Model save

README.md

@@ -1,15 +1,12 @@
 ---
 base_model: sanchit-gandhi/Mistral-7B-v0.1-6-layer
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 datasets:
-- stingning/ultrachat
+- generator
 model-index:
 - name: sanchit-gandhi/Mistral-7B-v0.1-6-layer
   results: []
@@ -20,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sanchit-gandhi/Mistral-7B-v0.1-6-layer
 
-This model is a fine-tuned version of [sanchit-gandhi/Mistral-7B-v0.1-6-layer](https://huggingface.co/sanchit-gandhi/Mistral-7B-v0.1-6-layer) on the stingning/ultrachat dataset.
+This model is a fine-tuned version of [sanchit-gandhi/Mistral-7B-v0.1-6-layer](https://huggingface.co/sanchit-gandhi/Mistral-7B-v0.1-6-layer) on the generator dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0042
 

all_results.json

@@ -1,14 +1,14 @@
 {
-    "epoch": 4.944375772558715,
+    "epoch": 4.944622991347343,
     "eval_loss": 1.0042184591293335,
-    "eval_runtime": 1.489,
+    "eval_runtime": 1.4747,
     "eval_samples": 1000,
-    "eval_samples_per_second": 429.142,
-    "eval_steps_per_second": 2.015,
-    "total_flos": 9.058112140235663e+19,
-    "train_loss": 1.0958750234603882,
-    "train_runtime": 36068.0493,
+    "eval_samples_per_second": 433.323,
+    "eval_steps_per_second": 2.034,
+    "total_flos": 9.058565045825516e+19,
+    "train_loss": 4.2969823139893115e-05,
+    "train_runtime": 9.0702,
     "train_samples": 1467352,
-    "train_samples_per_second": 141.954,
-    "train_steps_per_second": 0.555
+    "train_samples_per_second": 564484.818,
+    "train_steps_per_second": 2205.019
 }

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.944375772558715,
+    "epoch": 4.944622991347343,
     "eval_loss": 1.0042184591293335,
-    "eval_runtime": 1.489,
+    "eval_runtime": 1.4747,
     "eval_samples": 1000,
-    "eval_samples_per_second": 429.142,
-    "eval_steps_per_second": 2.015
+    "eval_samples_per_second": 433.323,
+    "eval_steps_per_second": 2.034
 }

runs/Apr25_23-48-22_ip-26-0-167-177/events.out.tfevents.1714088955.ip-26-0-167-177.211869.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5bb52086161b69b7bee8d1573821c6c75cfa78e0ebccc0e11f07cbeaa87a85
+size 5066

runs/Apr25_23-48-22_ip-26-0-167-177/events.out.tfevents.1714088965.ip-26-0-167-177.211869.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8c8ad8159f97d9fe023daef4c143bcbd4d78735d51d18574ae401864f72c77
+size 364

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 4.944375772558715,
-    "total_flos": 9.058112140235663e+19,
-    "train_loss": 1.0958750234603882,
-    "train_runtime": 36068.0493,
+    "epoch": 4.944622991347343,
+    "total_flos": 9.058565045825516e+19,
+    "train_loss": 4.2969823139893115e-05,
+    "train_runtime": 9.0702,
     "train_samples": 1467352,
-    "train_samples_per_second": 141.954,
-    "train_steps_per_second": 0.555
+    "train_samples_per_second": 564484.818,
+    "train_steps_per_second": 2205.019
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.944375772558715,
+  "epoch": 4.944622991347343,
   "eval_steps": 5000,
-  "global_step": 20000,
+  "global_step": 20001,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5648,13 +5648,13 @@
       "step": 20000
     },
     {
-      "epoch": 4.944375772558715,
-      "step": 20000,
-      "total_flos": 9.058112140235663e+19,
-      "train_loss": 1.0958750234603882,
-      "train_runtime": 36068.0493,
-      "train_samples_per_second": 141.954,
-      "train_steps_per_second": 0.555
+      "epoch": 4.944622991347343,
+      "step": 20001,
+      "total_flos": 9.058565045825516e+19,
+      "train_loss": 4.2969823139893115e-05,
+      "train_runtime": 9.0702,
+      "train_samples_per_second": 564484.818,
+      "train_steps_per_second": 2205.019
     }
   ],
   "logging_steps": 25,
@@ -5662,7 +5662,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 5000,
-  "total_flos": 9.058112140235663e+19,
+  "total_flos": 9.058565045825516e+19,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781c0a2347f9f34d96f08a02d9262669403d18a6358c936df9c6d50431430243
+oid sha256:7260f27f85882e7b3af12df5cb1c852d833c8dcc1c57bc5b853702adf12a2c00
 size 4984

