Upload folder using huggingface_hub

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: RC-inspire-LLM-ex1-b256
+  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. -->
+
+# RC-inspire-LLM-ex1-b256
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1645
+
+## 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: 0.0035355339059327372
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 2048
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 4.0101        | 0.1718 | 5000  | 3.6379          |
+| 3.5732        | 0.3435 | 10000 | 3.4689          |
+| 3.4485        | 0.5153 | 15000 | 3.3665          |
+| 3.349         | 0.6871 | 20000 | 3.2674          |
+| 3.247         | 0.8588 | 25000 | 3.1645          |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.19.1

checkpoint-10000/config.json

@@ -0,0 +1,43 @@
+{
+  "GLU_mode": "unshared",
+  "RC_backward": true,
+  "architectures": [
+    "HGRNBitForCausalLM"
+  ],
+  "attn_mode": "fused_reservoir",
+  "bos_token_id": 1,
+  "conv_size": 4,
+  "devided_num": 1,
+  "embedded_vec_num": 1,
+  "eos_token_id": 2,
+  "expand_ratio": 1,
+  "fg_mode": "unshared",
+  "fg_shared": "unshared",
+  "fuse_cross_entropy": true,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "inputLayer_backward": true,
+  "intermediate_size": null,
+  "max_position_embeddings": 2048,
+  "model_type": "hgrn_bit",
+  "multiple_readout": false,
+  "num_heads": 1,
+  "num_hidden_layers": 24,
+  "reservoir_backward": true,
+  "reservoir_kernel": true,
+  "rms_norm_eps": 1e-06,
+  "share_conv_kernel": true,
+  "sparse": 0.8,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "train_use_cache": false,
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "use_lower_bound": true,
+  "use_r": true,
+  "use_short_conv": false,
+  "using_residual": false,
+  "vocab_size": 32000
+}

checkpoint-10000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0.dev0"
+}

checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e78d5cc26f1a6b5188cd9378790390fbc8a5a35070435d6721693bd81574c7
+size 1597239512

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb791fb59b9e731db0e4e40e29be4773c86abdc4cffd84ceecc4868274ee437
+size 2791616442

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81251299c0659180c7c7c03eaf1df9fcca7393c48331b204dd67be5b9661a2c7
+size 14244

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efff0a5d6bf80b1cd3c3cc4caf0b1d1b0073967333ef1b084358dbb92db7bab6
+size 1256

checkpoint-10000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-10000/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.34353783854580433,
+  "eval_steps": 5000,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17176891927290217,
+      "grad_norm": 0.08905366063117981,
+      "learning_rate": 0.0033617902217971778,
+      "loss": 4.0101,
+      "step": 5000
+    },
+    {
+      "epoch": 0.17176891927290217,
+      "eval_loss": 3.637869119644165,
+      "eval_runtime": 50.7828,
+      "eval_samples_per_second": 1024.107,
+      "eval_steps_per_second": 4.017,
+      "step": 5000
+    },
+    {
+      "epoch": 0.34353783854580433,
+      "grad_norm": 0.16601510345935822,
+      "learning_rate": 0.0027140761611464783,
+      "loss": 3.5732,
+      "step": 10000
+    },
+    {
+      "epoch": 0.34353783854580433,
+      "eval_loss": 3.468949794769287,
+      "eval_runtime": 48.0534,
+      "eval_samples_per_second": 1082.275,
+      "eval_steps_per_second": 4.245,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 29108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.0056233222144e+18,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1850dc2c79c3f528a5f300fc0db6f77b6a5d6c40974f54a27b47a836321f15a
+size 5304

checkpoint-15000/config.json

@@ -0,0 +1,43 @@
+{
+  "GLU_mode": "unshared",
+  "RC_backward": true,
+  "architectures": [
+    "HGRNBitForCausalLM"
+  ],
+  "attn_mode": "fused_reservoir",
+  "bos_token_id": 1,
+  "conv_size": 4,
+  "devided_num": 1,
+  "embedded_vec_num": 1,
+  "eos_token_id": 2,
+  "expand_ratio": 1,
+  "fg_mode": "unshared",
+  "fg_shared": "unshared",
+  "fuse_cross_entropy": true,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "inputLayer_backward": true,
+  "intermediate_size": null,
+  "max_position_embeddings": 2048,
+  "model_type": "hgrn_bit",
+  "multiple_readout": false,
+  "num_heads": 1,
+  "num_hidden_layers": 24,
+  "reservoir_backward": true,
+  "reservoir_kernel": true,
+  "rms_norm_eps": 1e-06,
+  "share_conv_kernel": true,
+  "sparse": 0.8,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "train_use_cache": false,
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "use_lower_bound": true,
+  "use_r": true,
+  "use_short_conv": false,
+  "using_residual": false,
+  "vocab_size": 32000
+}

