jssky commited on
Commit
db76f38
·
verified ·
1 Parent(s): d1e7580

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 sha256:9ff24fd41233de6fbf475060d4c2de797c73c6a5214b92c8276152228e45ddeb
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef039086e6370220f6756f552d58e0cb564302668350534f4abb6bb611b2751
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e8e5376b77622ebe1a9eb9968aaf4787321acadcafe4d079557bf2429cb4f98
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a7379985a56e77bbc28e9739a2be3d794cafd42b80543e5376d84bfda9fa0a3
3
  size 18810036
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc31493e63ecd538ed9797ce7f0b1f45e546239d1056d5181e4cff524b5c4118
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7567ae8a1ec33e28c23869de794452faaab4545ecafbc1b4920ceae179c9547
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
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": 0.0019112845424862626,
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": 17.012,
74
  "eval_steps_per_second": 17.012,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 216286290247680.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002866926813729394,
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": 17.012,
74
  "eval_steps_per_second": 17.012,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002229831966233973,
79
+ "grad_norm": 13.027796745300293,
80
+ "learning_rate": 0.0001,
81
+ "loss": 2.2495,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0025483793899816836,
86
+ "grad_norm": 18.181108474731445,
87
+ "learning_rate": 0.00012,
88
+ "loss": 3.5551,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002866926813729394,
93
+ "grad_norm": 9.172633171081543,
94
+ "learning_rate": 0.00014,
95
+ "loss": 1.5026,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002866926813729394,
100
+ "eval_loss": 2.45552396774292,
101
+ "eval_runtime": 38.888,
102
+ "eval_samples_per_second": 16.998,
103
+ "eval_steps_per_second": 16.998,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 324429435371520.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null