Upload model

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "output_m_01IR-10_train_2e-11_3_26/checkpoint-10",
+  "architectures": [
+    "StableLmForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "stablelm",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100257,
+  "partial_rotary_factor": 0.25,
+  "qk_layernorm": false,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "use_parallel_residual": false,
+  "use_qkv_bias": true,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "do_sample": true,
+  "eos_token_id": 100257,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00c26338afb8e94f0374a800ae0f0581dd3fdece8fe14650ed6bfc9a18f1c12
+size 4984037184

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1bec6af3762088adef39551c5aedf38e4cd5870caa6b9aa84e3c8974b8435db
+size 1594062688

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_size": 6578061312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.bias": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a148f052d360ce6169fb3c442ff74ba55793f102958f744eda7c9287eb92353a
+size 411849948

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9233fd73340c857eb5d9ed7d538f3cda2965de7ca74cd437a6d7478e4e1c63
+size 1064

special_tokens_map.json

@@ -0,0 +1,59 @@
+{
+  "additional_special_tokens": [
+    "<|reg_extra|>",
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<gh_stars>",
+    "<filename>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<|endofprompt|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|pause|>",
+    "<|reg0|>",
+    "<|reg1|>",
+    "<|reg2|>",
+    "<|reg3|>",
+    "<|reg4|>",
+    "<|reg5|>",
+    "<|reg6|>",
+    "<|reg7|>",
+    "<|extra0|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,319 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|reg_extra|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<|pause|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<|reg0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "<|reg1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<|reg2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "<|reg3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|reg4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|reg5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|reg6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|reg7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|extra0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|reg_extra|>",
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|fim_pad|>",
+    "<gh_stars>",
+    "<filename>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>",
+    "<|endofprompt|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|pause|>",
+    "<|reg0|>",
+    "<|reg1|>",
+    "<|reg2|>",
+    "<|reg3|>",
+    "<|reg4|>",
+    "<|reg5|>",
+    "<|reg6|>",
+    "<|reg7|>",
+    "<|extra0|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "max_length": 3896,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,1083 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.46345811051693403,
+  "eval_steps": 202,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0030897207367795603,
+      "grad_norm": 122071.1171875,
+      "learning_rate": 4.0000000000000004e-11,
+      "loss": 28.8142,
+      "step": 1
+    },
+    {
+      "epoch": 0.006179441473559121,
+      "grad_norm": 119214.984375,
+      "learning_rate": 8.000000000000001e-11,
+      "loss": 28.2909,
+      "step": 2
+    },
+    {
+      "epoch": 0.009269162210338681,
+      "grad_norm": 126446.515625,
+      "learning_rate": 1.2e-10,
+      "loss": 27.4632,
+      "step": 3
+    },
+    {
+      "epoch": 0.012358882947118241,
+      "grad_norm": 113183.5078125,
