Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede770e2c93a20c7e95465ffbc1b7322c057f808a95ccf160ca2e462e1643dc6
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f52777382383565b8c47c69275029c5af5b187e57d3319c8fe86fff8ea5e06
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90dd04e1668494d7eb511e8e3da667c56e92297c32ff5791e63af794b11031e7
+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"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105280e80a64c500f2b1796cc943f79b202170e25cca55485de3501e983b3ece
+size 28967182666

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7fa99bec52037f142ebe2cfa38ff74516e45af5c929299f94881877ec45f6f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d7b29622aad5c1fe8076c47dca89375b807eadcccb5b96a957a143cf4798a4
+size 1064

trainer_state.json

@@ -0,0 +1,780 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4089421935197287,
+  "eval_steps": 187,
+  "global_step": 2992,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.8125,
+      "learning_rate": 1e-05,
+      "loss": 1.2442,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.46875,
+      "learning_rate": 1e-05,
+      "loss": 1.1455,
+      "step": 187
+    },
+    {
+      "epoch": 0.03,
+      "eval_validation_privacy_sources_loss": 0.9909348487854004,
+      "eval_validation_privacy_sources_runtime": 210.9899,
+      "eval_validation_privacy_sources_samples_per_second": 1.815,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 187
+    },
+    {
+      "epoch": 0.03,
+      "eval_validation_agenda_digitale_loss": 1.5858619213104248,
+      "eval_validation_agenda_digitale_runtime": 187.2047,
+      "eval_validation_agenda_digitale_samples_per_second": 1.816,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 187
+    },
+    {
+      "epoch": 0.03,
+      "eval_validation_leggepertutti_loss": 1.3584009408950806,
+      "eval_validation_leggepertutti_runtime": 35.7769,
+      "eval_validation_leggepertutti_samples_per_second": 1.817,
+      "eval_validation_leggepertutti_steps_per_second": 0.922,
+      "step": 187
+    },
+    {
+      "epoch": 0.03,
+      "eval_validation_altalexprivacy_loss": 1.3655166625976562,
+      "eval_validation_altalexprivacy_runtime": 58.3249,
+      "eval_validation_altalexprivacy_samples_per_second": 1.817,
+      "eval_validation_altalexprivacy_steps_per_second": 0.909,
+      "step": 187
+    },
+    {
+      "epoch": 0.03,
+      "eval_validation_stack_loss": 0.5954318642616272,
+      "eval_validation_stack_runtime": 190.5195,
+      "eval_validation_stack_samples_per_second": 1.816,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 187
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.21875,
+      "learning_rate": 1e-05,
+      "loss": 1.0615,
+      "step": 374
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_privacy_sources_loss": 0.9419633746147156,
+      "eval_validation_privacy_sources_runtime": 210.7968,
+      "eval_validation_privacy_sources_samples_per_second": 1.817,
+      "eval_validation_privacy_sources_steps_per_second": 0.911,
+      "step": 374
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_agenda_digitale_loss": 1.561063528060913,
+      "eval_validation_agenda_digitale_runtime": 187.1864,
+      "eval_validation_agenda_digitale_samples_per_second": 1.816,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 374
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_leggepertutti_loss": 1.3387541770935059,
+      "eval_validation_leggepertutti_runtime": 35.7704,
+      "eval_validation_leggepertutti_samples_per_second": 1.817,
+      "eval_validation_leggepertutti_steps_per_second": 0.923,
+      "step": 374
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_altalexprivacy_loss": 1.32594895362854,
+      "eval_validation_altalexprivacy_runtime": 58.3358,
+      "eval_validation_altalexprivacy_samples_per_second": 1.817,
+      "eval_validation_altalexprivacy_steps_per_second": 0.909,
+      "step": 374
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_stack_loss": 0.5792369246482849,
+      "eval_validation_stack_runtime": 190.4571,
+      "eval_validation_stack_samples_per_second": 1.817,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 374
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.421875,
+      "learning_rate": 1e-05,
+      "loss": 1.0133,
+      "step": 561
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_privacy_sources_loss": 0.9125503897666931,
+      "eval_validation_privacy_sources_runtime": 210.7361,
