Training in progress, step 2000, checkpoint

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2000/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 131072
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.51.3"
+}

checkpoint-2000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87fe50bcf9d9da8e44acbb106e6f319f1c52807c85a60e1c64685a42021fe885
+size 4983007904

checkpoint-2000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1250f7237e0475c5d46ba6b8406634cd8763e593f0878ed457a1ff0a981bb935
+size 4999836776

checkpoint-2000/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522db5c07abe6728ed81c4745857e6f02cf49d3a32c766840a4f3ae7cb5c2bda
+size 4983067960

checkpoint-2000/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e96e4bf925fb4375b9b504d81204c495a2722ac9e03286b744a38fb8d5503ca
+size 1073741952

checkpoint-2000/model.safetensors.index.json

@@ -0,0 +1,334 @@
+{
+  "metadata": {
+    "total_size": 16039616512
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510758458355ecf3413ac4b83a5feb02fd4f38fcd4f4d4af5e9db24c8b1edf55
+size 13446394

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a0b33951175d647c9e952d07f42797de84ed09d0cd0a06290ddc3c0073b7e2
+size 14498

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd38d316dd9f41fef58099ade0ad1204cda80689b93c579586f4bde2645634fe
+size 1064

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7edbeaf20dd7f571b5dd1c54d9ace4f9b6299127cc7ba2afb14a6d51a4a79a4
+size 17078136

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 192.0,
+      "learning_rate": 7.2e-07,
+      "loss": 17.8929,
+      "step": 10
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 116.5,
+      "learning_rate": 1.52e-06,
+      "loss": 17.1894,
+      "step": 20
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 93.5,
+      "learning_rate": 2.3200000000000002e-06,
+      "loss": 17.1662,
+      "step": 30
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 59.0,
+      "learning_rate": 3.12e-06,
+      "loss": 15.5562,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 93.5,
+      "learning_rate": 3.920000000000001e-06,
+      "loss": 14.6218,
+      "step": 50
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 122.5,
+      "learning_rate": 4.7200000000000005e-06,
+      "loss": 14.0262,
+      "step": 60
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 135.0,
+      "learning_rate": 5.5200000000000005e-06,
+      "loss": 14.516,
+      "step": 70
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 211.0,
+      "learning_rate": 6.3200000000000005e-06,
+      "loss": 13.598,
+      "step": 80
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 172.0,
+      "learning_rate": 7.1200000000000004e-06,
+      "loss": 14.4849,
+      "step": 90
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 183.0,
+      "learning_rate": 7.92e-06,
+      "loss": 13.3844,
+      "step": 100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 144.0,
+      "learning_rate": 8.720000000000001e-06,
+      "loss": 13.5488,
+      "step": 110
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 153.0,
+      "learning_rate": 9.52e-06,
+      "loss": 14.8995,
+      "step": 120
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 156.0,
+      "learning_rate": 1.0320000000000001e-05,
+      "loss": 14.0248,
+      "step": 130
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 276.0,
+      "learning_rate": 1.1120000000000002e-05,
+      "loss": 14.2637,
+      "step": 140
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 176.0,
+      "learning_rate": 1.1920000000000001e-05,
+      "loss": 15.7517,
+      "step": 150
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 178.0,
+      "learning_rate": 1.2720000000000002e-05,
+      "loss": 15.2519,
+      "step": 160
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 5408.0,
+      "learning_rate": 1.3520000000000003e-05,
+      "loss": 51.245,
+      "step": 170
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 576.0,
+      "learning_rate": 1.432e-05,
+      "loss": 23.1949,
+      "step": 180
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 402.0,
+      "learning_rate": 1.5120000000000001e-05,
+      "loss": 18.3584,
+      "step": 190
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 178.0,
+      "learning_rate": 1.5920000000000003e-05,
+      "loss": 17.5383,
+      "step": 200
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 2064.0,
+      "learning_rate": 1.672e-05,
+      "loss": 22.9987,
