Initial upload of M1_lr_5e-7_bs_1_ga_2_gpus_8_qwen2_dpo_apagasus_5k_id_0_1000_repeat_1.1_beta_0.1_ftx_1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9983948635634029,
+    "total_flos": 2.2772099803879834e+17,
+    "train_loss": 1.2078840717242079,
+    "train_runtime": 1561.3327,
+    "train_samples_per_second": 3.19,
+    "train_steps_per_second": 0.199
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen2-7B-Instruct_lr_5e-7_bs_1_ga_2_gpus_8_qwen2_dpo_apagasus_5k_id_0_1000_repeat_1.1_beta_0.1_ftx_1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2069150db4cd68019d21d5d718558b9c078754ffa30c3b04f71123a09a023ed6
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120e2ca1bd472a8379e7a3d6f86ab3464c14b78a1bad2d94e971c5631067d168
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62646001719a50ce69cbe2573cc63bdc375289808cebfaf51963dd86e29d6d13
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5762681a7b49d99cd808ffc31b4976726e6c50f7ebafcbed9562adc3c4d72e2a
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "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_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_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_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_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_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_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_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_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_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_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_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_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_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_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_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_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_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_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_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.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.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.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.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_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_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_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_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_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_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_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_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.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.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9983948635634029,
+    "total_flos": 2.2772099803879834e+17,
+    "train_loss": 1.2078840717242079,
+    "train_runtime": 1561.3327,
+    "train_samples_per_second": 3.19,
+    "train_steps_per_second": 0.199
+}

trainer_log.jsonl

@@ -0,0 +1,63 @@
+{"current_steps": 5, "total_steps": 311, "loss": 1.7067, "accuracy": 0.30000001192092896, "learning_rate": 2.5e-08, "epoch": 0.016051364365971106, "percentage": 1.61, "elapsed_time": "0:00:12", "remaining_time": "0:12:59"}
+{"current_steps": 10, "total_steps": 311, "loss": 1.6959, "accuracy": 0.5, "learning_rate": 5e-08, "epoch": 0.03210272873194221, "percentage": 3.22, "elapsed_time": "0:00:25", "remaining_time": "0:12:56"}
+{"current_steps": 15, "total_steps": 311, "loss": 1.7259, "accuracy": 0.4000000059604645, "learning_rate": 7.5e-08, "epoch": 0.048154093097913325, "percentage": 4.82, "elapsed_time": "0:00:38", "remaining_time": "0:12:31"}
+{"current_steps": 20, "total_steps": 311, "loss": 1.6493, "accuracy": 0.4000000059604645, "learning_rate": 1e-07, "epoch": 0.06420545746388442, "percentage": 6.43, "elapsed_time": "0:00:49", "remaining_time": "0:11:56"}
+{"current_steps": 25, "total_steps": 311, "loss": 1.6874, "accuracy": 0.4000000059604645, "learning_rate": 1.25e-07, "epoch": 0.08025682182985554, "percentage": 8.04, "elapsed_time": "0:01:00", "remaining_time": "0:11:37"}
+{"current_steps": 30, "total_steps": 311, "loss": 1.6706, "accuracy": 0.4000000059604645, "learning_rate": 1.5e-07, "epoch": 0.09630818619582665, "percentage": 9.65, "elapsed_time": "0:01:11", "remaining_time": "0:11:14"}
+{"current_steps": 35, "total_steps": 311, "loss": 1.6214, "accuracy": 0.800000011920929, "learning_rate": 1.75e-07, "epoch": 0.11235955056179775, "percentage": 11.25, "elapsed_time": "0:01:24", "remaining_time": "0:11:06"}
+{"current_steps": 40, "total_steps": 311, "loss": 1.6157, "accuracy": 0.699999988079071, "learning_rate": 2e-07, "epoch": 0.12841091492776885, "percentage": 12.86, "elapsed_time": "0:01:37", "remaining_time": "0:10:59"}
+{"current_steps": 45, "total_steps": 311, "loss": 1.5777, "accuracy": 0.800000011920929, "learning_rate": 2.25e-07, "epoch": 0.14446227929373998, "percentage": 14.47, "elapsed_time": "0:01:48", "remaining_time": "0:10:39"}
+{"current_steps": 50, "total_steps": 311, "loss": 1.5188, "accuracy": 0.8999999761581421, "learning_rate": 2.5e-07, "epoch": 0.16051364365971107, "percentage": 16.08, "elapsed_time": "0:01:59", "remaining_time": "0:10:22"}
+{"current_steps": 55, "total_steps": 311, "loss": 1.453, "accuracy": 0.8999999761581421, "learning_rate": 2.75e-07, "epoch": 0.17656500802568217, "percentage": 17.68, "elapsed_time": "0:02:09", "remaining_time": "0:10:03"}
+{"current_steps": 60, "total_steps": 311, "loss": 1.4078, "accuracy": 1.0, "learning_rate": 3e-07, "epoch": 0.1926163723916533, "percentage": 19.29, "elapsed_time": "0:02:20", "remaining_time": "0:09:47"}
+{"current_steps": 65, "total_steps": 311, "loss": 1.4782, "accuracy": 1.0, "learning_rate": 3.25e-07, "epoch": 0.2086677367576244, "percentage": 20.9, "elapsed_time": "0:02:32", "remaining_time": "0:09:36"}
+{"current_steps": 70, "total_steps": 311, "loss": 1.3096, "accuracy": 1.0, "learning_rate": 3.5e-07, "epoch": 0.2247191011235955, "percentage": 22.51, "elapsed_time": "0:02:44", "remaining_time": "0:09:24"}
