Add files using upload-large-folder tool

hyperparameters.json

@@ -0,0 +1,56 @@
+{
+    "train_config": "config/is_selfssm.swe_2048.json",
+    "model_name": "Selfssm",
+    "devices": 8,
+    "train_name": "is_selfssm.swe_2048",
+    "name": "is_selfssm.swe_2048_Selfssm",
+    "model_type": "selfssm",
+    "nodes": 1,
+    "block_size": 4096,
+    "max_tokens": 20000000000,
+    "global_batch_size": 512,
+    "micro_batch_size": 2,
+    "batch_size": 64,
+    "gradient_accumulation_steps": 32,
+    "learning_rate": 0.0004,
+    "total_evals": 400,
+    "warmup_tokens": 200000000,
+    "eval_iters": 200,
+    "resume_ckpt": "token-3775135744.iter-014400-ckpt.pth",
+    "log_step_interval": 10,
+    "save_step_interval": 300,
+    "eval_step_interval": 300,
+    "num_extrapol": 4,
+    "weight_decay": 0.1,
+    "beta1": 0.9,
+    "beta2": 0.95,
+    "grad_clip": 1.0,
+    "decay_lr": true,
+    "min_lr": 4e-05,
+    "attn_type": "flash_attention_2",
+    "attn_window_size": 2048,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "load_linear_data": "next",
+    "load_linear_overlap": 0,
+    "load_linear_also_copy_rate": 0,
+    "data_do_shuffle": false,
+    "load_input_data": "",
+    "log_iter_interval": 320,
+    "tok": "llama2_tok",
+    "transformer_hidden_size": 1024,
+    "transformer_num_hidden_layers": 12,
+    "transformer_intermediate_size": 4096,
+    "linear_hidden_states": 2048,
+    "linear_cal_loss": false,
+    "linear_num_hidden_layers": 12,
+    "linear_hidden_name": "output_embedding",
+    "linear_multiply_self_attn_B": false,
+    "linear_input_w_selfattn": false,
+    "integrate_self_attn_weight": "",
+    "integrate_self_attn_weight_rate": 1,
+    "tie_word_embedding_layer": true,
+    "linear_up_project": false,
+    "linear_up_project_size": 0,
+    "interact_mode": "cross_attn"
+}

model_config.json

@@ -0,0 +1,113 @@
+{
+    "vocab_size": 32000,
+    "hidden_size": 1024,
+    "state_size": 16,
+    "num_hidden_layers": 12,
+    "layer_norm_epsilon": 1e-05,
+    "conv_kernel": 4,
+    "expand": 2,
+    "intermediate_size": 4096,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "pad_token_id": null,
+    "use_bias": false,
+    "use_conv_bias": true,
+    "hidden_act": "silu",
+    "initializer_range": 0.1,
+    "time_step_rank": 64,
+    "time_step_scale": 1.0,
+    "time_step_min": 0.001,
+    "time_step_max": 0.1,
+    "time_step_init_scheme": "random",
+    "time_step_floor": 0.0001,
+    "rescale_prenorm_residual": false,
+    "residual_in_fp32": true,
+    "use_cache": true,
+    "use_mambapy": false,
+    "block_size": 4096,
+    "name": "Selfssm",
+    "max_position_embeddings": 4096,
+    "num_attention_heads": 16,
+    "linear_hidden_name": "output_embedding",
+    "num_key_value_heads": 16,
+    "decoder_initializer_range": 0.02,
+    "decoder_use_cache": true,
+    "rope_theta": 10000.0,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "clip_qkv": null,
+    "window_size": 2048,
+    "output_attentions": false,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "torchscript": false,
+    "torch_dtype": null,
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": true,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": true,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": null,
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "",
+    "_attn_implementation_autoset": false,
+    "transformers_version": "4.46.2",
+    "local_rank": 0,
+    "attn_window_size": 2048,
+    "itermediate_size": 4096,
+    "interact_mode": "cross_attn",
+    "n_layer": 12,
+    "n_embd": 1024,
+    "linear_hidden_states": 2048,
+    "linear_multiply_self_attn_B": false,
+    "linear_input_w_selfattn": false,
+    "linear_cal_loss": false,
+    "integrate_self_attn_weight": "",
+    "integrate_self_attn_weight_rate": 1,
+    "model_type": "selfssm"
+}

token-9122676736.iter-139200-ckpt.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6df836e818a99ccb1e0ec7cca1f7a6070339abea460583c0d14d64e20e55dc
+size 5464607563