robiual-awal commited on
Commit
27922ea
·
verified ·
1 Parent(s): 9f97385

Training in progress, step 26, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc5076cacaf7e8a80abd37a284e0d10df67e391dd2920d6b2fe213d84ecb0dde
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709abda29b236750e74ffc137a6e99122bc23914f4155b915fb6a8e879a9a2b9
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fd98f838ae0c58432487aea91e1aa587f3e6d0393a63afc485639eacbe7d069
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:418c247b4e4628d3afc0272af48b5489153522f5f2c21f112dbf3cd39bd8d028
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a84ddc90db20c8ebbe7132f591333b49cb59751c1225abbbb520a5d2fc22243
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e453425e46ef89b1031d0bda05882dbcfe99c05687a3971ab75cd3cb186192
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
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": 0.0009682524904571269,
5
  "eval_steps": 13,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,21 @@
30
  "eval_samples_per_second": 34.93,
31
  "eval_steps_per_second": 17.465,
32
  "step": 13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 10,
@@ -49,7 +64,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 2265426859917312.0,
53
  "train_batch_size": 2,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0019365049809142538,
5
  "eval_steps": 13,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
30
  "eval_samples_per_second": 34.93,
31
  "eval_steps_per_second": 17.465,
32
  "step": 13
33
+ },
34
+ {
35
+ "epoch": 0.0014896192160878876,
36
+ "grad_norm": 1.4779833555221558,
37
+ "learning_rate": 0.00015000000000000001,
38
+ "loss": 1.7836,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.0019365049809142538,
43
+ "eval_loss": 1.6129094362258911,
44
+ "eval_runtime": 162.5125,
45
+ "eval_samples_per_second": 34.791,
46
+ "eval_steps_per_second": 17.396,
47
+ "step": 26
48
  }
49
  ],
50
  "logging_steps": 10,
 
64
  "attributes": {}
65
  }
66
  },
67
+ "total_flos": 4530853719834624.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null