add model

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/gpfs/projects/bsc88/text/models/instruction-tuning/models/base_models_with_special_tokens/bsc_7b_hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da2f6a0e9fe9d1a3e1899e0c690263395c554258758900ec03258fcc7112169
+size 4982973048

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fa922b11b2069e35bcc4a2c08cd0073327d4868f4636c67c52d71ad01d97ac
+size 4995660232

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7102060b21c44380268cbe9f4775d40746fc70c87da8957a094549f244a2e6
+size 3460482936

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a298ea8033e8c4fa2f819644de8be413c78fffc84d656a7bd47e7bacfb976f
+size 2097152128

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15536234496
+  },
+  "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-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-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.weight": "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-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.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.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_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_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.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.weight": "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-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.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.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.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.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.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.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.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.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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.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.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_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_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.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.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_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_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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "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.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.weight": "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 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139de51e6bbe12b772a255e157829f43bd67b63a4d55f1fe0e3abce37b2d8c9a
+size 19066993

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa490e57cebce5cb1a0a5b1a5d3fa4de05aee53dc3a44791f1c3401db44d802d
+size 4813274

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1209 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984871406959153,
+  "eval_steps": 42,
+  "global_step": 165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006051437216338881,
+      "grad_norm": 2485872861586.4854,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1824,
+      "step": 1
+    },
+    {
+      "epoch": 0.012102874432677761,
+      "grad_norm": 2374258153298.8555,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.2088,
+      "step": 2
+    },
+    {
+      "epoch": 0.018154311649016642,
+      "grad_norm": 396.1724444566197,
+      "learning_rate": 1.2e-05,
+      "loss": 1.2027,
+      "step": 3
+    },
+    {
+      "epoch": 0.024205748865355523,
+      "grad_norm": 7397.331100311796,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.1208,
+      "step": 4
+    },
+    {
+      "epoch": 0.030257186081694403,
+      "grad_norm": 84.86083374215458,
+      "learning_rate": 2e-05,
+      "loss": 0.9113,
+      "step": 5
+    },
+    {
+      "epoch": 0.036308623298033284,
+      "grad_norm": 978.6354359559489,
+      "learning_rate": 1.9998072404820648e-05,
+      "loss": 0.9526,
+      "step": 6
+    },
+    {
+      "epoch": 0.04236006051437216,
+      "grad_norm": 21.90749318992135,
+      "learning_rate": 1.9992290362407232e-05,