checkpoint-15000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0.dev0"
+}

checkpoint-15000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f549b96dbaccad2881b839013ed4a37f2c6087bc2b0332c76b018fcb2965e90
+size 1597239512

checkpoint-15000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beac9b590b819bf4c4cc029c12e8596bb958135a9a27960a6722928b89c381c9
+size 2791616442

checkpoint-15000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c320026f18de12243cb360a01cb850b8785b8a9028a5a6bde02330279a42450
+size 14244

checkpoint-15000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244a13713ea1139416b8913546b61526f04d73d2dd2a3256ddb5df31a1c0eb71
+size 1256

checkpoint-15000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-15000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-15000/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-15000/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5153067578187065,
+  "eval_steps": 5000,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17176891927290217,
+      "grad_norm": 0.08905366063117981,
+      "learning_rate": 0.0033617902217971778,
+      "loss": 4.0101,
+      "step": 5000
+    },
+    {
+      "epoch": 0.17176891927290217,
+      "eval_loss": 3.637869119644165,
+      "eval_runtime": 50.7828,
+      "eval_samples_per_second": 1024.107,
+      "eval_steps_per_second": 4.017,
+      "step": 5000
+    },
+    {
+      "epoch": 0.34353783854580433,
+      "grad_norm": 0.16601510345935822,
+      "learning_rate": 0.0027140761611464783,
+      "loss": 3.5732,
+      "step": 10000
+    },
+    {
+      "epoch": 0.34353783854580433,
+      "eval_loss": 3.468949794769287,
+      "eval_runtime": 48.0534,
+      "eval_samples_per_second": 1082.275,
+      "eval_steps_per_second": 4.245,
+      "step": 10000
+    },
+    {
+      "epoch": 0.5153067578187065,
+      "grad_norm": 0.14218954741954803,
+      "learning_rate": 0.0017784362562822313,
+      "loss": 3.4485,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5153067578187065,
+      "eval_loss": 3.3664753437042236,
+      "eval_runtime": 48.0196,
+      "eval_samples_per_second": 1083.037,
+      "eval_steps_per_second": 4.248,
+      "step": 15000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 29108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.5084349833216e+18,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1850dc2c79c3f528a5f300fc0db6f77b6a5d6c40974f54a27b47a836321f15a
+size 5304

checkpoint-20000/config.json

@@ -0,0 +1,43 @@
+{
+  "GLU_mode": "unshared",
+  "RC_backward": true,
+  "architectures": [
+    "HGRNBitForCausalLM"
+  ],
+  "attn_mode": "fused_reservoir",
+  "bos_token_id": 1,
+  "conv_size": 4,
+  "devided_num": 1,
+  "embedded_vec_num": 1,
+  "eos_token_id": 2,
+  "expand_ratio": 1,
+  "fg_mode": "unshared",
+  "fg_shared": "unshared",
+  "fuse_cross_entropy": true,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "inputLayer_backward": true,
+  "intermediate_size": null,
+  "max_position_embeddings": 2048,
+  "model_type": "hgrn_bit",
+  "multiple_readout": false,
+  "num_heads": 1,
+  "num_hidden_layers": 24,
+  "reservoir_backward": true,
+  "reservoir_kernel": true,
+  "rms_norm_eps": 1e-06,
+  "share_conv_kernel": true,
+  "sparse": 0.8,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "train_use_cache": false,
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "use_lower_bound": true,
+  "use_r": true,
+  "use_short_conv": false,
+  "using_residual": false,
+  "vocab_size": 32000
+}

checkpoint-20000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0.dev0"
+}

checkpoint-20000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39dcb8f95023732e1ab3434d74fcc2cdebbb123d54386c7079f99e3d9fc18a0d
+size 1597239512

checkpoint-20000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f54534cb83a6eda52c6d71703e35114e42941016f3c38e3601de91f583fda7e
+size 2791616442

checkpoint-20000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a122e66b2ab5c994fe151f34a5046128009bee762e6370fadfacc41f43f30b25
+size 14244

checkpoint-20000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a4e80fd709c60c7883a98478aa8f71ef7726c83490bf303fc13c96c24ffebe
+size 1256

checkpoint-20000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-20000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-20000/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-20000/trainer_state.json

