Upload folder using huggingface_hub

Qwen/Qwen1.5_1.8B_amazon/README.md

@@ -0,0 +1,72 @@
+---
+license: other
+base_model: Qwen/Qwen1.5-1.8B
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: Qwen1.5_1.8B_amazon
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen1.5_1.8B_amazon
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5073
+- Accuracy: 0.8524
+- F1 Macro: 0.8290
+- F1 Micro: 0.8524
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
+| 1.5641        | 0.13  | 50   | 1.2905          | 0.6476   | 0.5589   | 0.6476   |
+| 0.744         | 0.26  | 100  | 0.7994          | 0.7694   | 0.7166   | 0.7694   |
+| 0.7245        | 0.39  | 150  | 0.6846          | 0.7997   | 0.7450   | 0.7997   |
+| 0.6491        | 0.53  | 200  | 0.6406          | 0.8155   | 0.7679   | 0.8155   |
+| 0.6193        | 0.66  | 250  | 0.5427          | 0.8399   | 0.7970   | 0.8399   |
+| 0.4828        | 0.79  | 300  | 0.5453          | 0.8366   | 0.8114   | 0.8366   |
+| 0.6122        | 0.92  | 350  | 0.5073          | 0.8524   | 0.8290   | 0.8524   |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

Qwen/Qwen1.5_1.8B_amazon/added_tokens.json

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

Qwen/Qwen1.5_1.8B_amazon/all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.852437417654809,
+    "eval_f1_macro": 0.8289709215944268,
+    "eval_f1_micro": 0.852437417654809,
+    "eval_loss": 0.5073133111000061,
+    "eval_runtime": 3.9722,
+    "eval_samples": 1518,
+    "eval_samples_per_second": 382.155,
+    "eval_steps_per_second": 12.084,
+    "test_accuracy": 0.8656126482213439,
+    "test_f1_macro": 0.8295835523548035,
+    "test_f1_micro": 0.8656126482213439,
+    "test_loss": 0.4794342815876007,
+    "test_runtime": 4.0382,
+    "test_samples_per_second": 375.908,
+    "test_steps_per_second": 11.886,
+    "train_loss": 1.0740083393297697,
+    "train_runtime": 415.974,
+    "train_samples": 12144,
+    "train_samples_per_second": 29.194,
+    "train_steps_per_second": 0.914
+}

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/added_tokens.json

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

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "finetuning_task": "text-classification",
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "10",
+    "3": "11",
+    "4": "12",
+    "5": "13",
+    "6": "14",
+    "7": "15",
+    "8": "16",
+    "9": "17",
+    "10": "18",
+    "11": "19",
+    "12": "2",
+    "13": "20",
+    "14": "21",
+    "15": "22",
+    "16": "3",
+    "17": "4",
+    "18": "5",
+    "19": "6",
+    "20": "7",
+    "21": "8",
+    "22": "9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "10": 2,
+    "11": 3,
+    "12": 4,
+    "13": 5,
+    "14": 6,
+    "15": 7,
+    "16": 8,
+    "17": 9,
+    "18": 10,
+    "19": 11,
+    "2": 12,
+    "20": 13,
+    "21": 14,
+    "22": 15,
+    "3": 16,
+    "4": 17,
+    "5": 18,
+    "6": 19,
+    "7": 20,
+    "8": 21,
+    "9": 22
+  },
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 151643,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08f9ddeb9dca9bf94cdc457dd21a296528f54c1a28b8af27f936599ebc5e46d
+size 9150715276

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7e454f14efa9979ff8e981a3dac6698bd7f776065bdc719c7e7d2ff8fd9a1e
+size 9150720140

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/global_step350/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f80552d860681d5289ac4fcfaa66284b26fcd501aea94b38410446e3284d61
+size 3050314104

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/latest

@@ -0,0 +1 @@
+global_step350

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808b083c2b74b6e447184a8246a4f99aa1838fe9f48beb716cd8d58963f8bbdd
+size 3050267112

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1d637e319354543bdf6602f8671d0efc3f4c6a598f00c1d5dcff1b2ab0526b
+size 14512

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a10e91fc2fde9de5ea613418b9d98240dbbdab43b35a47dfeeda62762dc069e
+size 14512

