Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta2_0.999

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
ff891e3
·
verified ·
1 Parent(s): 2b6e754

Training in progress, epoch 1

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +44 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3974a7495294b1a587f561380085e39911a32a8ba4ecaa2260c1bc9d65ebd55f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a3a6f274e8e78830e220a706dfb087ac7d768e2c4d5d6b7db49c9d2cc681cd
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d32ffd533b21571e03ca787d986862a2b947698f285b607a86974c1c696c6203
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56db0fe160f49d43c8a537d938e848793028eba10a70dd57a51a81875e7e759e
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f4b789726bb5917c3f5144df97ae1210013deb05bb8c792fa187872c39499fc
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9358194c8aeb5118bf43e18ad105096333fd90e1e889eefd037288edc623bb
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03254866092eea668e015971f861c4cf46e0e2cdc07716ff3874f3ce3f837759
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adfd2f41cdebce52a2ed45f1c81072660d8d4e45fd37d9e74f32526a2a50671e
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -43,3 +43,47 @@
43
  {"current_steps": 430, "total_steps": 1314, "loss": 0.6344, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:16:19", "remaining_time": "12:53:38"}
44
  {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6250933408737183, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:31:10", "remaining_time": "13:02:21"}
45
  {"current_steps": 440, "total_steps": 1314, "loss": 0.6472, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:33:36", "remaining_time": "13:01:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  {"current_steps": 430, "total_steps": 1314, "loss": 0.6344, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:16:19", "remaining_time": "12:53:38"}
44
  {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6250933408737183, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:31:10", "remaining_time": "13:02:21"}
45
  {"current_steps": 440, "total_steps": 1314, "loss": 0.6472, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:33:36", "remaining_time": "13:01:50"}
46
+ {"current_steps": 450, "total_steps": 1314, "loss": 0.6016, "learning_rate": 5e-06, "epoch": 1.0262108262108263, "percentage": 34.25, "elapsed_time": "6:42:22", "remaining_time": "12:52:32"}
47
+ {"current_steps": 460, "total_steps": 1314, "loss": 0.5954, "learning_rate": 5e-06, "epoch": 1.049002849002849, "percentage": 35.01, "elapsed_time": "6:51:06", "remaining_time": "12:43:14"}
48
+ {"current_steps": 470, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.0717948717948718, "percentage": 35.77, "elapsed_time": "6:59:52", "remaining_time": "12:33:58"}
49
+ {"current_steps": 480, "total_steps": 1314, "loss": 0.6037, "learning_rate": 5e-06, "epoch": 1.0945868945868946, "percentage": 36.53, "elapsed_time": "7:08:37", "remaining_time": "12:24:44"}
50
+ {"current_steps": 490, "total_steps": 1314, "loss": 0.6087, "learning_rate": 5e-06, "epoch": 1.1173789173789175, "percentage": 37.29, "elapsed_time": "7:17:23", "remaining_time": "12:15:31"}
51
+ {"current_steps": 500, "total_steps": 1314, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 1.1401709401709401, "percentage": 38.05, "elapsed_time": "7:26:08", "remaining_time": "12:06:19"}
52
+ {"current_steps": 510, "total_steps": 1314, "loss": 0.5965, "learning_rate": 5e-06, "epoch": 1.162962962962963, "percentage": 38.81, "elapsed_time": "7:34:54", "remaining_time": "11:57:08"}