wandb/debug.log

@@ -1,28 +1,28 @@
-2024-04-25 13:45:18,225 INFO    MainThread:156194 [wandb_setup.py:_flush():76] Current SDK version is 0.16.6
-2024-04-25 13:45:18,225 INFO    MainThread:156194 [wandb_setup.py:_flush():76] Configure stats pid to 156194
-2024-04-25 13:45:18,225 INFO    MainThread:156194 [wandb_setup.py:_flush():76] Loading settings from /admin/home/sanchit/.config/wandb/settings
-2024-04-25 13:45:18,225 INFO    MainThread:156194 [wandb_setup.py:_flush():76] Loading settings from /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/settings
-2024-04-25 13:45:18,225 INFO    MainThread:156194 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
-2024-04-25 13:45:18,225 INFO    MainThread:156194 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
-2024-04-25 13:45:18,225 INFO    MainThread:156194 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_sft.py', 'program_abspath': '/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/run_sft.py', 'program': '/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/./run_sft.py'}
-2024-04-25 13:45:18,226 INFO    MainThread:156194 [wandb_setup.py:_flush():76] Applying login settings: {}
-2024-04-25 13:45:18,226 INFO    MainThread:156194 [wandb_init.py:_log_setup():521] Logging user logs to /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/logs/debug.log
-2024-04-25 13:45:18,226 INFO    MainThread:156194 [wandb_init.py:_log_setup():522] Logging internal logs to /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/logs/debug-internal.log
-2024-04-25 13:45:18,226 INFO    MainThread:156194 [wandb_init.py:init():561] calling init triggers
-2024-04-25 13:45:18,226 INFO    MainThread:156194 [wandb_init.py:init():568] wandb.init called with sweep_config: {}
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Current SDK version is 0.16.6
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Configure stats pid to 211869
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Loading settings from /admin/home/sanchit/.config/wandb/settings
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Loading settings from /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/settings
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_sft.py', 'program_abspath': '/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/run_sft.py', 'program': '/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/./run_sft.py'}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:_log_setup():521] Logging user logs to /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/logs/debug.log
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:_log_setup():522] Logging internal logs to /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/logs/debug-internal.log
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:init():561] calling init triggers
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:init():568] wandb.init called with sweep_config: {}
 config: {}
-2024-04-25 13:45:18,226 INFO    MainThread:156194 [wandb_init.py:init():611] starting backend
-2024-04-25 13:45:18,226 INFO    MainThread:156194 [wandb_init.py:init():615] setting up manager
-2024-04-25 13:45:18,231 INFO    MainThread:156194 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2024-04-25 13:45:18,239 INFO    MainThread:156194 [wandb_init.py:init():623] backend started and connected
-2024-04-25 13:45:18,241 INFO    MainThread:156194 [wandb_init.py:init():715] updated telemetry
-2024-04-25 13:45:18,267 INFO    MainThread:156194 [wandb_init.py:init():748] communicating run to backend with 90.0 second timeout
-2024-04-25 13:45:18,506 INFO    MainThread:156194 [wandb_run.py:_on_init():2357] communicating current version
-2024-04-25 13:45:18,558 INFO    MainThread:156194 [wandb_run.py:_on_init():2366] got version response 
-2024-04-25 13:45:18,558 INFO    MainThread:156194 [wandb_init.py:init():799] starting run threads in backend
-2024-04-25 13:45:22,708 INFO    MainThread:156194 [wandb_run.py:_console_start():2335] atexit reg
-2024-04-25 13:45:22,708 INFO    MainThread:156194 [wandb_run.py:_redirect():2190] redirect: wrap_raw
-2024-04-25 13:45:22,708 INFO    MainThread:156194 [wandb_run.py:_redirect():2255] Wrapping output streams.
-2024-04-25 13:45:22,708 INFO    MainThread:156194 [wandb_run.py:_redirect():2280] Redirects installed.
-2024-04-25 13:45:22,709 INFO    MainThread:156194 [wandb_init.py:init():842] run started, returning control to user process
-2024-04-25 13:45:22,711 INFO    MainThread:156194 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 6, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'sanchit-gandhi/Mistral-7B-v0.1-6-layer', 'transformers_version': '4.40.1', 'model_type': 'mistral', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 20000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Apr25_13-44-28_ip-26-0-167-177', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 5000, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 5000, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 7200, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'max_seq_length': 2048}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:init():611] starting backend
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:init():615] setting up manager
+2024-04-25 23:49:16,508 INFO    MainThread:211869 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-04-25 23:49:16,515 INFO    MainThread:211869 [wandb_init.py:init():623] backend started and connected
+2024-04-25 23:49:16,518 INFO    MainThread:211869 [wandb_init.py:init():715] updated telemetry
+2024-04-25 23:49:16,536 INFO    MainThread:211869 [wandb_init.py:init():748] communicating run to backend with 90.0 second timeout
+2024-04-25 23:49:16,777 INFO    MainThread:211869 [wandb_run.py:_on_init():2357] communicating current version
+2024-04-25 23:49:16,826 INFO    MainThread:211869 [wandb_run.py:_on_init():2366] got version response 
+2024-04-25 23:49:16,826 INFO    MainThread:211869 [wandb_init.py:init():799] starting run threads in backend
+2024-04-25 23:49:21,061 INFO    MainThread:211869 [wandb_run.py:_console_start():2335] atexit reg
+2024-04-25 23:49:21,061 INFO    MainThread:211869 [wandb_run.py:_redirect():2190] redirect: wrap_raw
+2024-04-25 23:49:21,061 INFO    MainThread:211869 [wandb_run.py:_redirect():2255] Wrapping output streams.
+2024-04-25 23:49:21,062 INFO    MainThread:211869 [wandb_run.py:_redirect():2280] Redirects installed.
+2024-04-25 23:49:21,063 INFO    MainThread:211869 [wandb_init.py:init():842] run started, returning control to user process
+2024-04-25 23:49:21,064 INFO    MainThread:211869 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 6, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'sanchit-gandhi/Mistral-7B-v0.1-6-layer', 'transformers_version': '4.40.1', 'model_type': 'mistral', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 20000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Apr25_23-48-22_ip-26-0-167-177', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 5000, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 5000, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 7200, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'max_seq_length': 2048}

wandb/run-20240425_134518-etajcxpg/files/output.log

@@ -18874,3 +18874,5 @@ Upload 2 LFS files: 100%|██████████| 2/2 [00:00<00:00,  5.07
 [INFO|tokenization_utils_base.py:2488] 2024-04-25 23:47:40,804 >> tokenizer config file saved in ./tokenizer_config.json
 [INFO|tokenization_utils_base.py:2497] 2024-04-25 23:47:40,806 >> Special tokens file saved in ./special_tokens_map.json
 [INFO|modelcard.py:450] 2024-04-25 23:47:40,849 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}, 'dataset': {'name': 'stingning/ultrachat', 'type': 'stingning/ultrachat', 'config': 'default', 'split': 'train', 'args': 'default'}}
+2024-04-25 23:47:45 - INFO - __main__ - *** Training complete ***

wandb/run-20240425_134518-etajcxpg/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.8191, "train/grad_norm": 0.6796875, "train/learning_rate": 0.0, "train/epoch": 4.944375772558715, "train/global_step": 20000, "_timestamp": 1714088841.5880787, "_runtime": 36123.348269701004, "_step": 806, "eval/loss": 1.0042184591293335, "eval/runtime": 1.489, "eval/samples_per_second": 429.142, "eval/steps_per_second": 2.015, "train_runtime": 36068.0493, "train_samples_per_second": 141.954, "train_steps_per_second": 0.555, "total_flos": 9.058112140235663e+19, "train_loss": 1.0958750234603882}
+{"train/loss": 0.8191, "train/grad_norm": 0.6796875, "train/learning_rate": 0.0, "train/epoch": 4.944375772558715, "train/global_step": 20000, "_timestamp": 1714088841.5880787, "_runtime": 36123.348269701004, "_step": 806, "eval/loss": 1.0042184591293335, "eval/runtime": 1.489, "eval/samples_per_second": 429.142, "eval/steps_per_second": 2.015, "train_runtime": 36068.0493, "train_samples_per_second": 141.954, "train_steps_per_second": 0.555, "total_flos": 9.058112140235663e+19, "train_loss": 1.0958750234603882, "_wandb": {"runtime": 36146}}

