chauhoang commited on
Commit
d0a58c6
·
verified ·
1 Parent(s): e5f3f3e

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:cbc81772dfabe6201ad2602053dc282cf278af7d521d5635035de8c40cf1795f
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5195a07da41c50f20077ce33d658cfac667c32e5f27c756b8648e34a5a1be6c0
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7245bbf2b0239608460ac3e531b3ee31b39ed7a25bd593bea290c06f61ddb39a
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c65ebc3eb7d2a956dccac1c913da9b83159d26d4767de5d5c69173557408818
3
  size 8075796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac15b70ec0c058b1bdd2f905ce5a56a5bc379016ef5e77498a1541d1a110e43a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb982c82a551e3a58a95d10f65f011252d6abd765e8ca6964152da3997e170eb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.0076263107721639654,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.6559,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 201399981834240.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.011439466158245948,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.6559,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.008799589352496884,
72
+ "grad_norm": 2.4237823486328125,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.7524,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.008799589352496884,
79
+ "eval_loss": 1.596480131149292,
80
+ "eval_runtime": 47.8654,
81
+ "eval_samples_per_second": 30.001,
82
+ "eval_steps_per_second": 15.0,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.010266187577913031,
87
+ "grad_norm": 0.6278929710388184,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.6188,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 303059020283904.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null