tuantmdev commited on
Commit
9e6c376
·
verified ·
1 Parent(s): d16cba7

Training in progress, step 50, 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:f64ac84dbe1463c7c6ca0e6a5958a7331ceeeffe9084699fa50f8d5b5b70bec9
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9476d7be18f4ceecb28c956ab03806aa18eebb94380c879f7b9acdedf874a05f
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2b22e8dae438fd8f008f664af8f5bdc08e1fe634a6a4de0956e2a2bc640370f
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef77485d1365eba9b378643ebe0d7ce31337d9fbedf5adc0eba76d6875e2c46b
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01283d4ca0eaccd314f1efbb61833065b381abcc0b2da248ed6705bb59ec03ed
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290c25578e5f47c7ce2b07ffb07add247247c949297495049011facbccf2586d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:053f8a597fb71bde446a175404cc18fe6996cf501293c3abfb94953dfd03d780
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b23fe3d7c8cff984a05b7865b1b491bac693fd2f496a4e0e24b70ad75a25bd
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": 0.13090611577009614,
5
  "eval_steps": 10,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -75,6 +75,21 @@
75
  "eval_samples_per_second": 3.397,
76
  "eval_steps_per_second": 1.702,
77
  "step": 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  }
79
  ],
80
  "logging_steps": 10,
@@ -89,12 +104,12 @@
89
  "should_evaluate": false,
90
  "should_log": false,
91
  "should_save": true,
92
- "should_training_stop": false
93
  },
94
  "attributes": {}
95
  }
96
  },
97
- "total_flos": 1.08715755700224e+17,
98
  "train_batch_size": 2,
99
  "trial_name": null,
100
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.16363264471262018,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
75
  "eval_samples_per_second": 3.397,
76
  "eval_steps_per_second": 1.702,
77
  "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.16363264471262018,
81
+ "grad_norm": 4.1900763511657715,
82
+ "learning_rate": 0.0,
83
+ "loss": 16.0078,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.16363264471262018,
88
+ "eval_loss": 1.003811001777649,
89
+ "eval_runtime": 152.0311,
90
+ "eval_samples_per_second": 3.387,
91
+ "eval_steps_per_second": 1.697,
92
+ "step": 50
93
  }
94
  ],
95
  "logging_steps": 10,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 1.3589469462528e+17,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null