+      "learning_rate": 1.6000000000000002e-10,
+      "loss": 29.2478,
+      "step": 4
+    },
+    {
+      "epoch": 0.015448603683897801,
+      "grad_norm": 122417.453125,
+      "learning_rate": 2e-10,
+      "loss": 27.6777,
+      "step": 5
+    },
+    {
+      "epoch": 0.018538324420677363,
+      "grad_norm": 122875.0234375,
+      "learning_rate": 1.9998728465660104e-10,
+      "loss": 26.864,
+      "step": 6
+    },
+    {
+      "epoch": 0.02162804515745692,
+      "grad_norm": 123327.859375,
+      "learning_rate": 1.9994914186000328e-10,
+      "loss": 27.4961,
+      "step": 7
+    },
+    {
+      "epoch": 0.024717765894236483,
+      "grad_norm": 125148.296875,
+      "learning_rate": 1.9988558131018187e-10,
+      "loss": 27.0758,
+      "step": 8
+    },
+    {
+      "epoch": 0.027807486631016044,
+      "grad_norm": 123805.0078125,
+      "learning_rate": 1.9979661917102113e-10,
+      "loss": 26.7955,
+      "step": 9
+    },
+    {
+      "epoch": 0.030897207367795602,
+      "grad_norm": 137252.546875,
+      "learning_rate": 1.996822780662041e-10,
+      "loss": 23.848,
+      "step": 10
+    },
+    {
+      "epoch": 0.03398692810457516,
+      "grad_norm": 123848.6953125,
+      "learning_rate": 1.99542587073459e-10,
+      "loss": 26.2061,
+      "step": 11
+    },
+    {
+      "epoch": 0.037076648841354726,
+      "grad_norm": 103722.9296875,
+      "learning_rate": 1.9937758171716467e-10,
+      "loss": 30.3732,
+      "step": 12
+    },
+    {
+      "epoch": 0.040166369578134284,
+      "grad_norm": 132914.09375,
+      "learning_rate": 1.9918730395931647e-10,
+      "loss": 25.836,
+      "step": 13
+    },
+    {
+      "epoch": 0.04325609031491384,
+      "grad_norm": 122652.0546875,
+      "learning_rate": 1.9897180218885506e-10,
+      "loss": 26.7338,
+      "step": 14
+    },
+    {
+      "epoch": 0.04634581105169341,
+      "grad_norm": 125711.875,
+      "learning_rate": 1.9873113120936074e-10,
+      "loss": 27.9079,
+      "step": 15
+    },
+    {
+      "epoch": 0.049435531788472965,
+      "grad_norm": 131257.78125,
+      "learning_rate": 1.9846535222511647e-10,
+      "loss": 25.2777,
+      "step": 16
+    },
+    {
+      "epoch": 0.052525252525252523,
+      "grad_norm": 135439.875,
+      "learning_rate": 1.9817453282554334e-10,
+      "loss": 25.622,
+      "step": 17
+    },
+    {
+      "epoch": 0.05561497326203209,
+      "grad_norm": 112875.90625,
+      "learning_rate": 1.97858746968012e-10,
+      "loss": 28.8657,
+      "step": 18
+    },
+    {
+      "epoch": 0.05870469399881165,
+      "grad_norm": 124934.046875,
+      "learning_rate": 1.9751807495903485e-10,
+      "loss": 27.4469,
+      "step": 19
+    },
+    {
+      "epoch": 0.061794414735591205,
+      "grad_norm": 126672.046875,
+      "learning_rate": 1.9715260343384348e-10,
+      "loss": 26.0207,
+      "step": 20
+    },
+    {
+      "epoch": 0.06488413547237076,
+      "grad_norm": 121388.1953125,
+      "learning_rate": 1.9676242533435677e-10,
+      "loss": 28.2452,
+      "step": 21
+    },
+    {
+      "epoch": 0.06797385620915032,
+      "grad_norm": 126791.9921875,
+      "learning_rate": 1.963476398855452e-10,
+      "loss": 27.0343,
+      "step": 22
+    },
+    {
+      "epoch": 0.0710635769459299,
+      "grad_norm": 120207.7734375,
+      "learning_rate": 1.9590835257019716e-10,
+      "loss": 27.06,
+      "step": 23
+    },
+    {
+      "epoch": 0.07415329768270945,
+      "grad_norm": 119256.28125,
+      "learning_rate": 1.9544467510209388e-10,
+      "loss": 27.0009,
+      "step": 24
+    },
+    {
+      "epoch": 0.07724301841948901,
+      "grad_norm": 132457.265625,
+      "learning_rate": 1.9495672539760009e-10,
