Training in progress, epoch 1

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "tonyshark/deepseek-v3-1b",
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tonyshark/deepseek-v3-1b--configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "tonyshark/deepseek-v3-1b--modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "tonyshark/deepseek-v3-1b--modeling_deepseek.DeepseekV3ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 5376,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 640,
+  "moe_layer_freq": 1,
+  "n_group": 8,
+  "n_routed_experts": 32,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 8,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 13,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pretraining_tp": 1,
+  "q_lora_rank": 1536,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "topk_method": "noaux_tc",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 129280
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d0893b4a6f7ad8282fe4255f087a31b6c0b1f6d95b956cb1d85a85e11fa7e3
+size 4198331024

runs/Jan15_10-25-03_06039d86ac92/events.out.tfevents.1736936704.06039d86ac92.261.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d32314bf5809424b8c7a9081b5d6b1225fed17b47196c81b6a2ffe023036761
+size 6768

runs/Jan15_10-30-52_06039d86ac92/events.out.tfevents.1736937053.06039d86ac92.238.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4962571ecb847d3a10ad6fa491eaab5bb4cf869c928a590326e9de0bd6fdf726
+size 6768

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7c9b1413f6cec1536a0b59ee4c7b74475ec0262a7c616cfbcb6dfe12832aa5
+size 5624