tensor24 commited on
Commit
54b20af
·
verified ·
1 Parent(s): fc9e042

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f939652dd04005c3d2451e32e4bf8d528f1528ebf2c2c019292b62ec9db06ef
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888b368de7cb2201a1b7d4380e079ab302498c000802efb1d44741c47b4b249c
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edfb3a7c5c1363646263166f196a8fd83391df4a8ec0b74ba2eb887ce5123952
3
  size 7086458
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:977d7f2806c6cdd23ef8c6ea8ae5b15bd1faee401028443644d6cd25dc172f36
3
  size 7086458
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb99f881fd507ed941d1b5415daafcff09a468076b52be03a90f2705750747b3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5bf32784e874d54ada3ba03f47fd6da65734a246fe744b0bb3b93e5778e3831
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.008519701810436636,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 15.613,
74
  "eval_steps_per_second": 7.833,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 166605103300608.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.012779552715654952,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 15.613,
74
  "eval_steps_per_second": 7.833,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.009939652112176074,
79
+ "grad_norm": 3.573564052581787,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.9925,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.011359602413915513,
86
+ "grad_norm": 2.61667537689209,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.8804,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.012779552715654952,
93
+ "grad_norm": 2.5469532012939453,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.4361,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.012779552715654952,
100
+ "eval_loss": 3.613114356994629,
101
+ "eval_runtime": 19.0203,
102
+ "eval_samples_per_second": 15.615,
103
+ "eval_steps_per_second": 7.834,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 249907654950912.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null