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c1c646c9b712a4834345fe22046fc71096a5565a8a35ccaa0f8943b016cf5a
+size 1064

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/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,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/trainer_state.json

@@ -0,0 +1,343 @@
+{
+  "best_metric": 0.5073133111000061,
+  "best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350",
+  "epoch": 0.9210526315789473,
+  "eval_steps": 50,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 129.14089965820312,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 7.3844,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 123.16605377197266,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 4.8281,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 73.3310546875,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 3.2703,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 79.52980041503906,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 2.0736,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 65.27238464355469,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 1.5641,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.647562582345191,
+      "eval_f1_macro": 0.5588571972473421,
+      "eval_f1_micro": 0.647562582345191,
+      "eval_loss": 1.2904983758926392,
+      "eval_runtime": 4.0513,
+      "eval_samples_per_second": 374.697,
+      "eval_steps_per_second": 11.848,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 50.00752258300781,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.1144,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 39.85783386230469,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 1.1287,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 62.46803665161133,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.8914,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 42.484432220458984,
+      "learning_rate": 3.815789473684211e-06,
+      "loss": 0.8281,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 48.54948043823242,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.744,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.769433465085639,
+      "eval_f1_macro": 0.716629286760697,
+      "eval_f1_micro": 0.769433465085639,
+      "eval_loss": 0.7993608117103577,
+      "eval_runtime": 4.0452,
+      "eval_samples_per_second": 375.256,
+      "eval_steps_per_second": 11.866,
+      "step": 100
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 47.28898239135742,
+      "learning_rate": 3.5526315789473687e-06,
+      "loss": 0.9268,
+      "step": 110
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 49.59343338012695,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.7649,
+      "step": 120
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 36.2591438293457,
+      "learning_rate": 3.289473684210527e-06,
+      "loss": 0.716,
+      "step": 130
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 47.06060791015625,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.5508,
+      "step": 140
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 45.960975646972656,
+      "learning_rate": 3.0263157894736843e-06,
+      "loss": 0.7245,
+      "step": 150
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.7997364953886693,
+      "eval_f1_macro": 0.744994161609646,
+      "eval_f1_micro": 0.7997364953886693,
+      "eval_loss": 0.6845870614051819,
+      "eval_runtime": 4.0142,
+      "eval_samples_per_second": 378.16,
+      "eval_steps_per_second": 11.958,
+      "step": 150
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 49.28917694091797,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.6837,
+      "step": 160
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 34.09211349487305,
+      "learning_rate": 2.7631578947368424e-06,
+      "loss": 0.6589,
+      "step": 170
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 38.694705963134766,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.6702,
+      "step": 180
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 64.92501068115234,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7353,
+      "step": 190
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 39.18191909790039,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.6491,
+      "step": 200
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.8155467720685112,
+      "eval_f1_macro": 0.7679142075529768,
+      "eval_f1_micro": 0.8155467720685112,
+      "eval_loss": 0.640599250793457,
+      "eval_runtime": 4.0408,
+      "eval_samples_per_second": 375.669,
+      "eval_steps_per_second": 11.879,
+      "step": 200
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 39.82322311401367,
+      "learning_rate": 2.236842105263158e-06,
+      "loss": 0.545,
+      "step": 210
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 60.72475051879883,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.5595,
+      "step": 220
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 42.45864486694336,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.6386,
+      "step": 230
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 48.077884674072266,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 0.649,
+      "step": 240
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 48.596435546875,
+      "learning_rate": 1.710526315789474e-06,
+      "loss": 0.6193,
+      "step": 250
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.8399209486166008,
+      "eval_f1_macro": 0.7970428846372188,
+      "eval_f1_micro": 0.8399209486166008,
+      "eval_loss": 0.5427243113517761,
+      "eval_runtime": 4.3118,
+      "eval_samples_per_second": 352.055,
+      "eval_steps_per_second": 11.132,
+      "step": 250
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 45.50446319580078,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.6343,
+      "step": 260
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 40.66709518432617,
+      "learning_rate": 1.4473684210526317e-06,
+      "loss": 0.5493,
+      "step": 270
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 50.266971588134766,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.5177,
+      "step": 280
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 41.21518325805664,
+      "learning_rate": 1.1842105263157894e-06,
+      "loss": 0.4751,
+      "step": 290
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 35.079444885253906,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 0.4828,
+      "step": 300
+    },
+    {
+      "epoch": 0.79,
+      "eval_accuracy": 0.836627140974967,
+      "eval_f1_macro": 0.8114023231734937,
+      "eval_f1_micro": 0.836627140974967,
+      "eval_loss": 0.5453078746795654,
+      "eval_runtime": 4.0339,
+      "eval_samples_per_second": 376.309,
+      "eval_steps_per_second": 11.899,
+      "step": 300
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 51.024139404296875,
+      "learning_rate": 9.210526315789474e-07,
+      "loss": 0.4726,
+      "step": 310
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 41.68681335449219,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.5492,
+      "step": 320
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 31.459598541259766,
+      "learning_rate": 6.578947368421053e-07,
+      "loss": 0.6464,
+      "step": 330
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 37.8900260925293,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 0.4235,
+      "step": 340
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 80.35220336914062,
+      "learning_rate": 3.9473684210526315e-07,
+      "loss": 0.6122,
+      "step": 350
+    },
+    {
+      "epoch": 0.92,
+      "eval_accuracy": 0.852437417654809,
+      "eval_f1_macro": 0.8289709215944268,
+      "eval_f1_micro": 0.852437417654809,
+      "eval_loss": 0.5073133111000061,
+      "eval_runtime": 4.0684,
+      "eval_samples_per_second": 373.116,
+      "eval_steps_per_second": 11.798,
+      "step": 350
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "total_flos": 1.0447038185472e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b20cc25ef3f3381a0bb4e70b578853792c4ac9c2ffef36a86d3a450a66fc2aa
+size 5944

