844,
+      "logps/ref_chosen": -124.12315368652344,
+      "logps/ref_rejected": -134.275390625,
+      "logps/rejected": -136.24940490722656,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.01930420845746994,
+      "rewards/margins": 0.00043603626545518637,
+      "rewards/rejected": -0.01974024437367916,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.4873650074005127,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.8243989944458,
+      "logits/rejected": 10.843228340148926,
+      "logps/chosen": -119.30509185791016,
+      "logps/ref_chosen": -116.83765411376953,
+      "logps/ref_rejected": -130.78997802734375,
+      "logps/rejected": -133.15672302246094,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.024674497544765472,
+      "rewards/margins": -0.0010069820564240217,
+      "rewards/rejected": -0.02366751804947853,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.8769639134407043,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.427848815917969,
+      "logits/rejected": 11.37716293334961,
+      "logps/chosen": -120.9067611694336,
+      "logps/ref_chosen": -118.43791961669922,
+      "logps/ref_rejected": -132.5309600830078,
+      "logps/rejected": -134.91236877441406,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.02468838170170784,
+      "rewards/margins": -0.0008744060760363936,
+      "rewards/rejected": -0.023813974112272263,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.8736073970794678,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.956391334533691,
+      "logits/rejected": 10.684510231018066,
+      "logps/chosen": -128.198486328125,
+      "logps/ref_chosen": -124.82101440429688,
+      "logps/ref_rejected": -135.32565307617188,
+      "logps/rejected": -138.8860626220703,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.033774565905332565,
+      "rewards/margins": 0.0018295131158083677,
+      "rewards/rejected": -0.0356040820479393,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7293412089347839,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.677412033081055,
+      "logits/rejected": 11.254134178161621,
+      "logps/chosen": -122.79344940185547,
+      "logps/ref_chosen": -119.69990539550781,
+      "logps/ref_rejected": -130.34449768066406,
+      "logps/rejected": -133.39932250976562,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.030935294926166534,
+      "rewards/margins": -0.0003869622596539557,
+      "rewards/rejected": -0.030548332259058952,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.6406402587890625,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.172043800354004,
+      "logits/rejected": 10.859190940856934,
+      "logps/chosen": -118.11813354492188,
+      "logps/ref_chosen": -114.52975463867188,
+      "logps/ref_rejected": -129.5846405029297,
+      "logps/rejected": -133.20779418945312,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.035883828997612,
+      "rewards/margins": 0.00034771906211972237,
+      "rewards/rejected": -0.036231543868780136,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.7559142708778381,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.747884750366211,
+      "logits/rejected": 11.173224449157715,
+      "logps/chosen": -121.89351654052734,
+      "logps/ref_chosen": -117.67997741699219,
+      "logps/ref_rejected": -128.00650024414062,
+      "logps/rejected": -132.31655883789062,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.042135339230298996,
+      "rewards/margins": 0.0009651560103520751,
+      "rewards/rejected": -0.043100498616695404,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.49808746576309204,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.380050659179688,
+      "logits/rejected": 10.91146469116211,
+      "logps/chosen": -125.04395294189453,
+      "logps/ref_chosen": -120.92308044433594,
+      "logps/ref_rejected": -133.8301544189453,
+      "logps/rejected": -138.79052734375,
+      "loss": 0.689,
+      "rewards/accuracies": 0.6328125,
+      "rewards/chosen": -0.0412086620926857,
+      "rewards/margins": 0.008395083248615265,
+      "rewards/rejected": -0.04960374906659126,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.5601547956466675,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.563058853149414,
+      "logits/rejected": 11.37236499786377,
+      "logps/chosen": -126.93672180175781,
+      "logps/ref_chosen": -121.84554290771484,
+      "logps/ref_rejected": -133.343017578125,
+      "logps/rejected": -138.12808227539062,
+      "loss": 0.6948,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.050911907106637955,
+      "rewards/margins": -0.0030612414702773094,
+      "rewards/rejected": -0.04785066470503807,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.41351014375686646,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.687071800231934,
+      "logits/rejected": 10.572582244873047,
+      "logps/chosen": -124.77998352050781,
+      "logps/ref_chosen": -119.20828247070312,
+      "logps/ref_rejected": -134.38436889648438,
+      "logps/rejected": -140.02293395996094,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.055717017501592636,
+      "rewards/margins": 0.0006685962434858084,
+      "rewards/rejected": -0.056385621428489685,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.6027271747589111,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.03482437133789,
