Upload folder using huggingface_hub

config.json

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

generation_config.json

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

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528a2b964295aca4003035271c33b00b5fe254c72e7e8587de06a132d8e9fec1
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960d7d24cc2027e22b1712179ab63f7a9a304b8f6f03699f2d49623a31c5b288
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef675e87ea5568a4f7dee2e678c66d2d6d2b0aaeecb576c0309782e636e89ee0
+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 sha256:14ec130a892766f75c217bff262041b517cb2c58d7c184b8dddc3da9a6421c7d
+size 28967182538

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055c41c62dfa2eea5baabf03e7ba33603de704c81765c1c934ef50fd3eb738ff
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfef4f1da59516232cba70a35d55777efc96017896b3166b41fc3b40ec1377e
+size 1000

trainer_state.json

@@ -0,0 +1,592 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.47084125631106155,
+  "eval_steps": 187,
+  "global_step": 2244,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 10.4375,
+      "learning_rate": 2.1276595744680852e-07,
+      "loss": 1.5104,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.90625,
+      "learning_rate": 1e-05,
+      "loss": 1.1784,
+      "step": 187
+    },
+    {
+      "epoch": 0.04,
+      "eval_validation_loss": 0.956233024597168,
+      "eval_validation_runtime": 190.0844,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 187
+    },
+    {
+      "epoch": 0.04,
+      "eval_validation_privacy_sources_loss": 0.956233024597168,
+      "eval_validation_privacy_sources_runtime": 190.1247,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 187
+    },
+    {
+      "epoch": 0.04,
+      "eval_validation_agenda_digitale_loss": 1.5249053239822388,
+      "eval_validation_agenda_digitale_runtime": 170.8208,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 187
+    },
+    {
+      "epoch": 0.04,
+      "eval_validation_legal_articles_loss": 1.4138059616088867,
+      "eval_validation_legal_articles_runtime": 274.0975,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 187
+    },
+    {
+      "epoch": 0.04,
+      "eval_validation_leggepertutti_loss": 1.2507734298706055,
+      "eval_validation_leggepertutti_runtime": 26.1774,
+      "eval_validation_leggepertutti_samples_per_second": 0.726,
+      "eval_validation_leggepertutti_steps_per_second": 0.726,
+      "step": 187
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.5625,
+      "learning_rate": 1e-05,
+      "loss": 1.0602,
+      "step": 374
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_loss": 0.9068162441253662,
+      "eval_validation_runtime": 190.0623,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 374
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_privacy_sources_loss": 0.9068162441253662,
+      "eval_validation_privacy_sources_runtime": 190.1749,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 374
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_agenda_digitale_loss": 1.5025277137756348,
+      "eval_validation_agenda_digitale_runtime": 170.8116,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 374
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_legal_articles_loss": 1.3901658058166504,
+      "eval_validation_legal_articles_runtime": 274.2187,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 374
+    },
+    {
+      "epoch": 0.08,
+      "eval_validation_leggepertutti_loss": 1.2389607429504395,
+      "eval_validation_leggepertutti_runtime": 26.1823,
+      "eval_validation_leggepertutti_samples_per_second": 0.726,
+      "eval_validation_leggepertutti_steps_per_second": 0.726,
+      "step": 374
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.375,
+      "learning_rate": 1e-05,
+      "loss": 0.9973,
+      "step": 561
+    },
+    {
+      "epoch": 0.12,
+      "eval_validation_loss": 0.8726317286491394,
+      "eval_validation_runtime": 190.0376,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 561
+    },
+    {
+      "epoch": 0.12,
+      "eval_validation_privacy_sources_loss": 0.8726317286491394,
+      "eval_validation_privacy_sources_runtime": 189.9977,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 561
+    },
+    {
+      "epoch": 0.12,
+      "eval_validation_agenda_digitale_loss": 1.4876974821090698,
