Best000 commited on
Commit
666f96b
·
verified ·
1 Parent(s): 9e8d95c

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:536c66abfac199ed29145eca797ffb8bf8468ed8dfcd92cb132a9b044b7b1354
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1768afbd8f52fee9d41030742dab94e5f55a854fd2d6042420e9a32cb120ab87
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:442c37a9ab5c617c559915f28015871835942e31925cd3e381e96db0471bc4c8
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d017b73d91b33f88359c8c23f551321a7a7e71ff7dff7ce2902a2c3c2768b79
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e10c39b995ebe95975b4f9cbc2995e7b3d5c8e07289a69b691ae1c71fe53b0dc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7569a9cdb08554d4a832d7202284fc3bca41833a2f4143b049eb740311660cd6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d20e72f8ddab5b772229d3ba92a4d0a968180fb094c827027933aaf0ddc696fe
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a31de681372f89725884c16f61509c8be9fe1aabdebb5de708e80e690a719fa
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": 0.00168282066633226,
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,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 32.782,
46
  "eval_steps_per_second": 16.391,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 4879380929052672.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00252423099949839,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 32.782,
46
  "eval_steps_per_second": 16.391,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0019417161534603,
51
+ "grad_norm": 0.786532461643219,
52
+ "learning_rate": 0.00012,
53
+ "loss": 1.5097,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.00252423099949839,
58
+ "eval_loss": 1.2688605785369873,
59
+ "eval_runtime": 198.2622,
60
+ "eval_samples_per_second": 32.815,
61
+ "eval_steps_per_second": 16.408,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 7319071393579008.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null