Hugging Face's logo

rbelanec
/
train_mrpc_1744902652

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
eef00fa
·
verified ·
1 Parent(s): dfcdaf0

Training in progress, step 200

Browse files
Files changed (8) hide show
  1. adapter_config.json +35 -0
  2. adapter_model.safetensors +3 -0
  3. special_tokens_map.json +24 -0
  4. tokenizer.json +0 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +0 -0
  7. trainer_log.jsonl +41 -0
  8. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
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": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "k_proj",
28
+ "v_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "trainable_token_indices": null,
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:128a8af0f7a3d96c116fb3a837422f4322a1eeb91d0948245e0a07b823234eb8
3
+ size 58745928
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_log.jsonl ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 40000, "loss": 0.3457, "lr": 4.999999876629946e-05, "epoch": 0.024213075060532687, "percentage": 0.01, "elapsed_time": "0:00:06", "remaining_time": "15:07:04", "throughput": 1189.89, "total_tokens": 8096}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 0.2047, "lr": 4.999999375439123e-05, "epoch": 0.048426150121065374, "percentage": 0.03, "elapsed_time": "0:00:10", "remaining_time": "11:52:13", "throughput": 1587.13, "total_tokens": 16960}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 0.2076, "lr": 4.9999984887169785e-05, "epoch": 0.07263922518159806, "percentage": 0.04, "elapsed_time": "0:00:14", "remaining_time": "10:46:25", "throughput": 1744.04, "total_tokens": 25376}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.1939, "lr": 4.9999972164636506e-05, "epoch": 0.09685230024213075, "percentage": 0.05, "elapsed_time": "0:00:18", "remaining_time": "10:16:30", "throughput": 1872.83, "total_tokens": 34656}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.1773, "lr": 4.999995558679334e-05, "epoch": 0.12106537530266344, "percentage": 0.06, "elapsed_time": "0:00:22", "remaining_time": "9:55:19", "throughput": 1925.25, "total_tokens": 43008}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.1983, "lr": 4.999993515364287e-05, "epoch": 0.14527845036319612, "percentage": 0.07, "elapsed_time": "0:00:26", "remaining_time": "9:41:51", "throughput": 1969.84, "total_tokens": 51616}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.1865, "lr": 4.999991086518822e-05, "epoch": 0.1694915254237288, "percentage": 0.09, "elapsed_time": "0:00:30", "remaining_time": "9:32:56", "throughput": 1998.28, "total_tokens": 60160}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.1458, "lr": 4.999988272143315e-05, "epoch": 0.1937046004842615, "percentage": 0.1, "elapsed_time": "0:00:34", "remaining_time": "9:26:19", "throughput": 2029.33, "total_tokens": 69024}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.1955, "lr": 4.999985072238199e-05, "epoch": 0.2179176755447942, "percentage": 0.11, "elapsed_time": "0:00:37", "remaining_time": "9:20:45", "throughput": 2052.06, "total_tokens": 77760}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.1516, "lr": 4.999981486803969e-05, "epoch": 0.24213075060532688, "percentage": 0.12, "elapsed_time": "0:00:41", "remaining_time": "9:16:01", "throughput": 2072.33, "total_tokens": 86528}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.1507, "lr": 4.999977515841176e-05, "epoch": 0.26634382566585957, "percentage": 0.14, "elapsed_time": "0:00:45", "remaining_time": "9:12:15", "throughput": 2081.7, "total_tokens": 94976}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.1406, "lr": 4.9999731593504344e-05, "epoch": 0.29055690072639223, "percentage": 0.15, "elapsed_time": "0:00:49", "remaining_time": "9:08:47", "throughput": 2096.03, "total_tokens": 103680}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.1258, "lr": 4.999968417332415e-05, "epoch": 0.31476997578692495, "percentage": 0.16, "elapsed_time": "0:00:53", "remaining_time": "9:06:03", "throughput": 2106.26, "total_tokens": 112320}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.1414, "lr": 4.999963289787848e-05, "epoch": 0.3389830508474576, "percentage": 0.18, "elapsed_time": "0:00:57", "remaining_time": "9:03:48", "throughput": 2115.25, "total_tokens": 120992}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.0918, "lr": 4.999957776717526e-05, "epoch": 0.36319612590799033, "percentage": 0.19, "elapsed_time": "0:01:01", "remaining_time": "9:02:14", "throughput": 2126.83, "total_tokens": 129984}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.1625, "lr": 4.9999518781222984e-05, "epoch": 0.387409200968523, "percentage": 0.2, "elapsed_time": "0:01:04", "remaining_time": "9:00:33", "throughput": 2134.27, "total_tokens": 138720}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.148, "lr": 4.9999455940030746e-05, "epoch": 0.4116222760290557, "percentage": 0.21, "elapsed_time": "0:01:08", "remaining_time": "8:59:08", "throughput": 2142.87, "total_tokens": 147616}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.1093, "lr": 4.999938924360824e-05, "epoch": 0.4358353510895884, "percentage": 0.22, "elapsed_time": "0:01:12", "remaining_time": "8:57:30", "throughput": 2148.51, "total_tokens": 156256}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.1559, "lr": 4.999931869196575e-05, "epoch": 0.4600484261501211, "percentage": 0.24, "elapsed_time": "0:01:16", "remaining_time": "8:56:08", "throughput": 