Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v3.1-claude-3-5-haiku-20241022

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
be0a0eb
•
1 Parent(s): 3ab8d58

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 +41 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:882fbc354c93cc6d2545c230e08d49544a6345f90a3cae9676b6d1d9a27f5c7f
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d89090294f2cac6c6342665ff4c0eb70cb472b310e315d43ca09a54d4490521
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8c3ea15e5a737d9b96e657dcc96800fa88a91ee3c116b0a6d7242e7ba2b9284
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f1fa1cfe66b292ee53ee30c83dcb27af13dfcf8209c51e4fa98dff2f2164b7c
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eead24df65cb4f657d37539f22bd814d064a4cb32d1e8b1db76a7f727a3a520f
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:683dd4fbc604c51b2f41e1cf990ebeb3b816dde501cae68e5b1eeef645c99b56
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:916cfd550ce712604c09205a3b11f5ac6e3a026ead73678953fd66acd3247d60
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7753b866151984244767cf0aef745b4529082a8835af0dacd8e9ede6b9ebc42c
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -84,3 +84,44 @@
84
  {"current_steps": 830, "total_steps": 1257, "loss": 0.3953, "lr": 5e-06, "epoch": 1.9785650491217623, "percentage": 66.03, "elapsed_time": "7:28:12", "remaining_time": "3:50:35"}
85
  {"current_steps": 838, "total_steps": 1257, "eval_loss": 0.43693724274635315, "epoch": 1.997618338791307, "percentage": 66.67, "elapsed_time": "7:37:21", "remaining_time": "3:48:40"}
86
  {"current_steps": 840, "total_steps": 1257, "loss": 0.4321, "lr": 5e-06, "epoch": 2.004167907115213, "percentage": 66.83, "elapsed_time": "7:39:36", "remaining_time": "3:48:09"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  {"current_steps": 830, "total_steps": 1257, "loss": 0.3953, "lr": 5e-06, "epoch": 1.9785650491217623, "percentage": 66.03, "elapsed_time": "7:28:12", "remaining_time": "3:50:35"}
85
  {"current_steps": 838, "total_steps": 1257, "eval_loss": 0.43693724274635315, "epoch": 1.997618338791307, "percentage": 66.67, "elapsed_time": "7:37:21", "remaining_time": "3:48:40"}
86
  {"current_steps": 840, "total_steps": 1257, "loss": 0.4321, "lr": 5e-06, "epoch": 2.004167907115213, "percentage": 66.83, "elapsed_time": "7:39:36", "remaining_time": "3:48:09"}
87
+ {"current_steps": 850, "total_steps": 1257, "loss": 0.3538, "lr": 5e-06, "epoch": 2.0279845192021435, "percentage": 67.62, "elapsed_time": "7:44:53", "remaining_time": "3:42:35"}
88
+ {"current_steps": 860, "total_steps": 1257, "loss": 0.353, "lr": 5e-06, "epoch": 2.051801131289074, "percentage": 68.42, "elapsed_time": "7:50:09", "remaining_time": "3:37:02"}
89
+ {"current_steps": 870, "total_steps": 1257, "loss": 0.3476, "lr": 5e-06, "epoch": 2.0756177433760046, "percentage": 69.21, "elapsed_time": "7:55:28", "remaining_time": "3:31:30"}
90
+ {"current_steps": 880, "total_steps": 1257, "loss": 0.3513, "lr": 5e-06, "epoch": 2.0994343554629356, "percentage": 70.01, "elapsed_time": "8:00:47", "remaining_time": "3:25:58"}
91
+ {"current_steps": 890, "total_steps": 1257, "loss": 0.352, "lr": 5e-06, "epoch": 2.123250967549866, "percentage": 70.8, "elapsed_time": "8:06:07", "remaining_time": "3:20:27"}
92
