Upload folder using huggingface_hub

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.6828734450847135,
-    "train_runtime": 21591.6608,
+    "train_loss": 0.6834336294733948,
+    "train_runtime": 21601.4132,
     "train_samples": 1226825,
-    "train_samples_per_second": 10.261,
+    "train_samples_per_second": 10.256,
     "train_steps_per_second": 0.08
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dbeb685d7d510b5b4c7da8fe1d03b8f773bf280e3f72dc4169866082af7499d
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427ad29929638bb52e893bfcb56dc3d62ff983cb0ca3fe94632236a53cf92899
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a55b7da5a70d0d6188a090c4f1d3a684af53cf5ccd5b3409e4aab415a5cf6d
+size 4540516344

model.safetensors.index.json

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

runs/Apr16_09-24-54_ggpu163/events.out.tfevents.1713252388.ggpu163.2321076.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479b535148b79606c4ff9efc86ad71394d5dd7a0cac334316ecee7784475d976
+size 41835

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.6828734450847135,
-    "train_runtime": 21591.6608,
+    "train_loss": 0.6834336294733948,
+    "train_runtime": 21601.4132,
     "train_samples": 1226825,
-    "train_samples_per_second": 10.261,
+    "train_samples_per_second": 10.256,
     "train_steps_per_second": 0.08
 }

trainer_state.json

@@ -17,9 +17,9 @@
     },
     {
       "epoch": 0.02,
-      "grad_norm": 15.875,
+      "grad_norm": 15.8125,
       "learning_rate": 2.0000000000000003e-06,
-      "loss": 1.2023,
+      "loss": 1.2022,
       "step": 10
     },
     {
@@ -31,889 +31,889 @@
     },
     {
       "epoch": 0.05,
-      "grad_norm": 1.734375,
+      "grad_norm": 1.859375,
       "learning_rate": 6e-06,
       "loss": 0.9902,
       "step": 30
     },
     {
       "epoch": 0.07,
-      "grad_norm": 1.8125,
+      "grad_norm": 1.9296875,
       "learning_rate": 8.000000000000001e-06,
       "loss": 0.9469,
       "step": 40
     },
     {
       "epoch": 0.09,
-      "grad_norm": 1.8359375,
+      "grad_norm": 1.53125,
       "learning_rate": 1e-05,
-      "loss": 0.9271,
+      "loss": 0.9267,
       "step": 50
     },
     {
       "epoch": 0.1,
-      "grad_norm": 1.3125,
+      "grad_norm": 1.2890625,
       "learning_rate": 9.999126844313853e-06,
-      "loss": 0.9067,
+      "loss": 0.9064,
       "step": 60
     },
     {
       "epoch": 0.12,
-      "grad_norm": 1.328125,
+      "grad_norm": 1.2421875,
       "learning_rate": 9.996507682215754e-06,
-      "loss": 0.8857,
+      "loss": 0.8855,
       "step": 70
     },
     {
       "epoch": 0.14,
-      "grad_norm": 1.265625,
+      "grad_norm": 1.1796875,
       "learning_rate": 9.992143428480215e-06,
-      "loss": 0.8738,
+      "loss": 0.8732,
       "step": 80
     },
     {
       "epoch": 0.16,
-      "grad_norm": 1.265625,
+      "grad_norm": 1.1328125,
       "learning_rate": 9.986035607376421e-06,
-      "loss": 0.8758,
+      "loss": 0.8754,
       "step": 90
     },
     {
       "epoch": 0.17,
-      "grad_norm": 1.3828125,
+      "grad_norm": 1.234375,
       "learning_rate": 9.97818635213586e-06,
-      "loss": 0.8689,
+      "loss": 0.8692,
       "step": 100
     },
     {
       "epoch": 0.19,
-      "grad_norm": 1.15625,
+      "grad_norm": 1.2421875,
       "learning_rate": 9.968598404207276e-06,
-      "loss": 0.8657,
+      "loss": 0.8661,
       "step": 110
     },
     {
       "epoch": 0.21,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.3203125,
       "learning_rate": 9.957275112299164e-06,
-      "loss": 0.8516,
+      "loss": 0.8518,
       "step": 120
     },
     {
       "epoch": 0.23,
-      "grad_norm": 1.15625,
+      "grad_norm": 1.2734375,
       "learning_rate": 9.944220431210216e-06,
-      "loss": 0.8466,
+      "loss": 0.8465,
       "step": 130
     },
     {
       "epoch": 0.24,
-      "grad_norm": 1.28125,
+      "grad_norm": 1.296875,
       "learning_rate": 9.929438920448038e-06,
-      "loss": 0.8462,
+      "loss": 0.8465,
       "step": 140
     },
     {
       "epoch": 0.26,
-      "grad_norm": 1.140625,
+      "grad_norm": 1.15625,
       "learning_rate": 9.912935742636698e-06,
-      "loss": 0.8377,
+      "loss": 0.8386,
       "step": 150
     },
     {
       "epoch": 0.28,
-      "grad_norm": 1.1953125,
+      "grad_norm": 1.15625,
       "learning_rate": 9.894716661713616e-06,
-      "loss": 0.8335,
+      "loss": 0.8346,
       "step": 160
     },
     {
       "epoch": 0.29,
-      "grad_norm": 1.046875,
+      "grad_norm": 1.1015625,