Qwen/Qwen1.5_1.8B_amazon/checkpoint-350/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

Qwen/Qwen1.5_1.8B_amazon/config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "finetuning_task": "text-classification",
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "10",
+    "3": "11",
+    "4": "12",
+    "5": "13",
+    "6": "14",
+    "7": "15",
+    "8": "16",
+    "9": "17",
+    "10": "18",
+    "11": "19",
+    "12": "2",
+    "13": "20",
+    "14": "21",
+    "15": "22",
+    "16": "3",
+    "17": "4",
+    "18": "5",
+    "19": "6",
+    "20": "7",
+    "21": "8",
+    "22": "9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "10": 2,
+    "11": 3,
+    "12": 4,
+    "13": 5,
+    "14": 6,
+    "15": 7,
+    "16": 8,
+    "17": 9,
+    "18": 10,
+    "19": 11,
+    "2": 12,
+    "20": 13,
+    "21": 14,
+    "22": 15,
+    "3": 16,
+    "4": 17,
+    "5": 18,
+    "6": 19,
+    "7": 20,
+    "8": 21,
+    "9": 22
+  },
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 151643,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

Qwen/Qwen1.5_1.8B_amazon/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.852437417654809,
+    "eval_f1_macro": 0.8289709215944268,
+    "eval_f1_micro": 0.852437417654809,
+    "eval_loss": 0.5073133111000061,
+    "eval_runtime": 3.9722,
+    "eval_samples": 1518,
+    "eval_samples_per_second": 382.155,
+    "eval_steps_per_second": 12.084
+}

Qwen/Qwen1.5_1.8B_amazon/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808b083c2b74b6e447184a8246a4f99aa1838fe9f48beb716cd8d58963f8bbdd
+size 3050267112

Qwen/Qwen1.5_1.8B_amazon/run.log

@@ -0,0 +1,4 @@
+03/15/2024 11:43:05 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False
+03/15/2024 11:43:05 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: False
+03/15/2024 11:43:15 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
+03/15/2024 11:43:15 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.