+      "eval_validation_privacy_sources_samples_per_second": 1.817,
+      "eval_validation_privacy_sources_steps_per_second": 0.911,
+      "step": 561
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_agenda_digitale_loss": 1.5489054918289185,
+      "eval_validation_agenda_digitale_runtime": 187.1329,
+      "eval_validation_agenda_digitale_samples_per_second": 1.817,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 561
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_leggepertutti_loss": 1.3227838277816772,
+      "eval_validation_leggepertutti_runtime": 35.7601,
+      "eval_validation_leggepertutti_samples_per_second": 1.818,
+      "eval_validation_leggepertutti_steps_per_second": 0.923,
+      "step": 561
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_altalexprivacy_loss": 1.305092453956604,
+      "eval_validation_altalexprivacy_runtime": 58.3163,
+      "eval_validation_altalexprivacy_samples_per_second": 1.818,
+      "eval_validation_altalexprivacy_steps_per_second": 0.909,
+      "step": 561
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_stack_loss": 0.569362461566925,
+      "eval_validation_stack_runtime": 190.4309,
+      "eval_validation_stack_samples_per_second": 1.817,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 561
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.828125,
+      "learning_rate": 1e-05,
+      "loss": 0.9878,
+      "step": 748
+    },
+    {
+      "epoch": 0.1,
+      "eval_validation_privacy_sources_loss": 0.8928124904632568,
+      "eval_validation_privacy_sources_runtime": 210.6755,
+      "eval_validation_privacy_sources_samples_per_second": 1.818,
+      "eval_validation_privacy_sources_steps_per_second": 0.911,
+      "step": 748
+    },
+    {
+      "epoch": 0.1,
+      "eval_validation_agenda_digitale_loss": 1.5373064279556274,
+      "eval_validation_agenda_digitale_runtime": 187.1042,
+      "eval_validation_agenda_digitale_samples_per_second": 1.817,
+      "eval_validation_agenda_digitale_steps_per_second": 0.909,
+      "step": 748
+    },
+    {
+      "epoch": 0.1,
+      "eval_validation_leggepertutti_loss": 1.3180450201034546,
+      "eval_validation_leggepertutti_runtime": 35.7671,
+      "eval_validation_leggepertutti_samples_per_second": 1.817,
+      "eval_validation_leggepertutti_steps_per_second": 0.923,
+      "step": 748
+    },
+    {
+      "epoch": 0.1,
+      "eval_validation_altalexprivacy_loss": 1.2893434762954712,
+      "eval_validation_altalexprivacy_runtime": 58.3327,
+      "eval_validation_altalexprivacy_samples_per_second": 1.817,
+      "eval_validation_altalexprivacy_steps_per_second": 0.909,
+      "step": 748
+    },
+    {
+      "epoch": 0.1,
+      "eval_validation_stack_loss": 0.555778980255127,
+      "eval_validation_stack_runtime": 190.4189,
+      "eval_validation_stack_samples_per_second": 1.817,
+      "eval_validation_stack_steps_per_second": 0.909,
+      "step": 748
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.0,
+      "learning_rate": 1e-05,
+      "loss": 0.9849,
+      "step": 935
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_privacy_sources_loss": 0.8825064301490784,
+      "eval_validation_privacy_sources_runtime": 210.6896,
+      "eval_validation_privacy_sources_samples_per_second": 1.818,
+      "eval_validation_privacy_sources_steps_per_second": 0.911,
+      "step": 935
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_agenda_digitale_loss": 1.5294857025146484,
+      "eval_validation_agenda_digitale_runtime": 187.007,
+      "eval_validation_agenda_digitale_samples_per_second": 1.818,
+      "eval_validation_agenda_digitale_steps_per_second": 0.909,
+      "step": 935
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_leggepertutti_loss": 1.3130334615707397,
+      "eval_validation_leggepertutti_runtime": 35.7713,
+      "eval_validation_leggepertutti_samples_per_second": 1.817,
+      "eval_validation_leggepertutti_steps_per_second": 0.923,
+      "step": 935
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_altalexprivacy_loss": 1.2819935083389282,
+      "eval_validation_altalexprivacy_runtime": 58.2912,
+      "eval_validation_altalexprivacy_samples_per_second": 1.818,
+      "eval_validation_altalexprivacy_steps_per_second": 0.909,
+      "step": 935
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_stack_loss": 0.5473493337631226,
+      "eval_validation_stack_runtime": 190.3335,
+      "eval_validation_stack_samples_per_second": 1.818,
