Hugging Face's logo

mlfoundations-dev
/
hp_ablations_qwen_bsz512

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
600f476
•
1 Parent(s): 4258165

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:b9431c1a2b1300e688093b33db727cd9a3d31813ca7d57071fe012a5ee64cce1
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c231b8c00cc0167859cad2a2e5e6ffc4baa2c94250d2540db7c468bd136579
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fd235ef775198f5a4c665ea176aa91425876335f91fba549ca8fe5e4b7b82c6
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e86c2588abfde80d3f3058580b604393a73974cfc146451728810133f15fe6f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36e2a54b95d6e72886fdc77ac2c19ffd122269618c1a18df6bad8f6610bfed58
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4055e770a7ce1e76aff172279c59bc17fc4bfd8fe9ea12127bd32c88c85bbc96
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e078b091ed1e3df2b49f8bd00ca21b9bd2e92e2a0fd80fc1a6bd6a7d6379a7f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97159107c62fc44ed9f6f1207f396f6fa479bd9b080d6aa4a04b0767b24ab3cb
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": "6:16:17", "remaining_time": "12:53:35"}
44
  {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6251770257949829, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:31:04", "remaining_time": "13:02:09"}
45
  {"current_steps": 440, "total_steps": 1314, "loss": 0.6472, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:33:30", "remaining_time": "13:01:38"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  {"current_steps": 430, "total_steps": 1314, "loss": 0.6345, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:16:17", "remaining_time": "12:53:35"}
44
  {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6251770257949829, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:31:04", "remaining_time": "13:02:09"}
45
  {"current_steps": 440, "total_steps": 1314, "loss": 0.6472, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:33:30", "remaining_time": "13:01:38"}
46
+ {"current_steps": 450, "total_steps": 1314, "loss": 0.6018, "learning_rate": 5e-06, "epoch": 1.0262108262108263, "percentage": 34.25, "elapsed_time": "6:42:17", "remaining_time": "12:52:24"}
47
+ {"current_steps": 460, "total_steps": 1314, "loss": 0.5955, "learning_rate": 5e-06, "epoch": 1.049002849002849, "percentage": 35.01, "elapsed_time": "6:51:03", "remaining_time": "12:43:07"}
48
+ {"current_steps": 470, "total_steps": 1314, "loss": 0.5964, "learning_rate": 5e-06, "epoch": 1.0717948717948718, "percentage": 35.77, "elapsed_time": "6:59:48", "remaining_time": "12:33:51"}
49
+ {"current_steps": 480, "total_steps": 1314, "loss": 0.6039, "learning_rate": 5e-06, "epoch": 1.0945868945868946, "percentage": 36.53, "elapsed_time": "7:08:35", "remaining_time": "12:24:41"}
50
+ {"current_steps": 490, "total_steps": 1314, "loss": 0.6089, "learning_rate": 5e-06, "epoch": 1.1173789173789175, "percentage": 37.29, "elapsed_time": "7:17:20", "remaining_time": "12:15:26"}
51
+ {"current_steps": 500, "total_steps": 1314, "loss": 0.5988, "learning_rate": 5e-06, "epoch": 1.1401709401709401, "percentage": 38.05, "elapsed_time": "7:26:07", "remaining_time": "12:06:17"}
52
+ {"current_steps": 510, "total_steps": 1314, "loss": 0.5967, "learning_rate": 5e-06, "epoch": 1.162962962962963, "percentage": 38.81, "elapsed_time": "7:34:53", "remaining_time": "11:57:06"}
53
+ {"current_steps": 520, "total_steps": 1314, "loss": 0.6024, "learning_rate": 5e-06, "epoch": 1.1857549857549858, "percentage": 39.57, "elapsed_time": "7:43:39", "remaining_time": "11:47:57"}
54
+ {"current_steps": 530, "total_steps": 1314, "loss": 0.5953, "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": 0.6056, "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": 0.6022, "learning_rate": 5e-06, "epoch": 1.2541310541310542, "percentage": 41.86, "elapsed_time": "8:09:53", "remaining_time": "11:20:30"}
57
+ {"current_steps": 560, "total_steps": 1314, "loss": 0.6037, "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": 0.5977, "learning_rate": 5e-06, "epoch": 1.2997150997150997, "percentage": 43.38, "elapsed_time": "8:27:27", "remaining_time": "11:02:21"}
59
+ {"current_steps": 580, "total_steps": 1314, "loss": 0.5963, "learning_rate": 5e-06, "epoch": 1.3225071225071225, "percentage": 44.14, "elapsed_time": "8:36:14", "remaining_time": "10:53:18"}
60
+ {"current_steps": 590, "total_steps": 1314, "loss": 0.5959, "learning_rate": 5e-06, "epoch": 1.3452991452991454, "percentage": 44.9, "elapsed_time": "8:45:00", "remaining_time": "10:44:14"}
61
+ {"current_steps": 600, "total_steps": 1314, "loss": 0.6016, "learning_rate": 5e-06, "epoch": 1.368091168091168, "percentage": 45.66, "elapsed_time": "8:53:46", "remaining_time": "10:35:11"}
62
+ {"current_steps": 610, "total_steps": 1314, "loss": 0.6016, "learning_rate": 5e-06, "epoch": 1.390883190883191, "percentage": 46.42, "elapsed_time": "9:02:30", "remaining_time": "10:26:06"}
63
