VERSIL91 commited on
Commit
af23206
1 Parent(s): f50ba18

Training in progress, step 12, 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:f232bd228e4f664dbba85e67cfcc3c6164d36ace7266b89d7a699205dd4c12a9
3
  size 200068512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343dfb75fb5c0ea331bb2fea28faa4a62f086a7a5d2e36f8ee0ac386ded7fb33
3
  size 200068512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0730d46ab97c102b2ceae9a7bfa3bb9dc1bab4b85c9a5e3a25267670d64e8f06
3
  size 102030196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff2227ceb1f5a2ee89106e1c6e1021a48cff57efe25c1149e99d0bec513e79a
3
  size 102030196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccf4171573c4aa942fd9e6830083f77573db8b338bc5d43c1892694648afeb6a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742ac93365f9f5139042c83640a290eb5bf78fa0571f5209fdc989f29567f644
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9249a82eef8eec6a1c71d7af2159d50f378e28b90f1d4a939b2f9ac7c40432e
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": 0.5289256198347108,
5
  "eval_steps": 4,
6
- "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -87,6 +87,42 @@
87
  "eval_samples_per_second": 6.041,
88
  "eval_steps_per_second": 3.021,
89
  "step": 8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
  }
91
  ],
92
  "logging_steps": 1,
@@ -106,7 +142,7 @@
106
  "attributes": {}
107
  }
108
  },
109
- "total_flos": 4.908123913872998e+16,
110
  "train_batch_size": 2,
111
  "trial_name": null,
112
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7933884297520661,
5
  "eval_steps": 4,
6
+ "global_step": 12,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
87
  "eval_samples_per_second": 6.041,
88
  "eval_steps_per_second": 3.021,
89
  "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.5950413223140496,
93
+ "grad_norm": 4.271751403808594,
94
+ "learning_rate": 9e-05,
95
+ "loss": 2.8224,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.6611570247933884,
100
+ "grad_norm": 4.623085975646973,
101
+ "learning_rate": 0.0001,
102
+ "loss": 3.1332,
103
+ "step": 10
104
+ },
105
+ {
106
+ "epoch": 0.7272727272727273,
107
+ "grad_norm": 7.002574920654297,
108
+ "learning_rate": 9.330127018922194e-05,
109
+ "loss": 2.8715,
110
+ "step": 11
111
+ },
112
+ {
113
+ "epoch": 0.7933884297520661,
114
+ "grad_norm": 10.354272842407227,
115
+ "learning_rate": 7.500000000000001e-05,
116
+ "loss": 3.1827,
117
+ "step": 12
118
+ },
119
+ {
120
+ "epoch": 0.7933884297520661,
121
+ "eval_loss": 2.666003942489624,
122
+ "eval_runtime": 4.2925,
123
+ "eval_samples_per_second": 6.057,
124
+ "eval_steps_per_second": 3.029,
125
+ "step": 12
126
  }
127
  ],
128
  "logging_steps": 1,
 
142
  "attributes": {}
143
  }
144
  },
145
+ "total_flos": 7.362185870809498e+16,
146
  "train_batch_size": 2,
147
  "trial_name": null,
148
  "trial_params": null