+      "eval_validation_stack_steps_per_second": 0.909,
+      "step": 935
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.84375,
+      "learning_rate": 1e-05,
+      "loss": 0.949,
+      "step": 1122
+    },
+    {
+      "epoch": 0.15,
+      "eval_validation_privacy_sources_loss": 0.8628236651420593,
+      "eval_validation_privacy_sources_runtime": 210.6338,
+      "eval_validation_privacy_sources_samples_per_second": 1.818,
+      "eval_validation_privacy_sources_steps_per_second": 0.912,
+      "step": 1122
+    },
+    {
+      "epoch": 0.15,
+      "eval_validation_agenda_digitale_loss": 1.5227819681167603,
+      "eval_validation_agenda_digitale_runtime": 187.0513,
+      "eval_validation_agenda_digitale_samples_per_second": 1.818,
+      "eval_validation_agenda_digitale_steps_per_second": 0.909,
+      "step": 1122
+    },
+    {
+      "epoch": 0.15,
+      "eval_validation_leggepertutti_loss": 1.3133653402328491,
+      "eval_validation_leggepertutti_runtime": 35.7704,
+      "eval_validation_leggepertutti_samples_per_second": 1.817,
+      "eval_validation_leggepertutti_steps_per_second": 0.923,
+      "step": 1122
+    },
+    {
+      "epoch": 0.15,
+      "eval_validation_altalexprivacy_loss": 1.270833134651184,
+      "eval_validation_altalexprivacy_runtime": 58.3107,
+      "eval_validation_altalexprivacy_samples_per_second": 1.818,
+      "eval_validation_altalexprivacy_steps_per_second": 0.909,
+      "step": 1122
+    },
+    {
+      "epoch": 0.15,
+      "eval_validation_stack_loss": 0.5453876852989197,
+      "eval_validation_stack_runtime": 190.3729,
+      "eval_validation_stack_samples_per_second": 1.817,
+      "eval_validation_stack_steps_per_second": 0.909,
+      "step": 1122
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.0,
+      "learning_rate": 1e-05,
+      "loss": 0.9454,
+      "step": 1309
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_privacy_sources_loss": 0.8534297347068787,
+      "eval_validation_privacy_sources_runtime": 211.0071,
+      "eval_validation_privacy_sources_samples_per_second": 1.815,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 1309
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_agenda_digitale_loss": 1.5153428316116333,
+      "eval_validation_agenda_digitale_runtime": 187.3358,
+      "eval_validation_agenda_digitale_samples_per_second": 1.815,
+      "eval_validation_agenda_digitale_steps_per_second": 0.907,
+      "step": 1309
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_leggepertutti_loss": 1.3075683116912842,
+      "eval_validation_leggepertutti_runtime": 35.8327,
+      "eval_validation_leggepertutti_samples_per_second": 1.814,
+      "eval_validation_leggepertutti_steps_per_second": 0.921,
+      "step": 1309
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_altalexprivacy_loss": 1.2597737312316895,
+      "eval_validation_altalexprivacy_runtime": 58.4031,
+      "eval_validation_altalexprivacy_samples_per_second": 1.815,
+      "eval_validation_altalexprivacy_steps_per_second": 0.907,
+      "step": 1309
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_stack_loss": 0.53725665807724,
+      "eval_validation_stack_runtime": 190.6517,
+      "eval_validation_stack_samples_per_second": 1.815,
+      "eval_validation_stack_steps_per_second": 0.907,
+      "step": 1309
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.171875,
+      "learning_rate": 1e-05,
+      "loss": 0.9365,
+      "step": 1496
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_privacy_sources_loss": 0.8417152762413025,
+      "eval_validation_privacy_sources_runtime": 210.9207,
+      "eval_validation_privacy_sources_samples_per_second": 1.816,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 1496
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_agenda_digitale_loss": 1.5109071731567383,
+      "eval_validation_agenda_digitale_runtime": 187.2506,
+      "eval_validation_agenda_digitale_samples_per_second": 1.816,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 1496
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_leggepertutti_loss": 1.3020944595336914,
+      "eval_validation_leggepertutti_runtime": 35.811,
+      "eval_validation_leggepertutti_samples_per_second": 1.815,
+      "eval_validation_leggepertutti_steps_per_second": 0.922,
+      "step": 1496
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_altalexprivacy_loss": 1.2524465322494507,
+      "eval_validation_altalexprivacy_runtime": 58.3785,