+{"current_steps": 75, "total_steps": 311, "loss": 1.2167, "accuracy": 1.0, "learning_rate": 3.75e-07, "epoch": 0.24077046548956663, "percentage": 24.12, "elapsed_time": "0:02:55", "remaining_time": "0:09:12"}
+{"current_steps": 80, "total_steps": 311, "loss": 1.2813, "accuracy": 1.0, "learning_rate": 4e-07, "epoch": 0.2568218298555377, "percentage": 25.72, "elapsed_time": "0:03:06", "remaining_time": "0:08:59"}
+{"current_steps": 85, "total_steps": 311, "loss": 1.2639, "accuracy": 1.0, "learning_rate": 4.2499999999999995e-07, "epoch": 0.27287319422150885, "percentage": 27.33, "elapsed_time": "0:03:20", "remaining_time": "0:08:52"}
+{"current_steps": 90, "total_steps": 311, "loss": 1.2788, "accuracy": 1.0, "learning_rate": 4.5e-07, "epoch": 0.28892455858747995, "percentage": 28.94, "elapsed_time": "0:03:31", "remaining_time": "0:08:39"}
+{"current_steps": 95, "total_steps": 311, "loss": 1.1874, "accuracy": 1.0, "learning_rate": 4.7499999999999995e-07, "epoch": 0.30497592295345105, "percentage": 30.55, "elapsed_time": "0:03:43", "remaining_time": "0:08:27"}
+{"current_steps": 100, "total_steps": 311, "loss": 1.176, "accuracy": 1.0, "learning_rate": 5e-07, "epoch": 0.32102728731942215, "percentage": 32.15, "elapsed_time": "0:03:54", "remaining_time": "0:08:15"}
+{"current_steps": 105, "total_steps": 311, "loss": 1.1563, "accuracy": 1.0, "learning_rate": 4.99307556613492e-07, "epoch": 0.33707865168539325, "percentage": 33.76, "elapsed_time": "0:08:30", "remaining_time": "0:16:41"}
+{"current_steps": 110, "total_steps": 311, "loss": 1.1971, "accuracy": 1.0, "learning_rate": 4.972340622767164e-07, "epoch": 0.35313001605136435, "percentage": 35.37, "elapsed_time": "0:08:42", "remaining_time": "0:15:54"}
+{"current_steps": 115, "total_steps": 311, "loss": 1.069, "accuracy": 1.0, "learning_rate": 4.937910032091967e-07, "epoch": 0.36918138041733545, "percentage": 36.98, "elapsed_time": "0:08:53", "remaining_time": "0:15:09"}
+{"current_steps": 120, "total_steps": 311, "loss": 1.0784, "accuracy": 1.0, "learning_rate": 4.889974523987784e-07, "epoch": 0.3852327447833066, "percentage": 38.59, "elapsed_time": "0:09:04", "remaining_time": "0:14:26"}
+{"current_steps": 125, "total_steps": 311, "loss": 1.1384, "accuracy": 1.0, "learning_rate": 4.828799639459138e-07, "epoch": 0.4012841091492777, "percentage": 40.19, "elapsed_time": "0:09:15", "remaining_time": "0:13:47"}
+{"current_steps": 130, "total_steps": 311, "loss": 1.1446, "accuracy": 1.0, "learning_rate": 4.754724259659727e-07, "epoch": 0.4173354735152488, "percentage": 41.8, "elapsed_time": "0:09:27", "remaining_time": "0:13:10"}
+{"current_steps": 135, "total_steps": 311, "loss": 1.1268, "accuracy": 1.0, "learning_rate": 4.6681587286443143e-07, "epoch": 0.4333868378812199, "percentage": 43.41, "elapsed_time": "0:09:40", "remaining_time": "0:12:36"}
+{"current_steps": 140, "total_steps": 311, "loss": 1.1836, "accuracy": 1.0, "learning_rate": 4.569582580248508e-07, "epoch": 0.449438202247191, "percentage": 45.02, "elapsed_time": "0:09:52", "remaining_time": "0:12:03"}
+{"current_steps": 145, "total_steps": 311, "loss": 1.0783, "accuracy": 0.8999999761581421, "learning_rate": 4.4595418816885e-07, "epoch": 0.4654895666131621, "percentage": 46.62, "elapsed_time": "0:10:04", "remaining_time": "0:11:31"}
+{"current_steps": 150, "total_steps": 311, "loss": 1.2031, "accuracy": 1.0, "learning_rate": 4.338646208596008e-07, "epoch": 0.48154093097913325, "percentage": 48.23, "elapsed_time": "0:10:15", "remaining_time": "0:11:01"}
+{"current_steps": 155, "total_steps": 311, "loss": 1.0329, "accuracy": 1.0, "learning_rate": 4.207565268245355e-07, "epoch": 0.49759229534510435, "percentage": 49.84, "elapsed_time": "0:10:27", "remaining_time": "0:10:31"}
+{"current_steps": 160, "total_steps": 311, "loss": 1.0657, "accuracy": 1.0, "learning_rate": 4.0670251896784847e-07, "epoch": 0.5136436597110754, "percentage": 51.45, "elapsed_time": "0:10:41", "remaining_time": "0:10:04"}
+{"current_steps": 165, "total_steps": 311, "loss": 1.1023, "accuracy": 0.8999999761581421, "learning_rate": 3.917804501278941e-07, "epoch": 0.5296950240770465, "percentage": 53.05, "elapsed_time": "0:10:53", "remaining_time": "0:09:37"}
+{"current_steps": 170, "total_steps": 311, "loss": 1.0674, "accuracy": 1.0, "learning_rate": 3.760729818077223e-07, "epoch": 0.5457463884430177, "percentage": 54.66, "elapsed_time": "0:11:05", "remaining_time": "0:09:12"}
+{"current_steps": 175, "total_steps": 311, "loss": 0.9874, "accuracy": 1.0, "learning_rate": 3.596671262677898e-07, "epoch": 0.5617977528089888, "percentage": 56.27, "elapsed_time": "0:11:17", "remaining_time": "0:08:46"}
+{"current_steps": 180, "total_steps": 311, "loss": 1.2047, "accuracy": 1.0, "learning_rate": 3.426537645174456e-07, "epoch": 0.5778491171749599, "percentage": 57.88, "elapsed_time": "0:11:28", "remaining_time": "0:08:21"}
+{"current_steps": 185, "total_steps": 311, "loss": 1.0531, "accuracy": 1.0, "learning_rate": 3.2512714287530003e-07, "epoch": 0.593900481540931, "percentage": 59.49, "elapsed_time": "0:11:40", "remaining_time": "0:07:57"}
+{"current_steps": 190, "total_steps": 311, "loss": 1.0844, "accuracy": 1.0, "learning_rate": 3.071843508873045e-07, "epoch": 0.6099518459069021, "percentage": 61.09, "elapsed_time": "0:11:53", "remaining_time": "0:07:34"}
+{"current_steps": 195, "total_steps": 311, "loss": 1.087, "accuracy": 1.0, "learning_rate": 2.8892478349463983e-07, "epoch": 0.6260032102728732, "percentage": 62.7, "elapsed_time": "0:12:05", "remaining_time": "0:07:11"}
+{"current_steps": 200, "total_steps": 311, "loss": 1.0463, "accuracy": 1.0, "learning_rate": 2.704495904307581e-07, "epoch": 0.6420545746388443, "percentage": 64.31, "elapsed_time": "0:12:17", "remaining_time": "0:06:49"}
+{"current_steps": 205, "total_steps": 311, "loss": 1.1441, "accuracy": 1.0, "learning_rate": 2.5186111589767186e-07, "epoch": 0.6581059390048154, "percentage": 65.92, "elapsed_time": "0:17:05", "remaining_time": "0:08:50"}
+{"current_steps": 210, "total_steps": 311, "loss": 1.046, "accuracy": 1.0, "learning_rate": 2.3326233162542652e-07, "epoch": 0.6741573033707865, "percentage": 67.52, "elapsed_time": "0:17:16", "remaining_time": "0:08:18"}
