Upload folder using huggingface_hub

checkpoint-683/config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
+  "architectures": [
+    "DetikzifyForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "concat_patches": 2,
+  "eos_token_id": 32014,
+  "feature_layer": 26,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "mm_hidden_size": 2304,
+  "model_type": "detikzify",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "num_patches": 364,
+  "patch_token_id": 32013,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vision_config": {
+    "architecture": "vit_so400m_patch14_siglip_384",
+    "classifier": "head",
+    "crop_mode": "center",
+    "crop_pct": 0.9,
+    "custom_load": false,
+    "first_conv": "patch_embed.proj",
+    "fixed_input_size": true,
+    "hf_hub_filename": "open_clip_pytorch_model.bin",
+    "hf_hub_id": "timm/ViT-SO400M-14-SigLIP-384",
+    "input_size": [
+      3,
+      384,
+      384
+    ],
+    "interpolation": "bicubic",
+    "mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "num_classes": 0,
+    "pool_size": null,
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "tag": "webli",
+    "url": ""
+  },
+  "vision_tower": "vit_so400m_patch14_siglip_384.webli",
+  "vocab_size": 32256
+}

checkpoint-683/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "pad_token_id": 32018,
+  "transformers_version": "4.46.2"
+}

checkpoint-683/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73632ddfeb04782135280bc86899d1961675d91bc7179ab91cad7f1cfd6d3c4
+size 4986380064

checkpoint-683/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164045a2e70a472c4b550997ffe54d4017d5e9233f5e957f41db29e09d2bb286
+size 418415560

checkpoint-683/model.safetensors.index.json

@@ -0,0 +1,228 @@
+{
+  "metadata": {
+    "total_size": 5404770304
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-683/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dc78be11432e03047c380f8fcf98cc3e59ef5fef6dad566a369ac7fe194e1d
+size 10809735574

checkpoint-683/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-683/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68f79ce4b652a7ea2fbf1c918f3978f1c7af4bd620090afe83f8d157595937f
+size 1064

