Hugging Face's logo

ccore
/
getcode-v2

Text Generation
Transformers
TensorBoard
Safetensors
opt
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
ccore commited on
Commit
4bb79b6
·
verified ·
1 Parent(s): 3d8a730

Training in progress, epoch 1, 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 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5990468375083d2d44289b05135a6192d533a8e788b77ae1daac92644955e56
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07b7d4a9c1b86f87d485901d5e37ea7b953f9e365829f31dbaea704f076c7bd
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b54aa78399d23de4fbb5f625c787c823a4cf1c373bdc55dc8441636e3f6900b
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868dd0dcf987dbe3fc0f6e805629c90bab980bfee1dec1990f93a52eeb7c144f
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:243bed054e6ca95566a31f84929c545f9505688d6a662df2d1ba4f4954f9e518
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759145ece1000f3e66fd124e9d92191400585f54ff12c451de1a4fc9d6ebb688
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57298e368684a7f74b8580ab500ef876b797e959380e8c09da0e2d665556ed4b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6602c18a1ebe894c1d51ce5c9cea3744db091c466423f123d4fa8b7754d9378a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.9048793911933899,
3
  "best_model_checkpoint": "./opt_trained3/checkpoint-1361",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 1361,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -29,6 +29,27 @@
29
  "eval_samples_per_second": 50.377,
30
  "eval_steps_per_second": 12.595,
31
  "step": 1361
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "logging_steps": 500,
@@ -43,12 +64,12 @@
43
  "should_evaluate": false,
44
  "should_log": false,
45
  "should_save": true,
46
- "should_training_stop": false
47
  },
48
  "attributes": {}
49
  }
50
  },
51
- "total_flos": 6.8780176144128e+16,
52
  "train_batch_size": 32,
53
  "trial_name": null,
54
  "trial_params": null
 
1
  {
2
  "best_metric": 0.9048793911933899,
3
  "best_model_checkpoint": "./opt_trained3/checkpoint-1361",
4
+ "epoch": 1.99898924928788,
5
  "eval_steps": 500,
6
+ "global_step": 2720,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
29
  "eval_samples_per_second": 50.377,
30
  "eval_steps_per_second": 12.595,
31
  "step": 1361
32
+ },
33
+ {
34
+ "epoch": 1.1021777083524764,
35
+ "grad_norm": 1.1806821823120117,
36
+ "learning_rate": 4.195020556092935e-05,
37
+ "loss": 0.9113,
38
+ "step": 1500
39
+ },
40
+ {
41
+ "epoch": 1.4697234218505928,
42
+ "grad_norm": 1.2350996732711792,
43
+ "learning_rate": 1.631521781767214e-05,
44
+ "loss": 0.907,
45
+ "step": 2000
46
+ },
47
+ {
48
+ "epoch": 1.837269135348709,
49
+ "grad_norm": 0.9862784147262573,
50
+ "learning_rate": 1.6054963006338742e-06,
51
+ "loss": 0.9047,
52
+ "step": 2500
53
  }
54
  ],
55
  "logging_steps": 500,
 
64
  "should_evaluate": false,
65
  "should_log": false,
66
  "should_save": true,
67
+ "should_training_stop": true
68
  },
69
  "attributes": {}
70
  }
71
  },
72
+ "total_flos": 1.37491227277056e+17,
73
  "train_batch_size": 32,
74
  "trial_name": null,
75
  "trial_params": null