Training in progress, step 123, checkpoint

checkpoint-123/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-123/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-123/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-123/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1cf1486402edebd636bcc8dc9b00b42b99be0ab42e72d6607cb906f0eb628f
+size 4943162336

checkpoint-123/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8f1e9ff6152bcac3885bffa18b3633190b5a2565517d7a3c6b8c93b8c927e5
+size 4999819336

checkpoint-123/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c620508af5e78bcd9bbdfd506fb3750ea17d67b4b0e68734f01e5c53bd4bdb6
+size 4540516344

checkpoint-123/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-123/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f39233625bea816ff1a5c435a9c4b6d23a4189c00701eedba3ce5f506535e4
+size 15492462246

checkpoint-123/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812567333fb32e55661e6686f4b3654dfbe566e1b855763b28d24d828628d1fb
+size 14308

checkpoint-123/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f9837e9eec9737ea6da3bd9c054e53411a3ff30dc9ab5693c7e5be8bb4ca6e
+size 1064

checkpoint-123/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-123/tokenizer.model

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

checkpoint-123/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-123/trainer_state.json

@@ -0,0 +1,927 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9375,
+  "eval_steps": 41,
+  "global_step": 123,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02403846153846154,
+      "grad_norm": 46.75,
+      "learning_rate": 2e-05,
+      "loss": 1.6475,
+      "step": 1
+    },
+    {
+      "epoch": 0.02403846153846154,
+      "eval_loss": 1.52475106716156,
+      "eval_runtime": 69.3846,
+      "eval_samples_per_second": 10.636,
+      "eval_steps_per_second": 2.666,
+      "step": 1
+    },
+    {
+      "epoch": 0.04807692307692308,
+      "grad_norm": 30.5,
+      "learning_rate": 2e-05,
+      "loss": 1.4745,
+      "step": 2
+    },
+    {
+      "epoch": 0.07211538461538461,
+      "grad_norm": 26.875,
+      "learning_rate": 2e-05,
+      "loss": 1.2137,
+      "step": 3
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 9.5625,
+      "learning_rate": 2e-05,
+      "loss": 1.0085,
+      "step": 4
+    },
+    {
+      "epoch": 0.1201923076923077,
+      "grad_norm": 5.71875,
+      "learning_rate": 2e-05,
+      "loss": 0.8997,
+      "step": 5
+    },
+    {
+      "epoch": 0.14423076923076922,
+      "grad_norm": 9.0625,
+      "learning_rate": 2e-05,
+      "loss": 0.9036,
+      "step": 6
+    },
+    {
+      "epoch": 0.16826923076923078,
+      "grad_norm": 3.703125,
+      "learning_rate": 2e-05,
+      "loss": 0.8543,
+      "step": 7
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 3.984375,
+      "learning_rate": 2e-05,
+      "loss": 0.7644,
+      "step": 8
+    },
+    {
+      "epoch": 0.21634615384615385,
+      "grad_norm": 5.625,
+      "learning_rate": 2e-05,
+      "loss": 0.7612,
+      "step": 9
+    },
+    {
+      "epoch": 0.2403846153846154,
+      "grad_norm": 16.625,
+      "learning_rate": 2e-05,
+      "loss": 0.7604,
+      "step": 10
+    },
+    {
+      "epoch": 0.2644230769230769,
+      "grad_norm": 4.1875,
+      "learning_rate": 2e-05,
+      "loss": 0.7401,
+      "step": 11
+    },
+    {
+      "epoch": 0.28846153846153844,
+      "grad_norm": 3.65625,
+      "learning_rate": 2e-05,
