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": "4.38.0.dev0",
+  "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": "4.38.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4d2ab6e7c9b74eba6d9e46cdcabe3526491b02ecee8c1a4b40866198ed6f76
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7eb288100be3ee1b8649f8649ed6f847387ee68d49ed96df77cb3ff1158faa
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ead1e05bc4a615e23f5d1f9020a6599101eb4393fa0215720a6b1faa19fc1ce
+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:e7c540959445d12e5d079642aadb6870c1578773e291b4634edc928c1c2ff1bf
+size 28967182538

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c60d2a1e8b44fd78e0b85059c03c82fa570f9a225c06e53dacd3368476f4b2a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e760fb832771d138c43e11ea1be6d034038b28af491760c5f2a85af27f846a92
+size 1000

trainer_state.json

@@ -0,0 +1,749 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2239490887051387,
+  "eval_steps": 93,
+  "global_step": 1767,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 1.2904,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1e-05,
+      "loss": 1.2883,
+      "step": 93
+    },
+    {
+      "epoch": 0.06,
+      "eval_validation_privacy_sources_loss": 0.931429386138916,
+      "eval_validation_privacy_sources_runtime": 224.921,
+      "eval_validation_privacy_sources_samples_per_second": 1.258,
+      "eval_validation_privacy_sources_steps_per_second": 0.631,
+      "step": 93
+    },
+    {
+      "epoch": 0.06,
+      "eval_validation_agenda_digitale_loss": 1.4688478708267212,
+      "eval_validation_agenda_digitale_runtime": 201.5869,
+      "eval_validation_agenda_digitale_samples_per_second": 1.26,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 93
+    },
+    {
+      "epoch": 0.06,
+      "eval_validation_leggepertutti_loss": 1.293728232383728,
+      "eval_validation_leggepertutti_runtime": 37.3205,
+      "eval_validation_leggepertutti_samples_per_second": 1.259,
+      "eval_validation_leggepertutti_steps_per_second": 0.643,
+      "step": 93
+    },
+    {
+      "epoch": 0.06,
+      "eval_validation_altalexprivacy_loss": 1.3008275032043457,
+      "eval_validation_altalexprivacy_runtime": 62.7339,
+      "eval_validation_altalexprivacy_samples_per_second": 1.259,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 93
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1e-05,
+      "loss": 1.1632,
+      "step": 186
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_privacy_sources_loss": 0.8801236152648926,
+      "eval_validation_privacy_sources_runtime": 224.5622,
+      "eval_validation_privacy_sources_samples_per_second": 1.26,
+      "eval_validation_privacy_sources_steps_per_second": 0.632,
+      "step": 186
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_agenda_digitale_loss": 1.4332246780395508,
+      "eval_validation_agenda_digitale_runtime": 201.5945,
+      "eval_validation_agenda_digitale_samples_per_second": 1.26,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 186
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_leggepertutti_loss": 1.2643470764160156,
+      "eval_validation_leggepertutti_runtime": 37.3205,
+      "eval_validation_leggepertutti_samples_per_second": 1.259,
+      "eval_validation_leggepertutti_steps_per_second": 0.643,
+      "step": 186
+    },
+    {
+      "epoch": 0.13,
+      "eval_validation_altalexprivacy_loss": 1.2626982927322388,
+      "eval_validation_altalexprivacy_runtime": 62.7289,
+      "eval_validation_altalexprivacy_samples_per_second": 1.259,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 186
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1e-05,
+      "loss": 1.1339,
+      "step": 279
+    },
+    {
+      "epoch": 0.19,
+      "eval_validation_privacy_sources_loss": 0.8503767251968384,
+      "eval_validation_privacy_sources_runtime": 224.5704,
+      "eval_validation_privacy_sources_samples_per_second": 1.26,
+      "eval_validation_privacy_sources_steps_per_second": 0.632,
+      "step": 279
+    },
+    {
+      "epoch": 0.19,
+      "eval_validation_agenda_digitale_loss": 1.4141554832458496,
+      "eval_validation_agenda_digitale_runtime": 201.4979,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 279
+    },
+    {
+      "epoch": 0.19,
+      "eval_validation_leggepertutti_loss": 1.2566713094711304,
+      "eval_validation_leggepertutti_runtime": 37.3026,
+      "eval_validation_leggepertutti_samples_per_second": 1.26,
+      "eval_validation_leggepertutti_steps_per_second": 0.643,
+      "step": 279
+    },
+    {
+      "epoch": 0.19,
+      "eval_validation_altalexprivacy_loss": 1.2368062734603882,