Qwen/Qwen1.5_1.8B_amazon/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

Qwen/Qwen1.5_1.8B_amazon/test_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "test_accuracy": 0.8656126482213439,
+    "test_f1_macro": 0.8295835523548035,
+    "test_f1_micro": 0.8656126482213439,
+    "test_loss": 0.4794342815876007,
+    "test_runtime": 4.0382,
+    "test_samples_per_second": 375.908,
+    "test_steps_per_second": 11.886
+}

Qwen/Qwen1.5_1.8B_amazon/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,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen/Qwen1.5_1.8B_amazon/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.0740083393297697,
+    "train_runtime": 415.974,
+    "train_samples": 12144,
+    "train_samples_per_second": 29.194,
+    "train_steps_per_second": 0.914
+}

Qwen/Qwen1.5_1.8B_amazon/trainer_state.json

@@ -0,0 +1,373 @@
+{
+  "best_metric": 0.5073133111000061,
+  "best_model_checkpoint": "../../experiments_checkpoints/MAdAiLab/Qwen/Qwen1.5_1.8B_amazon/checkpoint-350",
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "grad_norm": 129.14089965820312,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 7.3844,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 123.16605377197266,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 4.8281,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 73.3310546875,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 3.2703,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 79.52980041503906,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 2.0736,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 65.27238464355469,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 1.5641,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.647562582345191,
+      "eval_f1_macro": 0.5588571972473421,
+      "eval_f1_micro": 0.647562582345191,
+      "eval_loss": 1.2904983758926392,
+      "eval_runtime": 4.0513,
+      "eval_samples_per_second": 374.697,
+      "eval_steps_per_second": 11.848,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 50.00752258300781,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.1144,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 39.85783386230469,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 1.1287,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 62.46803665161133,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.8914,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 42.484432220458984,
+      "learning_rate": 3.815789473684211e-06,
+      "loss": 0.8281,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 48.54948043823242,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.744,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.769433465085639,
+      "eval_f1_macro": 0.716629286760697,
+      "eval_f1_micro": 0.769433465085639,
+      "eval_loss": 0.7993608117103577,
+      "eval_runtime": 4.0452,
+      "eval_samples_per_second": 375.256,
+      "eval_steps_per_second": 11.866,
+      "step": 100
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 47.28898239135742,
+      "learning_rate": 3.5526315789473687e-06,
+      "loss": 0.9268,
+      "step": 110
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 49.59343338012695,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.7649,
+      "step": 120
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 36.2591438293457,
+      "learning_rate": 3.289473684210527e-06,
+      "loss": 0.716,
+      "step": 130
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 47.06060791015625,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.5508,
+      "step": 140
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 45.960975646972656,
+      "learning_rate": 3.0263157894736843e-06,
+      "loss": 0.7245,
+      "step": 150
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.7997364953886693,
+      "eval_f1_macro": 0.744994161609646,
+      "eval_f1_micro": 0.7997364953886693,
+      "eval_loss": 0.6845870614051819,
+      "eval_runtime": 4.0142,
+      "eval_samples_per_second": 378.16,
+      "eval_steps_per_second": 11.958,
+      "step": 150
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 49.28917694091797,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.6837,
+      "step": 160
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 34.09211349487305,
+      "learning_rate": 2.7631578947368424e-06,
+      "loss": 0.6589,
+      "step": 170
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 38.694705963134766,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.6702,
+      "step": 180
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 64.92501068115234,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7353,
+      "step": 190