+      "loss": 0.8599,
+      "step": 7
+    },
+    {
+      "epoch": 0.048411497730711045,
+      "grad_norm": 74.82087090537057,
+      "learning_rate": 1.998265610184716e-05,
+      "loss": 1.1003,
+      "step": 8
+    },
+    {
+      "epoch": 0.05446293494704992,
+      "grad_norm": 4.882285623570468,
+      "learning_rate": 1.9969173337331283e-05,
+      "loss": 0.8362,
+      "step": 9
+    },
+    {
+      "epoch": 0.060514372163388806,
+      "grad_norm": 7.899288581834525,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 0.8923,
+      "step": 10
+    },
+    {
+      "epoch": 0.06656580937972768,
+      "grad_norm": 3.4242116473646225,
+      "learning_rate": 1.9930684569549265e-05,
+      "loss": 0.8299,
+      "step": 11
+    },
+    {
+      "epoch": 0.07261724659606657,
+      "grad_norm": 2.5233147164579126,
+      "learning_rate": 1.990569340443577e-05,
+      "loss": 0.8059,
+      "step": 12
+    },
+    {
+      "epoch": 0.07866868381240545,
+      "grad_norm": 3.051443861824001,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 0.7651,
+      "step": 13
+    },
+    {
+      "epoch": 0.08472012102874432,
+      "grad_norm": 2.6097710859490357,
+      "learning_rate": 1.9844265680898917e-05,
+      "loss": 0.7637,
+      "step": 14
+    },
+    {
+      "epoch": 0.0907715582450832,
+      "grad_norm": 2.1938445776094744,
+      "learning_rate": 1.9807852804032306e-05,
+      "loss": 0.7701,
+      "step": 15
+    },
+    {
+      "epoch": 0.09682299546142209,
+      "grad_norm": 3.039971331985702,
+      "learning_rate": 1.9767658813208725e-05,
+      "loss": 0.7326,
+      "step": 16
+    },
+    {
+      "epoch": 0.10287443267776097,
+      "grad_norm": 2.3582600372243494,
+      "learning_rate": 1.9723699203976768e-05,
+      "loss": 0.7477,
+      "step": 17
+    },
+    {
+      "epoch": 0.10892586989409984,
+      "grad_norm": 2.044504064644785,
+      "learning_rate": 1.96759909236026e-05,
+      "loss": 0.7279,
+      "step": 18
+    },
+    {
+      "epoch": 0.11497730711043873,
+      "grad_norm": 2.110191157985126,
+      "learning_rate": 1.9624552364536472e-05,
+      "loss": 0.7295,
+      "step": 19
+    },
+    {
+      "epoch": 0.12102874432677761,
+      "grad_norm": 2.0796944865165714,
+      "learning_rate": 1.956940335732209e-05,
+      "loss": 0.7085,
+      "step": 20
+    },
+    {
+      "epoch": 0.12708018154311648,
+      "grad_norm": 2.522674133160586,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.7311,
+      "step": 21
+    },
+    {
+      "epoch": 0.13313161875945537,
+      "grad_norm": 2.0811107085167437,
+      "learning_rate": 1.944806046466878e-05,
+      "loss": 0.7146,
+      "step": 22
+    },
+    {
+      "epoch": 0.13918305597579425,
+      "grad_norm": 2.265003278256734,
+      "learning_rate": 1.9381913359224844e-05,
+      "loss": 0.7091,
+      "step": 23
+    },
+    {
+      "epoch": 0.14523449319213314,
+      "grad_norm": 1.8790084467988264,
+      "learning_rate": 1.9312149347588035e-05,
+      "loss": 0.7004,
+      "step": 24
+    },
+    {
+      "epoch": 0.15128593040847202,
+      "grad_norm": 2.1570176309321036,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.7147,
+      "step": 25
+    },
+    {
+      "epoch": 0.1573373676248109,
+      "grad_norm": 2.044429433610023,
+      "learning_rate": 1.916187957117136e-05,
+      "loss": 0.683,
+      "step": 26
+    },
+    {
+      "epoch": 0.16338880484114976,
+      "grad_norm": 1.9500024997189427,
+      "learning_rate": 1.9081431738250815e-05,
+      "loss": 0.6534,
+      "step": 27
+    },
+    {
+      "epoch": 0.16944024205748864,
+      "grad_norm": 1.8107376027349673,
+      "learning_rate": 1.8997482840522218e-05,
+      "loss": 0.658,
+      "step": 28
+    },
+    {
+      "epoch": 0.17549167927382753,
+      "grad_norm": 1.893340947855662,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.6909,
+      "step": 29
+    },
+    {
+      "epoch": 0.1815431164901664,
+      "grad_norm": 1.7401143745241425,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 0.6714,
+      "step": 30
+    },
+    {
+      "epoch": 0.1875945537065053,
