Schoelkopf's group workspace
mamba-tp2-bs16-fusedinner_3yv14en0_7pcsp4pn
What makes this group special?
Tags
ip-10-0-251-210-0
Notes
Author
State
Crashed
Start time
March 13th, 2024 11:25:01 AM
Runtime
20m 30s
Tracked hours
-
Run path
eleutherai/mamba-neox-tp-memsavings/sdndl855
OS
Linux-5.15.0-1037-aws-x86_64-with-glibc2.31
Python version
3.9.18
Git repository
git clone https://github.com/EleutherAI/gpt-neox
Git state
git checkout -b "ip-10-0-251-210-0" 696454f00c71c702a10f5a0e2f28ebbe065e2704
Command
/weka/hailey/mistral-support-neox/gpt-neox/train.py --deepspeed_config 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 --megatron_config {"launcher": "slurm", "no_ssh_check": true, "train_batch_size": 1024, "train_micro_batch_size_per_gpu": 16, "gradient_accumulation_steps": 4, "optimizer": {"type": "Adam", "params": {"lr": 0.0006, "betas": [0.9, 0.95], "eps": 1e-08}}, "fp16": {"fp16": true, "enabled": true, "loss_scale": 0, "loss_scale_window": 1000, "initial_scale_power": 12, "hysteresis": 2, "min_loss_scale": 1}, "zero_optimization": {"stage": 1, "allgather_partitions": true, "allgather_bucket_size": 500000000, "overlap_comm": true, "reduce_scatter": true, "reduce_bucket_size": 500000000, "contiguous_gradients": true, "cpu_offload": false}, "wall_clock_breakdown": true, "precision": "fp16", "num_layers": 24, "hidden_size": 768, "num_attention_heads": 12, "seq_length": 2048, "max_position_embeddings": 2048, "norm": "rmsnorm", "rms_norm_epsilon": 1e-05, "pos_emb": "rotary", "no_weight_tying": true, "attention_config": ["mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba", "mamba"], "sparsity_config": {}, "activation": "silu", "rotary_pct": 0.25, "output_layer_init_method": "single_residual_scaled_normal", "gpt_j_residual": true, "mamba_selective_scan_fusion": true, "mamba_causal_conv_fusion": true, "mamba_inner_func_fusion": true, "lr_decay_style": "cosine", "lr_decay_iters": 143000, "min_lr": 6e-05, "optimizer_type": "Adam", "zero_stage": 1, "zero_reduce_scatter": true, "zero_contiguous_gradients": true, "zero_reduce_bucket_size": 500000000, "zero_allgather_bucket_size": 500000000, "lr": 0.0006, "tokenizer_type": "HFTokenizer", "train_data_paths": ["/weka/pile/pile_20B_tokenizer_text_document"], "test_data_paths": ["/weka/pile/pile_20B_tokenizer_text_document"], "valid_data_paths": ["/weka/pile/pile_20B_tokenizer_text_document"], "train_data_weights": [1.0], "valid_data_weights": [1.0], "test_data_weights": [1.0], "data_impl": "mmap", "config_files": {"mamba-160m.yml": "{\n  \"pipe_parallel_size\": 0,\n  \"model_parallel_size\": 2,\n\n  \"num_layers\": 24,\n  \"hidden_size\": 768,\n  \"num_attention_heads\": 12,\n  \"seq_length\": 2048,\n  \"max_position_embeddings\": 2048,\n  \"pos_emb\": \"rotary\",\n  \"rotary_pct\": 0.25,\n  \"no_weight_tying\": true,\n  \"gpt_j_residual\": true,\n  \"output_layer_parallelism\": \"column\",\n\n  \"attention_config\": [[[\"mamba\"], 24]],\n\n  # \"scaled_upper_triang_masked_softmax_fusion\": true,\n  # \"bias_gelu_fusion\": true,\n\n  \"mamba_selective_scan_fusion\": true,\n  \"mamba_causal_conv_fusion\": true,\n  \"mamba_inner_func_fusion\": true,\n  \"mamba_selective_fp32_params\": true,\n\n  \"activation\": \"silu\",\n  \"norm\": \"rmsnorm\",\n  \"rms_norm_epsilon\": 1.0e-5,\n\n  \"output_layer_init_method\": \"single_residual_scaled_normal\",\n\n\n  # \"init_method\": \"small_init\",\n  # \"output_layer_init_method\": \"wang_init\",\n\n  \"optimizer\": {\n    \"type\": \"Adam\",\n    \"params\": {\n      \"lr\": 0.0006,\n      \"betas\": [0.9, 