+{"current_steps": 215, "total_steps": 311, "loss": 1.093, "accuracy": 1.0, "learning_rate": 2.1475626645535367e-07, "epoch": 0.6902086677367576, "percentage": 69.13, "elapsed_time": "0:17:28", "remaining_time": "0:07:48"}
+{"current_steps": 220, "total_steps": 311, "loss": 1.0305, "accuracy": 1.0, "learning_rate": 1.9644543560695136e-07, "epoch": 0.7062600321027287, "percentage": 70.74, "elapsed_time": "0:17:40", "remaining_time": "0:07:18"}
+{"current_steps": 225, "total_steps": 311, "loss": 1.0172, "accuracy": 1.0, "learning_rate": 1.784312727899994e-07, "epoch": 0.7223113964686998, "percentage": 72.35, "elapsed_time": "0:17:51", "remaining_time": "0:06:49"}
+{"current_steps": 230, "total_steps": 311, "loss": 1.0822, "accuracy": 1.0, "learning_rate": 1.6081356830774623e-07, "epoch": 0.7383627608346709, "percentage": 73.95, "elapsed_time": "0:18:03", "remaining_time": "0:06:21"}
+{"current_steps": 235, "total_steps": 311, "loss": 0.9993, "accuracy": 0.8999999761581421, "learning_rate": 1.4368991626382548e-07, "epoch": 0.7544141252006421, "percentage": 75.56, "elapsed_time": "0:18:15", "remaining_time": "0:05:54"}
+{"current_steps": 240, "total_steps": 311, "loss": 1.1002, "accuracy": 1.0, "learning_rate": 1.2715517393512238e-07, "epoch": 0.7704654895666132, "percentage": 77.17, "elapsed_time": "0:18:27", "remaining_time": "0:05:27"}
+{"current_steps": 245, "total_steps": 311, "loss": 0.983, "accuracy": 1.0, "learning_rate": 1.1130093630542198e-07, "epoch": 0.7865168539325843, "percentage": 78.78, "elapsed_time": "0:18:39", "remaining_time": "0:05:01"}
+{"current_steps": 250, "total_steps": 311, "loss": 1.0852, "accuracy": 1.0, "learning_rate": 9.621502867068285e-08, "epoch": 0.8025682182985554, "percentage": 80.39, "elapsed_time": "0:18:51", "remaining_time": "0:04:36"}
+{"current_steps": 255, "total_steps": 311, "loss": 1.0466, "accuracy": 1.0, "learning_rate": 8.198102012667407e-08, "epoch": 0.8186195826645265, "percentage": 81.99, "elapsed_time": "0:19:03", "remaining_time": "0:04:11"}
+{"current_steps": 260, "total_steps": 311, "loss": 1.1013, "accuracy": 1.0, "learning_rate": 6.86777606340341e-08, "epoch": 0.8346709470304976, "percentage": 83.6, "elapsed_time": "0:19:15", "remaining_time": "0:03:46"}
+{"current_steps": 265, "total_steps": 311, "loss": 0.9904, "accuracy": 1.0, "learning_rate": 5.637894422520026e-08, "epoch": 0.8507223113964687, "percentage": 85.21, "elapsed_time": "0:19:26", "remaining_time": "0:03:22"}
+{"current_steps": 270, "total_steps": 311, "loss": 1.0834, "accuracy": 1.0, "learning_rate": 4.515270077284594e-08, "epoch": 0.8667736757624398, "percentage": 86.82, "elapsed_time": "0:19:37", "remaining_time": "0:02:58"}
+{"current_steps": 275, "total_steps": 311, "loss": 1.0789, "accuracy": 1.0, "learning_rate": 3.506121858124253e-08, "epoch": 0.8828250401284109, "percentage": 88.42, "elapsed_time": "0:19:48", "remaining_time": "0:02:35"}
+{"current_steps": 280, "total_steps": 311, "loss": 1.0365, "accuracy": 1.0, "learning_rate": 2.6160399891218986e-08, "epoch": 0.898876404494382, "percentage": 90.03, "elapsed_time": "0:20:00", "remaining_time": "0:02:12"}
+{"current_steps": 285, "total_steps": 311, "loss": 1.0772, "accuracy": 1.0, "learning_rate": 1.8499551207066726e-08, "epoch": 0.9149277688603531, "percentage": 91.64, "elapsed_time": "0:20:12", "remaining_time": "0:01:50"}
+{"current_steps": 290, "total_steps": 311, "loss": 1.0249, "accuracy": 1.0, "learning_rate": 1.2121110160836696e-08, "epoch": 0.9309791332263242, "percentage": 93.25, "elapsed_time": "0:20:24", "remaining_time": "0:01:28"}
+{"current_steps": 295, "total_steps": 311, "loss": 0.9998, "accuracy": 0.8999999761581421, "learning_rate": 7.060410427078472e-09, "epoch": 0.9470304975922953, "percentage": 94.86, "elapsed_time": "0:20:36", "remaining_time": "0:01:07"}
+{"current_steps": 300, "total_steps": 311, "loss": 1.0632, "accuracy": 1.0, "learning_rate": 3.345485990286029e-09, "epoch": 0.9630818619582665, "percentage": 96.46, "elapsed_time": "0:20:47", "remaining_time": "0:00:45"}
+{"current_steps": 305, "total_steps": 311, "loss": 1.0695, "accuracy": 1.0, "learning_rate": 9.969158493204066e-10, "epoch": 0.9791332263242376, "percentage": 98.07, "elapsed_time": "0:25:30", "remaining_time": "0:00:30"}
+{"current_steps": 310, "total_steps": 311, "loss": 1.0752, "accuracy": 1.0, "learning_rate": 2.7710019076532255e-11, "epoch": 0.9951845906902087, "percentage": 99.68, "elapsed_time": "0:25:43", "remaining_time": "0:00:04"}
+{"current_steps": 311, "total_steps": 311, "epoch": 0.9983948635634029, "percentage": 100.0, "elapsed_time": "0:25:45", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,960 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9983948635634029,
+  "eval_steps": 500,
+  "global_step": 311,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016051364365971106,
+      "grad_norm": 121.10428619384766,
+      "learning_rate": 2.5e-08,
+      "logits/chosen": -1.2638301849365234,
+      "logits/rejected": -1.665239930152893,
+      "logps/chosen": -546.0797119140625,
+      "logps/rejected": -221.3369598388672,
+      "loss": 1.7067,
+      "rewards/accuracies": 0.30000001192092896,
+      "rewards/chosen": 0.010043257847428322,
+      "rewards/margins": 0.0191060658544302,
+      "rewards/rejected": -0.009062806144356728,
+      "step": 5
+    },
+    {
+      "epoch": 0.03210272873194221,
+      "grad_norm": 145.65426635742188,
+      "learning_rate": 5e-08,
+      "logits/chosen": -1.3794753551483154,
+      "logits/rejected": -1.45535147190094,
+      "logps/chosen": -480.9561462402344,
+      "logps/rejected": -280.5528259277344,
+      "loss": 1.6959,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.02216443046927452,
+      "rewards/margins": 0.0013258367544040084,
+      "rewards/rejected": 0.020838594064116478,
+      "step": 10
+    },
+    {
+      "epoch": 0.048154093097913325,
+      "grad_norm": 137.42625427246094,
+      "learning_rate": 7.5e-08,
+      "logits/chosen": -0.8316283226013184,
+      "logits/rejected": -1.2710667848587036,
+      "logps/chosen": -655.1801147460938,
+      "logps/rejected": -274.896240234375,
+      "loss": 1.7259,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.04486668482422829,
+      "rewards/margins": -0.04116218164563179,
