Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840382e6d7facc1928b2eac5cd3813bc9809d2149ec76be8688df2ef32339040
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff188e5af1b10b83fc3c644e1f9dc102681d68d1a5c20988f502e450cbd3f98
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8deafb8378f65fc1dbf7b7b34256b865f10fb5b847be0f8742d03ae2278dda
+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 sha256:11619acbd22123328c049723871d99dffb9262c04db08297479f572e223a7371
+size 12068282

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:ea68a321c24ed5e477c5e6f257c8561ec45b98300d73b7db44d75c895b0063b9
+size 1064

trainer_state.json

@@ -0,0 +1,579 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.27193823980420445,
+  "eval_steps": 375,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 1.8182,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 1.8531,
+      "step": 375
+    },
+    {
+      "epoch": 0.02,
+      "eval_validation_privacy_sources_loss": 1.0427056550979614,
+      "eval_validation_privacy_sources_runtime": 201.1093,
+      "eval_validation_privacy_sources_samples_per_second": 1.904,
+      "eval_validation_privacy_sources_steps_per_second": 1.904,
+      "step": 375
+    },
+    {
+      "epoch": 0.02,
+      "eval_validation_agenda_digitale_loss": 1.5768671035766602,
+      "eval_validation_agenda_digitale_runtime": 178.6225,
+      "eval_validation_agenda_digitale_samples_per_second": 1.903,
+      "eval_validation_agenda_digitale_steps_per_second": 1.903,
+      "step": 375
+    },
+    {
+      "epoch": 0.02,
+      "eval_validation_leggepertutti_loss": 1.41618013381958,
+      "eval_validation_leggepertutti_runtime": 34.1702,
+      "eval_validation_leggepertutti_samples_per_second": 1.902,
+      "eval_validation_leggepertutti_steps_per_second": 1.902,
+      "step": 375
+    },
+    {
+      "epoch": 0.02,
+      "eval_validation_altalexprivacy_loss": 1.420487880706787,
+      "eval_validation_altalexprivacy_runtime": 55.6679,
+      "eval_validation_altalexprivacy_samples_per_second": 1.904,
+      "eval_validation_altalexprivacy_steps_per_second": 1.904,
+      "step": 375
+    },
+    {
+      "epoch": 0.02,
+      "eval_validation_mc4_it_loss": 2.0156803131103516,
+      "eval_validation_mc4_it_runtime": 74.5861,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 375
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 1.659,
+      "step": 750
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_privacy_sources_loss": 0.9875672459602356,
+      "eval_validation_privacy_sources_runtime": 201.0647,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 750
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_agenda_digitale_loss": 1.5326132774353027,
+      "eval_validation_agenda_digitale_runtime": 178.5645,
+      "eval_validation_agenda_digitale_samples_per_second": 1.904,
+      "eval_validation_agenda_digitale_steps_per_second": 1.904,
+      "step": 750
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_leggepertutti_loss": 1.3737919330596924,
+      "eval_validation_leggepertutti_runtime": 34.1417,
+      "eval_validation_leggepertutti_samples_per_second": 1.904,
+      "eval_validation_leggepertutti_steps_per_second": 1.904,
+      "step": 750
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_altalexprivacy_loss": 1.3635202646255493,
+      "eval_validation_altalexprivacy_runtime": 55.6795,
+      "eval_validation_altalexprivacy_samples_per_second": 1.904,
+      "eval_validation_altalexprivacy_steps_per_second": 1.904,
+      "step": 750
+    },
+    {
+      "epoch": 0.05,
+      "eval_validation_mc4_it_loss": 1.9601805210113525,
+      "eval_validation_mc4_it_runtime": 74.5661,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 750
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1e-05,
+      "loss": 1.5963,
+      "step": 1125
+    },
+    {
+      "epoch": 0.07,
+      "eval_validation_privacy_sources_loss": 0.9522767066955566,
+      "eval_validation_privacy_sources_runtime": 201.0521,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 1125
+    },
+    {
+      "epoch": 0.07,
+      "eval_validation_agenda_digitale_loss": 1.4975751638412476,
+      "eval_validation_agenda_digitale_runtime": 178.5472,
+      "eval_validation_agenda_digitale_samples_per_second": 1.904,
+      "eval_validation_agenda_digitale_steps_per_second": 1.904,
+      "step": 1125
+    },
+    {
+      "epoch": 0.07,
+      "eval_validation_leggepertutti_loss": 1.3494906425476074,
+      "eval_validation_leggepertutti_runtime": 34.1339,
+      "eval_validation_leggepertutti_samples_per_second": 1.904,
+      "eval_validation_leggepertutti_steps_per_second": 1.904,
