Hugging Face's logo

SystemAdmin123
/
SmolLM-360M

Text Generation
Transformers
Safetensors
llama
axolotl
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
SystemAdmin123 commited on
Commit
5d6e7e5
·
verified ·
1 Parent(s): 316dd19

Training in progress, step 40, checkpoint

Browse files
Files changed (8) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +25 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b999a352785b09d15860c1320662d8ec817d298e02812f21d68f01e900838dea
3
  size 723674912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf30145777b99e1483b3b8af8ca3c954b0bee05ef0cd517f6e62511cecc1737
3
  size 723674912
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2899f09cd2c54fdf5ef96e88d4218eefc8c7ef1b0315b44f21f9a89576e1bb98
3
  size 735625370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6361dd5e29307df7b873ae303523973ac614868fbd2cc1c02b982d5d15c248f8
3
  size 735625370
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69a04a1208f7a0d6f51f37a136b5c2e55bf3f53b3d0fd57164c5b83ca47a2645
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9664d03c75ff248cdee237bc0f578d0ab4ef30cf459a48b947cc8ba96efcf94a
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 sha256:080a7e72d6be938a9418e60003db90412af8a61e6434f9e9f1b598cca861dbcd
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0fc8395b524cd5cac61206279bf13d167d68f260f6be7c6c7eca67cec66f27c
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:c3d114a75d37be476b865187eb2b3d29d9343b131614a08f42be0014f110ce6f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca0fe34fb6c7827e42ed53ce617ab6af68578cc38e07c82ad0cc484dafb3017
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 sha256:4fc5a0f78838743362c5d5378dff81ea2f7d0039da53a423f1759e861bc6b233
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1cc5e77aed95b6e97dac8961ae1ecb44cecf9736fe10dadd3ddbb8b2eb1ac6
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bb34b6c62864960ca7a1a2bf6005b33b4420cc8055506432b79e0fe18bca2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b5eb3be65174d535b2988d2d3d904fb7ecffa959b2cce72a3b7b18e92c3e6a
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": 2.5,
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": 309.27,
38
  "eval_steps_per_second": 3.503,
39
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 10,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 7113876738932736.0,
60
  "train_batch_size": 23,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.0,
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": 309.27,
38
  "eval_steps_per_second": 3.503,
39
  "step": 20
40
+ },
41
+ {
42
+ "epoch": 3.75,
43
+ "grad_norm": 0.162109375,
44
+ "learning_rate": 0.00019458172417006347,
45
+ "loss": 2.1785,
46
+ "step": 30
47
+ },
48
+ {
49
+ "epoch": 5.0,
50
+ "grad_norm": 0.1376953125,
51
+ "learning_rate": 0.0001879473751206489,
52
+ "loss": 2.136,
53
+ "step": 40
54
+ },
55
+ {
56
+ "epoch": 5.0,
57
+ "eval_loss": 2.082921028137207,
58
+ "eval_runtime": 4.8453,
59
+ "eval_samples_per_second": 309.785,
60
+ "eval_steps_per_second": 3.509,
61
+ "step": 40
62
  }
63
  ],
64
  "logging_steps": 10,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 1.4227753477865472e+16,
82
  "train_batch_size": 23,
83
  "trial_name": null,
84
  "trial_params": null