+      "rewards/rejected": -0.00370450085029006,
+      "step": 15
+    },
+    {
+      "epoch": 0.06420545746388442,
+      "grad_norm": 123.21935272216797,
+      "learning_rate": 1e-07,
+      "logits/chosen": -1.4025318622589111,
+      "logits/rejected": -1.769675850868225,
+      "logps/chosen": -484.6539611816406,
+      "logps/rejected": -182.8202667236328,
+      "loss": 1.6493,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.011784935370087624,
+      "rewards/margins": 0.01474493183195591,
+      "rewards/rejected": -0.002959995297715068,
+      "step": 20
+    },
+    {
+      "epoch": 0.08025682182985554,
+      "grad_norm": 115.37054443359375,
+      "learning_rate": 1.25e-07,
+      "logits/chosen": -1.213343620300293,
+      "logits/rejected": -1.4221173524856567,
+      "logps/chosen": -401.516357421875,
+      "logps/rejected": -167.65040588378906,
+      "loss": 1.6874,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.024040672928094864,
+      "rewards/margins": -0.017848897725343704,
+      "rewards/rejected": -0.006191774271428585,
+      "step": 25
+    },
+    {
+      "epoch": 0.09630818619582665,
+      "grad_norm": 104.660400390625,
+      "learning_rate": 1.5e-07,
+      "logits/chosen": -1.0414670705795288,
+      "logits/rejected": -1.2284868955612183,
+      "logps/chosen": -231.41452026367188,
+      "logps/rejected": -204.5773162841797,
+      "loss": 1.6706,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": -0.001331291743554175,
+      "rewards/margins": -0.002074225340038538,
+      "rewards/rejected": 0.0007429312099702656,
+      "step": 30
+    },
+    {
+      "epoch": 0.11235955056179775,
+      "grad_norm": 114.4107894897461,
+      "learning_rate": 1.75e-07,
+      "logits/chosen": -1.4061366319656372,
+      "logits/rejected": -1.4403215646743774,
+      "logps/chosen": -654.1046752929688,
+      "logps/rejected": -296.5850524902344,
+      "loss": 1.6214,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.020063400268554688,
+      "rewards/margins": 0.021649112924933434,
+      "rewards/rejected": -0.04171251505613327,
+      "step": 35
+    },
+    {
+      "epoch": 0.12841091492776885,
+      "grad_norm": 109.54496002197266,
+      "learning_rate": 2e-07,
+      "logits/chosen": -1.1106269359588623,
+      "logits/rejected": -1.0706493854522705,
+      "logps/chosen": -390.37689208984375,
+      "logps/rejected": -305.8371887207031,
+      "loss": 1.6157,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.003482551546767354,
+      "rewards/margins": 0.06457197666168213,
+      "rewards/rejected": -0.06805451959371567,
+      "step": 40
+    },
+    {
+      "epoch": 0.14446227929373998,
+      "grad_norm": 89.41961669921875,
+      "learning_rate": 2.25e-07,
+      "logits/chosen": -1.5494025945663452,
+      "logits/rejected": -1.4573886394500732,
+      "logps/chosen": -386.77001953125,
+      "logps/rejected": -287.19512939453125,
+      "loss": 1.5777,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.007915372028946877,
+      "rewards/margins": 0.15702402591705322,
+      "rewards/rejected": -0.16493940353393555,
+      "step": 45
+    },
+    {
+      "epoch": 0.16051364365971107,
+      "grad_norm": 95.20951080322266,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": -1.142269492149353,
+      "logits/rejected": -1.4179078340530396,
+      "logps/chosen": -457.00225830078125,
+      "logps/rejected": -332.7820739746094,
+      "loss": 1.5188,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.07464755326509476,
+      "rewards/margins": 0.3128935396671295,
+      "rewards/rejected": -0.23824600875377655,
+      "step": 50
+    },
+    {
+      "epoch": 0.17656500802568217,
+      "grad_norm": 88.16427612304688,
+      "learning_rate": 2.75e-07,
+      "logits/chosen": -1.3489106893539429,
+      "logits/rejected": -1.466799020767212,
+      "logps/chosen": -344.6269836425781,
+      "logps/rejected": -176.01918029785156,
+      "loss": 1.453,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.033908139914274216,
+      "rewards/margins": 0.24989934265613556,
+      "rewards/rejected": -0.21599121391773224,
+      "step": 55
+    },
+    {
+      "epoch": 0.1926163723916533,
+      "grad_norm": 77.65755462646484,
+      "learning_rate": 3e-07,
+      "logits/chosen": -0.9685641527175903,
+      "logits/rejected": -1.1202367544174194,
+      "logps/chosen": -398.91015625,
+      "logps/rejected": -301.5136413574219,
+      "loss": 1.4078,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.10223056375980377,
+      "rewards/margins": 0.5195897817611694,
+      "rewards/rejected": -0.41735926270484924,
+      "step": 60
+    },
+    {
+      "epoch": 0.2086677367576244,
+      "grad_norm": 72.0479507446289,
+      "learning_rate": 3.25e-07,
+      "logits/chosen": -1.190237283706665,
+      "logits/rejected": -1.4059275388717651,
+      "logps/chosen": -533.5418090820312,
+      "logps/rejected": -236.84814453125,
+      "loss": 1.4782,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.22575466334819794,
+      "rewards/margins": 0.7698931694030762,
+      "rewards/rejected": -0.5441386103630066,
+      "step": 65
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 60.58078384399414,
+      "learning_rate": 3.5e-07,
+      "logits/chosen": -1.9404817819595337,
+      "logits/rejected": -1.863373041152954,
+      "logps/chosen": -516.4696044921875,
+      "logps/rejected": -345.7939758300781,
+      "loss": 1.3096,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.18703202903270721,
+      "rewards/margins": 1.115755558013916,
+      "rewards/rejected": -0.9287236332893372,
+      "step": 70
+    },
+    {
+      "epoch": 0.24077046548956663,
+      "grad_norm": 55.802974700927734,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": -1.5013229846954346,
+      "logits/rejected": -1.702341079711914,
+      "logps/chosen": -484.9268493652344,
+      "logps/rejected": -278.0371398925781,
+      "loss": 1.2167,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.13444054126739502,
+      "rewards/margins": 1.1699440479278564,
+      "rewards/rejected": -1.035503625869751,
+      "step": 75
+    },
+    {
+      "epoch": 0.2568218298555377,