+      "logits/rejected": 10.820859909057617,
+      "logps/chosen": -121.17003631591797,
+      "logps/ref_chosen": -114.62059020996094,
+      "logps/ref_rejected": -128.0896759033203,
+      "logps/rejected": -134.1069793701172,
+      "loss": 0.6959,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.06549445539712906,
+      "rewards/margins": -0.005321440752595663,
+      "rewards/rejected": -0.06017300859093666,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.5877695083618164,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.00536060333252,
+      "logits/rejected": 10.877461433410645,
+      "logps/chosen": -124.2905044555664,
+      "logps/ref_chosen": -117.84042358398438,
+      "logps/ref_rejected": -131.79171752929688,
+      "logps/rejected": -137.91160583496094,
+      "loss": 0.6949,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.06450086086988449,
+      "rewards/margins": -0.0033018956892192364,
+      "rewards/rejected": -0.061198972165584564,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5177574157714844,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.104101181030273,
+      "logits/rejected": 10.70304012298584,
+      "logps/chosen": -129.96224975585938,
+      "logps/ref_chosen": -123.75523376464844,
+      "logps/ref_rejected": -138.6237030029297,
+      "logps/rejected": -144.98983764648438,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.062070075422525406,
+      "rewards/margins": 0.0015914504183456302,
+      "rewards/rejected": -0.06366152316331863,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.57741379737854,
+      "learning_rate": 4.246923569447104e-07,
+      "logits/chosen": 10.097904205322266,
+      "logits/rejected": 10.884883880615234,
+      "logps/chosen": -130.04393005371094,
+      "logps/ref_chosen": -122.53610229492188,
+      "logps/ref_rejected": -141.00828552246094,
+      "logps/rejected": -148.18405151367188,
+      "loss": 0.695,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.07507827132940292,
+      "rewards/margins": -0.003320657880976796,
+      "rewards/rejected": -0.07175761461257935,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 0.5819231867790222,
+      "learning_rate": 4.161178683597054e-07,
+      "logits/chosen": 10.32345199584961,
+      "logits/rejected": 11.267877578735352,
+      "logps/chosen": -132.95077514648438,
+      "logps/ref_chosen": -124.1744384765625,
+      "logps/ref_rejected": -139.68605041503906,
+      "logps/rejected": -148.0929718017578,
+      "loss": 0.6952,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.08776339888572693,
+      "rewards/margins": -0.0036940835416316986,
+      "rewards/rejected": -0.08406931161880493,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.6049931645393372,
+      "learning_rate": 4.0717821664772124e-07,
+      "logits/chosen": 10.15705394744873,
+      "logits/rejected": 11.114046096801758,
+      "logps/chosen": -125.23123931884766,
+      "logps/ref_chosen": -117.1941146850586,
+      "logps/ref_rejected": -129.4031982421875,
+      "logps/rejected": -137.76333618164062,
+      "loss": 0.6918,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.08037131279706955,
+      "rewards/margins": 0.0032299975864589214,
+      "rewards/rejected": -0.08360131084918976,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.5475514531135559,
+      "learning_rate": 3.978930531033806e-07,
+      "logits/chosen": 9.436954498291016,
+      "logits/rejected": 10.49735164642334,
+      "logps/chosen": -125.24280548095703,
+      "logps/ref_chosen": -117.17620086669922,
+      "logps/ref_rejected": -130.76107788085938,
+      "logps/rejected": -138.6796875,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.08066616207361221,
+      "rewards/margins": -0.001479951897636056,
+      "rewards/rejected": -0.07918620854616165,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.599656343460083,
+      "learning_rate": 3.882827885312998e-07,
+      "logits/chosen": 10.068204879760742,
+      "logits/rejected": 10.938701629638672,
+      "logps/chosen": -130.98472595214844,
+      "logps/ref_chosen": -123.2500228881836,
+      "logps/ref_rejected": -133.91970825195312,
+      "logps/rejected": -141.19216918945312,
+      "loss": 0.6957,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.07734709233045578,
+      "rewards/margins": -0.004622358828783035,
+      "rewards/rejected": -0.07272473722696304,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.4804610311985016,
+      "learning_rate": 3.7836854837871044e-07,
+      "logits/chosen": 10.131808280944824,
+      "logits/rejected": 11.42764663696289,
+      "logps/chosen": -127.49568176269531,
+      "logps/ref_chosen": -118.52604675292969,
+      "logps/ref_rejected": -139.1146240234375,
+      "logps/rejected": -147.99575805664062,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.08969634026288986,
+      "rewards/margins": -0.0008849686128087342,
+      "rewards/rejected": -0.08881138265132904,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.4208291471004486,
+      "learning_rate": 3.681721262971413e-07,
+      "logits/chosen": 9.75320816040039,
+      "logits/rejected": 10.846428871154785,
+      "logps/chosen": -119.75810241699219,
+      "logps/ref_chosen": -111.525146484375,
+      "logps/ref_rejected": -128.1785888671875,
+      "logps/rejected": -136.38653564453125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.08232954144477844,