wandb/run-20240425_134518-etajcxpg/logs/debug-internal.log

@@ -37486,3 +37486,146 @@
 2024-04-25 23:47:38,974 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: status_report
 2024-04-25 23:47:41,480 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: internal_messages
 2024-04-25 23:47:42,275 INFO    Thread-12 :156911 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/output.log
+2024-04-25 23:47:44,851 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: status_report
+2024-04-25 23:47:45,210 DEBUG   SenderThread:156911 [sender.py:send():379] send: exit
+2024-04-25 23:47:45,210 INFO    SenderThread:156911 [sender.py:send_exit():586] handling exit code: 0
+2024-04-25 23:47:45,211 INFO    SenderThread:156911 [sender.py:send_exit():588] handling runtime: 36146
+2024-04-25 23:47:45,213 INFO    SenderThread:156911 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:47:45,213 INFO    SenderThread:156911 [sender.py:send_exit():594] send defer
+2024-04-25 23:47:45,213 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:45,213 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 0
+2024-04-25 23:47:45,213 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:45,213 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 0
+2024-04-25 23:47:45,213 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 1
+2024-04-25 23:47:45,213 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:45,213 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 1
+2024-04-25 23:47:45,213 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:45,213 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 1
+2024-04-25 23:47:45,213 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 2
+2024-04-25 23:47:45,214 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:45,214 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 2
+2024-04-25 23:47:45,214 INFO    HandlerThread:156911 [system_monitor.py:finish():203] Stopping system monitor
+2024-04-25 23:47:45,214 DEBUG   SystemMonitor:156911 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-04-25 23:47:45,215 INFO    HandlerThread:156911 [interfaces.py:finish():202] Joined cpu monitor
+2024-04-25 23:47:45,215 DEBUG   SystemMonitor:156911 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-04-25 23:47:45,215 INFO    HandlerThread:156911 [interfaces.py:finish():202] Joined disk monitor
+2024-04-25 23:47:45,280 INFO    Thread-12 :156911 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/wandb-summary.json
+2024-04-25 23:47:45,963 INFO    HandlerThread:156911 [interfaces.py:finish():202] Joined gpu monitor
+2024-04-25 23:47:45,963 INFO    HandlerThread:156911 [interfaces.py:finish():202] Joined memory monitor
+2024-04-25 23:47:45,963 INFO    HandlerThread:156911 [interfaces.py:finish():202] Joined network monitor
+2024-04-25 23:47:45,964 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:45,964 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 2
+2024-04-25 23:47:45,964 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 3
+2024-04-25 23:47:45,965 DEBUG   SenderThread:156911 [sender.py:send():379] send: stats
+2024-04-25 23:47:45,965 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:45,965 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 3
+2024-04-25 23:47:45,965 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:45,965 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 3
+2024-04-25 23:47:45,965 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 4
+2024-04-25 23:47:45,965 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:45,966 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 4
+2024-04-25 23:47:45,966 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:45,966 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 4
+2024-04-25 23:47:45,966 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 5
+2024-04-25 23:47:45,966 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:45,966 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 5
+2024-04-25 23:47:45,966 DEBUG   SenderThread:156911 [sender.py:send():379] send: summary
+2024-04-25 23:47:45,968 INFO    SenderThread:156911 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:47:45,968 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:45,968 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 5
+2024-04-25 23:47:45,968 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 6
+2024-04-25 23:47:45,968 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:45,968 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 6
+2024-04-25 23:47:45,968 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:45,968 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 6
+2024-04-25 23:47:45,968 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 7
+2024-04-25 23:47:45,968 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: status_report
+2024-04-25 23:47:45,968 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:45,968 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 7
+2024-04-25 23:47:45,969 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:45,969 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 7
+2024-04-25 23:47:46,210 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: poll_exit
+2024-04-25 23:47:48,284 INFO    Thread-12 :156911 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/output.log
+2024-04-25 23:47:49,328 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 8
+2024-04-25 23:47:49,328 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: poll_exit
+2024-04-25 23:47:49,328 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:49,328 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 8
+2024-04-25 23:47:49,329 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:49,329 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 8
+2024-04-25 23:47:49,329 INFO    SenderThread:156911 [job_builder.py:build():318] Attempting to build job artifact
+2024-04-25 23:47:49,330 INFO    SenderThread:156911 [job_builder.py:_get_source_type():455] is repo sourced job
+2024-04-25 23:47:49,436 INFO    SenderThread:156911 [job_builder.py:build():431] adding wandb-job metadata file
+2024-04-25 23:47:49,454 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 9
+2024-04-25 23:47:49,454 DEBUG   SenderThread:156911 [sender.py:send():379] send: artifact
+2024-04-25 23:47:49,454 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:49,456 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 9
+2024-04-25 23:47:50,155 INFO    wandb-upload_0:156911 [upload_job.py:push():89] Uploaded file /tmp/tmpt5uhix_o/wandb-job.json
+2024-04-25 23:47:50,174 INFO    wandb-upload_1:156911 [upload_job.py:push():89] Uploaded file /admin/home/sanchit/.local/share/wandb/artifacts/staging/tmpslw5rny7
+2024-04-25 23:47:50,212 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: poll_exit
+2024-04-25 23:47:50,286 INFO    Thread-12 :156911 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/output.log
