Hugging Face's logo

SystemAdmin123
/
Phi-3.5-mini-instruct

Safetensors
phi3
custom_code
Model card Files
xet
Community
SystemAdmin123 commited on
Commit
78f8d63
·
verified ·
1 Parent(s): c1baf6b

Training in progress, step 60, checkpoint

Browse files
Files changed (9) hide show
  1. last-checkpoint/model-00001-of-00002.safetensors +1 -1
  2. last-checkpoint/model-00002-of-00002.safetensors +1 -1
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/rng_state_0.pth +1 -1
  5. last-checkpoint/rng_state_1.pth +1 -1
  6. last-checkpoint/rng_state_2.pth +1 -1
  7. last-checkpoint/rng_state_3.pth +1 -1
  8. last-checkpoint/scheduler.pt +1 -1
  9. last-checkpoint/trainer_state.json +25 -3
last-checkpoint/model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:863fb83edaa68087c315bded0101ea0421106ab19d884d942d9b1f9e6f687811
3
  size 4972163696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca78c56901396f034547c9a389a8248cba7409ee84cf453dd7bfa8c03d2a7e43
3
  size 4972163696
last-checkpoint/model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:544d5da4b603c7580f53bf3816392356bd8ae060d82335562f39db5a861a6990
3
  size 2669366920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672f2a2870cbcbcc5ea6c5027d2e0fbce4de08c42b10c83315612fcda56617db
3
  size 2669366920
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:827273f8e9622fd93fd32f8272b66b671a5ac3ee1868260e9c627561572cdaf6
3
  size 7762295162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9db8761eb7ef6153de6524361d61df1be9569589d82343778180eb252038c1e
3
  size 7762295162
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:dbbc0a86104f167e435d82d912099d9f4e8e28814d0b3054a66bc62faad66266
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:ab9aca62c8968a97eee76d9db5ace24bd5602b66748ad8ebaa3c5beb481c0acd
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 sha256:4ecef8be965f4a8a3ed32d79c73f9a4a9b6fc06e37821a549724a0a8e8322513
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:a0d44c275e240e610f81071dc60b4fd4a20c4c4c06cc32abe80112f3f1a29d61
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": 0.7547169811320755,
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": 51.277,
60
  "eval_steps_per_second": 3.211,
61
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 10,
@@ -78,7 +100,7 @@
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 2.927427160375296e+16,
82
  "train_batch_size": 4,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.1320754716981132,
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": 51.277,
60
  "eval_steps_per_second": 3.211,
61
  "step": 40
62
+ },
63
+ {
64
+ "epoch": 0.9433962264150944,
65
+ "grad_norm": 0.96875,
66
+ "learning_rate": 0.00019939306773179497,
67
+ "loss": 1.7421,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 1.1320754716981132,
72
+ "grad_norm": 1.0234375,
73
+ "learning_rate": 0.00019863613034027224,
74
+ "loss": 1.3307,
75
+ "step": 60
76
+ },
77
+ {
78
+ "epoch": 1.1320754716981132,
79
+ "eval_loss": 1.6943310499191284,
80
+ "eval_runtime": 21.4164,
81
+ "eval_samples_per_second": 70.087,
82
+ "eval_steps_per_second": 4.389,
83
+ "step": 60
84
  }
85
  ],
86
  "logging_steps": 10,
 
100
  "attributes": {}
101
  }
102
  },
103
+ "total_flos": 4.386566654079795e+16,
104
  "train_batch_size": 4,
105
  "trial_name": null,
106
  "trial_params": null