duyphu commited on
Commit
e782477
·
verified ·
1 Parent(s): ba9b269

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:c03d5e8c34ab44b87a4cb440ca1c3b7f5ff7b8a484a119cbc3e3e8014d7776b4
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d651af4daa00ad2fda3e657d2699cb3b89ba5090cd1bcaf66be7217afda025
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a03935a39f6f99141d751c2cd93a0571264a6c47b24246bcce451039b0ba194d
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e8a091eb5c65706b76be15dcbeb1b4da685af5726f8e72d2d8105f5c6f097cf
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bec698543fc8efe1c42cfec18e55613892ce220f315dbecc631afb9ede0781a9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e4d5e471bed97943d25263dc996afb538f27403572e606e5959a900d36724d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.0015654006321810245,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,43 @@
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 0.0789,
90
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +139,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 552036615585792.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00200692388741157,
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,
 
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 0.0789,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.001605539109929256,
94
+ "grad_norm": 0.18934212625026703,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.0868,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.001605539109929256,
101
+ "eval_loss": 0.05584266409277916,
102
+ "eval_runtime": 390.0591,
103
+ "eval_samples_per_second": 26.893,
104
+ "eval_steps_per_second": 13.447,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0018062314986704128,
109
+ "grad_norm": 0.16572099924087524,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.1018,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.00200692388741157,
116
+ "grad_norm": 0.5182934403419495,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.0613,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.00200692388741157,
123
+ "eval_loss": 0.055324818938970566,
124
+ "eval_runtime": 390.8541,
125
+ "eval_samples_per_second": 26.839,
126
+ "eval_steps_per_second": 13.419,
127
+ "step": 50
128
  }
129
  ],
130
  "logging_steps": 5,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 712305310433280.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null