Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v3.1-llama-3.1-405b

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
gsmyrnis commited on
Commit
b84621f
·
verified ·
1 Parent(s): 4d8ef13

Training in progress, epoch 3

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 sha256:0f2f1ddded1d2396006b280219cdf6742ae611a284028001ff9e1234e2b00c60
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d26ac89b433098421fed856645e713bd1b6a77e12f30775e2bdb04a6418350a2
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:a6d2d5db3ea39ebad270e00b28eb4cf1d8edd6d6d945a06f8748feb33a46a337
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e369b152203a4637d5390d5d275a193464a58055e136ab366d2652d89878b75e
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8013eaf77d81598fe97415aa42849412a1ee397f6dc4500f72e1078d28e2b68a
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c123299d6fae495f4f23650c70503f25676f9b440d19f2858084c4e92edde846
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6012b5aed8766f14025f784803bb19a36652bb6f0ee1486a0e293dd32cb2ffb6
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5fede60b30e9f4b392b6849c679350f1b469036bb25f8bd24fe69022be1205
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -87,3 +87,44 @@
87
  {"current_steps": 850, "total_steps": 1266, "loss": 0.2369, "lr": 5e-06, "epoch": 2.014218009478673, "percentage": 67.14, "elapsed_time": "1:28:00", "remaining_time": "0:43:04"}
88
  {"current_steps": 860, "total_steps": 1266, "loss": 0.2195, "lr": 5e-06, "epoch": 2.037914691943128, "percentage": 67.93, "elapsed_time": "1:28:58", "remaining_time": "0:42:00"}
89
  {"current_steps": 870, "total_steps": 1266, "loss": 0.2199, "lr": 5e-06, "epoch": 2.061611374407583, "percentage": 68.72, "elapsed_time": "1:29:59", "remaining_time": "0:40:57"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
87
  {"current_steps": 850, "total_steps": 1266, "loss": 0.2369, "lr": 5e-06, "epoch": 2.014218009478673, "percentage": 67.14, "elapsed_time": "1:28:00", "remaining_time": "0:43:04"}
88
  {"current_steps": 860, "total_steps": 1266, "loss": 0.2195, "lr": 5e-06, "epoch": 2.037914691943128, "percentage": 67.93, "elapsed_time": "1:28:58", "remaining_time": "0:42:00"}
89
  {"current_steps": 870, "total_steps": 1266, "loss": 0.2199, "lr": 5e-06, "epoch": 2.061611374407583, "percentage": 68.72, "elapsed_time": "1:29:59", "remaining_time": "0:40:57"}
90
+ {"current_steps": 880, "total_steps": 1266, "loss": 0.2204, "lr": 5e-06, "epoch": 2.085308056872038, "percentage": 69.51, "elapsed_time": "1:30:57", "remaining_time": "0:39:53"}
91
+ {"current_steps": 890, "total_steps": 1266, "loss": 0.2207, "lr": 5e-06, "epoch": 2.109004739336493, "percentage": 70.3, "elapsed_time": "1:31:56", "remaining_time": "0:38:50"}
92
+ {"current_steps": 900, "total_steps": 1266, "loss": 0.2205, "lr": 5e-06, "epoch": 2.132701421800948, "percentage": 71.09, "elapsed_time": "1:32:55", "remaining_time": "0:37:47"}
93
+ {"current_steps": 910, "total_steps": 1266, "loss": 0.2202, "lr": 5e-06, "epoch": 2.156398104265403, "percentage": 71.88, "elapsed_time": "1:33:53", "remaining_time": "0:36:43"}
94
+ {"current_steps": 920, "total_steps": 1266, "loss": 0.2213, "lr": 5e-06, "epoch": 2.1800947867298577, "percentage": 72.67, "elapsed_time": "1:34:51", "remaining_time": "0:35:40"}