2153.16, "total_tokens": 164896}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.1737, "lr": 4.999924428511416e-05, "epoch": 0.48426150121065376, "percentage": 0.25, "elapsed_time": "0:01:20", "remaining_time": "8:54:55", "throughput": 2158.1, "total_tokens": 173600}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.1427, "lr": 4.999916602306494e-05, "epoch": 0.5084745762711864, "percentage": 0.26, "elapsed_time": "0:01:24", "remaining_time": "8:54:02", "throughput": 2166.27, "total_tokens": 182688}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.1191, "lr": 4.999908390583016e-05, "epoch": 0.5326876513317191, "percentage": 0.27, "elapsed_time": "0:01:28", "remaining_time": "8:53:02", "throughput": 2169.76, "total_tokens": 191360}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.1304, "lr": 4.999899793342247e-05, "epoch": 0.5569007263922519, "percentage": 0.29, "elapsed_time": "0:01:32", "remaining_time": "8:52:18", "throughput": 2171.84, "total_tokens": 200000}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.1561, "lr": 4.999890810585516e-05, "epoch": 0.5811138014527845, "percentage": 0.3, "elapsed_time": "0:01:35", "remaining_time": "8:51:28", "throughput": 2174.07, "total_tokens": 208608}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.1181, "lr": 4.999881442314206e-05, "epoch": 0.6053268765133172, "percentage": 0.31, "elapsed_time": "0:01:39", "remaining_time": "8:50:35", "throughput": 2176.9, "total_tokens": 217248}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.1473, "lr": 4.9998716885297617e-05, "epoch": 0.6295399515738499, "percentage": 0.33, "elapsed_time": "0:01:43", "remaining_time": "8:50:15", "throughput": 2179.66, "total_tokens": 226112}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.1404, "lr": 4.999861549233688e-05, "epoch": 0.6537530266343826, "percentage": 0.34, "elapsed_time": "0:01:47", "remaining_time": "8:49:30", "throughput": 2181.32, "total_tokens": 234688}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.1308, "lr": 4.999851024427548e-05, "epoch": 0.6779661016949152, "percentage": 0.35, "elapsed_time": "0:01:51", "remaining_time": "8:48:51", "throughput": 2180.7, "total_tokens": 243040}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.2127, "lr": 4.999840114112965e-05, "epoch": 0.7021791767554479, "percentage": 0.36, "elapsed_time": "0:01:55", "remaining_time": "8:48:15", "throughput": 2181.72, "total_tokens": 251584}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.1956, "lr": 4.999828818291621e-05, "epoch": 0.7263922518159807, "percentage": 0.38, "elapsed_time": "0:01:59", "remaining_time": "8:47:36", "throughput": 2185.18, "total_tokens": 260384}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.1452, "lr": 4.999817136965259e-05, "epoch": 0.7506053268765133, "percentage": 0.39, "elapsed_time": "0:02:03", "remaining_time": "8:46:59", "throughput": 2184.31, "total_tokens": 268672}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.1375, "lr": 4.9998050701356794e-05, "epoch": 0.774818401937046, "percentage": 0.4, "elapsed_time": "0:02:06", "remaining_time": "8:46:21", "throughput": 2185.45, "total_tokens": 277184}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.1388, "lr": 4.999792617804744e-05, "epoch": 0.7990314769975787, "percentage": 0.41, "elapsed_time": "0:02:10", "remaining_time": "8:45:50", "throughput": 2186.36, "total_tokens": 285728}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.1, "lr": 4.9997797799743724e-05, "epoch": 0.8232445520581114, "percentage": 0.43, "elapsed_time": "0:02:14", "remaining_time": "8:45:18", "throughput": 2188.42, "total_tokens": 294400}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.1465, "lr": 4.999766556646545e-05, "epoch": 0.847457627118644, "percentage": 0.44, "elapsed_time": "0:02:18", "remaining_time": "8:45:03", "throughput": 2191.62, "total_tokens": 303392}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.0925, "lr": 4.9997529478232996e-05, "epoch": 0.8716707021791767, "percentage": 0.45, "elapsed_time": "0:02:22", "remaining_time": "8:44:41", "throughput": 2194.01, "total_tokens": 312224}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.1034, "lr": 4.9997389535067365e-05, "epoch": 0.8958837772397095, "percentage": 0.46, "elapsed_time": "0:02:26", "remaining_time": "8:44:17", "throughput": 2196.69, "total_tokens": 321088}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.102, "lr": 4.999724573699012e-05, "epoch": 0.9200968523002422, "percentage": 0.47, "elapsed_time": "0:02:30", "remaining_time": "8:43:53", "throughput": 2198.11, "total_tokens": 329760}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.1164, "lr": 4.9997098084023457e-05, "epoch": 0.9443099273607748, "percentage": 0.49, "elapsed_time": "0:02:33", "remaining_time": "8:43:35", "throughput": 2199.84, "total_tokens": 338560}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.147, "lr": 4.999694657619013e-05, "epoch": 0.9685230024213075, "percentage": 0.5, "elapsed_time": "0:02:37", "remaining_time": "8:43:10", "throughput": 2198.66, "total_tokens": 346816}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.12923812866210938, "epoch": 0.9685230024213075, "percentage": 0.5, "elapsed_time": "0:02:43", "remaining_time": "9:01:14", "throughput": 2125.22, "total_tokens": 346816}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7921c914eb1231ed5ca58a123cd942bea5dd9197f29a3040f1c24ca17723512e
3
+ size 5752