+      "loss": 0.7323,
+      "step": 12
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 3.015625,
+      "learning_rate": 2e-05,
+      "loss": 0.7352,
+      "step": 13
+    },
+    {
+      "epoch": 0.33653846153846156,
+      "grad_norm": 4.875,
+      "learning_rate": 2e-05,
+      "loss": 0.6942,
+      "step": 14
+    },
+    {
+      "epoch": 0.3605769230769231,
+      "grad_norm": 2.21875,
+      "learning_rate": 2e-05,
+      "loss": 0.6315,
+      "step": 15
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 4.21875,
+      "learning_rate": 2e-05,
+      "loss": 0.6571,
+      "step": 16
+    },
+    {
+      "epoch": 0.40865384615384615,
+      "grad_norm": 19.125,
+      "learning_rate": 2e-05,
+      "loss": 0.6898,
+      "step": 17
+    },
+    {
+      "epoch": 0.4326923076923077,
+      "grad_norm": 2.703125,
+      "learning_rate": 2e-05,
+      "loss": 0.7134,
+      "step": 18
+    },
+    {
+      "epoch": 0.4567307692307692,
+      "grad_norm": 1.9140625,
+      "learning_rate": 2e-05,
+      "loss": 0.6883,
+      "step": 19
+    },
+    {
+      "epoch": 0.4807692307692308,
+      "grad_norm": 4.875,
+      "learning_rate": 2e-05,
+      "loss": 0.6097,
+      "step": 20
+    },
+    {
+      "epoch": 0.5048076923076923,
+      "grad_norm": 2.6875,
+      "learning_rate": 2e-05,
+      "loss": 0.6761,
+      "step": 21
+    },
+    {
+      "epoch": 0.5288461538461539,
+      "grad_norm": 2.03125,
+      "learning_rate": 2e-05,
+      "loss": 0.6996,
+      "step": 22
+    },
+    {
+      "epoch": 0.5528846153846154,
+      "grad_norm": 2.09375,
+      "learning_rate": 2e-05,
+      "loss": 0.623,
+      "step": 23
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 1.9296875,
+      "learning_rate": 2e-05,
+      "loss": 0.665,
+      "step": 24
+    },
+    {
+      "epoch": 0.6009615384615384,
+      "grad_norm": 13.75,
+      "learning_rate": 2e-05,
+      "loss": 0.6474,
+      "step": 25
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 2.640625,
+      "learning_rate": 2e-05,
+      "loss": 0.6863,
+      "step": 26
+    },
+    {
+      "epoch": 0.6490384615384616,
+      "grad_norm": 2.625,
+      "learning_rate": 2e-05,
+      "loss": 0.6728,
+      "step": 27
+    },
+    {
+      "epoch": 0.6730769230769231,
+      "grad_norm": 11.5,
+      "learning_rate": 2e-05,
+      "loss": 0.7127,
+      "step": 28
+    },
+    {
+      "epoch": 0.6971153846153846,
+      "grad_norm": 3.140625,
+      "learning_rate": 2e-05,
+      "loss": 0.6501,
+      "step": 29
+    },
+    {
+      "epoch": 0.7211538461538461,
+      "grad_norm": 1.84375,
+      "learning_rate": 2e-05,
+      "loss": 0.6633,
+      "step": 30
+    },
+    {
+      "epoch": 0.7451923076923077,
+      "grad_norm": 1.953125,
+      "learning_rate": 2e-05,
+      "loss": 0.5909,
+      "step": 31
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.5809,
+      "step": 32
+    },
+    {
+      "epoch": 0.7932692307692307,
+      "grad_norm": 1.671875,
+      "learning_rate": 2e-05,
+      "loss": 0.5731,
+      "step": 33
+    },
+    {
+      "epoch": 0.8173076923076923,
+      "grad_norm": 13.3125,
+      "learning_rate": 2e-05,
+      "loss": 0.659,
+      "step": 34
+    },
+    {
+      "epoch": 0.8413461538461539,
+      "grad_norm": 3.5,
+      "learning_rate": 2e-05,
+      "loss": 0.5966,
+      "step": 35
+    },
+    {
+      "epoch": 0.8653846153846154,
+      "grad_norm": 2.015625,
+      "learning_rate": 2e-05,