95
+ {"current_steps": 930, "total_steps": 1266, "loss": 0.2237, "lr": 5e-06, "epoch": 2.2037914691943126, "percentage": 73.46, "elapsed_time": "1:35:50", "remaining_time": "0:34:37"}
96
+ {"current_steps": 940, "total_steps": 1266, "loss": 0.2196, "lr": 5e-06, "epoch": 2.227488151658768, "percentage": 74.25, "elapsed_time": "1:36:48", "remaining_time": "0:33:34"}
97
+ {"current_steps": 950, "total_steps": 1266, "loss": 0.2213, "lr": 5e-06, "epoch": 2.251184834123223, "percentage": 75.04, "elapsed_time": "1:37:48", "remaining_time": "0:32:32"}
98
+ {"current_steps": 960, "total_steps": 1266, "loss": 0.22, "lr": 5e-06, "epoch": 2.2748815165876777, "percentage": 75.83, "elapsed_time": "1:38:46", "remaining_time": "0:31:29"}
99
+ {"current_steps": 970, "total_steps": 1266, "loss": 0.2209, "lr": 5e-06, "epoch": 2.2985781990521326, "percentage": 76.62, "elapsed_time": "1:39:45", "remaining_time": "0:30:26"}
100
+ {"current_steps": 980, "total_steps": 1266, "loss": 0.225, "lr": 5e-06, "epoch": 2.322274881516588, "percentage": 77.41, "elapsed_time": "1:40:44", "remaining_time": "0:29:24"}
101
+ {"current_steps": 990, "total_steps": 1266, "loss": 0.2236, "lr": 5e-06, "epoch": 2.345971563981043, "percentage": 78.2, "elapsed_time": "1:41:43", "remaining_time": "0:28:21"}
102
+ {"current_steps": 1000, "total_steps": 1266, "loss": 0.2216, "lr": 5e-06, "epoch": 2.3696682464454977, "percentage": 78.99, "elapsed_time": "1:42:42", "remaining_time": "0:27:19"}
103
+ {"current_steps": 1010, "total_steps": 1266, "loss": 0.2233, "lr": 5e-06, "epoch": 2.3933649289099526, "percentage": 79.78, "elapsed_time": "1:43:40", "remaining_time": "0:26:16"}
104
+ {"current_steps": 1020, "total_steps": 1266, "loss": 0.2228, "lr": 5e-06, "epoch": 2.4170616113744074, "percentage": 80.57, "elapsed_time": "1:44:38", "remaining_time": "0:25:14"}
105
+ {"current_steps": 1030, "total_steps": 1266, "loss": 0.2226, "lr": 5e-06, "epoch": 2.4407582938388623, "percentage": 81.36, "elapsed_time": "1:45:36", "remaining_time": "0:24:11"}
106
+ {"current_steps": 1040, "total_steps": 1266, "loss": 0.2211, "lr": 5e-06, "epoch": 2.4644549763033177, "percentage": 82.15, "elapsed_time": "1:46:35", "remaining_time": "0:23:09"}
107
+ {"current_steps": 1050, "total_steps": 1266, "loss": 0.2225, "lr": 5e-06, "epoch": 2.4881516587677726, "percentage": 82.94, "elapsed_time": "1:47:34", "remaining_time": "0:22:07"}
108
+ {"current_steps": 1060, "total_steps": 1266, "loss": 0.2207, "lr": 5e-06, "epoch": 2.5118483412322274, "percentage": 83.73, "elapsed_time": "1:48:33", "remaining_time": "0:21:05"}
109
+ {"current_steps": 1070, "total_steps": 1266, "loss": 0.2224, "lr": 5e-06, "epoch": 2.5355450236966823, "percentage": 84.52, "elapsed_time": "1:49:32", "remaining_time": "0:20:03"}
110
+ {"current_steps": 1080, "total_steps": 1266, "loss": 0.2193, "lr": 5e-06, "epoch": 2.5592417061611377, "percentage": 85.31, "elapsed_time": "1:50:32", "remaining_time": "0:19:02"}
111
+ {"current_steps": 1090, "total_steps": 1266, "loss": 0.2215, "lr": 5e-06, "epoch": 2.5829383886255926, "percentage": 86.1, "elapsed_time": "1:51:30", "remaining_time": "0:18:00"}
112
+ {"current_steps": 1100, "total_steps": 1266, "loss": 0.2239, "lr": 5e-06, "epoch": 2.6066350710900474, "percentage": 86.89, "elapsed_time": "1:52:29", "remaining_time": "0:16:58"}
