Hugging Face's logo

ben81828
/
qwenvl-2B-cadica-direction-then-detect-and-classify-scale4

Safetensors
Model card Files Community
ben81828 commited on
Commit
3afa50a
·
verified ·
1 Parent(s): 4994c05

Training in progress, step 50

Browse files
Files changed (4) hide show
  1. adapter_config.json +1 -1
  2. adapter_model.safetensors +1 -1
  3. trainer_log.jsonl +11 -22
  4. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,7 +19,7 @@
19
  "r": 8,
20
  "rank_pattern": {},
21
  "revision": null,
22
- "target_modules": "^(?!.*patch_embed).*(?:q_proj|gate_proj|fc1|down_proj|v_proj|k_proj|o_proj|up_proj|fc2|proj|qkv).*",
23
  "task_type": "CAUSAL_LM",
24
  "use_dora": false,
25
  "use_rslora": false
 
19
  "r": 8,
20
  "rank_pattern": {},
21
  "revision": null,
22
+ "target_modules": "^(?!.*patch_embed).*(?:fc2|up_proj|fc1|proj|v_proj|o_proj|down_proj|qkv|q_proj|gate_proj|k_proj).*",
23
  "task_type": "CAUSAL_LM",
24
  "use_dora": false,
25
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd6565301e016283ab568872df6816af131f681b9f5c3f0a097d4f9d809b23f6
3
  size 29034840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfe67a44369497ba941790aaedb13a9e576b7a570ced2e459401c6bd22bed7b
3
  size 29034840
trainer_log.jsonl CHANGED
@@ -1,22 +1,11 @@
1
- {"current_steps": 5, "total_steps": 1200, "loss": 2.0085, "lr": 8.333333333333334e-06, "epoch": 0.0012876641771825909, "percentage": 0.42, "elapsed_time": "0:02:45", "remaining_time": "10:58:10", "throughput": 317.04, "total_tokens": 52384}
2
- {"current_steps": 10, "total_steps": 1200, "loss": 1.8139, "lr": 1.6666666666666667e-05, "epoch": 0.0025753283543651817, "percentage": 0.83, "elapsed_time": "0:04:12", "remaining_time": "8:20:47", "throughput": 414.0, "total_tokens": 104536}
3
- {"current_steps": 15, "total_steps": 1200, "loss": 1.9531, "lr": 2.5e-05, "epoch": 0.0038629925315477724, "percentage": 1.25, "elapsed_time": "0:05:38", "remaining_time": "7:26:14", "throughput": 463.53, "total_tokens": 157096}
4
- {"current_steps": 20, "total_steps": 1200, "loss": 1.6164, "lr": 3.3333333333333335e-05, "epoch": 0.0051506567087303634, "percentage": 1.67, "elapsed_time": "0:07:06", "remaining_time": "6:59:04", "throughput": 489.09, "total_tokens": 208440}
5
- {"current_steps": 25, "total_steps": 1200, "loss": 1.3548, "lr": 4.166666666666667e-05, "epoch": 0.006438320885912954, "percentage": 2.08, "elapsed_time": "0:08:32", "remaining_time": "6:41:21", "throughput": 507.48, "total_tokens": 260024}
6
- {"current_steps": 30, "total_steps": 1200, "loss": 1.0577, "lr": 5e-05, "epoch": 0.007725985063095545, "percentage": 2.5, "elapsed_time": "0:09:59", "remaining_time": "6:29:30", "throughput": 520.49, "total_tokens": 311896}
7
- {"current_steps": 35, "total_steps": 1200, "loss": 0.9109, "lr": 5.833333333333334e-05, "epoch": 0.009013649240278136, "percentage": 2.92, "elapsed_time": "0:11:25", "remaining_time": "6:20:09", "throughput": 531.16, "total_tokens": 363984}
8
- {"current_steps": 40, "total_steps": 1200, "loss": 0.8895, "lr": 6.666666666666667e-05, "epoch": 0.010301313417460727, "percentage": 3.33, "elapsed_time": "0:12:52", "remaining_time": "6:13:26", "throughput": 537.86, "total_tokens": 415560}
9