+ {"current_steps": 620, "total_steps": 1314, "loss": 0.6042, "learning_rate": 5e-06, "epoch": 1.4136752136752135, "percentage": 47.18, "elapsed_time": "9:11:15", "remaining_time": "10:17:02"}
64
+ {"current_steps": 630, "total_steps": 1314, "loss": 0.6022, "learning_rate": 5e-06, "epoch": 1.4364672364672364, "percentage": 47.95, "elapsed_time": "9:20:01", "remaining_time": "10:08:01"}
65
+ {"current_steps": 640, "total_steps": 1314, "loss": 0.5971, "learning_rate": 5e-06, "epoch": 1.4592592592592593, "percentage": 48.71, "elapsed_time": "9:28:48", "remaining_time": "9:59:02"}
66
+ {"current_steps": 650, "total_steps": 1314, "loss": 0.595, "learning_rate": 5e-06, "epoch": 1.4820512820512821, "percentage": 49.47, "elapsed_time": "9:37:36", "remaining_time": "9:50:03"}
67
+ {"current_steps": 660, "total_steps": 1314, "loss": 0.5946, "learning_rate": 5e-06, "epoch": 1.504843304843305, "percentage": 50.23, "elapsed_time": "9:46:24", "remaining_time": "9:41:04"}
68
+ {"current_steps": 670, "total_steps": 1314, "loss": 0.6023, "learning_rate": 5e-06, "epoch": 1.5276353276353276, "percentage": 50.99, "elapsed_time": "9:55:09", "remaining_time": "9:32:03"}
69
+ {"current_steps": 680, "total_steps": 1314, "loss": 0.5908, "learning_rate": 5e-06, "epoch": 1.5504273504273505, "percentage": 51.75, "elapsed_time": "10:03:54", "remaining_time": "9:23:02"}
70
+ {"current_steps": 690, "total_steps": 1314, "loss": 0.5948, "learning_rate": 5e-06, "epoch": 1.573219373219373, "percentage": 52.51, "elapsed_time": "10:12:39", "remaining_time": "9:14:03"}
71
+ {"current_steps": 700, "total_steps": 1314, "loss": 0.6104, "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": 0.5974, "learning_rate": 5e-06, "epoch": 1.6188034188034188, "percentage": 54.03, "elapsed_time": "10:30:07", "remaining_time": "8:56:02"}
73
+ {"current_steps": 720, "total_steps": 1314, "loss": 0.602, "learning_rate": 5e-06, "epoch": 1.6415954415954417, "percentage": 54.79, "elapsed_time": "10:38:52", "remaining_time": "8:47:04"}
74
+ {"current_steps": 730, "total_steps": 1314, "loss": 0.5951, "learning_rate": 5e-06, "epoch": 1.6643874643874645, "percentage": 55.56, "elapsed_time": "10:47:36", "remaining_time": "8:38:05"}
75
+ {"current_steps": 740, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.6871794871794872, "percentage": 56.32, "elapsed_time": "10:56:21", "remaining_time": "8:29:07"}
76
+ {"current_steps": 750, "total_steps": 1314, "loss": 0.5936, "learning_rate": 5e-06, "epoch": 1.7099715099715098, "percentage": 57.08, "elapsed_time": "11:05:08", "remaining_time": "8:20:11"}
77
+ {"current_steps": 760, "total_steps": 1314, "loss": 0.5975, "learning_rate": 5e-06, "epoch": 1.7327635327635327, "percentage": 57.84, "elapsed_time": "11:13:53", "remaining_time": "8:11:14"}
78
+ {"current_steps": 770, "total_steps": 1314, "loss": 0.5939, "learning_rate": 5e-06, "epoch": 1.7555555555555555, "percentage": 58.6, "elapsed_time": "11:22:39", "remaining_time": "8:02:17"}
79
+ {"current_steps": 780, "total_steps": 1314, "loss": 0.6011, "learning_rate": 5e-06, "epoch": 1.7783475783475784, "percentage": 59.36, "elapsed_time": "11:31:25", "remaining_time": "7:53:21"}
80
+ {"current_steps": 790, "total_steps": 1314, "loss": 0.5986, "learning_rate": 5e-06, "epoch": 1.8011396011396013, "percentage": 60.12, "elapsed_time": "11:40:08", "remaining_time": "7:44:24"}
81
+ {"current_steps": 800, "total_steps": 1314, "loss": 0.5854, "learning_rate": 5e-06, "epoch": 1.823931623931624, "percentage": 60.88, "elapsed_time": "11:48:51", "remaining_time": "7:35:26"}
82
+ {"current_steps": 810, "total_steps": 1314, "loss": 0.5933, "learning_rate": 5e-06, "epoch": 1.8467236467236468, "percentage": 61.64, "elapsed_time": "11:57:36", "remaining_time": "7:26:30"}
83
+ {"current_steps": 820, "total_steps": 1314, "loss": 0.591, "learning_rate": 5e-06, "epoch": 1.8695156695156694, "percentage": 62.4, "elapsed_time": "12:06:22", "remaining_time": "7:17:35"}
84
+ {"current_steps": 830, "total_steps": 1314, "loss": 0.5948, "learning_rate": 5e-06, "epoch": 1.8923076923076922, "percentage": 63.17, "elapsed_time": "12:15:08", "remaining_time": "7:08:41"}
85
+ {"current_steps": 840, "total_steps": 1314, "loss": 0.5993, "learning_rate": 5e-06, "epoch": 1.915099715099715, "percentage": 63.93, "elapsed_time": "12:23:53", "remaining_time": "6:59:46"}
86
+ {"current_steps": 850, "total_steps": 1314, "loss": 0.5974, "learning_rate": 5e-06, "epoch": 1.937891737891738, "percentage": 64.69, "elapsed_time": "12:32:38", "remaining_time": "6:50:51"}
87
+ {"current_steps": 860, "total_steps": 1314, "loss": 0.5987, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:41:24", "remaining_time": "6:41:57"}
88
+ {"current_steps": 870, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:50:10", "remaining_time": "6:33:03"}
89
+ {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187289953231812, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:03:39", "remaining_time": "6:30:29"}