checkpoint-683/trainer_state.json

@@ -0,0 +1,509 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.99949609473419,
+  "eval_steps": 500,
+  "global_step": 683,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016082826556767352,
+      "grad_norm": 65.62212371826172,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.8077,
+      "step": 10
+    },
+    {
+      "epoch": 0.032165653113534705,
+      "grad_norm": 50.16935729980469,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.6155,
+      "step": 20
+    },
+    {
+      "epoch": 0.048248479670302054,
+      "grad_norm": 32.083778381347656,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.5188,
+      "step": 30
+    },
+    {
+      "epoch": 0.06433130622706941,
+      "grad_norm": 27.791507720947266,
+      "learning_rate": 2.8571428571428574e-05,
+      "loss": 0.4476,
+      "step": 40
+    },
+    {
+      "epoch": 0.08041413278383676,
+      "grad_norm": 33.207706451416016,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.4035,
+      "step": 50
+    },
+    {
+      "epoch": 0.09649695934060411,
+      "grad_norm": 29.39824104309082,
+      "learning_rate": 3.99995163828731e-05,
+      "loss": 0.373,
+      "step": 60
+    },
+    {
+      "epoch": 0.11257978589737146,
+      "grad_norm": 27.801868438720703,
+      "learning_rate": 3.999407595879474e-05,
+      "loss": 0.33,
+      "step": 70
+    },
+    {
+      "epoch": 0.12866261245413882,
+      "grad_norm": 27.443641662597656,
+      "learning_rate": 3.998259223910273e-05,
+      "loss": 0.3121,
+      "step": 80
+    },
+    {
+      "epoch": 0.14474543901090617,
+      "grad_norm": 27.026424407958984,
+      "learning_rate": 3.9965068694800805e-05,
+      "loss": 0.2868,
+      "step": 90
+    },
+    {
+      "epoch": 0.16082826556767352,
+      "grad_norm": 27.81942367553711,
+      "learning_rate": 3.9941510622455766e-05,
+      "loss": 0.2675,
+      "step": 100
+    },
+    {
+      "epoch": 0.17691109212444087,
+      "grad_norm": 27.47068214416504,
+      "learning_rate": 3.9911925142596474e-05,
+      "loss": 0.252,
+      "step": 110
+    },
+    {
+      "epoch": 0.19299391868120822,
+      "grad_norm": 27.166418075561523,
+      "learning_rate": 3.9876321197561714e-05,
+      "loss": 0.233,
+      "step": 120
+    },
+    {
+      "epoch": 0.20907674523797556,
+      "grad_norm": 26.941362380981445,
+      "learning_rate": 3.983470954879728e-05,
+      "loss": 0.2216,
+      "step": 130
+    },
+    {
+      "epoch": 0.2251595717947429,
+      "grad_norm": 25.84792709350586,
+      "learning_rate": 3.9787102773603325e-05,
+      "loss": 0.2057,
+      "step": 140
+    },
+    {
+      "epoch": 0.2412423983515103,
+      "grad_norm": 24.429794311523438,
+      "learning_rate": 3.973351526133279e-05,
+      "loss": 0.1997,
+      "step": 150
+    },
+    {
+      "epoch": 0.25732522490827764,
+      "grad_norm": 25.138715744018555,
+      "learning_rate": 3.967396320904215e-05,
+      "loss": 0.1799,
+      "step": 160
+    },
+    {
+      "epoch": 0.273408051465045,
+      "grad_norm": 23.31828498840332,
+      "learning_rate": 3.960846461659586e-05,
+      "loss": 0.1778,
+      "step": 170
+    },
+    {
+      "epoch": 0.28949087802181234,
+      "grad_norm": 27.868120193481445,
+      "learning_rate": 3.953703928122569e-05,
+      "loss": 0.17,
+      "step": 180
+    },
+    {
+      "epoch": 1.018596079745351,
+      "grad_norm": 23.8084659576416,
+      "learning_rate": 3.945970879154704e-05,
+      "loss": 0.1812,
+      "step": 190
+    },
+    {
+      "epoch": 1.0722063997319484,
+      "grad_norm": 28.152708053588867,
+      "learning_rate": 3.9376496521033636e-05,
+      "loss": 0.1811,
+      "step": 200
+    },
+    {
+      "epoch": 1.1258167197185458,
+      "grad_norm": 25.456472396850586,
+      "learning_rate": 3.92874276209528e-05,
+      "loss": 0.1703,
+      "step": 210
+    },
+    {
+      "epoch": 1.1794270397051432,
+      "grad_norm": 24.26827049255371,
+      "learning_rate": 3.919252901276339e-05,
+      "loss": 0.1772,
+      "step": 220
+    },
+    {
+      "epoch": 1.2330373596917408,
+      "grad_norm": 23.77770233154297,
+      "learning_rate": 3.909182937997866e-05,
