Upload folder using huggingface_hub

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--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": "float32",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32011
+}

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": "4.40.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0b4e52c279bb0c001bc5add4747bcd0f76ae3021e0c494b26e3bcc1b463d89
+size 4961201152

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b85b407ef8a977cf237d09d1eea6f45cac1b034c284ad69e9a85ac53fe19fa2
+size 4983111176

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c575e9af34b468803e85e571bec25711481005ef300f1de2b70ce5e4cd4e3e
+size 4945374704

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:039a923da7450d1953c64df560a4c8289ec43bcee6490e256dcc059c66255f3f
+size 393351296

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 15283015680
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b901262891c97b18b30ecc1125283e1f76958450e507ab529889c61a9101ae0
+size 30566201634

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d443fe92d884b41152079d0a798667000e213b61ace3999525c785c947b9fd4f
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,130 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "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
+}

trainer_state.json

@@ -0,0 +1,543 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.957146863129987,
+  "eval_steps": 500,
+  "global_step": 14500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10197058148724093,
+      "grad_norm": 3.7134974002838135,
+      "learning_rate": 4.8313957441022504e-05,
+      "log_odds_chosen": 0.2222207486629486,
+      "log_odds_ratio": -0.6578092575073242,
+      "logits/chosen": -0.44847217202186584,
+      "logits/rejected": -0.7988718152046204,
+      "logps/chosen": -1.3054556846618652,
+      "logps/rejected": -1.482597827911377,
+      "loss": 1.2524,
+      "nll_loss": 1.1866657733917236,
+      "rewards/accuracies": 0.5920000076293945,
+      "rewards/chosen": -0.13054557144641876,
+      "rewards/margins": 0.01771421544253826,
+      "rewards/rejected": -0.14825978875160217,
+      "step": 500
+    },
+    {
+      "epoch": 0.20394116297448187,
+      "grad_norm": 2.004502058029175,
+      "learning_rate": 4.6614317764633906e-05,
+      "log_odds_chosen": 0.35723409056663513,
+      "log_odds_ratio": -0.629149317741394,
+      "logits/chosen": -1.3414314985275269,
+      "logits/rejected": -1.5448620319366455,
+      "logps/chosen": -1.255893588066101,
+      "logps/rejected": -1.5381147861480713,
+      "loss": 1.0135,
+      "nll_loss": 0.9506049752235413,
+      "rewards/accuracies": 0.609000027179718,
+      "rewards/chosen": -0.12558937072753906,
+      "rewards/margins": 0.028222110122442245,
+      "rewards/rejected": -0.1538114696741104,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3059117444617228,
+      "grad_norm": 1.5967992544174194,
+      "learning_rate": 4.4914678088245294e-05,
+      "log_odds_chosen": 0.45203697681427,
+      "log_odds_ratio": -0.6168015003204346,
+      "logits/chosen": -1.578227162361145,
+      "logits/rejected": -1.7268493175506592,
+      "logps/chosen": -1.1664234399795532,
+      "logps/rejected": -1.515409231185913,
+      "loss": 0.9167,
+      "nll_loss": 0.8550541400909424,
+      "rewards/accuracies": 0.6147500276565552,
+      "rewards/chosen": -0.11664234101772308,
+      "rewards/margins": 0.034898579120635986,
+      "rewards/rejected": -0.15154090523719788,
+      "step": 1500
+    },
+    {
+      "epoch": 0.40788232594896373,