+      "grad_norm": 1.6745153162006545,
+      "learning_rate": 1.8724960070727974e-05,
+      "loss": 0.6977,
+      "step": 31
+    },
+    {
+      "epoch": 0.19364599092284418,
+      "grad_norm": 1.7140573912873658,
+      "learning_rate": 1.862734385977792e-05,
+      "loss": 0.6804,
+      "step": 32
+    },
+    {
+      "epoch": 0.19969742813918306,
+      "grad_norm": 1.6077423149312056,
+      "learning_rate": 1.8526401643540924e-05,
+      "loss": 0.6716,
+      "step": 33
+    },
+    {
+      "epoch": 0.20574886535552195,
+      "grad_norm": 1.4358147690664171,
+      "learning_rate": 1.8422172337162865e-05,
+      "loss": 0.6664,
+      "step": 34
+    },
+    {
+      "epoch": 0.2118003025718608,
+      "grad_norm": 2.812059503039093,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 0.667,
+      "step": 35
+    },
+    {
+      "epoch": 0.2178517397881997,
+      "grad_norm": 1.7686345457161963,
+      "learning_rate": 1.8204014435255136e-05,
+      "loss": 0.6973,
+      "step": 36
+    },
+    {
+      "epoch": 0.22390317700453857,
+      "grad_norm": 1.470592147128763,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.6708,
+      "step": 37
+    },
+    {
+      "epoch": 0.22995461422087746,
+      "grad_norm": 1.4325487355932993,
+      "learning_rate": 1.797320653772707e-05,
+      "loss": 0.636,
+      "step": 38
+    },
+    {
+      "epoch": 0.23600605143721634,
+      "grad_norm": 1.5158022833486517,
+      "learning_rate": 1.785316930880745e-05,
+      "loss": 0.632,
+      "step": 39
+    },
+    {
+      "epoch": 0.24205748865355523,
+      "grad_norm": 1.4035210760893406,
+      "learning_rate": 1.773010453362737e-05,
+      "loss": 0.654,
+      "step": 40
+    },
+    {
+      "epoch": 0.2481089258698941,
+      "grad_norm": 1.344913257545713,
+      "learning_rate": 1.7604059656000313e-05,
+      "loss": 0.6524,
+      "step": 41
+    },
+    {
+      "epoch": 0.25416036308623297,
+      "grad_norm": 1.5331768604954814,
+      "learning_rate": 1.747508326862597e-05,
+      "loss": 0.6752,
+      "step": 42
+    },
+    {
+      "epoch": 0.25416036308623297,
+      "eval_loss": 0.6497564315795898,
+      "eval_runtime": 240.9191,
+      "eval_samples_per_second": 17.558,
+      "eval_steps_per_second": 0.278,
+      "step": 42
+    },
+    {
+      "epoch": 0.26021180030257185,
+      "grad_norm": 1.3453112551443027,
+      "learning_rate": 1.7343225094356857e-05,
+      "loss": 0.6378,
+      "step": 43
+    },
+    {
+      "epoch": 0.26626323751891073,
+      "grad_norm": 1.2901427277827926,
+      "learning_rate": 1.720853596702919e-05,
+      "loss": 0.6535,
+      "step": 44
+    },
+    {
+      "epoch": 0.2723146747352496,
+      "grad_norm": 1.279593413533858,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.6482,
+      "step": 45
+    },
+    {
+      "epoch": 0.2783661119515885,
+      "grad_norm": 1.485821081722045,
+      "learning_rate": 1.6930873625456362e-05,
+      "loss": 0.6701,
+      "step": 46
+    },
+    {
+      "epoch": 0.2844175491679274,
+      "grad_norm": 1.1782047694848008,
+      "learning_rate": 1.678800745532942e-05,
+      "loss": 0.639,
+      "step": 47
+    },
+    {
+      "epoch": 0.29046898638426627,
+      "grad_norm": 1.182935652668345,
+      "learning_rate": 1.664252437911282e-05,
+      "loss": 0.6353,
+      "step": 48
+    },
+    {
+      "epoch": 0.29652042360060515,
+      "grad_norm": 1.3371967812238952,
+      "learning_rate": 1.6494480483301836e-05,
+      "loss": 0.6513,
+      "step": 49
+    },
+    {
+      "epoch": 0.30257186081694404,
+      "grad_norm": 1.3464560857933685,
+      "learning_rate": 1.6343932841636455e-05,
+      "loss": 0.637,
+      "step": 50
+    },
+    {
+      "epoch": 0.3086232980332829,
+      "grad_norm": 1.2225531139436927,
+      "learning_rate": 1.6190939493098344e-05,
+      "loss": 0.6313,
+      "step": 51
+    },
+    {
+      "epoch": 0.3146747352496218,
+      "grad_norm": 1.2321828901853542,
+      "learning_rate": 1.6035559419535714e-05,
+      "loss": 0.6469,
+      "step": 52
+    },
+    {
+      "epoch": 0.3207261724659607,