+      "loss": 0.1654,
+      "step": 230
+    },
+    {
+      "epoch": 1.2866476796783382,
+      "grad_norm": 24.42105484008789,
+      "learning_rate": 3.8985359159496516e-05,
+      "loss": 0.1504,
+      "step": 240
+    },
+    {
+      "epoch": 1.3402579996649355,
+      "grad_norm": 24.336668014526367,
+      "learning_rate": 3.8873150532399885e-05,
+      "loss": 0.1368,
+      "step": 250
+    },
+    {
+      "epoch": 1.393868319651533,
+      "grad_norm": 24.254329681396484,
+      "learning_rate": 3.8755237414229834e-05,
+      "loss": 0.1454,
+      "step": 260
+    },
+    {
+      "epoch": 1.4474786396381303,
+      "grad_norm": 25.233129501342773,
+      "learning_rate": 3.8631655444734414e-05,
+      "loss": 0.1373,
+      "step": 270
+    },
+    {
+      "epoch": 1.5010889596247279,
+      "grad_norm": 23.18859100341797,
+      "learning_rate": 3.850244197709641e-05,
+      "loss": 0.1341,
+      "step": 280
+    },
+    {
+      "epoch": 1.554699279611325,
+      "grad_norm": 24.764631271362305,
+      "learning_rate": 3.8367636066643224e-05,
+      "loss": 0.139,
+      "step": 290
+    },
+    {
+      "epoch": 1.6083095995979226,
+      "grad_norm": 23.146198272705078,
+      "learning_rate": 3.822727845904216e-05,
+      "loss": 0.1256,
+      "step": 300
+    },
+    {
+      "epoch": 1.66191991958452,
+      "grad_norm": 23.295623779296875,
+      "learning_rate": 3.808141157798492e-05,
+      "loss": 0.1206,
+      "step": 310
+    },
+    {
+      "epoch": 1.7155302395711174,
+      "grad_norm": 21.969825744628906,
+      "learning_rate": 3.793007951236485e-05,
+      "loss": 0.12,
+      "step": 320
+    },
+    {
+      "epoch": 1.769140559557715,
+      "grad_norm": 21.317886352539062,
+      "learning_rate": 3.777332800295088e-05,
+      "loss": 0.1116,
+      "step": 330
+    },
+    {
+      "epoch": 1.8227508795443121,
+      "grad_norm": 23.39339256286621,
+      "learning_rate": 3.7611204428562175e-05,
+      "loss": 0.1129,
+      "step": 340
+    },
+    {
+      "epoch": 1.8763611995309097,
+      "grad_norm": 27.18583869934082,
+      "learning_rate": 3.74437577917477e-05,
+      "loss": 0.109,
+      "step": 350
+    },
+    {
+      "epoch": 1.9299715195175071,
+      "grad_norm": 21.890743255615234,
+      "learning_rate": 3.727103870397495e-05,
+      "loss": 0.1021,
+      "step": 360
+    },
+    {
+      "epoch": 1.9835818395041045,
+      "grad_norm": 23.11468505859375,
+      "learning_rate": 3.709309937033247e-05,
+      "loss": 0.1003,
+      "step": 370
+    },
+    {
+      "epoch": 2.022323003275384,
+      "grad_norm": 25.56001853942871,
+      "learning_rate": 3.6909993573750586e-05,
+      "loss": 0.1186,
+      "step": 380
+    },
+    {
+      "epoch": 2.054572940287226,
+      "grad_norm": 23.89845085144043,
+      "learning_rate": 3.6721776658745335e-05,
+      "loss": 0.1298,
+      "step": 390
+    },
+    {
+      "epoch": 2.086822877299068,
+      "grad_norm": 24.464975357055664,
+      "learning_rate": 3.652850551469031e-05,
+      "loss": 0.1265,
+      "step": 400
+    },
+    {
+      "epoch": 2.1190728143109094,
+      "grad_norm": 23.46689796447754,
+      "learning_rate": 3.63302385586216e-05,
+      "loss": 0.1248,
+      "step": 410
+    },
+    {
+      "epoch": 2.1513227513227515,
+      "grad_norm": 21.452667236328125,
+      "learning_rate": 3.6127035717581035e-05,
+      "loss": 0.1128,
+      "step": 420
+    },
+    {
+      "epoch": 2.183572688334593,
+      "grad_norm": 22.750587463378906,
+      "learning_rate": 3.59189584105029e-05,
+      "loss": 0.1068,
+      "step": 430
+    },
+    {
+      "epoch": 2.215822625346435,
+      "grad_norm": 23.539155960083008,
+      "learning_rate": 3.570606952964991e-05,
+      "loss": 0.1089,
+      "step": 440
+    },
+    {
+      "epoch": 2.2480725623582765,
+      "grad_norm": 22.286226272583008,
+      "learning_rate": 3.54884334216036e-05,
+      "loss": 0.1012,
+      "step": 450
+    },
+    {
+      "epoch": 2.2803224993701185,
+      "grad_norm": 25.91316795349121,
+      "learning_rate": 3.526611586781547e-05,
+      "loss": 0.1085,
+      "step": 460
+    },
+    {
+      "epoch": 2.31257243638196,