+      "grad_norm": 1.4804637432098389,
+      "learning_rate": 4.321503841185669e-05,
+      "log_odds_chosen": 0.5433089733123779,
+      "log_odds_ratio": -0.605213463306427,
+      "logits/chosen": -1.7934901714324951,
+      "logits/rejected": -1.9556081295013428,
+      "logps/chosen": -1.108548879623413,
+      "logps/rejected": -1.5245370864868164,
+      "loss": 0.8516,
+      "nll_loss": 0.7910776734352112,
+      "rewards/accuracies": 0.628250002861023,
+      "rewards/chosen": -0.11085488647222519,
+      "rewards/margins": 0.04159883037209511,
+      "rewards/rejected": -0.1524537056684494,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5098529074362047,
+      "grad_norm": 1.2357059717178345,
+      "learning_rate": 4.151539873546808e-05,
+      "log_odds_chosen": 0.6769158244132996,
+      "log_odds_ratio": -0.5792952179908752,
+      "logits/chosen": -1.9547886848449707,
+      "logits/rejected": -2.1045212745666504,
+      "logps/chosen": -1.04926335811615,
+      "logps/rejected": -1.554589033126831,
+      "loss": 0.7987,
+      "nll_loss": 0.7408133745193481,
+      "rewards/accuracies": 0.656499981880188,
+      "rewards/chosen": -0.10492634028196335,
+      "rewards/margins": 0.050532568246126175,
+      "rewards/rejected": -0.15545891225337982,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6118234889234456,
+      "grad_norm": 1.753408432006836,
+      "learning_rate": 3.981575905907948e-05,
+      "log_odds_chosen": 0.7549012303352356,
+      "log_odds_ratio": -0.5683782696723938,
+      "logits/chosen": -2.111973285675049,
+      "logits/rejected": -2.268782615661621,
+      "logps/chosen": -1.0075668096542358,
+      "logps/rejected": -1.5643786191940308,
+      "loss": 0.7492,
+      "nll_loss": 0.6923843026161194,
+      "rewards/accuracies": 0.640999972820282,
+      "rewards/chosen": -0.1007566824555397,
+      "rewards/margins": 0.055681198835372925,
+      "rewards/rejected": -0.15643785893917084,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7137940704106865,
+      "grad_norm": 1.8108484745025635,
+      "learning_rate": 3.811611938269087e-05,
+      "log_odds_chosen": 0.7971724271774292,
+      "log_odds_ratio": -0.5602663159370422,
+      "logits/chosen": -2.263519525527954,
+      "logits/rejected": -2.3989477157592773,
+      "logps/chosen": -0.9775514006614685,
+      "logps/rejected": -1.5509178638458252,
+      "loss": 0.7398,
+      "nll_loss": 0.6837689280509949,
+      "rewards/accuracies": 0.6542500257492065,
+      "rewards/chosen": -0.09775513410568237,
+      "rewards/margins": 0.05733664333820343,
+      "rewards/rejected": -0.1550917774438858,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8157646518979275,
+      "grad_norm": 0.9750083684921265,
+      "learning_rate": 3.641647970630227e-05,
+      "log_odds_chosen": 0.8391203880310059,
+      "log_odds_ratio": -0.5608585476875305,
+      "logits/chosen": -2.2849109172821045,
+      "logits/rejected": -2.413522720336914,
+      "logps/chosen": -0.9366417527198792,
+      "logps/rejected": -1.5379432439804077,
+      "loss": 0.708,
+      "nll_loss": 0.6518718600273132,
+      "rewards/accuracies": 0.6554999947547913,
+      "rewards/chosen": -0.09366416931152344,
+      "rewards/margins": 0.06013017147779465,
+      "rewards/rejected": -0.1537943333387375,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9177352333851684,
+      "grad_norm": 1.1859960556030273,
+      "learning_rate": 3.471684002991366e-05,
+      "log_odds_chosen": 0.9322497844696045,
+      "log_odds_ratio": -0.5479665398597717,
