Hugging Face's logo

mlfoundations-dev
/
OpenHermes-2.5-sedrick

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
3c9527d
·
verified ·
1 Parent(s): 6ddddc5

Training in progress, epoch 2

Browse files
Files changed (14) hide show
  1. config.json.sagemaker-uploaded +0 -0
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00001-of-00004.safetensors.sagemaker-uploaded +0 -0
  4. model-00002-of-00004.safetensors +1 -1
  5. model-00002-of-00004.safetensors.sagemaker-uploaded +0 -0
  6. model-00003-of-00004.safetensors +1 -1
  7. model-00003-of-00004.safetensors.sagemaker-uploaded +0 -0
  8. model-00004-of-00004.safetensors +1 -1
  9. model-00004-of-00004.safetensors.sagemaker-uploaded +0 -0
  10. special_tokens_map.json.sagemaker-uploaded +0 -0
  11. tokenizer.json.sagemaker-uploaded +0 -0
  12. tokenizer_config.json.sagemaker-uploaded +0 -0
  13. trainer_log.jsonl +35 -0
  14. training_args.bin.sagemaker-uploaded +0 -0
config.json.sagemaker-uploaded ADDED
File without changes
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb657859286fd5ed6ba647ecf593df53494eab8b97635d25a6dc952b493d592c
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2c254da2b960b0831d007c8c8bdec12c41e39f85916342ffa4718ed5b53063
3
  size 4976698672
model-00001-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b83efb602ac7a7c436435b52b08c0f0b478df6ca8e39fb697f86ee8922974da
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf8d3c8e051572947d2cb9dd591031279e8b98f6a20bacce2e03435c6f9b268
3
  size 4999802720
model-00002-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ba77148717a99c79ea7d19094d8e340af2e2e3ea7bc356e0ebeefd04f989923
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fff1a43ab3fb634cc2f44ddf6a482f3670eadff7d1d40664d4cdce17aaf88f6b
3
  size 4915916176
model-00003-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b4219143595ff9987e84436cde7251b4c5394b980d8f2029344a2b09bba9261
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18443209f7b1f5fb2c615af56a2033fc9a6f7ff22657dba8e7cf9f8c8faf8be
3
  size 1168138808
model-00004-of-00004.safetensors.sagemaker-uploaded ADDED
File without changes
special_tokens_map.json.sagemaker-uploaded ADDED
File without changes
tokenizer.json.sagemaker-uploaded ADDED
File without changes
tokenizer_config.json.sagemaker-uploaded ADDED
File without changes
trainer_log.jsonl CHANGED
@@ -33,3 +33,38 @@
33
  {"current_steps": 330, "total_steps": 1005, "loss": 0.6025, "learning_rate": 5e-06, "epoch": 0.9850746268656716, "percentage": 32.84, "elapsed_time": "0:48:05", "remaining_time": "1:38:22"}
34
  {"current_steps": 335, "total_steps": 1005, "eval_loss": 0.6102219223976135, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:49:49", "remaining_time": "1:39:38"}
35
  {"current_steps": 340, "total_steps": 1005, "loss": 0.5854, "learning_rate": 5e-06, "epoch": 1.0149253731343284, "percentage": 33.83, "elapsed_time": "0:51:25", "remaining_time": "1:40:33"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  {"current_steps": 330, "total_steps": 1005, "loss": 0.6025, "learning_rate": 5e-06, "epoch": 0.9850746268656716, "percentage": 32.84, "elapsed_time": "0:48:05", "remaining_time": "1:38:22"}
34
  {"current_steps": 335, "total_steps": 1005, "eval_loss": 0.6102219223976135, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:49:49", "remaining_time": "1:39:38"}
35
  {"current_steps": 340, "total_steps": 1005, "loss": 0.5854, "learning_rate": 5e-06, "epoch": 1.0149253731343284, "percentage": 33.83, "elapsed_time": "0:51:25", "remaining_time": "1:40:33"}
