kostiantynk1205 commited on
Commit
d71689d
·
verified ·
1 Parent(s): 134b746

Training in progress, step 6, 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:bdb46af0d444c31ed4a3deee81de32ac29f080b8b46d793024429a8439598f73
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b69f16d03ad48960c5ce34cd9af7fe911b0289a04084b97d558322d59b1a40
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b95d6a77e3bdc2535ed4787b48aa6e466c78e749636e0d6d78e476ad7876a0e9
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55dca9f568541576d1ed2d2201a492726dfd7970d07e992d6aa8d2258bfe7868
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fac8dc3559aa6a81370bb141163d5dc06aeeb8795a754c1c7ff70e9049a5afd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31b023efb06514ca94fe879833ac32e1c4067a5c53f09b3b9c2d73968e6d54e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 9.358914365933551e-05,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 12.17,
45
  "eval_steps_per_second": 6.085,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1899734583214080.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00018717828731867103,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 12.17,
45
  "eval_steps_per_second": 6.085,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00012478552487911403,
50
+ "grad_norm": 0.2368977963924408,
51
+ "learning_rate": 8e-05,
52
+ "loss": 7.9581,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00015598190609889253,
57
+ "grad_norm": 0.2663523256778717,
58
+ "learning_rate": 0.0001,
59
+ "loss": 8.0291,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00018717828731867103,
64
+ "grad_norm": 0.3481164872646332,
65
+ "learning_rate": 0.00012,
66
+ "loss": 8.4042,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00018717828731867103,
71
+ "eval_loss": 2.069063663482666,
72
+ "eval_runtime": 1110.048,
73
+ "eval_samples_per_second": 12.159,
74
+ "eval_steps_per_second": 6.08,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 3720313558794240.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null