Hugging Face's logo

mlfoundations-dev
/
oh_v1.3_opengpt_x2

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
gsmyrnis commited on
Commit
7ab0ec6
·
verified ·
1 Parent(s): aae557e

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 +27 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c663a80ef595fde4b6adf06c0387ed45da1be47a9d1836fbd21acd0fe820398
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e6a5e0618d3a3acdfac4fd91a62f411e699007ab38bacbe7bbefa76a72ad22
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79fdc144370dccffab74eff6413a9189dc13bf88d7c2fc7d18ffc578e6ecaae0
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91dd3b85dd05b3caa81d1a98a290b257589ecd2c6e33080dcc862caf572a43ac
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e929ee0f6714d2ed5e65215336ddebb41a3e3fb9889a4a863f9ca3da18f0576
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f27b08b9dd7e1fe42cda95a25c0ac4fd8b73aab5af0aef5325f47c34f537091d
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a1e08177ef47e01a8cb3d8bb3c9b69ed573c95f6c24005027cde95d87c8513a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9266dd59e94e0c04302fd8a5f884675c67b8162d09d22dff5732314377716358
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -57,3 +57,30 @@
57
  {"current_steps": 550, "total_steps": 822, "loss": 0.6708, "learning_rate": 5e-06, "epoch": 2.0072992700729926, "percentage": 66.91, "elapsed_time": "0:58:10", "remaining_time": "0:28:46"}
58
  {"current_steps": 560, "total_steps": 822, "loss": 0.6358, "learning_rate": 5e-06, "epoch": 2.0437956204379564, "percentage": 68.13, "elapsed_time": "0:59:08", "remaining_time": "0:27:40"}
59
  {"current_steps": 570, "total_steps": 822, "loss": 0.6306, "learning_rate": 5e-06, "epoch": 2.0802919708029197, "percentage": 69.34, "elapsed_time": "1:00:06", "remaining_time": "0:26:34"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  {"current_steps": 550, "total_steps": 822, "loss": 0.6708, "learning_rate": 5e-06, "epoch": 2.0072992700729926, "percentage": 66.91, "elapsed_time": "0:58:10", "remaining_time": "0:28:46"}
58
  {"current_steps": 560, "total_steps": 822, "loss": 0.6358, "learning_rate": 5e-06, "epoch": 2.0437956204379564, "percentage": 68.13, "elapsed_time": "0:59:08", "remaining_time": "0:27:40"}
59
  {"current_steps": 570, "total_steps": 822, "loss": 0.6306, "learning_rate": 5e-06, "epoch": 2.0802919708029197, "percentage": 69.34, "elapsed_time": "1:00:06", "remaining_time": "0:26:34"}
60
+ {"current_steps": 580, "total_steps": 822, "loss": 0.6289, "learning_rate": 5e-06, "epoch": 2.116788321167883, "percentage": 70.56, "elapsed_time": "1:01:04", "remaining_time": "0:25:29"}
61
+ {"current_steps": 590, "total_steps": 822, "loss": 0.6303, "learning_rate": 5e-06, "epoch": 2.153284671532847, "percentage": 71.78, "elapsed_time": "1:02:02", "remaining_time": "0:24:23"}
62
+ {"current_steps": 600, "total_steps": 822, "loss": 0.6291, "learning_rate": 5e-06, "epoch": 2.18978102189781, "percentage": 72.99, "elapsed_time": "1:03:01", "remaining_time": "0:23:19"}
63
+ {"current_steps": 610, "total_steps": 822, "loss": 0.6266, "learning_rate": 5e-06, "epoch": 2.2262773722627736, "percentage": 74.21, "elapsed_time": "1:03:59", "remaining_time": "0:22:14"}
64
+ {"current_steps": 620, "total_steps": 822, "loss": 0.6316, "learning_rate": 5e-06, "epoch": 2.2627737226277373, "percentage": 75.43, "elapsed_time": "1:04:57", "remaining_time": "0:21:09"}
65
+ {"current_steps": 630, "total_steps": 822, "loss": 0.6324, "learning_rate": 5e-06, "epoch": 2.2992700729927007, "percentage": 76.64, "elapsed_time": "1:05:55", "remaining_time": "0:20:05"}
66
+ {"current_steps": 640, "total_steps": 822, "loss": 0.6276, "learning_rate": 5e-06, "epoch": 2.335766423357664, "percentage": 77.86, "elapsed_time": "1:06:54", "remaining_time": "0:19:01"}