+      "eval_validation_altalexprivacy_runtime": 62.6933,
+      "eval_validation_altalexprivacy_samples_per_second": 1.26,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 279
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1e-05,
+      "loss": 1.1007,
+      "step": 372
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_privacy_sources_loss": 0.8314403295516968,
+      "eval_validation_privacy_sources_runtime": 224.5386,
+      "eval_validation_privacy_sources_samples_per_second": 1.26,
+      "eval_validation_privacy_sources_steps_per_second": 0.632,
+      "step": 372
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_agenda_digitale_loss": 1.3996949195861816,
+      "eval_validation_agenda_digitale_runtime": 201.5206,
+      "eval_validation_agenda_digitale_samples_per_second": 1.26,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 372
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_leggepertutti_loss": 1.2466578483581543,
+      "eval_validation_leggepertutti_runtime": 37.3026,
+      "eval_validation_leggepertutti_samples_per_second": 1.26,
+      "eval_validation_leggepertutti_steps_per_second": 0.643,
+      "step": 372
+    },
+    {
+      "epoch": 0.26,
+      "eval_validation_altalexprivacy_loss": 1.2185348272323608,
+      "eval_validation_altalexprivacy_runtime": 62.6898,
+      "eval_validation_altalexprivacy_samples_per_second": 1.26,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 372
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1e-05,
+      "loss": 1.0747,
+      "step": 465
+    },
+    {
+      "epoch": 0.32,
+      "eval_validation_privacy_sources_loss": 0.8157272338867188,
+      "eval_validation_privacy_sources_runtime": 224.5077,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.632,
+      "step": 465
+    },
+    {
+      "epoch": 0.32,
+      "eval_validation_agenda_digitale_loss": 1.3890674114227295,
+      "eval_validation_agenda_digitale_runtime": 201.5006,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 465
+    },
+    {
+      "epoch": 0.32,
+      "eval_validation_leggepertutti_loss": 1.2424800395965576,
+      "eval_validation_leggepertutti_runtime": 37.28,
+      "eval_validation_leggepertutti_samples_per_second": 1.261,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 465
+    },
+    {
+      "epoch": 0.32,
+      "eval_validation_altalexprivacy_loss": 1.203458547592163,
+      "eval_validation_altalexprivacy_runtime": 62.6722,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 465
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1e-05,
+      "loss": 1.0703,
+      "step": 558
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_privacy_sources_loss": 0.8016490936279297,
+      "eval_validation_privacy_sources_runtime": 224.4789,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 558
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_agenda_digitale_loss": 1.3786152601242065,
+      "eval_validation_agenda_digitale_runtime": 201.4702,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 558
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_leggepertutti_loss": 1.23654043674469,
+      "eval_validation_leggepertutti_runtime": 37.2956,
+      "eval_validation_leggepertutti_samples_per_second": 1.26,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 558
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_altalexprivacy_loss": 1.1914178133010864,
+      "eval_validation_altalexprivacy_runtime": 62.6741,
+      "eval_validation_altalexprivacy_samples_per_second": 1.26,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 558
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 1.0514,
+      "step": 651
+    },
+    {
+      "epoch": 0.45,
+      "eval_validation_privacy_sources_loss": 0.7911774516105652,
+      "eval_validation_privacy_sources_runtime": 224.3988,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 651
+    },
+    {
+      "epoch": 0.45,
+      "eval_validation_agenda_digitale_loss": 1.370524525642395,
+      "eval_validation_agenda_digitale_runtime": 201.3956,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.631,
+      "step": 651
+    },
+    {
+      "epoch": 0.45,
+      "eval_validation_leggepertutti_loss": 1.2246781587600708,
+      "eval_validation_leggepertutti_runtime": 37.2851,
+      "eval_validation_leggepertutti_samples_per_second": 1.261,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 651
+    },
+    {
+      "epoch": 0.45,
+      "eval_validation_altalexprivacy_loss": 1.1746492385864258,
+      "eval_validation_altalexprivacy_runtime": 62.6484,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 651
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 1.0495,