+      "eval_validation_agenda_digitale_runtime": 170.7148,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 561
+    },
+    {
+      "epoch": 0.12,
+      "eval_validation_legal_articles_loss": 1.3721040487289429,
+      "eval_validation_legal_articles_runtime": 273.9951,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 561
+    },
+    {
+      "epoch": 0.12,
+      "eval_validation_leggepertutti_loss": 1.213807463645935,
+      "eval_validation_leggepertutti_runtime": 26.1576,
+      "eval_validation_leggepertutti_samples_per_second": 0.726,
+      "eval_validation_leggepertutti_steps_per_second": 0.726,
+      "step": 561
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.734375,
+      "learning_rate": 1e-05,
+      "loss": 0.9936,
+      "step": 748
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_loss": 0.8519095778465271,
+      "eval_validation_runtime": 190.0914,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 748
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_privacy_sources_loss": 0.8519095778465271,
+      "eval_validation_privacy_sources_runtime": 190.1871,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 748
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_agenda_digitale_loss": 1.4739274978637695,
+      "eval_validation_agenda_digitale_runtime": 170.8961,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 748
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_legal_articles_loss": 1.3598031997680664,
+      "eval_validation_legal_articles_runtime": 274.1856,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 748
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_leggepertutti_loss": 1.2074390649795532,
+      "eval_validation_leggepertutti_runtime": 26.177,
+      "eval_validation_leggepertutti_samples_per_second": 0.726,
+      "eval_validation_leggepertutti_steps_per_second": 0.726,
+      "step": 748
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.90625,
+      "learning_rate": 1e-05,
+      "loss": 0.9671,
+      "step": 935
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_loss": 0.8343605399131775,
+      "eval_validation_runtime": 190.0578,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 935
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_privacy_sources_loss": 0.8343605399131775,
+      "eval_validation_privacy_sources_runtime": 190.0981,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 935
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_agenda_digitale_loss": 1.4663511514663696,
+      "eval_validation_agenda_digitale_runtime": 170.7988,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 935
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_legal_articles_loss": 1.3504709005355835,
+      "eval_validation_legal_articles_runtime": 274.1096,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 935
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_leggepertutti_loss": 1.19623863697052,
+      "eval_validation_leggepertutti_runtime": 26.1751,
+      "eval_validation_leggepertutti_samples_per_second": 0.726,
+      "eval_validation_leggepertutti_steps_per_second": 0.726,
+      "step": 935
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 18.625,
+      "learning_rate": 1e-05,
+      "loss": 0.9582,
+      "step": 1122
+    },
+    {
+      "epoch": 0.24,
+      "eval_validation_loss": 0.8237400650978088,
+      "eval_validation_runtime": 190.0819,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 1122
+    },
+    {
+      "epoch": 0.24,
+      "eval_validation_privacy_sources_loss": 0.8237400650978088,
+      "eval_validation_privacy_sources_runtime": 190.0975,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 1122
+    },
+    {
+      "epoch": 0.24,
+      "eval_validation_agenda_digitale_loss": 1.4592102766036987,
+      "eval_validation_agenda_digitale_runtime": 170.7961,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 1122
+    },
+    {
+      "epoch": 0.24,
+      "eval_validation_legal_articles_loss": 1.341143250465393,
+      "eval_validation_legal_articles_runtime": 274.155,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 1122
+    },
+    {
+      "epoch": 0.24,
+      "eval_validation_leggepertutti_loss": 1.1890021562576294,
+      "eval_validation_leggepertutti_runtime": 26.1699,
+      "eval_validation_leggepertutti_samples_per_second": 0.726,
+      "eval_validation_leggepertutti_steps_per_second": 0.726,
+      "step": 1122
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 2.28125,
