Nexspear commited on
Commit
92177de
·
verified ·
1 Parent(s): 54c57c5

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 sha256:808588e3070f78e3cf4d33686eab28299211490510913ea9d6c6d045efa51258
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a881b9ede27e6fe7b4a5686f147a35c3228469bf4c2a0d373c6781e0476cd3c
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86b9c75d07340b2990c492fd478b7277f1771afdea1ad2cc32128fdf1f42f6ef
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dbfebd3fe652d3d30024a7b8979935956c9e590c2a1102dad08d1f03b4c31c4
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:020139e153f4c8d31ac5d8f3f8eddb884a05ef9097c5744142d8a10568d20a45
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a3ad7b7bfc7839be699b6022c9be914cdb816fb3b96f7f412bcb11b77d7b59
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.022190611664295874,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,27 @@
88
  "eval_samples_per_second": 43.647,
89
  "eval_steps_per_second": 21.824,
90
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +123,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 356152655216640.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02844950213371266,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "eval_samples_per_second": 43.647,
89
  "eval_steps_per_second": 21.824,
90
  "step": 39
91
+ },
92
+ {
93
+ "epoch": 0.02275960170697013,
94
+ "grad_norm": 7.097616195678711,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 1.2129,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.025604551920341393,
101
+ "grad_norm": 5.339874267578125,
102
+ "learning_rate": 3.8060233744356633e-06,
103
+ "loss": 1.017,
104
+ "step": 45
105
+ },
106
+ {
107
+ "epoch": 0.02844950213371266,
108
+ "grad_norm": 5.095871448516846,
109
+ "learning_rate": 0.0,
110
+ "loss": 1.1316,
111
+ "step": 50
112
  }
113
  ],
114
  "logging_steps": 5,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 456320589496320.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null