Hugging Face's logo

rbelanec
/
train_mnli_1744891313

Safetensors
Model card Files
xet
 Community
rbelanec commited on
Commit
2f79816
·
verified ·
1 Parent(s): adb75a8

Training in progress, step 200

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. adapter_config.json +18 -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 +41 -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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "google/gemma-3-1b-it",
4
+ "exclude_modules": null,
5
+ "fan_in_fan_out": false,
6
+ "feedforward_modules": "down_proj",
7
+ "inference_mode": true,
8
+ "init_ia3_weights": true,
9
+ "modules_to_save": null,
10
+ "peft_type": "IA3",
11
+ "revision": null,
12
+ "target_modules": [
13
+ "down_proj",
14
+ "k_proj",
15
+ "v_proj"
16
+ ],
17
+ "task_type": "CAUSAL_LM"
18
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f9f8865136c671903afaeeb876a02782184ca99f70d384155fb8f7d63472a4
3
+ size 182352
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 20000, "loss": 5.1835, "lr": 4.9999995065197964e-05, "epoch": 0.0009054075465719007, "percentage": 0.03, "elapsed_time": "0:00:08", "remaining_time": "9:05:32", "throughput": 4675.81, "total_tokens": 38272}
2
+ {"current_steps": 10, "total_steps": 20000, "loss": 5.4678, "lr": 4.9999975017568026e-05, "epoch": 0.0018108150931438014, "percentage": 0.05, "elapsed_time": "0:00:15", "remaining_time": "8:21:46", "throughput": 4823.06, "total_tokens": 72640}
3
+ {"current_steps": 15, "total_steps": 20000, "loss": 5.306, "lr": 4.999993954869741e-05, "epoch": 0.002716222639715702, "percentage": 0.07, "elapsed_time": "0:00:21", "remaining_time": "8:06:35", "throughput": 4848.25, "total_tokens": 106240}
4
+ {"current_steps": 20, "total_steps": 20000, "loss": 5.3055, "lr": 4.9999888658608e-05, "epoch": 0.0036216301862876028, "percentage": 0.1, "elapsed_time": "0:00:28", "remaining_time": "7:58:49", "throughput": 4862.52, "total_tokens": 139840}
5
+ {"current_steps": 25, "total_steps": 20000, "loss": 5.4678, "lr": 4.999982234733118e-05, "epoch": 0.004527037732859503, "percentage": 0.12, "elapsed_time": "0:00:35", "remaining_time": "7:54:21", "throughput": 4931.78, "total_tokens": 175680}
6
+ {"current_steps": 30, "total_steps": 20000, "loss": 5.3684, "lr": 4.9999740614907876e-05, "epoch": 0.005432445279431404, "percentage": 0.15, "elapsed_time": "0:00:42", "remaining_time": "7:51:07", "throughput": 4950.95, "total_tokens": 210240}
7
+ {"current_steps": 35, "total_steps": 20000, "loss": 5.2575, "lr": 4.999964346138848e-05, "epoch": 0.0063378528260033045, "percentage": 0.18, "elapsed_time": "0:00:49", "remaining_time": "7:48:48", "throughput": 4959.18, "total_tokens": 244544}
8
+ {"current_steps": 40, "total_steps": 20000, "loss": 5.1128, "lr": 4.9999530886832935e-05, "epoch": 0.0072432603725752056, "percentage": 0.2, "elapsed_time": "0:00:56", "remaining_time": "7:47:21", "throughput": 5019.09, "total_tokens": 282048}
9
+ {"current_steps": 45, "total_steps": 20000, "loss": 4.9499, "lr": 4.999940289131067e-05, "epoch": 0.008148667919147106, "percentage": 0.22, "elapsed_time": "0:01:03", "remaining_time": "7:46:00", "throughput": 5052.71, "total_tokens": 318592}
10
+ {"current_steps": 50, "total_steps": 20000, "loss": 4.0645, "lr": 4.999925947490066e-05, "epoch": 0.009054075465719007, "percentage": 0.25, "elapsed_time": "0:01:09", "remaining_time": "7:44:49", "throughput": 5062.44, "total_tokens": 353856}
11
+ {"current_steps": 55, "total_steps": 20000, "loss": 3.3731, "lr": 4.999910063769136e-05, "epoch": 0.009959483012290908, "percentage": 0.27, "elapsed_time": "0:01:16", "remaining_time": "7:44:23", "throughput": 5125.93, "total_tokens": 393856}
12
