Hugging Face's logo

rbelanec
/
train_multirc_1745950261

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files
xet
Community
rbelanec commited on
Commit
eeaa98a
路
verified 路
1 Parent(s): a6122bb

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
+ "v_proj",
28
+ "k_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:ef4b3d3242aa83013e24e0594ff157e70599ef5a63640753668f5ffed566758e
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": 2.4052, "lr": 4.999999876629946e-05, "epoch": 0.0008157272208173587, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "7:12:09", "throughput": 2448.19, "total_tokens": 7936}
2
+ {"current_steps": 10, "total_steps": 40000, "loss": 1.3686, "lr": 4.999999375439123e-05, "epoch": 0.0016314544416347174, "percentage": 0.03, "elapsed_time": "0:00:05", "remaining_time": "5:55:40", "throughput": 3202.11, "total_tokens": 17088}
3
+ {"current_steps": 15, "total_steps": 40000, "loss": 0.7674, "lr": 4.9999984887169785e-05, "epoch": 0.002447181662452076, "percentage": 0.04, "elapsed_time": "0:00:07", "remaining_time": "5:29:48", "throughput": 3633.94, "total_tokens": 26976}
4
+ {"current_steps": 20, "total_steps": 40000, "loss": 0.5275, "lr": 4.9999972164636506e-05, "epoch": 0.0032629088832694347, "percentage": 0.05, "elapsed_time": "0:00:09", "remaining_time": "5:16:13", "throughput": 3954.65, "total_tokens": 37536}
5
+ {"current_steps": 25, "total_steps": 40000, "loss": 0.5193, "lr": 4.999995558679334e-05, "epoch": 0.004078636104086793, "percentage": 0.06, "elapsed_time": "0:00:11", "remaining_time": "5:07:58", "throughput": 3999.87, "total_tokens": 46224}
6
+ {"current_steps": 30, "total_steps": 40000, "loss": 0.4229, "lr": 4.999993515364287e-05, "epoch": 0.004894363324904152, "percentage": 0.07, "elapsed_time": "0:00:13", "remaining_time": "5:02:34", "throughput": 4108.51, "total_tokens": 55984}
7
+ {"current_steps": 35, "total_steps": 40000, "loss": 0.2686, "lr": 4.999991086518822e-05, "epoch": 0.005710090545721511, "percentage": 0.09, "elapsed_time": "0:00:15", "remaining_time": "4:59:09", "throughput": 4195.61, "total_tokens": 65952}
8
+ {"current_steps": 40, "total_steps": 40000, "loss": 0.3117, "lr": 4.999988272143315e-05, "epoch": 0.0065258177665388694, "percentage": 0.1, "elapsed_time": "0:00:17", "remaining_time": "4:56:06", "throughput": 4287.74, "total_tokens": 76256}
9
+ {"current_steps": 45, "total_steps": 40000, "loss": 0.2426, "lr": 4.999985072238199e-05, "epoch": 0.007341544987356228, "percentage": 0.11, "elapsed_time": "0:00:19", "remaining_time": "4:53:47", "throughput": 4335.91, "total_tokens": 86080}
10
+ {"current_steps": 50, "total_steps": 40000, "loss": 0.2255, "lr": 4.999981486803969e-05, "epoch": 0.008157272208173586, "percentage": 0.12, "elapsed_time": "0:00:21", "remaining_time": "4:51:48", "throughput": 4405.01, "total_tokens": 96528}
11
+ {"current_steps": 55, "total_steps": 40000, "loss": 0.1462, "lr": 4.999977515841176e-05, "epoch": 0.008972999428990946, "percentage": 0.14, "elapsed_time": "0:00:23", "remaining_time": "4:50:14", "throughput": 4426.75, "total_tokens": 106144}
12
+ {"current_steps": 60, "total_steps": 40000, "loss": 0.2708, "lr": 4.9999731593504344e-05, "epoch": 0.009788726649808304, "percentage": 0.15, "elapsed_time": "0:00:26", "remaining_time": "4:48:53", "throughput": 4423.35, "total_tokens": 115184}
13
+ {"current_steps": 65, "total_steps": 40000, "loss": 0.1493, "lr": 4.999968417332415e-05, "epoch": 0.010604453870625663, "percentage": 0.16, "elapsed_time": "0:00:28", "remaining_time": "4:47:44", "throughput": 4416.18, "total_tokens": 124096}
14
+ {"current_steps": 70, "total_steps": 40000, "loss": 0.161, "lr": 4.999963289787848e-05, "epoch": 0.011420181091443021, "percentage": 0.18, "elapsed_time": "0:00:30", "remaining_time": "4:46:55", "throughput": 4416.23, "total_tokens": 133280}
