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": 37845
+}

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 sha256:23d6bd5bfdca20944accc57eee3fb4c9918430d7a194ba0b315df10b9c2a47bb
+size 4991044576

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d10c9dee130e410ebdcdea1830c2875d4f1c322a27f544bc2ffbc5c7c96c28
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c0908fade7241de72eaa195ba2735df0de94627422e749e7df1235ec3eea6e
+size 4588398592

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14579228672
+  },
+  "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:b742298d88813a00bb6dddc337c9691df4c59fd79344b8a66e828daf53f89849
+size 29158711534

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54f589a3cbef0ef8ce9a09bbd5dc0ead8cb21c6fd1c12773dff16e3681779ad
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de424787aecc67cbfaf6b26f2ed4096b5abe3cdca60e239e3006014ddfe229e9
+size 1000

trainer_state.json

@@ -0,0 +1,673 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3183926616980246,
+  "eval_steps": 93,
+  "global_step": 1581,
+  "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": 22.2771,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1e-05,
+      "loss": 3.3736,
+      "step": 93
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_privacy_sources_loss": 1.4779064655303955,
+      "eval_validation_privacy_sources_runtime": 169.7235,
+      "eval_validation_privacy_sources_samples_per_second": 1.355,
+      "eval_validation_privacy_sources_steps_per_second": 0.678,
+      "step": 93
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_agenda_digitale_loss": 2.152458429336548,
+      "eval_validation_agenda_digitale_runtime": 160.5968,
+      "eval_validation_agenda_digitale_samples_per_second": 1.357,
+      "eval_validation_agenda_digitale_steps_per_second": 0.679,
+      "step": 93
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_leggepertutti_loss": 1.8981273174285889,
+      "eval_validation_leggepertutti_runtime": 28.0044,
+      "eval_validation_leggepertutti_samples_per_second": 1.357,
+      "eval_validation_leggepertutti_steps_per_second": 0.678,
+      "step": 93
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_altalexprivacy_loss": 1.9700795412063599,
+      "eval_validation_altalexprivacy_runtime": 45.7,
+      "eval_validation_altalexprivacy_samples_per_second": 1.357,
+      "eval_validation_altalexprivacy_steps_per_second": 0.678,
+      "step": 93
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 1.7135,
+      "step": 186
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_privacy_sources_loss": 1.289480209350586,
+      "eval_validation_privacy_sources_runtime": 169.4222,
+      "eval_validation_privacy_sources_samples_per_second": 1.358,
+      "eval_validation_privacy_sources_steps_per_second": 0.679,
+      "step": 186
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_agenda_digitale_loss": 1.9645200967788696,
+      "eval_validation_agenda_digitale_runtime": 160.5935,
+      "eval_validation_agenda_digitale_samples_per_second": 1.357,
+      "eval_validation_agenda_digitale_steps_per_second": 0.679,
+      "step": 186
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_leggepertutti_loss": 1.7435646057128906,
+      "eval_validation_leggepertutti_runtime": 27.9989,
+      "eval_validation_leggepertutti_samples_per_second": 1.357,
+      "eval_validation_leggepertutti_steps_per_second": 0.679,
+      "step": 186
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_altalexprivacy_loss": 1.7977099418640137,
+      "eval_validation_altalexprivacy_runtime": 45.6746,
+      "eval_validation_altalexprivacy_samples_per_second": 1.357,
+      "eval_validation_altalexprivacy_steps_per_second": 0.679,
+      "step": 186
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1e-05,
+      "loss": 1.5958,
+      "step": 279
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_privacy_sources_loss": 1.2112126350402832,
+      "eval_validation_privacy_sources_runtime": 169.4752,