+      "learning_rate": 1e-05,
+      "loss": 0.9456,
+      "step": 1309
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_loss": 0.8131315112113953,
+      "eval_validation_runtime": 189.7603,
+      "eval_validation_samples_per_second": 0.727,
+      "eval_validation_steps_per_second": 0.727,
+      "step": 1309
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_privacy_sources_loss": 0.8131315112113953,
+      "eval_validation_privacy_sources_runtime": 189.8097,
+      "eval_validation_privacy_sources_samples_per_second": 0.727,
+      "eval_validation_privacy_sources_steps_per_second": 0.727,
+      "step": 1309
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_agenda_digitale_loss": 1.4516360759735107,
+      "eval_validation_agenda_digitale_runtime": 170.4955,
+      "eval_validation_agenda_digitale_samples_per_second": 0.727,
+      "eval_validation_agenda_digitale_steps_per_second": 0.727,
+      "step": 1309
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_legal_articles_loss": 1.3339463472366333,
+      "eval_validation_legal_articles_runtime": 273.5945,
+      "eval_validation_legal_articles_samples_per_second": 0.727,
+      "eval_validation_legal_articles_steps_per_second": 0.727,
+      "step": 1309
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_leggepertutti_loss": 1.1844114065170288,
+      "eval_validation_leggepertutti_runtime": 26.1031,
+      "eval_validation_leggepertutti_samples_per_second": 0.728,
+      "eval_validation_leggepertutti_steps_per_second": 0.728,
+      "step": 1309
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 2.203125,
+      "learning_rate": 1e-05,
+      "loss": 0.9118,
+      "step": 1496
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_loss": 0.8056552410125732,
+      "eval_validation_runtime": 189.1065,
+      "eval_validation_samples_per_second": 0.73,
+      "eval_validation_steps_per_second": 0.73,
+      "step": 1496
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_privacy_sources_loss": 0.8056552410125732,
+      "eval_validation_privacy_sources_runtime": 189.1418,
+      "eval_validation_privacy_sources_samples_per_second": 0.73,
+      "eval_validation_privacy_sources_steps_per_second": 0.73,
+      "step": 1496
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_agenda_digitale_loss": 1.4482883214950562,
+      "eval_validation_agenda_digitale_runtime": 169.9314,
+      "eval_validation_agenda_digitale_samples_per_second": 0.73,
+      "eval_validation_agenda_digitale_steps_per_second": 0.73,
+      "step": 1496
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_legal_articles_loss": 1.3298695087432861,
+      "eval_validation_legal_articles_runtime": 272.7633,
+      "eval_validation_legal_articles_samples_per_second": 0.73,
+      "eval_validation_legal_articles_steps_per_second": 0.73,
+      "step": 1496
+    },
+    {
+      "epoch": 0.31,
+      "eval_validation_leggepertutti_loss": 1.178873896598816,
+      "eval_validation_leggepertutti_runtime": 26.0447,
+      "eval_validation_leggepertutti_samples_per_second": 0.73,
+      "eval_validation_leggepertutti_steps_per_second": 0.73,
+      "step": 1496
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.28125,
+      "learning_rate": 1e-05,
+      "loss": 0.9018,
+      "step": 1683
+    },
+    {
+      "epoch": 0.35,
+      "eval_validation_loss": 0.7955409288406372,
+      "eval_validation_runtime": 190.0308,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 1683
+    },
+    {
+      "epoch": 0.35,
+      "eval_validation_privacy_sources_loss": 0.7955409288406372,
+      "eval_validation_privacy_sources_runtime": 190.1015,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 1683
+    },
+    {
+      "epoch": 0.35,
+      "eval_validation_agenda_digitale_loss": 1.4420207738876343,
+      "eval_validation_agenda_digitale_runtime": 170.7677,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 1683
+    },
+    {
+      "epoch": 0.35,
+      "eval_validation_legal_articles_loss": 1.3251116275787354,
+      "eval_validation_legal_articles_runtime": 274.0824,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 1683
+    },
+    {
+      "epoch": 0.35,
+      "eval_validation_leggepertutti_loss": 1.1761751174926758,
+      "eval_validation_leggepertutti_runtime": 26.1786,
+      "eval_validation_leggepertutti_samples_per_second": 0.726,
+      "eval_validation_leggepertutti_steps_per_second": 0.726,
+      "step": 1683
