Training in progress, step 68, checkpoint

checkpoint-68/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-68/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-68/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.52.3"
+}

checkpoint-68/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d980165c8203b71c88b6eaa503c00b997c3a793e75c894d3c3d44844799de1a8
+size 4943162336

checkpoint-68/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc234e910ca3f5a87f2f0f7601790e1fbf88887a0fe6c280d5cf6a780c1edb97
+size 4999819336

checkpoint-68/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbb1adbd9e577dd059a907d346e029823789dcb5389295fe7ab8058d1081012
+size 4540516344

checkpoint-68/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-68/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacfa5d967d661c2ff5fad36d8ddd20dbce683cc7241e6195d00f3e640b4ae6b
+size 15492462246

checkpoint-68/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ceee57d115406f795a8e36637e43c2e58b5e5df69cc43ee7bc575609de5a15
+size 14308

checkpoint-68/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c407a31ce222c384e16fa0682de26239d930ef60214e4a140d5bba81b4f26030
+size 1064

checkpoint-68/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-68/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-68/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-68/trainer_state.json

@@ -0,0 +1,550 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.7900677200902937,
+  "eval_steps": 17,
+  "global_step": 68,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.056433408577878104,
+      "grad_norm": 50.25,
+      "learning_rate": 2e-05,
+      "loss": 1.5402,
+      "step": 1
+    },
+    {
+      "epoch": 0.056433408577878104,
+      "eval_loss": 1.258617877960205,
+      "eval_runtime": 29.1736,
+      "eval_samples_per_second": 10.866,
+      "eval_steps_per_second": 2.742,
+      "step": 1
+    },
+    {
+      "epoch": 0.11286681715575621,
+      "grad_norm": 22.875,
+      "learning_rate": 2e-05,
+      "loss": 1.1625,
+      "step": 2
+    },
+    {
+      "epoch": 0.16930022573363432,
+      "grad_norm": 16.125,
+      "learning_rate": 2e-05,
+      "loss": 1.0449,
+      "step": 3
+    },
+    {
+      "epoch": 0.22573363431151242,
+      "grad_norm": 15.3125,
+      "learning_rate": 2e-05,
+      "loss": 0.8866,
+      "step": 4
+    },
+    {
+      "epoch": 0.28216704288939054,
+      "grad_norm": 5.1875,
+      "learning_rate": 2e-05,
+      "loss": 0.7271,
+      "step": 5
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "grad_norm": 6.25,
+      "learning_rate": 2e-05,
+      "loss": 0.798,
+      "step": 6
+    },
+    {
+      "epoch": 0.39503386004514673,
+      "grad_norm": 7.125,
+      "learning_rate": 2e-05,
+      "loss": 0.7125,
+      "step": 7
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 14.9375,
+      "learning_rate": 2e-05,
+      "loss": 0.8068,
+      "step": 8
+    },
+    {
+      "epoch": 0.5079006772009029,
+      "grad_norm": 4.125,
+      "learning_rate": 2e-05,
+      "loss": 0.714,
+      "step": 9
+    },
+    {
+      "epoch": 0.5643340857787811,
+      "grad_norm": 6.90625,
+      "learning_rate": 2e-05,
+      "loss": 0.5888,
+      "step": 10
+    },
+    {
+      "epoch": 0.6207674943566591,