@@ -0,0 +1,93 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6870756770916087,
+  "eval_steps": 5000,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17176891927290217,
+      "grad_norm": 0.08905366063117981,
+      "learning_rate": 0.0033617902217971778,
+      "loss": 4.0101,
+      "step": 5000
+    },
+    {
+      "epoch": 0.17176891927290217,
+      "eval_loss": 3.637869119644165,
+      "eval_runtime": 50.7828,
+      "eval_samples_per_second": 1024.107,
+      "eval_steps_per_second": 4.017,
+      "step": 5000
+    },
+    {
+      "epoch": 0.34353783854580433,
+      "grad_norm": 0.16601510345935822,
+      "learning_rate": 0.0027140761611464783,
+      "loss": 3.5732,
+      "step": 10000
+    },
+    {
+      "epoch": 0.34353783854580433,
+      "eval_loss": 3.468949794769287,
+      "eval_runtime": 48.0534,
+      "eval_samples_per_second": 1082.275,
+      "eval_steps_per_second": 4.245,
+      "step": 10000
+    },
+    {
+      "epoch": 0.5153067578187065,
+      "grad_norm": 0.14218954741954803,
+      "learning_rate": 0.0017784362562822313,
+      "loss": 3.4485,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5153067578187065,
+      "eval_loss": 3.3664753437042236,
+      "eval_runtime": 48.0196,
+      "eval_samples_per_second": 1083.037,
+      "eval_steps_per_second": 4.248,
+      "step": 15000
+    },
+    {
+      "epoch": 0.6870756770916087,
+      "grad_norm": 0.1738550066947937,
+      "learning_rate": 0.0008397182465799535,
+      "loss": 3.349,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6870756770916087,
+      "eval_loss": 3.267368793487549,
+      "eval_runtime": 48.4112,
+      "eval_samples_per_second": 1074.275,
+      "eval_steps_per_second": 4.214,
+      "step": 20000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 29108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.00112466444288e+19,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1850dc2c79c3f528a5f300fc0db6f77b6a5d6c40974f54a27b47a836321f15a
+size 5304

checkpoint-25000/config.json

@@ -0,0 +1,43 @@
+{
+  "GLU_mode": "unshared",
+  "RC_backward": true,
+  "architectures": [
+    "HGRNBitForCausalLM"
+  ],
+  "attn_mode": "fused_reservoir",
+  "bos_token_id": 1,
+  "conv_size": 4,
+  "devided_num": 1,
+  "embedded_vec_num": 1,
+  "eos_token_id": 2,
+  "expand_ratio": 1,
+  "fg_mode": "unshared",
+  "fg_shared": "unshared",
+  "fuse_cross_entropy": true,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "inputLayer_backward": true,
+  "intermediate_size": null,
+  "max_position_embeddings": 2048,
+  "model_type": "hgrn_bit",
+  "multiple_readout": false,
+  "num_heads": 1,
+  "num_hidden_layers": 24,
+  "reservoir_backward": true,
+  "reservoir_kernel": true,
+  "rms_norm_eps": 1e-06,
+  "share_conv_kernel": true,
+  "sparse": 0.8,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "train_use_cache": false,
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "use_lower_bound": true,
+  "use_r": true,
+  "use_short_conv": false,
+  "using_residual": false,
+  "vocab_size": 32000
+}

checkpoint-25000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.0.dev0"
+}

checkpoint-25000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3a6dcecd38d317124466ba11002be40c9390f752e04bc980e528403c990e4f5
+size 1597239512

checkpoint-25000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d459ec63e6d7ad77f48e99072add1927679ea3c300c380d9dfd665068e1ed1
+size 2791616442

