VERSIL91 commited on
Commit
3affc17
·
verified ·
1 Parent(s): 8f25a91

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 sha256:84d76f09c9072873bbfd251583bed002c9aece431bdd3665c7e1c6e63c603132
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c7c80b30c00862c3f04b6da7cda4e9a8bdd0a398aa26b5c7394ea3b1d7aed7
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc3e7376f249f11e372459ea9ae48c0d43555d8b32c32071c30f0ddd8a76988
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d56ffdbbb5262b6de34ae3f27b9a21923a59e3fd961322546d38a8e94c7c2c2
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:a48eb09d6f8ec3776cb3006f752dd526e23bfa4f52d890a7fb0d73bdb532d9b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b85494d654ca3bad691b5c77e861826b4c6af03f4ee7066fd965552b5b2589
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": 0.03474484256243214,
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": 19.85,
38
  "eval_steps_per_second": 10.027,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2565280056213504.0,
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": 0.06948968512486428,
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": 19.85,
38
  "eval_steps_per_second": 10.027,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.05211726384364821,
43
+ "grad_norm": 1.145268201828003,
44
+ "learning_rate": 3e-05,
45
+ "loss": 15.4215,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.06948968512486428,
50
+ "grad_norm": 1.080140471458435,
51
+ "learning_rate": 4e-05,
52
+ "loss": 14.0206,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.06948968512486428,
57
+ "eval_loss": 1.1434835195541382,
58
+ "eval_runtime": 4.9004,
59
+ "eval_samples_per_second": 19.794,
60
+ "eval_steps_per_second": 9.999,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 5171278843478016.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null