0.95],\n      \"eps\": 1.0e-8\n    }\n  },\n  \"min_lr\": 0.00006,\n\n  \"zero_optimization\": {\n    \"stage\": 1,\n    \"allgather_partitions\": true,\n    \"allgather_bucket_size\": 500000000,\n    \"overlap_comm\": true,\n    \"reduce_scatter\": true,\n    \"reduce_bucket_size\": 500000000,\n    \"contiguous_gradients\": true,\n    \"cpu_offload\": false\n  },\n\n  \"train_micro_batch_size_per_gpu\": 16,\n  \"gradient_accumulation_steps\": 4,\n  \"data_impl\": \"mmap\",\n  \"num_workers\": 1,\n\n  \"checkpoint_activations\": true,\n  \"checkpoint_num_layers\": 1,\n  \"partition_activations\": true,\n  \"synchronize_each_layer\": true,\n\n  \"gradient_clipping\": 1.0,\n  \"weight_decay\": 0.1,\n  \"hidden_dropout\": 0,\n  \"attention_dropout\": 0,\n\n  \"fp16\": {\n    \"fp16\": true,\n    \"enabled\": true,\n    \"loss_scale\": 0,\n    \"loss_scale_window\": 1000,\n    \"initial_scale_power\": 12,\n    \"hysteresis\": 2,\n    \"min_loss_scale\": 1\n  },\n\n  \"train_iters\": 143001,\n  \"lr_decay_iters\": 143000,\n  \"distributed_backend\": \"nccl\",\n  \"lr_decay_style\": \"cosine\",\n  \"warmup\": 0.01,\n  \"checkpoint_factor\": 250,\n  # \"extra_save_iters\": [0,1,2,4,8,16,32,64,128,256,512],\n  \"eval_interval\": 143000,\n  \"eval_iters\": 10,\n\n  \"log_interval\": 10,\n  \"steps_per_print\": 10,\n  \"wall_clock_breakdown\": true,\n\n  \"tokenizer_type\": \"HFTokenizer\",\n  \"vocab_file\": \"/weka/pile/20B_tokenizer.json\",\n\n  # \"save\": \"/weka/hailey/mamba-ckpts/mamba-160m-pythia-test-conv-bias\",\n  # \"load\": \"/weka/hailey/mamba-ckpts/mamba-160m-pythia-test-conv-bias\",\n\n  # \"s3_path\": \"s3://s-eai-neox-west/hailey/mamba/test-ckpts/mamba-160m-pythia-test-conv-bias\",\n\n  # \"keep_last_n_checkpoints\": 2,\n\n  \"train_data_paths\": [\"/weka/pile/pile_20B_tokenizer_text_document\"],\n  \"valid_data_paths\": [\"/weka/pile/pile_20B_tokenizer_text_document\"],\n  \"test_data_paths\": [\"/weka/pile/pile_20B_tokenizer_text_document\"],\n\n  \"launcher\": \"slurm\", \n  \"deepspeed_slurm\": true,\n  #  \"account\": \"eleuther\",\n  \"no_ssh_check\": true,\n\n  \"use_wandb\": true,\n  \"wandb_group\": \"mamba-tp2-bs16-fusedinner\",\n  \"wandb_team\": \"eleutherai\",\n  \"wandb_project\": \"mamba-neox-tp-memsavings\",\n}\n"}, "checkpoint_factor": 250, "batch_size": 16, "train_iters": 143001, "eval_iters": 10, "eval_interval": 143000, "vocab_file": "/weka/pile/20B_tokenizer.json", "num_workers": 1, "checkpoint_activations": true, "synchronize_each_layer": true, "partition_activations": true, "dynamic_loss_scale": true, "model_parallel_size": 2, "world_size": 32, "use_wandb": true, "wandb_group": "mamba-tp2-bs16-fusedinner_3yv14en0_7pcsp4pn", "wandb_team": "eleutherai", "wandb_project": "mamba-neox-tp-memsavings", "log_interval": 10, "text_gen_type": "unconditional", "local_rank": 0, "rank": 0, "deepspeed_slurm": true, "user_script": "/weka/hailey/mistral-support-neox/gpt-neox/train.py", "save_iters": [250, 500, 750, 1000, 1250, 1500, 1750, 2000, 2250, 2500, 2750, 3000, 3250, 3500, 3750, 4000, 4250, 4500, 4750, 5000, 5250, 5500, 5750, 6000, 6250, 6500, 6750, 7000, 7250, 7500, 7750, 8000, 8250, 8500, 8750, 9000, 9250, 9500, 9750, 10000, 10250, 10500, 10750, 11000, 11250, 11500, 11750, 12000, 12250, 12500, 12750, 13000, 13250, 13500, 13750, 14000, 14250, 14500, 14750, 15000, 15250, 15500, 15750, 16000, 16250, 16500, 16750, 17000, 17250, 17500, 17750, 18000, 18250, 18500, 18750, 19000, 19250, 19500, 19750, 20000, 20250, 20500, 20750, 21000, 21250, 21500, 21750, 22000, 