+      "grad_norm": 45.57625961303711,
+      "learning_rate": 4e-07,
+      "logits/chosen": -1.6308963298797607,
+      "logits/rejected": -1.5779510736465454,
+      "logps/chosen": -291.3985900878906,
+      "logps/rejected": -270.9822082519531,
+      "loss": 1.2813,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.2150442898273468,
+      "rewards/margins": 1.1736772060394287,
+      "rewards/rejected": -0.9586329460144043,
+      "step": 80
+    },
+    {
+      "epoch": 0.27287319422150885,
+      "grad_norm": 46.700130462646484,
+      "learning_rate": 4.2499999999999995e-07,
+      "logits/chosen": -1.02730393409729,
+      "logits/rejected": -1.5920169353485107,
+      "logps/chosen": -311.2256774902344,
+      "logps/rejected": -146.46307373046875,
+      "loss": 1.2639,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.32850438356399536,
+      "rewards/margins": 0.914591908454895,
+      "rewards/rejected": -0.5860875248908997,
+      "step": 85
+    },
+    {
+      "epoch": 0.28892455858747995,
+      "grad_norm": 43.620941162109375,
+      "learning_rate": 4.5e-07,
+      "logits/chosen": -1.3487294912338257,
+      "logits/rejected": -1.7090362310409546,
+      "logps/chosen": -540.0745849609375,
+      "logps/rejected": -243.54287719726562,
+      "loss": 1.2788,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.15325233340263367,
+      "rewards/margins": 1.6475521326065063,
+      "rewards/rejected": -1.4942998886108398,
+      "step": 90
+    },
+    {
+      "epoch": 0.30497592295345105,
+      "grad_norm": 38.739105224609375,
+      "learning_rate": 4.7499999999999995e-07,
+      "logits/chosen": -2.071296215057373,
+      "logits/rejected": -2.0040106773376465,
+      "logps/chosen": -402.5144958496094,
+      "logps/rejected": -291.44757080078125,
+      "loss": 1.1874,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.31765127182006836,
+      "rewards/margins": 2.010577440261841,
+      "rewards/rejected": -1.6929261684417725,
+      "step": 95
+    },
+    {
+      "epoch": 0.32102728731942215,
+      "grad_norm": 34.593257904052734,
+      "learning_rate": 5e-07,
+      "logits/chosen": -1.8184257745742798,
+      "logits/rejected": -1.8116085529327393,
+      "logps/chosen": -411.0416564941406,
+      "logps/rejected": -215.6116943359375,
+      "loss": 1.176,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.17730842530727386,
+      "rewards/margins": 1.6420629024505615,
+      "rewards/rejected": -1.464754343032837,
+      "step": 100
+    },
+    {
+      "epoch": 0.33707865168539325,
+      "grad_norm": 39.810089111328125,
+      "learning_rate": 4.99307556613492e-07,
+      "logits/chosen": -1.4572077989578247,
+      "logits/rejected": -1.8333911895751953,
+      "logps/chosen": -613.5606079101562,
+      "logps/rejected": -280.7749328613281,
+      "loss": 1.1563,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.21885092556476593,
+      "rewards/margins": 2.2480263710021973,
+      "rewards/rejected": -2.029175281524658,
+      "step": 105
+    },
+    {
+      "epoch": 0.35313001605136435,
+      "grad_norm": 29.89188575744629,
+      "learning_rate": 4.972340622767164e-07,
+      "logits/chosen": -1.4872273206710815,
+      "logits/rejected": -1.661569356918335,
+      "logps/chosen": -434.12689208984375,
+      "logps/rejected": -226.6045379638672,
+      "loss": 1.1971,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.037406109273433685,
+      "rewards/margins": 2.0358262062072754,
+      "rewards/rejected": -1.9984201192855835,
+      "step": 110
+    },
+    {
+      "epoch": 0.36918138041733545,
+      "grad_norm": 34.67169952392578,
+      "learning_rate": 4.937910032091967e-07,
+      "logits/chosen": -1.5089974403381348,
+      "logits/rejected": -1.4937382936477661,
+      "logps/chosen": -326.23577880859375,
+      "logps/rejected": -242.26766967773438,
+      "loss": 1.069,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.1510745882987976,
+      "rewards/margins": 2.4666709899902344,
+      "rewards/rejected": -2.315596580505371,
+      "step": 115
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 26.853172302246094,
+      "learning_rate": 4.889974523987784e-07,
+      "logits/chosen": -1.709498405456543,
+      "logits/rejected": -1.7816112041473389,
+      "logps/chosen": -299.94091796875,
+      "logps/rejected": -224.59716796875,
+      "loss": 1.0784,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.08231879025697708,
+      "rewards/margins": 1.5635088682174683,
+      "rewards/rejected": -1.4811900854110718,
+      "step": 120
+    },
+    {
+      "epoch": 0.4012841091492777,
+      "grad_norm": 25.12617301940918,
+      "learning_rate": 4.828799639459138e-07,
+      "logits/chosen": -2.142733573913574,
+      "logits/rejected": -1.8604745864868164,
+      "logps/chosen": -554.5831298828125,
+      "logps/rejected": -431.9894104003906,
+      "loss": 1.1384,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.324582576751709,
+      "rewards/margins": 3.6467995643615723,
+      "rewards/rejected": -3.322216749191284,
+      "step": 125
+    },
+    {
+      "epoch": 0.4173354735152488,
+      "grad_norm": 19.279260635375977,
+      "learning_rate": 4.754724259659727e-07,
+      "logits/chosen": -1.729953408241272,
+      "logits/rejected": -2.0016226768493652,
+      "logps/chosen": -337.40460205078125,
+      "logps/rejected": -218.6181182861328,
+      "loss": 1.1446,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.23123934864997864,
+      "rewards/margins": 2.4159419536590576,
+      "rewards/rejected": -2.1847023963928223,
+      "step": 130
+    },
+    {
+      "epoch": 0.4333868378812199,
+      "grad_norm": 39.15530776977539,
+      "learning_rate": 4.6681587286443143e-07,
+      "logits/chosen": -1.7074105739593506,
+      "logits/rejected": -2.001408815383911,
+      "logps/chosen": -609.3516235351562,
+      "logps/rejected": -355.2177734375,
+      "loss": 1.1268,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.2101774662733078,
+      "rewards/margins": 3.605560302734375,
+      "rewards/rejected": -3.3953826427459717,
+      "step": 135
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 28.309494018554688,
