Hugging Face's logo

mlfoundations-dev
/
deepspeed_no_offload_liger_packing

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
46f404a
·
verified ·
1 Parent(s): 3ee7130

Training in progress, epoch 1

Browse files
Files changed (6) 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 +8 -19
  6. training_args.bin +1 -1
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab9d35db6894fb4cec2b33a202b0cd88997ea0934ce4257646b19687778fa15f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10cf29ce3834c907a9f26350351f2af0899f977114fd1941220925ecbb93d4e
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ea2121ec99563c2ba80997c248c47cfc1b8dcdb7dda7d2f0779861a268ae540
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39e80fdda6fbc392f7bb71c1e172b0c6b464ed9a541504ea3fd4bf47a32e39f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b6e3e5ce72ae182abc7cb493d71ef1d1b43def7e0489e917e6733be0047cd07
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7795c37c378e4f452801019c70353efa1563074b51a3c0debe1c1ef6f79db32d
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:be564a5e509a9ee8ab4d1531616fd58a131301f295112332e584900589301a45
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc57cbe95dcdacba21104458d30bfdad48d708e1adc4bb229933f7732b1d612
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -1,19 +1,8 @@
1
- {"current_steps": 1, "total_steps": 18, "loss": 1.2879, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:01:20", "remaining_time": "0:22:41"}
2
- {"current_steps": 2, "total_steps": 18, "loss": 1.3268, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:24", "remaining_time": "0:19:14"}
3
- {"current_steps": 3, "total_steps": 18, "loss": 1.2078, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:03:28", "remaining_time": "0:17:23"}
4
- {"current_steps": 4, "total_steps": 18, "loss": 1.1303, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:04:32", "remaining_time": "0:15:55"}
5
- {"current_steps": 5, "total_steps": 18, "loss": 1.1449, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:05:37", "remaining_time": "0:14:36"}
6
- {"current_steps": 6, "total_steps": 18, "loss": 1.085, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:31", "remaining_time": "0:13:03"}
7
- {"current_steps": 7, "total_steps": 18, "loss": 1.07, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:08:30", "remaining_time": "0:13:22"}
8
- {"current_steps": 8, "total_steps": 18, "loss": 1.0364, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:09:34", "remaining_time": "0:11:58"}
9
- {"current_steps": 9, "total_steps": 18, "loss": 1.0098, "lr": 5.975451610080643e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:10:38", "remaining_time": "0:10:38"}
10
- {"current_steps": 10, "total_steps": 18, "loss": 0.9637, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:11:43", "remaining_time": "0:09:22"}
11
- {"current_steps": 11, "total_steps": 18, "loss": 0.9329, "lr": 4.02454838991936e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "0:12:47", "remaining_time": "0:08:08"}
12
- {"current_steps": 12, "total_steps": 18, "loss": 0.9329, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:13:41", "remaining_time": "0:06:50"}
13
- {"current_steps": 13, "total_steps": 18, "loss": 0.9097, "lr": 2.2221488349019903e-06, "epoch": 2.1666666666666665, "percentage": 72.22, "elapsed_time": "0:15:41", "remaining_time": "0:06:02"}
14
- {"current_steps": 14, "total_steps": 18, "loss": 0.8906, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:16:46", "remaining_time": "0:04:47"}
15
- {"current_steps": 15, "total_steps": 18, "loss": 0.9138, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:17:50", "remaining_time": "0:03:34"}
16
- {"current_steps": 16, "total_steps": 18, "loss": 0.9051, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:18:54", "remaining_time": "0:02:21"}
17
- {"current_steps": 17, "total_steps": 18, "loss": 0.902, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:19:58", "remaining_time": "0:01:10"}
18
- {"current_steps": 18, "total_steps": 18, "loss": 0.8931, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:20:53", "remaining_time": "0:00:00"}
19
- {"current_steps": 18, "total_steps": 18, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:22:23", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 1, "total_steps": 18, "loss": 1.2879, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:01:25", "remaining_time": "0:24:05"}
2
+ {"current_steps": 2, "total_steps": 18, "loss": 1.3268, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:30", "remaining_time": "0:20:00"}
3
+ {"current_steps": 3, "total_steps": 18, "loss": 1.2077, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:03:35", "remaining_time": "0:17:56"}
4
+ {"current_steps": 4, "total_steps": 18, "loss": 1.1302, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:04:40", "remaining_time": "0:16:21"}
5
+ {"current_steps": 5, "total_steps": 18, "loss": 1.1449, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:05:45", "remaining_time": "0:14:58"}
6
+ {"current_steps": 6, "total_steps": 18, "loss": 1.085, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:41", "remaining_time": "0:13:22"}
7
+ {"current_steps": 7, "total_steps": 18, "loss": 1.07, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:08:40", "remaining_time": "0:13:38"}
8
+ {"current_steps": 8, "total_steps": 18, "loss": 1.0365, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:09:45", "remaining_time": "0:12:12"}
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b22a51bbb652ed5772b9879ad9a5817ee2ffa646998de84610e435d720e3291f
3
  size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ff0aecf748840f1547ebdce711be83357b602d5eb9c486d96b03d6c214c83d
3
  size 7224