Hugging Face's logo

SystemAdmin123
/
Phi-3.5-mini-instruct

Safetensors
phi3
custom_code
Model card Files
xet
Community
SystemAdmin123 commited on
Commit
6aa038f
·
verified ·
1 Parent(s): 938a5f2

Training in progress, step 40, 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 sha256:450c9abcb2cd1e6e4af1e4a59c9778c0e70b3b369df43240c125a97e65d6cfee
3
  size 4972163696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863fb83edaa68087c315bded0101ea0421106ab19d884d942d9b1f9e6f687811
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 sha256:2f959b5005cd08bf04586e9bad600aa7cc023cdd6f2dd81a4a7d263bfa2bfc38
3
  size 2669366920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:544d5da4b603c7580f53bf3816392356bd8ae060d82335562f39db5a861a6990
3
  size 2669366920
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:639e343e79bae0448a1b42afe1619f93ce550e6d374e094643980e6e3b64c319
3
  size 7762295162
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827273f8e9622fd93fd32f8272b66b671a5ac3ee1868260e9c627561572cdaf6
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 sha256:1f60241cb6cb86cf9966e8cfe2248be00bce643b5808e2c3b78c9cb618eea253
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc88fb92d712b475d32be3d1ada8ec5320caecbc5bee07323ed8ad65bd7eca3f
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 sha256:2e76feebe960d60536ad1ed0bcaee2e12a3f8432f33b7ee3b0cae559b12130c0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d28c1500c52bfe18425b4bed2ac7a058807aa679eb235e2858e4c59d93c46b
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 sha256:2f5988c600823ef881ed3900c9909420e69870efab70abf3dca0673a3c88b057
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cef6593c9f9ee2d65b822806f53981afe9f4e72293b225f0334e12cac10ae5c
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 sha256:7090a3c6759641db81e3ee589636615551bb1b7ce0948f2fd4ab7d7beb35de9c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295a7f74fd8125d4af9e8f677f10a9107aa9a572a3832d0bb0378329494588ed
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3d7496cd5cad5fcd343f51f06f864ca525a833da3ba71e9c4d90915510423ac
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572996e9dc190ff3f3a6efdf58de929f593fa2dd2f97d74fed7646828651b17f
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": 0.37735849056603776,
5
  "eval_steps": 20,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 77.279,
38
  "eval_steps_per_second": 4.84,
39
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 10,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1.463713580187648e+16,
60
  "train_batch_size": 4,
61
  "trial_name": null,
62
  "trial_params": null
 
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,
 
37
  "eval_samples_per_second": 77.279,
38
  "eval_steps_per_second": 4.84,
39
  "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.5660377358490566,
43
+ "grad_norm": 1.3359375,
44
+ "learning_rate": 0.0002,
45
+ "loss": 1.7454,
46
+ "step": 30
47
+ },
48
+ {
49
+ "epoch": 0.7547169811320755,
50
+ "grad_norm": 0.96875,
51
+ "learning_rate": 0.00019984815164333163,
52
+ "loss": 1.752,
53
+ "step": 40
54
+ },
55
+ {
56
+ "epoch": 0.7547169811320755,
57
+ "eval_loss": 1.5965954065322876,
58
+ "eval_runtime": 29.2724,
59
+ "eval_samples_per_second": 51.277,
60
+ "eval_steps_per_second": 3.211,
61
+ "step": 40
62
  }
63
  ],
64
  "logging_steps": 10,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2.927427160375296e+16,
82
  "train_batch_size": 4,
83
  "trial_name": null,
84
  "trial_params": null