15
+ {"current_steps": 75, "total_steps": 40000, "loss": 0.2371, "lr": 4.999957776717526e-05, "epoch": 0.012235908312260381, "percentage": 0.19, "elapsed_time": "0:00:32", "remaining_time": "4:46:05", "throughput": 4436.82, "total_tokens": 143072}
16
+ {"current_steps": 80, "total_steps": 40000, "loss": 0.4047, "lr": 4.9999518781222984e-05, "epoch": 0.013051635533077739, "percentage": 0.2, "elapsed_time": "0:00:34", "remaining_time": "4:45:20", "throughput": 4424.75, "total_tokens": 151808}
17
+ {"current_steps": 85, "total_steps": 40000, "loss": 0.1763, "lr": 4.9999455940030746e-05, "epoch": 0.013867362753895097, "percentage": 0.21, "elapsed_time": "0:00:36", "remaining_time": "4:44:38", "throughput": 4431.8, "total_tokens": 161184}
18
+ {"current_steps": 90, "total_steps": 40000, "loss": 0.1932, "lr": 4.999938924360824e-05, "epoch": 0.014683089974712456, "percentage": 0.22, "elapsed_time": "0:00:38", "remaining_time": "4:44:02", "throughput": 4458.04, "total_tokens": 171328}
19
+ {"current_steps": 95, "total_steps": 40000, "loss": 0.3198, "lr": 4.999931869196575e-05, "epoch": 0.015498817195529814, "percentage": 0.24, "elapsed_time": "0:00:40", "remaining_time": "4:43:32", "throughput": 4451.88, "total_tokens": 180304}
20
+ {"current_steps": 100, "total_steps": 40000, "loss": 0.2359, "lr": 4.999924428511416e-05, "epoch": 0.016314544416347172, "percentage": 0.25, "elapsed_time": "0:00:42", "remaining_time": "4:43:01", "throughput": 4488.44, "total_tokens": 191024}
21
+ {"current_steps": 105, "total_steps": 40000, "loss": 0.2293, "lr": 4.999916602306494e-05, "epoch": 0.017130271637164532, "percentage": 0.26, "elapsed_time": "0:00:44", "remaining_time": "4:42:40", "throughput": 4504.02, "total_tokens": 201056}
22
+ {"current_steps": 110, "total_steps": 40000, "loss": 0.2658, "lr": 4.999908390583016e-05, "epoch": 0.01794599885798189, "percentage": 0.27, "elapsed_time": "0:00:46", "remaining_time": "4:42:26", "throughput": 4532.53, "total_tokens": 211808}
23
+ {"current_steps": 115, "total_steps": 40000, "loss": 0.1653, "lr": 4.999899793342247e-05, "epoch": 0.01876172607879925, "percentage": 0.29, "elapsed_time": "0:00:48", "remaining_time": "4:42:05", "throughput": 4510.74, "total_tokens": 220128}
24
+ {"current_steps": 120, "total_steps": 40000, "loss": 0.2473, "lr": 4.999890810585516e-05, "epoch": 0.019577453299616607, "percentage": 0.3, "elapsed_time": "0:00:50", "remaining_time": "4:41:43", "throughput": 4507.4, "total_tokens": 229264}
25
+ {"current_steps": 125, "total_steps": 40000, "loss": 0.2832, "lr": 4.999881442314206e-05, "epoch": 0.020393180520433967, "percentage": 0.31, "elapsed_time": "0:00:52", "remaining_time": "4:41:23", "throughput": 4517.9, "total_tokens": 239120}
26
+ {"current_steps": 130, "total_steps": 40000, "loss": 0.1388, "lr": 4.9998716885297617e-05, "epoch": 0.021208907741251327, "percentage": 0.33, "elapsed_time": "0:00:54", "remaining_time": "4:41:07", "throughput": 4521.3, "total_tokens": 248656}
27
+ {"current_steps": 135, "total_steps": 40000, "loss": 0.1793, "lr": 4.999861549233688e-05, "epoch": 0.022024634962068683, "percentage": 0.34, "elapsed_time": "0:00:57", "remaining_time": "4:40:49", "throughput": 4536.5, "total_tokens": 258848}
28
+ {"current_steps": 140, "total_steps": 40000, "loss": 0.1571, "lr": 4.999851024427548e-05, "epoch": 0.022840362182886043, "percentage": 0.35, "elapsed_time": "0:00:59", "remaining_time": "4:40:33", "throughput": 4531.67, "total_tokens": 267936}
29
+ {"current_steps": 145, "total_steps": 40000, "loss": 0.2039, "lr": 4.999840114112965e-05, "epoch": 0.023656089403703402, "percentage": 0.36, "elapsed_time": "0:01:01", "remaining_time": "4:40:20", "throughput": 4533.94, "total_tokens": 277456}