       "learning_rate": 9.874788040916433e-06,
-      "loss": 0.8363,
+      "loss": 0.8376,
       "step": 170
     },
     {
       "epoch": 0.31,
-      "grad_norm": 1.125,
+      "grad_norm": 1.1484375,
       "learning_rate": 9.853156840560576e-06,
-      "loss": 0.8231,
+      "loss": 0.8245,
       "step": 180
     },
     {
       "epoch": 0.33,
       "grad_norm": 1.234375,
       "learning_rate": 9.82983061560828e-06,
-      "loss": 0.8186,
+      "loss": 0.8201,
       "step": 190
     },
     {
       "epoch": 0.35,
-      "grad_norm": 1.234375,
+      "grad_norm": 1.328125,
       "learning_rate": 9.804817513029927e-06,
-      "loss": 0.8274,
+      "loss": 0.8287,
       "step": 200
     },
     {
       "epoch": 0.36,
-      "grad_norm": 1.25,
+      "grad_norm": 1.4921875,
       "learning_rate": 9.778126268958614e-06,
-      "loss": 0.8121,
+      "loss": 0.8136,
       "step": 210
     },
     {
       "epoch": 0.38,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.1875,
       "learning_rate": 9.749766205638954e-06,
-      "loss": 0.8086,
+      "loss": 0.8097,
       "step": 220
     },
     {
       "epoch": 0.4,
-      "grad_norm": 1.0703125,
+      "grad_norm": 1.3203125,
       "learning_rate": 9.719747228171163e-06,
-      "loss": 0.8032,
+      "loss": 0.8038,
       "step": 230
     },
     {
       "epoch": 0.42,
-      "grad_norm": 1.140625,
+      "grad_norm": 1.2265625,
       "learning_rate": 9.688079821051594e-06,
-      "loss": 0.8001,
+      "loss": 0.8007,
       "step": 240
     },
     {
       "epoch": 0.43,
-      "grad_norm": 1.078125,
+      "grad_norm": 1.1015625,
       "learning_rate": 9.65477504451088e-06,
-      "loss": 0.7901,
+      "loss": 0.791,
       "step": 250
     },
     {
       "epoch": 0.45,
-      "grad_norm": 1.1796875,
+      "grad_norm": 1.15625,
       "learning_rate": 9.619844530651026e-06,
-      "loss": 0.7966,
+      "loss": 0.7975,
       "step": 260
     },
     {
       "epoch": 0.47,
-      "grad_norm": 1.0390625,
+      "grad_norm": 1.046875,
       "learning_rate": 9.583300479382754e-06,
-      "loss": 0.7904,
+      "loss": 0.7916,
       "step": 270
     },
     {
       "epoch": 0.49,
-      "grad_norm": 1.28125,
+      "grad_norm": 1.2421875,
       "learning_rate": 9.545155654164523e-06,
-      "loss": 0.7905,
+      "loss": 0.7919,
       "step": 280
     },
     {
       "epoch": 0.5,
-      "grad_norm": 1.125,
+      "grad_norm": 1.1875,
       "learning_rate": 9.50542337754475e-06,
-      "loss": 0.7979,
+      "loss": 0.7991,
       "step": 290
     },
     {
       "epoch": 0.52,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.1328125,
       "learning_rate": 9.464117526508736e-06,
-      "loss": 0.7846,
+      "loss": 0.7858,
       "step": 300
     },
     {
       "epoch": 0.54,
-      "grad_norm": 1.2421875,
+      "grad_norm": 1.265625,
       "learning_rate": 9.421252527631964e-06,
-      "loss": 0.7775,
+      "loss": 0.7785,
       "step": 310
     },
     {
       "epoch": 0.55,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.1171875,
       "learning_rate": 9.376843352041434e-06,
-      "loss": 0.785,
+      "loss": 0.7859,
       "step": 320
     },
     {
       "epoch": 0.57,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.0703125,
       "learning_rate": 9.33090551018682e-06,
-      "loss": 0.7771,
+      "loss": 0.778,
       "step": 330
     },
     {
       "epoch": 0.59,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.140625,
       "learning_rate": 9.283455046423254e-06,
-      "loss": 0.777,
+      "loss": 0.778,
       "step": 340
     },
     {
       "epoch": 0.61,
-      "grad_norm": 1.125,
+      "grad_norm": 1.1640625,
       "learning_rate": 9.234508533407633e-06,
-      "loss": 0.7779,
+      "loss": 0.7788,
       "step": 350
     },
     {
       "epoch": 0.62,
-      "grad_norm": 1.1328125,
+      "grad_norm": 1.140625,
       "learning_rate": 9.184083066310419e-06,
-      "loss": 0.7757,
+      "loss": 0.7765,
       "step": 360
     },
     {
       "epoch": 0.64,
-      "grad_norm": 1.0703125,
+      "grad_norm": 1.0625,
       "learning_rate": 9.132196256844941e-06,
-      "loss": 0.7634,
+      "loss": 0.7643,
       "step": 370
     },
     {
       "epoch": 0.66,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.1171875,
       "learning_rate": 9.078866227116288e-06,
-      "loss": 0.7634,
+      "loss": 0.7642,
       "step": 380
     },
     {
       "epoch": 0.68,
-      "grad_norm": 1.1328125,
+      "grad_norm": 1.1015625,
       "learning_rate": 9.02411160329194e-06,