+      "grad_norm": 1.3402583020833378,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.6366,
+      "step": 53
+    },
+    {
+      "epoch": 0.3267776096822995,
+      "grad_norm": 1.1557802726800193,
+      "learning_rate": 1.5717879602276123e-05,
+      "loss": 0.6178,
+      "step": 54
+    },
+    {
+      "epoch": 0.3328290468986384,
+      "grad_norm": 1.2101508308008404,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 0.6479,
+      "step": 55
+    },
+    {
+      "epoch": 0.3388804841149773,
+      "grad_norm": 1.42141235053728,
+      "learning_rate": 1.5391383229110005e-05,
+      "loss": 0.6458,
+      "step": 56
+    },
+    {
+      "epoch": 0.34493192133131617,
+      "grad_norm": 1.2999993867502941,
+      "learning_rate": 1.5224985647159489e-05,
+      "loss": 0.6347,
+      "step": 57
+    },
+    {
+      "epoch": 0.35098335854765506,
+      "grad_norm": 1.3406194889045318,
+      "learning_rate": 1.5056573733779848e-05,
+      "loss": 0.6391,
+      "step": 58
+    },
+    {
+      "epoch": 0.35703479576399394,
+      "grad_norm": 1.3433628422807478,
+      "learning_rate": 1.4886212414969551e-05,
+      "loss": 0.6468,
+      "step": 59
+    },
+    {
+      "epoch": 0.3630862329803328,
+      "grad_norm": 1.2918891896945706,
+      "learning_rate": 1.4713967368259981e-05,
+      "loss": 0.6263,
+      "step": 60
+    },
+    {
+      "epoch": 0.3691376701966717,
+      "grad_norm": 2.773236659243322,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.6446,
+      "step": 61
+    },
+    {
+      "epoch": 0.3751891074130106,
+      "grad_norm": 1.4437223516048685,
+      "learning_rate": 1.436409240673342e-05,
+      "loss": 0.6379,
+      "step": 62
+    },
+    {
+      "epoch": 0.3812405446293495,
+      "grad_norm": 1.4841854042584977,
+      "learning_rate": 1.4186597375374283e-05,
+      "loss": 0.6222,
+      "step": 63
+    },
+    {
+      "epoch": 0.38729198184568836,
+      "grad_norm": 1.2593547293298168,
+      "learning_rate": 1.4007488331031409e-05,
+      "loss": 0.6166,
+      "step": 64
+    },
+    {
+      "epoch": 0.39334341906202724,
+      "grad_norm": 1.2697035696692358,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.654,
+      "step": 65
+    },
+    {
+      "epoch": 0.39939485627836613,
+      "grad_norm": 1.5125181803042715,
+      "learning_rate": 1.3644704998791501e-05,
+      "loss": 0.6491,
+      "step": 66
+    },
+    {
+      "epoch": 0.405446293494705,
+      "grad_norm": 1.1671607547969556,
+      "learning_rate": 1.346117057077493e-05,
+      "loss": 0.6456,
+      "step": 67
+    },
+    {
+      "epoch": 0.4114977307110439,
+      "grad_norm": 1.1858707062216176,
+      "learning_rate": 1.3276301795616937e-05,
+      "loss": 0.6409,
+      "step": 68
+    },
+    {
+      "epoch": 0.4175491679273828,
+      "grad_norm": 1.274887597351961,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.6314,
+      "step": 69
+    },
+    {
+      "epoch": 0.4236006051437216,
+      "grad_norm": 1.1952319371476656,
+      "learning_rate": 1.2902846772544625e-05,
+      "loss": 0.6338,
+      "step": 70
+    },
+    {
+      "epoch": 0.4296520423600605,
+      "grad_norm": 1.2039189391326874,
+      "learning_rate": 1.2714404498650743e-05,
+      "loss": 0.6367,
+      "step": 71
+    },
+    {
+      "epoch": 0.4357034795763994,
+      "grad_norm": 1.2493232936493541,
+      "learning_rate": 1.252491577015158e-05,
+      "loss": 0.6143,
+      "step": 72
+    },
+    {
+      "epoch": 0.44175491679273826,
+      "grad_norm": 1.2124826419990378,
+      "learning_rate": 1.2334453638559057e-05,
+      "loss": 0.6281,
+      "step": 73
+    },
+    {
+      "epoch": 0.44780635400907715,
+      "grad_norm": 1.754723638913915,
+      "learning_rate": 1.2143091530650508e-05,
+      "loss": 0.637,
+      "step": 74
+    },
+    {
+      "epoch": 0.45385779122541603,
+      "grad_norm": 1.2667778628244222,
+      "learning_rate": 1.1950903220161286e-05,
+      "loss": 0.6477,
+      "step": 75
+    },
+    {
+      "epoch": 0.4599092284417549,
+      "grad_norm": 1.1693479009083907,
+      "learning_rate": 1.1757962799343548e-05,
+      "loss": 0.6133,
+      "step": 76
+    },
+    {