+      "rewards/margins": -0.00024991348618641496,
+      "rewards/rejected": -0.08207963407039642,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.7168395519256592,
+      "learning_rate": 3.577159362352426e-07,
+      "logits/chosen": 9.947325706481934,
+      "logits/rejected": 11.155643463134766,
+      "logps/chosen": -124.97373962402344,
+      "logps/ref_chosen": -116.80255126953125,
+      "logps/ref_rejected": -134.80767822265625,
+      "logps/rejected": -142.88174438476562,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4296875,
+      "rewards/chosen": -0.08171181380748749,
+      "rewards/margins": -0.0009711601305752993,
+      "rewards/rejected": -0.08074064552783966,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 1.1801953315734863,
+      "learning_rate": 3.470229631680624e-07,
+      "logits/chosen": 10.00582504272461,
+      "logits/rejected": 10.817474365234375,
+      "logps/chosen": -127.24813842773438,
+      "logps/ref_chosen": -118.635009765625,
+      "logps/ref_rejected": -133.8279571533203,
+      "logps/rejected": -142.4803924560547,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.08613133430480957,
+      "rewards/margins": 0.0003930249949917197,
+      "rewards/rejected": -0.0865243598818779,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.5862898230552673,
+      "learning_rate": 3.361167125710832e-07,
+      "logits/chosen": 10.005105972290039,
+      "logits/rejected": 10.864886283874512,
+      "logps/chosen": -135.84164428710938,
+      "logps/ref_chosen": -126.42659759521484,
+      "logps/ref_rejected": -143.6361846923828,
+      "logps/rejected": -153.5630340576172,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.09415031969547272,
+      "rewards/margins": 0.005118116270750761,
+      "rewards/rejected": -0.09926842898130417,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.7007870674133301,
+      "learning_rate": 3.2502115875008516e-07,
+      "logits/chosen": 10.54973030090332,
+      "logits/rejected": 11.243837356567383,
+      "logps/chosen": -131.86981201171875,
+      "logps/ref_chosen": -123.14965057373047,
+      "logps/ref_rejected": -134.22947692871094,
+      "logps/rejected": -143.7413787841797,
+      "loss": 0.6895,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.0872015431523323,
+      "rewards/margins": 0.007917709648609161,
+      "rewards/rejected": -0.09511925280094147,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.7300606966018677,
+      "learning_rate": 3.137606921404191e-07,
+      "logits/chosen": 10.125234603881836,
+      "logits/rejected": 10.481938362121582,
+      "logps/chosen": -127.8335189819336,
+      "logps/ref_chosen": -118.79129791259766,
+      "logps/ref_rejected": -126.64965057373047,
+      "logps/rejected": -135.0525665283203,
+      "loss": 0.6966,
+      "rewards/accuracies": 0.4296875,
+      "rewards/chosen": -0.09042223542928696,
+      "rewards/margins": -0.006393034942448139,
+      "rewards/rejected": -0.0840291976928711,
+      "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 sha256:4f53b04f950ecaf7266bb70f1df1989b2b5d2e6f85dc23e6ec33647f6e18c1f4
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389dee5a07142051b72fed75424db02b92f924ca356f16fd8d514e6f435dc6c8
+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": 0.39343583583831787,
+      "learning_rate": 6.25e-08,
+      "logits/chosen": 10.071717262268066,
+      "logits/rejected": 10.610974311828613,
+      "logps/chosen": -121.14067077636719,
+      "logps/ref_chosen": -121.14067077636719,
+      "logps/ref_rejected": -137.65684509277344,
+      "logps/rejected": -137.65684509277344,
+      "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": 0.7521647214889526,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": 10.222262382507324,
+      "logits/rejected": 10.754176139831543,
+      "logps/chosen": -116.48068237304688,
+      "logps/ref_chosen": -116.48068237304688,
+      "logps/ref_rejected": -130.27796936035156,
+      "logps/rejected": -130.27796936035156,
+      "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": 0.5880491137504578,
+      "learning_rate": 1.875e-07,
+      "logits/chosen": 10.01984977722168,
+      "logits/rejected": 10.62405776977539,
+      "logps/chosen": -123.36822509765625,
+      "logps/ref_chosen": -122.6683349609375,
+      "logps/ref_rejected": -132.69850158691406,
+      "logps/rejected": -133.207275390625,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.006998830940574408,
+      "rewards/margins": -0.0019110905705019832,
+      "rewards/rejected": -0.005087739787995815,
+      "step": 3
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.4605408310890198,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": 9.99990463256836,
+      "logits/rejected": 10.736846923828125,
+      "logps/chosen": -123.02133178710938,
+      "logps/ref_chosen": -122.59739685058594,
+      "logps/ref_rejected": -129.70767211914062,
+      "logps/rejected": -129.98374938964844,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.004239337984472513,
+      "rewards/margins": -0.0014785109087824821,
+      "rewards/rejected": -0.0027608266100287437,
+      "step": 4
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.469856321811676,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 10.075482368469238,
