chauhoang commited on
Commit
e390c7f
·
verified ·
1 Parent(s): 9f32f32

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 sha256:5dd1865f6271e0be19ca89e38a9963ef86d8c9e307af9c6e69938815d5e9b86e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:685ed3a74e8b6b47fe840d77fe8987389504efa4ce3dadc58ce502175ceafd34
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:154ef3d8e37cca28e54fa08bf46aa2850ee8e2852da23f90da4b9fdd1aafc1ab
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e60668d1a4b3db94aac6005e1225c167c15af27a819f31a6434b13b718a0b24
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:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05903a3f9bd20d677c99c3e506efa2d1a286732f42b0455337aa37751cf18687
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": 0.005848172446110591,
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": 6.8076,
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": 1.3670824330395648e+16,
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": 0.007497656982193065,
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": 6.8076,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.005998125585754452,
94
+ "grad_norm": 10.162247657775879,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 6.6806,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.005998125585754452,
101
+ "eval_loss": 1.6791855096817017,
102
+ "eval_runtime": 333.3267,
103
+ "eval_samples_per_second": 8.424,
104
+ "eval_steps_per_second": 4.212,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.006747891283973758,
109
+ "grad_norm": 11.431609153747559,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 6.7861,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.007497656982193065,
116
+ "grad_norm": 10.58781909942627,
117
+ "learning_rate": 0.0,
118
+ "loss": 6.319,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.007497656982193065,
123
+ "eval_loss": 1.6756504774093628,
124
+ "eval_runtime": 332.7507,
125
+ "eval_samples_per_second": 8.439,
126
+ "eval_steps_per_second": 4.219,
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": 1.7482881114832896e+16,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null