+      "grad_norm": 4.25,
+      "learning_rate": 2e-05,
+      "loss": 0.6669,
+      "step": 11
+    },
+    {
+      "epoch": 0.6772009029345373,
+      "grad_norm": 2.1875,
+      "learning_rate": 2e-05,
+      "loss": 0.6013,
+      "step": 12
+    },
+    {
+      "epoch": 0.7336343115124153,
+      "grad_norm": 5.625,
+      "learning_rate": 2e-05,
+      "loss": 0.6516,
+      "step": 13
+    },
+    {
+      "epoch": 0.7900677200902935,
+      "grad_norm": 3.140625,
+      "learning_rate": 2e-05,
+      "loss": 0.6153,
+      "step": 14
+    },
+    {
+      "epoch": 0.8465011286681715,
+      "grad_norm": 2.234375,
+      "learning_rate": 2e-05,
+      "loss": 0.6073,
+      "step": 15
+    },
+    {
+      "epoch": 0.9029345372460497,
+      "grad_norm": 3.09375,
+      "learning_rate": 2e-05,
+      "loss": 0.5704,
+      "step": 16
+    },
+    {
+      "epoch": 0.9593679458239278,
+      "grad_norm": 2.328125,
+      "learning_rate": 2e-05,
+      "loss": 0.5945,
+      "step": 17
+    },
+    {
+      "epoch": 0.9593679458239278,
+      "eval_loss": 0.5594621896743774,
+      "eval_runtime": 30.0451,
+      "eval_samples_per_second": 10.551,
+      "eval_steps_per_second": 2.663,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7109375,
+      "learning_rate": 2e-05,
+      "loss": 0.5665,
+      "step": 18
+    },
+    {
+      "epoch": 1.0564334085778782,
+      "grad_norm": 2.484375,
+      "learning_rate": 2e-05,
+      "loss": 0.4544,
+      "step": 19
+    },
+    {
+      "epoch": 1.1128668171557563,
+      "grad_norm": 6.1875,
+      "learning_rate": 2e-05,
+      "loss": 0.4602,
+      "step": 20
+    },
+    {
+      "epoch": 1.1693002257336342,
+      "grad_norm": 54.0,
+      "learning_rate": 2e-05,
+      "loss": 0.5028,
+      "step": 21
+    },
+    {
+      "epoch": 1.2257336343115124,
+      "grad_norm": 6.34375,
+      "learning_rate": 2e-05,
+      "loss": 0.5169,
+      "step": 22
+    },
+    {
+      "epoch": 1.2821670428893905,
+      "grad_norm": 3.421875,
+      "learning_rate": 2e-05,
+      "loss": 0.465,
+      "step": 23
+    },
+    {
+      "epoch": 1.3386004514672687,
+      "grad_norm": 2.578125,
+      "learning_rate": 2e-05,
+      "loss": 0.436,
+      "step": 24
+    },
+    {
+      "epoch": 1.3950338600451468,
+      "grad_norm": 2.4375,
+      "learning_rate": 2e-05,
+      "loss": 0.4245,
+      "step": 25
+    },
+    {
+      "epoch": 1.4514672686230248,
+      "grad_norm": 1.8359375,
+      "learning_rate": 2e-05,
+      "loss": 0.4177,
+      "step": 26
+    },
+    {
+      "epoch": 1.507900677200903,
+      "grad_norm": 2.03125,
+      "learning_rate": 2e-05,
+      "loss": 0.4641,
+      "step": 27
+    },
+    {
+      "epoch": 1.564334085778781,
+      "grad_norm": 9.9375,
+      "learning_rate": 2e-05,
+      "loss": 0.4754,
+      "step": 28
+    },
+    {
+      "epoch": 1.620767494356659,
+      "grad_norm": 3.140625,
+      "learning_rate": 2e-05,
+      "loss": 0.393,
+      "step": 29
+    },
+    {
+      "epoch": 1.6772009029345374,
+      "grad_norm": 3.078125,
+      "learning_rate": 2e-05,
+      "loss": 0.4413,
+      "step": 30
+    },
+    {
+      "epoch": 1.7336343115124153,
+      "grad_norm": 2.015625,
+      "learning_rate": 2e-05,
+      "loss": 0.4375,