+      "loss": 26.5873,
+      "step": 25
+    },
+    {
+      "epoch": 0.08033273915626857,
+      "grad_norm": 130291.3515625,
+      "learning_rate": 1.9444462754567682e-10,
+      "loss": 27.6641,
+      "step": 26
+    },
+    {
+      "epoch": 0.08342245989304813,
+      "grad_norm": 122393.9375,
+      "learning_rate": 1.9390851177632496e-10,
+      "loss": 26.8649,
+      "step": 27
+    },
+    {
+      "epoch": 0.08651218062982768,
+      "grad_norm": 123576.078125,
+      "learning_rate": 1.9334851442746664e-10,
+      "loss": 28.0714,
+      "step": 28
+    },
+    {
+      "epoch": 0.08960190136660724,
+      "grad_norm": 121570.703125,
+      "learning_rate": 1.9276477791027375e-10,
+      "loss": 26.8387,
+      "step": 29
+    },
+    {
+      "epoch": 0.09269162210338681,
+      "grad_norm": 117390.9921875,
+      "learning_rate": 1.9215745067295168e-10,
+      "loss": 28.8172,
+      "step": 30
+    },
+    {
+      "epoch": 0.09578134284016637,
+      "grad_norm": 127661.9609375,
+      "learning_rate": 1.9152668716298797e-10,
+      "loss": 27.3977,
+      "step": 31
+    },
+    {
+      "epoch": 0.09887106357694593,
+      "grad_norm": 129576.4453125,
+      "learning_rate": 1.9087264778787533e-10,
+      "loss": 25.7966,
+      "step": 32
+    },
+    {
+      "epoch": 0.10196078431372549,
+      "grad_norm": 117011.7578125,
+      "learning_rate": 1.9019549887431877e-10,
+      "loss": 29.9255,
+      "step": 33
+    },
+    {
+      "epoch": 0.10505050505050505,
+      "grad_norm": 120770.2265625,
+      "learning_rate": 1.894954126259376e-10,
+      "loss": 27.4423,
+      "step": 34
+    },
+    {
+      "epoch": 0.1081402257872846,
+      "grad_norm": 118635.3671875,
+      "learning_rate": 1.8877256707947306e-10,
+      "loss": 29.0251,
+      "step": 35
+    },
+    {
+      "epoch": 0.11122994652406418,
+      "grad_norm": 122824.8203125,
+      "learning_rate": 1.88027146059512e-10,
+      "loss": 28.9256,
+      "step": 36
+    },
+    {
+      "epoch": 0.11431966726084374,
+      "grad_norm": 126411.421875,
+      "learning_rate": 1.872593391317394e-10,
+      "loss": 26.5279,
+      "step": 37
+    },
+    {
+      "epoch": 0.1174093879976233,
+      "grad_norm": 132717.421875,
+      "learning_rate": 1.8646934155473023e-10,
+      "loss": 24.6933,
+      "step": 38
+    },
+    {
+      "epoch": 0.12049910873440285,
+      "grad_norm": 121920.703125,
+      "learning_rate": 1.8565735423029405e-10,
+      "loss": 27.9129,
+      "step": 39
+    },
+    {
+      "epoch": 0.12358882947118241,
+      "grad_norm": 118110.3515625,
+      "learning_rate": 1.8482358365238414e-10,
+      "loss": 28.6163,
+      "step": 40
+    },
+    {
+      "epoch": 0.12667855020796198,
+      "grad_norm": 120299.3359375,
+      "learning_rate": 1.839682418545848e-10,
+      "loss": 28.5066,
+      "step": 41
+    },
+    {
+      "epoch": 0.12976827094474153,
+      "grad_norm": 140847.53125,
+      "learning_rate": 1.8309154635618964e-10,
+      "loss": 26.3515,
+      "step": 42
+    },
+    {
+      "epoch": 0.1328579916815211,
+      "grad_norm": 112302.9609375,
+      "learning_rate": 1.8219372010688515e-10,
+      "loss": 28.644,
+      "step": 43
+    },
+    {
+      "epoch": 0.13594771241830064,
+      "grad_norm": 123308.875,
+      "learning_rate": 1.8127499143005265e-10,
+      "loss": 27.6619,
+      "step": 44
+    },
+    {
+      "epoch": 0.13903743315508021,
+      "grad_norm": 125378.4921875,
+      "learning_rate": 1.8033559396470454e-10,
+      "loss": 26.452,
+      "step": 45
+    },
+    {
+      "epoch": 0.1421271538918598,
+      "grad_norm": 123326.15625,
+      "learning_rate": 1.7937576660606797e-10,