+      "eval_validation_privacy_sources_samples_per_second": 1.357,
+      "eval_validation_privacy_sources_steps_per_second": 0.679,
+      "step": 279
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_agenda_digitale_loss": 1.8859468698501587,
+      "eval_validation_agenda_digitale_runtime": 160.6253,
+      "eval_validation_agenda_digitale_samples_per_second": 1.357,
+      "eval_validation_agenda_digitale_steps_per_second": 0.679,
+      "step": 279
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_leggepertutti_loss": 1.6768569946289062,
+      "eval_validation_leggepertutti_runtime": 28.0039,
+      "eval_validation_leggepertutti_samples_per_second": 1.357,
+      "eval_validation_leggepertutti_steps_per_second": 0.678,
+      "step": 279
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_altalexprivacy_loss": 1.7135707139968872,
+      "eval_validation_altalexprivacy_runtime": 45.6744,
+      "eval_validation_altalexprivacy_samples_per_second": 1.357,
+      "eval_validation_altalexprivacy_steps_per_second": 0.679,
+      "step": 279
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1e-05,
+      "loss": 1.5249,
+      "step": 372
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_privacy_sources_loss": 1.1636546850204468,
+      "eval_validation_privacy_sources_runtime": 169.3483,
+      "eval_validation_privacy_sources_samples_per_second": 1.358,
+      "eval_validation_privacy_sources_steps_per_second": 0.679,
+      "step": 372
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_agenda_digitale_loss": 1.839213490486145,
+      "eval_validation_agenda_digitale_runtime": 160.5345,
+      "eval_validation_agenda_digitale_samples_per_second": 1.358,
+      "eval_validation_agenda_digitale_steps_per_second": 0.679,
+      "step": 372
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_leggepertutti_loss": 1.6400021314620972,
+      "eval_validation_leggepertutti_runtime": 27.9724,
+      "eval_validation_leggepertutti_samples_per_second": 1.358,
+      "eval_validation_leggepertutti_steps_per_second": 0.679,
+      "step": 372
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_altalexprivacy_loss": 1.6672061681747437,
+      "eval_validation_altalexprivacy_runtime": 45.6542,
+      "eval_validation_altalexprivacy_samples_per_second": 1.358,
+      "eval_validation_altalexprivacy_steps_per_second": 0.679,
+      "step": 372
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1e-05,
+      "loss": 1.4843,
+      "step": 465
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_privacy_sources_loss": 1.1293103694915771,
+      "eval_validation_privacy_sources_runtime": 169.8454,
+      "eval_validation_privacy_sources_samples_per_second": 1.354,
+      "eval_validation_privacy_sources_steps_per_second": 0.677,
+      "step": 465
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_agenda_digitale_loss": 1.8078429698944092,
+      "eval_validation_agenda_digitale_runtime": 160.9923,
+      "eval_validation_agenda_digitale_samples_per_second": 1.354,
+      "eval_validation_agenda_digitale_steps_per_second": 0.677,
+      "step": 465
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_leggepertutti_loss": 1.6059364080429077,
+      "eval_validation_leggepertutti_runtime": 28.0726,
+      "eval_validation_leggepertutti_samples_per_second": 1.354,
+      "eval_validation_leggepertutti_steps_per_second": 0.677,
+      "step": 465
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_altalexprivacy_loss": 1.62712562084198,
+      "eval_validation_altalexprivacy_runtime": 45.8103,
+      "eval_validation_altalexprivacy_samples_per_second": 1.353,
+      "eval_validation_altalexprivacy_steps_per_second": 0.677,
+      "step": 465
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1e-05,
+      "loss": 1.4525,
+      "step": 558
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_privacy_sources_loss": 1.1031160354614258,
+      "eval_validation_privacy_sources_runtime": 169.8338,