-      "loss": 0.7658,
+      "loss": 0.7666,
       "step": 390
     },
     {
       "epoch": 0.69,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.1484375,
       "learning_rate": 8.96795150909635e-06,
-      "loss": 0.7578,
+      "loss": 0.7585,
       "step": 400
     },
     {
       "epoch": 0.71,
-      "grad_norm": 1.21875,
+      "grad_norm": 1.203125,
       "learning_rate": 8.910405559131752e-06,
-      "loss": 0.7598,
+      "loss": 0.7603,
       "step": 410
     },
     {
       "epoch": 0.73,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.0625,
       "learning_rate": 8.851493852027515e-06,
-      "loss": 0.7596,
+      "loss": 0.7602,
       "step": 420
     },
     {
       "epoch": 0.75,
-      "grad_norm": 1.265625,
+      "grad_norm": 1.2578125,
       "learning_rate": 8.791236963420458e-06,
-      "loss": 0.7555,
+      "loss": 0.7561,
       "step": 430
     },
     {
       "epoch": 0.76,
       "grad_norm": 1.109375,
       "learning_rate": 8.729655938768542e-06,
-      "loss": 0.7569,
+      "loss": 0.7575,
       "step": 440
     },
     {
       "epoch": 0.78,
       "grad_norm": 1.109375,
       "learning_rate": 8.666772286000505e-06,
-      "loss": 0.7618,
+      "loss": 0.7622,
       "step": 450
     },
     {
       "epoch": 0.8,
-      "grad_norm": 34.5,
+      "grad_norm": 31.125,
       "learning_rate": 8.602607968003935e-06,
-      "loss": 0.754,
+      "loss": 0.7554,
       "step": 460
     },
     {
       "epoch": 0.81,
-      "grad_norm": 1.4140625,
+      "grad_norm": 1.265625,
       "learning_rate": 8.53718539495448e-06,
-      "loss": 0.7425,
+      "loss": 0.7429,
       "step": 470
     },
     {
       "epoch": 0.83,
-      "grad_norm": 1.1875,
+      "grad_norm": 1.3359375,
       "learning_rate": 8.470527416488799e-06,
-      "loss": 0.7554,
+      "loss": 0.7561,
       "step": 480
     },
     {
       "epoch": 0.85,
-      "grad_norm": 1.140625,
+      "grad_norm": 1.203125,
       "learning_rate": 8.402657313724065e-06,
-      "loss": 0.7517,
+      "loss": 0.7591,
       "step": 490
     },
     {
       "epoch": 0.87,
-      "grad_norm": 1.421875,
+      "grad_norm": 1.4296875,
       "learning_rate": 8.333598791126737e-06,
-      "loss": 0.7453,
+      "loss": 0.7455,
       "step": 500
     },
     {
       "epoch": 0.88,
-      "grad_norm": 1.1875,
+      "grad_norm": 1.15625,
       "learning_rate": 8.263375968233487e-06,
-      "loss": 0.7395,
+      "loss": 0.7397,
       "step": 510
     },
     {
       "epoch": 0.9,
-      "grad_norm": 1.1171875,
+      "grad_norm": 1.1484375,
       "learning_rate": 8.192013371227157e-06,
-      "loss": 0.7501,
+      "loss": 0.7506,
       "step": 520
     },
     {
       "epoch": 0.92,
-      "grad_norm": 1.1796875,
+      "grad_norm": 1.15625,
       "learning_rate": 8.119535924370692e-06,
-      "loss": 0.7473,
+      "loss": 0.7478,
       "step": 530
     },
     {
       "epoch": 0.94,
-      "grad_norm": 1.1640625,
+      "grad_norm": 1.140625,
       "learning_rate": 8.045968941302024e-06,
-      "loss": 0.7407,
+      "loss": 0.7414,
       "step": 540
     },
     {
       "epoch": 0.95,
-      "grad_norm": 1.1484375,
+      "grad_norm": 1.328125,
       "learning_rate": 7.971338116192986e-06,
-      "loss": 0.7425,
+      "loss": 0.7436,
       "step": 550
     },
     {
       "epoch": 0.97,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.15625,
       "learning_rate": 7.895669514775302e-06,
-      "loss": 0.7432,
+      "loss": 0.744,
       "step": 560
     },
     {
       "epoch": 0.99,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.109375,
       "learning_rate": 7.818989565236806e-06,
-      "loss": 0.7342,
+      "loss": 0.7347,
       "step": 570
     },
     {
       "epoch": 1.01,
-      "grad_norm": 1.5859375,
+      "grad_norm": 1.609375,
       "learning_rate": 7.74132504899108e-06,
-      "loss": 0.7181,
+      "loss": 0.7188,
       "step": 580
     },
     {
       "epoch": 1.02,
-      "grad_norm": 1.3203125,
+      "grad_norm": 1.296875,
       "learning_rate": 7.662703091323713e-06,
-      "loss": 0.6629,
+      "loss": 0.6638,
       "step": 590
     },
     {
       "epoch": 1.04,
-      "grad_norm": 1.1875,
+      "grad_norm": 1.2421875,
       "learning_rate": 7.583151151918464e-06,
-      "loss": 0.6644,
+      "loss": 0.6657,
       "step": 600
     },
     {
       "epoch": 1.06,
       "grad_norm": 1.1875,
       "learning_rate": 7.502697015266623e-06,
-      "loss": 0.6537,
+      "loss": 0.6547,
       "step": 610
     },
     {
       "epoch": 1.07,
