初始化项目，由ModelHub XC社区提供模型

Model: aixk/kosmo-TEST
Source: Original Platform

slots/0/checkpoint-3/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neftune_alpha": 0.0,
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "qk_norm": true,
+  "rezero_init": 0.0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 100000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 53120
+}

slots/0/checkpoint-3/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

slots/0/checkpoint-3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c144cd04d6eecc6995e70c1d93b9ff507b7bee20031918b66b49ca36eec7a0
+size 669621248

slots/0/checkpoint-3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

slots/0/checkpoint-3/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4657658338546753,
+      "learning_rate": 1e-05,
+      "loss": 11.592748641967773,
+      "step": 1
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 282408920285184.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

slots/0/checkpoint-3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb4adf0b4a3af69a461248080f7e3a32cbcac1817718a04a0c9502f5564770e
+size 5201

slots/0/latest.json

@@ -0,0 +1 @@
+{"worker_id": "slot:0", "checkpoint": "slots/0/checkpoint-3", "step": 3, "updated_at": 1777265165}