+      "loss": 26.3463,
+      "step": 46
+    },
+    {
+      "epoch": 0.14521687462863933,
+      "grad_norm": 117453.265625,
+      "learning_rate": 1.7839575344483237e-10,
+      "loss": 29.4332,
+      "step": 47
+    },
+    {
+      "epoch": 0.1483065953654189,
+      "grad_norm": 118000.7265625,
+      "learning_rate": 1.773958037050753e-10,
+      "loss": 28.7868,
+      "step": 48
+    },
+    {
+      "epoch": 0.15139631610219845,
+      "grad_norm": 127199.6953125,
+      "learning_rate": 1.7637617168088326e-10,
+      "loss": 25.8592,
+      "step": 49
+    },
+    {
+      "epoch": 0.15448603683897802,
+      "grad_norm": 115966.7265625,
+      "learning_rate": 1.753371166716828e-10,
+      "loss": 28.3176,
+      "step": 50
+    },
+    {
+      "epoch": 0.15757575757575756,
+      "grad_norm": 120307.578125,
+      "learning_rate": 1.7427890291629892e-10,
+      "loss": 28.7395,
+      "step": 51
+    },
+    {
+      "epoch": 0.16066547831253714,
+      "grad_norm": 110086.4296875,
+      "learning_rate": 1.732017995257575e-10,
+      "loss": 29.0903,
+      "step": 52
+    },
+    {
+      "epoch": 0.1637551990493167,
+      "grad_norm": 125848.5,
+      "learning_rate": 1.721060804148482e-10,
+      "loss": 27.0135,
+      "step": 53
+    },
+    {
+      "epoch": 0.16684491978609625,
+      "grad_norm": 138127.296875,
+      "learning_rate": 1.7099202423246632e-10,
+      "loss": 24.2078,
+      "step": 54
+    },
+    {
+      "epoch": 0.16993464052287582,
+      "grad_norm": 126173.71875,
+      "learning_rate": 1.6985991429075038e-10,
+      "loss": 27.1029,
+      "step": 55
+    },
+    {
+      "epoch": 0.17302436125965537,
+      "grad_norm": 113517.828125,
+      "learning_rate": 1.687100384930338e-10,
+      "loss": 28.6511,
+      "step": 56
+    },
+    {
+      "epoch": 0.17611408199643494,
+      "grad_norm": 125443.1640625,
+      "learning_rate": 1.6754268926062938e-10,
+      "loss": 28.0516,
+      "step": 57
+    },
+    {
+      "epoch": 0.17920380273321448,
+      "grad_norm": 120414.265625,
+      "learning_rate": 1.6635816345846412e-10,
+      "loss": 26.6481,
+      "step": 58
+    },
+    {
+      "epoch": 0.18229352346999406,
+      "grad_norm": 142621.21875,
+      "learning_rate": 1.6515676231958488e-10,
+      "loss": 24.7811,
+      "step": 59
+    },
+    {
+      "epoch": 0.18538324420677363,
+      "grad_norm": 128307.296875,
+      "learning_rate": 1.6393879136855248e-10,
+      "loss": 24.9562,
+      "step": 60
+    },
+    {
+      "epoch": 0.18847296494355317,
+      "grad_norm": 131207.0625,
+      "learning_rate": 1.6270456034374474e-10,
+      "loss": 26.3174,
+      "step": 61
+    },
+    {
+      "epoch": 0.19156268568033274,
+      "grad_norm": 126856.7578125,
+      "learning_rate": 1.6145438311858797e-10,
+      "loss": 24.581,
+      "step": 62
+    },
+    {
+      "epoch": 0.1946524064171123,
+      "grad_norm": 130663.9921875,
+      "learning_rate": 1.601885776217367e-10,
+      "loss": 24.543,
+      "step": 63
+    },
+    {
+      "epoch": 0.19774212715389186,
+      "grad_norm": 117330.453125,
+      "learning_rate": 1.589074657562223e-10,
+      "loss": 26.1565,
+      "step": 64
+    },
+    {
+      "epoch": 0.20083184789067143,
+      "grad_norm": 126654.546875,
+      "learning_rate": 1.5761137331759085e-10,
+      "loss": 26.9999,
+      "step": 65
+    },
+    {
+      "epoch": 0.20392156862745098,
+      "grad_norm": 122709.8984375,
+      "learning_rate": 1.5630062991105098e-10,
+      "loss": 26.9336,
+      "step": 66
+    },
+    {
+      "epoch": 0.20701128936423055,
+      "grad_norm": 111839.421875,
+      "learning_rate": 1.5497556886765316e-10,
+      "loss": 29.4629,
