Chtmp223's workspace
Runs
50
Name
3 visualized
learning_rate
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.000001
0.00001
0.00001
0.00005
0.00005
0.000001
Commit
Runtime
GitHub
Hostname
Notes
State
Tags
beta
disable_dropout
do_eval
eval_strategy
generate_during_eval
gradient_checkpointing_kwargs.use_reentrant
hub_model_id
is_encoder_decoder
label_pad_token_id
logging_first_step
logging_steps
max_completion_length
max_length
max_prompt_length
max_seq_length
num_train_epochs
optim
output_dir
overwrite_output_dir
per_device_train_batch_size
remove_unused_columns
run_name
save_steps
save_total_limit
transformers_version
truncation_mode
warmup_ratio
warmup_steps
_attn_implementation_autoset
dataset_num_proc
deepspeed
eval_on_start
eval_use_gather_object
generation_max_length
head_dim
include_for_metrics
max_window_layers
model/num_parameters
peft_config.default.base_model_name_or_path
1b5398f539c7d94a530f3f32b53553a3b1928314
6d 4h 8m 34s
-
-
Finished
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-ft/llamafactory_qwen/
false
1
false
/scratch3/workspace/ctpham_umass_edu-ft/llamafactory_qwen/
50
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
333312
-
1b5398f539c7d94a530f3f32b53553a3b1928314
6h 53m
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-ft/llamafactory_qwen/
false
1
false
/scratch3/workspace/ctpham_umass_edu-ft/llamafactory_qwen/
50
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
333312
-
1b5398f539c7d94a530f3f32b53553a3b1928314
7h 20m 33s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-ft/llamafactory_qwen/
false
1
false
/scratch3/workspace/ctpham_umass_edu-ft/llamafactory_qwen/
50
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
11m 16s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
false
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
1
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
333312
-
1b5398f539c7d94a530f3f32b53553a3b1928314
15m 31s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
false
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
1
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
9m 30s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
false
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
1
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
1m 15s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
true
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
1
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
9m 31s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
true
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
1
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
5m 30s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-ft/llamafactory_qwen/
true
1
false
/scratch3/workspace/ctpham_umass_edu-ft/llamafactory_qwen/
1
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
11m 15s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
true
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
1
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
4m 15s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
true
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
1
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
2s
-
-
Failed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
true
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
50
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
128
-
-
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
15m 31s
-
-
Crashed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
true
1
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
500
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
2m 4s
-
-
Failed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
true
16
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
500
-
4.45.0
-
0.05
0
-
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
-
28
0
-
1b5398f539c7d94a530f3f32b53553a3b1928314
2m 3s
-
-
Failed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
-
1
adamw_torch
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
true
16
false
/scratch3/workspace/ctpham_umass_edu-models/llamafactory_qwen/
500
-
4.46.1
-
0.05
0
true
-
examples/deepspeed/ds_z3_offload_config.json
false
false
131072
-
[]
28
0
-
e913668712eb78418ce362166d926cb624883a5b
1m 27s
-
-
Failed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
131071
1
adamw_8bit
/scratch/workspace/ctpham_umass_edu-llama/unsloth
false
1
true
/scratch/workspace/ctpham_umass_edu-llama/unsloth
300
-
4.44.2
-
0
5
-
2
-
false
false
-
-
-
-
8072204288
unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
a63feff37959a09b3cd5f9c2c418dec303f61dfc
42s
-
-
Failed
-
-
false
no
-
-
-
false
-
false
1
-
20
-
131071
1
adamw_8bit
/scratch/workspace/ctpham_umass_edu-llama/unsloth
false
2
true
unsloth-2-4-64-64-0.05
300
-
4.44.2
-
0
5
-
2
-
false
false
-
-
-
-
8198033408
unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
984bd623f0f7ba2e0f45cd4a26fbf035b06df5f6
3h 58m 1s
-
-
Crashed
-
-
false
no
-
false
suri-sft
false
-
true
10
-
20
-
15024
2
adamw_torch
/scratch/workspace/ctpham_umass_edu-goliath
true
1
true
suri-sft-single
2
2
4.41.2
-
0.1
0
-
-
-
-
-
-
-
-
-
-
-
22b3cf678049b36ec935aa3f812497f742b5e636
1m 31s
-
-
Killed
0.4
true
false
no
false
false
test-orpo
-
-100
false
10
15000
15024
5000
-
2
adamw_torch
/scratch/workspace/ctpham_umass_edu-ft/orpo-test
false
1
false
orpo-test
3
3
4.41.1
keep_end
0
0
-
-
-
-
-
-
-
-
-
-
-
276ade04b2ffef82ec58d16e711a6d9c51bd265e
5h 20m 5s
-
-
Crashed
0.1
true
false
no
false
true
orpo_full_single_1e-6
-
-100
false
10
15000
15024
5000
-
2
adamw_torch
/scratch/workspace/ctpham_umass_edu-ft/orpo_full_single_1e-6
false
2
false
orpo_full_single_1e-6
3
3
4.41.1
keep_end
0
0
-
-
-
-
-
-
-
-
-
-
-
1-20
of 50