+      "logits/rejected": 10.892666816711426,
+      "logps/chosen": -117.554931640625,
+      "logps/ref_chosen": -117.5941162109375,
+      "logps/ref_rejected": -132.1708984375,
+      "logps/rejected": -132.1227264404297,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": 0.0003917121794074774,
+      "rewards/margins": -9.010493522509933e-05,
+      "rewards/rejected": 0.0004818170564249158,
+      "step": 5
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.5541566610336304,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 10.660999298095703,
+      "logits/rejected": 11.290507316589355,
+      "logps/chosen": -127.00320434570312,
+      "logps/ref_chosen": -126.12411499023438,
+      "logps/ref_rejected": -136.9976043701172,
+      "logps/rejected": -137.75950622558594,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.00879070907831192,
+      "rewards/margins": -0.0011717069428414106,
+      "rewards/rejected": -0.007619001902639866,
+      "step": 6
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.4422788619995117,
+      "learning_rate": 4.375e-07,
+      "logits/chosen": 9.958097457885742,
+      "logits/rejected": 10.642163276672363,
+      "logps/chosen": -115.61244201660156,
+      "logps/ref_chosen": -115.08863830566406,
+      "logps/ref_rejected": -125.91255187988281,
+      "logps/rejected": -126.15577697753906,
+      "loss": 0.6946,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.005238103214651346,
+      "rewards/margins": -0.0028058765456080437,
+      "rewards/rejected": -0.002432226436212659,
+      "step": 7
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.5495327115058899,
+      "learning_rate": 5e-07,
+      "logits/chosen": 10.345503807067871,
+      "logits/rejected": 10.97708797454834,
+      "logps/chosen": -121.48406982421875,
+      "logps/ref_chosen": -121.4114761352539,
+      "logps/ref_rejected": -134.62770080566406,
+      "logps/rejected": -134.7586212158203,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.0007259202538989484,
+      "rewards/margins": 0.0005832896567881107,
+      "rewards/rejected": -0.0013092098524793983,
+      "step": 8
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.43922048807144165,
+      "learning_rate": 4.997252228714278e-07,
+      "logits/chosen": 10.159126281738281,
+      "logits/rejected": 11.002123832702637,
+      "logps/chosen": -122.51399230957031,
+      "logps/ref_chosen": -121.59207153320312,
+      "logps/ref_rejected": -134.70025634765625,
+      "logps/rejected": -135.55740356445312,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.00921926274895668,
+      "rewards/margins": -0.0006479143630713224,
+      "rewards/rejected": -0.008571348153054714,
+      "step": 9
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.6643485426902771,
+      "learning_rate": 4.989014955054745e-07,
+      "logits/chosen": 9.9464111328125,
+      "logits/rejected": 10.739057540893555,
+      "logps/chosen": -117.91310119628906,
+      "logps/ref_chosen": -117.16349029541016,
+      "logps/ref_rejected": -129.98167419433594,
+      "logps/rejected": -130.65924072265625,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.007496046833693981,
+      "rewards/margins": -0.0007203805143944919,
+      "rewards/rejected": -0.00677566509693861,
+      "step": 10
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.4432956576347351,
+      "learning_rate": 4.975306286336627e-07,
+      "logits/chosen": 10.095781326293945,
+      "logits/rejected": 11.001167297363281,
+      "logps/chosen": -123.26506042480469,
+      "logps/ref_chosen": -121.95927429199219,
+      "logps/ref_rejected": -136.18655395507812,
+      "logps/rejected": -137.39865112304688,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.01305788941681385,
+      "rewards/margins": -0.0009369202307425439,
+      "rewards/rejected": -0.012120969593524933,
+      "step": 11
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.3955974280834198,
+      "learning_rate": 4.956156357188939e-07,
+      "logits/chosen": 10.129995346069336,
+      "logits/rejected": 10.673677444458008,
+      "logps/chosen": -126.05357360839844,
+      "logps/ref_chosen": -124.12315368652344,
+      "logps/ref_rejected": -134.275390625,
+      "logps/rejected": -136.24940490722656,
+      "loss": 0.693,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.01930420845746994,
+      "rewards/margins": 0.00043603626545518637,
+      "rewards/rejected": -0.01974024437367916,
+      "step": 12
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.4873650074005127,
+      "learning_rate": 4.931607263312032e-07,
+      "logits/chosen": 9.8243989944458,
+      "logits/rejected": 10.843228340148926,
+      "logps/chosen": -119.30509185791016,
+      "logps/ref_chosen": -116.83765411376953,
+      "logps/ref_rejected": -130.78997802734375,
+      "logps/rejected": -133.15672302246094,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.4453125,
+      "rewards/chosen": -0.024674497544765472,
+      "rewards/margins": -0.0010069820564240217,
+      "rewards/rejected": -0.02366751804947853,
+      "step": 13
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.8769639134407043,
+      "learning_rate": 4.9017129689421e-07,
+      "logits/chosen": 10.427848815917969,
+      "logits/rejected": 11.37716293334961,
+      "logps/chosen": -120.9067611694336,
+      "logps/ref_chosen": -118.43791961669922,