+      "step": 210
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 190.0,
+      "learning_rate": 1.752e-05,
+      "loss": 19.4033,
+      "step": 220
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 150.0,
+      "learning_rate": 1.832e-05,
+      "loss": 15.7816,
+      "step": 230
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 182.0,
+      "learning_rate": 1.912e-05,
+      "loss": 20.0571,
+      "step": 240
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 302.0,
+      "learning_rate": 1.9920000000000002e-05,
+      "loss": 19.3505,
+      "step": 250
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 246.0,
+      "learning_rate": 1.9999210442038164e-05,
+      "loss": 19.3353,
+      "step": 260
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 139.0,
+      "learning_rate": 1.9996481265944146e-05,
+      "loss": 17.5568,
+      "step": 270
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 314.0,
+      "learning_rate": 1.9991803256020393e-05,
+      "loss": 24.114,
+      "step": 280
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 168.0,
+      "learning_rate": 1.99851773242542e-05,
+      "loss": 24.3222,
+      "step": 290
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 157.0,
+      "learning_rate": 1.99766047623841e-05,
+      "loss": 17.1357,
+      "step": 300
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 243.0,
+      "learning_rate": 1.996608724164801e-05,
+      "loss": 17.5944,
+      "step": 310
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 168.0,
+      "learning_rate": 1.995362681245744e-05,
+      "loss": 17.9973,
+      "step": 320
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 129.0,
+      "learning_rate": 1.9939225903997748e-05,
+      "loss": 16.3556,
+      "step": 330
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 109.0,
+      "learning_rate": 1.992288732375458e-05,
+      "loss": 15.275,
+      "step": 340
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 148.0,
+      "learning_rate": 1.9904614256966514e-05,
+      "loss": 16.484,
+      "step": 350
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 139.0,
+      "learning_rate": 1.9884410266004134e-05,
+      "loss": 17.0713,
+      "step": 360
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 252.0,
+      "learning_rate": 1.986227928967551e-05,
+      "loss": 17.0777,
+      "step": 370
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 160.0,
+      "learning_rate": 1.983822564245833e-05,
+      "loss": 16.9359,
+      "step": 380
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 128.0,
+      "learning_rate": 1.981225401365877e-05,
+      "loss": 33.823,
+      "step": 390
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 142.0,
+      "learning_rate": 1.9784369466497333e-05,
+      "loss": 17.8366,
+      "step": 400
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 604.0,
+      "learning_rate": 1.9754577437121733e-05,
+      "loss": 17.0926,
+      "step": 410
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 138.0,
+      "learning_rate": 1.9722883733547128e-05,
+      "loss": 25.0166,
+      "step": 420
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 140.0,
+      "learning_rate": 1.968929453452383e-05,
+      "loss": 16.1607,
+      "step": 430
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 100.0,
+      "learning_rate": 1.965381638833274e-05,
+      "loss": 15.8693,
+      "step": 440
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 127.5,
+      "learning_rate": 1.9616456211508756e-05,
+      "loss": 16.6326,
+      "step": 450
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 136.0,
+      "learning_rate": 1.9577221287492368e-05,
+      "loss": 16.4813,
+      "step": 460
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 175.0,
+      "learning_rate": 1.9536119265209763e-05,
+      "loss": 16.9464,
+      "step": 470
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 128.0,
+      "learning_rate": 1.9493158157581617e-05,
+      "loss": 16.8985,
+      "step": 480
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 141.0,
+      "learning_rate": 1.9448346339960984e-05,
+      "loss": 16.1715,
+      "step": 490
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 112.0,
+      "learning_rate": 1.9401692548500504e-05,
+      "loss": 15.8461,
+      "step": 500
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 145.0,
+      "learning_rate": 1.935320587844926e-05,
+      "loss": 16.108,