-      "grad_norm": 1.1484375,
+      "grad_norm": 1.15625,
       "learning_rate": 7.421368780962951e-06,
-      "loss": 0.659,
+      "loss": 0.6598,
       "step": 620
     },
     {
       "epoch": 1.09,
-      "grad_norm": 1.1953125,
+      "grad_norm": 1.1875,
       "learning_rate": 7.339194853891536e-06,
-      "loss": 0.6518,
+      "loss": 0.6528,
       "step": 630
     },
     {
       "epoch": 1.11,
-      "grad_norm": 1.34375,
+      "grad_norm": 1.375,
       "learning_rate": 7.256203934305047e-06,
-      "loss": 0.653,
+      "loss": 0.6538,
       "step": 640
     },
     {
       "epoch": 1.13,
-      "grad_norm": 1.3671875,
+      "grad_norm": 1.3515625,
       "learning_rate": 7.172425007800822e-06,
-      "loss": 0.6566,
+      "loss": 0.6573,
       "step": 650
     },
     {
       "epoch": 1.14,
       "grad_norm": 1.3046875,
       "learning_rate": 7.087887335197281e-06,
-      "loss": 0.6528,
+      "loss": 0.6538,
       "step": 660
     },
     {
       "epoch": 1.16,
-      "grad_norm": 1.15625,
+      "grad_norm": 1.1953125,
       "learning_rate": 7.0026204423142364e-06,
-      "loss": 0.6547,
+      "loss": 0.6562,
       "step": 670
     },
     {
       "epoch": 1.18,
-      "grad_norm": 1.125,
+      "grad_norm": 1.1171875,
       "learning_rate": 6.91665410966063e-06,
-      "loss": 0.6503,
+      "loss": 0.6516,
       "step": 680
     },
     {
       "epoch": 1.2,
-      "grad_norm": 1.125,
+      "grad_norm": 1.140625,
       "learning_rate": 6.830018362033335e-06,
-      "loss": 0.6486,
+      "loss": 0.6492,
       "step": 690
     },
     {
       "epoch": 1.21,
-      "grad_norm": 1.46875,
+      "grad_norm": 1.3046875,
       "learning_rate": 6.742743458030614e-06,
-      "loss": 0.6496,
+      "loss": 0.6508,
       "step": 700
     },
     {
       "epoch": 1.23,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.15625,
       "learning_rate": 6.654859879483942e-06,
-      "loss": 0.6485,
+      "loss": 0.6492,
       "step": 710
     },
     {
       "epoch": 1.25,
-      "grad_norm": 1.1484375,
+      "grad_norm": 1.125,
       "learning_rate": 6.566398320811852e-06,
-      "loss": 0.6534,
+      "loss": 0.6541,
       "step": 720
     },
     {
       "epoch": 1.27,
-      "grad_norm": 1.0703125,
+      "grad_norm": 1.0859375,
       "learning_rate": 6.477389678299528e-06,
-      "loss": 0.6473,
+      "loss": 0.6481,
       "step": 730
     },
     {
       "epoch": 1.28,
-      "grad_norm": 1.1640625,
+      "grad_norm": 1.171875,
       "learning_rate": 6.387865039307899e-06,
-      "loss": 0.6503,
+      "loss": 0.6511,
       "step": 740
     },
     {
       "epoch": 1.3,
-      "grad_norm": 1.140625,
+      "grad_norm": 1.15625,
       "learning_rate": 6.297855671415999e-06,
-      "loss": 0.6537,
+      "loss": 0.6546,
       "step": 750
     },
     {
       "epoch": 1.32,
-      "grad_norm": 1.203125,
+      "grad_norm": 1.1484375,
       "learning_rate": 6.207393011500382e-06,
-      "loss": 0.6483,
+      "loss": 0.6491,
       "step": 760
     },
     {
       "epoch": 1.33,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.1015625,
       "learning_rate": 6.116508654755402e-06,
-      "loss": 0.648,
+      "loss": 0.6482,
       "step": 770
     },
     {
       "epoch": 1.35,
-      "grad_norm": 1.1171875,
+      "grad_norm": 1.1328125,
       "learning_rate": 6.025234343658209e-06,
-      "loss": 0.6456,
+      "loss": 0.6464,
       "step": 780
     },
     {
       "epoch": 1.37,
-      "grad_norm": 1.1328125,
+      "grad_norm": 1.40625,
       "learning_rate": 5.933601956882299e-06,
-      "loss": 0.6459,
+      "loss": 0.6466,
       "step": 790
     },
     {
       "epoch": 1.39,
       "grad_norm": 1.171875,
       "learning_rate": 5.841643498163488e-06,
-      "loss": 0.6543,
+      "loss": 0.6549,
       "step": 800
     },
     {
       "epoch": 1.4,
-      "grad_norm": 1.203125,
+      "grad_norm": 1.1796875,
       "learning_rate": 5.7493910851222244e-06,
-      "loss": 0.6438,
+      "loss": 0.6445,
       "step": 810
     },
     {
       "epoch": 1.42,
-      "grad_norm": 1.3828125,
+      "grad_norm": 1.1328125,
       "learning_rate": 5.656876938046112e-06,
-      "loss": 0.6428,
+      "loss": 0.6432,
       "step": 820
     },
     {
       "epoch": 1.44,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.09375,
       "learning_rate": 5.56413336863658e-06,
-      "loss": 0.6442,
+      "loss": 0.6485,
       "step": 830
     },
     {
       "epoch": 1.46,
-      "grad_norm": 1.1796875,
+      "grad_norm": 1.1875,