+ {"current_steps": 900, "total_steps": 1257, "loss": 0.3509, "lr": 5e-06, "epoch": 2.1470675796367966, "percentage": 71.6, "elapsed_time": "8:11:26", "remaining_time": "3:14:56"}
93
+ {"current_steps": 910, "total_steps": 1257, "loss": 0.3517, "lr": 5e-06, "epoch": 2.170884191723727, "percentage": 72.39, "elapsed_time": "8:16:43", "remaining_time": "3:09:24"}
94
+ {"current_steps": 920, "total_steps": 1257, "loss": 0.3547, "lr": 5e-06, "epoch": 2.194700803810658, "percentage": 73.19, "elapsed_time": "8:22:02", "remaining_time": "3:03:53"}
95
+ {"current_steps": 930, "total_steps": 1257, "loss": 0.3513, "lr": 5e-06, "epoch": 2.2185174158975887, "percentage": 73.99, "elapsed_time": "8:27:21", "remaining_time": "2:58:23"}
96
+ {"current_steps": 940, "total_steps": 1257, "loss": 0.3534, "lr": 5e-06, "epoch": 2.242334027984519, "percentage": 74.78, "elapsed_time": "8:32:42", "remaining_time": "2:52:54"}
97
+ {"current_steps": 950, "total_steps": 1257, "loss": 0.3525, "lr": 5e-06, "epoch": 2.2661506400714497, "percentage": 75.58, "elapsed_time": "8:38:02", "remaining_time": "2:47:24"}
98
+ {"current_steps": 960, "total_steps": 1257, "loss": 0.3561, "lr": 5e-06, "epoch": 2.2899672521583803, "percentage": 76.37, "elapsed_time": "8:43:20", "remaining_time": "2:41:54"}
99
+ {"current_steps": 970, "total_steps": 1257, "loss": 0.3574, "lr": 5e-06, "epoch": 2.3137838642453112, "percentage": 77.17, "elapsed_time": "8:48:39", "remaining_time": "2:36:25"}
100
+ {"current_steps": 980, "total_steps": 1257, "loss": 0.3568, "lr": 5e-06, "epoch": 2.3376004763322418, "percentage": 77.96, "elapsed_time": "8:53:58", "remaining_time": "2:30:55"}
101
+ {"current_steps": 990, "total_steps": 1257, "loss": 0.3545, "lr": 5e-06, "epoch": 2.3614170884191723, "percentage": 78.76, "elapsed_time": "8:59:18", "remaining_time": "2:25:26"}
102
+ {"current_steps": 1000, "total_steps": 1257, "loss": 0.3503, "lr": 5e-06, "epoch": 2.385233700506103, "percentage": 79.55, "elapsed_time": "9:04:37", "remaining_time": "2:19:58"}
103
+ {"current_steps": 1010, "total_steps": 1257, "loss": 0.3539, "lr": 5e-06, "epoch": 2.409050312593034, "percentage": 80.35, "elapsed_time": "9:09:55", "remaining_time": "2:14:29"}
104
+ {"current_steps": 1020, "total_steps": 1257, "loss": 0.3567, "lr": 5e-06, "epoch": 2.4328669246799643, "percentage": 81.15, "elapsed_time": "9:15:15", "remaining_time": "2:09:00"}
105
+ {"current_steps": 1030, "total_steps": 1257, "loss": 0.355, "lr": 5e-06, "epoch": 2.456683536766895, "percentage": 81.94, "elapsed_time": "9:20:35", "remaining_time": "2:03:32"}
106
+ {"current_steps": 1040, "total_steps": 1257, "loss": 0.3551, "lr": 5e-06, "epoch": 2.4805001488538254, "percentage": 82.74, "elapsed_time": "9:25:54", "remaining_time": "1:58:04"}
107
+ {"current_steps": 1050, "total_steps": 1257, "loss": 0.3552, "lr": 5e-06, "epoch": 2.504316760940756, "percentage": 83.53, "elapsed_time": "9:31:13", "remaining_time": "1:52:36"}
108
+ {"current_steps": 1060, "total_steps": 1257, "loss": 0.3532, "lr": 5e-06, "epoch": 2.528133373027687, "percentage": 84.33, "elapsed_time": "9:36:33", "remaining_time": "1:47:09"}
109
+ {"current_steps": 1070, "total_steps": 1257, "loss": 0.3546, "lr": 5e-06, "epoch": 2.5519499851146175, "percentage": 85.12, "elapsed_time": "9:41:52", "remaining_time": "1:41:41"}
110