+      "grad_norm": 25.620323181152344,
+      "learning_rate": 3.503918406472411e-05,
+      "loss": 0.0935,
+      "step": 470
+    },
+    {
+      "epoch": 2.344822373393802,
+      "grad_norm": 20.377058029174805,
+      "learning_rate": 3.480770660344486e-05,
+      "loss": 0.0982,
+      "step": 480
+    },
+    {
+      "epoch": 2.377072310405644,
+      "grad_norm": 20.553796768188477,
+      "learning_rate": 3.457175344903783e-05,
+      "loss": 0.084,
+      "step": 490
+    },
+    {
+      "epoch": 2.4093222474174856,
+      "grad_norm": 20.02320671081543,
+      "learning_rate": 3.433139591936068e-05,
+      "loss": 0.0964,
+      "step": 500
+    },
+    {
+      "epoch": 2.441572184429327,
+      "grad_norm": 21.293182373046875,
+      "learning_rate": 3.4086706663512454e-05,
+      "loss": 0.0835,
+      "step": 510
+    },
+    {
+      "epoch": 2.4738221214411693,
+      "grad_norm": 19.96319580078125,
+      "learning_rate": 3.3837759639875113e-05,
+      "loss": 0.0785,
+      "step": 520
+    },
+    {
+      "epoch": 2.506072058453011,
+      "grad_norm": 22.20425796508789,
+      "learning_rate": 3.358463009375927e-05,
+      "loss": 0.0779,
+      "step": 530
+    },
+    {
+      "epoch": 2.5383219954648526,
+      "grad_norm": 18.57112693786621,
+      "learning_rate": 3.332739453466098e-05,
+      "loss": 0.0814,
+      "step": 540
+    },
+    {
+      "epoch": 2.5705719324766942,
+      "grad_norm": 20.270761489868164,
+      "learning_rate": 3.306613071313641e-05,
+      "loss": 0.0808,
+      "step": 550
+    },
+    {
+      "epoch": 2.602821869488536,
+      "grad_norm": 19.787559509277344,
+      "learning_rate": 3.280091759730144e-05,
+      "loss": 0.0743,
+      "step": 560
+    },
+    {
+      "epoch": 2.635071806500378,
+      "grad_norm": 18.70611572265625,
+      "learning_rate": 3.25318353489631e-05,
+      "loss": 0.0757,
+      "step": 570
+    },
+    {
+      "epoch": 2.6673217435122196,
+      "grad_norm": 20.557205200195312,
+      "learning_rate": 3.2258965299390465e-05,
+      "loss": 0.0692,
+      "step": 580
+    },
+    {
+      "epoch": 2.6995716805240617,
+      "grad_norm": 20.602092742919922,
+      "learning_rate": 3.1982389924731805e-05,
+      "loss": 0.0699,
+      "step": 590
+    },
+    {
+      "epoch": 2.7318216175359034,
+      "grad_norm": 22.87337303161621,
+      "learning_rate": 3.17021928210859e-05,
+      "loss": 0.0662,
+      "step": 600
+    },
+    {
+      "epoch": 2.764071554547745,
+      "grad_norm": 22.488433837890625,
+      "learning_rate": 3.141845867923469e-05,
+      "loss": 0.0799,
+      "step": 610
+    },
+    {
+      "epoch": 2.7963214915595866,
+      "grad_norm": 20.05706787109375,
+      "learning_rate": 3.113127325904519e-05,
+      "loss": 0.0665,
+      "step": 620
+    },
+    {
+      "epoch": 2.8285714285714287,
+      "grad_norm": 18.822357177734375,
+      "learning_rate": 3.084072336354812e-05,
+      "loss": 0.0668,
+      "step": 630
+    },
+    {
+      "epoch": 2.8608213655832704,
+      "grad_norm": 17.79743194580078,
+      "learning_rate": 3.05468968127014e-05,
+      "loss": 0.0604,
+      "step": 640
+    },
+    {
+      "epoch": 2.893071302595112,
+      "grad_norm": 19.10596466064453,
+      "learning_rate": 3.0249882416846117e-05,
+      "loss": 0.059,
+      "step": 650
+    },
+    {
+      "epoch": 2.925321239606954,
+      "grad_norm": 20.25804328918457,
+      "learning_rate": 2.9949769949863266e-05,
+      "loss": 0.0646,
+      "step": 660
+    },
+    {
+      "epoch": 2.9575711766187958,
+      "grad_norm": 19.09357452392578,
+      "learning_rate": 2.96466501220392e-05,
+      "loss": 0.0569,
+      "step": 670
+    },
+    {
+      "epoch": 2.9898211136306374,
+      "grad_norm": 15.293481826782227,
+      "learning_rate": 2.934061455264802e-05,
+      "loss": 0.0574,
+      "step": 680
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1863,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.564245582272266e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-683/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe26717ade77091d84e0f68e22523033018b95d33245be7b8f5b046cac304f98
+size 5304