+      "step": 744
+    },
+    {
+      "epoch": 0.52,
+      "eval_validation_privacy_sources_loss": 0.7825378775596619,
+      "eval_validation_privacy_sources_runtime": 224.4583,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 744
+    },
+    {
+      "epoch": 0.52,
+      "eval_validation_agenda_digitale_loss": 1.3625833988189697,
+      "eval_validation_agenda_digitale_runtime": 201.4512,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 744
+    },
+    {
+      "epoch": 0.52,
+      "eval_validation_leggepertutti_loss": 1.2221735715866089,
+      "eval_validation_leggepertutti_runtime": 37.2828,
+      "eval_validation_leggepertutti_samples_per_second": 1.261,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 744
+    },
+    {
+      "epoch": 0.52,
+      "eval_validation_altalexprivacy_loss": 1.1648091077804565,
+      "eval_validation_altalexprivacy_runtime": 62.6567,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 744
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1e-05,
+      "loss": 1.0352,
+      "step": 837
+    },
+    {
+      "epoch": 0.58,
+      "eval_validation_privacy_sources_loss": 0.7749003171920776,
+      "eval_validation_privacy_sources_runtime": 224.4818,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 837
+    },
+    {
+      "epoch": 0.58,
+      "eval_validation_agenda_digitale_loss": 1.3573260307312012,
+      "eval_validation_agenda_digitale_runtime": 201.5563,
+      "eval_validation_agenda_digitale_samples_per_second": 1.26,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 837
+    },
+    {
+      "epoch": 0.58,
+      "eval_validation_leggepertutti_loss": 1.2192293405532837,
+      "eval_validation_leggepertutti_runtime": 37.3176,
+      "eval_validation_leggepertutti_samples_per_second": 1.259,
+      "eval_validation_leggepertutti_steps_per_second": 0.643,
+      "step": 837
+    },
+    {
+      "epoch": 0.58,
+      "eval_validation_altalexprivacy_loss": 1.157555103302002,
+      "eval_validation_altalexprivacy_runtime": 62.6856,
+      "eval_validation_altalexprivacy_samples_per_second": 1.26,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 837
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1e-05,
+      "loss": 1.0313,
+      "step": 930
+    },
+    {
+      "epoch": 0.64,
+      "eval_validation_privacy_sources_loss": 0.7667441368103027,
+      "eval_validation_privacy_sources_runtime": 224.4122,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 930
+    },
+    {
+      "epoch": 0.64,
+      "eval_validation_agenda_digitale_loss": 1.3520750999450684,
+      "eval_validation_agenda_digitale_runtime": 201.3866,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.631,
+      "step": 930
+    },
+    {
+      "epoch": 0.64,
+      "eval_validation_leggepertutti_loss": 1.2199019193649292,
+      "eval_validation_leggepertutti_runtime": 37.2711,
+      "eval_validation_leggepertutti_samples_per_second": 1.261,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 930
+    },
+    {
+      "epoch": 0.64,
+      "eval_validation_altalexprivacy_loss": 1.1514625549316406,
+      "eval_validation_altalexprivacy_runtime": 62.655,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 930
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1e-05,
+      "loss": 1.0224,
+      "step": 1023
+    },
+    {
+      "epoch": 0.71,
+      "eval_validation_privacy_sources_loss": 0.7590793371200562,
+      "eval_validation_privacy_sources_runtime": 224.4414,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 1023
+    },
+    {
+      "epoch": 0.71,
+      "eval_validation_agenda_digitale_loss": 1.3455318212509155,
+      "eval_validation_agenda_digitale_runtime": 201.454,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 1023
+    },
+    {
+      "epoch": 0.71,
+      "eval_validation_leggepertutti_loss": 1.214867353439331,
+      "eval_validation_leggepertutti_runtime": 37.2952,
+      "eval_validation_leggepertutti_samples_per_second": 1.26,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1023
+    },
+    {
+      "epoch": 0.71,
+      "eval_validation_altalexprivacy_loss": 1.1438390016555786,
+      "eval_validation_altalexprivacy_runtime": 62.655,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 1023
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1e-05,
+      "loss": 1.0195,
+      "step": 1116
+    },
+    {
+      "epoch": 0.77,
+      "eval_validation_privacy_sources_loss": 0.7519943714141846,
+      "eval_validation_privacy_sources_runtime": 224.249,
+      "eval_validation_privacy_sources_samples_per_second": 1.262,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 1116
+    },
