Hugging Face's logo

rakhman-llm
/
text-to-code-python-codet5-base-xlcost

Safetensors
English
t5
code
Model card Files
xet
Community
1
rakhman-llm commited on
Commit
84251f4
·
verified ·
1 Parent(s): 8b4b602

Training in progress, step 4000, checkpoint

Browse files
Files changed (6) 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 +13 -6
  6. last-checkpoint/training_args.bin +1 -1
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:018e14b315fe7c2c4f3f3ecd8b30c12df557b1aac16e8d43200e427cde5012f9
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194586d3329b3915640ca629be211ec70f5b61a397ac703ca6f5434939582492
3
  size 891558696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:646034272609dc9d2c0541f1cb2326b461015d3659964f877ee677294404bf96
3
  size 1783272762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b0e76ee6269a9a9fabb2d984a5ea1939801a3483f6171f3a83c136b30abd349
3
  size 1783272762
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f98b2585ba496f632a735b8a7a739e3fb4531f5d994b75a9fec9af2a855a040b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a996d3bec7c1a1d5cfa47430ef266e5a8dd93e8eb7ea3732980f3263a8c33f9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c975e68baf84112bcf6e3bf3a6f55c44889e07688f04dbbc115884a58a2446b4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fba9b63cba9667080cabcc507a8b9f4b22657fbfa4fbd93588927df6c34fd73
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": 1.5112262521588946,
5
  "eval_steps": 500,
6
- "global_step": 3500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -39,9 +39,9 @@
39
  {
40
  "epoch": 1.0,
41
  "eval_loss": 0.33670297265052795,
42
- "eval_runtime": 28.3351,
43
- "eval_samples_per_second": 16.658,
44
- "eval_steps_per_second": 4.164,
45
  "step": 2316
46
  },
47
  {
@@ -64,6 +64,13 @@
64
  "learning_rate": 9.93091537132988e-06,
65
  "loss": 0.3728,
66
  "step": 3500
 
 
 
 
 
 
 
67
  }
68
  ],
69
  "logging_steps": 500,
@@ -83,7 +90,7 @@
83
  "attributes": {}
84
  }
85
  },
86
- "total_flos": 8524801509949440.0,
87
  "train_batch_size": 4,
88
  "trial_name": null,
89
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.7271157167530224,
5
  "eval_steps": 500,
6
+ "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
39
  {
40
  "epoch": 1.0,
41
  "eval_loss": 0.33670297265052795,
42
+ "eval_runtime": 28.2248,
43
+ "eval_samples_per_second": 16.723,
44
+ "eval_steps_per_second": 4.181,
45
  "step": 2316
46
  },
47
  {
 
64
  "learning_rate": 9.93091537132988e-06,
65
  "loss": 0.3728,
66
  "step": 3500
67
+ },
68
+ {
69
+ "epoch": 1.7271157167530224,
70
+ "grad_norm": 0.9635007381439209,
71
+ "learning_rate": 8.491652274035695e-06,
72
+ "loss": 0.3675,
73
+ "step": 4000
74
  }
75
  ],
76
  "logging_steps": 500,
 
90
  "attributes": {}
91
  }
92
  },
93
+ "total_flos": 9742717291069440.0,
94
  "train_batch_size": 4,
95
  "trial_name": null,
96
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0589186e917e79226308cded95843db5013776fee27e83a39d678ba03ec762d3
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d71d788b491a41c54d3b024285748be4a2e443d732e96343f48dd9941e304a
3
  size 5432