22250, 22500, 22750, 23000, 23250, 23500, 23750, 24000, 24250, 24500, 24750, 25000, 25250, 25500, 25750, 26000, 26250, 26500, 26750, 27000, 27250, 27500, 27750, 28000, 28250, 28500, 28750, 29000, 29250, 29500, 29750, 30000, 30250, 30500, 30750, 31000, 31250, 31500, 31750, 32000, 32250, 32500, 32750, 33000, 33250, 33500, 33750, 34000, 34250, 34500, 34750, 35000, 35250, 35500, 35750, 36000, 36250, 36500, 36750, 37000, 37250, 37500, 37750, 38000, 38250, 38500, 38750, 39000, 39250, 39500, 39750, 40000, 40250, 40500, 40750, 41000, 41250, 41500, 41750, 42000, 42250, 42500, 42750, 43000, 43250, 43500, 43750, 44000, 44250, 44500, 44750, 45000, 45250, 45500, 45750, 46000, 46250, 46500, 46750, 47000, 47250, 47500, 47750, 48000, 48250, 48500, 48750, 49000, 49250, 49500, 49750, 50000, 50250, 50500, 50750, 51000, 51250, 51500, 51750, 52000, 52250, 52500, 52750, 53000, 53250, 53500, 53750, 54000, 54250, 54500, 54750, 55000, 55250, 55500, 55750, 56000, 56250, 56500, 56750, 57000, 57250, 57500, 57750, 58000, 58250, 58500, 58750, 59000, 59250, 59500, 59750, 60000, 60250, 60500, 60750, 61000, 61250, 61500, 61750, 62000, 62250, 62500, 62750, 63000, 63250, 63500, 63750, 64000, 64250, 64500, 64750, 65000, 65250, 65500, 65750, 66000, 66250, 66500, 66750, 67000, 67250, 67500, 67750, 68000, 68250, 68500, 68750, 69000, 69250, 69500, 69750, 70000, 70250, 70500, 70750, 71000, 71250, 71500, 71750, 72000, 72250, 72500, 72750, 73000, 73250, 73500, 73750, 74000, 74250, 74500, 74750, 75000, 75250, 75500, 75750, 76000, 76250, 76500, 76750, 77000, 77250, 77500, 77750, 78000, 78250, 78500, 78750, 79000, 79250, 79500, 79750, 80000, 80250, 80500, 80750, 81000, 81250, 81500, 81750, 82000, 82250, 82500, 82750, 83000, 83250, 83500, 83750, 84000, 84250, 84500, 84750, 85000, 85250, 85500, 85750, 86000, 86250, 86500, 86750, 87000, 87250, 87500, 87750, 88000, 88250, 88500, 88750, 89000, 89250, 89500, 89750, 90000, 90250, 90500, 90750, 91000, 91250, 91500, 91750, 92000, 92250, 92500, 92750, 93000, 93250, 93500, 93750, 94000, 94250, 94500, 94750, 95000, 95250, 95500, 95750, 96000, 96250, 96500, 96750, 97000, 97250, 97500, 97750, 98000, 98250, 98500, 98750, 99000, 99250, 99500, 99750, 100000, 100250, 100500, 100750, 101000, 101250, 101500, 101750, 102000, 102250, 102500, 102750, 103000, 103250, 103500, 103750, 104000, 104250, 104500, 104750, 105000, 105250, 105500, 105750, 106000, 106250, 106500, 106750, 107000, 107250, 107500, 107750, 108000, 108250, 108500, 108750, 109000, 109250, 109500, 109750, 110000, 110250, 110500, 110750, 111000, 111250, 111500, 111750, 112000, 112250, 112500, 112750, 113000, 113250, 113500, 113750, 114000, 114250, 114500, 114750, 115000, 115250, 115500, 115750, 116000, 116250, 116500, 116750, 117000, 117250, 117500, 117750, 118000, 118250, 118500, 118750, 119000, 119250, 119500, 119750, 120000, 120250, 120500, 120750, 121000, 121250, 121500, 121750, 122000, 122250, 122500, 122750, 123000, 123250, 123500, 123750, 124000, 124250, 124500, 124750, 125000, 125250, 125500, 125750, 126000, 126250, 126500, 126750, 127000, 127250, 127500, 127750, 128000, 128250, 128500, 128750, 129000, 129250, 129500, 129750, 130000, 130250, 130500, 130750, 131000, 131250, 131500, 131750, 132000, 132250, 132500, 132750, 133000, 133250, 133500, 133750, 134000, 134250, 134500, 134750, 135000, 135250, 135500, 135750, 136000, 136250, 136500, 136750, 137000, 137250, 137500, 137750, 138000, 138250, 138500, 138750, 139000, 139250, 139500, 139750, 140000, 140250, 140500, 140750, 141000, 141250, 141500, 141750, 142000, 142250, 142500, 142750, 143000], "global_num_gpus": 32}