       "learning_rate": 5.471192768723618e-06,
-      "loss": 0.6428,
+      "loss": 0.6445,
       "step": 840
     },
     {
       "epoch": 1.47,
-      "grad_norm": 1.1328125,
+      "grad_norm": 1.15625,
       "learning_rate": 5.378087598952543e-06,
-      "loss": 0.648,
+      "loss": 0.6493,
       "step": 850
     },
     {
       "epoch": 1.49,
       "grad_norm": 1.1015625,
       "learning_rate": 5.284850377446715e-06,
-      "loss": 0.6411,
+      "loss": 0.6493,
       "step": 860
     },
     {
       "epoch": 1.51,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.109375,
       "learning_rate": 5.191513668450178e-06,
-      "loss": 0.647,
+      "loss": 0.6481,
       "step": 870
     },
     {
       "epoch": 1.53,
-      "grad_norm": 1.1640625,
+      "grad_norm": 1.125,
       "learning_rate": 5.098110070954209e-06,
-      "loss": 0.6477,
+      "loss": 0.6487,
       "step": 880
     },
     {
       "epoch": 1.54,
       "grad_norm": 1.1328125,
       "learning_rate": 5.004672207311709e-06,
-      "loss": 0.6457,
+      "loss": 0.6466,
       "step": 890
     },
     {
       "epoch": 1.56,
-      "grad_norm": 1.140625,
+      "grad_norm": 1.1328125,
       "learning_rate": 4.911232711843459e-06,
-      "loss": 0.6399,
+      "loss": 0.6407,
       "step": 900
     },
     {
       "epoch": 1.58,
-      "grad_norm": 1.140625,
+      "grad_norm": 1.1015625,
       "learning_rate": 4.817824219440167e-06,
-      "loss": 0.6414,
+      "loss": 0.6417,
       "step": 910
     },
     {
       "epoch": 1.59,
-      "grad_norm": 1.1484375,
+      "grad_norm": 1.1015625,
       "learning_rate": 4.724479354164347e-06,
-      "loss": 0.6378,
+      "loss": 0.6385,
       "step": 920
     },
     {
       "epoch": 1.61,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.109375,
       "learning_rate": 4.631230717855949e-06,
-      "loss": 0.6437,
+      "loss": 0.6441,
       "step": 930
     },
     {
       "epoch": 1.63,
-      "grad_norm": 1.1484375,
+      "grad_norm": 1.140625,
       "learning_rate": 4.538110878745784e-06,
-      "loss": 0.6439,
+      "loss": 0.6445,
       "step": 940
     },
     {
       "epoch": 1.65,
-      "grad_norm": 1.2265625,
+      "grad_norm": 1.203125,
       "learning_rate": 4.4451523600806555e-06,
-      "loss": 0.6394,
+      "loss": 0.6397,
       "step": 950
     },
     {
       "epoch": 1.66,
       "grad_norm": 1.1328125,
       "learning_rate": 4.352387628764223e-06,
-      "loss": 0.638,
+      "loss": 0.6387,
       "step": 960
     },
     {
       "epoch": 1.68,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.125,
       "learning_rate": 4.259849084017537e-06,
-      "loss": 0.6361,
+      "loss": 0.6374,
       "step": 970
     },
     {
       "epoch": 1.7,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.09375,
       "learning_rate": 4.16756904606321e-06,
-      "loss": 0.626,
+      "loss": 0.6268,
       "step": 980
     },
     {
       "epoch": 1.72,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.140625,
       "learning_rate": 4.075579744837185e-06,
-      "loss": 0.6424,
+      "loss": 0.6394,
       "step": 990
     },
     {
       "epoch": 1.73,
-      "grad_norm": 1.2265625,
+      "grad_norm": 1.171875,
       "learning_rate": 3.983913308732033e-06,
-      "loss": 0.6348,
+      "loss": 0.635,
       "step": 1000
     },
     {
       "epoch": 1.75,
-      "grad_norm": 1.1328125,
+      "grad_norm": 1.09375,
       "learning_rate": 3.89260175337572e-06,
-      "loss": 0.6433,
+      "loss": 0.644,
       "step": 1010
     },
     {
       "epoch": 1.77,
-      "grad_norm": 1.1328125,
+      "grad_norm": 1.109375,
       "learning_rate": 3.801676970449755e-06,
-      "loss": 0.6352,
+      "loss": 0.6357,
       "step": 1020
     },
     {
       "epoch": 1.79,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.171875,
       "learning_rate": 3.711170716550627e-06,
-      "loss": 0.6308,
+      "loss": 0.6314,
       "step": 1030
     },
     {
       "epoch": 1.8,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.125,
       "learning_rate": 3.6211146020984246e-06,
-      "loss": 0.636,
+      "loss": 0.6364,
       "step": 1040
     },
     {
       "epoch": 1.82,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.1171875,
       "learning_rate": 3.531540080296513e-06,
-      "loss": 0.6352,
+      "loss": 0.6356,
       "step": 1050
     },
     {
       "epoch": 1.84,
       "grad_norm": 1.125,
       "learning_rate": 3.442478436146108e-06,
-      "loss": 0.6368,
+      "loss": 0.6373,
       "step": 1060
     },
