Add 60m/mars_lion_lr5e_4_b1_0_9_b2_0_98_eps_1e_8_A100_ppl_32_4056_20260416_193855

60m/mars_lion_lr5e_4_b1_0_9_b2_0_98_eps_1e_8_A100_ppl_32_4056_20260416_193855/model_10000/config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1376,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

60m/mars_lion_lr5e_4_b1_0_9_b2_0_98_eps_1e_8_A100_ppl_32_4056_20260416_193855/model_10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e4a4643101b40d1d019aa3db62c6e6c0214a98aedcbbc0e000d294d331e847
+size 116156896

60m/mars_lion_lr5e_4_b1_0_9_b2_0_98_eps_1e_8_A100_ppl_32_4056_20260416_193855/model_10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f04bdc728a6d7db5b7264acf4aef2119be1548205c7ed8b8b6b2e28d692f0c1
+size 348513146

60m/mars_lion_lr5e_4_b1_0_9_b2_0_98_eps_1e_8_A100_ppl_32_4056_20260416_193855/model_10000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4825556e3bda41c9a5393fcb7ec41bc16534c2f420fa9faec84dfa133c031873
+size 116181735

60m/mars_lion_lr5e_4_b1_0_9_b2_0_98_eps_1e_8_A100_ppl_32_4056_20260416_193855/model_10000/training_state.json

@@ -0,0 +1,7 @@
+{
+    "global_step": 10000,
+    "update_step": 10000,
+    "tokens_seen": 999923888,
+    "tokens_seen_before": 999826428,
+    "update_time": 0.30499839782714844
+}