System Hardware
| CPU count | 48 |
| Logical CPU count | 96 |
| GPU count | 8 |
| GPU type | NVIDIA A100-SXM4-40GB |
W&B CLI Version
0.16.3
Config
Config parameters are your model's inputs. Learn more
- {} 258 keys▶
- null
- "silu"
- null
- false
- 1,000
- null
- false
- [] 24 items▶
- 0
- false
- null
- null
- null
- 16
- null
- false
- false
- false
- null
- true
- 250
- false
- 1
- "linear"
- false
- 1
- null
- null
- null
- null
- {} 1 key▶
- "{ "pipe_parallel_size": 0, "model_parallel_size": 2, "num_layers": 24, "hidden_size": 768, "num_attention_heads": 12, "seq_length": 2048, "max_position_embeddings": 2048, "pos_emb": "rotary", "rotary_pct": 0.25, "no_weight_tying": true, "gpt_j_residual": true, "output_layer_parallelism": "column", "attention_config": [[["mamba"], 24]], # "scaled_upper_triang_masked_softmax_fusion": true, # "bias_gelu_fusion": true, "mamba_selective_scan_fusion": true, "mamba_causal_conv_fusion": true, "mamba_inner_func_fusion": true, "mamba_selective_fp32_params": true, "activation": "silu", "norm": "rmsnorm", "rms_norm_epsilon": 1.0e-5, "output_layer_init_method": "single_residual_scaled_normal", # "init_method": "small_init", # "output_layer_init_method": "wang_init", "optimizer": { "type": "Adam", "params": { "lr": 0.0006, "betas": [0.9, 0.95], "eps": 1.0e-8 } }, "min_lr": 0.00006, "zero_optimization": { "stage": 1, "allgather_partitions": true, "allgather_bucket_size": 500000000, "overlap_comm": true, "reduce_scatter": true, "reduce_bucket_size": 500000000, "contiguous_gradients": true, "cpu_offload": false }, "train_micro_batch_size_per_gpu": 16, "gradient_accumulation_steps": 4, "data_impl": "mmap", "num_workers": 1, "checkpoint_activations": true, "checkpoint_num_layers": 1, "partition_activations": true, "synchronize_each_layer": true, "gradient_clipping": 1.0, "weight_decay": 0.1, "hidden_dropout": 0, "attention_dropout": 0, "fp16": { "fp16": true, "enabled": true, "loss_scale": 0, "loss_scale_window": 1000, "initial_scale_power": 12, "hysteresis": 2, "min_loss_scale": 1 }, "train_iters": 143001, "lr_decay_iters": 143000, "distributed_backend": "nccl", "lr_decay_style": "cosine", "warmup": 0.01, "checkpoint_factor": 250, # "extra_save_iters": [0,1,2,4,8,16,32,64,128,256,512], "eval_interval": 143000, "eval_iters": 10, "log_interval": 10, "steps_per_print": 10, "wall_clock_breakdown": true, "tokenizer_type": "HFTokenizer", "vocab_file": "/weka/pile/20B_tokenizer.json", # "save": "/weka/hailey/mamba-ckpts/mamba-160m-pythia-test-conv-bias", # "load": "/weka/hailey/mamba-ckpts/mamba-160m-pythia-test-conv-bias", # "s3_path": "s3://s-eai-neox-west/hailey/mamba/test-ckpts/mamba-160m-pythia-test-conv-bias", # "keep_last_n_checkpoints": 2, "train_data_paths": ["/weka/pile/pile_20B_tokenizer_text_document"], "valid_data_paths": ["/weka/pile/pile_20B_tokenizer_text_document"], "test_data_paths": ["/weka/pile/pile_20B_tokenizer_text_document"], "launcher": "slurm", "deepspeed_slurm": true, # "account": "eleuther", "no_ssh_check": true, "use_wandb": true, "wandb_group": "mamba-tp2-bs16-fusedinner", "wandb_team": "eleutherai", "wandb_project": "mamba-neox-tp-memsavings", } "
- false
- false
- true
- null
- null
- 0
- null
- "mmap"
- null
- null
- false
- null
- true
- true
- null
- {} 8 keys▶
- 500,000,000
- true
- 1
46 ... 95▶▶96 ... 145▶▶146 ... 195▶▶196 ... 245▶▶246 ... 253▶▶
Summary
Summary metrics are your model's outputs. Learn more
No summary metrics saved for this run.
Check the summary metrics documentation for more information.