+      "step": 67
+    },
+    {
+      "epoch": 0.2101010101010101,
+      "grad_norm": 115566.3515625,
+      "learning_rate": 1.536365271595212e-10,
+      "loss": 28.8732,
+      "step": 68
+    },
+    {
+      "epoch": 0.21319073083778967,
+      "grad_norm": 120251.84375,
+      "learning_rate": 1.5228384531415808e-10,
+      "loss": 28.2254,
+      "step": 69
+    },
+    {
+      "epoch": 0.2162804515745692,
+      "grad_norm": 109853.484375,
+      "learning_rate": 1.5091786732784717e-10,
+      "loss": 28.8846,
+      "step": 70
+    },
+    {
+      "epoch": 0.21937017231134878,
+      "grad_norm": 124965.2890625,
+      "learning_rate": 1.495389405781719e-10,
+      "loss": 27.476,
+      "step": 71
+    },
+    {
+      "epoch": 0.22245989304812835,
+      "grad_norm": 123831.765625,
+      "learning_rate": 1.4814741573567514e-10,
+      "loss": 28.3641,
+      "step": 72
+    },
+    {
+      "epoch": 0.2255496137849079,
+      "grad_norm": 122635.5625,
+      "learning_rate": 1.467436466746814e-10,
+      "loss": 26.8985,
+      "step": 73
+    },
+    {
+      "epoch": 0.22863933452168747,
+      "grad_norm": 114768.140625,
+      "learning_rate": 1.4532799038330386e-10,
+      "loss": 27.3799,
+      "step": 74
+    },
+    {
+      "epoch": 0.23172905525846701,
+      "grad_norm": 126590.0,
+      "learning_rate": 1.4390080687266012e-10,
+      "loss": 27.1862,
+      "step": 75
+    },
+    {
+      "epoch": 0.2348187759952466,
+      "grad_norm": 121103.6640625,
+      "learning_rate": 1.4246245908531884e-10,
+      "loss": 28.5261,
+      "step": 76
+    },
+    {
+      "epoch": 0.23790849673202613,
+      "grad_norm": 116113.4765625,
+      "learning_rate": 1.410133128030009e-10,
+      "loss": 29.2815,
+      "step": 77
+    },
+    {
+      "epoch": 0.2409982174688057,
+      "grad_norm": 124221.265625,
+      "learning_rate": 1.3955373655355853e-10,
+      "loss": 28.5093,
+      "step": 78
+    },
+    {
+      "epoch": 0.24408793820558528,
+      "grad_norm": 122242.0625,
+      "learning_rate": 1.3808410151725631e-10,
+      "loss": 27.9406,
+      "step": 79
+    },
+    {
+      "epoch": 0.24717765894236482,
+      "grad_norm": 129292.234375,
+      "learning_rate": 1.3660478143237748e-10,
+      "loss": 25.4098,
+      "step": 80
+    },
+    {
+      "epoch": 0.25026737967914436,
+      "grad_norm": 113323.875,
+      "learning_rate": 1.351161525001795e-10,
+      "loss": 30.2781,
+      "step": 81
+    },
+    {
+      "epoch": 0.25335710041592396,
+      "grad_norm": 120109.671875,
+      "learning_rate": 1.3361859328922368e-10,
+      "loss": 28.7683,
+      "step": 82
+    },
+    {
+      "epoch": 0.2564468211527035,
+      "grad_norm": 131119.078125,
+      "learning_rate": 1.3211248463910263e-10,
+      "loss": 26.0915,
+      "step": 83
+    },
+    {
+      "epoch": 0.25953654188948305,
+      "grad_norm": 133106.078125,
+      "learning_rate": 1.3059820956358996e-10,
+      "loss": 25.8208,
+      "step": 84
+    },
+    {
+      "epoch": 0.26262626262626265,
+      "grad_norm": 117423.5859375,
+      "learning_rate": 1.290761531532374e-10,
+      "loss": 28.491,
+      "step": 85
+    },
+    {
+      "epoch": 0.2657159833630422,
+      "grad_norm": 135454.3125,
+      "learning_rate": 1.2754670247744354e-10,
+      "loss": 24.7346,
+      "step": 86
+    },
+    {
+      "epoch": 0.26880570409982174,
+      "grad_norm": 125783.6484375,
+      "learning_rate": 1.260102464860195e-10,
+      "loss": 25.684,
+      "step": 87
+    },
+    {
+      "epoch": 0.2718954248366013,
+      "grad_norm": 124170.6484375,
+      "learning_rate": 1.2446717591027624e-10,
+      "loss": 27.912,
+      "step": 88