+2024-04-25 23:47:50,813 INFO    SenderThread:156911 [sender.py:send_artifact():1468] sent artifact job-https___huggingface.co_sanchit-gandhi_distil-zephyr-1.5b-ssft-ultrachat_run_sft.py - {'id': 'QXJ0aWZhY3Q6ODEwNTI5OTk0', 'state': 'PENDING', 'artifactSequence': {'id': 'QXJ0aWZhY3RDb2xsZWN0aW9uOjE2NjI0NzU4Nw==', 'latestArtifact': {'id': 'QXJ0aWZhY3Q6ODA4NTQyNDIx', 'versionIndex': 0}}}
+2024-04-25 23:47:50,813 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:50,813 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 9
+2024-04-25 23:47:50,813 INFO    SenderThread:156911 [dir_watcher.py:finish():358] shutting down directory watcher
+2024-04-25 23:47:51,289 INFO    SenderThread:156911 [dir_watcher.py:finish():388] scan: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files
+2024-04-25 23:47:51,289 INFO    SenderThread:156911 [dir_watcher.py:finish():402] scan save: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/wandb-metadata.json wandb-metadata.json
+2024-04-25 23:47:51,289 INFO    SenderThread:156911 [dir_watcher.py:finish():402] scan save: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/config.yaml config.yaml
+2024-04-25 23:47:51,289 INFO    SenderThread:156911 [dir_watcher.py:finish():402] scan save: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/conda-environment.yaml conda-environment.yaml
+2024-04-25 23:47:51,290 INFO    SenderThread:156911 [dir_watcher.py:finish():402] scan save: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/output.log output.log
+2024-04-25 23:47:51,293 INFO    SenderThread:156911 [dir_watcher.py:finish():402] scan save: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/requirements.txt requirements.txt
+2024-04-25 23:47:51,296 INFO    SenderThread:156911 [dir_watcher.py:finish():402] scan save: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/wandb-summary.json wandb-summary.json
+2024-04-25 23:47:51,298 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 10
+2024-04-25 23:47:51,298 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: poll_exit
+2024-04-25 23:47:51,298 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:51,301 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 10
+2024-04-25 23:47:51,301 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:51,301 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 10
+2024-04-25 23:47:51,301 INFO    SenderThread:156911 [file_pusher.py:finish():172] shutting down file pusher
+2024-04-25 23:47:51,477 INFO    wandb-upload_0:156911 [upload_job.py:push():131] Uploaded file /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/config.yaml
+2024-04-25 23:47:51,602 INFO    wandb-upload_1:156911 [upload_job.py:push():131] Uploaded file /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/conda-environment.yaml
+2024-04-25 23:47:51,684 INFO    wandb-upload_2:156911 [upload_job.py:push():131] Uploaded file /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/output.log
+2024-04-25 23:47:51,688 INFO    wandb-upload_3:156911 [upload_job.py:push():131] Uploaded file /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/requirements.txt
+2024-04-25 23:47:51,720 INFO    wandb-upload_4:156911 [upload_job.py:push():131] Uploaded file /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/files/wandb-summary.json
+2024-04-25 23:47:51,920 INFO    Thread-11 (_thread_body):156911 [sender.py:transition_state():614] send defer: 11
+2024-04-25 23:47:51,921 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:51,921 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 11
+2024-04-25 23:47:51,921 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:51,921 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 11
+2024-04-25 23:47:51,921 INFO    SenderThread:156911 [file_pusher.py:join():178] waiting for file pusher
+2024-04-25 23:47:51,921 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 12
+2024-04-25 23:47:51,922 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:51,922 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 12
+2024-04-25 23:47:51,922 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:51,922 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 12
+2024-04-25 23:47:51,922 INFO    SenderThread:156911 [file_stream.py:finish():614] file stream finish called
+2024-04-25 23:47:52,002 INFO    SenderThread:156911 [file_stream.py:finish():618] file stream finish is done
+2024-04-25 23:47:52,002 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 13
+2024-04-25 23:47:52,002 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:52,002 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 13
+2024-04-25 23:47:52,002 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:52,002 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 13
+2024-04-25 23:47:52,002 INFO    SenderThread:156911 [sender.py:transition_state():614] send defer: 14
+2024-04-25 23:47:52,003 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: defer
+2024-04-25 23:47:52,003 DEBUG   SenderThread:156911 [sender.py:send():379] send: final
+2024-04-25 23:47:52,003 INFO    HandlerThread:156911 [handler.py:handle_request_defer():172] handle defer: 14
+2024-04-25 23:47:52,003 DEBUG   SenderThread:156911 [sender.py:send():379] send: footer
+2024-04-25 23:47:52,003 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: defer
+2024-04-25 23:47:52,003 INFO    SenderThread:156911 [sender.py:send_request_defer():610] handle sender defer: 14
+2024-04-25 23:47:52,003 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: poll_exit
+2024-04-25 23:47:52,004 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: poll_exit
+2024-04-25 23:47:52,004 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: poll_exit
+2024-04-25 23:47:52,004 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: server_info
+2024-04-25 23:47:52,004 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: poll_exit
+2024-04-25 23:47:52,004 DEBUG   SenderThread:156911 [sender.py:send_request():406] send_request: server_info
+2024-04-25 23:47:52,005 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: get_summary
+2024-04-25 23:47:52,006 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: sampled_history
+2024-04-25 23:47:52,008 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-25 23:47:52,058 INFO    MainThread:156911 [wandb_run.py:_footer_history_summary_info():3936] rendering history
+2024-04-25 23:47:52,059 INFO    MainThread:156911 [wandb_run.py:_footer_history_summary_info():3968] rendering summary
+2024-04-25 23:47:52,060 INFO    MainThread:156911 [wandb_run.py:_footer_sync_info():3895] logging synced files
+2024-04-25 23:47:52,060 DEBUG   HandlerThread:156911 [handler.py:handle_request():146] handle_request: shutdown
+2024-04-25 23:47:52,060 INFO    HandlerThread:156911 [handler.py:finish():866] shutting down handler
+2024-04-25 23:47:53,004 INFO    WriterThread:156911 [datastore.py:close():296] close: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_134518-etajcxpg/run-etajcxpg.wandb
+2024-04-25 23:47:53,058 INFO    SenderThread:156911 [sender.py:finish():1546] shutting down sender
+2024-04-25 23:47:53,059 INFO    SenderThread:156911 [file_pusher.py:finish():172] shutting down file pusher
+2024-04-25 23:47:53,059 INFO    SenderThread:156911 [file_pusher.py:join():178] waiting for file pusher