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
+  "architectures": [
+    "DetikzifyForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "concat_patches": 2,
+  "eos_token_id": 32014,
+  "feature_layer": 26,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "mm_hidden_size": 2304,
+  "model_type": "detikzify",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "num_patches": 364,
+  "patch_token_id": 32013,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "use_mm_proj": true,
+  "vision_config": {
+    "architecture": "vit_so400m_patch14_siglip_384",
+    "classifier": "head",
+    "crop_mode": "center",
+    "crop_pct": 0.9,
+    "custom_load": false,
+    "first_conv": "patch_embed.proj",
+    "fixed_input_size": true,
+    "hf_hub_filename": "open_clip_pytorch_model.bin",
+    "hf_hub_id": "timm/ViT-SO400M-14-SigLIP-384",
+    "input_size": [
+      3,
+      384,
+      384
+    ],
+    "interpolation": "bicubic",
+    "mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "num_classes": 0,
+    "pool_size": null,
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "tag": "webli",
+    "url": ""
+  },
+  "vision_tower": "vit_so400m_patch14_siglip_384.webli",
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "pad_token_id": 32018,
+  "transformers_version": "4.46.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73632ddfeb04782135280bc86899d1961675d91bc7179ab91cad7f1cfd6d3c4
+size 4986380064