+      "step": 510
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 136.0,
+      "learning_rate": 1.9302895782379648e-05,
+      "loss": 15.7665,
+      "step": 520
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 112.0,
+      "learning_rate": 1.925077206834458e-05,
+      "loss": 14.6068,
+      "step": 530
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 93.0,
+      "learning_rate": 1.9196844897965393e-05,
+      "loss": 15.5989,
+      "step": 540
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 121.0,
+      "learning_rate": 1.914112478445079e-05,
+      "loss": 15.9623,
+      "step": 550
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 95.0,
+      "learning_rate": 1.9083622590547313e-05,
+      "loss": 15.6861,
+      "step": 560
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 114.5,
+      "learning_rate": 1.9024349526421596e-05,
+      "loss": 15.4145,
+      "step": 570
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 114.5,
+      "learning_rate": 1.896331714747493e-05,
+      "loss": 14.4382,
+      "step": 580
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 111.0,
+      "learning_rate": 1.8900537352090523e-05,
+      "loss": 14.8372,
+      "step": 590
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 129.0,
+      "learning_rate": 1.8836022379313884e-05,
+      "loss": 16.0596,
+      "step": 600
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 97.0,
+      "learning_rate": 1.8769784806466768e-05,
+      "loss": 14.8813,
+      "step": 610
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 97.0,
+      "learning_rate": 1.870183754669526e-05,
+      "loss": 13.9936,
+      "step": 620
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 111.5,
+      "learning_rate": 1.863219384645227e-05,
+      "loss": 14.9816,
+      "step": 630
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 108.5,
+      "learning_rate": 1.8560867282915164e-05,
+      "loss": 14.2031,
+      "step": 640
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 104.0,
+      "learning_rate": 1.848787176133882e-05,
+      "loss": 14.7739,
+      "step": 650
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 89.0,
+      "learning_rate": 1.8413221512344805e-05,
+      "loss": 14.7629,
+      "step": 660
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 113.5,
+      "learning_rate": 1.8336931089147076e-05,
+      "loss": 14.6109,
+      "step": 670
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 97.5,
+      "learning_rate": 1.8259015364714786e-05,
+      "loss": 15.1143,
+      "step": 680
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 108.0,
+      "learning_rate": 1.8179489528872808e-05,
+      "loss": 14.3949,
+      "step": 690
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 111.5,
+      "learning_rate": 1.80983690853404e-05,
+      "loss": 14.4273,
+      "step": 700
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 112.5,
+      "learning_rate": 1.8015669848708768e-05,
+      "loss": 13.8492,
+      "step": 710
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 119.5,
+      "learning_rate": 1.793140794135795e-05,
+      "loss": 14.5132,
+      "step": 720
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 100.0,
+      "learning_rate": 1.7845599790313735e-05,
+      "loss": 13.9506,
+      "step": 730
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 133.0,
+      "learning_rate": 1.7758262124045195e-05,
+      "loss": 13.6922,
+      "step": 740
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 100.5,
+      "learning_rate": 1.7669411969203417e-05,
+      "loss": 14.3881,
+      "step": 750
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 128.0,
+      "learning_rate": 1.7579066647302134e-05,
+      "loss": 14.2717,
+      "step": 760
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 98.0,
+      "learning_rate": 1.7487243771340862e-05,
+      "loss": 13.3169,
+      "step": 770
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 95.0,
+      "learning_rate": 1.7393961242371203e-05,
+      "loss": 13.9998,
+      "step": 780
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 118.5,
+      "learning_rate": 1.7299237246007018e-05,
+      "loss": 13.8477,
+      "step": 790
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 83.0,
+      "learning_rate": 1.720309024887907e-05,
+      "loss": 13.4694,
+      "step": 800
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 119.0,
+      "learning_rate": 1.710553899503496e-05,
