dixedus commited on
Commit
9ac1aa9
·
verified ·
1 Parent(s): 2b7cea5

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:b0437e213488f2d1ceaadabe26b642c36171fce0b2fb7132091b543c3ca71329
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a837c13d578e456627561a53f18821ea077f3c23952dbdc52a5446f206b8a64d
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4426a17839627b83fc1e77057f2cf41ba8d6f3127d38369eef1834830820cf5b
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a972369b92c3c2629dcb3abba53e875d8264fe8840ee1cbdb3b59d663a1278a
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c535d322f74c9d3b81f5ae8eda9978ae89ee98f7142986d1695029a6439098ec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5224358fefc4a6c20673e2c295e1dbc37dff7b6514472d01bd9b5aa0159f5f9
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": 0.002917105583015963,
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": 6.94,
103
  "eval_steps_per_second": 0.868,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 7.11969523850281e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0038894741106879505,
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": 6.94,
103
  "eval_steps_per_second": 0.868,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.0032412284255732924,
108
+ "grad_norm": 0.6563200950622559,
109
+ "learning_rate": 8.83022221559489e-05,
110
+ "loss": 1.8499,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.0035653512681306215,
115
+ "grad_norm": 0.7679675817489624,
116
+ "learning_rate": 8.473291852294987e-05,
117
+ "loss": 1.9908,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.0038894741106879505,
122
+ "grad_norm": 0.7943200469017029,
123
+ "learning_rate": 8.07830737662829e-05,
124
+ "loss": 1.8507,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.0038894741106879505,
129
+ "eval_loss": 1.880576252937317,
130
+ "eval_runtime": 2247.2974,
131
+ "eval_samples_per_second": 6.937,
132
+ "eval_steps_per_second": 0.867,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 9.492926984670413e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null