great0001 commited on
Commit
609667c
·
verified ·
1 Parent(s): e57d47a

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:cf5c62e6d72e4be1fa164769bd4820843d4da6100777d8acb74fb6c0aae68a80
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c9b3b47600daded264a7e85b3c382736e49ae78c17f2bca6f8aa69438c93f5
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8976bce44c5800901d376933163fedb66d77a749ed663dae6ba1168ae0c12371
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22813b9391f44b16ad258c2663dbdc3bab92dc9564a15b8adfd028326c3c094
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
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": 0.0009064471050345583,
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": 32.482,
74
  "eval_steps_per_second": 16.247,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109738548887552.0,
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": 0.0013596706575518375,
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": 32.482,
74
  "eval_steps_per_second": 16.247,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.001057521622540318,
79
+ "grad_norm": 0.43568184971809387,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.1669,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0012085961400460777,
86
+ "grad_norm": 0.6850478649139404,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7176,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0013596706575518375,
93
+ "grad_norm": 0.4434090852737427,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.2542,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0013596706575518375,
100
+ "eval_loss": 1.299032211303711,
101
+ "eval_runtime": 85.6635,
102
+ "eval_samples_per_second": 32.534,
103
+ "eval_steps_per_second": 16.273,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1664607823331328.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null