113
+ {"current_steps": 1110, "total_steps": 1266, "loss": 0.225, "lr": 5e-06, "epoch": 2.6303317535545023, "percentage": 87.68, "elapsed_time": "1:53:27", "remaining_time": "0:15:56"}
114
+ {"current_steps": 1120, "total_steps": 1266, "loss": 0.2217, "lr": 5e-06, "epoch": 2.654028436018957, "percentage": 88.47, "elapsed_time": "1:54:25", "remaining_time": "0:14:54"}
115
+ {"current_steps": 1130, "total_steps": 1266, "loss": 0.2223, "lr": 5e-06, "epoch": 2.677725118483412, "percentage": 89.26, "elapsed_time": "1:55:23", "remaining_time": "0:13:53"}
116
+ {"current_steps": 1140, "total_steps": 1266, "loss": 0.2202, "lr": 5e-06, "epoch": 2.7014218009478674, "percentage": 90.05, "elapsed_time": "1:56:22", "remaining_time": "0:12:51"}
117
+ {"current_steps": 1150, "total_steps": 1266, "loss": 0.2203, "lr": 5e-06, "epoch": 2.7251184834123223, "percentage": 90.84, "elapsed_time": "1:57:20", "remaining_time": "0:11:50"}
118
+ {"current_steps": 1160, "total_steps": 1266, "loss": 0.2195, "lr": 5e-06, "epoch": 2.748815165876777, "percentage": 91.63, "elapsed_time": "1:58:19", "remaining_time": "0:10:48"}
119
+ {"current_steps": 1170, "total_steps": 1266, "loss": 0.2201, "lr": 5e-06, "epoch": 2.772511848341232, "percentage": 92.42, "elapsed_time": "1:59:18", "remaining_time": "0:09:47"}
120
+ {"current_steps": 1180, "total_steps": 1266, "loss": 0.2241, "lr": 5e-06, "epoch": 2.7962085308056874, "percentage": 93.21, "elapsed_time": "2:00:17", "remaining_time": "0:08:46"}
121
+ {"current_steps": 1190, "total_steps": 1266, "loss": 0.2185, "lr": 5e-06, "epoch": 2.8199052132701423, "percentage": 94.0, "elapsed_time": "2:01:15", "remaining_time": "0:07:44"}
122
+ {"current_steps": 1200, "total_steps": 1266, "loss": 0.2218, "lr": 5e-06, "epoch": 2.843601895734597, "percentage": 94.79, "elapsed_time": "2:02:14", "remaining_time": "0:06:43"}
123
+ {"current_steps": 1210, "total_steps": 1266, "loss": 0.2211, "lr": 5e-06, "epoch": 2.867298578199052, "percentage": 95.58, "elapsed_time": "2:03:12", "remaining_time": "0:05:42"}
124
+ {"current_steps": 1220, "total_steps": 1266, "loss": 0.2194, "lr": 5e-06, "epoch": 2.890995260663507, "percentage": 96.37, "elapsed_time": "2:04:10", "remaining_time": "0:04:40"}
125
+ {"current_steps": 1230, "total_steps": 1266, "loss": 0.2258, "lr": 5e-06, "epoch": 2.914691943127962, "percentage": 97.16, "elapsed_time": "2:05:09", "remaining_time": "0:03:39"}
126
+ {"current_steps": 1240, "total_steps": 1266, "loss": 0.2218, "lr": 5e-06, "epoch": 2.938388625592417, "percentage": 97.95, "elapsed_time": "2:06:07", "remaining_time": "0:02:38"}
127
+ {"current_steps": 1250, "total_steps": 1266, "loss": 0.2211, "lr": 5e-06, "epoch": 2.962085308056872, "percentage": 98.74, "elapsed_time": "2:07:07", "remaining_time": "0:01:37"}
128
+ {"current_steps": 1260, "total_steps": 1266, "loss": 0.2241, "lr": 5e-06, "epoch": 2.985781990521327, "percentage": 99.53, "elapsed_time": "2:08:39", "remaining_time": "0:00:36"}
129
+ {"current_steps": 1266, "total_steps": 1266, "eval_loss": 0.30088362097740173, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:11:24", "remaining_time": "0:00:00"}
130
+ {"current_steps": 1266, "total_steps": 1266, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:13:03", "remaining_time": "0:00:00"}