+      "logits/chosen": -2.4118337631225586,
+      "logits/rejected": -2.5123636722564697,
+      "logps/chosen": -0.9224444031715393,
+      "logps/rejected": -1.572380781173706,
+      "loss": 0.6784,
+      "nll_loss": 0.6236190795898438,
+      "rewards/accuracies": 0.6604999899864197,
+      "rewards/chosen": -0.09224444627761841,
+      "rewards/margins": 0.06499364972114563,
+      "rewards/rejected": -0.15723808109760284,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0197058148724094,
+      "grad_norm": 1.545590877532959,
+      "learning_rate": 3.301720035352505e-05,
+      "log_odds_chosen": 1.231202244758606,
+      "log_odds_ratio": -0.4899790585041046,
+      "logits/chosen": -2.496483564376831,
+      "logits/rejected": -2.5658133029937744,
+      "logps/chosen": -0.8024629950523376,
+      "logps/rejected": -1.6277039051055908,
+      "loss": 0.5995,
+      "nll_loss": 0.5504766702651978,
+      "rewards/accuracies": 0.7229999899864197,
+      "rewards/chosen": -0.08024629950523376,
+      "rewards/margins": 0.08252407610416412,
+      "rewards/rejected": -0.16277039051055908,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1216763963596503,
+      "grad_norm": 1.1230560541152954,
+      "learning_rate": 3.132095995648923e-05,
+      "log_odds_chosen": 2.3458921909332275,
+      "log_odds_ratio": -0.2528613209724426,
+      "logits/chosen": -2.7195615768432617,
+      "logits/rejected": -2.732959270477295,
+      "logps/chosen": -0.4438183605670929,
+      "logps/rejected": -1.9251257181167603,
+      "loss": 0.3371,
+      "nll_loss": 0.311859130859375,
+      "rewards/accuracies": 0.9585000276565552,
+      "rewards/chosen": -0.04438183456659317,
+      "rewards/margins": 0.14813074469566345,
+      "rewards/rejected": -0.19251257181167603,
+      "step": 5500
+    },
+    {
+      "epoch": 1.2236469778468912,
+      "grad_norm": 1.688524603843689,
+      "learning_rate": 2.9621320280100618e-05,
+      "log_odds_chosen": 2.3827967643737793,
+      "log_odds_ratio": -0.25957345962524414,
+      "logits/chosen": -2.720367193222046,
+      "logits/rejected": -2.767230987548828,
+      "logps/chosen": -0.44125357270240784,
+      "logps/rejected": -1.953121304512024,
+      "loss": 0.334,
+      "nll_loss": 0.3080129623413086,
+      "rewards/accuracies": 0.9617499709129333,
+      "rewards/chosen": -0.04412535950541496,
+      "rewards/margins": 0.1511867791414261,
+      "rewards/rejected": -0.19531212747097015,
+      "step": 6000
+    },
+    {
+      "epoch": 1.3256175593341322,
+      "grad_norm": 1.2772260904312134,
+      "learning_rate": 2.792507988306479e-05,
+      "log_odds_chosen": 2.2994472980499268,
+      "log_odds_ratio": -0.26726964116096497,
+      "logits/chosen": -2.7083919048309326,
+      "logits/rejected": -2.772411823272705,
+      "logps/chosen": -0.45140743255615234,
+      "logps/rejected": -1.911563754081726,
+      "loss": 0.3471,
+      "nll_loss": 0.32037463784217834,
+      "rewards/accuracies": 0.9572499990463257,
+      "rewards/chosen": -0.045140739530324936,
+      "rewards/margins": 0.14601562917232513,
+      "rewards/rejected": -0.19115637242794037,
+      "step": 6500
+    },
+    {
+      "epoch": 1.427588140821373,
+      "grad_norm": 1.3095237016677856,
+      "learning_rate": 2.622544020667619e-05,
+      "log_odds_chosen": 2.344271659851074,
+      "log_odds_ratio": -0.27038824558258057,
+      "logits/chosen": -2.74202823638916,
+      "logits/rejected": -2.7950618267059326,
+      "logps/chosen": -0.42455798387527466,