+      "eval_validation_altalexprivacy_samples_per_second": 1.816,
+      "eval_validation_altalexprivacy_steps_per_second": 0.908,
+      "step": 1496
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_stack_loss": 0.5389564037322998,
+      "eval_validation_stack_runtime": 190.5717,
+      "eval_validation_stack_samples_per_second": 1.816,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 1496
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.734375,
+      "learning_rate": 1e-05,
+      "loss": 0.9186,
+      "step": 1683
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_privacy_sources_loss": 0.8329127430915833,
+      "eval_validation_privacy_sources_runtime": 211.0554,
+      "eval_validation_privacy_sources_samples_per_second": 1.815,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 1683
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_agenda_digitale_loss": 1.505892038345337,
+      "eval_validation_agenda_digitale_runtime": 187.3144,
+      "eval_validation_agenda_digitale_samples_per_second": 1.815,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 1683
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_leggepertutti_loss": 1.296944260597229,
+      "eval_validation_leggepertutti_runtime": 35.8059,
+      "eval_validation_leggepertutti_samples_per_second": 1.815,
+      "eval_validation_leggepertutti_steps_per_second": 0.922,
+      "step": 1683
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_altalexprivacy_loss": 1.241568684577942,
+      "eval_validation_altalexprivacy_runtime": 58.381,
+      "eval_validation_altalexprivacy_samples_per_second": 1.816,
+      "eval_validation_altalexprivacy_steps_per_second": 0.908,
+      "step": 1683
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_stack_loss": 0.5280548334121704,
+      "eval_validation_stack_runtime": 190.6339,
+      "eval_validation_stack_samples_per_second": 1.815,
+      "eval_validation_stack_steps_per_second": 0.907,
+      "step": 1683
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.765625,
+      "learning_rate": 1e-05,
+      "loss": 0.9282,
+      "step": 1870
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_privacy_sources_loss": 0.8271979689598083,
+      "eval_validation_privacy_sources_runtime": 211.0996,
+      "eval_validation_privacy_sources_samples_per_second": 1.814,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 1870
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_agenda_digitale_loss": 1.5014517307281494,
+      "eval_validation_agenda_digitale_runtime": 187.3966,
+      "eval_validation_agenda_digitale_samples_per_second": 1.814,
+      "eval_validation_agenda_digitale_steps_per_second": 0.907,
+      "step": 1870
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_leggepertutti_loss": 1.2852504253387451,
+      "eval_validation_leggepertutti_runtime": 35.8382,
+      "eval_validation_leggepertutti_samples_per_second": 1.814,
+      "eval_validation_leggepertutti_steps_per_second": 0.921,
+      "step": 1870
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_altalexprivacy_loss": 1.231817603111267,
+      "eval_validation_altalexprivacy_runtime": 58.4131,
+      "eval_validation_altalexprivacy_samples_per_second": 1.815,
+      "eval_validation_altalexprivacy_steps_per_second": 0.907,
+      "step": 1870
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_stack_loss": 0.5229911208152771,
+      "eval_validation_stack_runtime": 190.7066,
+      "eval_validation_stack_samples_per_second": 1.814,
+      "eval_validation_stack_steps_per_second": 0.907,
+      "step": 1870
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.1875,
+      "learning_rate": 1e-05,
+      "loss": 0.9263,
+      "step": 2057
+    },
+    {
+      "epoch": 0.28,
+      "eval_validation_privacy_sources_loss": 0.8199824690818787,
+      "eval_validation_privacy_sources_runtime": 211.0532,
+      "eval_validation_privacy_sources_samples_per_second": 1.815,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 2057
+    },
+    {
+      "epoch": 0.28,
+      "eval_validation_agenda_digitale_loss": 1.4965113401412964,
+      "eval_validation_agenda_digitale_runtime": 187.3679,
+      "eval_validation_agenda_digitale_samples_per_second": 1.815,
+      "eval_validation_agenda_digitale_steps_per_second": 0.907,
+      "step": 2057
+    },
+    {
+      "epoch": 0.28,
+      "eval_validation_leggepertutti_loss": 1.2861623764038086,
+      "eval_validation_leggepertutti_runtime": 35.8184,
+      "eval_validation_leggepertutti_samples_per_second": 1.815,