+      "eval_validation_privacy_sources_samples_per_second": 1.354,
+      "eval_validation_privacy_sources_steps_per_second": 0.677,
+      "step": 558
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_agenda_digitale_loss": 1.7819572687149048,
+      "eval_validation_agenda_digitale_runtime": 160.9065,
+      "eval_validation_agenda_digitale_samples_per_second": 1.355,
+      "eval_validation_agenda_digitale_steps_per_second": 0.677,
+      "step": 558
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_leggepertutti_loss": 1.585649847984314,
+      "eval_validation_leggepertutti_runtime": 28.0472,
+      "eval_validation_leggepertutti_samples_per_second": 1.355,
+      "eval_validation_leggepertutti_steps_per_second": 0.677,
+      "step": 558
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_altalexprivacy_loss": 1.6030628681182861,
+      "eval_validation_altalexprivacy_runtime": 45.7744,
+      "eval_validation_altalexprivacy_samples_per_second": 1.354,
+      "eval_validation_altalexprivacy_steps_per_second": 0.677,
+      "step": 558
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 1.4045,
+      "step": 651
+    },
+    {
+      "epoch": 0.54,
+      "eval_validation_privacy_sources_loss": 1.076947808265686,
+      "eval_validation_privacy_sources_runtime": 169.8094,
+      "eval_validation_privacy_sources_samples_per_second": 1.354,
+      "eval_validation_privacy_sources_steps_per_second": 0.677,
+      "step": 651
+    },
+    {
+      "epoch": 0.54,
+      "eval_validation_agenda_digitale_loss": 1.7600467205047607,
+      "eval_validation_agenda_digitale_runtime": 160.9231,
+      "eval_validation_agenda_digitale_samples_per_second": 1.355,
+      "eval_validation_agenda_digitale_steps_per_second": 0.677,
+      "step": 651
+    },
+    {
+      "epoch": 0.54,
+      "eval_validation_leggepertutti_loss": 1.568356990814209,
+      "eval_validation_leggepertutti_runtime": 28.0579,
+      "eval_validation_leggepertutti_samples_per_second": 1.354,
+      "eval_validation_leggepertutti_steps_per_second": 0.677,
+      "step": 651
+    },
+    {
+      "epoch": 0.54,
+      "eval_validation_altalexprivacy_loss": 1.5807151794433594,
+      "eval_validation_altalexprivacy_runtime": 45.7761,
+      "eval_validation_altalexprivacy_samples_per_second": 1.354,
+      "eval_validation_altalexprivacy_steps_per_second": 0.677,
+      "step": 651
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 1.3958,
+      "step": 744
+    },
+    {
+      "epoch": 0.62,
+      "eval_validation_privacy_sources_loss": 1.0633326768875122,
+      "eval_validation_privacy_sources_runtime": 169.7153,
+      "eval_validation_privacy_sources_samples_per_second": 1.355,
+      "eval_validation_privacy_sources_steps_per_second": 0.678,
+      "step": 744
+    },
+    {
+      "epoch": 0.62,
+      "eval_validation_agenda_digitale_loss": 1.7451695203781128,
+      "eval_validation_agenda_digitale_runtime": 160.896,
+      "eval_validation_agenda_digitale_samples_per_second": 1.355,
+      "eval_validation_agenda_digitale_steps_per_second": 0.677,
+      "step": 744
+    },
+    {
+      "epoch": 0.62,
+      "eval_validation_leggepertutti_loss": 1.5583051443099976,
+      "eval_validation_leggepertutti_runtime": 28.048,
+      "eval_validation_leggepertutti_samples_per_second": 1.355,
+      "eval_validation_leggepertutti_steps_per_second": 0.677,
+      "step": 744
+    },
+    {
+      "epoch": 0.62,
+      "eval_validation_altalexprivacy_loss": 1.5672190189361572,
+      "eval_validation_altalexprivacy_runtime": 45.7525,
+      "eval_validation_altalexprivacy_samples_per_second": 1.355,
+      "eval_validation_altalexprivacy_steps_per_second": 0.678,
+      "step": 744
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 1.3715,
+      "step": 837
+    },
+    {
+      "epoch": 0.7,
+      "eval_validation_privacy_sources_loss": 1.046081304550171,
+      "eval_validation_privacy_sources_runtime": 169.714,
+      "eval_validation_privacy_sources_samples_per_second": 1.355,