+      "learning_rate": 4.569582580248508e-07,
+      "logits/chosen": -1.3231592178344727,
+      "logits/rejected": -1.3130943775177002,
+      "logps/chosen": -456.9552307128906,
+      "logps/rejected": -249.678466796875,
+      "loss": 1.1836,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.09645295143127441,
+      "rewards/margins": 2.3201193809509277,
+      "rewards/rejected": -2.2236666679382324,
+      "step": 140
+    },
+    {
+      "epoch": 0.4654895666131621,
+      "grad_norm": 25.581401824951172,
+      "learning_rate": 4.4595418816885e-07,
+      "logits/chosen": -2.18888783454895,
+      "logits/rejected": -1.896630048751831,
+      "logps/chosen": -391.4627380371094,
+      "logps/rejected": -396.46240234375,
+      "loss": 1.0783,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.3204360604286194,
+      "rewards/margins": 3.3659069538116455,
+      "rewards/rejected": -3.045470714569092,
+      "step": 145
+    },
+    {
+      "epoch": 0.48154093097913325,
+      "grad_norm": 27.107683181762695,
+      "learning_rate": 4.338646208596008e-07,
+      "logits/chosen": -1.3190141916275024,
+      "logits/rejected": -1.4809017181396484,
+      "logps/chosen": -668.1514892578125,
+      "logps/rejected": -365.1762390136719,
+      "loss": 1.2031,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.00630459189414978,
+      "rewards/margins": 4.1467790603637695,
+      "rewards/rejected": -4.140474796295166,
+      "step": 150
+    },
+    {
+      "epoch": 0.49759229534510435,
+      "grad_norm": 23.90721893310547,
+      "learning_rate": 4.207565268245355e-07,
+      "logits/chosen": -1.243398904800415,
+      "logits/rejected": -1.5890659093856812,
+      "logps/chosen": -605.8566284179688,
+      "logps/rejected": -339.843994140625,
+      "loss": 1.0329,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.4351004958152771,
+      "rewards/margins": 4.156341552734375,
+      "rewards/rejected": -3.721240997314453,
+      "step": 155
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 15.980473518371582,
+      "learning_rate": 4.0670251896784847e-07,
+      "logits/chosen": -1.6174713373184204,
+      "logits/rejected": -2.031649112701416,
+      "logps/chosen": -572.9243774414062,
+      "logps/rejected": -294.9161376953125,
+      "loss": 1.0657,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.5264326333999634,
+      "rewards/margins": 3.414010524749756,
+      "rewards/rejected": -2.887577533721924,
+      "step": 160
+    },
+    {
+      "epoch": 0.5296950240770465,
+      "grad_norm": 16.01748275756836,
+      "learning_rate": 3.917804501278941e-07,
+      "logits/chosen": -1.8946282863616943,
+      "logits/rejected": -2.036999225616455,
+      "logps/chosen": -455.58428955078125,
+      "logps/rejected": -225.6637725830078,
+      "loss": 1.1023,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.3108845353126526,
+      "rewards/margins": 2.991553544998169,
+      "rewards/rejected": -2.680669069290161,
+      "step": 165
+    },
+    {
+      "epoch": 0.5457463884430177,
+      "grad_norm": 18.181249618530273,
+      "learning_rate": 3.760729818077223e-07,
+      "logits/chosen": -1.3452972173690796,
+      "logits/rejected": -1.663169264793396,
+      "logps/chosen": -400.55657958984375,
+      "logps/rejected": -260.5176086425781,
+      "loss": 1.0674,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.9225478172302246,
+      "rewards/margins": 3.818953037261963,
+      "rewards/rejected": -2.8964052200317383,
+      "step": 170
+    },
+    {
+      "epoch": 0.5617977528089888,
+      "grad_norm": 12.927690505981445,
+      "learning_rate": 3.596671262677898e-07,
+      "logits/chosen": -0.9975664019584656,
+      "logits/rejected": -1.590592384338379,
+      "logps/chosen": -484.78472900390625,
+      "logps/rejected": -326.25018310546875,
+      "loss": 0.9874,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.8374244570732117,
+      "rewards/margins": 4.229715824127197,
+      "rewards/rejected": -3.392291307449341,
+      "step": 175
+    },
+    {
+      "epoch": 0.5778491171749599,
+      "grad_norm": 22.454750061035156,
+      "learning_rate": 3.426537645174456e-07,
+      "logits/chosen": -1.1456716060638428,
+      "logits/rejected": -0.9254422187805176,
+      "logps/chosen": -229.30184936523438,
+      "logps/rejected": -184.46151733398438,
+      "loss": 1.2047,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.03938926011323929,
+      "rewards/margins": 2.173858880996704,
+      "rewards/rejected": -2.2132482528686523,
+      "step": 180
+    },
+    {
+      "epoch": 0.593900481540931,
+      "grad_norm": 19.639509201049805,
+      "learning_rate": 3.2512714287530003e-07,
+      "logits/chosen": -1.6827218532562256,
+      "logits/rejected": -1.6239674091339111,
+      "logps/chosen": -248.2288818359375,
+      "logps/rejected": -174.70457458496094,
+      "loss": 1.0531,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.023051679134368896,
+      "rewards/margins": 2.488781690597534,
+      "rewards/rejected": -2.5118331909179688,
+      "step": 185
+    },
+    {
+      "epoch": 0.6099518459069021,
+      "grad_norm": 28.825136184692383,
+      "learning_rate": 3.071843508873045e-07,
+      "logits/chosen": -1.655289649963379,
+      "logits/rejected": -1.2866331338882446,
+      "logps/chosen": -399.61016845703125,
+      "logps/rejected": -372.4976806640625,
+      "loss": 1.0844,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.24592149257659912,
+      "rewards/margins": 4.032209873199463,
+      "rewards/rejected": -3.7862884998321533,
+      "step": 190
+    },
+    {
+      "epoch": 0.6260032102728732,
+      "grad_norm": 14.884502410888672,
+      "learning_rate": 2.8892478349463983e-07,
+      "logits/chosen": -1.6147607564926147,
+      "logits/rejected": -1.9210180044174194,
+      "logps/chosen": -517.3702392578125,
+      "logps/rejected": -201.2556915283203,
+      "loss": 1.087,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.48443666100502014,
+      "rewards/margins": 3.167422294616699,
+      "rewards/rejected": -2.682985782623291,
+      "step": 195
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 20.6270694732666,