+      "epoch": 0.4659606656580938,
+      "grad_norm": 1.1085663874308165,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.6053,
+      "step": 77
+    },
+    {
+      "epoch": 0.4720121028744327,
+      "grad_norm": 1.2275476075576535,
+      "learning_rate": 1.1370123416819683e-05,
+      "loss": 0.6222,
+      "step": 78
+    },
+    {
+      "epoch": 0.47806354009077157,
+      "grad_norm": 1.2913381715274397,
+      "learning_rate": 1.1175373974578378e-05,
+      "loss": 0.6225,
+      "step": 79
+    },
+    {
+      "epoch": 0.48411497730711045,
+      "grad_norm": 1.1929623616502596,
+      "learning_rate": 1.098017140329561e-05,
+      "loss": 0.6149,
+      "step": 80
+    },
+    {
+      "epoch": 0.49016641452344933,
+      "grad_norm": 1.1929734366136742,
+      "learning_rate": 1.0784590957278452e-05,
+      "loss": 0.6109,
+      "step": 81
+    },
+    {
+      "epoch": 0.4962178517397882,
+      "grad_norm": 1.166286080240029,
+      "learning_rate": 1.058870803651189e-05,
+      "loss": 0.6197,
+      "step": 82
+    },
+    {
+      "epoch": 0.5022692889561271,
+      "grad_norm": 1.251236063248938,
+      "learning_rate": 1.0392598157590687e-05,
+      "loss": 0.615,
+      "step": 83
+    },
+    {
+      "epoch": 0.5083207261724659,
+      "grad_norm": 1.1723348633981843,
+      "learning_rate": 1.0196336924606282e-05,
+      "loss": 0.6243,
+      "step": 84
+    },
+    {
+      "epoch": 0.5083207261724659,
+      "eval_loss": 0.6196625232696533,
+      "eval_runtime": 229.3836,
+      "eval_samples_per_second": 18.441,
+      "eval_steps_per_second": 0.292,
+      "step": 84
+    },
+    {
+      "epoch": 0.5143721633888049,
+      "grad_norm": 1.264238673034934,
+      "learning_rate": 1e-05,
+      "loss": 0.601,
+      "step": 85
+    },
+    {
+      "epoch": 0.5204236006051437,
+      "grad_norm": 1.1869923729073102,
+      "learning_rate": 9.80366307539372e-06,
+      "loss": 0.635,
+      "step": 86
+    },
+    {
+      "epoch": 0.5264750378214826,
+      "grad_norm": 1.155605537137944,
+      "learning_rate": 9.607401842409318e-06,
+      "loss": 0.6086,
+      "step": 87
+    },
+    {
+      "epoch": 0.5325264750378215,
+      "grad_norm": 1.1810059527345225,
+      "learning_rate": 9.41129196348811e-06,
+      "loss": 0.6066,
+      "step": 88
+    },
+    {
+      "epoch": 0.5385779122541604,
+      "grad_norm": 1.48288275051847,
+      "learning_rate": 9.215409042721553e-06,
+      "loss": 0.6074,
+      "step": 89
+    },
+    {
+      "epoch": 0.5446293494704992,
+      "grad_norm": 1.2236480314592646,
+      "learning_rate": 9.019828596704394e-06,
+      "loss": 0.6005,
+      "step": 90
+    },
+    {
+      "epoch": 0.5506807866868382,
+      "grad_norm": 1.225104434933414,
+      "learning_rate": 8.824626025421625e-06,
+      "loss": 0.6209,
+      "step": 91
+    },
+    {
+      "epoch": 0.556732223903177,
+      "grad_norm": 1.3753239293064896,
+      "learning_rate": 8.629876583180322e-06,
+      "loss": 0.6284,
+      "step": 92
+    },
+    {
+      "epoch": 0.5627836611195158,
+      "grad_norm": 1.1165345494257204,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.5922,
+      "step": 93
+    },
+    {
+      "epoch": 0.5688350983358548,
+      "grad_norm": 1.1302938437987953,
+      "learning_rate": 8.242037200656455e-06,
+      "loss": 0.5945,
+      "step": 94
+    },
+    {
+      "epoch": 0.5748865355521936,
+      "grad_norm": 1.0925454165360629,
+      "learning_rate": 8.04909677983872e-06,
+      "loss": 0.603,
+      "step": 95
+    },
+    {
+      "epoch": 0.5809379727685325,
+      "grad_norm": 1.257734967726645,
+      "learning_rate": 7.856908469349495e-06,
+      "loss": 0.614,
+      "step": 96
+    },
+    {
+      "epoch": 0.5869894099848714,
+      "grad_norm": 1.128472303920492,
+      "learning_rate": 7.66554636144095e-06,
+      "loss": 0.6285,
+      "step": 97
+    },
+    {
+      "epoch": 0.5930408472012103,
+      "grad_norm": 1.1421760663082452,
+      "learning_rate": 7.4750842298484205e-06,
+      "loss": 0.6185,
+      "step": 98
+    },
+    {
+      "epoch": 0.5990922844175491,
+      "grad_norm": 1.1243624229579912,