checkpoint-25000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e903193b9436b564ddd981aa997531d38001c0b4ac1060961dcb1b49ca731c
+size 14244

checkpoint-25000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5f2b5a867e23793f577d96fdf47e336899195593ab9a9b8cf3cde59db844b1
+size 1256

checkpoint-25000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-25000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-25000/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-25000/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8588445963645108,
+  "eval_steps": 5000,
+  "global_step": 25000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17176891927290217,
+      "grad_norm": 0.08905366063117981,
+      "learning_rate": 0.0033617902217971778,
+      "loss": 4.0101,
+      "step": 5000
+    },
+    {
+      "epoch": 0.17176891927290217,
+      "eval_loss": 3.637869119644165,
+      "eval_runtime": 50.7828,
+      "eval_samples_per_second": 1024.107,
+      "eval_steps_per_second": 4.017,
+      "step": 5000
+    },
+    {
+      "epoch": 0.34353783854580433,
+      "grad_norm": 0.16601510345935822,
+      "learning_rate": 0.0027140761611464783,
+      "loss": 3.5732,
+      "step": 10000
+    },
+    {
+      "epoch": 0.34353783854580433,
+      "eval_loss": 3.468949794769287,
+      "eval_runtime": 48.0534,
+      "eval_samples_per_second": 1082.275,
+      "eval_steps_per_second": 4.245,
+      "step": 10000
+    },
+    {
+      "epoch": 0.5153067578187065,
+      "grad_norm": 0.14218954741954803,
+      "learning_rate": 0.0017784362562822313,
+      "loss": 3.4485,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5153067578187065,
+      "eval_loss": 3.3664753437042236,
+      "eval_runtime": 48.0196,
+      "eval_samples_per_second": 1083.037,
+      "eval_steps_per_second": 4.248,
+      "step": 15000
+    },
+    {
+      "epoch": 0.6870756770916087,
+      "grad_norm": 0.1738550066947937,
+      "learning_rate": 0.0008397182465799535,
+      "loss": 3.349,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6870756770916087,
+      "eval_loss": 3.267368793487549,
+      "eval_runtime": 48.4112,
+      "eval_samples_per_second": 1074.275,
+      "eval_steps_per_second": 4.214,
+      "step": 20000
+    },
+    {
+      "epoch": 0.8588445963645108,
+      "grad_norm": 0.1809106469154358,
+      "learning_rate": 0.00018334773665531966,
+      "loss": 3.247,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8588445963645108,
+      "eval_loss": 3.1645448207855225,
+      "eval_runtime": 47.7975,
+      "eval_samples_per_second": 1088.069,
+      "eval_steps_per_second": 4.268,
+      "step": 25000
+    }
+  ],
+  "logging_steps": 5000,
+  "max_steps": 29108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2514058305536e+19,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-25000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1850dc2c79c3f528a5f300fc0db6f77b6a5d6c40974f54a27b47a836321f15a
+size 5304

checkpoint-29108/config.json

@@ -0,0 +1,43 @@
+{
+  "GLU_mode": "unshared",
+  "RC_backward": true,
+  "architectures": [
+    "HGRNBitForCausalLM"
+  ],
+  "attn_mode": "fused_reservoir",
+  "bos_token_id": 1,
+  "conv_size": 4,
+  "devided_num": 1,
+  "embedded_vec_num": 1,
+  "eos_token_id": 2,
+  "expand_ratio": 1,
+  "fg_mode": "unshared",
+  "fg_shared": "unshared",
+  "fuse_cross_entropy": true,
+  "hidden_act": "swish",
+  "hidden_ratio": 4,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "inputLayer_backward": true,
+  "intermediate_size": null,
+  "max_position_embeddings": 2048,
+  "model_type": "hgrn_bit",
+  "multiple_readout": false,
+  "num_heads": 1,
+  "num_hidden_layers": 24,
+  "reservoir_backward": true,
+  "reservoir_kernel": true,
+  "rms_norm_eps": 1e-06,
+  "share_conv_kernel": true,
+  "sparse": 0.8,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "train_use_cache": false,
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "use_lower_bound": true,
+  "use_r": true,
+  "use_short_conv": false,
+  "using_residual": false,
+  "vocab_size": 32000
+}