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
15e9c1a
•
1 Parent(s): 600f476

Training in progress, epoch 2

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 sha256:31c231b8c00cc0167859cad2a2e5e6ffc4baa2c94250d2540db7c468bd136579
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa08e29bcc9fc1121cb2edbee8cdc2f6ef7f580945907dc104479e237cbdc1a1
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e86c2588abfde80d3f3058580b604393a73974cfc146451728810133f15fe6f
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7255891ee03cbbe4146d036db3c5ea2023fbf02794346a104a98bdabd89ac9fb
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4055e770a7ce1e76aff172279c59bc17fc4bfd8fe9ea12127bd32c88c85bbc96
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b07b85c1ff64dda749d5113cfd9b4bcd964a3123559560028982ce6d6a5bd1
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97159107c62fc44ed9f6f1207f396f6fa479bd9b080d6aa4a04b0767b24ab3cb
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b5043033431efa7d86f5829b7e0088ef44aa2ca1d2e2c4b688623ce82dc5925
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -87,3 +87,47 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
90
+ {"current_steps": 880, "total_steps": 1314, "loss": 0.6155, "learning_rate": 5e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:07:25", "remaining_time": "6:28:20"}
91
+ {"current_steps": 890, "total_steps": 1314, "loss": 0.5547, "learning_rate": 5e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:16:11", "remaining_time": "6:19:18"}
92
+ {"current_steps": 900, "total_steps": 1314, "loss": 0.5698, "learning_rate": 5e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:24:56", "remaining_time": "6:10:16"}
93
+ {"current_steps": 910, "total_steps": 1314, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:33:42", "remaining_time": "6:01:15"}
94
+ {"current_steps": 920, "total_steps": 1314, "loss": 0.5711, "learning_rate": 5e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:42:27", "remaining_time": "5:52:13"}
95
+ {"current_steps": 930, "total_steps": 1314, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:51:12", "remaining_time": "5:43:12"}
96
+ {"current_steps": 940, "total_steps": 1314, "loss": 0.5638, "learning_rate": 5e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "13:59:56", "remaining_time": "5:34:11"}
97
+ {"current_steps": 950, "total_steps": 1314, "loss": 0.5647, "learning_rate": 5e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:08:41", "remaining_time": "5:25:10"}
98
+ {"current_steps": 960, "total_steps": 1314, "loss": 0.5698, "learning_rate": 5e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:17:27", "remaining_time": "5:16:11"}
99
+ {"current_steps": 970, "total_steps": 1314, "loss": 0.5692, "learning_rate": 5e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:26:14", "remaining_time": "5:07:12"}
100
+ {"current_steps": 980, "total_steps": 1314, "loss": 0.5588, "learning_rate": 5e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:35:01", "remaining_time": "4:58:13"}
101
+ {"current_steps": 990, "total_steps": 1314, "loss": 0.5679, "learning_rate": 5e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:43:49", "remaining_time": "4:49:15"}
102
+ {"current_steps": 1000, "total_steps": 1314, "loss": 0.5682, "learning_rate": 5e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:52:34", "remaining_time": "4:40:16"}
103
+ {"current_steps": 1010, "total_steps": 1314, "loss": 0.5657, "learning_rate": 5e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "15:01:22", "remaining_time": "4:31:18"}
104
+ {"current_steps": 1020, "total_steps": 1314, "loss": 0.5688, "learning_rate": 5e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:10:07", "remaining_time": "4:22:19"}
105
+ {"current_steps": 1030, "total_steps": 1314, "loss": 0.57, "learning_rate": 5e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:18:54", "remaining_time": "4:13:22"}
106
+ {"current_steps": 1040, "total_steps": 1314, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:27:41", "remaining_time": "4:04:24"}
107
+ {"current_steps": 1050, "total_steps": 1314, "loss": 0.5674, "learning_rate": 5e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:36:28", "remaining_time": "3:55:27"}
108