+      "loss": 0.5799,
+      "step": 36
+    },
+    {
+      "epoch": 0.8894230769230769,
+      "grad_norm": 2.28125,
+      "learning_rate": 2e-05,
+      "loss": 0.6153,
+      "step": 37
+    },
+    {
+      "epoch": 0.9134615384615384,
+      "grad_norm": 2.046875,
+      "learning_rate": 2e-05,
+      "loss": 0.6436,
+      "step": 38
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 1.953125,
+      "learning_rate": 2e-05,
+      "loss": 0.5768,
+      "step": 39
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 1.84375,
+      "learning_rate": 2e-05,
+      "loss": 0.6041,
+      "step": 40
+    },
+    {
+      "epoch": 0.9855769230769231,
+      "grad_norm": 2.015625,
+      "learning_rate": 2e-05,
+      "loss": 0.6333,
+      "step": 41
+    },
+    {
+      "epoch": 0.9855769230769231,
+      "eval_loss": 0.585032045841217,
+      "eval_runtime": 69.4374,
+      "eval_samples_per_second": 10.628,
+      "eval_steps_per_second": 2.664,
+      "step": 41
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9375,
+      "learning_rate": 2e-05,
+      "loss": 0.6087,
+      "step": 42
+    },
+    {
+      "epoch": 1.0240384615384615,
+      "grad_norm": 2.9375,
+      "learning_rate": 2e-05,
+      "loss": 0.5003,
+      "step": 43
+    },
+    {
+      "epoch": 1.0480769230769231,
+      "grad_norm": 1.9765625,
+      "learning_rate": 2e-05,
+      "loss": 0.471,
+      "step": 44
+    },
+    {
+      "epoch": 1.0721153846153846,
+      "grad_norm": 22.375,
+      "learning_rate": 2e-05,
+      "loss": 0.4576,
+      "step": 45
+    },
+    {
+      "epoch": 1.0961538461538463,
+      "grad_norm": 5.5,
+      "learning_rate": 2e-05,
+      "loss": 0.5028,
+      "step": 46
+    },
+    {
+      "epoch": 1.1201923076923077,
+      "grad_norm": 4.03125,
+      "learning_rate": 2e-05,
+      "loss": 0.4581,
+      "step": 47
+    },
+    {
+      "epoch": 1.1442307692307692,
+      "grad_norm": 14.125,
+      "learning_rate": 2e-05,
+      "loss": 0.4503,
+      "step": 48
+    },
+    {
+      "epoch": 1.1682692307692308,
+      "grad_norm": 2.96875,
+      "learning_rate": 2e-05,
+      "loss": 0.4328,
+      "step": 49
+    },
+    {
+      "epoch": 1.1923076923076923,
+      "grad_norm": 16.875,
+      "learning_rate": 2e-05,
+      "loss": 0.5451,
+      "step": 50
+    },
+    {
+      "epoch": 1.2163461538461537,
+      "grad_norm": 2.40625,
+      "learning_rate": 2e-05,
+      "loss": 0.424,
+      "step": 51
+    },
+    {
+      "epoch": 1.2403846153846154,
+      "grad_norm": 1.765625,
+      "learning_rate": 2e-05,
+      "loss": 0.4696,
+      "step": 52
+    },
+    {
+      "epoch": 1.2644230769230769,
+      "grad_norm": 2.765625,
+      "learning_rate": 2e-05,
+      "loss": 0.5376,
+      "step": 53
+    },
+    {
+      "epoch": 1.2884615384615383,
+      "grad_norm": 2.203125,
+      "learning_rate": 2e-05,
+      "loss": 0.4419,
+      "step": 54
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 3.6875,
+      "learning_rate": 2e-05,
+      "loss": 0.4742,
+      "step": 55
+    },
+    {
+      "epoch": 1.3365384615384617,
+      "grad_norm": 2.0625,
+      "learning_rate": 2e-05,
+      "loss": 0.4412,
+      "step": 56
+    },
+    {
+      "epoch": 1.3605769230769231,
+      "grad_norm": 1.9296875,
+      "learning_rate": 2e-05,
+      "loss": 0.432,
+      "step": 57
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 1.75,
+      "learning_rate": 2e-05,
+      "loss": 0.4197,
+      "step": 58