+      "learning_rate": 7.285595501349259e-06,
+      "loss": 0.6312,
+      "step": 99
+    },
+    {
+      "epoch": 0.6051437216338881,
+      "grad_norm": 1.2053726091706483,
+      "learning_rate": 7.097153227455379e-06,
+      "loss": 0.6184,
+      "step": 100
+    },
+    {
+      "epoch": 0.6111951588502269,
+      "grad_norm": 1.2905397800780836,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.6016,
+      "step": 101
+    },
+    {
+      "epoch": 0.6172465960665658,
+      "grad_norm": 1.1119701235429014,
+      "learning_rate": 6.723698204383067e-06,
+      "loss": 0.5947,
+      "step": 102
+    },
+    {
+      "epoch": 0.6232980332829047,
+      "grad_norm": 1.0439743919075113,
+      "learning_rate": 6.538829429225068e-06,
+      "loss": 0.5838,
+      "step": 103
+    },
+    {
+      "epoch": 0.6293494704992436,
+      "grad_norm": 1.0887711124033599,
+      "learning_rate": 6.355295001208504e-06,
+      "loss": 0.6027,
+      "step": 104
+    },
+    {
+      "epoch": 0.6354009077155824,
+      "grad_norm": 1.0882356853978903,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.5957,
+      "step": 105
+    },
+    {
+      "epoch": 0.6414523449319214,
+      "grad_norm": 1.098158642309974,
+      "learning_rate": 5.9925116689685925e-06,
+      "loss": 0.6121,
+      "step": 106
+    },
+    {
+      "epoch": 0.6475037821482602,
+      "grad_norm": 1.118376343327207,
+      "learning_rate": 5.813402624625722e-06,
+      "loss": 0.5984,
+      "step": 107
+    },
+    {
+      "epoch": 0.653555219364599,
+      "grad_norm": 1.1834759273908468,
+      "learning_rate": 5.635907593266578e-06,
+      "loss": 0.6317,
+      "step": 108
+    },
+    {
+      "epoch": 0.659606656580938,
+      "grad_norm": 1.0902626718892547,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.598,
+      "step": 109
+    },
+    {
+      "epoch": 0.6656580937972768,
+      "grad_norm": 1.0904339069847084,
+      "learning_rate": 5.286032631740023e-06,
+      "loss": 0.595,
+      "step": 110
+    },
+    {
+      "epoch": 0.6717095310136157,
+      "grad_norm": 1.1365339473040479,
+      "learning_rate": 5.1137875850304545e-06,
+      "loss": 0.6077,
+      "step": 111
+    },
+    {
+      "epoch": 0.6777609682299546,
+      "grad_norm": 1.2850035932836996,
+      "learning_rate": 4.943426266220156e-06,
+      "loss": 0.5951,
+      "step": 112
+    },
+    {
+      "epoch": 0.6838124054462935,
+      "grad_norm": 1.1128153520291575,
+      "learning_rate": 4.775014352840512e-06,
+      "loss": 0.6092,
+      "step": 113
+    },
+    {
+      "epoch": 0.6898638426626323,
+      "grad_norm": 1.106251089348545,
+      "learning_rate": 4.608616770889998e-06,
+      "loss": 0.61,
+      "step": 114
+    },
+    {
+      "epoch": 0.6959152798789713,
+      "grad_norm": 1.1431262362719048,
+      "learning_rate": 4.444297669803981e-06,
+      "loss": 0.602,
+      "step": 115
+    },
+    {
+      "epoch": 0.7019667170953101,
+      "grad_norm": 1.2142474830783798,
+      "learning_rate": 4.282120397723879e-06,
+      "loss": 0.5988,
+      "step": 116
+    },
+    {
+      "epoch": 0.708018154311649,
+      "grad_norm": 1.1882349202638232,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.6238,
+      "step": 117
+    },
+    {
+      "epoch": 0.7140695915279879,
+      "grad_norm": 1.109339846325976,
+      "learning_rate": 3.964440580464286e-06,
+      "loss": 0.5895,
+      "step": 118
+    },
+    {
+      "epoch": 0.7201210287443268,
+      "grad_norm": 1.1110191612272007,
+      "learning_rate": 3.8090605069016596e-06,
+      "loss": 0.6105,
+      "step": 119
+    },
+    {
+      "epoch": 0.7261724659606656,
+      "grad_norm": 1.1179333014320294,
+      "learning_rate": 3.6560671583635467e-06,
+      "loss": 0.5932,
+      "step": 120
+    },
+    {
+      "epoch": 0.7322239031770046,
+      "grad_norm": 1.1265078817662724,
+      "learning_rate": 3.505519516698165e-06,
+      "loss": 0.5999,
+      "step": 121
+    },
+    {
+      "epoch": 0.7382753403933434,
+      "grad_norm": 1.075578490050491,
+      "learning_rate": 3.3574756208871862e-06,
+      "loss": 0.5915,
+      "step": 122
+    },