+ {"current_steps": 1080, "total_steps": 1257, "loss": 0.356, "lr": 5e-06, "epoch": 2.575766597201548, "percentage": 85.92, "elapsed_time": "9:47:11", "remaining_time": "1:36:14"}
111
+ {"current_steps": 1090, "total_steps": 1257, "loss": 0.3593, "lr": 5e-06, "epoch": 2.599583209288479, "percentage": 86.71, "elapsed_time": "9:52:31", "remaining_time": "1:30:46"}
112
+ {"current_steps": 1100, "total_steps": 1257, "loss": 0.3574, "lr": 5e-06, "epoch": 2.6233998213754095, "percentage": 87.51, "elapsed_time": "9:57:50", "remaining_time": "1:25:19"}
113
+ {"current_steps": 1110, "total_steps": 1257, "loss": 0.3582, "lr": 5e-06, "epoch": 2.64721643346234, "percentage": 88.31, "elapsed_time": "10:03:09", "remaining_time": "1:19:52"}
114
+ {"current_steps": 1120, "total_steps": 1257, "loss": 0.3567, "lr": 5e-06, "epoch": 2.6710330455492706, "percentage": 89.1, "elapsed_time": "10:08:28", "remaining_time": "1:14:25"}
115
+ {"current_steps": 1130, "total_steps": 1257, "loss": 0.3574, "lr": 5e-06, "epoch": 2.694849657636201, "percentage": 89.9, "elapsed_time": "10:13:47", "remaining_time": "1:08:59"}
116
+ {"current_steps": 1140, "total_steps": 1257, "loss": 0.3547, "lr": 5e-06, "epoch": 2.7186662697231316, "percentage": 90.69, "elapsed_time": "10:19:07", "remaining_time": "1:03:32"}
117
+ {"current_steps": 1150, "total_steps": 1257, "loss": 0.3547, "lr": 5e-06, "epoch": 2.7424828818100626, "percentage": 91.49, "elapsed_time": "10:24:26", "remaining_time": "0:58:06"}
118
+ {"current_steps": 1160, "total_steps": 1257, "loss": 0.3586, "lr": 5e-06, "epoch": 2.766299493896993, "percentage": 92.28, "elapsed_time": "10:29:46", "remaining_time": "0:52:39"}
119
+ {"current_steps": 1170, "total_steps": 1257, "loss": 0.3498, "lr": 5e-06, "epoch": 2.7901161059839237, "percentage": 93.08, "elapsed_time": "10:35:06", "remaining_time": "0:47:13"}
120
+ {"current_steps": 1180, "total_steps": 1257, "loss": 0.3611, "lr": 5e-06, "epoch": 2.8139327180708547, "percentage": 93.87, "elapsed_time": "10:40:25", "remaining_time": "0:41:47"}
121
+ {"current_steps": 1190, "total_steps": 1257, "loss": 0.3593, "lr": 5e-06, "epoch": 2.837749330157785, "percentage": 94.67, "elapsed_time": "10:45:44", "remaining_time": "0:36:21"}
122
+ {"current_steps": 1200, "total_steps": 1257, "loss": 0.357, "lr": 5e-06, "epoch": 2.8615659422447157, "percentage": 95.47, "elapsed_time": "10:51:03", "remaining_time": "0:30:55"}
123
+ {"current_steps": 1210, "total_steps": 1257, "loss": 0.356, "lr": 5e-06, "epoch": 2.8853825543316463, "percentage": 96.26, "elapsed_time": "10:56:23", "remaining_time": "0:25:29"}
124
+ {"current_steps": 1220, "total_steps": 1257, "loss": 0.357, "lr": 5e-06, "epoch": 2.909199166418577, "percentage": 97.06, "elapsed_time": "11:01:43", "remaining_time": "0:20:04"}
125
+ {"current_steps": 1230, "total_steps": 1257, "loss": 0.3531, "lr": 5e-06, "epoch": 2.9330157785055073, "percentage": 97.85, "elapsed_time": "11:07:02", "remaining_time": "0:14:38"}
126
+ {"current_steps": 1240, "total_steps": 1257, "loss": 0.3583, "lr": 5e-06, "epoch": 2.9568323905924383, "percentage": 98.65, "elapsed_time": "11:12:22", "remaining_time": "0:09:13"}
127
+ {"current_steps": 1250, "total_steps": 1257, "loss": 0.3539, "lr": 5e-06, "epoch": 2.980649002679369, "percentage": 99.44, "elapsed_time": "11:17:42", "remaining_time": "0:03:47"}