     {
       "epoch": 1.85,
-      "grad_norm": 1.1171875,
+      "grad_norm": 1.109375,
       "learning_rate": 3.353960775519612e-06,
-      "loss": 0.6386,
+      "loss": 0.6394,
       "step": 1070
     },
     {
       "epoch": 1.87,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.109375,
       "learning_rate": 3.266018014296506e-06,
-      "loss": 0.6371,
+      "loss": 0.6377,
       "step": 1080
     },
     {
       "epoch": 1.89,
       "grad_norm": 1.109375,
       "learning_rate": 3.1786808675655973e-06,
-      "loss": 0.6308,
+      "loss": 0.6313,
       "step": 1090
     },
     {
       "epoch": 1.91,
       "grad_norm": 1.1015625,
       "learning_rate": 3.0919798388973977e-06,
-      "loss": 0.6394,
+      "loss": 0.6403,
       "step": 1100
     },
     {
       "epoch": 1.92,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.078125,
       "learning_rate": 3.005945209690378e-06,
-      "loss": 0.6318,
+      "loss": 0.6325,
       "step": 1110
     },
     {
       "epoch": 1.94,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.09375,
       "learning_rate": 2.920607028594819e-06,
-      "loss": 0.6281,
+      "loss": 0.6285,
       "step": 1120
     },
     {
       "epoch": 1.96,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.09375,
       "learning_rate": 2.835995101017943e-06,
-      "loss": 0.6366,
+      "loss": 0.6372,
       "step": 1130
     },
     {
       "epoch": 1.98,
-      "grad_norm": 1.1171875,
+      "grad_norm": 1.1015625,
       "learning_rate": 2.7521389787140264e-06,
-      "loss": 0.6326,
+      "loss": 0.6336,
       "step": 1140
     },
     {
       "epoch": 1.99,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.109375,
       "learning_rate": 2.6690679494630734e-06,
-      "loss": 0.6318,
+      "loss": 0.6325,
       "step": 1150
     },
     {
       "epoch": 2.01,
-      "grad_norm": 1.7265625,
+      "grad_norm": 1.765625,
       "learning_rate": 2.5868110268416974e-06,
-      "loss": 0.603,
+      "loss": 0.6033,
       "step": 1160
     },
     {
       "epoch": 2.03,
-      "grad_norm": 1.328125,
+      "grad_norm": 3.0,
       "learning_rate": 2.5053969400897847e-06,
       "loss": 0.5946,
       "step": 1170
     },
     {
       "epoch": 2.05,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.125,
       "learning_rate": 2.4248541240764484e-06,
-      "loss": 0.5963,
+      "loss": 0.5962,
       "step": 1180
     },
     {
       "epoch": 2.06,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.140625,
       "learning_rate": 2.345210709368802e-06,
-      "loss": 0.5989,
+      "loss": 0.6014,
       "step": 1190
     },
     {
       "epoch": 2.08,
-      "grad_norm": 1.125,
+      "grad_norm": 1.09375,
       "learning_rate": 2.2664945124070076e-06,
-      "loss": 0.5926,
+      "loss": 0.5929,
       "step": 1200
     },
     {
       "epoch": 2.1,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.1015625,
       "learning_rate": 2.1887330257890554e-06,
-      "loss": 0.5868,
+      "loss": 0.5869,
       "step": 1210
     },
     {
       "epoch": 2.11,
       "grad_norm": 1.09375,
       "learning_rate": 2.1119534086686265e-06,
-      "loss": 0.5908,
+      "loss": 0.5909,
       "step": 1220
     },
     {
       "epoch": 2.13,
       "grad_norm": 1.109375,
       "learning_rate": 2.036182477269429e-06,
-      "loss": 0.5918,
+      "loss": 0.5916,
       "step": 1230
     },
     {
       "epoch": 2.15,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.078125,
       "learning_rate": 1.9614466955193007e-06,
-      "loss": 0.5982,
+      "loss": 0.5981,
       "step": 1240
     },
     {
       "epoch": 2.17,
       "grad_norm": 1.1015625,
       "learning_rate": 1.8877721658073589e-06,
-      "loss": 0.5901,
+      "loss": 0.5903,
       "step": 1250
     },
     {
       "epoch": 2.18,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.1015625,
       "learning_rate": 1.8151846198674227e-06,
-      "loss": 0.5967,
+      "loss": 0.5964,
       "step": 1260
     },
     {
       "epoch": 2.2,
-      "grad_norm": 1.0703125,
+      "grad_norm": 1.09375,
       "learning_rate": 1.7437094097908813e-06,
-      "loss": 0.5953,
+      "loss": 0.5952,
       "step": 1270
     },
     {
       "epoch": 2.22,
-      "grad_norm": 1.1328125,
+      "grad_norm": 1.109375,
       "learning_rate": 1.6733714991721738e-06,
-      "loss": 0.5902,
+      "loss": 0.5901,
       "step": 1280
     },
     {
       "epoch": 2.24,
-      "grad_norm": 1.078125,
+      "grad_norm": 1.0859375,
       "learning_rate": 1.6041954543899452e-06,
