dimasik87 commited on
Commit
572c8a9
·
verified ·
1 Parent(s): d6202a5

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78311b02dd3851987a6d0394afff6fb39258daafd5e89d4041635dfd000b3300
3
  size 97307544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a75acaa9c0923b3ce2f86f82caa824047564e8e22cc0f07e2e83cf22ab78b9bb
3
  size 97307544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eca405f3287eeaadbcc1828326779807617bf776724bd12986a64ea0fc24c553
3
  size 194742714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b869c79a588d911379bb179c2a336b972c3c2b2d49d9bfc4a97b9789a9774b
3
  size 194742714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4789694b0dfbba236adc1e0423cccff54c291754e75185fa5ae6a3664fb3ce4a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6684d632e0ed9894b7d3581195993fbfd0a1de05dcd5960c38ed169d3e9d554
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0008089387734465848,
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,
@@ -59,6 +59,28 @@
59
  "eval_samples_per_second": 7.904,
60
  "eval_steps_per_second": 7.904,
61
  "step": 4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -78,7 +100,7 @@
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 1117937171693568.0,
82
  "train_batch_size": 1,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0012134081601698772,
5
  "eval_steps": 2,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 7.904,
60
  "eval_steps_per_second": 7.904,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.001011173466808231,
65
+ "grad_norm": 0.3636244535446167,
66
+ "learning_rate": 0.0001,
67
+ "loss": 2.1186,
68
+ "step": 5
69
+ },
70
+ {
71
+ "epoch": 0.0012134081601698772,
72
+ "grad_norm": 0.4586368799209595,
73
+ "learning_rate": 0.00012,
74
+ "loss": 1.9298,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0012134081601698772,
79
+ "eval_loss": 2.1426615715026855,
80
+ "eval_runtime": 131.861,
81
+ "eval_samples_per_second": 7.895,
82
+ "eval_steps_per_second": 7.895,
83
+ "step": 6
84
  }
85
  ],
86
  "logging_steps": 1,
 
100
  "attributes": {}
101
  }
102
  },
103
+ "total_flos": 1676905757540352.0,
104
  "train_batch_size": 1,
105
  "trial_name": null,
106
  "trial_params": null