+      "step": 1125
+    },
+    {
+      "epoch": 0.07,
+      "eval_validation_altalexprivacy_loss": 1.3334871530532837,
+      "eval_validation_altalexprivacy_runtime": 55.6542,
+      "eval_validation_altalexprivacy_samples_per_second": 1.905,
+      "eval_validation_altalexprivacy_steps_per_second": 1.905,
+      "step": 1125
+    },
+    {
+      "epoch": 0.07,
+      "eval_validation_mc4_it_loss": 1.9144717454910278,
+      "eval_validation_mc4_it_runtime": 74.5606,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 1125
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1e-05,
+      "loss": 1.577,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "eval_validation_privacy_sources_loss": 0.9246706366539001,
+      "eval_validation_privacy_sources_runtime": 201.0413,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "eval_validation_agenda_digitale_loss": 1.4834680557250977,
+      "eval_validation_agenda_digitale_runtime": 178.5955,
+      "eval_validation_agenda_digitale_samples_per_second": 1.904,
+      "eval_validation_agenda_digitale_steps_per_second": 1.904,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "eval_validation_leggepertutti_loss": 1.3424042463302612,
+      "eval_validation_leggepertutti_runtime": 34.1348,
+      "eval_validation_leggepertutti_samples_per_second": 1.904,
+      "eval_validation_leggepertutti_steps_per_second": 1.904,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "eval_validation_altalexprivacy_loss": 1.3129479885101318,
+      "eval_validation_altalexprivacy_runtime": 55.6818,
+      "eval_validation_altalexprivacy_samples_per_second": 1.904,
+      "eval_validation_altalexprivacy_steps_per_second": 1.904,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "eval_validation_mc4_it_loss": 1.897855281829834,
+      "eval_validation_mc4_it_runtime": 74.5687,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1e-05,
+      "loss": 1.551,
+      "step": 1875
+    },
+    {
+      "epoch": 0.11,
+      "eval_validation_privacy_sources_loss": 0.9161506295204163,
+      "eval_validation_privacy_sources_runtime": 201.028,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 1875
+    },
+    {
+      "epoch": 0.11,
+      "eval_validation_agenda_digitale_loss": 1.4714491367340088,
+      "eval_validation_agenda_digitale_runtime": 178.5046,
+      "eval_validation_agenda_digitale_samples_per_second": 1.905,
+      "eval_validation_agenda_digitale_steps_per_second": 1.905,
+      "step": 1875
+    },
+    {
+      "epoch": 0.11,
+      "eval_validation_leggepertutti_loss": 1.349782109260559,
+      "eval_validation_leggepertutti_runtime": 34.1218,
+      "eval_validation_leggepertutti_samples_per_second": 1.905,
+      "eval_validation_leggepertutti_steps_per_second": 1.905,
+      "step": 1875
+    },
+    {
+      "epoch": 0.11,
+      "eval_validation_altalexprivacy_loss": 1.3038463592529297,
+      "eval_validation_altalexprivacy_runtime": 55.6592,
+      "eval_validation_altalexprivacy_samples_per_second": 1.904,
+      "eval_validation_altalexprivacy_steps_per_second": 1.904,
+      "step": 1875
+    },
+    {
+      "epoch": 0.11,
+      "eval_validation_mc4_it_loss": 1.8886678218841553,
+      "eval_validation_mc4_it_runtime": 74.5616,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 1875
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1e-05,
+      "loss": 1.5334,
+      "step": 2250
+    },
+    {
+      "epoch": 0.14,
+      "eval_validation_privacy_sources_loss": 0.8999343514442444,
+      "eval_validation_privacy_sources_runtime": 201.0719,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 2250
+    },
+    {
+      "epoch": 0.14,
+      "eval_validation_agenda_digitale_loss": 1.470467448234558,
+      "eval_validation_agenda_digitale_runtime": 178.5136,
+      "eval_validation_agenda_digitale_samples_per_second": 1.905,
+      "eval_validation_agenda_digitale_steps_per_second": 1.905,
+      "step": 2250
+    },
+    {
+      "epoch": 0.14,
+      "eval_validation_leggepertutti_loss": 1.3344582319259644,
+      "eval_validation_leggepertutti_runtime": 34.1414,
+      "eval_validation_leggepertutti_samples_per_second": 1.904,
+      "eval_validation_leggepertutti_steps_per_second": 1.904,
+      "step": 2250
+    },
+    {
+      "epoch": 0.14,
+      "eval_validation_altalexprivacy_loss": 1.2899404764175415,
+      "eval_validation_altalexprivacy_runtime": 55.6737,
+      "eval_validation_altalexprivacy_samples_per_second": 1.904,
+      "eval_validation_altalexprivacy_steps_per_second": 1.904,
+      "step": 2250
+    },
+    {
+      "epoch": 0.14,
+      "eval_validation_mc4_it_loss": 1.8787847757339478,