wandb/run-20240425_134518-etajcxpg/logs/debug.log

@@ -26,3 +26,4 @@ config: {}
 2024-04-25 13:45:22,708 INFO    MainThread:156194 [wandb_run.py:_redirect():2280] Redirects installed.
 2024-04-25 13:45:22,709 INFO    MainThread:156194 [wandb_init.py:init():842] run started, returning control to user process
 2024-04-25 13:45:22,711 INFO    MainThread:156194 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 6, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'sanchit-gandhi/Mistral-7B-v0.1-6-layer', 'transformers_version': '4.40.1', 'model_type': 'mistral', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 20000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Apr25_13-44-28_ip-26-0-167-177', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 5000, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 5000, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 7200, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'max_seq_length': 2048}
+2024-04-25 23:47:53,062 WARNING MsgRouterThr:156194 [router.py:message_loop():77] message_loop has been closed

wandb/run-20240425_134518-etajcxpg/run-etajcxpg.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a76851c2a0cca9f9fa32a212b4f4df28d1dc0eaa2ac3e93dec53f87fc69e3d2
-size 9699339
+oid sha256:de5e99632979ecd500d1f6bef80d0b60abaf19f5e363ea3ee3d4842e1fe79c1f
+size 9712391

wandb/run-20240425_234916-ozdw63qu/files/conda-environment.yaml

@@ -0,0 +1,125 @@
+name: alignment
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - bzip2=1.0.8=h5eee18b_5
+  - ca-certificates=2024.3.11=h06a4308_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - libffi=3.4.4=h6a678d5_0
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libuuid=1.41.5=h5eee18b_0
+  - ncurses=6.4=h6a678d5_0
+  - openssl=3.0.13=h7f8727e_0
+  - pip=23.3.1=py311h06a4308_0
+  - python=3.11.9=h955ad1f_0
+  - readline=8.2=h5eee18b_0
+  - setuptools=68.2.2=py311h06a4308_0
+  - sqlite=3.41.2=h5eee18b_0
+  - tk=8.6.12=h1ccaba5_0
+  - wheel=0.41.2=py311h06a4308_0
+  - xz=5.4.6=h5eee18b_0
+  - zlib=1.2.13=h5eee18b_0
+  - pip:
+      - absl-py==2.1.0
+      - accelerate==0.29.3
+      - aiohttp==3.9.5
+      - aiosignal==1.3.1
+      - annotated-types==0.6.0
+      - appdirs==1.4.4
+      - attrs==23.2.0
+      - bitsandbytes==0.43.1
+      - certifi==2024.2.2
+      - charset-normalizer==3.3.2
+      - click==8.1.7
+      - datasets==2.19.0
+      - deepspeed==0.14.2
+      - dill==0.3.8
+      - docker-pycreds==0.4.0
+      - docstring-parser==0.16
+      - einops==0.7.0
+      - evaluate==0.4.1
+      - filelock==3.13.4
+      - frozenlist==1.4.1
+      - fsspec==2024.3.1
+      - gitdb==4.0.11
+      - gitpython==3.1.43
+      - grpcio==1.62.2
+      - hf-transfer==0.1.6
+      - hjson==3.1.0
+      - huggingface-hub==0.22.2
+      - idna==3.7
+      - jinja2==3.1.3
+      - markdown==3.6
+      - markdown-it-py==3.0.0
+      - markupsafe==2.1.5
+      - mdurl==0.1.2
+      - mpmath==1.3.0
+      - multidict==6.0.5
+      - multiprocess==0.70.16
+      - networkx==3.3
+      - ninja==1.11.1.1
+      - numpy==1.26.4
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu12==8.9.2.26
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-nccl-cu12==2.19.3
+      - nvidia-nvjitlink-cu12==12.4.127
+      - nvidia-nvtx-cu12==12.1.105
+      - packaging==24.0
+      - pandas==2.2.2
+      - peft==0.10.0
+      - pillow==10.3.0
+      - protobuf==3.20.2
+      - psutil==5.9.8
+      - py-cpuinfo==9.0.0
+      - pyarrow==16.0.0
+      - pyarrow-hotfix==0.6
+      - pydantic==2.7.1
+      - pydantic-core==2.18.2
+      - pygments==2.17.2
+      - pynvml==11.5.0
+      - python-dateutil==2.9.0.post0
+      - pytz==2024.1
+      - pyyaml==6.0.1
+      - regex==2024.4.16
+      - requests==2.31.0
+      - responses==0.18.0
+      - rich==13.7.1
+      - safetensors==0.4.3
+      - scipy==1.13.0
+      - sentencepiece==0.2.0
+      - sentry-sdk==2.0.0
+      - setproctitle==1.3.3
+      - shtab==1.7.1
+      - six==1.16.0
+      - smmap==5.0.1
+      - sympy==1.12
+      - tensorboard==2.16.2
+      - tensorboard-data-server==0.7.2
+      - tokenizers==0.19.1
+      - torch==2.2.2
+      - torchaudio==2.2.2
+      - torchvision==0.17.2
+      - tqdm==4.66.2
+      - transformers==4.40.1
+      - triton==2.2.0
+      - trl==0.8.6
+      - typing-extensions==4.11.0
+      - tyro==0.8.3
+      - tzdata==2024.1
+      - urllib3==2.2.1
+      - wandb==0.16.6
+      - werkzeug==3.0.2
+      - xxhash==3.4.1
+      - yarl==1.9.4
+prefix: /fsx/sanchit/miniconda3/envs/alignment

wandb/run-20240425_234916-ozdw63qu/files/config.yaml

@@ -0,0 +1,30 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.11.9
+    cli_version: 0.16.6
+    framework: huggingface
+    huggingface_version: 4.40.1
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1714088956.0
+    t:
+      1:
+      - 1
+      - 11
+      - 49
+      - 51
+      - 55
+      - 71
+      - 84
+      - 98
+      3:
+      - 23
+      4: 3.11.9
+      5: 0.16.6
+      6: 4.40.1
+      8:
+      - 5
+      13: linux-x86_64

wandb/run-20240425_234916-ozdw63qu/files/output.log

@@ -0,0 +1,39 @@
+
+20001it [00:03, 6357.99it/s]             [INFO|trainer.py:2316] 2024-04-25 23:49:24,222 >>
+Training completed. Do not forget to share your model on huggingface.co/models =)
+20001it [00:03, 6316.44it/s]
+[INFO|trainer.py:3614] 2024-04-25 23:49:24,260 >> ***** Running Evaluation *****
+[INFO|trainer.py:3616] 2024-04-25 23:49:24,260 >>   Num examples = 639
+[INFO|trainer.py:3619] 2024-04-25 23:49:24,260 >>   Batch size = 32
+  0%|          | 0/3 [00:00<?, ?it/s]
+{'train_runtime': 9.0702, 'train_samples_per_second': 564484.818, 'train_steps_per_second': 2205.019, 'train_loss': 4.2969823139893115e-05, 'epoch': 4.94}
+***** train metrics *****
+  epoch                    =        4.9446
+  total_flos               = 84364461208GF
+  train_loss               =           0.0
+  train_runtime            =    0:00:09.07
+  train_samples            =       1467352
+  train_samples_per_second =    564484.818
+  train_steps_per_second   =      2205.019
+2024-04-25 23:49:24 - INFO - __main__ - *** Evaluate ***
+***** eval metrics *****
+  epoch                   =     4.9446
+  eval_loss               =     1.0042
+  eval_runtime            = 0:00:01.47
+  eval_samples            =       1000
+  eval_samples_per_second =    433.323
+  eval_steps_per_second   =      2.034
+100%|██████████| 3/3 [00:01<00:00,  2.17it/s]
+[INFO|trainer.py:3305] 2024-04-25 23:49:25,759 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:471] 2024-04-25 23:49:25,761 >> Configuration saved in ./config.json
+[INFO|configuration_utils.py:697] 2024-04-25 23:49:25,763 >> Configuration saved in ./generation_config.json
+[INFO|modeling_utils.py:2590] 2024-04-25 23:49:30,656 >> Model weights saved in ./model.safetensors
+[INFO|tokenization_utils_base.py:2488] 2024-04-25 23:49:30,659 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-25 23:49:30,661 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|trainer.py:3305] 2024-04-25 23:49:30,684 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:471] 2024-04-25 23:49:30,686 >> Configuration saved in ./config.json
+[INFO|configuration_utils.py:697] 2024-04-25 23:49:30,687 >> Configuration saved in ./generation_config.json
+[INFO|modeling_utils.py:2590] 2024-04-25 23:49:35,765 >> Model weights saved in ./model.safetensors
+[INFO|tokenization_utils_base.py:2488] 2024-04-25 23:49:35,768 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2497] 2024-04-25 23:49:35,769 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|modelcard.py:450] 2024-04-25 23:49:35,816 >> Dropping the following result as it does not have all the necessary fields:

