duyphu commited on
Commit
e43a1cf
·
verified ·
1 Parent(s): 453f6e9

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 sha256:5a0387f358e9b49c4539cf2f8d1b9e088d23ad2b69de3e15b68b4bb51fc168d5
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df6e7ee5e49c1a35b7ad4c268bae86f4c3e05e89f857c2345acec351c544896
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9e309409196c259db87b647971765a3dade17f1a7793b0aeaa6545cefd703d0
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ad326ae05fff12586d19860345e966ff114774e10a23ecaaf86c804e9779ab
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d52990953d1b8a81a00b7cecfd9c211b1ca6db6b881889b76e3a32894320cdb
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": 0.02289740202553941,
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": 1.352,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4284339600752640.0,
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": 0.034346103038309116,
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": 1.352,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.026420079260237782,
72
+ "grad_norm": 1.4691051244735718,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.3647,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.026420079260237782,
79
+ "eval_loss": 1.2375024557113647,
80
+ "eval_runtime": 28.6253,
81
+ "eval_samples_per_second": 16.733,
82
+ "eval_steps_per_second": 8.384,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.030823425803610745,
87
+ "grad_norm": 1.1990418434143066,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.2334,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6426509401128960.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null