Upload SFT warmstart checkpoint-1000 for Qwen2.5-0.5B trained on cognitive behavioral reasoning

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd22a5af354785f6508f3965d65674ff0c247c853fc8ddbbb6ee66cba1a1006b
+size 1976163472

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5175eff5dccb9668a64ed328d8adef4528a7c854b7c1dd36de43cf4550d7fc01
+size 3952509771

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1047afaeb78bfefb5fd31cf31495f63e1d5860542b224294777dc9a8b20c58
+size 16389

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1705a17f9d6d640e6377f77fe8891ffef651f541363de0056e2dfa62f25c1bd4
+size 16389

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab1c3a0edbd4f742052fc6b51f05a3b5007cd0a9206db9846113ec36893101d
+size 16389

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183e8dfc6d1e37c32093f78d53ac8a2bb735a002f6b8b5e01daccac684f44445
+size 16389

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1cfc8ea83252c4f88d78bf9df1ea5ca3cc076c41f209742a4542060c806ca8
+size 16389

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870d09281998d4a17beafb9cce4ef3a071b9be91ca7875007bcd8f23302b4f15
+size 16389

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30af43e682687c937ae6f8f571ec1ba65bcd56697cd146d2a74d947f97704545
+size 16389

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2031fa13eedf00740d1878ba7c14fea55fb07c7013c9bcf6a15d2415789f0ca8
+size 16389

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800683ae7246d60903b17b6f65eb13163c8e5e80d343adfa16b43f7061550d5d
+size 1465

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 31.288,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.576,
+      "grad_norm": 1.8477455377578735,
+      "learning_rate": 1.902e-05,
+      "loss": 0.5372,
+      "step": 50
+    },
+    {
+      "epoch": 3.128,
+      "grad_norm": 2.0089797973632812,
+      "learning_rate": 1.802e-05,
+      "loss": 0.3413,
+      "step": 100
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 1.974068522453308,
+      "learning_rate": 1.702e-05,
+      "loss": 0.2378,
+      "step": 150
+    },
+    {
+      "epoch": 6.256,
+      "grad_norm": 2.1175522804260254,
+      "learning_rate": 1.6020000000000002e-05,
+      "loss": 0.1581,
+      "step": 200
+    },
+    {
+      "epoch": 7.832,
+      "grad_norm": 1.9842787981033325,
+      "learning_rate": 1.5020000000000002e-05,
+      "loss": 0.1031,
+      "step": 250
+    },
+    {
+      "epoch": 9.416,
+      "grad_norm": 1.7242268323898315,
+      "learning_rate": 1.6013333333333335e-05,
+      "loss": 0.081,
+      "step": 300
+    },
+    {
+      "epoch": 10.992,
+      "grad_norm": 1.9856055974960327,
+      "learning_rate": 1.5346666666666667e-05,
+      "loss": 0.0662,
+      "step": 350
+    },
+    {
+      "epoch": 12.544,
+      "grad_norm": 1.8598779439926147,
+      "learning_rate": 1.4680000000000002e-05,
+      "loss": 0.0495,
+      "step": 400
+    },
+    {
+      "epoch": 14.096,
+      "grad_norm": 1.4556602239608765,
+      "learning_rate": 1.4013333333333334e-05,
+      "loss": 0.0403,
+      "step": 450
+    },
+    {
+      "epoch": 15.672,
+      "grad_norm": 1.5721633434295654,
+      "learning_rate": 1.3346666666666667e-05,
+      "loss": 0.0317,
+      "step": 500
+    },
+    {
+      "epoch": 17.224,
+      "grad_norm": 1.2817391157150269,
+      "learning_rate": 1.268e-05,
+      "loss": 0.0276,
+      "step": 550
+    },
+    {
+      "epoch": 18.8,
+      "grad_norm": 1.367484211921692,
+      "learning_rate": 1.2013333333333334e-05,
+      "loss": 0.0244,
+      "step": 600
+    },
+    {
+      "epoch": 20.352,
+      "grad_norm": 1.272678017616272,
+      "learning_rate": 1.1346666666666668e-05,
+      "loss": 0.0222,
+      "step": 650
+    },
+    {
+      "epoch": 21.928,
+      "grad_norm": 0.9668142199516296,
+      "learning_rate": 1.0680000000000001e-05,
+      "loss": 0.0207,
+      "step": 700
+    },
+    {
+      "epoch": 23.48,
+      "grad_norm": 0.9578900933265686,
+      "learning_rate": 1.0013333333333335e-05,
+      "loss": 0.0193,
+      "step": 750
+    },
+    {
+      "epoch": 25.032,
+      "grad_norm": 0.5145262479782104,
+      "learning_rate": 9.346666666666666e-06,
+      "loss": 0.0175,
+      "step": 800
+    },
+    {
+      "epoch": 26.608,
+      "grad_norm": 0.44180870056152344,
+      "learning_rate": 8.68e-06,
+      "loss": 0.0162,
+      "step": 850
+    },
+    {
+      "epoch": 28.16,
+      "grad_norm": 0.43457069993019104,
+      "learning_rate": 8.013333333333333e-06,
+      "loss": 0.0156,
+      "step": 900
+    },
+    {
+      "epoch": 29.736,
+      "grad_norm": 0.5348331928253174,
+      "learning_rate": 7.346666666666668e-06,
+      "loss": 0.0145,
+      "step": 950
+    },
+    {
+      "epoch": 31.288,
+      "grad_norm": 0.43445634841918945,
+      "learning_rate": 6.680000000000001e-06,
+      "loss": 0.0141,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 47,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.879999744068813e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a833b2e23e7f02a1df4f0f2edd96f03ae2bbeefcd63ff66c401e51cba69d8f6
+size 5777