Upload folder using huggingface_hub

checkpoint-200/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-200/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:311dabb65e847795977f56083083f1bae5790b25fcae0db8d43f939c151b8947
+size 2384234968

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8fedd3b0b7761ccc5b5b5f0eb97d1a8f3992a69d39e2965d95f03c938c8ab2
+size 4768662910

checkpoint-200/rng_state.pth

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

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff0105aa7ecbcf2cbe9e48ef653e70d541e736c71e9edc33f55335b22e8801a
+size 988

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e0d8e16a36c5cae8268bbc48b1c6177471c3b7c006fd98baaf7cfd891c9d27
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_global_step": 200,
+  "best_metric": 1.0429821014404297,
+  "best_model_checkpoint": "models/MNLP_M3_rag_model/checkpoint-200",
+  "epoch": 1.04177545691906,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05221932114882506,
+      "grad_norm": 388.6032409667969,
+      "learning_rate": 2.7586206896551725e-06,
+      "loss": 11.4444,
+      "step": 10
+    },
+    {
+      "epoch": 0.10443864229765012,
+      "grad_norm": 16.180984497070312,
+      "learning_rate": 9.655172413793105e-06,
+      "loss": 1.9209,
+      "step": 20
+    },
+    {
+      "epoch": 0.1566579634464752,
+      "grad_norm": 77.73260498046875,
+      "learning_rate": 1.6551724137931037e-05,
+      "loss": 1.3128,
+      "step": 30
+    },
+    {
+      "epoch": 0.20887728459530025,
+      "grad_norm": 103.49502563476562,
+      "learning_rate": 1.981617647058824e-05,
+      "loss": 0.7444,
+      "step": 40
+    },
+    {
+      "epoch": 0.26109660574412535,
+      "grad_norm": 71.25463104248047,
+      "learning_rate": 1.9448529411764706e-05,
+      "loss": 0.7653,
+      "step": 50
+    },
+    {
+      "epoch": 0.3133159268929504,
+      "grad_norm": 168.3430633544922,
+      "learning_rate": 1.908088235294118e-05,
+      "loss": 0.6154,
+      "step": 60
+    },
+    {
+      "epoch": 0.36553524804177545,
+      "grad_norm": 46.75175857543945,
+      "learning_rate": 1.8713235294117647e-05,
+      "loss": 0.9861,
+      "step": 70
+    },
+    {
+      "epoch": 0.4177545691906005,
+      "grad_norm": 45.60316467285156,
+      "learning_rate": 1.8345588235294118e-05,
+      "loss": 0.9699,
+      "step": 80
+    },
+    {
+      "epoch": 0.4699738903394256,
+      "grad_norm": 72.48204040527344,
+      "learning_rate": 1.7977941176470592e-05,
+      "loss": 0.7536,
+      "step": 90
+    },
+    {
+      "epoch": 0.5221932114882507,
+      "grad_norm": 125.96574401855469,
+      "learning_rate": 1.761029411764706e-05,
+      "loss": 0.55,
+      "step": 100
+    },
+    {
+      "epoch": 0.5744125326370757,
+      "grad_norm": 25.672470092773438,
+      "learning_rate": 1.7242647058823533e-05,
+      "loss": 1.3258,
+      "step": 110
+    },
+    {
+      "epoch": 0.6266318537859008,
+      "grad_norm": 82.88054656982422,
+      "learning_rate": 1.6875e-05,
+      "loss": 0.7496,
+      "step": 120
+    },
+    {
+      "epoch": 0.6788511749347258,
+      "grad_norm": 66.79105377197266,
+      "learning_rate": 1.650735294117647e-05,
+      "loss": 0.7877,
+      "step": 130
+    },
+    {
+      "epoch": 0.7310704960835509,
+      "grad_norm": 99.85301971435547,
+      "learning_rate": 1.613970588235294e-05,
+      "loss": 0.6072,
+      "step": 140
+    },
+    {
+      "epoch": 0.783289817232376,
+      "grad_norm": 112.50544738769531,
+      "learning_rate": 1.5772058823529412e-05,
+      "loss": 0.6097,
+      "step": 150
+    },
+    {
+      "epoch": 0.835509138381201,
+      "grad_norm": 114.9411849975586,
+      "learning_rate": 1.5404411764705886e-05,
+      "loss": 0.6873,
+      "step": 160
+    },
+    {
+      "epoch": 0.8877284595300261,
+      "grad_norm": 129.22744750976562,
+      "learning_rate": 1.5036764705882353e-05,
+      "loss": 1.1041,
+      "step": 170
+    },
+    {
+      "epoch": 0.9399477806788512,
+      "grad_norm": 43.67152786254883,
+      "learning_rate": 1.4669117647058824e-05,
+      "loss": 0.7666,
+      "step": 180
+    },
+    {
+      "epoch": 0.9921671018276762,
+      "grad_norm": 53.90073013305664,
+      "learning_rate": 1.4301470588235296e-05,
+      "loss": 0.6146,
+      "step": 190
+    },
+    {
+      "epoch": 1.04177545691906,
+      "grad_norm": 279.6166076660156,
+      "learning_rate": 1.3933823529411765e-05,
+      "loss": 0.2116,
+      "step": 200
+    },
+    {
+      "epoch": 1.04177545691906,
+      "eval_loss": 1.0429821014404297,
+      "eval_runtime": 4.8371,
+      "eval_samples_per_second": 35.351,
+      "eval_steps_per_second": 4.548,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 573,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2158220059607040.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d046ee5acd3654a3e3e6d0880e6336c0a2bc9b3d60c38f413a60640aecea23e
+size 5240

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ade8bdd44aa601ae248da7fca7ec3da0d3f8d408d7d1dba9c73d68fd4c74251
+oid sha256:cd3e96d482be70c706f0334c42d89f1d061a38adde8752bcd501b4941414bb14
 size 2384234968