sergioalves commited on
Commit
3e3eaea
·
verified ·
1 Parent(s): 4752726

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40e238949324e148e2b7e36e3ab507639c68a0dc4a9ce222691e60152b47160d
3
  size 222865880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90ab29d27dc2bd68b2f84bdfffa26115df93f5712cb4a114d16ef5245d8f3be6
3
  size 222865880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b36989470f92445117965711da247334e4ee96bcabf2d4c31b8a5031810c2497
3
  size 445835066
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e91d331cd983953c20a76bc5a4699c7ea1e3f18c6f867bb1f46e64ac41dc42a
3
  size 445835066
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b1e9e74eb9ce556fb3a56ba6bf5b59adaffe1aec162bf64b4914e0fc6e813ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90457f2aa05b0bf6c779e9c18eabfb4d5b3e6a7ed4d46f5f4d989d3f73ffe883
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
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": 0.00228741350717676,
5
  "eval_steps": 8,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "learning_rate": 9e-05,
45
  "loss": 15.939,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 6808424939520000.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00457482701435352,
5
  "eval_steps": 8,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "learning_rate": 9e-05,
45
  "loss": 15.939,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0027448962086121117,
50
+ "grad_norm": 18.383453369140625,
51
+ "learning_rate": 9.755282581475769e-05,
52
+ "loss": 14.3148,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.0034311202607651397,
57
+ "grad_norm": 9.661179542541504,
58
+ "learning_rate": 8.535533905932738e-05,
59
+ "loss": 12.3137,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.0036598616114828157,
64
+ "eval_loss": 2.65584135055542,
65
+ "eval_runtime": 434.9451,
66
+ "eval_samples_per_second": 4.233,
67
+ "eval_steps_per_second": 2.118,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.004117344312918168,
72
+ "grad_norm": 8.729412078857422,
73
+ "learning_rate": 6.545084971874738e-05,
74
+ "loss": 10.2724,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1.361684987904e+16,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null