nat-hunt commited on
Commit
49a86df
·
verified ·
1 Parent(s): d306691

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e3dbb891655a04fde8f4c34e2d9a78d366b194ba8d510271c6af0c0a8a54dec
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a09cee8af7adc83628564ce327c15c2643cb711a0b70f1de54f32c20769fd771
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbd638be155de95e94e322b5d90c8c4dbaabfdb76c02b5c870c66beb446d6364
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d60bdc2d0e2a8657d182c92d3e0df208a5773ab7809c8685048471ab0b86f7
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:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.00011701551918323167,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 31.106,
74
  "eval_steps_per_second": 15.553,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1051601871568896.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00017552327877484752,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 31.106,
74
  "eval_steps_per_second": 15.553,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00013651810571377028,
79
+ "grad_norm": 27.31441307067871,
80
+ "learning_rate": 0.00014,
81
+ "loss": 10.5551,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0001560206922443089,
86
+ "grad_norm": 22.054399490356445,
87
+ "learning_rate": 0.00016,
88
+ "loss": 12.2846,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00017552327877484752,
93
+ "grad_norm": 20.389366149902344,
94
+ "learning_rate": 0.00018,
95
+ "loss": 9.8355,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00017552327877484752,
100
+ "eval_loss": 2.403569221496582,
101
+ "eval_runtime": 694.0715,
102
+ "eval_samples_per_second": 31.106,
103
+ "eval_steps_per_second": 15.553,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1577402807353344.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null