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 39.18191909790039,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.6491,
+      "step": 200
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.8155467720685112,
+      "eval_f1_macro": 0.7679142075529768,
+      "eval_f1_micro": 0.8155467720685112,
+      "eval_loss": 0.640599250793457,
+      "eval_runtime": 4.0408,
+      "eval_samples_per_second": 375.669,
+      "eval_steps_per_second": 11.879,
+      "step": 200
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 39.82322311401367,
+      "learning_rate": 2.236842105263158e-06,
+      "loss": 0.545,
+      "step": 210
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 60.72475051879883,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.5595,
+      "step": 220
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 42.45864486694336,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.6386,
+      "step": 230
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 48.077884674072266,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 0.649,
+      "step": 240
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 48.596435546875,
+      "learning_rate": 1.710526315789474e-06,
+      "loss": 0.6193,
+      "step": 250
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.8399209486166008,
+      "eval_f1_macro": 0.7970428846372188,
+      "eval_f1_micro": 0.8399209486166008,
+      "eval_loss": 0.5427243113517761,
+      "eval_runtime": 4.3118,
+      "eval_samples_per_second": 352.055,
+      "eval_steps_per_second": 11.132,
+      "step": 250
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 45.50446319580078,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.6343,
+      "step": 260
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 40.66709518432617,
+      "learning_rate": 1.4473684210526317e-06,
+      "loss": 0.5493,
+      "step": 270
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 50.266971588134766,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.5177,
+      "step": 280
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 41.21518325805664,
+      "learning_rate": 1.1842105263157894e-06,
+      "loss": 0.4751,
+      "step": 290
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 35.079444885253906,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 0.4828,
+      "step": 300
+    },
+    {
+      "epoch": 0.79,
+      "eval_accuracy": 0.836627140974967,
+      "eval_f1_macro": 0.8114023231734937,
+      "eval_f1_micro": 0.836627140974967,
+      "eval_loss": 0.5453078746795654,
+      "eval_runtime": 4.0339,
+      "eval_samples_per_second": 376.309,
+      "eval_steps_per_second": 11.899,
+      "step": 300
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 51.024139404296875,
+      "learning_rate": 9.210526315789474e-07,
+      "loss": 0.4726,
+      "step": 310
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 41.68681335449219,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.5492,
+      "step": 320
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 31.459598541259766,
+      "learning_rate": 6.578947368421053e-07,
+      "loss": 0.6464,
+      "step": 330
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 37.8900260925293,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 0.4235,
+      "step": 340
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 80.35220336914062,
+      "learning_rate": 3.9473684210526315e-07,
+      "loss": 0.6122,
+      "step": 350
+    },
+    {
+      "epoch": 0.92,
+      "eval_accuracy": 0.852437417654809,
+      "eval_f1_macro": 0.8289709215944268,
+      "eval_f1_micro": 0.852437417654809,
+      "eval_loss": 0.5073133111000061,
+      "eval_runtime": 4.0684,
+      "eval_samples_per_second": 373.116,
+      "eval_steps_per_second": 11.798,
+      "step": 350
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 35.06690979003906,
+      "learning_rate": 2.6315789473684213e-07,
+      "loss": 0.4292,
+      "step": 360
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 46.45317077636719,
+      "learning_rate": 1.3157894736842107e-07,
+      "loss": 0.5656,
+      "step": 370
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 42.95165252685547,
+      "learning_rate": 0.0,
+      "loss": 0.5355,
+      "step": 380
+    },
+    {
+      "epoch": 1.0,
+      "step": 380,
+      "total_flos": 1.13424986013696e+16,
+      "train_loss": 1.0740083393297697,
+      "train_runtime": 415.974,
+      "train_samples_per_second": 29.194,
+      "train_steps_per_second": 0.914
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "total_flos": 1.13424986013696e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen/Qwen1.5_1.8B_amazon/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b20cc25ef3f3381a0bb4e70b578853792c4ac9c2ffef36a86d3a450a66fc2aa
+size 5944