36
+ {"current_steps": 350, "total_steps": 1005, "loss": 0.5551, "learning_rate": 5e-06, "epoch": 1.044776119402985, "percentage": 34.83, "elapsed_time": "0:52:52", "remaining_time": "1:38:56"}
37
+ {"current_steps": 360, "total_steps": 1005, "loss": 0.5692, "learning_rate": 5e-06, "epoch": 1.0746268656716418, "percentage": 35.82, "elapsed_time": "0:54:19", "remaining_time": "1:37:19"}
38
+ {"current_steps": 370, "total_steps": 1005, "loss": 0.5534, "learning_rate": 5e-06, "epoch": 1.1044776119402986, "percentage": 36.82, "elapsed_time": "0:55:46", "remaining_time": "1:35:43"}
39
+ {"current_steps": 380, "total_steps": 1005, "loss": 0.5596, "learning_rate": 5e-06, "epoch": 1.1343283582089552, "percentage": 37.81, "elapsed_time": "0:57:13", "remaining_time": "1:34:07"}
40
+ {"current_steps": 390, "total_steps": 1005, "loss": 0.5603, "learning_rate": 5e-06, "epoch": 1.164179104477612, "percentage": 38.81, "elapsed_time": "0:58:40", "remaining_time": "1:32:30"}
41
+ {"current_steps": 400, "total_steps": 1005, "loss": 0.5477, "learning_rate": 5e-06, "epoch": 1.1940298507462686, "percentage": 39.8, "elapsed_time": "1:00:06", "remaining_time": "1:30:55"}
42
+ {"current_steps": 410, "total_steps": 1005, "loss": 0.5627, "learning_rate": 5e-06, "epoch": 1.2238805970149254, "percentage": 40.8, "elapsed_time": "1:01:33", "remaining_time": "1:29:20"}
43
+ {"current_steps": 420, "total_steps": 1005, "loss": 0.5613, "learning_rate": 5e-06, "epoch": 1.2537313432835822, "percentage": 41.79, "elapsed_time": "1:03:00", "remaining_time": "1:27:45"}
44
+ {"current_steps": 430, "total_steps": 1005, "loss": 0.5599, "learning_rate": 5e-06, "epoch": 1.2835820895522387, "percentage": 42.79, "elapsed_time": "1:04:27", "remaining_time": "1:26:11"}
45
+ {"current_steps": 440, "total_steps": 1005, "loss": 0.5506, "learning_rate": 5e-06, "epoch": 1.3134328358208955, "percentage": 43.78, "elapsed_time": "1:05:53", "remaining_time": "1:24:37"}
46
+ {"current_steps": 450, "total_steps": 1005, "loss": 0.5576, "learning_rate": 5e-06, "epoch": 1.3432835820895521, "percentage": 44.78, "elapsed_time": "1:07:21", "remaining_time": "1:23:04"}
47
+ {"current_steps": 460, "total_steps": 1005, "loss": 0.5604, "learning_rate": 5e-06, "epoch": 1.373134328358209, "percentage": 45.77, "elapsed_time": "1:08:48", "remaining_time": "1:21:31"}
48
+ {"current_steps": 470, "total_steps": 1005, "loss": 0.559, "learning_rate": 5e-06, "epoch": 1.4029850746268657, "percentage": 46.77, "elapsed_time": "1:10:15", "remaining_time": "1:19:58"}
49
+ {"current_steps": 480, "total_steps": 1005, "loss": 0.5598, "learning_rate": 5e-06, "epoch": 1.4328358208955223, "percentage": 47.76, "elapsed_time": "1:11:43", "remaining_time": "1:18:26"}
50
+ {"current_steps": 490, "total_steps": 1005, "loss": 0.5609, "learning_rate": 5e-06, "epoch": 1.462686567164179, "percentage": 48.76, "elapsed_time": "1:13:09", "remaining_time": "1:16:53"}
51
+ {"current_steps": 500, "total_steps": 1005, "loss": 0.5594, "learning_rate": 5e-06, "epoch": 1.4925373134328357, "percentage": 49.75, "elapsed_time": "1:14:36", "remaining_time": "1:15:21"}
52
+ {"current_steps": 510, "total_steps": 1005, "loss": 0.5596, "learning_rate": 5e-06, "epoch": 1.5223880597014925, "percentage": 50.75, "elapsed_time": "1:16:03", "remaining_time": "1:13:49"}
53