wandb/run-20240425_234916-ozdw63qu/files/requirements.txt

@@ -0,0 +1,102 @@
+GitPython==3.1.43
+Jinja2==3.1.3
+Markdown==3.6
+MarkupSafe==2.1.5
+PyYAML==6.0.1
+Pygments==2.17.2
+Werkzeug==3.0.2
+absl-py==2.1.0
+accelerate==0.29.3
+aiohttp==3.9.5
+aiosignal==1.3.1
+alignment-handbook==0.4.0.dev0
+annotated-types==0.6.0
+appdirs==1.4.4
+attrs==23.2.0
+bitsandbytes==0.43.1
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+datasets==2.19.0
+deepspeed==0.14.2
+dill==0.3.8
+docker-pycreds==0.4.0
+docstring_parser==0.16
+einops==0.7.0
+evaluate==0.4.1
+filelock==3.13.4
+frozenlist==1.4.1
+fsspec==2024.3.1
+gitdb==4.0.11
+grpcio==1.62.2
+hf_transfer==0.1.6
+hjson==3.1.0
+huggingface-hub==0.22.2
+idna==3.7
+markdown-it-py==3.0.0
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.5
+multiprocess==0.70.16
+networkx==3.3
+ninja==1.11.1.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.1.105
+packaging==24.0
+pandas==2.2.2
+peft==0.10.0
+pillow==10.3.0
+pip==23.3.1
+protobuf==3.20.2
+psutil==5.9.8
+py-cpuinfo==9.0.0
+pyarrow-hotfix==0.6
+pyarrow==16.0.0
+pydantic==2.7.1
+pydantic_core==2.18.2
+pynvml==11.5.0
+python-dateutil==2.9.0.post0
+pytz==2024.1
+regex==2024.4.16
+requests==2.31.0
+responses==0.18.0
+rich==13.7.1
+safetensors==0.4.3
+scipy==1.13.0
+sentencepiece==0.2.0
+sentry-sdk==2.0.0
+setproctitle==1.3.3
+setuptools==68.2.2
+shtab==1.7.1
+six==1.16.0
+smmap==5.0.1
+sympy==1.12
+tensorboard-data-server==0.7.2
+tensorboard==2.16.2
+tokenizers==0.19.1
+torch==2.2.2
+torchaudio==2.2.2
+torchvision==0.17.2
+tqdm==4.66.2
+transformers==4.40.1
+triton==2.2.0
+trl==0.8.6
+typing_extensions==4.11.0
+tyro==0.8.3
+tzdata==2024.1
+urllib3==2.2.1
+wandb==0.16.6
+wheel==0.41.2
+xxhash==3.4.1
+yarl==1.9.4

wandb/run-20240425_234916-ozdw63qu/files/wandb-metadata.json

@@ -0,0 +1,558 @@
+{
+    "os": "Linux-5.15.0-1048-aws-x86_64-with-glibc2.31",
+    "python": "3.11.9",
+    "heartbeatAt": "2024-04-25T23:49:16.939535",
+    "startedAt": "2024-04-25T23:49:16.496864",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "./config_full.yaml"
+    ],
+    "state": "running",
+    "program": "/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/./run_sft.py",
+    "codePathLocal": "run_sft.py",
+    "codePath": "run_sft.py",
+    "git": {
+        "remote": "https://huggingface.co/sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat",
+        "commit": "cbea69c6b95c970317a1e47c3f614b55b33f8ed9"
+    },
+    "email": null,
+    "root": "/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat",
+    "host": "ip-26-0-167-177",
+    "username": "sanchit",
+    "executable": "/fsx/sanchit/miniconda3/envs/alignment/bin/python",
+    "cpu_count": 96,
+    "cpu_count_logical": 96,
+    "cpu_freq": {
+        "current": 2718.7540416666648,
+        "min": 0.0,
+        "max": 0.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 2603.523,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3596.748,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3596.723,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3597.872,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3590.698,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2688.441,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3582.227,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3596.99,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 3597.34,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        },
+        {
+            "current": 2649.998,
+            "min": 0.0,
+            "max": 0.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 290.7472343444824,
+            "used": 58.58917236328125
+        }
+    },
+    "gpu": "NVIDIA H100 80GB HBM3",
+    "gpu_count": 8,
+    "gpu_devices": [
+        {
+            "name": "NVIDIA H100 80GB HBM3",
+            "memory_total": 85520809984
+        },
+        {
+            "name": "NVIDIA H100 80GB HBM3",
+            "memory_total": 85520809984
+        },
+        {
+            "name": "NVIDIA H100 80GB HBM3",
+            "memory_total": 85520809984
+        },
+        {
+            "name": "NVIDIA H100 80GB HBM3",
+            "memory_total": 85520809984
+        },
+        {
+            "name": "NVIDIA H100 80GB HBM3",
+            "memory_total": 85520809984
+        },
+        {
+            "name": "NVIDIA H100 80GB HBM3",
+            "memory_total": 85520809984
+        },
+        {
+            "name": "NVIDIA H100 80GB HBM3",
+            "memory_total": 85520809984
+        },
+        {
+            "name": "NVIDIA H100 80GB HBM3",
+            "memory_total": 85520809984
+        }
+    ],
+    "memory": {
+        "total": 1999.9855155944824
+    }
+}

wandb/run-20240425_234916-ozdw63qu/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train_runtime": 9.0702, "train_samples_per_second": 564484.818, "train_steps_per_second": 2205.019, "total_flos": 9.058565045825516e+19, "train_loss": 4.2969823139893115e-05, "train/epoch": 4.944622991347343, "train/global_step": 20001, "_timestamp": 1714088965.7540886, "_runtime": 9.237897634506226, "_step": 1, "eval/loss": 1.0042184591293335, "eval/runtime": 1.4747, "eval/samples_per_second": 433.323, "eval/steps_per_second": 2.034}