+      "loss": 14.0974,
+      "step": 810
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 93.0,
+      "learning_rate": 1.700660250228492e-05,
+      "loss": 13.7642,
+      "step": 820
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 113.0,
+      "learning_rate": 1.690630005849423e-05,
+      "loss": 13.5297,
+      "step": 830
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 98.0,
+      "learning_rate": 1.6804651217823055e-05,
+      "loss": 12.6107,
+      "step": 840
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 90.5,
+      "learning_rate": 1.6701675796914284e-05,
+      "loss": 13.7018,
+      "step": 850
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 84.5,
+      "learning_rate": 1.6597393871030264e-05,
+      "loss": 13.5795,
+      "step": 860
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 88.0,
+      "learning_rate": 1.649182577013906e-05,
+      "loss": 13.3089,
+      "step": 870
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 108.5,
+      "learning_rate": 1.6384992074951124e-05,
+      "loss": 14.8595,
+      "step": 880
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 109.5,
+      "learning_rate": 1.6276913612907005e-05,
+      "loss": 13.6668,
+      "step": 890
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 82.0,
+      "learning_rate": 1.6167611454117027e-05,
+      "loss": 14.3564,
+      "step": 900
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 88.5,
+      "learning_rate": 1.6057106907253617e-05,
+      "loss": 13.4427,
+      "step": 910
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 106.5,
+      "learning_rate": 1.5945421515397135e-05,
+      "loss": 12.7742,
+      "step": 920
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 98.0,
+      "learning_rate": 1.5832577051836016e-05,
+      "loss": 12.5311,
+      "step": 930
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 105.5,
+      "learning_rate": 1.5718595515822027e-05,
+      "loss": 13.2552,
+      "step": 940
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 104.0,
+      "learning_rate": 1.5603499128281447e-05,
+      "loss": 12.7764,
+      "step": 950
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 88.0,
+      "learning_rate": 1.5487310327483087e-05,
+      "loss": 12.5753,
+      "step": 960
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 88.0,
+      "learning_rate": 1.5370051764663872e-05,
+      "loss": 11.839,
+      "step": 970
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 79.0,
+      "learning_rate": 1.5251746299612959e-05,
+      "loss": 12.3413,
+      "step": 980
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 88.5,
+      "learning_rate": 1.5132416996215171e-05,
+      "loss": 11.7489,
+      "step": 990
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 79.0,
+      "learning_rate": 1.5012087117954643e-05,
+      "loss": 12.265,
+      "step": 1000
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 84.5,
+      "learning_rate": 1.4890780123379565e-05,
+      "loss": 12.1652,
+      "step": 1010
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 83.0,
+      "learning_rate": 1.4768519661528879e-05,
+      "loss": 11.4174,
+      "step": 1020
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 94.5,
+      "learning_rate": 1.464532956732188e-05,
+      "loss": 12.5315,
+      "step": 1030
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 87.0,
+      "learning_rate": 1.4521233856911507e-05,
+      "loss": 12.0051,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 85.5,
+      "learning_rate": 1.43962567230024e-05,
+      "loss": 12.177,
+      "step": 1050
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 91.0,
+      "learning_rate": 1.4270422530134433e-05,
+      "loss": 12.3925,
+      "step": 1060
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 96.5,
+      "learning_rate": 1.4143755809932843e-05,
+      "loss": 12.4198,
+      "step": 1070
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 82.0,
+      "learning_rate": 1.4016281256325702e-05,
+      "loss": 12.5425,
+      "step": 1080
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 73.5,
+      "learning_rate": 1.388802372072981e-05,
+      "loss": 12.0934,
+      "step": 1090
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 73.0,
+      "learning_rate": 1.3759008207205869e-05,
+      "loss": 11.4355,
+      "step": 1100
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 78.5,