+    },
+    {
+      "epoch": 0.2749851455733809,
+      "grad_norm": 123135.8984375,
+      "learning_rate": 1.2291788316365887e-10,
+      "loss": 27.8059,
+      "step": 89
+    },
+    {
+      "epoch": 0.27807486631016043,
+      "grad_norm": 127220.2890625,
+      "learning_rate": 1.213627622419535e-10,
+      "loss": 26.8872,
+      "step": 90
+    },
+    {
+      "epoch": 0.28116458704694,
+      "grad_norm": 114622.0625,
+      "learning_rate": 1.1980220862309098e-10,
+      "loss": 27.7952,
+      "step": 91
+    },
+    {
+      "epoch": 0.2842543077837196,
+      "grad_norm": 129463.1484375,
+      "learning_rate": 1.182366191665744e-10,
+      "loss": 25.9395,
+      "step": 92
+    },
+    {
+      "epoch": 0.2873440285204991,
+      "grad_norm": 138215.8125,
+      "learning_rate": 1.1666639201255506e-10,
+      "loss": 25.4167,
+      "step": 93
+    },
+    {
+      "epoch": 0.29043374925727866,
+      "grad_norm": 113110.0,
+      "learning_rate": 1.1509192648058249e-10,
+      "loss": 28.0616,
+      "step": 94
+    },
+    {
+      "epoch": 0.2935234699940582,
+      "grad_norm": 120913.9765625,
+      "learning_rate": 1.1351362296805485e-10,
+      "loss": 28.1966,
+      "step": 95
+    },
+    {
+      "epoch": 0.2966131907308378,
+      "grad_norm": 117201.953125,
+      "learning_rate": 1.1193188284839518e-10,
+      "loss": 27.8393,
+      "step": 96
+    },
+    {
+      "epoch": 0.29970291146761735,
+      "grad_norm": 124783.2890625,
+      "learning_rate": 1.1034710836897921e-10,
+      "loss": 26.5054,
+      "step": 97
+    },
+    {
+      "epoch": 0.3027926322043969,
+      "grad_norm": 127615.96875,
+      "learning_rate": 1.0875970254884129e-10,
+      "loss": 26.9284,
+      "step": 98
+    },
+    {
+      "epoch": 0.3058823529411765,
+      "grad_norm": 132355.703125,
+      "learning_rate": 1.0717006907618376e-10,
+      "loss": 25.1614,
+      "step": 99
+    },
+    {
+      "epoch": 0.30897207367795604,
+      "grad_norm": 132260.8125,
+      "learning_rate": 1.0557861220571625e-10,
+      "loss": 24.961,
+      "step": 100
+    },
+    {
+      "epoch": 0.3120617944147356,
+      "grad_norm": 117828.6796875,
+      "learning_rate": 1.0398573665585105e-10,
+      "loss": 28.4477,
+      "step": 101
+    },
+    {
+      "epoch": 0.3151515151515151,
+      "grad_norm": 130773.75,
+      "learning_rate": 1.023918475057803e-10,
+      "loss": 27.1515,
+      "step": 102
+    },
+    {
+      "epoch": 0.3182412358882947,
+      "grad_norm": 121530.078125,
+      "learning_rate": 1.0079735009246167e-10,
+      "loss": 27.9482,
+      "step": 103
+    },
+    {
+      "epoch": 0.32133095662507427,
+      "grad_norm": 122278.96875,
+      "learning_rate": 9.920264990753837e-11,
+      "loss": 28.2168,
+      "step": 104
+    },
+    {
+      "epoch": 0.3244206773618538,
+      "grad_norm": 112929.9140625,
+      "learning_rate": 9.760815249421973e-11,
+      "loss": 29.3778,
+      "step": 105
+    },
+    {
+      "epoch": 0.3275103980986334,
+      "grad_norm": 116076.59375,
+      "learning_rate": 9.601426334414898e-11,
+      "loss": 28.591,
+      "step": 106
+    },
+    {
+      "epoch": 0.33060011883541296,
+      "grad_norm": 128873.78125,
+      "learning_rate": 9.442138779428376e-11,
+      "loss": 26.1022,
+      "step": 107
+    },
+    {
+      "epoch": 0.3336898395721925,
+      "grad_norm": 127668.328125,
+      "learning_rate": 9.282993092381625e-11,
+      "loss": 25.6443,
+      "step": 108
+    },
+    {
+      "epoch": 0.33677956030897205,
+      "grad_norm": 122660.5625,
+      "learning_rate": 9.12402974511587e-11,
+      "loss": 26.6564,
+      "step": 109
+    },
+    {
+      "epoch": 0.33986928104575165,