30
+ {"current_steps": 150, "total_steps": 40000, "loss": 0.2658, "lr": 4.999828818291621e-05, "epoch": 0.024471816624520762, "percentage": 0.38, "elapsed_time": "0:01:03", "remaining_time": "4:40:05", "throughput": 4529.74, "total_tokens": 286544}
31
+ {"current_steps": 155, "total_steps": 40000, "loss": 0.2373, "lr": 4.999817136965259e-05, "epoch": 0.025287543845338118, "percentage": 0.39, "elapsed_time": "0:01:05", "remaining_time": "4:39:51", "throughput": 4550.18, "total_tokens": 297216}
32
+ {"current_steps": 160, "total_steps": 40000, "loss": 0.2183, "lr": 4.9998050701356794e-05, "epoch": 0.026103271066155478, "percentage": 0.4, "elapsed_time": "0:01:07", "remaining_time": "4:39:37", "throughput": 4563.23, "total_tokens": 307472}
33
+ {"current_steps": 165, "total_steps": 40000, "loss": 0.1058, "lr": 4.999792617804744e-05, "epoch": 0.026918998286972837, "percentage": 0.41, "elapsed_time": "0:01:09", "remaining_time": "4:39:24", "throughput": 4579.31, "total_tokens": 317984}
34
+ {"current_steps": 170, "total_steps": 40000, "loss": 0.3465, "lr": 4.9997797799743724e-05, "epoch": 0.027734725507790194, "percentage": 0.43, "elapsed_time": "0:01:11", "remaining_time": "4:39:10", "throughput": 4591.23, "total_tokens": 328240}
35
+ {"current_steps": 175, "total_steps": 40000, "loss": 0.1936, "lr": 4.999766556646545e-05, "epoch": 0.028550452728607553, "percentage": 0.44, "elapsed_time": "0:01:13", "remaining_time": "4:38:58", "throughput": 4579.55, "total_tokens": 336848}
36
+ {"current_steps": 180, "total_steps": 40000, "loss": 0.143, "lr": 4.9997529478232996e-05, "epoch": 0.029366179949424913, "percentage": 0.45, "elapsed_time": "0:01:15", "remaining_time": "4:38:51", "throughput": 4578.86, "total_tokens": 346304}
37
+ {"current_steps": 185, "total_steps": 40000, "loss": 0.2509, "lr": 4.9997389535067365e-05, "epoch": 0.030181907170242273, "percentage": 0.46, "elapsed_time": "0:01:17", "remaining_time": "4:38:38", "throughput": 4584.74, "total_tokens": 356160}
38
+ {"current_steps": 190, "total_steps": 40000, "loss": 0.2983, "lr": 4.999724573699012e-05, "epoch": 0.03099763439105963, "percentage": 0.47, "elapsed_time": "0:01:19", "remaining_time": "4:38:28", "throughput": 4583.39, "total_tokens": 365488}
39
+ {"current_steps": 195, "total_steps": 40000, "loss": 0.0909, "lr": 4.9997098084023457e-05, "epoch": 0.031813361611876985, "percentage": 0.49, "elapsed_time": "0:01:21", "remaining_time": "4:38:17", "throughput": 4591.73, "total_tokens": 375600}
40
+ {"current_steps": 200, "total_steps": 40000, "loss": 0.08, "lr": 4.999694657619013e-05, "epoch": 0.032629088832694345, "percentage": 0.5, "elapsed_time": "0:01:23", "remaining_time": "4:38:07", "throughput": 4592.22, "total_tokens": 385088}
41
+ {"current_steps": 200, "total_steps": 40000, "eval_loss": 0.2234242558479309, "epoch": 0.032629088832694345, "percentage": 0.5, "elapsed_time": "0:02:44", "remaining_time": "9:04:54", "throughput": 2343.88, "total_tokens": 385088}
42
+ {"current_steps": 205, "total_steps": 40000, "loss": 0.2614, "lr": 4.999679121351352e-05, "epoch": 0.033444816053511704, "percentage": 0.51, "elapsed_time": "0:02:47", "remaining_time": "9:02:58", "throughput": 2354.68, "total_tokens": 395168}
43
+ {"current_steps": 210, "total_steps": 40000, "loss": 0.1616, "lr": 4.9996631996017565e-05, "epoch": 0.034260543274329064, "percentage": 0.53, "elapsed_time": "0:02:49", "remaining_time": "8:56:47", "throughput": 2388.56, "total_tokens": 406016}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640658123913d416968d3068c8acbf6cbfed91bdc8dc566976ba41522190c176
3
+ size 5752