+    },
+    {
+      "epoch": 1.4086538461538463,
+      "grad_norm": 1.65625,
+      "learning_rate": 2e-05,
+      "loss": 0.4518,
+      "step": 59
+    },
+    {
+      "epoch": 1.4326923076923077,
+      "grad_norm": 1.96875,
+      "learning_rate": 2e-05,
+      "loss": 0.3878,
+      "step": 60
+    },
+    {
+      "epoch": 1.4567307692307692,
+      "grad_norm": 2.265625,
+      "learning_rate": 2e-05,
+      "loss": 0.414,
+      "step": 61
+    },
+    {
+      "epoch": 1.4807692307692308,
+      "grad_norm": 1.9765625,
+      "learning_rate": 2e-05,
+      "loss": 0.3948,
+      "step": 62
+    },
+    {
+      "epoch": 1.5048076923076923,
+      "grad_norm": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.4392,
+      "step": 63
+    },
+    {
+      "epoch": 1.5288461538461537,
+      "grad_norm": 1.5859375,
+      "learning_rate": 2e-05,
+      "loss": 0.4143,
+      "step": 64
+    },
+    {
+      "epoch": 1.5528846153846154,
+      "grad_norm": 1.796875,
+      "learning_rate": 2e-05,
+      "loss": 0.4347,
+      "step": 65
+    },
+    {
+      "epoch": 1.5769230769230769,
+      "grad_norm": 34.0,
+      "learning_rate": 2e-05,
+      "loss": 0.4579,
+      "step": 66
+    },
+    {
+      "epoch": 1.6009615384615383,
+      "grad_norm": 1.9609375,
+      "learning_rate": 2e-05,
+      "loss": 0.4311,
+      "step": 67
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 26.625,
+      "learning_rate": 2e-05,
+      "loss": 0.4307,
+      "step": 68
+    },
+    {
+      "epoch": 1.6490384615384617,
+      "grad_norm": 40.25,
+      "learning_rate": 2e-05,
+      "loss": 0.3755,
+      "step": 69
+    },
+    {
+      "epoch": 1.6730769230769231,
+      "grad_norm": 47.0,
+      "learning_rate": 2e-05,
+      "loss": 0.504,
+      "step": 70
+    },
+    {
+      "epoch": 1.6971153846153846,
+      "grad_norm": 4.9375,
+      "learning_rate": 2e-05,
+      "loss": 0.4272,
+      "step": 71
+    },
+    {
+      "epoch": 1.7211538461538463,
+      "grad_norm": 2.796875,
+      "learning_rate": 2e-05,
+      "loss": 0.4249,
+      "step": 72
+    },
+    {
+      "epoch": 1.7451923076923077,
+      "grad_norm": 3.359375,
+      "learning_rate": 2e-05,
+      "loss": 0.5176,
+      "step": 73
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 3.1875,
+      "learning_rate": 2e-05,
+      "loss": 0.4455,
+      "step": 74
+    },
+    {
+      "epoch": 1.7932692307692308,
+      "grad_norm": 2.46875,
+      "learning_rate": 2e-05,
+      "loss": 0.4212,
+      "step": 75
+    },
+    {
+      "epoch": 1.8173076923076923,
+      "grad_norm": 3.234375,
+      "learning_rate": 2e-05,
+      "loss": 0.4438,
+      "step": 76
+    },
+    {
+      "epoch": 1.8413461538461537,
+      "grad_norm": 7.59375,
+      "learning_rate": 2e-05,
+      "loss": 0.4491,
+      "step": 77
+    },
+    {
+      "epoch": 1.8653846153846154,
+      "grad_norm": 3.203125,
+      "learning_rate": 2e-05,
+      "loss": 0.4338,
+      "step": 78
+    },
+    {
+      "epoch": 1.8894230769230769,
+      "grad_norm": 13.375,
+      "learning_rate": 2e-05,
+      "loss": 0.4036,
+      "step": 79
+    },
+    {
+      "epoch": 1.9134615384615383,
+      "grad_norm": 5.0625,
+      "learning_rate": 2e-05,
+      "loss": 0.4289,
+      "step": 80
+    },
+    {
+      "epoch": 1.9375,
+      "grad_norm": 13.0,
+      "learning_rate": 2e-05,
+      "loss": 0.4295,
+      "step": 81
+    },
+    {
+      "epoch": 1.9615384615384617,