+      "learning_rate": 1.3629259867583864e-05,
+      "loss": 11.8871,
+      "step": 1110
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 76.5,
+      "learning_rate": 1.349880399655969e-05,
+      "loss": 11.2964,
+      "step": 1120
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 86.0,
+      "learning_rate": 1.3367666026763884e-05,
+      "loss": 11.2128,
+      "step": 1130
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 78.5,
+      "learning_rate": 1.3235871523803496e-05,
+      "loss": 11.5252,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 76.5,
+      "learning_rate": 1.3103446181278015e-05,
+      "loss": 11.3193,
+      "step": 1150
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 78.0,
+      "learning_rate": 1.297041581577035e-05,
+      "loss": 11.2879,
+      "step": 1160
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 81.5,
+      "learning_rate": 1.2836806361813846e-05,
+      "loss": 11.1236,
+      "step": 1170
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 72.0,
+      "learning_rate": 1.270264386683628e-05,
+      "loss": 10.7719,
+      "step": 1180
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 73.0,
+      "learning_rate": 1.256795448608188e-05,
+      "loss": 10.945,
+      "step": 1190
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 72.5,
+      "learning_rate": 1.2432764477512294e-05,
+      "loss": 11.3054,
+      "step": 1200
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 69.0,
+      "learning_rate": 1.2297100196687557e-05,
+      "loss": 11.0717,
+      "step": 1210
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 79.0,
+      "learning_rate": 1.2160988091628023e-05,
+      "loss": 11.1283,
+      "step": 1220
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 69.5,
+      "learning_rate": 1.202445469765826e-05,
+      "loss": 10.7246,
+      "step": 1230
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 64.5,
+      "learning_rate": 1.1887526632233954e-05,
+      "loss": 11.1319,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 74.0,
+      "learning_rate": 1.1750230589752763e-05,
+      "loss": 11.0599,
+      "step": 1250
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 90.5,
+      "learning_rate": 1.1612593336350209e-05,
+      "loss": 10.9624,
+      "step": 1260
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 74.5,
+      "learning_rate": 1.1474641704681551e-05,
+      "loss": 11.6825,
+      "step": 1270
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 83.5,
+      "learning_rate": 1.1336402588690727e-05,
+      "loss": 10.4348,
+      "step": 1280
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 60.25,
+      "learning_rate": 1.1197902938367297e-05,
+      "loss": 10.192,
+      "step": 1290
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 70.5,
+      "learning_rate": 1.105916975449252e-05,
+      "loss": 10.9921,
+      "step": 1300
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 68.5,
+      "learning_rate": 1.0920230083375474e-05,
+      "loss": 10.9344,
+      "step": 1310
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 94.5,
+      "learning_rate": 1.0781111011580336e-05,
+      "loss": 10.7657,
+      "step": 1320
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 66.0,
+      "learning_rate": 1.0641839660645806e-05,
+      "loss": 10.2728,
+      "step": 1330
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 86.0,
+      "learning_rate": 1.0502443181797696e-05,
+      "loss": 10.3206,
+      "step": 1340
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 71.0,
+      "learning_rate": 1.036294875065576e-05,
+      "loss": 10.4514,
+      "step": 1350
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 63.0,
+      "learning_rate": 1.0223383561935738e-05,
+      "loss": 10.148,
+      "step": 1360
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 69.0,
+      "learning_rate": 1.0083774824147707e-05,
+      "loss": 10.213,
+      "step": 1370
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 75.0,
+      "learning_rate": 9.944149754291719e-06,
+      "loss": 10.3198,
+      "step": 1380
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 75.0,
+      "learning_rate": 9.80453557255179e-06,
+      "loss": 9.7986,
+      "step": 1390
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 69.0,
+      "learning_rate": 9.664959496989286e-06,
+      "loss": 10.2986,
+      "step": 1400
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 74.0,
+      "learning_rate": 9.525448738236691e-06,