       "loss": 0.5891,
       "step": 1290
@@ -927,44 +927,44 @@
     },
     {
       "epoch": 2.27,
-      "grad_norm": 1.0703125,
+      "grad_norm": 1.1015625,
       "learning_rate": 1.469425190431592e-06,
-      "loss": 0.595,
+      "loss": 0.5946,
       "step": 1310
     },
     {
       "epoch": 2.29,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.109375,
       "learning_rate": 1.4038780414243875e-06,
-      "loss": 0.5978,
+      "loss": 0.5979,
       "step": 1320
     },
     {
       "epoch": 2.31,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.109375,
       "learning_rate": 1.3395868821516667e-06,
-      "loss": 0.5871,
+      "loss": 0.587,
       "step": 1330
     },
     {
       "epoch": 2.32,
-      "grad_norm": 1.078125,
+      "grad_norm": 1.1015625,
       "learning_rate": 1.2765741670899428e-06,
-      "loss": 0.5934,
+      "loss": 0.5933,
       "step": 1340
     },
     {
       "epoch": 2.34,
-      "grad_norm": 1.0625,
+      "grad_norm": 1.0859375,
       "learning_rate": 1.2148619042033994e-06,
-      "loss": 0.5928,
+      "loss": 0.5929,
       "step": 1350
     },
     {
       "epoch": 2.36,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.1015625,
       "learning_rate": 1.1544716472573336e-06,
-      "loss": 0.5853,
+      "loss": 0.5858,
       "step": 1360
     },
     {
@@ -976,42 +976,42 @@
     },
     {
       "epoch": 2.39,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.140625,
       "learning_rate": 1.0377410502471668e-06,
-      "loss": 0.5859,
+      "loss": 0.5858,
       "step": 1380
     },
     {
       "epoch": 2.41,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.0703125,
       "learning_rate": 9.814414797768756e-07,
-      "loss": 0.5956,
+      "loss": 0.5957,
       "step": 1390
     },
     {
       "epoch": 2.43,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.1015625,
       "learning_rate": 9.265454401954044e-07,
-      "loss": 0.5911,
+      "loss": 0.5915,
       "step": 1400
     },
     {
       "epoch": 2.44,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.078125,
       "learning_rate": 8.730721046183932e-07,
-      "loss": 0.5868,
+      "loss": 0.5869,
       "step": 1410
     },
     {
       "epoch": 2.46,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.1015625,
       "learning_rate": 8.210401492646497e-07,
-      "loss": 0.5946,
+      "loss": 0.5947,
       "step": 1420
     },
     {
       "epoch": 2.48,
-      "grad_norm": 1.0703125,
+      "grad_norm": 1.1015625,
       "learning_rate": 7.704677469332455e-07,
       "loss": 0.5925,
       "step": 1430
@@ -1020,208 +1020,208 @@
       "epoch": 2.5,
       "grad_norm": 1.125,
       "learning_rate": 7.213725606564436e-07,
-      "loss": 0.5947,
+      "loss": 0.5945,
       "step": 1440
     },
     {
       "epoch": 2.51,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.109375,
       "learning_rate": 6.737717375306684e-07,
-      "loss": 0.5923,
+      "loss": 0.5921,
       "step": 1450
     },
     {
       "epoch": 2.53,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.1328125,
       "learning_rate": 6.276819027276709e-07,
       "loss": 0.5861,
       "step": 1460
     },
     {
       "epoch": 2.55,
-      "grad_norm": 1.0625,
+      "grad_norm": 1.078125,
       "learning_rate": 5.831191536879843e-07,
-      "loss": 0.5956,
+      "loss": 0.5955,
       "step": 1470
     },
     {
       "epoch": 2.56,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.1015625,
       "learning_rate": 5.400990544986922e-07,
       "loss": 0.5896,
       "step": 1480
     },
     {
       "epoch": 2.58,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.28125,
       "learning_rate": 4.986366304574869e-07,
-      "loss": 0.5951,
+      "loss": 0.595,
       "step": 1490
     },
     {
       "epoch": 2.6,
       "grad_norm": 1.1015625,
       "learning_rate": 4.587463628248923e-07,
-      "loss": 0.5884,
+      "loss": 0.5887,
       "step": 1500
     },
     {
       "epoch": 2.62,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.1015625,
       "learning_rate": 4.2044218376651124e-07,
-      "loss": 0.5919,
+      "loss": 0.5929,
       "step": 1510
     },
     {
       "epoch": 2.63,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.09375,
       "learning_rate": 3.837374714870434e-07,
-      "loss": 0.6024,
+      "loss": 0.6026,
       "step": 1520
     },
     {
       "epoch": 2.65,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.1171875,
       "learning_rate": 3.486450455577828e-07,
-      "loss": 0.5936,