+      "logps/ref_rejected": -132.5309600830078,
+      "logps/rejected": -134.91236877441406,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.02468838170170784,
+      "rewards/margins": -0.0008744060760363936,
+      "rewards/rejected": -0.023813974112272263,
+      "step": 14
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.8736073970794678,
+      "learning_rate": 4.866539188226085e-07,
+      "logits/chosen": 9.956391334533691,
+      "logits/rejected": 10.684510231018066,
+      "logps/chosen": -128.198486328125,
+      "logps/ref_chosen": -124.82101440429688,
+      "logps/ref_rejected": -135.32565307617188,
+      "logps/rejected": -138.8860626220703,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.033774565905332565,
+      "rewards/margins": 0.0018295131158083677,
+      "rewards/rejected": -0.0356040820479393,
+      "step": 15
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.7293412089347839,
+      "learning_rate": 4.826163240767716e-07,
+      "logits/chosen": 10.677412033081055,
+      "logits/rejected": 11.254134178161621,
+      "logps/chosen": -122.79344940185547,
+      "logps/ref_chosen": -119.69990539550781,
+      "logps/ref_rejected": -130.34449768066406,
+      "logps/rejected": -133.39932250976562,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.030935294926166534,
+      "rewards/margins": -0.0003869622596539557,
+      "rewards/rejected": -0.030548332259058952,
+      "step": 16
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.6406402587890625,
+      "learning_rate": 4.780673881662242e-07,
+      "logits/chosen": 10.172043800354004,
+      "logits/rejected": 10.859190940856934,
+      "logps/chosen": -118.11813354492188,
+      "logps/ref_chosen": -114.52975463867188,
+      "logps/ref_rejected": -129.5846405029297,
+      "logps/rejected": -133.20779418945312,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.035883828997612,
+      "rewards/margins": 0.00034771906211972237,
+      "rewards/rejected": -0.036231543868780136,
+      "step": 17
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.7559142708778381,
+      "learning_rate": 4.730171106393466e-07,
+      "logits/chosen": 10.747884750366211,
+      "logits/rejected": 11.173224449157715,
+      "logps/chosen": -121.89351654052734,
+      "logps/ref_chosen": -117.67997741699219,
+      "logps/ref_rejected": -128.00650024414062,
+      "logps/rejected": -132.31655883789062,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.546875,
+      "rewards/chosen": -0.042135339230298996,
+      "rewards/margins": 0.0009651560103520751,
+      "rewards/rejected": -0.043100498616695404,
+      "step": 18
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.49808746576309204,
+      "learning_rate": 4.6747659310219757e-07,
+      "logits/chosen": 10.380050659179688,
+      "logits/rejected": 10.91146469116211,
+      "logps/chosen": -125.04395294189453,
+      "logps/ref_chosen": -120.92308044433594,
+      "logps/ref_rejected": -133.8301544189453,
+      "logps/rejected": -138.79052734375,
+      "loss": 0.689,
+      "rewards/accuracies": 0.6328125,
+      "rewards/chosen": -0.0412086620926857,
+      "rewards/margins": 0.008395083248615265,
+      "rewards/rejected": -0.04960374906659126,
+      "step": 19
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.5601547956466675,
+      "learning_rate": 4.6145801481477433e-07,
+      "logits/chosen": 10.563058853149414,
+      "logits/rejected": 11.37236499786377,
+      "logps/chosen": -126.93672180175781,
+      "logps/ref_chosen": -121.84554290771484,
+      "logps/ref_rejected": -133.343017578125,
+      "logps/rejected": -138.12808227539062,
+      "loss": 0.6948,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": -0.050911907106637955,
+      "rewards/margins": -0.0030612414702773094,
+      "rewards/rejected": -0.04785066470503807,
+      "step": 20
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.41351014375686646,
+      "learning_rate": 4.549746059183561e-07,
+      "logits/chosen": 9.687071800231934,
+      "logits/rejected": 10.572582244873047,
+      "logps/chosen": -124.77998352050781,
+      "logps/ref_chosen": -119.20828247070312,
+      "logps/ref_rejected": -134.38436889648438,
+      "logps/rejected": -140.02293395996094,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.055717017501592636,
+      "rewards/margins": 0.0006685962434858084,
+      "rewards/rejected": -0.056385621428489685,
+      "step": 21
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.6027271747589111,
+      "learning_rate": 4.480406183527823e-07,
+      "logits/chosen": 10.03482437133789,
+      "logits/rejected": 10.820859909057617,
+      "logps/chosen": -121.17003631591797,
+      "logps/ref_chosen": -114.62059020996094,
+      "logps/ref_rejected": -128.0896759033203,
+      "logps/rejected": -134.1069793701172,
+      "loss": 0.6959,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.06549445539712906,
+      "rewards/margins": -0.005321440752595663,
+      "rewards/rejected": -0.06017300859093666,
+      "step": 22
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.5877695083618164,
+      "learning_rate": 4.4067129452759546e-07,
+      "logits/chosen": 10.00536060333252,
+      "logits/rejected": 10.877461433410645,
+      "logps/chosen": -124.2905044555664,
+      "logps/ref_chosen": -117.84042358398438,