+      "learning_rate": 2.704495904307581e-07,
+      "logits/chosen": -1.466150164604187,
+      "logits/rejected": -1.8435227870941162,
+      "logps/chosen": -447.94708251953125,
+      "logps/rejected": -320.72796630859375,
+      "loss": 1.0463,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.4680330157279968,
+      "rewards/margins": 3.9673094749450684,
+      "rewards/rejected": -3.499276638031006,
+      "step": 200
+    },
+    {
+      "epoch": 0.6581059390048154,
+      "grad_norm": 20.02724266052246,
+      "learning_rate": 2.5186111589767186e-07,
+      "logits/chosen": -0.9430475234985352,
+      "logits/rejected": -1.5955369472503662,
+      "logps/chosen": -512.3245849609375,
+      "logps/rejected": -293.04388427734375,
+      "loss": 1.1441,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.22035065293312073,
+      "rewards/margins": 3.5233726501464844,
+      "rewards/rejected": -3.3030216693878174,
+      "step": 205
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 19.69023895263672,
+      "learning_rate": 2.3326233162542652e-07,
+      "logits/chosen": -1.889314889907837,
+      "logits/rejected": -2.119999885559082,
+      "logps/chosen": -283.8106384277344,
+      "logps/rejected": -217.4166259765625,
+      "loss": 1.046,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3023836016654968,
+      "rewards/margins": 2.977555751800537,
+      "rewards/rejected": -2.6751716136932373,
+      "step": 210
+    },
+    {
+      "epoch": 0.6902086677367576,
+      "grad_norm": 24.165843963623047,
+      "learning_rate": 2.1475626645535367e-07,
+      "logits/chosen": -1.2131136655807495,
+      "logits/rejected": -0.9721648097038269,
+      "logps/chosen": -373.4245910644531,
+      "logps/rejected": -234.89364624023438,
+      "loss": 1.093,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3658973276615143,
+      "rewards/margins": 3.6775901317596436,
+      "rewards/rejected": -3.311692714691162,
+      "step": 215
+    },
+    {
+      "epoch": 0.7062600321027287,
+      "grad_norm": 21.797191619873047,
+      "learning_rate": 1.9644543560695136e-07,
+      "logits/chosen": -1.5296471118927002,
+      "logits/rejected": -1.6277145147323608,
+      "logps/chosen": -412.1878356933594,
+      "logps/rejected": -314.4945373535156,
+      "loss": 1.0305,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.5929609537124634,
+      "rewards/margins": 3.6523776054382324,
+      "rewards/rejected": -3.0594162940979004,
+      "step": 220
+    },
+    {
+      "epoch": 0.7223113964686998,
+      "grad_norm": 19.618436813354492,
+      "learning_rate": 1.784312727899994e-07,
+      "logits/chosen": -1.4759819507598877,
+      "logits/rejected": -1.783433198928833,
+      "logps/chosen": -510.66180419921875,
+      "logps/rejected": -262.74725341796875,
+      "loss": 1.0172,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.28623512387275696,
+      "rewards/margins": 3.71972918510437,
+      "rewards/rejected": -3.4334940910339355,
+      "step": 225
+    },
+    {
+      "epoch": 0.7383627608346709,
+      "grad_norm": 15.515320777893066,
+      "learning_rate": 1.6081356830774623e-07,
+      "logits/chosen": -0.7434533834457397,
+      "logits/rejected": -1.0206338167190552,
+      "logps/chosen": -625.6656494140625,
+      "logps/rejected": -294.1523742675781,
+      "loss": 1.0822,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.5695539712905884,
+      "rewards/margins": 4.612680912017822,
+      "rewards/rejected": -4.043127536773682,
+      "step": 230
+    },
+    {
+      "epoch": 0.7544141252006421,
+      "grad_norm": 14.756795883178711,
+      "learning_rate": 1.4368991626382548e-07,
+      "logits/chosen": -1.3159469366073608,
+      "logits/rejected": -1.9151531457901,
+      "logps/chosen": -506.05084228515625,
+      "logps/rejected": -288.33526611328125,
+      "loss": 0.9993,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.8690406084060669,
+      "rewards/margins": 4.248424053192139,
+      "rewards/rejected": -3.3793838024139404,
+      "step": 235
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "grad_norm": 12.66774845123291,
+      "learning_rate": 1.2715517393512238e-07,
+      "logits/chosen": -1.2622467279434204,
+      "logits/rejected": -1.3659932613372803,
+      "logps/chosen": -591.2831420898438,
+      "logps/rejected": -315.7579040527344,
+      "loss": 1.1002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.42772501707077026,
+      "rewards/margins": 4.257325172424316,
+      "rewards/rejected": -3.8295998573303223,
+      "step": 240
+    },
+    {
+      "epoch": 0.7865168539325843,
+      "grad_norm": 16.25082015991211,
+      "learning_rate": 1.1130093630542198e-07,
+      "logits/chosen": -1.1802631616592407,
+      "logits/rejected": -1.249211072921753,
+      "logps/chosen": -482.888671875,
+      "logps/rejected": -345.88824462890625,
+      "loss": 0.983,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.8362643122673035,
+      "rewards/margins": 4.463853359222412,
+      "rewards/rejected": -3.627588987350464,
+      "step": 245
+    },
+    {
+      "epoch": 0.8025682182985554,
+      "grad_norm": 17.564659118652344,
+      "learning_rate": 9.621502867068285e-08,
+      "logits/chosen": -1.4240429401397705,
+      "logits/rejected": -1.372710943222046,
+      "logps/chosen": -459.75030517578125,
+      "logps/rejected": -321.6226501464844,
+      "loss": 1.0852,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.0832629203796387,
+      "rewards/margins": 4.887136936187744,
+      "rewards/rejected": -3.8038737773895264,
+      "step": 250
+    },
+    {
+      "epoch": 0.8186195826645265,
+      "grad_norm": 18.318283081054688,
+      "learning_rate": 8.198102012667407e-08,
+      "logits/chosen": -1.9069766998291016,
+      "logits/rejected": -1.9020580053329468,
+      "logps/chosen": -401.6404724121094,
+      "logps/rejected": -295.3546142578125,
+      "loss": 1.0466,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.12345659732818604,
+      "rewards/margins": 3.521843671798706,
+      "rewards/rejected": -3.3983871936798096,
+      "step": 255
+    },
+    {
+      "epoch": 0.8346709470304976,