+      "loss": 10.4321,
+      "step": 1410
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 74.5,
+      "learning_rate": 9.386030494192847e-06,
+      "loss": 9.978,
+      "step": 1420
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 70.0,
+      "learning_rate": 9.246731944720675e-06,
+      "loss": 9.8457,
+      "step": 1430
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 69.0,
+      "learning_rate": 9.107580246348395e-06,
+      "loss": 9.8384,
+      "step": 1440
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 71.5,
+      "learning_rate": 8.968602526975329e-06,
+      "loss": 9.4468,
+      "step": 1450
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 152.0,
+      "learning_rate": 8.829825880583228e-06,
+      "loss": 9.6898,
+      "step": 1460
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 59.0,
+      "learning_rate": 8.69127736195428e-06,
+      "loss": 9.3791,
+      "step": 1470
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 70.0,
+      "learning_rate": 8.552983981396709e-06,
+      "loss": 9.6053,
+      "step": 1480
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 63.0,
+      "learning_rate": 8.414972699479076e-06,
+      "loss": 9.5834,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 77.5,
+      "learning_rate": 8.277270421774234e-06,
+      "loss": 9.4602,
+      "step": 1500
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 64.0,
+      "learning_rate": 8.139903993614069e-06,
+      "loss": 9.2274,
+      "step": 1510
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 60.0,
+      "learning_rate": 8.00290019485593e-06,
+      "loss": 9.2331,
+      "step": 1520
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 386.0,
+      "learning_rate": 7.866285734661842e-06,
+      "loss": 9.2324,
+      "step": 1530
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 60.0,
+      "learning_rate": 7.730087246291503e-06,
+      "loss": 9.2647,
+      "step": 1540
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 58.25,
+      "learning_rate": 7.594331281910082e-06,
+      "loss": 9.117,
+      "step": 1550
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 72.0,
+      "learning_rate": 7.4590443074118325e-06,
+      "loss": 8.8587,
+      "step": 1560
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 66.5,
+      "learning_rate": 7.324252697260475e-06,
+      "loss": 9.1659,
+      "step": 1570
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 65.5,
+      "learning_rate": 7.189982729347491e-06,
+      "loss": 8.8773,
+      "step": 1580
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 63.5,
+      "learning_rate": 7.056260579869165e-06,
+      "loss": 8.9672,
+      "step": 1590
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 62.75,
+      "learning_rate": 6.923112318223497e-06,
+      "loss": 9.1023,
+      "step": 1600
+    },
+    {
+      "epoch": 0.644,
+      "grad_norm": 63.25,
+      "learning_rate": 6.790563901927907e-06,
+      "loss": 9.4185,
+      "step": 1610
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 66.5,
+      "learning_rate": 6.658641171558785e-06,
+      "loss": 9.3091,
+      "step": 1620
+    },
+    {
+      "epoch": 0.652,
+      "grad_norm": 62.5,
+      "learning_rate": 6.52736984571381e-06,
+      "loss": 8.9926,
+      "step": 1630
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 76.5,
+      "learning_rate": 6.396775515998055e-06,
+      "loss": 8.8942,
+      "step": 1640
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 85.0,
+      "learning_rate": 6.2668836420348535e-06,
+      "loss": 9.101,
+      "step": 1650
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 66.0,
+      "learning_rate": 6.137719546502401e-06,
+      "loss": 8.3126,
+      "step": 1660
+    },
+    {
+      "epoch": 0.668,
+      "grad_norm": 58.25,
+      "learning_rate": 6.009308410197048e-06,
+      "loss": 8.6663,
+      "step": 1670
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 68.5,
+      "learning_rate": 5.881675267124254e-06,
+      "loss": 8.749,
+      "step": 1680
+    },
+    {
+      "epoch": 0.676,
+      "grad_norm": 55.25,
+      "learning_rate": 5.754844999618144e-06,
+      "loss": 8.449,
+      "step": 1690
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 58.5,
+      "learning_rate": 5.628842333490674e-06,
+      "loss": 8.9409,
+      "step": 1700
+    },
+    {
+      "epoch": 0.684,
+      "grad_norm": 58.25,
+      "learning_rate": 5.50369183321126e-06,
