tuanna08go commited on
Commit
c3289ca
·
verified ·
1 Parent(s): a5fd991

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 sha256:8f77962b4c1f885dd32638297d162f5fbb1ea3e4ee514cdc0141bcc71937d0e9
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ccad1dbf3a728d2ccc8f465f1589f429ec2b636d0027a7ce40b3946b1a8ae4f
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db2941425babf3bba3cfff555739b500bfb55c9015620a762dcc258a2f96c7de
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b5618261d1197bd7fc4b71125473863cbb3ba79f1b86f91187a06678ae736f
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a66ada259260869481e778bff01664524ba6c2c0487bad481b74d64a06cf7bc3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a756382462073b0de6176b3e6342526a2c292eede77ec231bbca5b19bf17f2
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": 0.00422661139559457,
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": 1.5578,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 831323929313280.0,
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": 0.0063399170933918555,
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": 1.5578,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.00487685930260912,
72
+ "grad_norm": 0.27014607191085815,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.6137,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.00487685930260912,
79
+ "eval_loss": 1.619086503982544,
80
+ "eval_runtime": 75.1496,
81
+ "eval_samples_per_second": 34.478,
82
+ "eval_steps_per_second": 17.246,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0056896691863773064,
87
+ "grad_norm": 0.23945343494415283,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.6408,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1246985893969920.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null