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.375,
+      "learning_rate": 1e-05,
+      "loss": 0.8911,
+      "step": 1870
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_loss": 0.7886275053024292,
+      "eval_validation_runtime": 190.0169,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 1870
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_privacy_sources_loss": 0.7886275053024292,
+      "eval_validation_privacy_sources_runtime": 189.9755,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 1870
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_agenda_digitale_loss": 1.437984585762024,
+      "eval_validation_agenda_digitale_runtime": 170.7137,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 1870
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_legal_articles_loss": 1.3213441371917725,
+      "eval_validation_legal_articles_runtime": 273.9792,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 1870
+    },
+    {
+      "epoch": 0.39,
+      "eval_validation_leggepertutti_loss": 1.1724990606307983,
+      "eval_validation_leggepertutti_runtime": 26.1471,
+      "eval_validation_leggepertutti_samples_per_second": 0.727,
+      "eval_validation_leggepertutti_steps_per_second": 0.727,
+      "step": 1870
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 2.34375,
+      "learning_rate": 1e-05,
+      "loss": 0.8824,
+      "step": 2057
+    },
+    {
+      "epoch": 0.43,
+      "eval_validation_loss": 0.7812964916229248,
+      "eval_validation_runtime": 189.9852,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 2057
+    },
+    {
+      "epoch": 0.43,
+      "eval_validation_privacy_sources_loss": 0.7812964916229248,
+      "eval_validation_privacy_sources_runtime": 190.0648,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 2057
+    },
+    {
+      "epoch": 0.43,
+      "eval_validation_agenda_digitale_loss": 1.4352736473083496,
+      "eval_validation_agenda_digitale_runtime": 170.7674,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 2057
+    },
+    {
+      "epoch": 0.43,
+      "eval_validation_legal_articles_loss": 1.3146668672561646,
+      "eval_validation_legal_articles_runtime": 274.0088,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 2057
+    },
+    {
+      "epoch": 0.43,
+      "eval_validation_leggepertutti_loss": 1.1654175519943237,
+      "eval_validation_leggepertutti_runtime": 26.1671,
+      "eval_validation_leggepertutti_samples_per_second": 0.726,
+      "eval_validation_leggepertutti_steps_per_second": 0.726,
+      "step": 2057
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.515625,
+      "learning_rate": 1e-05,
+      "loss": 0.8871,
+      "step": 2244
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_loss": 0.7756069898605347,
+      "eval_validation_runtime": 190.0643,
+      "eval_validation_samples_per_second": 0.726,
+      "eval_validation_steps_per_second": 0.726,
+      "step": 2244
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_privacy_sources_loss": 0.7756069898605347,
+      "eval_validation_privacy_sources_runtime": 190.0095,
+      "eval_validation_privacy_sources_samples_per_second": 0.726,
+      "eval_validation_privacy_sources_steps_per_second": 0.726,
+      "step": 2244
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_agenda_digitale_loss": 1.431518316268921,
+      "eval_validation_agenda_digitale_runtime": 170.7517,
+      "eval_validation_agenda_digitale_samples_per_second": 0.726,
+      "eval_validation_agenda_digitale_steps_per_second": 0.726,
+      "step": 2244
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_legal_articles_loss": 1.3110154867172241,
+      "eval_validation_legal_articles_runtime": 274.0835,
+      "eval_validation_legal_articles_samples_per_second": 0.726,
+      "eval_validation_legal_articles_steps_per_second": 0.726,
+      "step": 2244
+    },
+    {
+      "epoch": 0.47,
+      "eval_validation_leggepertutti_loss": 1.161647915840149,
+      "eval_validation_leggepertutti_runtime": 26.1417,
+      "eval_validation_leggepertutti_samples_per_second": 0.727,
+      "eval_validation_leggepertutti_steps_per_second": 0.727,
+      "step": 2244
+    }
+  ],
+  "logging_steps": 187,
+  "max_steps": 4765,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 187,
+  "total_flos": 2.5097123275091214e+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 sha256:0243941b83ef2de867a93374f8a37948a6e3a9d886f1f852af27a74b60573afc
+size 4792