Hugging Face's logo

rbelanec
/
train_cb_1745950310

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
3365824
路
verified 路
1 Parent(s): 355c418

Training in progress, step 200

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. adapter_config.json +35 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +3 -0
  5. special_tokens_map.json +42 -0
  6. tokenizer.json +3 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +0 -0
  9. trainer_log.jsonl +43 -0
  10. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-3-1b-it",
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
+ "down_proj",
29
+ "v_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:d7d8655fae6c3ec8f72fac573e43d55085086e5281b141ded9297c3d1a0a7534
3
+ size 18124968
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<end_of_turn>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "boi_token": "<start_of_image>",
12
+ "bos_token": {
13
+ "content": "<bos>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eoi_token": "<end_of_image>",
20
+ "eos_token": {
21
+ "content": "<eos>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "image_token": "<image_soft_token>",
28
+ "pad_token": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "unk_token": {
36
+ "content": "<unk>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_log.jsonl ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 40000, "loss": 2.6928, "lr": 4.999999876629946e-05, "epoch": 0.08849557522123894, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "10:47:36", "throughput": 619.23, "total_tokens": 3008}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 1.1, "lr": 4.999999375439123e-05, "epoch": 0.17699115044247787, "percentage": 0.03, "elapsed_time": "0:00:07", "remaining_time": "7:48:57", "throughput": 870.92, "total_tokens": 6128}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 0.5093, "lr": 4.9999984887169785e-05, "epoch": 0.26548672566371684, "percentage": 0.04, "elapsed_time": "0:00:09", "remaining_time": "6:44:01", "throughput": 995.81, "total_tokens": 9056}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.1975, "lr": 4.9999972164636506e-05, "epoch": 0.35398230088495575, "percentage": 0.05, "elapsed_time": "0:00:11", "remaining_time": "6:11:51", "throughput": 1133.91, "total_tokens": 12656}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.5269, "lr": 4.999995558679334e-05, "epoch": 0.4424778761061947, "percentage": 0.06, "elapsed_time": "0:00:13", "remaining_time": "5:52:25", "throughput": 1195.36, "total_tokens": 15808}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.3717, "lr": 4.999993515364287e-05, "epoch": 0.5309734513274337, "percentage": 0.07, "elapsed_time": "0:00:15", "remaining_time": "5:39:48", "throughput": 1196.12, "total_tokens": 18304}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.1708, "lr": 4.999991086518822e-05, "epoch": 0.6194690265486725, "percentage": 0.09, "elapsed_time": "0:00:17", "remaining_time": "5:30:35", "throughput": 1249.85, "total_tokens": 21712}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.1173, "lr": 4.999988272143315e-05, "epoch": 0.7079646017699115, "percentage": 0.1, "elapsed_time": "0:00:19", "remaining_time": "5:23:49", "throughput": 1263.65, "total_tokens": 24576}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.0917, "lr": 4.999985072238199e-05, "epoch": 0.7964601769911505, "percentage": 0.11, "elapsed_time": "0:00:21", "remaining_time": "5:18:32", "throughput": 1258.41, "total_tokens": 27088}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.2997, "lr": 4.999981486803969e-05, "epoch": 0.8849557522123894, "percentage": 0.12, "elapsed_time": "0:00:23", "remaining_time": "5:14:07", "throughput": 1256.84, "total_tokens": 29648}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.1974, "lr": 4.999977515841176e-05, "epoch": 0.9734513274336283, "percentage": 0.14, "elapsed_time": "0:00:25", "remaining_time": "5:10:23", "throughput": 1249.17, "total_tokens": 32032}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.0836, "lr": 4.9999731593504344e-05, "epoch": 1.0530973451327434, "percentage": 0.15, "elapsed_time": "0:00:27", "remaining_time": "5:09:15", "throughput": 1242.11, "total_tokens": 34624}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.0943, "lr": 4.999968417332415e-05, "epoch": 1.1415929203539823, "percentage": 0.16, "elapsed_time": "0:00:29", "remaining_time": "5:06:42", "throughput": 1255.33, "total_tokens": 37600}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.2222, "lr": 4.999963289787848e-05, "epoch": 1.2300884955752212, "percentage": 0.18, "elapsed_time": "0:00:32", "remaining_time": "5:04:28", "throughput": 1256.96, "total_tokens": 40256}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.1158, "lr": 4.999957776717526e-05, "epoch": 1.3185840707964602, "percentage": 0.19, "elapsed_time": "0:00:34", "remaining_time": "5:02:26", "throughput": 1274.34, "total_tokens": 43440}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.1155, "lr": 4.9999518781222984e-05, "epoch": 1.407079646017699, "percentage": 0.2, "elapsed_time": "0:00:36", "remaining_time": "5:00:38", "throughput": 1277.81, "total_tokens": 46192}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.1563, "lr": 4.9999455940030746e-05, "epoch": 1.495575221238938, "percentage": 0.21, "elapsed_time": "0:00:38", "remaining_time": "4:59:05", "throughput": 1291.62, "total_tokens": 49360}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.4079, "lr": 4.999938924360824e-05, "epoch": 1.584070796460177, "percentage": 0.22, "elapsed_time": "0:00:40", "remaining_time": "4:57:44", "throughput": 1286.82, "total_tokens": 51840}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.0457, "lr": 4.999931869196575e-05, "epoch": 1.672566371681416, "percentage": 0.24, "elapsed_time": "0:00:42", "remaining_time": "4:56:26", "throughput": 