+      "eval_validation_mc4_it_runtime": 74.5812,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 2250
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 1.5289,
+      "step": 2625
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_privacy_sources_loss": 0.8850609064102173,
+      "eval_validation_privacy_sources_runtime": 201.0584,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 2625
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_agenda_digitale_loss": 1.45303213596344,
+      "eval_validation_agenda_digitale_runtime": 178.5557,
+      "eval_validation_agenda_digitale_samples_per_second": 1.904,
+      "eval_validation_agenda_digitale_steps_per_second": 1.904,
+      "step": 2625
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_leggepertutti_loss": 1.3301901817321777,
+      "eval_validation_leggepertutti_runtime": 34.1396,
+      "eval_validation_leggepertutti_samples_per_second": 1.904,
+      "eval_validation_leggepertutti_steps_per_second": 1.904,
+      "step": 2625
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_altalexprivacy_loss": 1.2740957736968994,
+      "eval_validation_altalexprivacy_runtime": 55.6629,
+      "eval_validation_altalexprivacy_samples_per_second": 1.904,
+      "eval_validation_altalexprivacy_steps_per_second": 1.904,
+      "step": 2625
+    },
+    {
+      "epoch": 0.16,
+      "eval_validation_mc4_it_loss": 1.8664617538452148,
+      "eval_validation_mc4_it_runtime": 74.5651,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 2625
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1e-05,
+      "loss": 1.5137,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_privacy_sources_loss": 0.8736271858215332,
+      "eval_validation_privacy_sources_runtime": 201.0614,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_agenda_digitale_loss": 1.4448249340057373,
+      "eval_validation_agenda_digitale_runtime": 178.5096,
+      "eval_validation_agenda_digitale_samples_per_second": 1.905,
+      "eval_validation_agenda_digitale_steps_per_second": 1.905,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_leggepertutti_loss": 1.3264199495315552,
+      "eval_validation_leggepertutti_runtime": 34.1392,
+      "eval_validation_leggepertutti_samples_per_second": 1.904,
+      "eval_validation_leggepertutti_steps_per_second": 1.904,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_altalexprivacy_loss": 1.2583509683609009,
+      "eval_validation_altalexprivacy_runtime": 55.6465,
+      "eval_validation_altalexprivacy_samples_per_second": 1.905,
+      "eval_validation_altalexprivacy_steps_per_second": 1.905,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18,
+      "eval_validation_mc4_it_loss": 1.8547219038009644,
+      "eval_validation_mc4_it_runtime": 74.5381,
+      "eval_validation_mc4_it_samples_per_second": 1.905,
+      "eval_validation_mc4_it_steps_per_second": 1.905,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1e-05,
+      "loss": 1.5191,
+      "step": 3375
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_privacy_sources_loss": 0.8653725385665894,
+      "eval_validation_privacy_sources_runtime": 201.0607,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 3375
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_agenda_digitale_loss": 1.437347173690796,
+      "eval_validation_agenda_digitale_runtime": 178.5114,
+      "eval_validation_agenda_digitale_samples_per_second": 1.905,
+      "eval_validation_agenda_digitale_steps_per_second": 1.905,
+      "step": 3375
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_leggepertutti_loss": 1.3095436096191406,
+      "eval_validation_leggepertutti_runtime": 34.1234,
+      "eval_validation_leggepertutti_samples_per_second": 1.905,
+      "eval_validation_leggepertutti_steps_per_second": 1.905,
+      "step": 3375
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_altalexprivacy_loss": 1.24440336227417,
+      "eval_validation_altalexprivacy_runtime": 55.6399,
+      "eval_validation_altalexprivacy_samples_per_second": 1.905,
+      "eval_validation_altalexprivacy_steps_per_second": 1.905,
+      "step": 3375
+    },
+    {
+      "epoch": 0.2,
+      "eval_validation_mc4_it_loss": 1.8478875160217285,
+      "eval_validation_mc4_it_runtime": 74.5544,
+      "eval_validation_mc4_it_samples_per_second": 1.905,
+      "eval_validation_mc4_it_steps_per_second": 1.905,
+      "step": 3375
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1e-05,
+      "loss": 1.5014,
+      "step": 3750
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_privacy_sources_loss": 0.866100013256073,
