Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_adambeta1_0.85

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
0986602
·
verified ·
1 Parent(s): 4b7347c

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 sha256:34e9a17d9832456f520a4c71e8b191a335b8d894ba5f2162061cf9c5554e987b
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be68bcf43a196f8c268fa82773db94bb8ed1421821f400f98f0a1d26679f349
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1892a69ce4a1fb45a79936db4ebf4829f12dd0673e7387bb4aab2d2a464f4d22
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944873d9eb8eb80a56c8fdc084276f1a9b6412082d4074c6819660b34805d052
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d5d0be74743fdfc335f8e8280e9c95d27973048beb162b5cd7969de398fb8fb
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52d8878fd4fe25eb437724fccce79d67b8dccfcaf540d5490f4c9a61c8a04df1
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93b5b10fde9d522a626e1cdaf6beaf072435341a9a80d508579947cb16cd50fa
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cbc09a5614daa52034cd278dd525e9def78f1b50890b86f2400cf24d62885ab
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -43,3 +43,47 @@
43
  {"current_steps": 430, "total_steps": 1314, "loss": 0.6345, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:16:02", "remaining_time": "12:53:05"}
44
  {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6251751184463501, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:30:52", "remaining_time": "13:01:45"}
45
  {"current_steps": 440, "total_steps": 1314, "loss": 0.6473, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:33:14", "remaining_time": "13:01:08"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  {"current_steps": 430, "total_steps": 1314, "loss": 0.6345, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:16:02", "remaining_time": "12:53:05"}
44
  {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6251751184463501, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:30:52", "remaining_time": "13:01:45"}
45
  {"current_steps": 440, "total_steps": 1314, "loss": 0.6473, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:33:14", "remaining_time": "13:01:08"}
46
+ {"current_steps": 450, "total_steps": 1314, "loss": 0.6019, "learning_rate": 5e-06, "epoch": 1.0262108262108263, "percentage": 34.25, "elapsed_time": "6:41:59", "remaining_time": "12:51:50"}
47
+ {"current_steps": 460, "total_steps": 1314, "loss": 0.5957, "learning_rate": 5e-06, "epoch": 1.049002849002849, "percentage": 35.01, "elapsed_time": "6:50:45", "remaining_time": "12:42:34"}
48
+ {"current_steps": 470, "total_steps": 1314, "loss": 0.5967, "learning_rate": 5e-06, "epoch": 1.0717948717948718, "percentage": 35.77, "elapsed_time": "6:59:28", "remaining_time": "12:33:16"}
49
+ {"current_steps": 480, "total_steps": 1314, "loss": 0.6042, "learning_rate": 5e-06, "epoch": 1.0945868945868946, "percentage": 36.53, "elapsed_time": "7:08:13", "remaining_time": "12:24:02"}
50
+ {"current_steps": 490, "total_steps": 1314, "loss": 0.6093, "learning_rate": 5e-06, "epoch": 1.1173789173789175, "percentage": 37.29, "elapsed_time": "7:16:58", "remaining_time": "12:14:49"}
51
+ {"current_steps": 500, "total_steps": 1314, "loss": 0.5991, "learning_rate": 5e-06, "epoch": 1.1401709401709401, "percentage": 38.05, "elapsed_time": "7:25:41", "remaining_time": "12:05:35"}
52
+ {"current_steps": 510, "total_steps": 1314, "loss": 0.597, "learning_rate": 5e-06, "epoch": 1.162962962962963, "percentage": 38.81, "elapsed_time": "7:34:25", "remaining_time": "11:56:23"}
