duyphu commited on
Commit
0380dc8
·
verified ·
1 Parent(s): c02d643

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:dd701c77ed33ad2c9d2a9005245fc7c4bf1f113e8fda45fc514315d2a65bc289
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5565bcbb8c0a9f441082a44f84a66e03d5c43610f4ce62aef113a2b36937493
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c7c25814e14d28ffdfe538f83854adad79338109d05fc8bfac1d2245ba2e55f
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad55304308fc34a8d80fcf11914f6b0906d83be79cf8e9a4f9530752214e951
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc8cd07aac7537c464bf38a5760aed564a544cf74a9537eab637e6cc69579c7c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713c29710caed13f0e77c70ef93720e0172f8970b01d57ba490781214d2694ea
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": 0.001960821282452535,
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": 2.8283,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1.476326772965376e+16,
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": 0.0029412319236788026,
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": 2.8283,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0022624860951375404,
72
+ "grad_norm": 3.4365930557250977,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.6388,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0022624860951375404,
79
+ "eval_loss": 0.6180438995361328,
80
+ "eval_runtime": 908.4724,
81
+ "eval_samples_per_second": 6.147,
82
+ "eval_steps_per_second": 3.073,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.002639567110993797,
87
+ "grad_norm": 3.5889577865600586,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.4266,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2.218056166146048e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null