Hugging Face's logo

ccore
/
getcode-350m

Text Generation
Transformers
TensorBoard
Safetensors
opt
text-generation-inference
Model card Files
xet
 Metrics Community
ccore commited on
Commit
896cd39
·
verified ·
1 Parent(s): bb0d341

Training in progress, epoch 2, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. 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 sha256:7eeef6ea82868fed037096afaae75138d366fdd8a948a478a6d39da41c0320cc
3
  size 1447317080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91fd7fef7c913bb40166ed36edd2f41fccb334c604d8ad710dd729958231a38c
3
  size 1447317080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e307af0d3d8da03f1b9c643b876554b892185b2c269d203e47abe5885b91daa
3
  size 2894813242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44bc94aa5951947f3a443e56090b2942fbbc3833f1851ba62e08e0d0b08ab9b
3
  size 2894813242
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f9b5be710a7d11d99443218152501810ac7e04613867545dd1469d3cfd97c06
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5a8207eb085bcd0143e42fa68c8c3ba984241f8e091d2d1b847c4f98e5ec17
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.344450980424881,
3
  "best_model_checkpoint": "./opt_trained2/checkpoint-803",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 803,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -22,6 +22,28 @@
22
  "eval_samples_per_second": 10.457,
23
  "eval_steps_per_second": 2.614,
24
  "step": 803
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 500,
@@ -41,7 +63,7 @@
41
  "attributes": {}
42
  }
43
  },
44
- "total_flos": 3.128721416568e+16,
45
  "train_batch_size": 4,
46
  "trial_name": null,
47
  "trial_params": null
 
1
  {
2
  "best_metric": 0.344450980424881,
3
  "best_model_checkpoint": "./opt_trained2/checkpoint-803",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 1606,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 10.457,
23
  "eval_steps_per_second": 2.614,
24
  "step": 803
25
+ },
26
+ {
27
+ "epoch": 1.2453300124533002,
28
+ "grad_norm": 1.1673122644424438,
29
+ "learning_rate": 0.000375093399750934,
30
+ "loss": 2.6965,
31
+ "step": 1000
32
+ },
33
+ {
34
+ "epoch": 1.86799501867995,
35
+ "grad_norm": 0.7170485258102417,
36
+ "learning_rate": 0.000362640099626401,
37
+ "loss": 2.5469,
38
+ "step": 1500
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "eval_loss": 0.3459263741970062,
43
+ "eval_runtime": 272.8846,
44
+ "eval_samples_per_second": 10.466,
45
+ "eval_steps_per_second": 2.616,
46
+ "step": 1606
47
  }
48
  ],
49
  "logging_steps": 500,
 
63
  "attributes": {}
64
  }
65
  },
66
+ "total_flos": 6.257442833136e+16,
67
  "train_batch_size": 4,
68
  "trial_name": null,
69
  "trial_params": null