+    {
+      "epoch": 0.77,
+      "eval_validation_agenda_digitale_loss": 1.3410755395889282,
+      "eval_validation_agenda_digitale_runtime": 201.2729,
+      "eval_validation_agenda_digitale_samples_per_second": 1.262,
+      "eval_validation_agenda_digitale_steps_per_second": 0.631,
+      "step": 1116
+    },
+    {
+      "epoch": 0.77,
+      "eval_validation_leggepertutti_loss": 1.212862253189087,
+      "eval_validation_leggepertutti_runtime": 37.2526,
+      "eval_validation_leggepertutti_samples_per_second": 1.262,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1116
+    },
+    {
+      "epoch": 0.77,
+      "eval_validation_altalexprivacy_loss": 1.1395570039749146,
+      "eval_validation_altalexprivacy_runtime": 62.6197,
+      "eval_validation_altalexprivacy_samples_per_second": 1.262,
+      "eval_validation_altalexprivacy_steps_per_second": 0.639,
+      "step": 1116
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1e-05,
+      "loss": 1.01,
+      "step": 1209
+    },
+    {
+      "epoch": 0.84,
+      "eval_validation_privacy_sources_loss": 0.7464994192123413,
+      "eval_validation_privacy_sources_runtime": 224.331,
+      "eval_validation_privacy_sources_samples_per_second": 1.262,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 1209
+    },
+    {
+      "epoch": 0.84,
+      "eval_validation_agenda_digitale_loss": 1.3382426500320435,
+      "eval_validation_agenda_digitale_runtime": 201.3361,
+      "eval_validation_agenda_digitale_samples_per_second": 1.262,
+      "eval_validation_agenda_digitale_steps_per_second": 0.631,
+      "step": 1209
+    },
+    {
+      "epoch": 0.84,
+      "eval_validation_leggepertutti_loss": 1.2104753255844116,
+      "eval_validation_leggepertutti_runtime": 37.2604,
+      "eval_validation_leggepertutti_samples_per_second": 1.261,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1209
+    },
+    {
+      "epoch": 0.84,
+      "eval_validation_altalexprivacy_loss": 1.1286804676055908,
+      "eval_validation_altalexprivacy_runtime": 62.6291,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.639,
+      "step": 1209
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1e-05,
+      "loss": 1.0002,
+      "step": 1302
+    },
+    {
+      "epoch": 0.9,
+      "eval_validation_privacy_sources_loss": 0.7395791411399841,
+      "eval_validation_privacy_sources_runtime": 224.281,
+      "eval_validation_privacy_sources_samples_per_second": 1.262,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 1302
+    },
+    {
+      "epoch": 0.9,
+      "eval_validation_agenda_digitale_loss": 1.3336013555526733,
+      "eval_validation_agenda_digitale_runtime": 201.3141,
+      "eval_validation_agenda_digitale_samples_per_second": 1.262,
+      "eval_validation_agenda_digitale_steps_per_second": 0.631,
+      "step": 1302
+    },
+    {
+      "epoch": 0.9,
+      "eval_validation_leggepertutti_loss": 1.2045289278030396,
+      "eval_validation_leggepertutti_runtime": 37.2746,
+      "eval_validation_leggepertutti_samples_per_second": 1.261,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1302
+    },
+    {
+      "epoch": 0.9,
+      "eval_validation_altalexprivacy_loss": 1.123989462852478,
+      "eval_validation_altalexprivacy_runtime": 62.6426,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.639,
+      "step": 1302
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1e-05,
+      "loss": 0.9931,
+      "step": 1395
+    },
+    {
+      "epoch": 0.97,
+      "eval_validation_privacy_sources_loss": 0.7345882058143616,
+      "eval_validation_privacy_sources_runtime": 224.3777,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 1395
+    },
+    {
+      "epoch": 0.97,
+      "eval_validation_agenda_digitale_loss": 1.3300620317459106,
+      "eval_validation_agenda_digitale_runtime": 201.3784,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.631,
+      "step": 1395
+    },
+    {
+      "epoch": 0.97,
+      "eval_validation_leggepertutti_loss": 1.2069214582443237,
+      "eval_validation_leggepertutti_runtime": 37.2549,
+      "eval_validation_leggepertutti_samples_per_second": 1.262,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1395
+    },
+    {
+      "epoch": 0.97,
+      "eval_validation_altalexprivacy_loss": 1.1184239387512207,
+      "eval_validation_altalexprivacy_runtime": 62.6446,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.639,
+      "step": 1395
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.9333,
+      "step": 1488
+    },
+    {
+      "epoch": 1.03,
+      "eval_validation_privacy_sources_loss": 0.7288182973861694,
+      "eval_validation_privacy_sources_runtime": 224.5187,