53
+ {"current_steps": 520, "total_steps": 1314, "loss": 0.6022, "learning_rate": 5e-06, "epoch": 1.1857549857549858, "percentage": 39.57, "elapsed_time": "7:43:39", "remaining_time": "11:47:58"}
54
+ {"current_steps": 530, "total_steps": 1314, "loss": 0.5952, "learning_rate": 5e-06, "epoch": 1.2085470085470085, "percentage": 40.33, "elapsed_time": "7:52:25", "remaining_time": "11:38:49"}
55
+ {"current_steps": 540, "total_steps": 1314, "loss": 0.6055, "learning_rate": 5e-06, "epoch": 1.2313390313390313, "percentage": 41.1, "elapsed_time": "8:01:10", "remaining_time": "11:29:40"}
56
+ {"current_steps": 550, "total_steps": 1314, "loss": 0.6021, "learning_rate": 5e-06, "epoch": 1.2541310541310542, "percentage": 41.86, "elapsed_time": "8:09:55", "remaining_time": "11:20:32"}
57
+ {"current_steps": 560, "total_steps": 1314, "loss": 0.6036, "learning_rate": 5e-06, "epoch": 1.2769230769230768, "percentage": 42.62, "elapsed_time": "8:18:40", "remaining_time": "11:11:25"}
58
+ {"current_steps": 570, "total_steps": 1314, "loss": 0.5976, "learning_rate": 5e-06, "epoch": 1.2997150997150997, "percentage": 43.38, "elapsed_time": "8:27:25", "remaining_time": "11:02:19"}
59
+ {"current_steps": 580, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.3225071225071225, "percentage": 44.14, "elapsed_time": "8:36:11", "remaining_time": "10:53:14"}
60
+ {"current_steps": 590, "total_steps": 1314, "loss": 0.5958, "learning_rate": 5e-06, "epoch": 1.3452991452991454, "percentage": 44.9, "elapsed_time": "8:44:57", "remaining_time": "10:44:11"}
61
+ {"current_steps": 600, "total_steps": 1314, "loss": 0.6014, "learning_rate": 5e-06, "epoch": 1.368091168091168, "percentage": 45.66, "elapsed_time": "8:53:43", "remaining_time": "10:35:07"}
62
+ {"current_steps": 610, "total_steps": 1314, "loss": 0.6015, "learning_rate": 5e-06, "epoch": 1.390883190883191, "percentage": 46.42, "elapsed_time": "9:02:29", "remaining_time": "10:26:04"}
63
+ {"current_steps": 620, "total_steps": 1314, "loss": 0.6041, "learning_rate": 5e-06, "epoch": 1.4136752136752135, "percentage": 47.18, "elapsed_time": "9:11:14", "remaining_time": "10:17:02"}
64
+ {"current_steps": 630, "total_steps": 1314, "loss": 0.6021, "learning_rate": 5e-06, "epoch": 1.4364672364672364, "percentage": 47.95, "elapsed_time": "9:20:00", "remaining_time": "10:08:00"}
65
+ {"current_steps": 640, "total_steps": 1314, "loss": 0.597, "learning_rate": 5e-06, "epoch": 1.4592592592592593, "percentage": 48.71, "elapsed_time": "9:28:46", "remaining_time": "9:58:59"}
66
+ {"current_steps": 650, "total_steps": 1314, "loss": 0.5948, "learning_rate": 5e-06, "epoch": 1.4820512820512821, "percentage": 49.47, "elapsed_time": "9:37:32", "remaining_time": "9:49:59"}
67
+ {"current_steps": 660, "total_steps": 1314, "loss": 0.5945, "learning_rate": 5e-06, "epoch": 1.504843304843305, "percentage": 50.23, "elapsed_time": "9:46:19", "remaining_time": "9:41:00"}
68
+ {"current_steps": 670, "total_steps": 1314, "loss": 0.6022, "learning_rate": 5e-06, "epoch": 1.5276353276353276, "percentage": 50.99, "elapsed_time": "9:55:05", "remaining_time": "9:31:59"}
69
+ {"current_steps": 680, "total_steps": 1314, "loss": 0.5907, "learning_rate": 5e-06, "epoch": 1.5504273504273505, "percentage": 51.75, "elapsed_time": "10:03:51", "remaining_time": "9:23:00"}
70
+ {"current_steps": 690, "total_steps": 1314, "loss": 0.5947, "learning_rate": 5e-06, "epoch": 1.573219373219373, "percentage": 52.51, "elapsed_time": "10:12:37", "remaining_time": "9:14:01"}
71
