tuantmdev commited on
Commit
79c9c31
·
verified ·
1 Parent(s): 257c15c

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:f79b364dea73e1b69301b84a8b0cfa2fc13ddb0f6a9dca829633e23368cedd10
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feccb29aa86ee2debbf276495fd6c6a75e9af69a5c9446055ec97793a3424bbc
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ca21684f9f9e3f1a6df596a034eaa626e4d5fd8f239f57b837a6a6985bcc34b
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0c221c188d55da2679c5de3caca3ac1b3a635f0281df84c24edcf7af15936e
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6801f510d1007979f48fafc6e6dbba57bfe570728833a0f896136ca6ebbdc156
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b949b2ac2e366272776693a998861c9fe476da1c7d168da068e36a3cdd6893b1
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": 0.13130898645876077,
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": 3.868,
76
  "eval_steps_per_second": 1.934,
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": 3.991778800907059e+16,
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": 0.16413623307345096,
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": 3.868,
76
  "eval_steps_per_second": 1.934,
77
  "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.16413623307345096,
81
+ "grad_norm": 14.40863037109375,
82
+ "learning_rate": 0.0,
83
+ "loss": 13.3591,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.16413623307345096,
88
+ "eval_loss": 0.8721047639846802,
89
+ "eval_runtime": 133.7719,
90
+ "eval_samples_per_second": 3.842,
91
+ "eval_steps_per_second": 1.921,
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": 4.990818939882701e+16,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null