+      "eval_validation_privacy_sources_runtime": 201.0279,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 3750
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_agenda_digitale_loss": 1.4383131265640259,
+      "eval_validation_agenda_digitale_runtime": 178.5206,
+      "eval_validation_agenda_digitale_samples_per_second": 1.905,
+      "eval_validation_agenda_digitale_steps_per_second": 1.905,
+      "step": 3750
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_leggepertutti_loss": 1.3121819496154785,
+      "eval_validation_leggepertutti_runtime": 34.1311,
+      "eval_validation_leggepertutti_samples_per_second": 1.904,
+      "eval_validation_leggepertutti_steps_per_second": 1.904,
+      "step": 3750
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_altalexprivacy_loss": 1.2500646114349365,
+      "eval_validation_altalexprivacy_runtime": 55.6505,
+      "eval_validation_altalexprivacy_samples_per_second": 1.905,
+      "eval_validation_altalexprivacy_steps_per_second": 1.905,
+      "step": 3750
+    },
+    {
+      "epoch": 0.23,
+      "eval_validation_mc4_it_loss": 1.8457143306732178,
+      "eval_validation_mc4_it_runtime": 74.5581,
+      "eval_validation_mc4_it_samples_per_second": 1.905,
+      "eval_validation_mc4_it_steps_per_second": 1.905,
+      "step": 3750
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1e-05,
+      "loss": 1.4925,
+      "step": 4125
+    },
+    {
+      "epoch": 0.25,
+      "eval_validation_privacy_sources_loss": 0.8534922003746033,
+      "eval_validation_privacy_sources_runtime": 201.0002,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 4125
+    },
+    {
+      "epoch": 0.25,
+      "eval_validation_agenda_digitale_loss": 1.426421046257019,
+      "eval_validation_agenda_digitale_runtime": 178.5283,
+      "eval_validation_agenda_digitale_samples_per_second": 1.904,
+      "eval_validation_agenda_digitale_steps_per_second": 1.904,
+      "step": 4125
+    },
+    {
+      "epoch": 0.25,
+      "eval_validation_leggepertutti_loss": 1.3124033212661743,
+      "eval_validation_leggepertutti_runtime": 34.1225,
+      "eval_validation_leggepertutti_samples_per_second": 1.905,
+      "eval_validation_leggepertutti_steps_per_second": 1.905,
+      "step": 4125
+    },
+    {
+      "epoch": 0.25,
+      "eval_validation_altalexprivacy_loss": 1.2354837656021118,
+      "eval_validation_altalexprivacy_runtime": 55.6534,
+      "eval_validation_altalexprivacy_samples_per_second": 1.905,
+      "eval_validation_altalexprivacy_steps_per_second": 1.905,
+      "step": 4125
+    },
+    {
+      "epoch": 0.25,
+      "eval_validation_mc4_it_loss": 1.839884638786316,
+      "eval_validation_mc4_it_runtime": 74.5669,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 4125
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1e-05,
+      "loss": 1.4953,
+      "step": 4500
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_privacy_sources_loss": 0.849433422088623,
+      "eval_validation_privacy_sources_runtime": 201.0776,
+      "eval_validation_privacy_sources_samples_per_second": 1.905,
+      "eval_validation_privacy_sources_steps_per_second": 1.905,
+      "step": 4500
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_agenda_digitale_loss": 1.4208179712295532,
+      "eval_validation_agenda_digitale_runtime": 178.5663,
+      "eval_validation_agenda_digitale_samples_per_second": 1.904,
+      "eval_validation_agenda_digitale_steps_per_second": 1.904,
+      "step": 4500
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_leggepertutti_loss": 1.3129136562347412,
+      "eval_validation_leggepertutti_runtime": 34.1427,
+      "eval_validation_leggepertutti_samples_per_second": 1.904,
+      "eval_validation_leggepertutti_steps_per_second": 1.904,
+      "step": 4500
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_altalexprivacy_loss": 1.2299654483795166,
+      "eval_validation_altalexprivacy_runtime": 55.664,
+      "eval_validation_altalexprivacy_samples_per_second": 1.904,
+      "eval_validation_altalexprivacy_steps_per_second": 1.904,
+      "step": 4500
+    },
+    {
+      "epoch": 0.27,
+      "eval_validation_mc4_it_loss": 1.8318015336990356,
+      "eval_validation_mc4_it_runtime": 74.5767,
+      "eval_validation_mc4_it_samples_per_second": 1.904,
+      "eval_validation_mc4_it_steps_per_second": 1.904,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 375,
+  "max_steps": 33094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 375,
+  "total_flos": 9.436585456041984e+18,
+  "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 sha256:1416eac7b08ba06348e92dafebae38c37b959841df010dcd3f885aab6249f9a6
+size 4792