dzanbek commited on
Commit
c52de90
·
verified ·
1 Parent(s): d8869a9

Training in progress, step 8, 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:f17131e2dcf0e09a0777cef5e5be461c26e2e79db8a7830f7c681821ceba2d1d
3
  size 63592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4530a3d0d7b77ff7f53d2f38bc4445f56cccbb13ff8d498136b48439e1322e
3
  size 63592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75256d7e13cbb0818e99cef5a26ba483a115571e64ef664512babf1fff9d146c
3
  size 132798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39cc8bc984b53ba9f17527979cf529b621910c76e7b71d3fa454cd8d2c12bd6
3
  size 132798
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d00dfae48b2782ecf08c0272c6aeaedad798ddbb45fa725272d2fe913436954
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f6aa419941080b507be30cc0a94dfedde767723ef862246fb9c06dfb8d3605
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
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": 0.00020445368272196002,
5
  "eval_steps": 2,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -81,6 +81,28 @@
81
  "eval_samples_per_second": 108.192,
82
  "eval_steps_per_second": 54.1,
83
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  }
85
  ],
86
  "logging_steps": 1,
@@ -100,7 +122,7 @@
100
  "attributes": {}
101
  }
102
  },
103
- "total_flos": 17781227520.0,
104
  "train_batch_size": 2,
105
  "trial_name": null,
106
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0002726049102959467,
5
  "eval_steps": 2,
6
+ "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
81
  "eval_samples_per_second": 108.192,
82
  "eval_steps_per_second": 54.1,
83
  "step": 6
84
+ },
85
+ {
86
+ "epoch": 0.00023852929650895337,
87
+ "grad_norm": 2.498781442642212,
88
+ "learning_rate": 7e-05,
89
+ "loss": 44.3137,
90
+ "step": 7
91
+ },
92
+ {
93
+ "epoch": 0.0002726049102959467,
94
+ "grad_norm": 2.4782936573028564,
95
+ "learning_rate": 8e-05,
96
+ "loss": 44.3997,
97
+ "step": 8
98
+ },
99
+ {
100
+ "epoch": 0.0002726049102959467,
101
+ "eval_loss": 11.08991527557373,
102
+ "eval_runtime": 114.0478,
103
+ "eval_samples_per_second": 108.349,
104
+ "eval_steps_per_second": 54.179,
105
+ "step": 8
106
  }
107
  ],
108
  "logging_steps": 1,
 
122
  "attributes": {}
123
  }
124
  },
125
+ "total_flos": 23396352000.0,
126
  "train_batch_size": 2,
127
  "trial_name": null,
128
  "trial_params": null