Hanzalwi commited on
Commit
5c6081e
1 Parent(s): 6046aa9

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:bacfee4e852aafb2738a24d09e5c4af4b855c4c32fb37fce5da9f9cb5341d284
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d400b185a0c396eb23cef9f0c6d63b5ee812b3b5b7e959da8649c8c623f1bbf8
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b011bd7927b529702f85b6fa8233ee827404eef6364a84445c4e312223498d94
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a9d0e2d590379e96436ebb3f22b220a4cb53dffd5fbc1c79d13c21ee3197d87
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab69399c8eb447c951d8e52fcc1c52406938e7f812da28a8e362df21f802f42a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60281c4008506649c7ada220785e38c906a536a16c271810e82687b16f02ad9e
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.379417896270752,
3
- "best_model_checkpoint": "./outputs/checkpoint-600",
4
- "epoch": 0.8,
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,
@@ -91,6 +91,20 @@
91
  "eval_samples_per_second": 12.727,
92
  "eval_steps_per_second": 1.596,
93
  "step": 600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
  }
95
  ],
96
  "logging_steps": 100,
@@ -98,7 +112,7 @@
98
  "num_input_tokens_seen": 0,
99
  "num_train_epochs": 3,
100
  "save_steps": 100,
101
- "total_flos": 3.823579745427456e+16,
102
  "trial_name": null,
103
  "trial_params": null
104
  }
 
1
  {
2
+ "best_metric": 1.3729456663131714,
3
+ "best_model_checkpoint": "./outputs/checkpoint-700",
4
+ "epoch": 0.9333333333333333,
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,
 
91
  "eval_samples_per_second": 12.727,
92
  "eval_steps_per_second": 1.596,
93
  "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.93,
97
+ "learning_rate": 0.0002,
98
+ "loss": 1.1333,
99
+ "step": 700
100
+ },
101
+ {
102
+ "epoch": 0.93,
103
+ "eval_loss": 1.3729456663131714,
104
+ "eval_runtime": 151.5395,
105
+ "eval_samples_per_second": 12.736,
106
+ "eval_steps_per_second": 1.597,
107
+ "step": 700
108
  }
109
  ],
110
  "logging_steps": 100,
 
112
  "num_input_tokens_seen": 0,
113
  "num_train_epochs": 3,
114
  "save_steps": 100,
115
+ "total_flos": 4.463977077374976e+16,
116
  "trial_name": null,
117
  "trial_params": null
118
  }