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164045a2e70a472c4b550997ffe54d4017d5e9233f5e957f41db29e09d2bb286
+size 418415560

model.safetensors.index.json

@@ -0,0 +1,228 @@
+{
+  "metadata": {
+    "total_size": 5404770304
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.mm_projector.bias": "model-00002-of-00002.safetensors",
+    "model.mm_projector.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

trainer_state.json

@@ -0,0 +1,518 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.99949609473419,
+  "eval_steps": 500,
+  "global_step": 683,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016082826556767352,
+      "grad_norm": 65.62212371826172,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.8077,
+      "step": 10
+    },
+    {
+      "epoch": 0.032165653113534705,
+      "grad_norm": 50.16935729980469,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.6155,
+      "step": 20
+    },
+    {
+      "epoch": 0.048248479670302054,
+      "grad_norm": 32.083778381347656,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.5188,
+      "step": 30
+    },
+    {
+      "epoch": 0.06433130622706941,
+      "grad_norm": 27.791507720947266,
+      "learning_rate": 2.8571428571428574e-05,
+      "loss": 0.4476,
+      "step": 40
+    },
+    {
+      "epoch": 0.08041413278383676,
+      "grad_norm": 33.207706451416016,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.4035,
+      "step": 50
+    },
+    {
+      "epoch": 0.09649695934060411,
+      "grad_norm": 29.39824104309082,
+      "learning_rate": 3.99995163828731e-05,
+      "loss": 0.373,
+      "step": 60
+    },
+    {
+      "epoch": 0.11257978589737146,
+      "grad_norm": 27.801868438720703,
+      "learning_rate": 3.999407595879474e-05,
+      "loss": 0.33,
+      "step": 70
+    },
+    {
+      "epoch": 0.12866261245413882,
+      "grad_norm": 27.443641662597656,
+      "learning_rate": 3.998259223910273e-05,
+      "loss": 0.3121,
+      "step": 80
+    },
+    {
+      "epoch": 0.14474543901090617,
+      "grad_norm": 27.026424407958984,
+      "learning_rate": 3.9965068694800805e-05,
+      "loss": 0.2868,
+      "step": 90
+    },
+    {
+      "epoch": 0.16082826556767352,
+      "grad_norm": 27.81942367553711,
+      "learning_rate": 3.9941510622455766e-05,
+      "loss": 0.2675,
+      "step": 100
+    },
+    {
+      "epoch": 0.17691109212444087,
+      "grad_norm": 27.47068214416504,
+      "learning_rate": 3.9911925142596474e-05,
+      "loss": 0.252,
+      "step": 110
+    },
+    {
+      "epoch": 0.19299391868120822,
+      "grad_norm": 27.166418075561523,
+      "learning_rate": 3.9876321197561714e-05,
+      "loss": 0.233,
+      "step": 120
+    },
+    {
+      "epoch": 0.20907674523797556,
+      "grad_norm": 26.941362380981445,
+      "learning_rate": 3.983470954879728e-05,
+      "loss": 0.2216,
+      "step": 130
+    },
+    {
+      "epoch": 0.2251595717947429,
+      "grad_norm": 25.84792709350586,
+      "learning_rate": 3.9787102773603325e-05,
+      "loss": 0.2057,
+      "step": 140
+    },
+    {
+      "epoch": 0.2412423983515103,
+      "grad_norm": 24.429794311523438,
+      "learning_rate": 3.973351526133279e-05,
+      "loss": 0.1997,
+      "step": 150
+    },
+    {
+      "epoch": 0.25732522490827764,
+      "grad_norm": 25.138715744018555,
+      "learning_rate": 3.967396320904215e-05,
+      "loss": 0.1799,
+      "step": 160
+    },
+    {
+      "epoch": 0.273408051465045,
+      "grad_norm": 23.31828498840332,
+      "learning_rate": 3.960846461659586e-05,
+      "loss": 0.1778,
+      "step": 170
+    },
+    {
+      "epoch": 0.28949087802181234,
+      "grad_norm": 27.868120193481445,
+      "learning_rate": 3.953703928122569e-05,
+      "loss": 0.17,
+      "step": 180
+    },
+    {
+      "epoch": 1.018596079745351,
+      "grad_norm": 23.8084659576416,
+      "learning_rate": 3.945970879154704e-05,
+      "loss": 0.1812,
+      "step": 190
+    },
+    {
+      "epoch": 1.0722063997319484,
+      "grad_norm": 28.152708053588867,
+      "learning_rate": 3.9376496521033636e-05,
+      "loss": 0.1811,
+      "step": 200
+    },
+    {
+      "epoch": 1.1258167197185458,
+      "grad_norm": 25.456472396850586,
+      "learning_rate": 3.92874276209528e-05,
+      "loss": 0.1703,
+      "step": 210
+    },
+    {
+      "epoch": 1.1794270397051432,
+      "grad_norm": 24.26827049255371,