+      "loss": 8.4775,
+      "step": 1710
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 89.5,
+      "learning_rate": 5.379417897117917e-06,
+      "loss": 8.355,
+      "step": 1720
+    },
+    {
+      "epoch": 0.692,
+      "grad_norm": 57.75,
+      "learning_rate": 5.256044752660709e-06,
+      "loss": 8.4883,
+      "step": 1730
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 60.25,
+      "learning_rate": 5.133596451678603e-06,
+      "loss": 8.255,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 61.0,
+      "learning_rate": 5.012096865710494e-06,
+      "loss": 8.4214,
+      "step": 1750
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 69.0,
+      "learning_rate": 4.891569681341403e-06,
+      "loss": 8.3666,
+      "step": 1760
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 91.5,
+      "learning_rate": 4.772038395584735e-06,
+      "loss": 8.8221,
+      "step": 1770
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 60.5,
+      "learning_rate": 4.6535263113014885e-06,
+      "loss": 8.5474,
+      "step": 1780
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 69.5,
+      "learning_rate": 4.53605653265731e-06,
+      "loss": 8.0251,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 68.0,
+      "learning_rate": 4.419651960618302e-06,
+      "loss": 7.8395,
+      "step": 1800
+    },
+    {
+      "epoch": 0.724,
+      "grad_norm": 55.75,
+      "learning_rate": 4.304335288486426e-06,
+      "loss": 8.4034,
+      "step": 1810
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 93.0,
+      "learning_rate": 4.190128997475402e-06,
+      "loss": 8.3004,
+      "step": 1820
+    },
+    {
+      "epoch": 0.732,
+      "grad_norm": 69.0,
+      "learning_rate": 4.0770553523279535e-06,
+      "loss": 7.9588,
+      "step": 1830
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 52.5,
+      "learning_rate": 3.965136396975235e-06,
+      "loss": 7.7649,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 63.5,
+      "learning_rate": 3.854393950239356e-06,
+      "loss": 8.6746,
+      "step": 1850
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 58.0,
+      "learning_rate": 3.7448496015797296e-06,
+      "loss": 8.4542,
+      "step": 1860
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 66.5,
+      "learning_rate": 3.636524706884181e-06,
+      "loss": 7.9523,
+      "step": 1870
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 67.5,
+      "learning_rate": 3.5294403843055604e-06,
+      "loss": 8.3026,
+      "step": 1880
+    },
+    {
+      "epoch": 0.756,
+      "grad_norm": 54.0,
+      "learning_rate": 3.4236175101447265e-06,
+      "loss": 8.2066,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 59.0,
+      "learning_rate": 3.3190767147806825e-06,
+      "loss": 8.4277,
+      "step": 1900
+    },
+    {
+      "epoch": 0.764,
+      "grad_norm": 57.75,
+      "learning_rate": 3.2158383786486204e-06,
+      "loss": 8.2385,
+      "step": 1910
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 56.75,
+      "learning_rate": 3.113922628266718e-06,
+      "loss": 8.0253,
+      "step": 1920
+    },
+    {
+      "epoch": 0.772,
+      "grad_norm": 75.5,
+      "learning_rate": 3.013349332312451e-06,
+      "loss": 8.4382,
+      "step": 1930
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 81.5,
+      "learning_rate": 2.9141380977491373e-06,
+      "loss": 8.2415,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 61.75,
+      "learning_rate": 2.816308266003541e-06,
+      "loss": 8.0811,
+      "step": 1950
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 65.5,
+      "learning_rate": 2.7198789091951903e-06,
+      "loss": 8.1608,
+      "step": 1960
+    },
+    {
+      "epoch": 0.788,
+      "grad_norm": 55.0,
+      "learning_rate": 2.624868826418262e-06,
+      "loss": 8.1292,
+      "step": 1970
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 58.75,
+      "learning_rate": 2.5312965400766475e-06,
+      "loss": 7.9587,
+      "step": 1980
+    },
+    {
+      "epoch": 0.796,
+      "grad_norm": 60.5,
+      "learning_rate": 2.4391802922729703e-06,
+      "loss": 7.6301,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 59.0,
+      "learning_rate": 2.3485380412522586e-06,
+      "loss": 8.6694,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4712053990162432e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3b1c197edc1cf2ff9b4edb01ff7f40f1d11ded0754942f97e3dd5c9caac05d
+size 5368