+      "grad_norm": 14.8125,
+      "learning_rate": 2e-05,
+      "loss": 0.4419,
+      "step": 82
+    },
+    {
+      "epoch": 1.9615384615384617,
+      "eval_loss": 0.5703663229942322,
+      "eval_runtime": 69.4191,
+      "eval_samples_per_second": 10.631,
+      "eval_steps_per_second": 2.665,
+      "step": 82
+    },
+    {
+      "epoch": 1.9855769230769231,
+      "grad_norm": 2.28125,
+      "learning_rate": 2e-05,
+      "loss": 0.4061,
+      "step": 83
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 14.0,
+      "learning_rate": 2e-05,
+      "loss": 0.4884,
+      "step": 84
+    },
+    {
+      "epoch": 2.0240384615384617,
+      "grad_norm": 3.4375,
+      "learning_rate": 2e-05,
+      "loss": 0.3164,
+      "step": 85
+    },
+    {
+      "epoch": 2.048076923076923,
+      "grad_norm": 3.375,
+      "learning_rate": 2e-05,
+      "loss": 0.3181,
+      "step": 86
+    },
+    {
+      "epoch": 2.0721153846153846,
+      "grad_norm": 106.0,
+      "learning_rate": 2e-05,
+      "loss": 0.3212,
+      "step": 87
+    },
+    {
+      "epoch": 2.0961538461538463,
+      "grad_norm": 8.625,
+      "learning_rate": 2e-05,
+      "loss": 0.3233,
+      "step": 88
+    },
+    {
+      "epoch": 2.1201923076923075,
+      "grad_norm": 6.9375,
+      "learning_rate": 2e-05,
+      "loss": 0.3091,
+      "step": 89
+    },
+    {
+      "epoch": 2.144230769230769,
+      "grad_norm": 2.5,
+      "learning_rate": 2e-05,
+      "loss": 0.2988,
+      "step": 90
+    },
+    {
+      "epoch": 2.168269230769231,
+      "grad_norm": 3.03125,
+      "learning_rate": 2e-05,
+      "loss": 0.3071,
+      "step": 91
+    },
+    {
+      "epoch": 2.1923076923076925,
+      "grad_norm": 2.765625,
+      "learning_rate": 2e-05,
+      "loss": 0.2747,
+      "step": 92
+    },
+    {
+      "epoch": 2.2163461538461537,
+      "grad_norm": 2.359375,
+      "learning_rate": 2e-05,
+      "loss": 0.2569,
+      "step": 93
+    },
+    {
+      "epoch": 2.2403846153846154,
+      "grad_norm": 3.75,
+      "learning_rate": 2e-05,
+      "loss": 0.304,
+      "step": 94
+    },
+    {
+      "epoch": 2.264423076923077,
+      "grad_norm": 2.796875,
+      "learning_rate": 2e-05,
+      "loss": 0.2659,
+      "step": 95
+    },
+    {
+      "epoch": 2.2884615384615383,
+      "grad_norm": 3.796875,
+      "learning_rate": 2e-05,
+      "loss": 0.293,
+      "step": 96
+    },
+    {
+      "epoch": 2.3125,
+      "grad_norm": 2.25,
+      "learning_rate": 2e-05,
+      "loss": 0.2865,
+      "step": 97
+    },
+    {
+      "epoch": 2.3365384615384617,
+      "grad_norm": 10.1875,
+      "learning_rate": 2e-05,
+      "loss": 0.2435,
+      "step": 98
+    },
+    {
+      "epoch": 2.360576923076923,
+      "grad_norm": 6.875,
+      "learning_rate": 2e-05,
+      "loss": 0.4193,
+      "step": 99
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": 2.609375,
+      "learning_rate": 2e-05,
+      "loss": 0.2777,
+      "step": 100
+    },
+    {
+      "epoch": 2.4086538461538463,
+      "grad_norm": 2.546875,
+      "learning_rate": 2e-05,
+      "loss": 0.3096,
+      "step": 101
+    },
+    {
+      "epoch": 2.4326923076923075,
+      "grad_norm": 23.375,
+      "learning_rate": 2e-05,
+      "loss": 0.4031,
+      "step": 102
+    },
+    {
+      "epoch": 2.456730769230769,
+      "grad_norm": 74.5,
+      "learning_rate": 2e-05,
+      "loss": 0.3268,
+      "step": 103
+    },
+    {
+      "epoch": 2.480769230769231,
+      "grad_norm": 7.40625,