+      "logps/rejected": -1.880998134613037,
+      "loss": 0.3258,
+      "nll_loss": 0.29875221848487854,
+      "rewards/accuracies": 0.952750027179718,
+      "rewards/chosen": -0.042455799877643585,
+      "rewards/margins": 0.14564399421215057,
+      "rewards/rejected": -0.18809978663921356,
+      "step": 7000
+    },
+    {
+      "epoch": 1.529558722308614,
+      "grad_norm": 1.1868637800216675,
+      "learning_rate": 2.452580053028758e-05,
+      "log_odds_chosen": 2.3831584453582764,
+      "log_odds_ratio": -0.26601019501686096,
+      "logits/chosen": -2.7699034214019775,
+      "logits/rejected": -2.8358941078186035,
+      "logps/chosen": -0.43710044026374817,
+      "logps/rejected": -1.9111379384994507,
+      "loss": 0.3313,
+      "nll_loss": 0.3046627938747406,
+      "rewards/accuracies": 0.9614999890327454,
+      "rewards/chosen": -0.043710045516490936,
+      "rewards/margins": 0.147403746843338,
+      "rewards/rejected": -0.19111379981040955,
+      "step": 7500
+    },
+    {
+      "epoch": 1.631529303795855,
+      "grad_norm": 1.8944728374481201,
+      "learning_rate": 2.2826160853898975e-05,
+      "log_odds_chosen": 2.470182180404663,
+      "log_odds_ratio": -0.2623186409473419,
+      "logits/chosen": -2.7561872005462646,
+      "logits/rejected": -2.7932546138763428,
+      "logps/chosen": -0.43067559599876404,
+      "logps/rejected": -1.9674099683761597,
+      "loss": 0.325,
+      "nll_loss": 0.2987590432167053,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -0.043067559599876404,
+      "rewards/margins": 0.1536734402179718,
+      "rewards/rejected": -0.196740984916687,
+      "step": 8000
+    },
+    {
+      "epoch": 1.7334998852830958,
+      "grad_norm": 1.0028513669967651,
+      "learning_rate": 2.112652117751037e-05,
+      "log_odds_chosen": 2.5264878273010254,
+      "log_odds_ratio": -0.25732529163360596,
+      "logits/chosen": -2.8135437965393066,
+      "logits/rejected": -2.852220058441162,
+      "logps/chosen": -0.41469958424568176,
+      "logps/rejected": -1.949130654335022,
+      "loss": 0.3154,
+      "nll_loss": 0.2897038757801056,
+      "rewards/accuracies": 0.9607499837875366,
+      "rewards/chosen": -0.04146995395421982,
+      "rewards/margins": 0.1534431129693985,
+      "rewards/rejected": -0.1949130743741989,
+      "step": 8500
+    },
+    {
+      "epoch": 1.8354704667703368,
+      "grad_norm": 0.9701994061470032,
+      "learning_rate": 1.9426881501121764e-05,
+      "log_odds_chosen": 2.3967556953430176,
+      "log_odds_ratio": -0.27115362882614136,
+      "logits/chosen": -2.7224009037017822,
+      "logits/rejected": -2.7754287719726562,
+      "logps/chosen": -0.4164165258407593,
+      "logps/rejected": -1.8547587394714355,
+      "loss": 0.3216,
+      "nll_loss": 0.29452264308929443,
+      "rewards/accuracies": 0.9505000114440918,
+      "rewards/chosen": -0.041641656309366226,
+      "rewards/margins": 0.1438342034816742,
+      "rewards/rejected": -0.18547587096691132,
+      "step": 9000
+    },
+    {
+      "epoch": 1.9374410482575777,
+      "grad_norm": 0.7663633823394775,
+      "learning_rate": 1.7727241824733156e-05,
+      "log_odds_chosen": 2.5609018802642822,
+      "log_odds_ratio": -0.26221731305122375,
+      "logits/chosen": -2.8092148303985596,
+      "logits/rejected": -2.836301803588867,
+      "logps/chosen": -0.3934709429740906,
+      "logps/rejected": -1.921687364578247,
+      "loss": 0.3055,
+      "nll_loss": 0.27924445271492004,
+      "rewards/accuracies": 0.9557499885559082,
+      "rewards/chosen": -0.0393470898270607,