+      "eval_validation_leggepertutti_steps_per_second": 0.921,
+      "step": 2057
+    },
+    {
+      "epoch": 0.28,
+      "eval_validation_altalexprivacy_loss": 1.2276028394699097,
+      "eval_validation_altalexprivacy_runtime": 58.4047,
+      "eval_validation_altalexprivacy_samples_per_second": 1.815,
+      "eval_validation_altalexprivacy_steps_per_second": 0.907,
+      "step": 2057
+    },
+    {
+      "epoch": 0.28,
+      "eval_validation_stack_loss": 0.5233271718025208,
+      "eval_validation_stack_runtime": 190.6786,
+      "eval_validation_stack_samples_per_second": 1.815,
+      "eval_validation_stack_steps_per_second": 0.907,
+      "step": 2057
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 3.03125,
+      "learning_rate": 1e-05,
+      "loss": 0.9055,
+      "step": 2244
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_privacy_sources_loss": 0.8143637180328369,
+      "eval_validation_privacy_sources_runtime": 210.9307,
+      "eval_validation_privacy_sources_samples_per_second": 1.816,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 2244
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_agenda_digitale_loss": 1.4932323694229126,
+      "eval_validation_agenda_digitale_runtime": 187.2867,
+      "eval_validation_agenda_digitale_samples_per_second": 1.815,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 2244
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_leggepertutti_loss": 1.2840496301651,
+      "eval_validation_leggepertutti_runtime": 35.7977,
+      "eval_validation_leggepertutti_samples_per_second": 1.816,
+      "eval_validation_leggepertutti_steps_per_second": 0.922,
+      "step": 2244
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_altalexprivacy_loss": 1.2231019735336304,
+      "eval_validation_altalexprivacy_runtime": 58.3774,
+      "eval_validation_altalexprivacy_samples_per_second": 1.816,
+      "eval_validation_altalexprivacy_steps_per_second": 0.908,
+      "step": 2244
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_stack_loss": 0.5161340236663818,
+      "eval_validation_stack_runtime": 190.6053,
+      "eval_validation_stack_samples_per_second": 1.815,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 2244
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.5625,
+      "learning_rate": 1e-05,
+      "loss": 0.9028,
+      "step": 2431
+    },
+    {
+      "epoch": 0.33,
+      "eval_validation_privacy_sources_loss": 0.8075902462005615,
+      "eval_validation_privacy_sources_runtime": 210.9173,
+      "eval_validation_privacy_sources_samples_per_second": 1.816,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 2431
+    },
+    {
+      "epoch": 0.33,
+      "eval_validation_agenda_digitale_loss": 1.4887945652008057,
+      "eval_validation_agenda_digitale_runtime": 187.2535,
+      "eval_validation_agenda_digitale_samples_per_second": 1.816,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 2431
+    },
+    {
+      "epoch": 0.33,
+      "eval_validation_leggepertutti_loss": 1.2816591262817383,
+      "eval_validation_leggepertutti_runtime": 35.8013,
+      "eval_validation_leggepertutti_samples_per_second": 1.816,
+      "eval_validation_leggepertutti_steps_per_second": 0.922,
+      "step": 2431
+    },
+    {
+      "epoch": 0.33,
+      "eval_validation_altalexprivacy_loss": 1.2183953523635864,
+      "eval_validation_altalexprivacy_runtime": 58.3818,
+      "eval_validation_altalexprivacy_samples_per_second": 1.816,
+      "eval_validation_altalexprivacy_steps_per_second": 0.908,
+      "step": 2431
+    },
+    {
+      "epoch": 0.33,
+      "eval_validation_stack_loss": 0.5140035152435303,
+      "eval_validation_stack_runtime": 190.5309,
+      "eval_validation_stack_samples_per_second": 1.816,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 2431
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.171875,
+      "learning_rate": 1e-05,
+      "loss": 0.886,
+      "step": 2618
+    },
+    {
+      "epoch": 0.36,
+      "eval_validation_privacy_sources_loss": 0.802619218826294,
+      "eval_validation_privacy_sources_runtime": 210.8958,
+      "eval_validation_privacy_sources_samples_per_second": 1.816,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 2618
+    },
+    {
+      "epoch": 0.36,
+      "eval_validation_agenda_digitale_loss": 1.4873639345169067,
+      "eval_validation_agenda_digitale_runtime": 187.2571,
+      "eval_validation_agenda_digitale_samples_per_second": 1.816,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 2618