- {"current_steps": 45, "total_steps": 1200, "loss": 0.821, "lr": 7.500000000000001e-05, "epoch": 0.011588977594643318, "percentage": 3.75, "elapsed_time": "0:14:19", "remaining_time": "6:07:45", "throughput": 543.81, "total_tokens": 467512}
10
- {"current_steps": 50, "total_steps": 1200, "loss": 0.8276, "lr": 8.333333333333334e-05, "epoch": 0.012876641771825908, "percentage": 4.17, "elapsed_time": "0:15:47", "remaining_time": "6:03:06", "throughput": 547.64, "total_tokens": 518736}
11
- {"current_steps": 50, "total_steps": 1200, "eval_loss": 0.9254846572875977, "epoch": 0.012876641771825908, "percentage": 4.17, "elapsed_time": "0:16:34", "remaining_time": "6:21:22", "throughput": 521.39, "total_tokens": 518736}
12
- {"current_steps": 55, "total_steps": 1200, "loss": 0.8789, "lr": 9.166666666666667e-05, "epoch": 0.014164305949008499, "percentage": 4.58, "elapsed_time": "0:18:08", "remaining_time": "6:17:45", "throughput": 523.55, "total_tokens": 570016}
13
- {"current_steps": 60, "total_steps": 1200, "loss": 0.8889, "lr": 0.0001, "epoch": 0.01545197012619109, "percentage": 5.0, "elapsed_time": "0:19:35", "remaining_time": "6:12:17", "throughput": 528.28, "total_tokens": 621088}
14
- {"current_steps": 65, "total_steps": 1200, "loss": 0.8255, "lr": 9.999525361252996e-05, "epoch": 0.01673963430337368, "percentage": 5.42, "elapsed_time": "0:21:01", "remaining_time": "6:07:09", "throughput": 533.33, "total_tokens": 672848}
15
- {"current_steps": 70, "total_steps": 1200, "loss": 0.8785, "lr": 9.998101535124758e-05, "epoch": 0.018027298480556272, "percentage": 5.83, "elapsed_time": "0:22:29", "remaining_time": "6:02:59", "throughput": 537.79, "total_tokens": 725568}
16
- {"current_steps": 75, "total_steps": 1200, "loss": 0.8808, "lr": 9.995728791936504e-05, "epoch": 0.01931496265773886, "percentage": 6.25, "elapsed_time": "0:23:55", "remaining_time": "5:58:53", "throughput": 541.54, "total_tokens": 777408}
17
- {"current_steps": 80, "total_steps": 1200, "loss": 0.7951, "lr": 9.992407582166581e-05, "epoch": 0.020602626834921454, "percentage": 6.67, "elapsed_time": "0:25:23", "remaining_time": "5:55:35", "throughput": 543.84, "total_tokens": 828784}
18
- {"current_steps": 85, "total_steps": 1200, "loss": 0.7978, "lr": 9.988138536364922e-05, "epoch": 0.021890291012104043, "percentage": 7.08, "elapsed_time": "0:26:50", "remaining_time": "5:52:03", "throughput": 546.55, "total_tokens": 880120}
19
- {"current_steps": 90, "total_steps": 1200, "loss": 0.8476, "lr": 9.98292246503335e-05, "epoch": 0.023177955189286635, "percentage": 7.5, "elapsed_time": "0:28:18", "remaining_time": "5:49:02", "throughput": 549.41, "total_tokens": 932904}
20
- {"current_steps": 95, "total_steps": 1200, "loss": 0.8286, "lr": 9.976760358471686e-05, "epoch": 0.024465619366469224, "percentage": 7.92, "elapsed_time": "0:29:46", "remaining_time": "5:46:16", "throughput": 551.87, "total_tokens": 985768}
21
- {"current_steps": 100, "total_steps": 1200, "loss": 0.8442, "lr": 9.969653386589748e-05, "epoch": 0.025753283543651816, "percentage": 8.33, "elapsed_time": "0:31:14", "remaining_time": "5:43:43", "throughput": 553.69, "total_tokens": 1038064}
22
- {"current_steps": 100, "total_steps": 1200, "eval_loss": 0.9066702723503113, "epoch": 0.025753283543651816, "percentage": 8.33, "elapsed_time": "0:31:34", "remaining_time": "5:47:16", "throughput": 548.02, "total_tokens": 1038064}
 