+      "step": 31
+    },
+    {
+      "epoch": 1.7900677200902935,
+      "grad_norm": 2.578125,
+      "learning_rate": 2e-05,
+      "loss": 0.4158,
+      "step": 32
+    },
+    {
+      "epoch": 1.8465011286681716,
+      "grad_norm": 1.828125,
+      "learning_rate": 2e-05,
+      "loss": 0.4339,
+      "step": 33
+    },
+    {
+      "epoch": 1.9029345372460496,
+      "grad_norm": 2.53125,
+      "learning_rate": 2e-05,
+      "loss": 0.443,
+      "step": 34
+    },
+    {
+      "epoch": 1.9029345372460496,
+      "eval_loss": 0.5419170260429382,
+      "eval_runtime": 30.2115,
+      "eval_samples_per_second": 10.493,
+      "eval_steps_per_second": 2.648,
+      "step": 34
+    },
+    {
+      "epoch": 1.959367945823928,
+      "grad_norm": 6.5,
+      "learning_rate": 2e-05,
+      "loss": 0.5505,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.609375,
+      "learning_rate": 2e-05,
+      "loss": 0.4309,
+      "step": 36
+    },
+    {
+      "epoch": 2.056433408577878,
+      "grad_norm": 2.21875,
+      "learning_rate": 2e-05,
+      "loss": 0.3024,
+      "step": 37
+    },
+    {
+      "epoch": 2.1128668171557563,
+      "grad_norm": 2.671875,
+      "learning_rate": 2e-05,
+      "loss": 0.3202,
+      "step": 38
+    },
+    {
+      "epoch": 2.1693002257336342,
+      "grad_norm": 2.1875,
+      "learning_rate": 2e-05,
+      "loss": 0.2802,
+      "step": 39
+    },
+    {
+      "epoch": 2.2257336343115126,
+      "grad_norm": 2.609375,
+      "learning_rate": 2e-05,
+      "loss": 0.2773,
+      "step": 40
+    },
+    {
+      "epoch": 2.2821670428893905,
+      "grad_norm": 14.0625,
+      "learning_rate": 2e-05,
+      "loss": 0.4582,
+      "step": 41
+    },
+    {
+      "epoch": 2.3386004514672685,
+      "grad_norm": 2.84375,
+      "learning_rate": 2e-05,
+      "loss": 0.2532,
+      "step": 42
+    },
+    {
+      "epoch": 2.395033860045147,
+      "grad_norm": 4.4375,
+      "learning_rate": 2e-05,
+      "loss": 0.2717,
+      "step": 43
+    },
+    {
+      "epoch": 2.4514672686230248,
+      "grad_norm": 2.671875,
+      "learning_rate": 2e-05,
+      "loss": 0.2863,
+      "step": 44
+    },
+    {
+      "epoch": 2.5079006772009027,
+      "grad_norm": 7.71875,
+      "learning_rate": 2e-05,
+      "loss": 0.2966,
+      "step": 45
+    },
+    {
+      "epoch": 2.564334085778781,
+      "grad_norm": 13.5625,
+      "learning_rate": 2e-05,
+      "loss": 0.3298,
+      "step": 46
+    },
+    {
+      "epoch": 2.620767494356659,
+      "grad_norm": 62.5,
+      "learning_rate": 2e-05,
+      "loss": 0.3529,
+      "step": 47
+    },
+    {
+      "epoch": 2.6772009029345374,
+      "grad_norm": 9.625,
+      "learning_rate": 2e-05,
+      "loss": 0.2862,
+      "step": 48
+    },
+    {
+      "epoch": 2.7336343115124153,
+      "grad_norm": 5.0,
+      "learning_rate": 2e-05,
+      "loss": 0.272,
+      "step": 49
+    },
+    {
+      "epoch": 2.7900677200902937,
+      "grad_norm": 12.0625,
+      "learning_rate": 2e-05,
+      "loss": 0.3045,
+      "step": 50
+    },
+    {
+      "epoch": 2.8465011286681716,
+      "grad_norm": 4.0625,
+      "learning_rate": 2e-05,
+      "loss": 0.3117,
+      "step": 51
+    },
+    {
+      "epoch": 2.8465011286681716,