+      "learning_rate": 3.919252901276339e-05,
+      "loss": 0.1772,
+      "step": 220
+    },
+    {
+      "epoch": 1.2330373596917408,
+      "grad_norm": 23.77770233154297,
+      "learning_rate": 3.909182937997866e-05,
+      "loss": 0.1654,
+      "step": 230
+    },
+    {
+      "epoch": 1.2866476796783382,
+      "grad_norm": 24.42105484008789,
+      "learning_rate": 3.8985359159496516e-05,
+      "loss": 0.1504,
+      "step": 240
+    },
+    {
+      "epoch": 1.3402579996649355,
+      "grad_norm": 24.336668014526367,
+      "learning_rate": 3.8873150532399885e-05,
+      "loss": 0.1368,
+      "step": 250
+    },
+    {
+      "epoch": 1.393868319651533,
+      "grad_norm": 24.254329681396484,
+      "learning_rate": 3.8755237414229834e-05,
+      "loss": 0.1454,
+      "step": 260
+    },
+    {
+      "epoch": 1.4474786396381303,
+      "grad_norm": 25.233129501342773,
+      "learning_rate": 3.8631655444734414e-05,
+      "loss": 0.1373,
+      "step": 270
+    },
+    {
+      "epoch": 1.5010889596247279,
+      "grad_norm": 23.18859100341797,
+      "learning_rate": 3.850244197709641e-05,
+      "loss": 0.1341,
+      "step": 280
+    },
+    {
+      "epoch": 1.554699279611325,
+      "grad_norm": 24.764631271362305,
+      "learning_rate": 3.8367636066643224e-05,
+      "loss": 0.139,
+      "step": 290
+    },
+    {
+      "epoch": 1.6083095995979226,
+      "grad_norm": 23.146198272705078,
+      "learning_rate": 3.822727845904216e-05,
+      "loss": 0.1256,
+      "step": 300
+    },
+    {
+      "epoch": 1.66191991958452,
+      "grad_norm": 23.295623779296875,
+      "learning_rate": 3.808141157798492e-05,
+      "loss": 0.1206,
+      "step": 310
+    },
+    {
+      "epoch": 1.7155302395711174,
+      "grad_norm": 21.969825744628906,
+      "learning_rate": 3.793007951236485e-05,
+      "loss": 0.12,
+      "step": 320
+    },
+    {
+      "epoch": 1.769140559557715,
+      "grad_norm": 21.317886352539062,
+      "learning_rate": 3.777332800295088e-05,
+      "loss": 0.1116,
+      "step": 330
+    },
+    {
+      "epoch": 1.8227508795443121,
+      "grad_norm": 23.39339256286621,
+      "learning_rate": 3.7611204428562175e-05,
+      "loss": 0.1129,
+      "step": 340
+    },
+    {
+      "epoch": 1.8763611995309097,
+      "grad_norm": 27.18583869934082,
+      "learning_rate": 3.74437577917477e-05,
+      "loss": 0.109,
+      "step": 350
+    },
+    {
+      "epoch": 1.9299715195175071,
+      "grad_norm": 21.890743255615234,
+      "learning_rate": 3.727103870397495e-05,
+      "loss": 0.1021,
+      "step": 360
+    },
+    {
+      "epoch": 1.9835818395041045,
+      "grad_norm": 23.11468505859375,
+      "learning_rate": 3.709309937033247e-05,
+      "loss": 0.1003,
+      "step": 370
+    },
+    {
+      "epoch": 2.022323003275384,
+      "grad_norm": 25.56001853942871,
+      "learning_rate": 3.6909993573750586e-05,
+      "loss": 0.1186,
+      "step": 380
+    },
+    {
+      "epoch": 2.054572940287226,
+      "grad_norm": 23.89845085144043,
+      "learning_rate": 3.6721776658745335e-05,
+      "loss": 0.1298,
+      "step": 390
+    },
+    {
+      "epoch": 2.086822877299068,
+      "grad_norm": 24.464975357055664,
+      "learning_rate": 3.652850551469031e-05,
+      "loss": 0.1265,
+      "step": 400
+    },
+    {
+      "epoch": 2.1190728143109094,
+      "grad_norm": 23.46689796447754,
+      "learning_rate": 3.63302385586216e-05,
+      "loss": 0.1248,
+      "step": 410
+    },
+    {
+      "epoch": 2.1513227513227515,
+      "grad_norm": 21.452667236328125,
+      "learning_rate": 3.6127035717581035e-05,
+      "loss": 0.1128,
+      "step": 420
+    },
+    {
+      "epoch": 2.183572688334593,
+      "grad_norm": 22.750587463378906,
+      "learning_rate": 3.59189584105029e-05,
+      "loss": 0.1068,
+      "step": 430
+    },
+    {
+      "epoch": 2.215822625346435,
+      "grad_norm": 23.539155960083008,
+      "learning_rate": 3.570606952964991e-05,
+      "loss": 0.1089,
+      "step": 440
+    },
+    {
+      "epoch": 2.2480725623582765,
+      "grad_norm": 22.286226272583008,
+      "learning_rate": 3.54884334216036e-05,
+      "loss": 0.1012,
+      "step": 450
+    },
+    {
+      "epoch": 2.2803224993701185,
+      "grad_norm": 25.91316795349121,
+      "learning_rate": 3.526611586781547e-05,
+      "loss": 0.1085,
+      "step": 460
+    },
+    {
+      "epoch": 2.31257243638196,