+ {"current_steps": 1060, "total_steps": 1314, "loss": 0.5756, "learning_rate": 5e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:45:16", "remaining_time": "3:46:30"}
109
+ {"current_steps": 1070, "total_steps": 1314, "loss": 0.5785, "learning_rate": 5e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:54:03", "remaining_time": "3:37:33"}
110
+ {"current_steps": 1080, "total_steps": 1314, "loss": 0.5738, "learning_rate": 5e-06, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:02:50", "remaining_time": "3:28:37"}
111
+ {"current_steps": 1090, "total_steps": 1314, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:11:38", "remaining_time": "3:19:40"}
112
+ {"current_steps": 1100, "total_steps": 1314, "loss": 0.5779, "learning_rate": 5e-06, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:20:26", "remaining_time": "3:10:44"}
113
+ {"current_steps": 1110, "total_steps": 1314, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:29:10", "remaining_time": "3:01:47"}
114
+ {"current_steps": 1120, "total_steps": 1314, "loss": 0.5695, "learning_rate": 5e-06, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:37:56", "remaining_time": "2:52:51"}
115
+ {"current_steps": 1130, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:46:40", "remaining_time": "2:43:55"}
116
+ {"current_steps": 1140, "total_steps": 1314, "loss": 0.5686, "learning_rate": 5e-06, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:55:26", "remaining_time": "2:34:59"}
117
+ {"current_steps": 1150, "total_steps": 1314, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:04:14", "remaining_time": "2:26:03"}
118
+ {"current_steps": 1160, "total_steps": 1314, "loss": 0.57, "learning_rate": 5e-06, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:13:01", "remaining_time": "2:17:08"}
119
+ {"current_steps": 1170, "total_steps": 1314, "loss": 0.5728, "learning_rate": 5e-06, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:21:46", "remaining_time": "2:08:13"}
120
+ {"current_steps": 1180, "total_steps": 1314, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:30:33", "remaining_time": "1:59:18"}
121
+ {"current_steps": 1190, "total_steps": 1314, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:39:21", "remaining_time": "1:50:23"}
122
+ {"current_steps": 1200, "total_steps": 1314, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:48:09", "remaining_time": "1:41:28"}
123
+ {"current_steps": 1210, "total_steps": 1314, "loss": 0.5756, "learning_rate": 5e-06, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "17:56:58", "remaining_time": "1:32:33"}
124
+ {"current_steps": 1220, "total_steps": 1314, "loss": 0.5655, "learning_rate": 5e-06, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:05:46", "remaining_time": "1:23:39"}
125
+ {"current_steps": 1230, "total_steps": 1314, "loss": 0.564, "learning_rate": 5e-06, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:14:32", "remaining_time": "1:14:44"}
126
+ {"current_steps": 1240, "total_steps": 1314, "loss": 0.5788, "learning_rate": 5e-06, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:23:19", "remaining_time": "1:05:50"}
127
+ {"current_steps": 1250, "total_steps": 1314, "loss": 0.5754, "learning_rate": 5e-06, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:32:06", "remaining_time": "0:56:56"}
128
+ {"current_steps": 1260, "total_steps": 1314, "loss": 0.5726, "learning_rate": 5e-06, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:40:53", "remaining_time": "0:48:02"}
129
+ {"current_steps": 1270, "total_steps": 1314, "loss": 0.5735, "learning_rate": 5e-06, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:49:37", "remaining_time": "0:39:08"}
130
+ {"current_steps": 1280, "total_steps": 1314, "loss": 0.5637, "learning_rate": 5e-06, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "18:58:22", "remaining_time": "0:30:14"}
131
+ {"current_steps": 1290, "total_steps": 1314, "loss": 0.5639, "learning_rate": 5e-06, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:07:07", "remaining_time": "0:21:20"}
132
+ {"current_steps": 1300, "total_steps": 1314, "loss": 0.5651, "learning_rate": 5e-06, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:15:52", "remaining_time": "0:12:26"}
133
+ {"current_steps": 1310, "total_steps": 1314, "loss": 0.5749, "learning_rate": 5e-06, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:24:38", "remaining_time": "0:03:33"}