Hugging Face's logo

SystemAdmin123
/
llama-7b

Safetensors
llama
Model card Files
xet
Community
SystemAdmin123 commited on
Commit
8dd8221
·
verified ·
1 Parent(s): 04490fd

Training in progress, step 60, checkpoint

Browse files
Files changed (10) hide show
  1. last-checkpoint/model-00001-of-00003.safetensors +1 -1
  2. last-checkpoint/model-00002-of-00003.safetensors +1 -1
  3. last-checkpoint/model-00003-of-00003.safetensors +1 -1
  4. last-checkpoint/optimizer.pt +1 -1
  5. last-checkpoint/rng_state_0.pth +1 -1
  6. last-checkpoint/rng_state_1.pth +1 -1
  7. last-checkpoint/rng_state_2.pth +1 -1
  8. last-checkpoint/rng_state_3.pth +1 -1
  9. last-checkpoint/scheduler.pt +1 -1
  10. last-checkpoint/trainer_state.json +25 -3
last-checkpoint/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:268996d6a7b89ae0f29dde4a67398cf04f727ed3e28393714d6df5af4ff1f0f5
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135fec0f91a2997432c1116dfdd206a20f678c4534db200650554f4212bede69
3
  size 4938985352
last-checkpoint/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de7e706d7e3f9d74ce4e683a82398a350d2ff6625c6056aa6a47be7a52bbcef2
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadcc0bd81f6261f98319b6e668eda6fdd4f3a7b4d94d1a35f2ead5bd6ae99da
3
  size 4947390880
last-checkpoint/model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8398f26be1335fd494b46970ebe464e368426e60743c23222af55e492baab031
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa5f07ba2ab062b773f191935c86440580e62c7f058c55acd342ed4ea30a609
3
  size 3590488816
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a55afd7d953d6726c6fe91f71198d7c9b43989ac82a7472593f46beba082ba9
3
  size 13687759344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a567984d453c9250806dff4d56a1da85e5dae420b8e5a3ea6d834d3f13c736e7
3
  size 13687759344
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc88fb92d712b475d32be3d1ada8ec5320caecbc5bee07323ed8ad65bd7eca3f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0038fb6f21ca3e81c3e1dfdbad93100e39e8e615b5fad9db02349c28cf41449e
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20d28c1500c52bfe18425b4bed2ac7a058807aa679eb235e2858e4c59d93c46b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f45ce61591188f6d757b7069c1b1c209c1709c8592fa9d63f48f22d8a29eddf
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cef6593c9f9ee2d65b822806f53981afe9f4e72293b225f0334e12cac10ae5c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9915dadbc42bf9335c9ddddb4bfdf5317e9867b7d547371a8e1a633499c3d5
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:295a7f74fd8125d4af9e8f677f10a9107aa9a572a3832d0bb0378329494588ed
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f7c5ddb0b28ad2aed8e01a65edd7968d02ddf7e6ec474ed5c5da54b3a7e8a6
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3671bd7fce476af6c5d68b2346a8d63f3c9e317781066d2c00973b04663cf26
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.37037037037037035,
5
  "eval_steps": 20,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,28 @@
59
  "eval_samples_per_second": 35.043,
60
  "eval_steps_per_second": 4.389,
61
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 10,
@@ -78,7 +100,7 @@
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 2.5981133346832384e+16,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5555555555555556,
5
  "eval_steps": 20,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 35.043,
60
  "eval_steps_per_second": 4.389,
61
  "step": 40
62
+ },
63
+ {
64
+ "epoch": 0.46296296296296297,
65
+ "grad_norm": 1.3203125,
66
+ "learning_rate": 0.00019939306773179497,
67
+ "loss": 1.8177,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.5555555555555556,
72
+ "grad_norm": 77.0,
73
+ "learning_rate": 0.00019863613034027224,
74
+ "loss": 1.9073,
75
+ "step": 60
76
+ },
77
+ {
78
+ "epoch": 0.5555555555555556,
79
+ "eval_loss": 1.8073501586914062,
80
+ "eval_runtime": 45.0134,
81
+ "eval_samples_per_second": 33.346,
82
+ "eval_steps_per_second": 4.177,
83
+ "step": 60
84
  }
85
  ],
86
  "logging_steps": 10,
 
100
  "attributes": {}
101
  }
102
  },
103
+ "total_flos": 3.897170002024858e+16,
104
  "train_batch_size": 2,
105
  "trial_name": null,
106
  "trial_params": null