+      "eval_validation_privacy_sources_steps_per_second": 0.678,
+      "step": 837
+    },
+    {
+      "epoch": 0.7,
+      "eval_validation_agenda_digitale_loss": 1.7291052341461182,
+      "eval_validation_agenda_digitale_runtime": 160.8608,
+      "eval_validation_agenda_digitale_samples_per_second": 1.355,
+      "eval_validation_agenda_digitale_steps_per_second": 0.678,
+      "step": 837
+    },
+    {
+      "epoch": 0.7,
+      "eval_validation_leggepertutti_loss": 1.5531929731369019,
+      "eval_validation_leggepertutti_runtime": 28.0451,
+      "eval_validation_leggepertutti_samples_per_second": 1.355,
+      "eval_validation_leggepertutti_steps_per_second": 0.677,
+      "step": 837
+    },
+    {
+      "epoch": 0.7,
+      "eval_validation_altalexprivacy_loss": 1.5526759624481201,
+      "eval_validation_altalexprivacy_runtime": 45.7626,
+      "eval_validation_altalexprivacy_samples_per_second": 1.355,
+      "eval_validation_altalexprivacy_steps_per_second": 0.677,
+      "step": 837
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1e-05,
+      "loss": 1.3555,
+      "step": 930
+    },
+    {
+      "epoch": 0.78,
+      "eval_validation_privacy_sources_loss": 1.0322965383529663,
+      "eval_validation_privacy_sources_runtime": 169.6103,
+      "eval_validation_privacy_sources_samples_per_second": 1.356,
+      "eval_validation_privacy_sources_steps_per_second": 0.678,
+      "step": 930
+    },
+    {
+      "epoch": 0.78,
+      "eval_validation_agenda_digitale_loss": 1.7139462232589722,
+      "eval_validation_agenda_digitale_runtime": 160.7355,
+      "eval_validation_agenda_digitale_samples_per_second": 1.356,
+      "eval_validation_agenda_digitale_steps_per_second": 0.678,
+      "step": 930
+    },
+    {
+      "epoch": 0.78,
+      "eval_validation_leggepertutti_loss": 1.5367027521133423,
+      "eval_validation_leggepertutti_runtime": 28.027,
+      "eval_validation_leggepertutti_samples_per_second": 1.356,
+      "eval_validation_leggepertutti_steps_per_second": 0.678,
+      "step": 930
+    },
+    {
+      "epoch": 0.78,
+      "eval_validation_altalexprivacy_loss": 1.5342811346054077,
+      "eval_validation_altalexprivacy_runtime": 45.7283,
+      "eval_validation_altalexprivacy_samples_per_second": 1.356,
+      "eval_validation_altalexprivacy_steps_per_second": 0.678,
+      "step": 930
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1e-05,
+      "loss": 1.3566,
+      "step": 1023
+    },
+    {
+      "epoch": 0.85,
+      "eval_validation_privacy_sources_loss": 1.022092342376709,
+      "eval_validation_privacy_sources_runtime": 169.4239,
+      "eval_validation_privacy_sources_samples_per_second": 1.358,
+      "eval_validation_privacy_sources_steps_per_second": 0.679,
+      "step": 1023
+    },
+    {
+      "epoch": 0.85,
+      "eval_validation_agenda_digitale_loss": 1.7054636478424072,
+      "eval_validation_agenda_digitale_runtime": 160.5379,
+      "eval_validation_agenda_digitale_samples_per_second": 1.358,
+      "eval_validation_agenda_digitale_steps_per_second": 0.679,
+      "step": 1023
+    },
+    {
+      "epoch": 0.85,
+      "eval_validation_leggepertutti_loss": 1.5282613039016724,
+      "eval_validation_leggepertutti_runtime": 27.9854,
+      "eval_validation_leggepertutti_samples_per_second": 1.358,
+      "eval_validation_leggepertutti_steps_per_second": 0.679,
+      "step": 1023
+    },
+    {
+      "epoch": 0.85,
+      "eval_validation_altalexprivacy_loss": 1.5194894075393677,
+      "eval_validation_altalexprivacy_runtime": 45.6648,
+      "eval_validation_altalexprivacy_samples_per_second": 1.358,
+      "eval_validation_altalexprivacy_steps_per_second": 0.679,
+      "step": 1023
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1e-05,
+      "loss": 1.3279,
+      "step": 1116
+    },
+    {
+      "epoch": 0.93,
+      "eval_validation_privacy_sources_loss": 1.0133976936340332,
+      "eval_validation_privacy_sources_runtime": 169.5192,
