Hugging Face's logo

AmberYifan
/
qwen2.5-7b-instruct-full-pretrain-junk-tweet-1m-en-gpt-sft

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
AmberYifan commited on
Commit
979e77f
·
verified ·
1 Parent(s): 150b06d

Training in progress, step 939

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 +14 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05165d98d7e7a095794c877f076957105c738e840c5b9d58f44047c7d0320704
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11feec52a42068064cfc95c752196d7fbce9c6759006d7d481936d3ad1cf2793
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5578c754ca6e63d7345a28af3e6a9149cd04fafc23ed12948f9476c841a1952a
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:895982d9591e5252500e99994b452ac4777b2b8e8e9635e3fbb1e79867130c06
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:750935adaaad3720c23a20e57680e087e1c414cc8646aaaa12d53552db45569c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c037d9b5996d07f5283d82f6a35b3e4fd7bb818a3f6048599f3f7b6be4da59d
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:d8f607b42f623d560dc93f092b0e13d3e78b64bf09a798a40b4abcfbb5919317
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4783c190695b8110380a58de536f58b92082ba8fce3bde4e1191f4d90f0c54a4
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -78,3 +78,17 @@
78
  {"current_steps": 780, "total_steps": 939, "loss": 0.206, "lr": 8.58858971477457e-07, "epoch": 2.4928, "percentage": 83.07, "elapsed_time": "0:14:53", "remaining_time": "0:03:02"}
79
  {"current_steps": 790, "total_steps": 939, "loss": 0.2173, "lr": 7.575718930512516e-07, "epoch": 2.5248, "percentage": 84.13, "elapsed_time": "0:15:04", "remaining_time": "0:02:50"}
80
  {"current_steps": 800, "total_steps": 939, "loss": 0.2037, "lr": 6.621482317764105e-07, "epoch": 2.5568, "percentage": 85.2, "elapsed_time": "0:15:15", "remaining_time": "0:02:38"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  {"current_steps": 780, "total_steps": 939, "loss": 0.206, "lr": 8.58858971477457e-07, "epoch": 2.4928, "percentage": 83.07, "elapsed_time": "0:14:53", "remaining_time": "0:03:02"}
79
  {"current_steps": 790, "total_steps": 939, "loss": 0.2173, "lr": 7.575718930512516e-07, "epoch": 2.5248, "percentage": 84.13, "elapsed_time": "0:15:04", "remaining_time": "0:02:50"}
80
  {"current_steps": 800, "total_steps": 939, "loss": 0.2037, "lr": 6.621482317764105e-07, "epoch": 2.5568, "percentage": 85.2, "elapsed_time": "0:15:15", "remaining_time": "0:02:38"}
81
+ {"current_steps": 810, "total_steps": 939, "loss": 0.2314, "lr": 5.727198717339511e-07, "epoch": 2.5888, "percentage": 86.26, "elapsed_time": "0:15:25", "remaining_time": "0:02:27"}
82
+ {"current_steps": 820, "total_steps": 939, "loss": 0.2208, "lr": 4.894104109594466e-07, "epoch": 2.6208, "percentage": 87.33, "elapsed_time": "0:15:36", "remaining_time": "0:02:15"}
83
+ {"current_steps": 830, "total_steps": 939, "loss": 0.2099, "lr": 4.123349906194357e-07, "epoch": 2.6528, "percentage": 88.39, "elapsed_time": "0:15:46", "remaining_time": "0:02:04"}
84
+ {"current_steps": 840, "total_steps": 939, "loss": 0.2293, "lr": 3.416001358759635e-07, "epoch": 2.6848, "percentage": 89.46, "elapsed_time": "0:15:57", "remaining_time": "0:01:52"}
85
+ {"current_steps": 850, "total_steps": 939, "loss": 0.2014, "lr": 2.7730360865923954e-07, "epoch": 2.7168, "percentage": 90.52, "elapsed_time": "0:16:07", "remaining_time": "0:01:41"}
86
+ {"current_steps": 860, "total_steps": 939, "loss": 0.2449, "lr": 2.1953427255185122e-07, "epoch": 2.7488, "percentage": 91.59, "elapsed_time": "0:16:18", "remaining_time": "0:01:29"}
87
+ {"current_steps": 870, "total_steps": 939, "loss": 0.2224, "lr": 1.6837196997130434e-07, "epoch": 2.7808, "percentage": 92.65, "elapsed_time": "0:16:28", "remaining_time": "0:01:18"}
88
+ {"current_steps": 880, "total_steps": 939, "loss": 0.1969, "lr": 1.2388741182062348e-07, "epoch": 2.8128, "percentage": 93.72, "elapsed_time": "0:16:39", "remaining_time": "0:01:06"}
89
+ {"current_steps": 890, "total_steps": 939, "loss": 0.2248, "lr": 8.614207975952083e-08, "epoch": 2.8448, "percentage": 94.78, "elapsed_time": "0:16:49", "remaining_time": "0:00:55"}
90
+ {"current_steps": 900, "total_steps": 939, "loss": 0.1906, "lr": 5.518814123121885e-08, "epoch": 2.8768000000000002, "percentage": 95.85, "elapsed_time": "0:17:00", "remaining_time": "0:00:44"}
91
+ {"current_steps": 910, "total_steps": 939, "loss": 0.1928, "lr": 3.10683773623488e-08, "epoch": 2.9088000000000003, "percentage": 96.91, "elapsed_time": "0:17:10", "remaining_time": "0:00:32"}
92
+ {"current_steps": 920, "total_steps": 939, "loss": 0.2329, "lr": 1.3816123835588835e-08, "epoch": 2.9408, "percentage": 97.98, "elapsed_time": "0:17:21", "remaining_time": "0:00:21"}
93
+ {"current_steps": 930, "total_steps": 939, "loss": 0.2185, "lr": 3.4552248167507576e-09, "epoch": 2.9728, "percentage": 99.04, "elapsed_time": "0:17:31", "remaining_time": "0:00:10"}
94
+ {"current_steps": 939, "total_steps": 939, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:18:35", "remaining_time": "0:00:00"}