wandb/run-20240425_234916-ozdw63qu/logs/debug-internal.log

@@ -0,0 +1,88 @@
+2024-04-25 23:49:16,511 INFO    StreamThr :212584 [internal.py:wandb_internal():86] W&B internal server running at pid: 212584, started at: 2024-04-25 23:49:16.510614
+2024-04-25 23:49:16,512 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: status
+2024-04-25 23:49:16,519 INFO    WriterThread:212584 [datastore.py:open_for_write():87] open: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/run-ozdw63qu.wandb
+2024-04-25 23:49:16,520 DEBUG   SenderThread:212584 [sender.py:send():379] send: header
+2024-04-25 23:49:16,537 DEBUG   SenderThread:212584 [sender.py:send():379] send: run
+2024-04-25 23:49:16,772 INFO    SenderThread:212584 [dir_watcher.py:__init__():211] watching files in: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files
+2024-04-25 23:49:16,772 INFO    SenderThread:212584 [sender.py:_start_run_threads():1124] run started: ozdw63qu with start time 1714088956.516191
+2024-04-25 23:49:16,778 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: check_version
+2024-04-25 23:49:16,778 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: check_version
+2024-04-25 23:49:16,833 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: run_start
+2024-04-25 23:49:16,892 DEBUG   HandlerThread:212584 [system_info.py:__init__():26] System info init
+2024-04-25 23:49:16,892 DEBUG   HandlerThread:212584 [system_info.py:__init__():41] System info init done
+2024-04-25 23:49:16,892 INFO    HandlerThread:212584 [system_monitor.py:start():194] Starting system monitor
+2024-04-25 23:49:16,893 INFO    SystemMonitor:212584 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-04-25 23:49:16,893 INFO    HandlerThread:212584 [system_monitor.py:probe():214] Collecting system info
+2024-04-25 23:49:16,893 INFO    SystemMonitor:212584 [interfaces.py:start():190] Started cpu monitoring
+2024-04-25 23:49:16,893 INFO    SystemMonitor:212584 [interfaces.py:start():190] Started disk monitoring
+2024-04-25 23:49:16,894 INFO    SystemMonitor:212584 [interfaces.py:start():190] Started gpu monitoring
+2024-04-25 23:49:16,894 INFO    SystemMonitor:212584 [interfaces.py:start():190] Started memory monitoring
+2024-04-25 23:49:16,895 INFO    SystemMonitor:212584 [interfaces.py:start():190] Started network monitoring
+2024-04-25 23:49:16,939 DEBUG   HandlerThread:212584 [system_info.py:probe():150] Probing system
+2024-04-25 23:49:16,942 DEBUG   HandlerThread:212584 [system_info.py:_probe_git():135] Probing git
+2024-04-25 23:49:16,961 DEBUG   HandlerThread:212584 [system_info.py:_probe_git():143] Probing git done
+2024-04-25 23:49:16,961 DEBUG   HandlerThread:212584 [system_info.py:probe():198] Probing system done
+2024-04-25 23:49:16,961 DEBUG   HandlerThread:212584 [system_monitor.py:probe():223] {'os': 'Linux-5.15.0-1048-aws-x86_64-with-glibc2.31', 'python': '3.11.9', 'heartbeatAt': '2024-04-25T23:49:16.939535', 'startedAt': '2024-04-25T23:49:16.496864', 'docker': None, 'cuda': None, 'args': ('./config_full.yaml',), 'state': 'running', 'program': '/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/./run_sft.py', 'codePathLocal': 'run_sft.py', 'codePath': 'run_sft.py', 'git': {'remote': 'https://huggingface.co/sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat', 'commit': 'cbea69c6b95c970317a1e47c3f614b55b33f8ed9'}, 'email': None, 'root': '/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat', 'host': 'ip-26-0-167-177', 'username': 'sanchit', 'executable': '/fsx/sanchit/miniconda3/envs/alignment/bin/python', 'cpu_count': 96, 'cpu_count_logical': 96, 'cpu_freq': {'current': 2718.7540416666648, 'min': 0.0, 'max': 0.0}, 'cpu_freq_per_core': [{'current': 2603.523, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 3596.748, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 3596.723, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 3597.872, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 3590.698, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2688.441, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 3582.227, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 3596.99, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 3597.34, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}, {'current': 2649.998, 'min': 0.0, 'max': 0.0}], 'disk': {'/': {'total': 290.7472343444824, 'used': 58.58917236328125}}, 'gpu': 'NVIDIA H100 80GB HBM3', 'gpu_count': 8, 'gpu_devices': [{'name': 'NVIDIA H100 80GB HBM3', 'memory_total': 85520809984}, {'name': 'NVIDIA H100 80GB HBM3', 'memory_total': 85520809984}, {'name': 'NVIDIA H100 80GB HBM3', 'memory_total': 85520809984}, {'name': 'NVIDIA H100 80GB HBM3', 'memory_total': 85520809984}, {'name': 'NVIDIA H100 80GB HBM3', 'memory_total': 85520809984}, {'name': 'NVIDIA H100 80GB HBM3', 'memory_total': 85520809984}, {'name': 'NVIDIA H100 80GB HBM3', 'memory_total': 85520809984}, {'name': 'NVIDIA H100 80GB HBM3', 'memory_total': 85520809984}], 'memory': {'total': 1999.9855155944824}}
+2024-04-25 23:49:16,962 INFO    HandlerThread:212584 [system_monitor.py:probe():224] Finished collecting system info
+2024-04-25 23:49:16,962 INFO    HandlerThread:212584 [system_monitor.py:probe():227] Publishing system info
+2024-04-25 23:49:16,962 DEBUG   HandlerThread:212584 [system_info.py:_save_conda():207] Saving list of conda packages installed into the current environment
+2024-04-25 23:49:17,774 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_created():271] file/dir created: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/conda-environment.yaml
+2024-04-25 23:49:20,884 DEBUG   HandlerThread:212584 [system_info.py:_save_conda():222] Saving conda packages done
+2024-04-25 23:49:20,887 INFO    HandlerThread:212584 [system_monitor.py:probe():229] Finished publishing system info
+2024-04-25 23:49:20,915 DEBUG   SenderThread:212584 [sender.py:send():379] send: files
+2024-04-25 23:49:20,915 INFO    SenderThread:212584 [sender.py:_save_file():1390] saving file wandb-metadata.json with policy now
+2024-04-25 23:49:21,061 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: python_packages
+2024-04-25 23:49:21,061 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: python_packages
+2024-04-25 23:49:21,061 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-25 23:49:21,062 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-25 23:49:21,063 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: stop_status
+2024-04-25 23:49:21,184 INFO    wandb-upload_0:212584 [upload_job.py:push():131] Uploaded file /tmp/tmp9wuipw18wandb/r4fodxap-wandb-metadata.json
+2024-04-25 23:49:21,185 DEBUG   SenderThread:212584 [sender.py:send():379] send: telemetry
+2024-04-25 23:49:21,185 DEBUG   SenderThread:212584 [sender.py:send():379] send: config
+2024-04-25 23:49:21,187 DEBUG   SenderThread:212584 [sender.py:send():379] send: metric
+2024-04-25 23:49:21,188 DEBUG   SenderThread:212584 [sender.py:send():379] send: telemetry
+2024-04-25 23:49:21,188 DEBUG   SenderThread:212584 [sender.py:send():379] send: metric
+2024-04-25 23:49:21,188 WARNING SenderThread:212584 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
+2024-04-25 23:49:21,188 DEBUG   SenderThread:212584 [sender.py:send():379] send: telemetry
+2024-04-25 23:49:21,778 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/conda-environment.yaml
+2024-04-25 23:49:21,778 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_created():271] file/dir created: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/wandb-metadata.json
+2024-04-25 23:49:21,778 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_created():271] file/dir created: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/requirements.txt
+2024-04-25 23:49:21,778 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_created():271] file/dir created: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/output.log
+2024-04-25 23:49:22,189 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: status_report
+2024-04-25 23:49:23,780 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/output.log
+2024-04-25 23:49:24,232 DEBUG   SenderThread:212584 [sender.py:send():379] send: telemetry
+2024-04-25 23:49:24,233 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: summary_record
+2024-04-25 23:49:24,234 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-25 23:49:24,236 INFO    SenderThread:212584 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:49:24,237 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: summary_record
+2024-04-25 23:49:24,238 INFO    SenderThread:212584 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:49:24,238 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: summary_record
+2024-04-25 23:49:24,239 INFO    SenderThread:212584 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:49:24,239 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: summary_record
+2024-04-25 23:49:24,240 INFO    SenderThread:212584 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:49:24,240 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: summary_record
+2024-04-25 23:49:24,242 INFO    SenderThread:212584 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:49:24,242 DEBUG   SenderThread:212584 [sender.py:send():379] send: metric
+2024-04-25 23:49:24,242 DEBUG   SenderThread:212584 [sender.py:send():379] send: history
+2024-04-25 23:49:24,242 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: summary_record
+2024-04-25 23:49:24,243 INFO    SenderThread:212584 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:49:24,782 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_created():271] file/dir created: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/wandb-summary.json
+2024-04-25 23:49:25,754 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-25 23:49:25,757 DEBUG   SenderThread:212584 [sender.py:send():379] send: metric
+2024-04-25 23:49:25,758 DEBUG   SenderThread:212584 [sender.py:send():379] send: metric
+2024-04-25 23:49:25,758 DEBUG   SenderThread:212584 [sender.py:send():379] send: metric
+2024-04-25 23:49:25,758 DEBUG   SenderThread:212584 [sender.py:send():379] send: metric
+2024-04-25 23:49:25,758 DEBUG   SenderThread:212584 [sender.py:send():379] send: history
+2024-04-25 23:49:25,758 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: summary_record
+2024-04-25 23:49:25,760 INFO    SenderThread:212584 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-25 23:49:25,783 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/wandb-summary.json
+2024-04-25 23:49:25,784 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/output.log
+2024-04-25 23:49:26,785 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/output.log
+2024-04-25 23:49:27,764 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: status_report
+2024-04-25 23:49:27,787 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/output.log
+2024-04-25 23:49:31,791 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/output.log
+2024-04-25 23:49:33,688 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: status_report
+2024-04-25 23:49:36,062 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-25 23:49:36,063 DEBUG   HandlerThread:212584 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-25 23:49:36,063 DEBUG   SenderThread:212584 [sender.py:send_request():406] send_request: stop_status
+2024-04-25 23:49:37,798 INFO    Thread-12 :212584 [dir_watcher.py:_on_file_modified():288] file/dir modified: /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/files/output.log

