duyphu commited on
Commit
b712b64
·
verified ·
1 Parent(s): 51129a5

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 sha256:670dd61e53ce95406b752c5220db2f0a83799bce8d2faf1c4e35bd919659bc9a
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630939c9cbb85d354f3765d1dddc485d21b2c1498805103443d3bbd445d582f0
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:917074b70458c93678a7b4d9c758c4da09235a4c23e73361045d1aa1d3999a91
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4345b9fa431415b0a1e9b27cb09b46f10e2394b7d04d4aea43ff4c662d1e4fc9
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b673c711547b35a519b3d8cb23444c14dd7567b9d6f2ab5ed7fb2b77cef601f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8ddabe315c0fa1febafc1c0530a018ec54acc652b2ec29db8346758a9bef0a
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": 0.017799075817217184,
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": 0.8905,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5456309960835072.0,
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": 0.026698613725825774,
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": 0.8905,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.020537395173712135,
72
+ "grad_norm": 0.22930027544498444,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.8468,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.020537395173712135,
79
+ "eval_loss": 0.8895410299301147,
80
+ "eval_runtime": 45.5486,
81
+ "eval_samples_per_second": 13.502,
82
+ "eval_steps_per_second": 6.762,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.023960294369330823,
87
+ "grad_norm": 0.22784306108951569,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.8522,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 8347339865456640.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null