+      "eval_validation_privacy_sources_samples_per_second": 1.357,
+      "eval_validation_privacy_sources_steps_per_second": 0.678,
+      "step": 1116
+    },
+    {
+      "epoch": 0.93,
+      "eval_validation_agenda_digitale_loss": 1.6934592723846436,
+      "eval_validation_agenda_digitale_runtime": 160.703,
+      "eval_validation_agenda_digitale_samples_per_second": 1.357,
+      "eval_validation_agenda_digitale_steps_per_second": 0.678,
+      "step": 1116
+    },
+    {
+      "epoch": 0.93,
+      "eval_validation_leggepertutti_loss": 1.5167473554611206,
+      "eval_validation_leggepertutti_runtime": 28.0019,
+      "eval_validation_leggepertutti_samples_per_second": 1.357,
+      "eval_validation_leggepertutti_steps_per_second": 0.679,
+      "step": 1116
+    },
+    {
+      "epoch": 0.93,
+      "eval_validation_altalexprivacy_loss": 1.5086991786956787,
+      "eval_validation_altalexprivacy_runtime": 45.6936,
+      "eval_validation_altalexprivacy_samples_per_second": 1.357,
+      "eval_validation_altalexprivacy_steps_per_second": 0.678,
+      "step": 1116
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.32,
+      "step": 1209
+    },
+    {
+      "epoch": 1.01,
+      "eval_validation_privacy_sources_loss": 1.0032093524932861,
+      "eval_validation_privacy_sources_runtime": 169.5456,
+      "eval_validation_privacy_sources_samples_per_second": 1.357,
+      "eval_validation_privacy_sources_steps_per_second": 0.678,
+      "step": 1209
+    },
+    {
+      "epoch": 1.01,
+      "eval_validation_agenda_digitale_loss": 1.68604576587677,
+      "eval_validation_agenda_digitale_runtime": 160.6963,
+      "eval_validation_agenda_digitale_samples_per_second": 1.357,
+      "eval_validation_agenda_digitale_steps_per_second": 0.678,
+      "step": 1209
+    },
+    {
+      "epoch": 1.01,
+      "eval_validation_leggepertutti_loss": 1.5239654779434204,
+      "eval_validation_leggepertutti_runtime": 28.0205,
+      "eval_validation_leggepertutti_samples_per_second": 1.356,
+      "eval_validation_leggepertutti_steps_per_second": 0.678,
+      "step": 1209
+    },
+    {
+      "epoch": 1.01,
+      "eval_validation_altalexprivacy_loss": 1.5007380247116089,
+      "eval_validation_altalexprivacy_runtime": 45.7063,
+      "eval_validation_altalexprivacy_samples_per_second": 1.356,
+      "eval_validation_altalexprivacy_steps_per_second": 0.678,
+      "step": 1209
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1998,
+      "step": 1302
+    },
+    {
+      "epoch": 1.09,
+      "eval_validation_privacy_sources_loss": 0.9907514452934265,
+      "eval_validation_privacy_sources_runtime": 169.4228,
+      "eval_validation_privacy_sources_samples_per_second": 1.358,
+      "eval_validation_privacy_sources_steps_per_second": 0.679,
+      "step": 1302
+    },
+    {
+      "epoch": 1.09,
+      "eval_validation_agenda_digitale_loss": 1.6758071184158325,
+      "eval_validation_agenda_digitale_runtime": 160.6151,
+      "eval_validation_agenda_digitale_samples_per_second": 1.357,
+      "eval_validation_agenda_digitale_steps_per_second": 0.679,
+      "step": 1302
+    },
+    {
+      "epoch": 1.09,
+      "eval_validation_leggepertutti_loss": 1.5173066854476929,
+      "eval_validation_leggepertutti_runtime": 27.9869,
+      "eval_validation_leggepertutti_samples_per_second": 1.358,
+      "eval_validation_leggepertutti_steps_per_second": 0.679,
+      "step": 1302
+    },
+    {
+      "epoch": 1.09,
+      "eval_validation_altalexprivacy_loss": 1.4873181581497192,
+      "eval_validation_altalexprivacy_runtime": 45.6834,
+      "eval_validation_altalexprivacy_samples_per_second": 1.357,
+      "eval_validation_altalexprivacy_steps_per_second": 0.679,
+      "step": 1302
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1635,
+      "step": 1395
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_privacy_sources_loss": 0.98543781042099,
+      "eval_validation_privacy_sources_runtime": 169.7781,