1
+ {"current_steps": 5, "total_steps": 1200, "loss": 1.9514, "lr": 8.333333333333334e-06, "epoch": 0.0022172949002217295, "percentage": 0.42, "elapsed_time": "0:02:46", "remaining_time": "11:01:57", "throughput": 316.43, "total_tokens": 52584}
2
+ {"current_steps": 10, "total_steps": 1200, "loss": 1.8884, "lr": 1.6666666666666667e-05, "epoch": 0.004434589800443459, "percentage": 0.83, "elapsed_time": "0:04:14", "remaining_time": "8:25:17", "throughput": 412.9, "total_tokens": 105192}
3
+ {"current_steps": 15, "total_steps": 1200, "loss": 1.8391, "lr": 2.5e-05, "epoch": 0.0066518847006651885, "percentage": 1.25, "elapsed_time": "0:05:42", "remaining_time": "7:30:40", "throughput": 460.93, "total_tokens": 157768}
4
+ {"current_steps": 20, "total_steps": 1200, "loss": 1.6078, "lr": 3.3333333333333335e-05, "epoch": 0.008869179600886918, "percentage": 1.67, "elapsed_time": "0:07:10", "remaining_time": "7:02:57", "throughput": 487.8, "total_tokens": 209816}
5
+ {"current_steps": 25, "total_steps": 1200, "loss": 1.3229, "lr": 4.166666666666667e-05, "epoch": 0.011086474501108648, "percentage": 2.08, "elapsed_time": "0:08:37", "remaining_time": "6:45:31", "throughput": 506.27, "total_tokens": 262088}
6
+ {"current_steps": 30, "total_steps": 1200, "loss": 1.0884, "lr": 5e-05, "epoch": 0.013303769401330377, "percentage": 2.5, "elapsed_time": "0:10:06", "remaining_time": "6:34:27", "throughput": 518.19, "total_tokens": 314464}
7
+ {"current_steps": 35, "total_steps": 1200, "loss": 0.9507, "lr": 5.833333333333334e-05, "epoch": 0.015521064301552107, "percentage": 2.92, "elapsed_time": "0:11:34", "remaining_time": "6:25:26", "throughput": 526.45, "total_tokens": 365768}
8
+ {"current_steps": 40, "total_steps": 1200, "loss": 0.8783, "lr": 6.666666666666667e-05, "epoch": 0.017738359201773836, "percentage": 3.33, "elapsed_time": "0:13:04", "remaining_time": "6:19:03", "throughput": 533.93, "total_tokens": 418744}
9
+ {"current_steps": 45, "total_steps": 1200, "loss": 0.8569, "lr": 7.500000000000001e-05, "epoch": 0.019955654101995565, "percentage": 3.75, "elapsed_time": "0:14:33", "remaining_time": "6:13:37", "throughput": 538.33, "total_tokens": 470176}
10
+ {"current_steps": 50, "total_steps": 1200, "loss": 0.8773, "lr": 8.333333333333334e-05, "epoch": 0.022172949002217297, "percentage": 4.17, "elapsed_time": "0:16:03", "remaining_time": "6:09:11", "throughput": 542.0, "total_tokens": 521992}
11
+ {"current_steps": 50, "total_steps": 1200, "eval_loss": 0.889969527721405, "epoch": 0.022172949002217297, "percentage": 4.17, "elapsed_time": "0:16:50", "remaining_time": "6:27:28", "throughput": 516.41, "total_tokens": 521992}
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac9d5c3e742f606d404f06b81343ea32100e49e7c82d2f615862965bded76d9c
3
  size 7416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62f3bc0acf4a5ff06124e1142d4e1cd2e75957edd7e732d13672ddea11c551bd
3
  size 7416