+      "eval_loss": 0.5844628214836121,
+      "eval_runtime": 29.2665,
+      "eval_samples_per_second": 10.832,
+      "eval_steps_per_second": 2.734,
+      "step": 51
+    },
+    {
+      "epoch": 2.9029345372460496,
+      "grad_norm": 2.546875,
+      "learning_rate": 2e-05,
+      "loss": 0.2715,
+      "step": 52
+    },
+    {
+      "epoch": 2.959367945823928,
+      "grad_norm": 4.09375,
+      "learning_rate": 2e-05,
+      "loss": 0.309,
+      "step": 53
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.25,
+      "learning_rate": 2e-05,
+      "loss": 0.2786,
+      "step": 54
+    },
+    {
+      "epoch": 3.056433408577878,
+      "grad_norm": 12.375,
+      "learning_rate": 2e-05,
+      "loss": 0.2069,
+      "step": 55
+    },
+    {
+      "epoch": 3.1128668171557563,
+      "grad_norm": 9.4375,
+      "learning_rate": 2e-05,
+      "loss": 0.2126,
+      "step": 56
+    },
+    {
+      "epoch": 3.1693002257336342,
+      "grad_norm": 4.78125,
+      "learning_rate": 2e-05,
+      "loss": 0.1945,
+      "step": 57
+    },
+    {
+      "epoch": 3.2257336343115126,
+      "grad_norm": 2.171875,
+      "learning_rate": 2e-05,
+      "loss": 0.1792,
+      "step": 58
+    },
+    {
+      "epoch": 3.2821670428893905,
+      "grad_norm": 3.21875,
+      "learning_rate": 2e-05,
+      "loss": 0.1815,
+      "step": 59
+    },
+    {
+      "epoch": 3.3386004514672685,
+      "grad_norm": 11.5,
+      "learning_rate": 2e-05,
+      "loss": 0.2217,
+      "step": 60
+    },
+    {
+      "epoch": 3.395033860045147,
+      "grad_norm": 19.5,
+      "learning_rate": 2e-05,
+      "loss": 0.2213,
+      "step": 61
+    },
+    {
+      "epoch": 3.4514672686230248,
+      "grad_norm": 6.15625,
+      "learning_rate": 2e-05,
+      "loss": 0.1815,
+      "step": 62
+    },
+    {
+      "epoch": 3.5079006772009027,
+      "grad_norm": 2.796875,
+      "learning_rate": 2e-05,
+      "loss": 0.1841,
+      "step": 63
+    },
+    {
+      "epoch": 3.564334085778781,
+      "grad_norm": 2.890625,
+      "learning_rate": 2e-05,
+      "loss": 0.1621,
+      "step": 64
+    },
+    {
+      "epoch": 3.620767494356659,
+      "grad_norm": 173.0,
+      "learning_rate": 2e-05,
+      "loss": 0.2054,
+      "step": 65
+    },
+    {
+      "epoch": 3.6772009029345374,
+      "grad_norm": 3.078125,
+      "learning_rate": 2e-05,
+      "loss": 0.1609,
+      "step": 66
+    },
+    {
+      "epoch": 3.7336343115124153,
+      "grad_norm": 2.015625,
+      "learning_rate": 2e-05,
+      "loss": 0.1758,
+      "step": 67
+    },
+    {
+      "epoch": 3.7900677200902937,
+      "grad_norm": 2.46875,
+      "learning_rate": 2e-05,
+      "loss": 0.1713,
+      "step": 68
+    },
+    {
+      "epoch": 3.7900677200902937,
+      "eval_loss": 0.6350371837615967,
+      "eval_runtime": 29.151,
+      "eval_samples_per_second": 10.874,
+      "eval_steps_per_second": 2.744,
+      "step": 68
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 85,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 17,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1402345104898785e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-68/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929076445961b02ebf8e3251be1d97b8181bc875b7535b103152b1ad82d9d386
+size 6904