1297.98, "total_tokens": 54960}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.1414, "lr": 4.999924428511416e-05, "epoch": 1.7610619469026547, "percentage": 0.25, "elapsed_time": "0:00:44", "remaining_time": "4:55:16", "throughput": 1301.16, "total_tokens": 57776}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.1734, "lr": 4.999916602306494e-05, "epoch": 1.8495575221238938, "percentage": 0.26, "elapsed_time": "0:00:46", "remaining_time": "4:54:18", "throughput": 1304.42, "total_tokens": 60624}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.0351, "lr": 4.999908390583016e-05, "epoch": 1.9380530973451329, "percentage": 0.27, "elapsed_time": "0:00:48", "remaining_time": "4:53:18", "throughput": 1306.95, "total_tokens": 63424}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.1362, "lr": 4.999899793342247e-05, "epoch": 2.017699115044248, "percentage": 0.29, "elapsed_time": "0:00:50", "remaining_time": "4:53:30", "throughput": 1290.81, "total_tokens": 65544}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.0021, "lr": 4.999890810585516e-05, "epoch": 2.106194690265487, "percentage": 0.3, "elapsed_time": "0:00:52", "remaining_time": "4:52:42", "throughput": 1297.18, "total_tokens": 68552}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.1074, "lr": 4.999881442314206e-05, "epoch": 2.1946902654867255, "percentage": 0.31, "elapsed_time": "0:00:54", "remaining_time": "4:51:55", "throughput": 1297.77, "total_tokens": 71256}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.067, "lr": 4.9998716885297617e-05, "epoch": 2.2831858407079646, "percentage": 0.33, "elapsed_time": "0:00:56", "remaining_time": "4:51:11", "throughput": 1302.49, "total_tokens": 74200}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.2343, "lr": 4.999861549233688e-05, "epoch": 2.3716814159292037, "percentage": 0.34, "elapsed_time": "0:00:59", "remaining_time": "4:50:31", "throughput": 1299.26, "total_tokens": 76696}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.0737, "lr": 4.999851024427548e-05, "epoch": 2.4601769911504423, "percentage": 0.35, "elapsed_time": "0:01:01", "remaining_time": "4:49:58", "throughput": 1303.28, "total_tokens": 79640}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.1341, "lr": 4.999840114112965e-05, "epoch": 2.5486725663716814, "percentage": 0.36, "elapsed_time": "0:01:03", "remaining_time": "4:49:22", "throughput": 1308.15, "total_tokens": 82632}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.0808, "lr": 4.999828818291621e-05, "epoch": 2.6371681415929205, "percentage": 0.38, "elapsed_time": "0:01:05", "remaining_time": "4:48:49", "throughput": 1310.68, "total_tokens": 85496}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.0805, "lr": 4.999817136965259e-05, "epoch": 2.725663716814159, "percentage": 0.39, "elapsed_time": "0:01:07", "remaining_time": "4:48:17", "throughput": 1324.54, "total_tokens": 89128}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.0858, "lr": 4.9998050701356794e-05, "epoch": 2.814159292035398, "percentage": 0.4, "elapsed_time": "0:01:09", "remaining_time": "4:47:46", "throughput": 1328.92, "total_tokens": 92152}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.1289, "lr": 4.999792617804744e-05, "epoch": 2.9026548672566372, "percentage": 0.41, "elapsed_time": "0:01:11", "remaining_time": "4:47:18", "throughput": 1325.33, "total_tokens": 94632}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.1869, "lr": 4.9997797799743724e-05, "epoch": 2.991150442477876, "percentage": 0.43, "elapsed_time": "0:01:13", "remaining_time": "4:46:48", "throughput": 1328.06, "total_tokens": 97544}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.0076, "lr": 4.999766556646545e-05, "epoch": 3.0707964601769913, "percentage": 0.44, "elapsed_time": "0:01:15", "remaining_time": "4:47:13", "throughput": 1320.42, "total_tokens": 99992}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.0042, "lr": 4.9997529478232996e-05, "epoch": 3.15929203539823, "percentage": 0.45, "elapsed_time": "0:01:17", "remaining_time": "4:46:47", "throughput": 1321.91, "total_tokens": 102824}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.0253, "lr": 4.9997389535067365e-05, "epoch": 3.247787610619469, "percentage": 0.46, "elapsed_time": "0:01:19", "remaining_time": "4:46:23", "throughput": 1322.71, "total_tokens": 105608}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.0016, "lr": 4.999724573699012e-05, "epoch": 3.336283185840708, "percentage": 0.47, "elapsed_time": "0:01:21", "remaining_time": "4:45:59", "throughput": 1327.41, "total_tokens": 108712}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.067, "lr": 4.9997098084023457e-05, "epoch": 3.4247787610619467, "percentage": 0.49, "elapsed_time": "0:01:23", "remaining_time": "4:45:37", "throughput": 1329.42, "total_tokens": 111608}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.1231, "lr": 4.999694657619013e-05, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:01:26", "remaining_time": "4:45:15", "throughput": 1331.31, "total_tokens": 114504}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.29828834533691406, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:01:27", "remaining_time": "4:48:47", "throughput": 1315.05, "total_tokens": 114504}
42
+ {"current_steps": 205, "total_steps": 40000, "loss": 0.1848, "lr": 4.999679121351352e-05, "epoch": 3.601769911504425, "percentage": 0.51, "elapsed_time": "0:01:31", "remaining_time": "4:57:33", "throughput": 1278.59, "total_tokens": 117592}
43
+ {"current_steps": 210, "total_steps": 40000, "loss": 0.0779, "lr": 4.9996631996017565e-05, "epoch": 3.6902654867256635, "percentage": 0.53, "elapsed_time": "0:01:34", "remaining_time": "4:57:01", "throughput": 1278.12, "total_tokens": 120216}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:060a843037681b2113da7bfa0e5579298cb81ccd5a0feddbbd9a473f6fc69852
3
+ size 5752