53
+ {"current_steps": 520, "total_steps": 1314, "loss": 0.6027, "learning_rate": 5e-06, "epoch": 1.1857549857549858, "percentage": 39.57, "elapsed_time": "7:43:09", "remaining_time": "11:47:12"}
54
+ {"current_steps": 530, "total_steps": 1314, "loss": 0.5957, "learning_rate": 5e-06, "epoch": 1.2085470085470085, "percentage": 40.33, "elapsed_time": "7:51:53", "remaining_time": "11:38:02"}
55
+ {"current_steps": 540, "total_steps": 1314, "loss": 0.6059, "learning_rate": 5e-06, "epoch": 1.2313390313390313, "percentage": 41.1, "elapsed_time": "8:00:37", "remaining_time": "11:28:54"}
56
+ {"current_steps": 550, "total_steps": 1314, "loss": 0.6025, "learning_rate": 5e-06, "epoch": 1.2541310541310542, "percentage": 41.86, "elapsed_time": "8:09:22", "remaining_time": "11:19:47"}
57
+ {"current_steps": 560, "total_steps": 1314, "loss": 0.6041, "learning_rate": 5e-06, "epoch": 1.2769230769230768, "percentage": 42.62, "elapsed_time": "8:18:08", "remaining_time": "11:10:42"}
58
+ {"current_steps": 570, "total_steps": 1314, "loss": 0.598, "learning_rate": 5e-06, "epoch": 1.2997150997150997, "percentage": 43.38, "elapsed_time": "8:26:52", "remaining_time": "11:01:36"}
59
+ {"current_steps": 580, "total_steps": 1314, "loss": 0.5966, "learning_rate": 5e-06, "epoch": 1.3225071225071225, "percentage": 44.14, "elapsed_time": "8:35:36", "remaining_time": "10:52:31"}
60
+ {"current_steps": 590, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.3452991452991454, "percentage": 44.9, "elapsed_time": "8:44:21", "remaining_time": "10:43:27"}
61
+ {"current_steps": 600, "total_steps": 1314, "loss": 0.6018, "learning_rate": 5e-06, "epoch": 1.368091168091168, "percentage": 45.66, "elapsed_time": "8:53:07", "remaining_time": "10:34:24"}
62
+ {"current_steps": 610, "total_steps": 1314, "loss": 0.6019, "learning_rate": 5e-06, "epoch": 1.390883190883191, "percentage": 46.42, "elapsed_time": "9:01:52", "remaining_time": "10:25:22"}
63
+ {"current_steps": 620, "total_steps": 1314, "loss": 0.6045, "learning_rate": 5e-06, "epoch": 1.4136752136752135, "percentage": 47.18, "elapsed_time": "9:10:37", "remaining_time": "10:16:20"}
64
+ {"current_steps": 630, "total_steps": 1314, "loss": 0.6025, "learning_rate": 5e-06, "epoch": 1.4364672364672364, "percentage": 47.95, "elapsed_time": "9:19:21", "remaining_time": "10:07:18"}
65
+ {"current_steps": 640, "total_steps": 1314, "loss": 0.5974, "learning_rate": 5e-06, "epoch": 1.4592592592592593, "percentage": 48.71, "elapsed_time": "9:28:06", "remaining_time": "9:58:16"}
66
+ {"current_steps": 650, "total_steps": 1314, "loss": 0.5953, "learning_rate": 5e-06, "epoch": 1.4820512820512821, "percentage": 49.47, "elapsed_time": "9:36:50", "remaining_time": "9:49:15"}
67
+ {"current_steps": 660, "total_steps": 1314, "loss": 0.595, "learning_rate": 5e-06, "epoch": 1.504843304843305, "percentage": 50.23, "elapsed_time": "9:45:34", "remaining_time": "9:40:15"}
68
+ {"current_steps": 670, "total_steps": 1314, "loss": 0.6026, "learning_rate": 5e-06, "epoch": 1.5276353276353276, "percentage": 50.99, "elapsed_time": "9:54:18", "remaining_time": "9:31:15"}
69
+ {"current_steps": 680, "total_steps": 1314, "loss": 0.5911, "learning_rate": 5e-06, "epoch": 1.5504273504273505, "percentage": 51.75, "elapsed_time": "10:03:02", "remaining_time": "9:22:14"}
70
+ {"current_steps": 690, "total_steps": 1314, "loss": 0.5951, "learning_rate": 5e-06, "epoch": 1.573219373219373, "percentage": 52.51, "elapsed_time": "10:11:45", "remaining_time": "9:13:14"}
71