+      "grad_norm": 120201.34375,
+      "learning_rate": 8.965289163102078e-11,
+      "loss": 25.9894,
+      "step": 110
+    },
+    {
+      "epoch": 0.3429590017825312,
+      "grad_norm": 127018.890625,
+      "learning_rate": 8.806811715160484e-11,
+      "loss": 25.5922,
+      "step": 111
+    },
+    {
+      "epoch": 0.34604872251931074,
+      "grad_norm": 126997.375,
+      "learning_rate": 8.648637703194516e-11,
+      "loss": 27.1782,
+      "step": 112
+    },
+    {
+      "epoch": 0.34913844325609034,
+      "grad_norm": 111071.9921875,
+      "learning_rate": 8.490807351941753e-11,
+      "loss": 29.0618,
+      "step": 113
+    },
+    {
+      "epoch": 0.3522281639928699,
+      "grad_norm": 109156.3125,
+      "learning_rate": 8.333360798744496e-11,
+      "loss": 31.8425,
+      "step": 114
+    },
+    {
+      "epoch": 0.3553178847296494,
+      "grad_norm": 126704.4375,
+      "learning_rate": 8.17633808334256e-11,
+      "loss": 26.271,
+      "step": 115
+    },
+    {
+      "epoch": 0.35840760546642897,
+      "grad_norm": 129102.53125,
+      "learning_rate": 8.019779137690906e-11,
+      "loss": 26.1617,
+      "step": 116
+    },
+    {
+      "epoch": 0.36149732620320857,
+      "grad_norm": 116444.125,
+      "learning_rate": 7.863723775804651e-11,
+      "loss": 29.3636,
+      "step": 117
+    },
+    {
+      "epoch": 0.3645870469399881,
+      "grad_norm": 119892.703125,
+      "learning_rate": 7.708211683634111e-11,
+      "loss": 28.351,
+      "step": 118
+    },
+    {
+      "epoch": 0.36767676767676766,
+      "grad_norm": 133809.671875,
+      "learning_rate": 7.553282408972381e-11,
+      "loss": 25.5753,
+      "step": 119
+    },
+    {
+      "epoch": 0.37076648841354726,
+      "grad_norm": 131220.359375,
+      "learning_rate": 7.398975351398053e-11,
+      "loss": 26.8812,
+      "step": 120
+    },
+    {
+      "epoch": 0.3738562091503268,
+      "grad_norm": 116611.2734375,
+      "learning_rate": 7.245329752255648e-11,
+      "loss": 29.5172,
+      "step": 121
+    },
+    {
+      "epoch": 0.37694592988710635,
+      "grad_norm": 133015.046875,
+      "learning_rate": 7.092384684676262e-11,
+      "loss": 25.8481,
+      "step": 122
+    },
+    {
+      "epoch": 0.38003565062388595,
+      "grad_norm": 136814.09375,
+      "learning_rate": 6.940179043641005e-11,
+      "loss": 24.7821,
+      "step": 123
+    },
+    {
+      "epoch": 0.3831253713606655,
+      "grad_norm": 111482.6875,
+      "learning_rate": 6.788751536089739e-11,
+      "loss": 28.6458,
+      "step": 124
+    },
+    {
+      "epoch": 0.38621509209744503,
+      "grad_norm": 105425.6796875,
+      "learning_rate": 6.638140671077632e-11,
+      "loss": 30.565,
+      "step": 125
+    },
+    {
+      "epoch": 0.3893048128342246,
+      "grad_norm": 126840.734375,
+      "learning_rate": 6.488384749982054e-11,
+      "loss": 24.9263,
+      "step": 126
+    },
+    {
+      "epoch": 0.3923945335710042,
+      "grad_norm": 126449.0078125,
+      "learning_rate": 6.339521856762254e-11,
+      "loss": 27.0906,
+      "step": 127
+    },
+    {
+      "epoch": 0.3954842543077837,
+      "grad_norm": 110226.4375,
+      "learning_rate": 6.191589848274368e-11,
+      "loss": 28.7828,
+      "step": 128
+    },
+    {
+      "epoch": 0.39857397504456327,
+      "grad_norm": 117383.6171875,
+      "learning_rate": 6.04462634464415e-11,
+      "loss": 27.1669,
+      "step": 129
+    },
+    {
+      "epoch": 0.40166369578134287,
+      "grad_norm": 129581.0390625,
+      "learning_rate": 5.898668719699914e-11,
+      "loss": 24.9744,
+      "step": 130
+    },
+    {
+      "epoch": 0.4047534165181224,