+      "rewards/margins": 0.1528216451406479,
+      "rewards/rejected": -0.192168727517128,
+      "step": 9500
+    },
+    {
+      "epoch": 2.039411629744819,
+      "grad_norm": 0.6147420406341553,
+      "learning_rate": 1.602760214834455e-05,
+      "log_odds_chosen": 3.2184579372406006,
+      "log_odds_ratio": -0.18695417046546936,
+      "logits/chosen": -3.0869991779327393,
+      "logits/rejected": -3.0871739387512207,
+      "logps/chosen": -0.3052729070186615,
+      "logps/rejected": -2.1187493801116943,
+      "loss": 0.2355,
+      "nll_loss": 0.2168271690607071,
+      "rewards/accuracies": 0.9782500267028809,
+      "rewards/chosen": -0.03052728995680809,
+      "rewards/margins": 0.18134763836860657,
+      "rewards/rejected": -0.21187493205070496,
+      "step": 10000
+    },
+    {
+      "epoch": 2.1413822112320595,
+      "grad_norm": 0.8968594074249268,
+      "learning_rate": 1.4327962471955947e-05,
+      "log_odds_chosen": 4.477025032043457,
+      "log_odds_ratio": -0.07086528092622757,
+      "logits/chosen": -3.4468417167663574,
+      "logits/rejected": -3.4328184127807617,
+      "logps/chosen": -0.1490449756383896,
+      "logps/rejected": -2.5894744396209717,
+      "loss": 0.1219,
+      "nll_loss": 0.11482993513345718,
+      "rewards/accuracies": 0.9940000176429749,
+      "rewards/chosen": -0.014904499053955078,
+      "rewards/margins": 0.24404291808605194,
+      "rewards/rejected": -0.2589474618434906,
+      "step": 10500
+    },
+    {
+      "epoch": 2.2433527927193007,
+      "grad_norm": 0.7543737292289734,
+      "learning_rate": 1.262832279556734e-05,
+      "log_odds_chosen": 4.517333030700684,
+      "log_odds_ratio": -0.07165472209453583,
+      "logits/chosen": -3.4554872512817383,
+      "logits/rejected": -3.4509389400482178,
+      "logps/chosen": -0.151213601231575,
+      "logps/rejected": -2.6054680347442627,
+      "loss": 0.1234,
+      "nll_loss": 0.11624418199062347,
+      "rewards/accuracies": 0.9909999966621399,
+      "rewards/chosen": -0.015121362172067165,
+      "rewards/margins": 0.24542541801929474,
+      "rewards/rejected": -0.2605467736721039,
+      "step": 11000
+    },
+    {
+      "epoch": 2.3453233742065414,
+      "grad_norm": 0.7870352864265442,
+      "learning_rate": 1.0928683119178734e-05,
+      "log_odds_chosen": 4.504143238067627,
+      "log_odds_ratio": -0.0680876150727272,
+      "logits/chosen": -3.3482730388641357,
+      "logits/rejected": -3.362037181854248,
+      "logps/chosen": -0.15102657675743103,
+      "logps/rejected": -2.60615873336792,
+      "loss": 0.1227,
+      "nll_loss": 0.11586029082536697,
+      "rewards/accuracies": 0.9937499761581421,
+      "rewards/chosen": -0.015102657489478588,
+      "rewards/margins": 0.24551323056221008,
+      "rewards/rejected": -0.26061588525772095,
+      "step": 11500
+    },
+    {
+      "epoch": 2.4472939556937825,
+      "grad_norm": 0.621370792388916,
+      "learning_rate": 9.22904344279013e-06,
+      "log_odds_chosen": 4.464700698852539,
+      "log_odds_ratio": -0.07176685333251953,
+      "logits/chosen": -3.3470752239227295,
+      "logits/rejected": -3.3573222160339355,
+      "logps/chosen": -0.14544738829135895,
+      "logps/rejected": -2.5615859031677246,
+      "loss": 0.12,
+      "nll_loss": 0.11279115825891495,
+      "rewards/accuracies": 0.9892500042915344,
+      "rewards/chosen": -0.014544738456606865,
+      "rewards/margins": 0.24161386489868164,
+      "rewards/rejected": -0.25615859031677246,
+      "step": 12000
+    },
+    {