+      "grad_norm": 14.781198501586914,
+      "learning_rate": 6.86777606340341e-08,
+      "logits/chosen": -1.7581796646118164,
+      "logits/rejected": -1.6436153650283813,
+      "logps/chosen": -182.29490661621094,
+      "logps/rejected": -156.72459411621094,
+      "loss": 1.1013,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.2946431040763855,
+      "rewards/margins": 2.2983453273773193,
+      "rewards/rejected": -2.003702163696289,
+      "step": 260
+    },
+    {
+      "epoch": 0.8507223113964687,
+      "grad_norm": 19.03549575805664,
+      "learning_rate": 5.637894422520026e-08,
+      "logits/chosen": -1.8069452047348022,
+      "logits/rejected": -1.8712180852890015,
+      "logps/chosen": -320.7396545410156,
+      "logps/rejected": -230.3447265625,
+      "loss": 0.9904,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.1634465754032135,
+      "rewards/margins": 2.5912208557128906,
+      "rewards/rejected": -2.427773952484131,
+      "step": 265
+    },
+    {
+      "epoch": 0.8667736757624398,
+      "grad_norm": 20.6317081451416,
+      "learning_rate": 4.515270077284594e-08,
+      "logits/chosen": -1.8391157388687134,
+      "logits/rejected": -1.8903614282608032,
+      "logps/chosen": -493.16998291015625,
+      "logps/rejected": -243.4764862060547,
+      "loss": 1.0834,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.6217156648635864,
+      "rewards/margins": 3.6283297538757324,
+      "rewards/rejected": -3.0066142082214355,
+      "step": 270
+    },
+    {
+      "epoch": 0.8828250401284109,
+      "grad_norm": 15.678504943847656,
+      "learning_rate": 3.506121858124253e-08,
+      "logits/chosen": -2.1319689750671387,
+      "logits/rejected": -2.3358452320098877,
+      "logps/chosen": -544.0633544921875,
+      "logps/rejected": -284.2521057128906,
+      "loss": 1.0789,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.1263357549905777,
+      "rewards/margins": 3.653578996658325,
+      "rewards/rejected": -3.5272433757781982,
+      "step": 275
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 35.75740051269531,
+      "learning_rate": 2.6160399891218986e-08,
+      "logits/chosen": -1.9280614852905273,
+      "logits/rejected": -2.3073010444641113,
+      "logps/chosen": -706.4361572265625,
+      "logps/rejected": -341.9065856933594,
+      "loss": 1.0365,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.607284426689148,
+      "rewards/margins": 4.847535133361816,
+      "rewards/rejected": -4.240251064300537,
+      "step": 280
+    },
+    {
+      "epoch": 0.9149277688603531,
+      "grad_norm": 12.305197715759277,
+      "learning_rate": 1.8499551207066726e-08,
+      "logits/chosen": -1.5439479351043701,
+      "logits/rejected": -1.656998872756958,
+      "logps/chosen": -385.1285095214844,
+      "logps/rejected": -361.050537109375,
+      "loss": 1.0772,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3932652473449707,
+      "rewards/margins": 4.640822410583496,
+      "rewards/rejected": -4.247557640075684,
+      "step": 285
+    },
+    {
+      "epoch": 0.9309791332263242,
+      "grad_norm": 17.36638069152832,
+      "learning_rate": 1.2121110160836696e-08,
+      "logits/chosen": -1.1358602046966553,
+      "logits/rejected": -1.322624921798706,
+      "logps/chosen": -359.67181396484375,
+      "logps/rejected": -275.7583312988281,
+      "loss": 1.0249,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.3709088861942291,
+      "rewards/margins": 3.387117862701416,
+      "rewards/rejected": -3.0162088871002197,
+      "step": 290
+    },
+    {
+      "epoch": 0.9470304975922953,
+      "grad_norm": 13.696333885192871,
+      "learning_rate": 7.060410427078472e-09,
+      "logits/chosen": -1.3360637426376343,
+      "logits/rejected": -1.6079111099243164,
+      "logps/chosen": -504.14727783203125,
+      "logps/rejected": -352.38812255859375,
+      "loss": 0.9998,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.5898990631103516,
+      "rewards/margins": 4.491053581237793,
+      "rewards/rejected": -3.9011547565460205,
+      "step": 295
+    },
+    {
+      "epoch": 0.9630818619582665,
+      "grad_norm": 19.26398468017578,
+      "learning_rate": 3.345485990286029e-09,
+      "logits/chosen": -2.010549783706665,
+      "logits/rejected": -1.7452675104141235,
+      "logps/chosen": -280.08685302734375,
+      "logps/rejected": -282.55950927734375,
+      "loss": 1.0632,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.5629211664199829,
+      "rewards/margins": 3.6783041954040527,
+      "rewards/rejected": -3.1153833866119385,
+      "step": 300
+    },
+    {
+      "epoch": 0.9791332263242376,
+      "grad_norm": 20.505722045898438,
+      "learning_rate": 9.969158493204066e-10,
+      "logits/chosen": -1.6427099704742432,
+      "logits/rejected": -1.7004835605621338,
+      "logps/chosen": -459.8740234375,
+      "logps/rejected": -258.29705810546875,
+      "loss": 1.0695,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.22339797019958496,
+      "rewards/margins": 3.7468554973602295,
+      "rewards/rejected": -3.5234577655792236,
+      "step": 305
+    },
+    {
+      "epoch": 0.9951845906902087,
+      "grad_norm": 17.717132568359375,
+      "learning_rate": 2.7710019076532255e-11,
+      "logits/chosen": -1.4575186967849731,
+      "logits/rejected": -1.1399505138397217,
+      "logps/chosen": -437.7586975097656,
+      "logps/rejected": -279.3139343261719,
+      "loss": 1.0752,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.02865469455718994,
+      "rewards/margins": 3.524338483810425,
+      "rewards/rejected": -3.495683193206787,
+      "step": 310
+    },
+    {
+      "epoch": 0.9983948635634029,
+      "step": 311,
+      "total_flos": 2.2772099803879834e+17,
+      "train_loss": 1.2078840717242079,
+      "train_runtime": 1561.3327,
+      "train_samples_per_second": 3.19,
+      "train_steps_per_second": 0.199
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 311,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 2.2772099803879834e+17,
+  "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:da96ce0b0d54654a796e414437f48f8550a2be70f85074f6eb0c43660bd98fd0
+size 6392