+    {
+      "epoch": 0.7443267776096822,
+      "grad_norm": 1.1242426718753973,
+      "learning_rate": 3.2119925446705824e-06,
+      "loss": 0.5989,
+      "step": 123
+    },
+    {
+      "epoch": 0.7503782148260212,
+      "grad_norm": 1.1091583294027973,
+      "learning_rate": 3.069126374543643e-06,
+      "loss": 0.5961,
+      "step": 124
+    },
+    {
+      "epoch": 0.75642965204236,
+      "grad_norm": 1.0901305589473516,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.6161,
+      "step": 125
+    },
+    {
+      "epoch": 0.762481089258699,
+      "grad_norm": 1.099855491597428,
+      "learning_rate": 2.791464032970812e-06,
+      "loss": 0.6126,
+      "step": 126
+    },
+    {
+      "epoch": 0.762481089258699,
+      "eval_loss": 0.5977321863174438,
+      "eval_runtime": 231.0076,
+      "eval_samples_per_second": 18.311,
+      "eval_steps_per_second": 0.29,
+      "step": 126
+    },
+    {
+      "epoch": 0.7685325264750378,
+      "grad_norm": 1.0434061101718985,
+      "learning_rate": 2.656774905643147e-06,
+      "loss": 0.5642,
+      "step": 127
+    },
+    {
+      "epoch": 0.7745839636913767,
+      "grad_norm": 1.221163997302398,
+      "learning_rate": 2.5249167313740307e-06,
+      "loss": 0.5941,
+      "step": 128
+    },
+    {
+      "epoch": 0.7806354009077155,
+      "grad_norm": 1.10442870611896,
+      "learning_rate": 2.395940343999691e-06,
+      "loss": 0.5968,
+      "step": 129
+    },
+    {
+      "epoch": 0.7866868381240545,
+      "grad_norm": 1.0758064420406537,
+      "learning_rate": 2.26989546637263e-06,
+      "loss": 0.5608,
+      "step": 130
+    },
+    {
+      "epoch": 0.7927382753403933,
+      "grad_norm": 1.1099638697418817,
+      "learning_rate": 2.146830691192553e-06,
+      "loss": 0.6061,
+      "step": 131
+    },
+    {
+      "epoch": 0.7987897125567323,
+      "grad_norm": 1.1012628722358688,
+      "learning_rate": 2.02679346227293e-06,
+      "loss": 0.6086,
+      "step": 132
+    },
+    {
+      "epoch": 0.8048411497730711,
+      "grad_norm": 1.0825334967123086,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.5999,
+      "step": 133
+    },
+    {
+      "epoch": 0.81089258698941,
+      "grad_norm": 1.0920843483364964,
+      "learning_rate": 1.7959855647448642e-06,
+      "loss": 0.5851,
+      "step": 134
+    },
+    {
+      "epoch": 0.8169440242057489,
+      "grad_norm": 1.0722929205729042,
+      "learning_rate": 1.6853038769745466e-06,
+      "loss": 0.5943,
+      "step": 135
+    },
+    {
+      "epoch": 0.8229954614220878,
+      "grad_norm": 1.0785356189051434,
+      "learning_rate": 1.577827662837136e-06,
+      "loss": 0.5939,
+      "step": 136
+    },
+    {
+      "epoch": 0.8290468986384266,
+      "grad_norm": 1.105404459630531,
+      "learning_rate": 1.4735983564590784e-06,
+      "loss": 0.5972,
+      "step": 137
+    },
+    {
+      "epoch": 0.8350983358547656,
+      "grad_norm": 1.064384582646943,
+      "learning_rate": 1.3726561402220818e-06,
+      "loss": 0.5834,
+      "step": 138
+    },
+    {
+      "epoch": 0.8411497730711044,
+      "grad_norm": 1.0873361026145811,
+      "learning_rate": 1.2750399292720284e-06,
+      "loss": 0.5727,
+      "step": 139
+    },
+    {
+      "epoch": 0.8472012102874432,
+      "grad_norm": 1.0146195797904674,
+      "learning_rate": 1.1807873565164507e-06,
+      "loss": 0.5555,
+      "step": 140
+    },
+    {
+      "epoch": 0.8532526475037822,
+      "grad_norm": 1.1102017699410431,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.6126,
+      "step": 141
+    },
+    {
+      "epoch": 0.859304084720121,
+      "grad_norm": 1.046330613810264,
+      "learning_rate": 1.0025171594777872e-06,
+      "loss": 0.5866,
+      "step": 142
+    },
+    {
+      "epoch": 0.8653555219364599,
+      "grad_norm": 1.054167660384435,
+      "learning_rate": 9.185682617491865e-07,
+      "loss": 0.6009,
+      "step": 143
+    },
+    {
+      "epoch": 0.8714069591527988,
+      "grad_norm": 1.0445275144423711,
+      "learning_rate": 8.381204288286415e-07,
+      "loss": 0.5756,
+      "step": 144
+    },
+    {
+      "epoch": 0.8774583963691377,