+      "logps/ref_rejected": -131.79171752929688,
+      "logps/rejected": -137.91160583496094,
+      "loss": 0.6949,
+      "rewards/accuracies": 0.46875,
+      "rewards/chosen": -0.06450086086988449,
+      "rewards/margins": -0.0033018956892192364,
+      "rewards/rejected": -0.061198972165584564,
+      "step": 23
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.5177574157714844,
+      "learning_rate": 4.3288283381591725e-07,
+      "logits/chosen": 10.104101181030273,
+      "logits/rejected": 10.70304012298584,
+      "logps/chosen": -129.96224975585938,
+      "logps/ref_chosen": -123.75523376464844,
+      "logps/ref_rejected": -138.6237030029297,
+      "logps/rejected": -144.98983764648438,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": -0.062070075422525406,
+      "rewards/margins": 0.0015914504183456302,
+      "rewards/rejected": -0.06366152316331863,
+      "step": 24
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.57741379737854,
+      "learning_rate": 4.246923569447104e-07,
+      "logits/chosen": 10.097904205322266,
+      "logits/rejected": 10.884883880615234,
+      "logps/chosen": -130.04393005371094,
+      "logps/ref_chosen": -122.53610229492188,
+      "logps/ref_rejected": -141.00828552246094,
+      "logps/rejected": -148.18405151367188,
+      "loss": 0.695,
+      "rewards/accuracies": 0.4609375,
+      "rewards/chosen": -0.07507827132940292,
+      "rewards/margins": -0.003320657880976796,
+      "rewards/rejected": -0.07175761461257935,
+      "step": 25
+    },
+    {
+      "epoch": 0.34252778921366817,
+      "grad_norm": 0.5819231867790222,
+      "learning_rate": 4.161178683597054e-07,
+      "logits/chosen": 10.32345199584961,
+      "logits/rejected": 11.267877578735352,
+      "logps/chosen": -132.95077514648438,
+      "logps/ref_chosen": -124.1744384765625,
+      "logps/ref_rejected": -139.68605041503906,
+      "logps/rejected": -148.0929718017578,
+      "loss": 0.6952,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.08776339888572693,
+      "rewards/margins": -0.0036940835416316986,
+      "rewards/rejected": -0.08406931161880493,
+      "step": 26
+    },
+    {
+      "epoch": 0.3557019349526554,
+      "grad_norm": 0.6049931645393372,
+      "learning_rate": 4.0717821664772124e-07,
+      "logits/chosen": 10.15705394744873,
+      "logits/rejected": 11.114046096801758,
+      "logps/chosen": -125.23123931884766,
+      "logps/ref_chosen": -117.1941146850586,
+      "logps/ref_rejected": -129.4031982421875,
+      "logps/rejected": -137.76333618164062,
+      "loss": 0.6918,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.08037131279706955,
+      "rewards/margins": 0.0032299975864589214,
+      "rewards/rejected": -0.08360131084918976,
+      "step": 27
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.5475514531135559,
+      "learning_rate": 3.978930531033806e-07,
+      "logits/chosen": 9.436954498291016,
+      "logits/rejected": 10.49735164642334,
+      "logps/chosen": -125.24280548095703,
+      "logps/ref_chosen": -117.17620086669922,
+      "logps/ref_rejected": -130.76107788085938,
+      "logps/rejected": -138.6796875,
+      "loss": 0.6941,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.08066616207361221,
+      "rewards/margins": -0.001479951897636056,
+      "rewards/rejected": -0.07918620854616165,
+      "step": 28
+    },
+    {
+      "epoch": 0.3820502264306299,
+      "grad_norm": 0.599656343460083,
+      "learning_rate": 3.882827885312998e-07,
+      "logits/chosen": 10.068204879760742,
+      "logits/rejected": 10.938701629638672,
+      "logps/chosen": -130.98472595214844,
+      "logps/ref_chosen": -123.2500228881836,
+      "logps/ref_rejected": -133.91970825195312,
+      "logps/rejected": -141.19216918945312,
+      "loss": 0.6957,
+      "rewards/accuracies": 0.453125,
+      "rewards/chosen": -0.07734709233045578,
+      "rewards/margins": -0.004622358828783035,
+      "rewards/rejected": -0.07272473722696304,
+      "step": 29
+    },
+    {
+      "epoch": 0.39522437216961714,
+      "grad_norm": 0.4804610311985016,
+      "learning_rate": 3.7836854837871044e-07,
+      "logits/chosen": 10.131808280944824,
+      "logits/rejected": 11.42764663696289,
+      "logps/chosen": -127.49568176269531,
+      "logps/ref_chosen": -118.52604675292969,
+      "logps/ref_rejected": -139.1146240234375,
+      "logps/rejected": -147.99575805664062,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.08969634026288986,
+      "rewards/margins": -0.0008849686128087342,
+      "rewards/rejected": -0.08881138265132904,
+      "step": 30
+    },
+    {
+      "epoch": 0.4083985179086044,
+      "grad_norm": 0.4208291471004486,
+      "learning_rate": 3.681721262971413e-07,
+      "logits/chosen": 9.75320816040039,
+      "logits/rejected": 10.846428871154785,
+      "logps/chosen": -119.75810241699219,
+      "logps/ref_chosen": -111.525146484375,
+      "logps/ref_rejected": -128.1785888671875,
+      "logps/rejected": -136.38653564453125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.08232954144477844,
+      "rewards/margins": -0.00024991348618641496,
+      "rewards/rejected": -0.08207963407039642,
+      "step": 31
+    },
+    {
+      "epoch": 0.4215726636475916,
+      "grad_norm": 0.7168395519256592,
+      "learning_rate": 3.577159362352426e-07,
+      "logits/chosen": 9.947325706481934,
+      "logits/rejected": 11.155643463134766,
