VERSIL91 commited on
Commit
006fd18
·
verified ·
1 Parent(s): 46a5772

Training in progress, step 4, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:525f758a4923140f93b67baf7adc0ef2ea428d0f267eea5dac38fda0acd6695b
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8307e8b17e36c31635f5cf15da5283cf2a20e5d91aef6ddc26cc60002abe8db0
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3e0dc028caae915b9f9d94d581c7831de66bef6682ec4ecd1e0fd8bcf1b13a6
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c61b0ab06eb9e2b6e33d5b12e576f46fb51ab69cfc491376bb51d38e5f3a4559
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
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": 0.00012829456431967797,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 38.325,
38
  "eval_steps_per_second": 19.163,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1318258338693120.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00025658912863935594,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 38.325,
38
  "eval_steps_per_second": 19.163,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.00019244184647951697,
43
+ "grad_norm": 1.6009812355041504,
44
+ "learning_rate": 3e-05,
45
+ "loss": 4.845,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00025658912863935594,
50
+ "grad_norm": 1.580448031425476,
51
+ "learning_rate": 4e-05,
52
+ "loss": 5.0451,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00025658912863935594,
57
+ "eval_loss": 5.014610767364502,
58
+ "eval_runtime": 641.9917,
59
+ "eval_samples_per_second": 40.898,
60
+ "eval_steps_per_second": 20.449,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2636516677386240.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null