+ {"current_steps": 60, "total_steps": 20000, "loss": 2.7362, "lr": 4.999892637978074e-05, "epoch": 0.010864890558862809, "percentage": 0.3, "elapsed_time": "0:01:23", "remaining_time": "7:43:25", "throughput": 5105.95, "total_tokens": 427200}
13
+ {"current_steps": 65, "total_steps": 20000, "loss": 1.8721, "lr": 4.9998736701276295e-05, "epoch": 0.011770298105434708, "percentage": 0.33, "elapsed_time": "0:01:30", "remaining_time": "7:42:41", "throughput": 5112.59, "total_tokens": 462784}
14
+ {"current_steps": 70, "total_steps": 20000, "loss": 1.6229, "lr": 4.999853160229504e-05, "epoch": 0.012675705652006609, "percentage": 0.35, "elapsed_time": "0:01:37", "remaining_time": "7:41:59", "throughput": 5105.73, "total_tokens": 497088}
15
+ {"current_steps": 75, "total_steps": 20000, "loss": 1.4611, "lr": 4.999831108296348e-05, "epoch": 0.01358111319857851, "percentage": 0.38, "elapsed_time": "0:01:44", "remaining_time": "7:41:19", "throughput": 5115.59, "total_tokens": 532992}
16
+ {"current_steps": 80, "total_steps": 20000, "loss": 1.3821, "lr": 4.999807514341764e-05, "epoch": 0.014486520745150411, "percentage": 0.4, "elapsed_time": "0:01:51", "remaining_time": "7:40:46", "throughput": 5099.62, "total_tokens": 566208}
17
+ {"current_steps": 85, "total_steps": 20000, "loss": 1.2037, "lr": 4.999782378380308e-05, "epoch": 0.015391928291722312, "percentage": 0.43, "elapsed_time": "0:01:57", "remaining_time": "7:40:16", "throughput": 5091.36, "total_tokens": 600128}
18
+ {"current_steps": 90, "total_steps": 20000, "loss": 1.1433, "lr": 4.999755700427482e-05, "epoch": 0.01629733583829421, "percentage": 0.45, "elapsed_time": "0:02:04", "remaining_time": "7:39:49", "throughput": 5091.2, "total_tokens": 634944}
19
+ {"current_steps": 95, "total_steps": 20000, "loss": 1.0306, "lr": 4.999727480499744e-05, "epoch": 0.017202743384866114, "percentage": 0.47, "elapsed_time": "0:02:11", "remaining_time": "7:39:24", "throughput": 5104.27, "total_tokens": 671488}
20
+ {"current_steps": 100, "total_steps": 20000, "loss": 1.0367, "lr": 4.9996977186145024e-05, "epoch": 0.018108150931438013, "percentage": 0.5, "elapsed_time": "0:02:18", "remaining_time": "7:39:02", "throughput": 5104.04, "total_tokens": 706432}
21
+ {"current_steps": 105, "total_steps": 20000, "loss": 1.0485, "lr": 4.999666414790113e-05, "epoch": 0.019013558478009913, "percentage": 0.53, "elapsed_time": "0:02:25", "remaining_time": "7:38:41", "throughput": 5112.45, "total_tokens": 742592}
22
+ {"current_steps": 110, "total_steps": 20000, "loss": 1.0926, "lr": 4.999633569045889e-05, "epoch": 0.019918966024581816, "percentage": 0.55, "elapsed_time": "0:02:32", "remaining_time": "7:38:22", "throughput": 5109.92, "total_tokens": 777216}
23
+ {"current_steps": 115, "total_steps": 20000, "loss": 1.1801, "lr": 4.9995991814020884e-05, "epoch": 0.020824373571153715, "percentage": 0.57, "elapsed_time": "0:02:38", "remaining_time": "7:38:06", "throughput": 5123.68, "total_tokens": 814464}
24
+ {"current_steps": 120, "total_steps": 20000, "loss": 1.1455, "lr": 4.999563251879925e-05, "epoch": 0.021729781117725618, "percentage": 0.6, "elapsed_time": "0:02:45", "remaining_time": "7:37:49", "throughput": 5124.23, "total_tokens": 849664}
25
+ {"current_steps": 125, "total_steps": 20000, "loss": 1.0672, "lr": 4.9995257805015615e-05, "epoch": 0.022635188664297517, "percentage": 0.62, "elapsed_time": "0:02:52", "remaining_time": "7:37:38", "throughput": 5129.39, "total_tokens": 885824}
26
+ {"current_steps": 130, "total_steps": 20000, "loss": 1.0501, "lr": 4.999486767290112e-05, "epoch": 0.023540596210869416, "percentage": 0.65, "elapsed_time": "0:02:59", "remaining_time": "7:37:21", "throughput": 5136.34, "total_tokens": 922176}
27