+      "eval_validation_privacy_sources_samples_per_second": 1.355,
+      "eval_validation_privacy_sources_steps_per_second": 0.677,
+      "step": 1395
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_agenda_digitale_loss": 1.671740174293518,
+      "eval_validation_agenda_digitale_runtime": 160.8659,
+      "eval_validation_agenda_digitale_samples_per_second": 1.355,
+      "eval_validation_agenda_digitale_steps_per_second": 0.678,
+      "step": 1395
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_leggepertutti_loss": 1.5131033658981323,
+      "eval_validation_leggepertutti_runtime": 28.0459,
+      "eval_validation_leggepertutti_samples_per_second": 1.355,
+      "eval_validation_leggepertutti_steps_per_second": 0.677,
+      "step": 1395
+    },
+    {
+      "epoch": 1.16,
+      "eval_validation_altalexprivacy_loss": 1.4810400009155273,
+      "eval_validation_altalexprivacy_runtime": 45.7413,
+      "eval_validation_altalexprivacy_samples_per_second": 1.355,
+      "eval_validation_altalexprivacy_steps_per_second": 0.678,
+      "step": 1395
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.188,
+      "step": 1488
+    },
+    {
+      "epoch": 1.24,
+      "eval_validation_privacy_sources_loss": 0.981711745262146,
+      "eval_validation_privacy_sources_runtime": 169.7712,
+      "eval_validation_privacy_sources_samples_per_second": 1.355,
+      "eval_validation_privacy_sources_steps_per_second": 0.677,
+      "step": 1488
+    },
+    {
+      "epoch": 1.24,
+      "eval_validation_agenda_digitale_loss": 1.669861078262329,
+      "eval_validation_agenda_digitale_runtime": 160.8963,
+      "eval_validation_agenda_digitale_samples_per_second": 1.355,
+      "eval_validation_agenda_digitale_steps_per_second": 0.677,
+      "step": 1488
+    },
+    {
+      "epoch": 1.24,
+      "eval_validation_leggepertutti_loss": 1.5106905698776245,
+      "eval_validation_leggepertutti_runtime": 28.0461,
+      "eval_validation_leggepertutti_samples_per_second": 1.355,
+      "eval_validation_leggepertutti_steps_per_second": 0.677,
+      "step": 1488
+    },
+    {
+      "epoch": 1.24,
+      "eval_validation_altalexprivacy_loss": 1.4784834384918213,
+      "eval_validation_altalexprivacy_runtime": 45.7714,
+      "eval_validation_altalexprivacy_samples_per_second": 1.355,
+      "eval_validation_altalexprivacy_steps_per_second": 0.677,
+      "step": 1488
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.169,
+      "step": 1581
+    },
+    {
+      "epoch": 1.32,
+      "eval_validation_privacy_sources_loss": 0.9772719740867615,
+      "eval_validation_privacy_sources_runtime": 169.5316,
+      "eval_validation_privacy_sources_samples_per_second": 1.357,
+      "eval_validation_privacy_sources_steps_per_second": 0.678,
+      "step": 1581
+    },
+    {
+      "epoch": 1.32,
+      "eval_validation_agenda_digitale_loss": 1.6676079034805298,
+      "eval_validation_agenda_digitale_runtime": 160.8887,
+      "eval_validation_agenda_digitale_samples_per_second": 1.355,
+      "eval_validation_agenda_digitale_steps_per_second": 0.677,
+      "step": 1581
+    },
+    {
+      "epoch": 1.32,
+      "eval_validation_leggepertutti_loss": 1.5096626281738281,
+      "eval_validation_leggepertutti_runtime": 28.0405,
+      "eval_validation_leggepertutti_samples_per_second": 1.355,
+      "eval_validation_leggepertutti_steps_per_second": 0.678,
+      "step": 1581
+    },
+    {
+      "epoch": 1.32,
+      "eval_validation_altalexprivacy_loss": 1.4747135639190674,
+      "eval_validation_altalexprivacy_runtime": 45.7877,
+      "eval_validation_altalexprivacy_samples_per_second": 1.354,
+      "eval_validation_altalexprivacy_steps_per_second": 0.677,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 93,
+  "max_steps": 2398,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 93,
+  "total_flos": 1.7741598460471149e+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 sha256:11d2f30289e9418cdc83eea0ade19c0773f84bd56b99965a4786332c67175c42
+size 4792