+      "logps/chosen": -124.97373962402344,
+      "logps/ref_chosen": -116.80255126953125,
+      "logps/ref_rejected": -134.80767822265625,
+      "logps/rejected": -142.88174438476562,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4296875,
+      "rewards/chosen": -0.08171181380748749,
+      "rewards/margins": -0.0009711601305752993,
+      "rewards/rejected": -0.08074064552783966,
+      "step": 32
+    },
+    {
+      "epoch": 0.43474680938657884,
+      "grad_norm": 1.1801953315734863,
+      "learning_rate": 3.470229631680624e-07,
+      "logits/chosen": 10.00582504272461,
+      "logits/rejected": 10.817474365234375,
+      "logps/chosen": -127.24813842773438,
+      "logps/ref_chosen": -118.635009765625,
+      "logps/ref_rejected": -133.8279571533203,
+      "logps/rejected": -142.4803924560547,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.08613133430480957,
+      "rewards/margins": 0.0003930249949917197,
+      "rewards/rejected": -0.0865243598818779,
+      "step": 33
+    },
+    {
+      "epoch": 0.44792095512556607,
+      "grad_norm": 0.5862898230552673,
+      "learning_rate": 3.361167125710832e-07,
+      "logits/chosen": 10.005105972290039,
+      "logits/rejected": 10.864886283874512,
+      "logps/chosen": -135.84164428710938,
+      "logps/ref_chosen": -126.42659759521484,
+      "logps/ref_rejected": -143.6361846923828,
+      "logps/rejected": -153.5630340576172,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.09415031969547272,
+      "rewards/margins": 0.005118116270750761,
+      "rewards/rejected": -0.09926842898130417,
+      "step": 34
+    },
+    {
+      "epoch": 0.4610951008645533,
+      "grad_norm": 0.7007870674133301,
+      "learning_rate": 3.2502115875008516e-07,
+      "logits/chosen": 10.54973030090332,
+      "logits/rejected": 11.243837356567383,
+      "logps/chosen": -131.86981201171875,
+      "logps/ref_chosen": -123.14965057373047,
+      "logps/ref_rejected": -134.22947692871094,
+      "logps/rejected": -143.7413787841797,
+      "loss": 0.6895,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.0872015431523323,
+      "rewards/margins": 0.007917709648609161,
+      "rewards/rejected": -0.09511925280094147,
+      "step": 35
+    },
+    {
+      "epoch": 0.47426924660354053,
+      "grad_norm": 0.7300606966018677,
+      "learning_rate": 3.137606921404191e-07,
+      "logits/chosen": 10.125234603881836,
+      "logits/rejected": 10.481938362121582,
+      "logps/chosen": -127.8335189819336,
+      "logps/ref_chosen": -118.79129791259766,
+      "logps/ref_rejected": -126.64965057373047,
+      "logps/rejected": -135.0525665283203,
+      "loss": 0.6966,
+      "rewards/accuracies": 0.4296875,
+      "rewards/chosen": -0.09042223542928696,
+      "rewards/margins": -0.006393034942448139,
+      "rewards/rejected": -0.0840291976928711,
+      "step": 36
+    },
+    {
+      "epoch": 0.4874433923425278,
+      "grad_norm": 0.456684947013855,
+      "learning_rate": 3.0236006569153616e-07,
+      "logits/chosen": 10.322757720947266,
+      "logits/rejected": 10.932893753051758,
+      "logps/chosen": -130.44381713867188,
+      "logps/ref_chosen": -121.899169921875,
+      "logps/ref_rejected": -136.85321044921875,
+      "logps/rejected": -145.57542419433594,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.4921875,
+      "rewards/chosen": -0.08544634282588959,
+      "rewards/margins": 0.00177572516258806,
+      "rewards/rejected": -0.08722206950187683,
+      "step": 37
+    },
+    {
+      "epoch": 0.500617538081515,
+      "grad_norm": 0.6402201056480408,
+      "learning_rate": 2.9084434045463254e-07,
+      "logits/chosen": 10.014504432678223,
+      "logits/rejected": 10.873030662536621,
+      "logps/chosen": -127.30659484863281,
+      "logps/ref_chosen": -118.75363159179688,
+      "logps/ref_rejected": -132.82818603515625,
+      "logps/rejected": -141.9580535888672,
+      "loss": 0.6905,
+      "rewards/accuracies": 0.5546875,
+      "rewards/chosen": -0.08552955836057663,
+      "rewards/margins": 0.005769058130681515,
+      "rewards/rejected": -0.09129861742258072,
+      "step": 38
+    },
+    {
+      "epoch": 0.5137916838205022,
+      "grad_norm": 0.5188658833503723,
+      "learning_rate": 2.7923883049302066e-07,
+      "logits/chosen": 10.178832054138184,
+      "logits/rejected": 10.932839393615723,
+      "logps/chosen": -137.26002502441406,
+      "logps/ref_chosen": -128.23240661621094,
+      "logps/ref_rejected": -140.05517578125,
+      "logps/rejected": -149.08457946777344,
+      "loss": 0.6934,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.09027623385190964,
+      "rewards/margins": 1.788110239431262e-05,
+      "rewards/rejected": -0.09029410034418106,
+      "step": 39
+    },
+    {
+      "epoch": 0.5269658295594895,
+      "grad_norm": 0.7729969024658203,
+      "learning_rate": 2.6756904723632324e-07,
+      "logits/chosen": 10.076566696166992,
+      "logits/rejected": 11.339007377624512,
+      "logps/chosen": -127.69380187988281,
+      "logps/ref_chosen": -118.38938903808594,
+      "logps/ref_rejected": -138.8988037109375,
+      "logps/rejected": -147.9398956298828,
+      "loss": 0.6947,
+      "rewards/accuracies": 0.484375,
+      "rewards/chosen": -0.09304402768611908,
+      "rewards/margins": -0.0026330682449042797,
+      "rewards/rejected": -0.09041095525026321,