+      "loss": 0.5933,
       "step": 1530
     },
     {
       "epoch": 2.67,
-      "grad_norm": 1.3515625,
+      "grad_norm": 1.1328125,
       "learning_rate": 3.1517716243922414e-07,
-      "loss": 0.5921,
+      "loss": 0.5923,
       "step": 1540
     },
     {
       "epoch": 2.69,
       "grad_norm": 1.0859375,
       "learning_rate": 2.8334551120034857e-07,
-      "loss": 0.5965,
+      "loss": 0.5962,
       "step": 1550
     },
     {
       "epoch": 2.7,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.125,
       "learning_rate": 2.5316120943606634e-07,
       "loss": 0.5922,
       "step": 1560
     },
     {
       "epoch": 2.72,
-      "grad_norm": 1.125,
+      "grad_norm": 1.0625,
       "learning_rate": 2.246347993842657e-07,
-      "loss": 0.5878,
+      "loss": 0.5872,
       "step": 1570
     },
     {
       "epoch": 2.74,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.0859375,
       "learning_rate": 1.977762442438025e-07,
-      "loss": 0.5946,
+      "loss": 0.5943,
       "step": 1580
     },
     {
       "epoch": 2.76,
-      "grad_norm": 1.0703125,
+      "grad_norm": 1.078125,
       "learning_rate": 1.725949246947345e-07,
       "loss": 0.5888,
       "step": 1590
     },
     {
       "epoch": 2.77,
-      "grad_norm": 1.1328125,
+      "grad_norm": 1.0859375,
       "learning_rate": 1.4909963562200036e-07,
-      "loss": 0.593,
+      "loss": 0.5929,
       "step": 1600
     },
     {
       "epoch": 2.79,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.09375,
       "learning_rate": 1.272985830437018e-07,
-      "loss": 0.5916,
+      "loss": 0.5914,
       "step": 1610
     },
     {
       "epoch": 2.81,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.0546875,
       "learning_rate": 1.0719938124504725e-07,
       "loss": 0.5984,
       "step": 1620
     },
     {
       "epoch": 2.82,
-      "grad_norm": 1.140625,
+      "grad_norm": 1.1015625,
       "learning_rate": 8.880905011897145e-08,
-      "loss": 0.5938,
+      "loss": 0.5939,
       "step": 1630
     },
     {
       "epoch": 2.84,
-      "grad_norm": 1.0703125,
+      "grad_norm": 1.0625,
       "learning_rate": 7.213401271435216e-08,
-      "loss": 0.5911,
+      "loss": 0.5913,
       "step": 1640
     },
     {
       "epoch": 2.86,
-      "grad_norm": 1.1171875,
+      "grad_norm": 1.0859375,
       "learning_rate": 5.718009299267968e-08,
-      "loss": 0.5826,
+      "loss": 0.5824,
       "step": 1650
     },
     {
       "epoch": 2.88,
       "grad_norm": 1.09375,
       "learning_rate": 4.395251379396781e-08,
-      "loss": 0.5969,
+      "loss": 0.5968,
       "step": 1660
     },
     {
       "epoch": 2.89,
-      "grad_norm": 1.09375,
+      "grad_norm": 1.078125,
       "learning_rate": 3.2455895012614146e-08,
       "loss": 0.5877,
       "step": 1670
     },
     {
       "epoch": 2.91,
-      "grad_norm": 1.0546875,
+      "grad_norm": 1.0703125,
       "learning_rate": 2.2694251983841896e-08,
-      "loss": 0.5877,
+      "loss": 0.5875,
       "step": 1680
     },
     {
       "epoch": 2.93,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.859375,
       "learning_rate": 1.4670994081297796e-08,
-      "loss": 0.5914,
+      "loss": 0.5915,
       "step": 1690
     },
     {
       "epoch": 2.95,
-      "grad_norm": 1.0859375,
+      "grad_norm": 1.0703125,
       "learning_rate": 8.38892352628573e-09,
-      "loss": 0.5922,
+      "loss": 0.592,
       "step": 1700
     },
     {
       "epoch": 2.96,
-      "grad_norm": 1.1171875,
+      "grad_norm": 1.109375,
       "learning_rate": 3.850234409055742e-09,
-      "loss": 0.5935,
+      "loss": 0.5934,
       "step": 1710
     },
     {
       "epoch": 2.98,
-      "grad_norm": 1.1015625,
+      "grad_norm": 1.078125,
       "learning_rate": 1.0565119224925646e-09,
-      "loss": 0.5911,
+      "loss": 0.5903,
       "step": 1720
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.109375,
+      "grad_norm": 1.125,
       "learning_rate": 8.731808465167746e-12,
       "loss": 0.5943,
       "step": 1730
@@ -1230,9 +1230,9 @@
       "epoch": 3.0,
       "step": 1731,
       "total_flos": 2.4199600073374433e+18,
-      "train_loss": 0.6828734450847135,
-      "train_runtime": 21591.6608,
-      "train_samples_per_second": 10.261,
+      "train_loss": 0.6834336294733948,
+      "train_runtime": 21601.4132,
+      "train_samples_per_second": 10.256,
       "train_steps_per_second": 0.08
     }
   ],

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e53cbc5a9c4333263e47ac5205d31cc71f785413fcb82b8917062b7fbb8fa2e
+size 5048