+ {"current_steps": 520, "total_steps": 1005, "loss": 0.5656, "learning_rate": 5e-06, "epoch": 1.5522388059701493, "percentage": 51.74, "elapsed_time": "1:17:30", "remaining_time": "1:12:17"}
54
+ {"current_steps": 530, "total_steps": 1005, "loss": 0.5566, "learning_rate": 5e-06, "epoch": 1.582089552238806, "percentage": 52.74, "elapsed_time": "1:18:57", "remaining_time": "1:10:46"}
55
+ {"current_steps": 540, "total_steps": 1005, "loss": 0.5585, "learning_rate": 5e-06, "epoch": 1.6119402985074627, "percentage": 53.73, "elapsed_time": "1:20:24", "remaining_time": "1:09:14"}
56
+ {"current_steps": 550, "total_steps": 1005, "loss": 0.5546, "learning_rate": 5e-06, "epoch": 1.6417910447761193, "percentage": 54.73, "elapsed_time": "1:21:51", "remaining_time": "1:07:43"}
57
+ {"current_steps": 560, "total_steps": 1005, "loss": 0.5556, "learning_rate": 5e-06, "epoch": 1.671641791044776, "percentage": 55.72, "elapsed_time": "1:23:19", "remaining_time": "1:06:12"}
58
+ {"current_steps": 570, "total_steps": 1005, "loss": 0.5532, "learning_rate": 5e-06, "epoch": 1.7014925373134329, "percentage": 56.72, "elapsed_time": "1:24:46", "remaining_time": "1:04:41"}
59
+ {"current_steps": 580, "total_steps": 1005, "loss": 0.5525, "learning_rate": 5e-06, "epoch": 1.7313432835820897, "percentage": 57.71, "elapsed_time": "1:26:13", "remaining_time": "1:03:10"}
60
+ {"current_steps": 590, "total_steps": 1005, "loss": 0.562, "learning_rate": 5e-06, "epoch": 1.7611940298507462, "percentage": 58.71, "elapsed_time": "1:27:40", "remaining_time": "1:01:39"}
61
+ {"current_steps": 600, "total_steps": 1005, "loss": 0.5639, "learning_rate": 5e-06, "epoch": 1.7910447761194028, "percentage": 59.7, "elapsed_time": "1:29:07", "remaining_time": "1:00:09"}
62
+ {"current_steps": 610, "total_steps": 1005, "loss": 0.5551, "learning_rate": 5e-06, "epoch": 1.8208955223880596, "percentage": 60.7, "elapsed_time": "1:30:33", "remaining_time": "0:58:38"}
63
+ {"current_steps": 620, "total_steps": 1005, "loss": 0.5584, "learning_rate": 5e-06, "epoch": 1.8507462686567164, "percentage": 61.69, "elapsed_time": "1:32:00", "remaining_time": "0:57:08"}
64
+ {"current_steps": 630, "total_steps": 1005, "loss": 0.564, "learning_rate": 5e-06, "epoch": 1.8805970149253732, "percentage": 62.69, "elapsed_time": "1:33:27", "remaining_time": "0:55:37"}
65
+ {"current_steps": 640, "total_steps": 1005, "loss": 0.5541, "learning_rate": 5e-06, "epoch": 1.9104477611940298, "percentage": 63.68, "elapsed_time": "1:34:53", "remaining_time": "0:54:07"}
66
+ {"current_steps": 650, "total_steps": 1005, "loss": 0.5557, "learning_rate": 5e-06, "epoch": 1.9402985074626866, "percentage": 64.68, "elapsed_time": "1:36:20", "remaining_time": "0:52:37"}
67
+ {"current_steps": 660, "total_steps": 1005, "loss": 0.5544, "learning_rate": 5e-06, "epoch": 1.9701492537313432, "percentage": 65.67, "elapsed_time": "1:37:47", "remaining_time": "0:51:06"}
68
+ {"current_steps": 670, "total_steps": 1005, "loss": 0.5528, "learning_rate": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:39:13", "remaining_time": "0:49:36"}
69
+ {"current_steps": 670, "total_steps": 1005, "eval_loss": 0.6019102334976196, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:40:14", "remaining_time": "0:50:07"}
70
+ {"current_steps": 680, "total_steps": 1005, "loss": 0.5048, "learning_rate": 5e-06, "epoch": 2.029850746268657, "percentage": 67.66, "elapsed_time": "1:42:40", "remaining_time": "0:49:04"}
training_args.bin.sagemaker-uploaded ADDED
File without changes