+      "learning_rate": 2e-05,
+      "loss": 0.296,
+      "step": 104
+    },
+    {
+      "epoch": 2.5048076923076925,
+      "grad_norm": 4.15625,
+      "learning_rate": 2e-05,
+      "loss": 0.3354,
+      "step": 105
+    },
+    {
+      "epoch": 2.5288461538461537,
+      "grad_norm": 11.0625,
+      "learning_rate": 2e-05,
+      "loss": 0.3167,
+      "step": 106
+    },
+    {
+      "epoch": 2.5528846153846154,
+      "grad_norm": 5.21875,
+      "learning_rate": 2e-05,
+      "loss": 0.2898,
+      "step": 107
+    },
+    {
+      "epoch": 2.5769230769230766,
+      "grad_norm": 2.8125,
+      "learning_rate": 2e-05,
+      "loss": 0.331,
+      "step": 108
+    },
+    {
+      "epoch": 2.6009615384615383,
+      "grad_norm": 1.84375,
+      "learning_rate": 2e-05,
+      "loss": 0.27,
+      "step": 109
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 2.40625,
+      "learning_rate": 2e-05,
+      "loss": 0.2685,
+      "step": 110
+    },
+    {
+      "epoch": 2.6490384615384617,
+      "grad_norm": 2.25,
+      "learning_rate": 2e-05,
+      "loss": 0.2999,
+      "step": 111
+    },
+    {
+      "epoch": 2.6730769230769234,
+      "grad_norm": 2.34375,
+      "learning_rate": 2e-05,
+      "loss": 0.3208,
+      "step": 112
+    },
+    {
+      "epoch": 2.6971153846153846,
+      "grad_norm": 3.078125,
+      "learning_rate": 2e-05,
+      "loss": 0.2631,
+      "step": 113
+    },
+    {
+      "epoch": 2.7211538461538463,
+      "grad_norm": 14.25,
+      "learning_rate": 2e-05,
+      "loss": 0.2943,
+      "step": 114
+    },
+    {
+      "epoch": 2.7451923076923075,
+      "grad_norm": 4.0,
+      "learning_rate": 2e-05,
+      "loss": 0.2793,
+      "step": 115
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 2.390625,
+      "learning_rate": 2e-05,
+      "loss": 0.3044,
+      "step": 116
+    },
+    {
+      "epoch": 2.793269230769231,
+      "grad_norm": 26.75,
+      "learning_rate": 2e-05,
+      "loss": 0.3307,
+      "step": 117
+    },
+    {
+      "epoch": 2.8173076923076925,
+      "grad_norm": 23.0,
+      "learning_rate": 2e-05,
+      "loss": 0.3476,
+      "step": 118
+    },
+    {
+      "epoch": 2.8413461538461537,
+      "grad_norm": 8.1875,
+      "learning_rate": 2e-05,
+      "loss": 0.3665,
+      "step": 119
+    },
+    {
+      "epoch": 2.8653846153846154,
+      "grad_norm": 3.84375,
+      "learning_rate": 2e-05,
+      "loss": 0.3058,
+      "step": 120
+    },
+    {
+      "epoch": 2.8894230769230766,
+      "grad_norm": 22.0,
+      "learning_rate": 2e-05,
+      "loss": 0.294,
+      "step": 121
+    },
+    {
+      "epoch": 2.9134615384615383,
+      "grad_norm": 3.84375,
+      "learning_rate": 2e-05,
+      "loss": 0.3188,
+      "step": 122
+    },
+    {
+      "epoch": 2.9375,
+      "grad_norm": 4.15625,
+      "learning_rate": 2e-05,
+      "loss": 0.2823,
+      "step": 123
+    },
+    {
+      "epoch": 2.9375,
+      "eval_loss": 0.5763112902641296,
+      "eval_runtime": 69.4422,
+      "eval_samples_per_second": 10.628,
+      "eval_steps_per_second": 2.664,
+      "step": 123
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 205,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 41,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.894188839301284e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-123/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc7c73496aa04ea8ae76ab74a6554e8d50305c826e2354d47fa5eab94079e980
+size 6904