havinash-ai commited on
Commit
0a1c202
·
verified ·
1 Parent(s): ebda762

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:cbec18e85f2ea43c53fd6d4db0b47201713cfade42c99baf110736db15241b23
3
  size 30026872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdd3b2dc188243f6b31377e176370514d2e3aed6d5d6ac1b47e498837e197e4e
3
  size 30026872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7567600c2d3f10bd6e2f0a165a1c0fa0f7698674b149f2f8b166beadd855166e
3
  size 15611412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2231c356f612a4507ed1398d23b13e6e9424e806c2ff634d9236b226864231f
3
  size 15611412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73fa16f4f4ee8745fd627c55e18b6b5ad2f1caa2e1c30235db086fca1162293c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f28b79cf91c88bb2613bcbee126e6b448ea7a88220ade3856668afa34bdef0
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": 0.006327573618885374,
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": 56.873,
31
  "eval_steps_per_second": 28.469,
32
  "step": 13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 10,
@@ -49,7 +64,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 631122010570752.0,
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": 0.012655147237770748,
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": 56.873,
31
  "eval_steps_per_second": 28.469,
32
  "step": 13
33
+ },
34
+ {
35
+ "epoch": 0.009734728644439037,
36
+ "grad_norm": 0.3252217471599579,
37
+ "learning_rate": 0.00015000000000000001,
38
+ "loss": 0.3332,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.012655147237770748,
43
+ "eval_loss": 0.38014551997184753,
44
+ "eval_runtime": 15.2871,
45
+ "eval_samples_per_second": 56.584,
46
+ "eval_steps_per_second": 28.325,
47
+ "step": 26
48
  }
49
  ],
50
  "logging_steps": 10,
 
64
  "attributes": {}
65
  }
66
  },
67
+ "total_flos": 1309342678646784.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null