+ {"current_steps": 700, "total_steps": 1314, "loss": 0.6106, "learning_rate": 5e-06, "epoch": 1.596011396011396, "percentage": 53.27, "elapsed_time": "10:20:30", "remaining_time": "9:04:16"}
72
+ {"current_steps": 710, "total_steps": 1314, "loss": 0.5977, "learning_rate": 5e-06, "epoch": 1.6188034188034188, "percentage": 54.03, "elapsed_time": "10:29:15", "remaining_time": "8:55:18"}
73
+ {"current_steps": 720, "total_steps": 1314, "loss": 0.6022, "learning_rate": 5e-06, "epoch": 1.6415954415954417, "percentage": 54.79, "elapsed_time": "10:37:59", "remaining_time": "8:46:20"}
74
+ {"current_steps": 730, "total_steps": 1314, "loss": 0.5953, "learning_rate": 5e-06, "epoch": 1.6643874643874645, "percentage": 55.56, "elapsed_time": "10:46:44", "remaining_time": "8:37:23"}
75
+ {"current_steps": 740, "total_steps": 1314, "loss": 0.5965, "learning_rate": 5e-06, "epoch": 1.6871794871794872, "percentage": 56.32, "elapsed_time": "10:55:28", "remaining_time": "8:28:25"}
76
+ {"current_steps": 750, "total_steps": 1314, "loss": 0.5938, "learning_rate": 5e-06, "epoch": 1.7099715099715098, "percentage": 57.08, "elapsed_time": "11:04:12", "remaining_time": "8:19:29"}
77
+ {"current_steps": 760, "total_steps": 1314, "loss": 0.5977, "learning_rate": 5e-06, "epoch": 1.7327635327635327, "percentage": 57.84, "elapsed_time": "11:12:57", "remaining_time": "8:10:32"}
78
+ {"current_steps": 770, "total_steps": 1314, "loss": 0.5941, "learning_rate": 5e-06, "epoch": 1.7555555555555555, "percentage": 58.6, "elapsed_time": "11:21:40", "remaining_time": "8:01:36"}
79
+ {"current_steps": 780, "total_steps": 1314, "loss": 0.6013, "learning_rate": 5e-06, "epoch": 1.7783475783475784, "percentage": 59.36, "elapsed_time": "11:30:25", "remaining_time": "7:52:40"}
80
+ {"current_steps": 790, "total_steps": 1314, "loss": 0.5988, "learning_rate": 5e-06, "epoch": 1.8011396011396013, "percentage": 60.12, "elapsed_time": "11:39:08", "remaining_time": "7:43:44"}
81
+ {"current_steps": 800, "total_steps": 1314, "loss": 0.5856, "learning_rate": 5e-06, "epoch": 1.823931623931624, "percentage": 60.88, "elapsed_time": "11:47:52", "remaining_time": "7:34:48"}
82
+ {"current_steps": 810, "total_steps": 1314, "loss": 0.5935, "learning_rate": 5e-06, "epoch": 1.8467236467236468, "percentage": 61.64, "elapsed_time": "11:56:37", "remaining_time": "7:25:53"}
83
+ {"current_steps": 820, "total_steps": 1314, "loss": 0.5912, "learning_rate": 5e-06, "epoch": 1.8695156695156694, "percentage": 62.4, "elapsed_time": "12:05:20", "remaining_time": "7:16:58"}
84
+ {"current_steps": 830, "total_steps": 1314, "loss": 0.5951, "learning_rate": 5e-06, "epoch": 1.8923076923076922, "percentage": 63.17, "elapsed_time": "12:14:03", "remaining_time": "7:08:03"}
85
+ {"current_steps": 840, "total_steps": 1314, "loss": 0.5996, "learning_rate": 5e-06, "epoch": 1.915099715099715, "percentage": 63.93, "elapsed_time": "12:22:47", "remaining_time": "6:59:08"}
86
+ {"current_steps": 850, "total_steps": 1314, "loss": 0.5976, "learning_rate": 5e-06, "epoch": 1.937891737891738, "percentage": 64.69, "elapsed_time": "12:31:31", "remaining_time": "6:50:14"}
87
+ {"current_steps": 860, "total_steps": 1314, "loss": 0.5989, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:40:14", "remaining_time": "6:41:20"}
88
+ {"current_steps": 870, "total_steps": 1314, "loss": 0.5964, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:48:58", "remaining_time": "6:32:26"}
89
+ {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6190649271011353, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:02:24", "remaining_time": "6:29:51"}