+      "grad_norm": 25.620323181152344,
+      "learning_rate": 3.503918406472411e-05,
+      "loss": 0.0935,
+      "step": 470
+    },
+    {
+      "epoch": 2.344822373393802,
+      "grad_norm": 20.377058029174805,
+      "learning_rate": 3.480770660344486e-05,
+      "loss": 0.0982,
+      "step": 480
+    },
+    {
+      "epoch": 2.377072310405644,
+      "grad_norm": 20.553796768188477,
+      "learning_rate": 3.457175344903783e-05,
+      "loss": 0.084,
+      "step": 490
+    },
+    {
+      "epoch": 2.4093222474174856,
+      "grad_norm": 20.02320671081543,
+      "learning_rate": 3.433139591936068e-05,
+      "loss": 0.0964,
+      "step": 500
+    },
+    {
+      "epoch": 2.441572184429327,
+      "grad_norm": 21.293182373046875,
+      "learning_rate": 3.4086706663512454e-05,
+      "loss": 0.0835,
+      "step": 510
+    },
+    {
+      "epoch": 2.4738221214411693,
+      "grad_norm": 19.96319580078125,
+      "learning_rate": 3.3837759639875113e-05,
+      "loss": 0.0785,
+      "step": 520
+    },
+    {
+      "epoch": 2.506072058453011,
+      "grad_norm": 22.20425796508789,
+      "learning_rate": 3.358463009375927e-05,
+      "loss": 0.0779,
+      "step": 530
+    },
+    {
+      "epoch": 2.5383219954648526,
+      "grad_norm": 18.57112693786621,
+      "learning_rate": 3.332739453466098e-05,
+      "loss": 0.0814,
+      "step": 540
+    },
+    {
+      "epoch": 2.5705719324766942,
+      "grad_norm": 20.270761489868164,
+      "learning_rate": 3.306613071313641e-05,
+      "loss": 0.0808,
+      "step": 550
+    },
+    {
+      "epoch": 2.602821869488536,
+      "grad_norm": 19.787559509277344,
+      "learning_rate": 3.280091759730144e-05,
+      "loss": 0.0743,
+      "step": 560
+    },
+    {
+      "epoch": 2.635071806500378,
+      "grad_norm": 18.70611572265625,
+      "learning_rate": 3.25318353489631e-05,
+      "loss": 0.0757,
+      "step": 570
+    },
+    {
+      "epoch": 2.6673217435122196,
+      "grad_norm": 20.557205200195312,
+      "learning_rate": 3.2258965299390465e-05,
+      "loss": 0.0692,
+      "step": 580
+    },
+    {
+      "epoch": 2.6995716805240617,
+      "grad_norm": 20.602092742919922,
+      "learning_rate": 3.1982389924731805e-05,
+      "loss": 0.0699,
+      "step": 590
+    },
+    {
+      "epoch": 2.7318216175359034,
+      "grad_norm": 22.87337303161621,
+      "learning_rate": 3.17021928210859e-05,
+      "loss": 0.0662,
+      "step": 600
+    },
+    {
+      "epoch": 2.764071554547745,
+      "grad_norm": 22.488433837890625,
+      "learning_rate": 3.141845867923469e-05,
+      "loss": 0.0799,
+      "step": 610
+    },
+    {
+      "epoch": 2.7963214915595866,
+      "grad_norm": 20.05706787109375,
+      "learning_rate": 3.113127325904519e-05,
+      "loss": 0.0665,
+      "step": 620
+    },
+    {
+      "epoch": 2.8285714285714287,
+      "grad_norm": 18.822357177734375,
+      "learning_rate": 3.084072336354812e-05,
+      "loss": 0.0668,
+      "step": 630
+    },
+    {
+      "epoch": 2.8608213655832704,
+      "grad_norm": 17.79743194580078,
+      "learning_rate": 3.05468968127014e-05,
+      "loss": 0.0604,
+      "step": 640
+    },
+    {
+      "epoch": 2.893071302595112,
+      "grad_norm": 19.10596466064453,
+      "learning_rate": 3.0249882416846117e-05,
+      "loss": 0.059,
+      "step": 650
+    },
+    {
+      "epoch": 2.925321239606954,
+      "grad_norm": 20.25804328918457,
+      "learning_rate": 2.9949769949863266e-05,
+      "loss": 0.0646,
+      "step": 660
+    },
+    {
+      "epoch": 2.9575711766187958,
+      "grad_norm": 19.09357452392578,
+      "learning_rate": 2.96466501220392e-05,
+      "loss": 0.0569,
+      "step": 670
+    },
+    {
+      "epoch": 2.9898211136306374,
+      "grad_norm": 15.293481826782227,
+      "learning_rate": 2.934061455264802e-05,
+      "loss": 0.0574,
+      "step": 680
+    },
+    {
+      "epoch": 2.99949609473419,
+      "step": 683,
+      "total_flos": 6.564245582272266e+17,
+      "train_loss": 0.1658007610769258,
+      "train_runtime": 25935.882,
+      "train_samples_per_second": 9.206,
+      "train_steps_per_second": 0.072
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1863,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.564245582272266e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe26717ade77091d84e0f68e22523033018b95d33245be7b8f5b046cac304f98
+size 5304