+      "grad_norm": 126919.765625,
+      "learning_rate": 5.753754091468115e-11,
+      "loss": 26.5326,
+      "step": 131
+    },
+    {
+      "epoch": 0.40784313725490196,
+      "grad_norm": 126623.8046875,
+      "learning_rate": 5.6099193127339865e-11,
+      "loss": 28.2028,
+      "step": 132
+    },
+    {
+      "epoch": 0.4109328579916815,
+      "grad_norm": 128991.1171875,
+      "learning_rate": 5.467200961669618e-11,
+      "loss": 27.0198,
+      "step": 133
+    },
+    {
+      "epoch": 0.4140225787284611,
+      "grad_norm": 127212.984375,
+      "learning_rate": 5.325635332531864e-11,
+      "loss": 27.5968,
+      "step": 134
+    },
+    {
+      "epoch": 0.41711229946524064,
+      "grad_norm": 114877.2421875,
+      "learning_rate": 5.1852584264324866e-11,
+      "loss": 29.2745,
+      "step": 135
+    },
+    {
+      "epoch": 0.4202020202020202,
+      "grad_norm": 110463.8828125,
+      "learning_rate": 5.046105942182815e-11,
+      "loss": 28.0633,
+      "step": 136
+    },
+    {
+      "epoch": 0.4232917409387998,
+      "grad_norm": 124949.09375,
+      "learning_rate": 4.908213267215287e-11,
+      "loss": 27.0064,
+      "step": 137
+    },
+    {
+      "epoch": 0.42638146167557933,
+      "grad_norm": 137615.125,
+      "learning_rate": 4.771615468584194e-11,
+      "loss": 25.8549,
+      "step": 138
+    },
+    {
+      "epoch": 0.4294711824123589,
+      "grad_norm": 125163.0,
+      "learning_rate": 4.636347284047877e-11,
+      "loss": 28.2664,
+      "step": 139
+    },
+    {
+      "epoch": 0.4325609031491384,
+      "grad_norm": 120346.09375,
+      "learning_rate": 4.502443113234688e-11,
+      "loss": 27.093,
+      "step": 140
+    },
+    {
+      "epoch": 0.435650623885918,
+      "grad_norm": 130197.5234375,
+      "learning_rate": 4.3699370088949064e-11,
+      "loss": 25.7805,
+      "step": 141
+    },
+    {
+      "epoch": 0.43874034462269756,
+      "grad_norm": 141218.203125,
+      "learning_rate": 4.238862668240919e-11,
+      "loss": 25.3932,
+      "step": 142
+    },
+    {
+      "epoch": 0.4418300653594771,
+      "grad_norm": 124990.84375,
+      "learning_rate": 4.1092534243777726e-11,
+      "loss": 25.7902,
+      "step": 143
+    },
+    {
+      "epoch": 0.4449197860962567,
+      "grad_norm": 131223.625,
+      "learning_rate": 3.981142237826332e-11,
+      "loss": 25.7262,
+      "step": 144
+    },
+    {
+      "epoch": 0.44800950683303625,
+      "grad_norm": 119055.7109375,
+      "learning_rate": 3.854561688141205e-11,
+      "loss": 27.7554,
+      "step": 145
+    },
+    {
+      "epoch": 0.4510992275698158,
+      "grad_norm": 127996.890625,
+      "learning_rate": 3.729543965625526e-11,
+      "loss": 25.1842,
+      "step": 146
+    },
+    {
+      "epoch": 0.45418894830659534,
+      "grad_norm": 130496.4609375,
+      "learning_rate": 3.606120863144753e-11,
+      "loss": 26.7469,
+      "step": 147
+    },
+    {
+      "epoch": 0.45727866904337494,
+      "grad_norm": 138091.28125,
+      "learning_rate": 3.484323768041515e-11,
+      "loss": 24.2791,
+      "step": 148
+    },
+    {
+      "epoch": 0.4603683897801545,
+      "grad_norm": 114539.9140625,
+      "learning_rate": 3.364183654153592e-11,
+      "loss": 27.8677,
+      "step": 149
+    },
+    {
+      "epoch": 0.46345811051693403,
+      "grad_norm": 129665.9140625,
+      "learning_rate": 3.245731073937068e-11,
+      "loss": 26.8488,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 202,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.489068960874496e+17,
+  "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 sha256:3ae1cc95d5e39f5cb4178e50f71683ddd694fe8a84ac52421fb6ca6964b31bb4
+size 5240