+      "step": 40
+    },
+    {
+      "epoch": 0.5401399752984768,
+      "grad_norm": 0.6295668482780457,
+      "learning_rate": 2.5586064340081516e-07,
+      "logits/chosen": 10.364312171936035,
+      "logits/rejected": 10.864094734191895,
+      "logps/chosen": -126.18923950195312,
+      "logps/ref_chosen": -117.82182312011719,
+      "logps/ref_rejected": -132.89553833007812,
+      "logps/rejected": -142.4484405517578,
+      "loss": 0.6875,
+      "rewards/accuracies": 0.5703125,
+      "rewards/chosen": -0.08367416262626648,
+      "rewards/margins": 0.011854931712150574,
+      "rewards/rejected": -0.09552909433841705,
+      "step": 41
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": 0.6686902046203613,
+      "learning_rate": 2.4413935659918487e-07,
+      "logits/chosen": 9.487873077392578,
+      "logits/rejected": 10.435559272766113,
+      "logps/chosen": -125.37492370605469,
+      "logps/ref_chosen": -117.0536117553711,
+      "logps/ref_rejected": -130.59812927246094,
+      "logps/rejected": -139.56155395507812,
+      "loss": 0.6903,
+      "rewards/accuracies": 0.5234375,
+      "rewards/chosen": -0.08321310579776764,
+      "rewards/margins": 0.006421199534088373,
+      "rewards/rejected": -0.08963430672883987,
+      "step": 42
+    },
+    {
+      "epoch": 0.5664882667764513,
+      "grad_norm": 0.5477384924888611,
+      "learning_rate": 2.3243095276367684e-07,
+      "logits/chosen": 9.582094192504883,
+      "logits/rejected": 10.506773948669434,
+      "logps/chosen": -124.29164123535156,
+      "logps/ref_chosen": -115.851806640625,
+      "logps/ref_rejected": -130.8096160888672,
+      "logps/rejected": -139.1727294921875,
+      "loss": 0.6938,
+      "rewards/accuracies": 0.515625,
+      "rewards/chosen": -0.08439842611551285,
+      "rewards/margins": -0.0007674552034586668,
+      "rewards/rejected": -0.08363097161054611,
+      "step": 43
+    },
+    {
+      "epoch": 0.5796624125154385,
+      "grad_norm": 0.4657438397407532,
+      "learning_rate": 2.2076116950697937e-07,
+      "logits/chosen": 9.838776588439941,
+      "logits/rejected": 10.566040992736816,
+      "logps/chosen": -126.56464385986328,
+      "logps/ref_chosen": -117.90168762207031,
+      "logps/ref_rejected": -132.960693359375,
+      "logps/rejected": -142.1176300048828,
+      "loss": 0.6909,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.08662942796945572,
+      "rewards/margins": 0.004940015729516745,
+      "rewards/rejected": -0.0915694385766983,
+      "step": 44
+    },
+    {
+      "epoch": 0.5928365582544257,
+      "grad_norm": 0.4596782922744751,
+      "learning_rate": 2.091556595453674e-07,
+      "logits/chosen": 9.941704750061035,
+      "logits/rejected": 10.477331161499023,
+      "logps/chosen": -127.3547592163086,
+      "logps/ref_chosen": -118.84819030761719,
+      "logps/ref_rejected": -134.4351806640625,
+      "logps/rejected": -143.46334838867188,
+      "loss": 0.6908,
+      "rewards/accuracies": 0.5390625,
+      "rewards/chosen": -0.08506564050912857,
+      "rewards/margins": 0.005216139368712902,
+      "rewards/rejected": -0.09028176963329315,
+      "step": 45
+    },
+    {
+      "epoch": 0.606010703993413,
+      "grad_norm": 0.7369089722633362,
+      "learning_rate": 1.9763993430846392e-07,
+      "logits/chosen": 9.956421852111816,
+      "logits/rejected": 10.419254302978516,
+      "logps/chosen": -124.58769989013672,
+      "logps/ref_chosen": -116.23255920410156,
+      "logps/ref_rejected": -127.91217041015625,
+      "logps/rejected": -137.61070251464844,
+      "loss": 0.6867,
+      "rewards/accuracies": 0.609375,
+      "rewards/chosen": -0.08355137705802917,
+      "rewards/margins": 0.013433952815830708,
+      "rewards/rejected": -0.0969853326678276,
+      "step": 46
+    },
+    {
+      "epoch": 0.6191848497324002,
+      "grad_norm": 0.6935871243476868,
+      "learning_rate": 1.862393078595809e-07,
+      "logits/chosen": 9.769856452941895,
+      "logits/rejected": 10.882231712341309,
+      "logps/chosen": -133.2343292236328,
+      "logps/ref_chosen": -123.88105773925781,
+      "logps/ref_rejected": -140.62420654296875,
+      "logps/rejected": -150.24195861816406,
+      "loss": 0.692,
+      "rewards/accuracies": 0.5078125,
+      "rewards/chosen": -0.09353267401456833,
+      "rewards/margins": 0.0026449086144566536,
+      "rewards/rejected": -0.0961775854229927,
+      "step": 47
+    },
+    {
+      "epoch": 0.6323589954713874,
+      "grad_norm": 0.9227128624916077,
+      "learning_rate": 1.7497884124991485e-07,
+      "logits/chosen": 10.461740493774414,
+      "logits/rejected": 11.23796272277832,
+      "logps/chosen": -129.02268981933594,
+      "logps/ref_chosen": -119.78947448730469,
+      "logps/ref_rejected": -134.12991333007812,
+      "logps/rejected": -143.42581176757812,
+      "loss": 0.693,
+      "rewards/accuracies": 0.4765625,
+      "rewards/chosen": -0.09233222156763077,
+      "rewards/margins": 0.0006269109435379505,
+      "rewards/rejected": -0.09295912832021713,
+      "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:b8daa158549478bd5b073773f705be437055ab86fa21623bcb3641a22021c68a
+size 4972489328

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa17ddf93029eb17d01d3ce466dce4e8f3be27cf051c8a7ace38b4f83c4fe5c6
+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
+  }
+}