+      "eval_validation_privacy_sources_samples_per_second": 1.26,
+      "eval_validation_privacy_sources_steps_per_second": 0.632,
+      "step": 1488
+    },
+    {
+      "epoch": 1.03,
+      "eval_validation_agenda_digitale_loss": 1.3277981281280518,
+      "eval_validation_agenda_digitale_runtime": 201.453,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 1488
+    },
+    {
+      "epoch": 1.03,
+      "eval_validation_leggepertutti_loss": 1.2111519575119019,
+      "eval_validation_leggepertutti_runtime": 37.295,
+      "eval_validation_leggepertutti_samples_per_second": 1.26,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1488
+    },
+    {
+      "epoch": 1.03,
+      "eval_validation_altalexprivacy_loss": 1.117422342300415,
+      "eval_validation_altalexprivacy_runtime": 62.6903,
+      "eval_validation_altalexprivacy_samples_per_second": 1.26,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 1488
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.8793,
+      "step": 1581
+    },
+    {
+      "epoch": 1.1,
+      "eval_validation_privacy_sources_loss": 0.725307047367096,
+      "eval_validation_privacy_sources_runtime": 224.423,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 1581
+    },
+    {
+      "epoch": 1.1,
+      "eval_validation_agenda_digitale_loss": 1.3268777132034302,
+      "eval_validation_agenda_digitale_runtime": 201.4386,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 1581
+    },
+    {
+      "epoch": 1.1,
+      "eval_validation_leggepertutti_loss": 1.2145886421203613,
+      "eval_validation_leggepertutti_runtime": 37.2788,
+      "eval_validation_leggepertutti_samples_per_second": 1.261,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1581
+    },
+    {
+      "epoch": 1.1,
+      "eval_validation_altalexprivacy_loss": 1.115631341934204,
+      "eval_validation_altalexprivacy_runtime": 62.6623,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 1581
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.8635,
+      "step": 1674
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_privacy_sources_loss": 0.7225270867347717,
+      "eval_validation_privacy_sources_runtime": 224.4785,
+      "eval_validation_privacy_sources_samples_per_second": 1.261,
+      "eval_validation_privacy_sources_steps_per_second": 0.633,
+      "step": 1674
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_agenda_digitale_loss": 1.3245998620986938,
+      "eval_validation_agenda_digitale_runtime": 201.4232,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.631,
+      "step": 1674
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_leggepertutti_loss": 1.2109320163726807,
+      "eval_validation_leggepertutti_runtime": 37.278,
+      "eval_validation_leggepertutti_samples_per_second": 1.261,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1674
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_altalexprivacy_loss": 1.1129626035690308,
+      "eval_validation_altalexprivacy_runtime": 62.6648,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 1674
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.864,
+      "step": 1767
+    },
+    {
+      "epoch": 1.22,
+      "eval_validation_privacy_sources_loss": 0.7220005989074707,
+      "eval_validation_privacy_sources_runtime": 224.574,
+      "eval_validation_privacy_sources_samples_per_second": 1.26,
+      "eval_validation_privacy_sources_steps_per_second": 0.632,
+      "step": 1767
+    },
+    {
+      "epoch": 1.22,
+      "eval_validation_agenda_digitale_loss": 1.324655532836914,
+      "eval_validation_agenda_digitale_runtime": 201.4962,
+      "eval_validation_agenda_digitale_samples_per_second": 1.261,
+      "eval_validation_agenda_digitale_steps_per_second": 0.63,
+      "step": 1767
+    },
+    {
+      "epoch": 1.22,
+      "eval_validation_leggepertutti_loss": 1.213049054145813,
+      "eval_validation_leggepertutti_runtime": 37.2931,
+      "eval_validation_leggepertutti_samples_per_second": 1.26,
+      "eval_validation_leggepertutti_steps_per_second": 0.644,
+      "step": 1767
+    },
+    {
+      "epoch": 1.22,
+      "eval_validation_altalexprivacy_loss": 1.1131935119628906,
+      "eval_validation_altalexprivacy_runtime": 62.6673,
+      "eval_validation_altalexprivacy_samples_per_second": 1.261,
+      "eval_validation_altalexprivacy_steps_per_second": 0.638,
+      "step": 1767
+    }
+  ],
+  "logging_steps": 93,
+  "max_steps": 2886,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 93,
+  "total_flos": 1.9762306963942146e+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 sha256:129ff86dd442515bf4e6ebaea37a2e5ce00e81d4b29245730d4318f99c5f4d8e
+size 4664