67
+ {"current_steps": 650, "total_steps": 822, "loss": 0.6376, "learning_rate": 5e-06, "epoch": 2.372262773722628, "percentage": 79.08, "elapsed_time": "1:07:52", "remaining_time": "0:17:57"}
68
+ {"current_steps": 660, "total_steps": 822, "loss": 0.6287, "learning_rate": 5e-06, "epoch": 2.408759124087591, "percentage": 80.29, "elapsed_time": "1:08:50", "remaining_time": "0:16:53"}
69
+ {"current_steps": 670, "total_steps": 822, "loss": 0.6355, "learning_rate": 5e-06, "epoch": 2.445255474452555, "percentage": 81.51, "elapsed_time": "1:09:48", "remaining_time": "0:15:50"}
70
+ {"current_steps": 680, "total_steps": 822, "loss": 0.6361, "learning_rate": 5e-06, "epoch": 2.4817518248175183, "percentage": 82.73, "elapsed_time": "1:10:46", "remaining_time": "0:14:46"}
71
+ {"current_steps": 690, "total_steps": 822, "loss": 0.6377, "learning_rate": 5e-06, "epoch": 2.5182481751824817, "percentage": 83.94, "elapsed_time": "1:11:45", "remaining_time": "0:13:43"}
72
+ {"current_steps": 700, "total_steps": 822, "loss": 0.6348, "learning_rate": 5e-06, "epoch": 2.554744525547445, "percentage": 85.16, "elapsed_time": "1:12:43", "remaining_time": "0:12:40"}
73
+ {"current_steps": 710, "total_steps": 822, "loss": 0.6409, "learning_rate": 5e-06, "epoch": 2.591240875912409, "percentage": 86.37, "elapsed_time": "1:13:41", "remaining_time": "0:11:37"}
74
+ {"current_steps": 720, "total_steps": 822, "loss": 0.6295, "learning_rate": 5e-06, "epoch": 2.627737226277372, "percentage": 87.59, "elapsed_time": "1:14:39", "remaining_time": "0:10:34"}
75
+ {"current_steps": 730, "total_steps": 822, "loss": 0.6353, "learning_rate": 5e-06, "epoch": 2.664233576642336, "percentage": 88.81, "elapsed_time": "1:15:37", "remaining_time": "0:09:31"}
76
+ {"current_steps": 740, "total_steps": 822, "loss": 0.6363, "learning_rate": 5e-06, "epoch": 2.7007299270072993, "percentage": 90.02, "elapsed_time": "1:16:36", "remaining_time": "0:08:29"}
77
+ {"current_steps": 750, "total_steps": 822, "loss": 0.6349, "learning_rate": 5e-06, "epoch": 2.7372262773722627, "percentage": 91.24, "elapsed_time": "1:17:34", "remaining_time": "0:07:26"}
78
+ {"current_steps": 760, "total_steps": 822, "loss": 0.6407, "learning_rate": 5e-06, "epoch": 2.7737226277372264, "percentage": 92.46, "elapsed_time": "1:18:32", "remaining_time": "0:06:24"}
79
+ {"current_steps": 770, "total_steps": 822, "loss": 0.631, "learning_rate": 5e-06, "epoch": 2.81021897810219, "percentage": 93.67, "elapsed_time": "1:19:30", "remaining_time": "0:05:22"}
80
+ {"current_steps": 780, "total_steps": 822, "loss": 0.6298, "learning_rate": 5e-06, "epoch": 2.846715328467153, "percentage": 94.89, "elapsed_time": "1:20:28", "remaining_time": "0:04:20"}
81
+ {"current_steps": 790, "total_steps": 822, "loss": 0.6325, "learning_rate": 5e-06, "epoch": 2.883211678832117, "percentage": 96.11, "elapsed_time": "1:21:27", "remaining_time": "0:03:17"}
82
+ {"current_steps": 800, "total_steps": 822, "loss": 0.6425, "learning_rate": 5e-06, "epoch": 2.9197080291970803, "percentage": 97.32, "elapsed_time": "1:22:25", "remaining_time": "0:02:15"}
83
+ {"current_steps": 810, "total_steps": 822, "loss": 0.6323, "learning_rate": 5e-06, "epoch": 2.9562043795620436, "percentage": 98.54, "elapsed_time": "1:23:23", "remaining_time": "0:01:14"}
84
+ {"current_steps": 820, "total_steps": 822, "loss": 0.6383, "learning_rate": 5e-06, "epoch": 2.9927007299270074, "percentage": 99.76, "elapsed_time": "1:24:21", "remaining_time": "0:00:12"}
85
+ {"current_steps": 822, "total_steps": 822, "eval_loss": 0.7370563745498657, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:26:35", "remaining_time": "0:00:00"}
86
+ {"current_steps": 822, "total_steps": 822, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:28:03", "remaining_time": "0:00:00"}