+ {"current_steps": 700, "total_steps": 1314, "loss": 0.6102, "learning_rate": 5e-06, "epoch": 1.596011396011396, "percentage": 53.27, "elapsed_time": "10:21:23", "remaining_time": "9:05:02"}
72
+ {"current_steps": 710, "total_steps": 1314, "loss": 0.5973, "learning_rate": 5e-06, "epoch": 1.6188034188034188, "percentage": 54.03, "elapsed_time": "10:30:09", "remaining_time": "8:56:04"}
73
+ {"current_steps": 720, "total_steps": 1314, "loss": 0.6019, "learning_rate": 5e-06, "epoch": 1.6415954415954417, "percentage": 54.79, "elapsed_time": "10:38:55", "remaining_time": "8:47:06"}
74
+ {"current_steps": 730, "total_steps": 1314, "loss": 0.595, "learning_rate": 5e-06, "epoch": 1.6643874643874645, "percentage": 55.56, "elapsed_time": "10:47:41", "remaining_time": "8:38:09"}
75
+ {"current_steps": 740, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.6871794871794872, "percentage": 56.32, "elapsed_time": "10:56:27", "remaining_time": "8:29:12"}
76
+ {"current_steps": 750, "total_steps": 1314, "loss": 0.5934, "learning_rate": 5e-06, "epoch": 1.7099715099715098, "percentage": 57.08, "elapsed_time": "11:05:13", "remaining_time": "8:20:15"}
77
+ {"current_steps": 760, "total_steps": 1314, "loss": 0.5974, "learning_rate": 5e-06, "epoch": 1.7327635327635327, "percentage": 57.84, "elapsed_time": "11:13:59", "remaining_time": "8:11:18"}
78
+ {"current_steps": 770, "total_steps": 1314, "loss": 0.5938, "learning_rate": 5e-06, "epoch": 1.7555555555555555, "percentage": 58.6, "elapsed_time": "11:22:45", "remaining_time": "8:02:21"}
79
+ {"current_steps": 780, "total_steps": 1314, "loss": 0.6009, "learning_rate": 5e-06, "epoch": 1.7783475783475784, "percentage": 59.36, "elapsed_time": "11:31:30", "remaining_time": "7:53:24"}
80
+ {"current_steps": 790, "total_steps": 1314, "loss": 0.5985, "learning_rate": 5e-06, "epoch": 1.8011396011396013, "percentage": 60.12, "elapsed_time": "11:40:16", "remaining_time": "7:44:29"}
81
+ {"current_steps": 800, "total_steps": 1314, "loss": 0.5853, "learning_rate": 5e-06, "epoch": 1.823931623931624, "percentage": 60.88, "elapsed_time": "11:49:02", "remaining_time": "7:35:33"}
82
+ {"current_steps": 810, "total_steps": 1314, "loss": 0.5931, "learning_rate": 5e-06, "epoch": 1.8467236467236468, "percentage": 61.64, "elapsed_time": "11:57:48", "remaining_time": "7:26:38"}
83
+ {"current_steps": 820, "total_steps": 1314, "loss": 0.5909, "learning_rate": 5e-06, "epoch": 1.8695156695156694, "percentage": 62.4, "elapsed_time": "12:06:34", "remaining_time": "7:17:43"}
84
+ {"current_steps": 830, "total_steps": 1314, "loss": 0.5947, "learning_rate": 5e-06, "epoch": 1.8923076923076922, "percentage": 63.17, "elapsed_time": "12:15:20", "remaining_time": "7:08:48"}
85
+ {"current_steps": 840, "total_steps": 1314, "loss": 0.5992, "learning_rate": 5e-06, "epoch": 1.915099715099715, "percentage": 63.93, "elapsed_time": "12:24:06", "remaining_time": "6:59:53"}
86
+ {"current_steps": 850, "total_steps": 1314, "loss": 0.5973, "learning_rate": 5e-06, "epoch": 1.937891737891738, "percentage": 64.69, "elapsed_time": "12:32:52", "remaining_time": "6:50:58"}
87
+ {"current_steps": 860, "total_steps": 1314, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:41:38", "remaining_time": "6:42:04"}
88
+ {"current_steps": 870, "total_steps": 1314, "loss": 0.596, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:50:23", "remaining_time": "6:33:10"}
89
+ {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187179088592529, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:03:54", "remaining_time": "6:30:36"}