+ {"current_steps": 135, "total_steps": 20000, "loss": 0.9761, "lr": 4.9994462122696415e-05, "epoch": 0.02444600375744132, "percentage": 0.68, "elapsed_time": "0:03:06", "remaining_time": "7:37:09", "throughput": 5140.01, "total_tokens": 958144}
28
+ {"current_steps": 140, "total_steps": 20000, "loss": 0.9137, "lr": 4.999404115465167e-05, "epoch": 0.025351411304013218, "percentage": 0.7, "elapsed_time": "0:03:13", "remaining_time": "7:36:51", "throughput": 5139.65, "total_tokens": 993152}
29
+ {"current_steps": 145, "total_steps": 20000, "loss": 0.7404, "lr": 4.999360476902656e-05, "epoch": 0.02625681885058512, "percentage": 0.73, "elapsed_time": "0:03:20", "remaining_time": "7:36:36", "throughput": 5140.41, "total_tokens": 1028480}
30
+ {"current_steps": 150, "total_steps": 20000, "loss": 0.9735, "lr": 4.999315296609026e-05, "epoch": 0.02716222639715702, "percentage": 0.75, "elapsed_time": "0:03:26", "remaining_time": "7:36:22", "throughput": 5138.66, "total_tokens": 1063296}
31
+ {"current_steps": 155, "total_steps": 20000, "loss": 0.9283, "lr": 4.999268574612147e-05, "epoch": 0.02806763394372892, "percentage": 0.78, "elapsed_time": "0:03:33", "remaining_time": "7:36:08", "throughput": 5134.06, "total_tokens": 1097472}
32
+ {"current_steps": 160, "total_steps": 20000, "loss": 0.8704, "lr": 4.99922031094084e-05, "epoch": 0.028973041490300822, "percentage": 0.8, "elapsed_time": "0:03:40", "remaining_time": "7:35:54", "throughput": 5134.23, "total_tokens": 1132608}
33
+ {"current_steps": 165, "total_steps": 20000, "loss": 0.8308, "lr": 4.999170505624875e-05, "epoch": 0.02987844903687272, "percentage": 0.83, "elapsed_time": "0:03:47", "remaining_time": "7:35:42", "throughput": 5137.33, "total_tokens": 1168512}
34
+ {"current_steps": 170, "total_steps": 20000, "loss": 0.8229, "lr": 4.999119158694977e-05, "epoch": 0.030783856583444624, "percentage": 0.85, "elapsed_time": "0:03:54", "remaining_time": "7:35:31", "throughput": 5140.3, "total_tokens": 1204416}
35
+ {"current_steps": 175, "total_steps": 20000, "loss": 0.7555, "lr": 4.999066270182817e-05, "epoch": 0.03168926413001653, "percentage": 0.88, "elapsed_time": "0:04:01", "remaining_time": "7:35:18", "throughput": 5138.64, "total_tokens": 1239168}
36
+ {"current_steps": 180, "total_steps": 20000, "loss": 0.933, "lr": 4.99901184012102e-05, "epoch": 0.03259467167658842, "percentage": 0.9, "elapsed_time": "0:04:07", "remaining_time": "7:35:03", "throughput": 5135.68, "total_tokens": 1273472}
37
+ {"current_steps": 185, "total_steps": 20000, "loss": 0.8469, "lr": 4.998955868543161e-05, "epoch": 0.033500079223160326, "percentage": 0.92, "elapsed_time": "0:04:14", "remaining_time": "7:34:52", "throughput": 5139.35, "total_tokens": 1309568}
38
+ {"current_steps": 190, "total_steps": 20000, "loss": 0.6934, "lr": 4.998898355483766e-05, "epoch": 0.03440548676973223, "percentage": 0.95, "elapsed_time": "0:04:21", "remaining_time": "7:34:39", "throughput": 5139.53, "total_tokens": 1344704}
39
+ {"current_steps": 195, "total_steps": 20000, "loss": 0.6844, "lr": 4.998839300978313e-05, "epoch": 0.035310894316304124, "percentage": 0.97, "elapsed_time": "0:04:28", "remaining_time": "7:34:26", "throughput": 5142.02, "total_tokens": 1380480}
40
+ {"current_steps": 200, "total_steps": 20000, "loss": 0.8344, "lr": 4.998778705063229e-05, "epoch": 0.03621630186287603, "percentage": 1.0, "elapsed_time": "0:04:35", "remaining_time": "7:34:16", "throughput": 5147.01, "total_tokens": 1417088}
41
+ {"current_steps": 200, "total_steps": 20000, "eval_loss": 0.6978357434272766, "epoch": 0.03621630186287603, "percentage": 1.0, "elapsed_time": "0:08:46", "remaining_time": "14:29:24", "throughput": 2689.42, "total_tokens": 1417088}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a60a677971a931020fadf2062811a4a03b4797cac7d6e541dce9051a9939a4
3
+ size 5752