+      "epoch": 2.549264537181023,
+      "grad_norm": 0.8108669519424438,
+      "learning_rate": 7.529403766401523e-06,
+      "log_odds_chosen": 4.566464424133301,
+      "log_odds_ratio": -0.06760641187429428,
+      "logits/chosen": -3.3751792907714844,
+      "logits/rejected": -3.371516227722168,
+      "logps/chosen": -0.14034530520439148,
+      "logps/rejected": -2.578918933868408,
+      "loss": 0.1152,
+      "nll_loss": 0.1084122508764267,
+      "rewards/accuracies": 0.9932500123977661,
+      "rewards/chosen": -0.014034531079232693,
+      "rewards/margins": 0.24385739862918854,
+      "rewards/rejected": -0.2578918933868408,
+      "step": 12500
+    },
+    {
+      "epoch": 2.6512351186682643,
+      "grad_norm": 1.0674421787261963,
+      "learning_rate": 5.829764090012918e-06,
+      "log_odds_chosen": 4.609077453613281,
+      "log_odds_ratio": -0.06549856811761856,
+      "logits/chosen": -3.320563316345215,
+      "logits/rejected": -3.3299055099487305,
+      "logps/chosen": -0.1383795589208603,
+      "logps/rejected": -2.625169515609741,
+      "loss": 0.1144,
+      "nll_loss": 0.10785890370607376,
+      "rewards/accuracies": 0.9932500123977661,
+      "rewards/chosen": -0.013837955892086029,
+      "rewards/margins": 0.2486789971590042,
+      "rewards/rejected": -0.26251694560050964,
+      "step": 13000
+    },
+    {
+      "epoch": 2.753205700155505,
+      "grad_norm": 0.9907452464103699,
+      "learning_rate": 4.1301244136243116e-06,
+      "log_odds_chosen": 4.6315083503723145,
+      "log_odds_ratio": -0.06764637678861618,
+      "logits/chosen": -3.35665225982666,
+      "logits/rejected": -3.365429639816284,
+      "logps/chosen": -0.14084672927856445,
+      "logps/rejected": -2.6286959648132324,
+      "loss": 0.1155,
+      "nll_loss": 0.10870947688817978,
+      "rewards/accuracies": 0.9917500019073486,
+      "rewards/chosen": -0.01408467348664999,
+      "rewards/margins": 0.24878491461277008,
+      "rewards/rejected": -0.26286956667900085,
+      "step": 13500
+    },
+    {
+      "epoch": 2.855176281642746,
+      "grad_norm": 1.0650596618652344,
+      "learning_rate": 2.4304847372357063e-06,
+      "log_odds_chosen": 4.683770656585693,
+      "log_odds_ratio": -0.06298153102397919,
+      "logits/chosen": -3.343515634536743,
+      "logits/rejected": -3.349973201751709,
+      "logps/chosen": -0.1364256739616394,
+      "logps/rejected": -2.6349427700042725,
+      "loss": 0.111,
+      "nll_loss": 0.10465656220912933,
+      "rewards/accuracies": 0.9919999837875366,
+      "rewards/chosen": -0.013642566278576851,
+      "rewards/margins": 0.24985171854496002,
+      "rewards/rejected": -0.26349425315856934,
+      "step": 14000
+    },
+    {
+      "epoch": 2.957146863129987,
+      "grad_norm": 0.7051740288734436,
+      "learning_rate": 7.308450608471004e-07,
+      "log_odds_chosen": 4.733154296875,
+      "log_odds_ratio": -0.06264213472604752,
+      "logits/chosen": -3.384558916091919,
+      "logits/rejected": -3.383835554122925,
+      "logps/chosen": -0.13168923556804657,
+      "logps/rejected": -2.653200149536133,
+      "loss": 0.1086,
+      "nll_loss": 0.10234662145376205,
+      "rewards/accuracies": 0.9934999942779541,
+      "rewards/chosen": -0.01316892635077238,
+      "rewards/margins": 0.2521510720252991,
+      "rewards/rejected": -0.2653200030326843,
+      "step": 14500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14709,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae5a922b425098874a0da3804301b0b15fd1825d4ff3710775d4c4c911386ff
+size 5432