Qwen/Qwen1.5_1.8B_patent/README.md

@@ -0,0 +1,88 @@
+---
+license: other
+base_model: Qwen/Qwen1.5-1.8B
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: Qwen1.5_1.8B_patent
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen1.5_1.8B_patent
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8989
+- Accuracy: 0.6976
+- F1 Macro: 0.6507
+- F1 Micro: 0.6976
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
+| 1.4469        | 0.13  | 50   | 1.3521          | 0.528    | 0.3842   | 0.528    |
+| 1.1465        | 0.26  | 100  | 1.1614          | 0.596    | 0.4991   | 0.596    |
+| 1.1717        | 0.38  | 150  | 1.0561          | 0.6286   | 0.5523   | 0.6286   |
+| 0.9861        | 0.51  | 200  | 0.9592          | 0.6682   | 0.5813   | 0.6682   |
+| 0.9701        | 0.64  | 250  | 0.9579          | 0.6658   | 0.5949   | 0.6658   |
+| 0.9389        | 0.77  | 300  | 0.9364          | 0.679    | 0.6287   | 0.679    |
+| 0.9914        | 0.9   | 350  | 0.9246          | 0.6756   | 0.6115   | 0.6756   |
+| 0.7508        | 1.02  | 400  | 0.9047          | 0.6812   | 0.6406   | 0.6812   |
+| 0.6312        | 1.15  | 450  | 0.9342          | 0.6844   | 0.6410   | 0.6844   |
+| 0.6436        | 1.28  | 500  | 0.9464          | 0.6848   | 0.6410   | 0.6848   |
+| 0.6429        | 1.41  | 550  | 0.9366          | 0.6846   | 0.6299   | 0.6846   |
+| 0.6471        | 1.53  | 600  | 0.9347          | 0.6812   | 0.6490   | 0.6812   |
+| 0.7045        | 1.66  | 650  | 0.9457          | 0.6696   | 0.6265   | 0.6696   |
+| 0.6311        | 1.79  | 700  | 0.9206          | 0.6924   | 0.6303   | 0.6924   |
+| 0.6659        | 1.92  | 750  | 0.8989          | 0.6976   | 0.6507   | 0.6976   |
+| 0.2872        | 2.05  | 800  | 1.0101          | 0.6888   | 0.6524   | 0.6888   |
+| 0.2666        | 2.17  | 850  | 1.1459          | 0.6824   | 0.6384   | 0.6824   |
+| 0.3211        | 2.3   | 900  | 1.1165          | 0.6704   | 0.6362   | 0.6704   |
+| 0.2831        | 2.43  | 950  | 1.1722          | 0.6698   | 0.6360   | 0.6698   |
+| 0.2545        | 2.56  | 1000 | 1.2073          | 0.6714   | 0.6459   | 0.6714   |
+| 0.2069        | 2.69  | 1050 | 1.1839          | 0.6798   | 0.6438   | 0.6798   |
+| 0.2109        | 2.81  | 1100 | 1.1677          | 0.6778   | 0.6443   | 0.6778   |
+| 0.2383        | 2.94  | 1150 | 1.1807          | 0.6776   | 0.6462   | 0.6776   |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

Qwen/Qwen1.5_1.8B_patent/added_tokens.json

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

Qwen/Qwen1.5_1.8B_patent/all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6976,
+    "eval_f1_macro": 0.650699169639119,
+    "eval_f1_micro": 0.6976,
+    "eval_loss": 0.8989499807357788,
+    "eval_runtime": 12.2605,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 407.812,
+    "eval_steps_per_second": 6.443,
+    "test_accuracy": 0.6908,
+    "test_f1_macro": 0.6462079547915075,
+    "test_f1_micro": 0.6908,
+    "test_loss": 0.9244624972343445,
+    "test_runtime": 12.378,
+    "test_samples_per_second": 403.941,
+    "test_steps_per_second": 6.382,
+    "train_loss": 0.7074367981737532,
+    "train_runtime": 1784.4626,
+    "train_samples": 25000,
+    "train_samples_per_second": 42.029,
+    "train_steps_per_second": 0.657
+}

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/added_tokens.json

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

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "finetuning_task": "text-classification",
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3",
+    "4": "4",
+    "5": "5",
+    "6": "6",
+    "7": "7",
+    "8": "8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8
+  },
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 151643,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6c8681261953fd13d2e121bc6e969f092204eb68c4e3a3b67203b6f9c51c2f
+size 9150543244

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57843e2145662a8ea34f9ad8de2e88294b32bff31b3b9157bebf972a74d1d73
+size 9150548108

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/global_step750/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:882c86c8a4f8b9c452381dd6b6167c73898a4966953847228af30e5fe30ddfbf
+size 3050256760

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/latest

@@ -0,0 +1 @@
+global_step750

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31a9c68e89b60ce7d325470530730b525db9a9b5810cdc0d66c2079e99fbbd3
+size 3050270294

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5074c2f514d867cbda77efd9d2604382ce7761bd256224868852ee06af0ae72c
+size 14512

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432b20563ba37d2f1c6b732f2e8893c9aea8ee994f464dc6a81b032c80692e4a
+size 14512

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e08b4ee45e38267a036605946e276f9b0ce759d911b0ea716489ed31202d826
+size 1064

Qwen/Qwen1.5_1.8B_patent/checkpoint-750/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}