kostiantynk-out commited on
Commit
66cf4f6
·
verified ·
1 Parent(s): f5c078c

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 sha256:35154f19a415ca70cdd45c324e75329f8fe692b9852b49036f2b985ad4998a16
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e14b18df2c6b40498fd4c7f3ee63f1cfa38a047714131fc5ccdd4443bc2f41c
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9ceaa3b93918e5c0062a6e612fd0525053f0137bb6fa3ee102c0bf1fe38598e
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072accb14366bf6a5f9b49f844febf1282052f5038bb058bd56df8a3ed81a228
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ec40ab5ce32b0b6a10bff4a1d056084884854a2252ae4ce10c40291cbba5eef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f671f97d721dc915fd4d99adc75c236b138ac6507f128ca203a7f2700368aa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.004246457882487445,
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": 26.07,
46
  "eval_steps_per_second": 13.035,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 4682654070865920.0,
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": 0.006369686823731167,
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": 26.07,
46
  "eval_steps_per_second": 13.035,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0048997590951778205,
51
+ "grad_norm": 2.958142042160034,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 9.6866,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.006369686823731167,
58
+ "eval_loss": 2.356375217437744,
59
+ "eval_runtime": 98.897,
60
+ "eval_samples_per_second": 26.068,
61
+ "eval_steps_per_second": 13.034,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 7044340471824384.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null