+      "grad_norm": 1.046910850171513,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.569,
+      "step": 145
+    },
+    {
+      "epoch": 0.8835098335854765,
+      "grad_norm": 1.0770440342943608,
+      "learning_rate": 6.878506524119644e-07,
+      "loss": 0.6137,
+      "step": 146
+    },
+    {
+      "epoch": 0.8895612708018155,
+      "grad_norm": 1.0749107136634029,
+      "learning_rate": 6.180866407751595e-07,
+      "loss": 0.5798,
+      "step": 147
+    },
+    {
+      "epoch": 0.8956127080181543,
+      "grad_norm": 1.1573025313733445,
+      "learning_rate": 5.519395353312195e-07,
+      "loss": 0.5959,
+      "step": 148
+    },
+    {
+      "epoch": 0.9016641452344932,
+      "grad_norm": 1.0236891796646002,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.5574,
+      "step": 149
+    },
+    {
+      "epoch": 0.9077155824508321,
+      "grad_norm": 1.0420631935147442,
+      "learning_rate": 4.305966426779118e-07,
+      "loss": 0.5898,
+      "step": 150
+    },
+    {
+      "epoch": 0.913767019667171,
+      "grad_norm": 1.0706305440714106,
+      "learning_rate": 3.7544763546352834e-07,
+      "loss": 0.6051,
+      "step": 151
+    },
+    {
+      "epoch": 0.9198184568835098,
+      "grad_norm": 1.0849945955512819,
+      "learning_rate": 3.2400907639740243e-07,
+      "loss": 0.5875,
+      "step": 152
+    },
+    {
+      "epoch": 0.9258698940998488,
+      "grad_norm": 1.10481174468143,
+      "learning_rate": 2.7630079602323447e-07,
+      "loss": 0.5891,
+      "step": 153
+    },
+    {
+      "epoch": 0.9319213313161876,
+      "grad_norm": 1.0696523504505417,
+      "learning_rate": 2.3234118679127615e-07,
+      "loss": 0.5979,
+      "step": 154
+    },
+    {
+      "epoch": 0.9379727685325264,
+      "grad_norm": 1.0717642752483758,
+      "learning_rate": 1.921471959676957e-07,
+      "loss": 0.6036,
+      "step": 155
+    },
+    {
+      "epoch": 0.9440242057488654,
+      "grad_norm": 3.074194566505756,
+      "learning_rate": 1.5573431910108404e-07,
+      "loss": 0.5895,
+      "step": 156
+    },
+    {
+      "epoch": 0.9500756429652042,
+      "grad_norm": 1.0642248909874026,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.5872,
+      "step": 157
+    },
+    {
+      "epoch": 0.9561270801815431,
+      "grad_norm": 1.116298645041687,
+      "learning_rate": 9.43065955642275e-08,
+      "loss": 0.5891,
+      "step": 158
+    },
+    {
+      "epoch": 0.962178517397882,
+      "grad_norm": 1.0761046903826774,
+      "learning_rate": 6.931543045073708e-08,
+      "loss": 0.5885,
+      "step": 159
+    },
+    {
+      "epoch": 0.9682299546142209,
+      "grad_norm": 1.098459824451828,
+      "learning_rate": 4.815273327803183e-08,
+      "loss": 0.589,
+      "step": 160
+    },
+    {
+      "epoch": 0.9742813918305597,
+      "grad_norm": 1.1259065136256217,
+      "learning_rate": 3.082666266872036e-08,
+      "loss": 0.6024,
+      "step": 161
+    },
+    {
+      "epoch": 0.9803328290468987,
+      "grad_norm": 1.0518319114128796,
+      "learning_rate": 1.7343898152841765e-08,
+      "loss": 0.6053,
+      "step": 162
+    },
+    {
+      "epoch": 0.9863842662632375,
+      "grad_norm": 1.1340594173533018,
+      "learning_rate": 7.70963759277099e-09,
+      "loss": 0.5828,
+      "step": 163
+    },
+    {
+      "epoch": 0.9924357034795764,
+      "grad_norm": 1.0611854225309354,
+      "learning_rate": 1.9275951793518154e-09,
+      "loss": 0.6039,
+      "step": 164
+    },
+    {
+      "epoch": 0.9984871406959153,
+      "grad_norm": 1.0395934059040783,
+      "learning_rate": 0.0,
+      "loss": 0.5772,
+      "step": 165
+    },
+    {
+      "epoch": 0.9984871406959153,
+      "step": 165,
+      "total_flos": 275962386186240.0,
+      "train_loss": 0.6538035761226307,
+      "train_runtime": 8048.9961,
+      "train_samples_per_second": 5.256,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 165,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 42,
+  "total_flos": 275962386186240.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe037b99f356eb155df7e819be36339479ddb8dac50023e5be90354e1244aa1
+size 6840