Nexspear commited on
Commit
b3a398a
·
verified ·
1 Parent(s): f3a8081

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59eb66b507e2a8d539f5d0662ebc0797af96a12cc07654cdf50738e65d73e839
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e313dae42c4d8192fa932173cce577e54ece11b24db4927e11d57cdd6d4df56
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9088d23a2844fc7986671dbdb45b1108f286de4125780eac86e13e57a22f2298
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6678bf0aa2b0ca5080f7a9607b564dd8ad41229bf3d39d455f12c26820e6f6
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d0440fe0e5910ed062e7da8e32dd6c2a310e10dc8b5186169b259a0a8b05db8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
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": 0.09345794392523364,
5
  "eval_steps": 5,
6
- "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,28 @@
30
  "eval_samples_per_second": 525.844,
31
  "eval_steps_per_second": 70.112,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 557753303040.0,
53
  "train_batch_size": 8,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.18691588785046728,
5
  "eval_steps": 5,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
30
  "eval_samples_per_second": 525.844,
31
  "eval_steps_per_second": 70.112,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.11214953271028037,
36
+ "grad_norm": 0.03669259324669838,
37
+ "learning_rate": 6e-05,
38
+ "loss": 10.3784,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.16822429906542055,
43
+ "grad_norm": 0.04349780082702637,
44
+ "learning_rate": 9e-05,
45
+ "loss": 10.3787,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.18691588785046728,
50
+ "eval_loss": 10.379013061523438,
51
+ "eval_runtime": 0.1698,
52
+ "eval_samples_per_second": 529.918,
53
+ "eval_steps_per_second": 70.656,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 1115506606080.0,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null