ardaspear commited on
Commit
4103ae6
·
verified ·
1 Parent(s): 234f680

Training in progress, step 36, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cc106e00c16d6b58ddef6887bd04dc4b4043d469f362929d901964babb90f4c
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673d7c5cad9ad5181b92cbd4f08207eedccd9fae02526ae2e6e8aa3ba07fa312
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac877155de5bcd1955fd21061043d0414af2d3252b29d2caae6c673d524da22
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b32f4b97916d417b3292c7c031872106624d481936c7d2d3407a559e14e67017
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e9527040002486149451560ed719648dcfbbd5e22a10158c5c0f97e71351844
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bc3598badc90bbf6730f907debc4da3bd41d1d4bdf1288c5e0666e60347bf21
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
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": 0.0010601018875703054,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 27.586,
103
  "eval_steps_per_second": 6.896,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 5468547044081664.0,
125
  "train_batch_size": 4,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0014134691834270738,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 27.586,
103
  "eval_steps_per_second": 6.896,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.0011778909861892282,
108
+ "grad_norm": 4.403312050271779e-05,
109
+ "learning_rate": 8.83022221559489e-05,
110
+ "loss": 0.0,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.001295680084808151,
115
+ "grad_norm": 3.843701051664539e-05,
116
+ "learning_rate": 8.473291852294987e-05,
117
+ "loss": 0.0,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.0014134691834270738,
122
+ "grad_norm": 4.2941730498569086e-05,
123
+ "learning_rate": 8.07830737662829e-05,
124
+ "loss": 0.0,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.0014134691834270738,
129
+ "eval_loss": 0.0005166567279957235,
130
+ "eval_runtime": 777.5045,
131
+ "eval_samples_per_second": 27.586,
132
+ "eval_steps_per_second": 6.896,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 7291396058775552.0,
154
  "train_batch_size": 4,
155
  "trial_name": null,
156
  "trial_params": null