flytech commited on
Commit
eddce0a
·
1 Parent(s): 9850581

Training in progress, step 700, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f333d800cd7c383c7a8320063438832839ce7fece3931ad8b890f0413c4a555
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58074245d17c58e496fffd42a65a16c059fa3a6f394079218c96a6d9faa41a0b
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cb3bdd870afd194a2689ca3346517401bb1df3a346d5b0c4250e169b35ce542
3
  size 20524127
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e796b9ca2ab57f97c9750ca044d0028ff8c4d69d96c3e2fdba5ff83b9a25acc
3
  size 20524127
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a51cf2740940fbaca46f09a810eeca0eb86be9f79d7d359cd271462beefad583
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff508809cde07c5626578863e1a6ba7029d6564718a3766a0e864597f46377e4
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb0b2196e2f29a6683acf49e9b6eb98e7393791df29402c783d469811f16cf26
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09921ec2b52ed1c6b0f6ed69eeab044aae49b679e52ca9804dd8ad029e7ac795
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.8808777429467085,
5
  "eval_steps": 100,
6
- "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -85,13 +85,26 @@
85
  "eval_samples_per_second": 1.755,
86
  "eval_steps_per_second": 0.22,
87
  "step": 600
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  }
89
  ],
90
  "logging_steps": 100,
91
  "max_steps": 957,
92
  "num_train_epochs": 3,
93
  "save_steps": 100,
94
- "total_flos": 9.961912403597722e+16,
95
  "trial_name": null,
96
  "trial_params": null
97
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.19435736677116,
5
  "eval_steps": 100,
6
+ "global_step": 700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
85
  "eval_samples_per_second": 1.755,
86
  "eval_steps_per_second": 0.22,
87
  "step": 600
88
+ },
89
+ {
90
+ "epoch": 2.19,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.5059,
93
+ "step": 700
94
+ },
95
+ {
96
+ "epoch": 2.19,
97
+ "eval_runtime": 512.3973,
98
+ "eval_samples_per_second": 1.756,
99
+ "eval_steps_per_second": 0.221,
100
+ "step": 700
101
  }
102
  ],
103
  "logging_steps": 100,
104
  "max_steps": 957,
105
  "num_train_epochs": 3,
106
  "save_steps": 100,
107
+ "total_flos": 1.1618770698318643e+17,
108
  "trial_name": null,
109
  "trial_params": null
110
  }