+    },
+    {
+      "epoch": 0.36,
+      "eval_validation_leggepertutti_loss": 1.278908133506775,
+      "eval_validation_leggepertutti_runtime": 35.8133,
+      "eval_validation_leggepertutti_samples_per_second": 1.815,
+      "eval_validation_leggepertutti_steps_per_second": 0.921,
+      "step": 2618
+    },
+    {
+      "epoch": 0.36,
+      "eval_validation_altalexprivacy_loss": 1.217095136642456,
+      "eval_validation_altalexprivacy_runtime": 58.3847,
+      "eval_validation_altalexprivacy_samples_per_second": 1.816,
+      "eval_validation_altalexprivacy_steps_per_second": 0.908,
+      "step": 2618
+    },
+    {
+      "epoch": 0.36,
+      "eval_validation_stack_loss": 0.5101712346076965,
+      "eval_validation_stack_runtime": 190.5834,
+      "eval_validation_stack_samples_per_second": 1.815,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 2618
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.78125,
+      "learning_rate": 1e-05,
+      "loss": 0.8815,
+      "step": 2805
+    },
+    {
+      "epoch": 0.38,
+      "eval_validation_privacy_sources_loss": 0.796984076499939,
+      "eval_validation_privacy_sources_runtime": 210.8742,
+      "eval_validation_privacy_sources_samples_per_second": 1.816,
+      "eval_validation_privacy_sources_steps_per_second": 0.91,
+      "step": 2805
+    },
+    {
+      "epoch": 0.38,
+      "eval_validation_agenda_digitale_loss": 1.4829306602478027,
+      "eval_validation_agenda_digitale_runtime": 187.223,
+      "eval_validation_agenda_digitale_samples_per_second": 1.816,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 2805
+    },
+    {
+      "epoch": 0.38,
+      "eval_validation_leggepertutti_loss": 1.2758851051330566,
+      "eval_validation_leggepertutti_runtime": 35.8041,
+      "eval_validation_leggepertutti_samples_per_second": 1.815,
+      "eval_validation_leggepertutti_steps_per_second": 0.922,
+      "step": 2805
+    },
+    {
+      "epoch": 0.38,
+      "eval_validation_altalexprivacy_loss": 1.2099803686141968,
+      "eval_validation_altalexprivacy_runtime": 58.3594,
+      "eval_validation_altalexprivacy_samples_per_second": 1.816,
+      "eval_validation_altalexprivacy_steps_per_second": 0.908,
+      "step": 2805
+    },
+    {
+      "epoch": 0.38,
+      "eval_validation_stack_loss": 0.505918562412262,
+      "eval_validation_stack_runtime": 190.523,
+      "eval_validation_stack_samples_per_second": 1.816,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 2805
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.90625,
+      "learning_rate": 1e-05,
+      "loss": 0.8852,
+      "step": 2992
+    },
+    {
+      "epoch": 0.41,
+      "eval_validation_privacy_sources_loss": 0.7935929894447327,
+      "eval_validation_privacy_sources_runtime": 210.8218,
+      "eval_validation_privacy_sources_samples_per_second": 1.817,
+      "eval_validation_privacy_sources_steps_per_second": 0.911,
+      "step": 2992
+    },
+    {
+      "epoch": 0.41,
+      "eval_validation_agenda_digitale_loss": 1.4817965030670166,
+      "eval_validation_agenda_digitale_runtime": 187.1739,
+      "eval_validation_agenda_digitale_samples_per_second": 1.816,
+      "eval_validation_agenda_digitale_steps_per_second": 0.908,
+      "step": 2992
+    },
+    {
+      "epoch": 0.41,
+      "eval_validation_leggepertutti_loss": 1.2713061571121216,
+      "eval_validation_leggepertutti_runtime": 35.7922,
+      "eval_validation_leggepertutti_samples_per_second": 1.816,
+      "eval_validation_leggepertutti_steps_per_second": 0.922,
+      "step": 2992
+    },
+    {
+      "epoch": 0.41,
+      "eval_validation_altalexprivacy_loss": 1.2076174020767212,
+      "eval_validation_altalexprivacy_runtime": 58.3429,
+      "eval_validation_altalexprivacy_samples_per_second": 1.817,
+      "eval_validation_altalexprivacy_steps_per_second": 0.908,
+      "step": 2992
+    },
+    {
+      "epoch": 0.41,
+      "eval_validation_stack_loss": 0.505508542060852,
+      "eval_validation_stack_runtime": 190.5073,
+      "eval_validation_stack_samples_per_second": 1.816,
+      "eval_validation_stack_steps_per_second": 0.908,
+      "step": 2992
+    }
+  ],
+  "logging_steps": 187,
+  "max_steps": 14632,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 187,
+  "total_flos": 1.2548561637545607e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826a37e23a09e1b606e2f71a423c0a9eb586c9a22d37cf5a7293450371d8b58d
+size 4792