cgalabs commited on
Commit
9420166
·
verified ·
1 Parent(s): 01e8944

Upload folder using huggingface_hub

Browse files
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": false,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "down_proj",
28
+ "q_proj",
29
+ "o_proj",
30
+ "gate_proj",
31
+ "up_proj",
32
+ "v_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e6124860789860d44a05828b9c7457608ee9122580dc695f54cae43e226d9c
3
+ size 134351144
stats.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"world_size": 1, "epochs": 3, "steps": 15, "seqs": 696, "tokens": 402027, "last_epoch_steps": 0, "last_epoch_seqs": 0, "last_epoch_tokens": 0, "total_seqs": 232, "nan_in_loss_seqs": 0, "experiment_tracking_run_id": null, "loss_ema": 0.6296908100446065, "loss_sum": 9.445362150669098, "mtp_loss_ema": 0, "mtp_loss_sum": 0, "eval_losses_avg": [0.6934893727302551, 0.6750823259353638, 0.6382126808166504, 0.6356888711452484, 0.6220795810222626, 0.6190989017486572]}
train_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"comet": false, "comet_api_key": null, "comet_workspace": null, "comet_project": null, "comet_run_id": "jsbjgp3p", "wandb": false, "wandb_api_key": null, "wandb_entity": null, "wandb_project": null, "wandb_run_id": "jsbjgp3p", "base_model_dir": "/llm-downloader-destination/base/fireworks/qwen2p5-vl-32b-instruct/hf", "output_model_dir": "gs://fireworks-artifacts-kerem6790-39b01e/tuned-model-jsbjgp3p/6b79fb/yks-vlm-lora-v2/checkpoint", "checkpoint_dir": "/dev/shm/checkpoints", "gcs_checkpoint_dir": "gs://fireworks-artifacts-kerem6790-39b01e/tuned-model-jsbjgp3p/6b79fb/yks-vlm-lora-v2/checkpoints/checkpoints", "max_checkpoints_to_keep": 1, "checkpoint_interval": 3600, "save_final_checkpoint": false, "train": true, "learning_rate": 0.0001, "learning_rate_warmup_steps": 0, "grad_accum_steps": 1, "epochs": 3, "early_stop": false, "seed": 42, "dataset_dir": "/mnt/staging/dataset", "eval_auto_carveout": true, "eval_dataset_dir": null, "train_limit": null, "max_context_len": 8192, "batch_size": 8192, "batch_size_samples": null, "max_data_workers": 0, "min_evals_per_epoch": 4, "precision": null, "status_file": "gs://fireworks-fine-tuning-job-status/sftj-kerem6790-jsbjgp3p-71b27551-62dc-423a-934d-e7ce17d0c39e", "billing_file": "gs://fireworks-fine-tuning-metadata/sftj-kerem6790-jsbjgp3p/billing-71b27551-62dc-423a-934d-e7ce17d0c39e", "metrics_file": "gs://fireworks-fine-tuning-metadata/sftj-kerem6790-jsbjgp3p/metrics.jsonl", "profile": null, "weight_sharding": null, "activation_sharding": null, "empty_weights": false, "nan_ratio_threshold": 0.05, "fast_api_port": 80, "optimizer": "adamw", "target_shard_size_gb": null, "peft_addon_dir": null, "lora_rank": 8, "lora_dropout": 0.05, "template_kind": "conversation", "template": null, "eval_train_ratio": 0.02, "mtp_config": {"enable_mtp": false, "freeze_base_model": false, "num_draft_tokens": 1}, "qat": true, "kld": false, "teft_tokens": [], "skip_dataset_filtering": false}