wandb/run-20240425_234916-ozdw63qu/logs/debug.log

@@ -0,0 +1,28 @@
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Current SDK version is 0.16.6
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Configure stats pid to 211869
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Loading settings from /admin/home/sanchit/.config/wandb/settings
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Loading settings from /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/settings
+2024-04-25 23:49:16,505 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'run_sft.py', 'program_abspath': '/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/run_sft.py', 'program': '/fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/./run_sft.py'}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_setup.py:_flush():76] Applying login settings: {}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:_log_setup():521] Logging user logs to /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/logs/debug.log
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:_log_setup():522] Logging internal logs to /fsx/sanchit/distil-zephyr-1.5b-ssft-ultrachat/wandb/run-20240425_234916-ozdw63qu/logs/debug-internal.log
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:init():561] calling init triggers
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:init():568] wandb.init called with sweep_config: {}
+config: {}
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:init():611] starting backend
+2024-04-25 23:49:16,506 INFO    MainThread:211869 [wandb_init.py:init():615] setting up manager
+2024-04-25 23:49:16,508 INFO    MainThread:211869 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2024-04-25 23:49:16,515 INFO    MainThread:211869 [wandb_init.py:init():623] backend started and connected
+2024-04-25 23:49:16,518 INFO    MainThread:211869 [wandb_init.py:init():715] updated telemetry
+2024-04-25 23:49:16,536 INFO    MainThread:211869 [wandb_init.py:init():748] communicating run to backend with 90.0 second timeout
+2024-04-25 23:49:16,777 INFO    MainThread:211869 [wandb_run.py:_on_init():2357] communicating current version
+2024-04-25 23:49:16,826 INFO    MainThread:211869 [wandb_run.py:_on_init():2366] got version response 
+2024-04-25 23:49:16,826 INFO    MainThread:211869 [wandb_init.py:init():799] starting run threads in backend
+2024-04-25 23:49:21,061 INFO    MainThread:211869 [wandb_run.py:_console_start():2335] atexit reg
+2024-04-25 23:49:21,061 INFO    MainThread:211869 [wandb_run.py:_redirect():2190] redirect: wrap_raw
+2024-04-25 23:49:21,061 INFO    MainThread:211869 [wandb_run.py:_redirect():2255] Wrapping output streams.
+2024-04-25 23:49:21,062 INFO    MainThread:211869 [wandb_run.py:_redirect():2280] Redirects installed.
+2024-04-25 23:49:21,063 INFO    MainThread:211869 [wandb_init.py:init():842] run started, returning control to user process
+2024-04-25 23:49:21,064 INFO    MainThread:211869 [wandb_run.py:_config_callback():1347] config_cb None None {'vocab_size': 32000, 'max_position_embeddings': 32768, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 6, 'num_attention_heads': 32, 'sliding_window': 4096, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'use_cache': False, 'rope_theta': 10000.0, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, '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': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['MistralForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': None, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'sanchit-gandhi/Mistral-7B-v0.1-6-layer', 'transformers_version': '4.40.1', 'model_type': 'mistral', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 20000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Apr25_23-48-22_ip-26-0-167-177', 'logging_strategy': 'steps', 'logging_first_step': True, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 5000, 'save_total_limit': 1, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 5000, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': {'use_reentrant': False}, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 7200, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'max_seq_length': 2048}