kokovova commited on
Commit
87b3897
·
verified ·
1 Parent(s): 9bb97ee

Training in progress, step 30, 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:dd65683c91756698e928435e3f7e395e0e7d2369a26ac43c21dee42954520f51
3
  size 159712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5e7ce6d3a0538bdfc2284a6069c5851873e4960e4c0f19bb3776db43a31324
3
  size 159712
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03de3358082ee2b86ba2dfbe561ec8a0a1e9dedff306696515fdb6bc835223e8
3
  size 336202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb4d397e4a53f7ec723527e999f38275cc7f72aa8a374d2641c8224fbb42ebd1
3
  size 336202
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d50f61a9d24412ccb5614996adc0c93b90c6c68062631ebea450b2af34b256f3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9e2753b11a378f439eb55a76dec3311b386900784ab3db90c49c8cceeb20fa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
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": 0.08859357696567,
5
  "eval_steps": 8,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,42 @@
73
  "learning_rate": 0.00013090169943749476,
74
  "loss": 10.8184,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +123,12 @@
87
  "should_evaluate": false,
88
  "should_log": false,
89
  "should_save": true,
90
- "should_training_stop": false
91
  },
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3300371988480.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.132890365448505,
5
  "eval_steps": 8,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 0.00013090169943749476,
74
  "loss": 10.8184,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.09302325581395349,
79
+ "grad_norm": 0.2741250991821289,
80
+ "learning_rate": 8.435655349597689e-05,
81
+ "loss": 10.8197,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.10631229235880399,
86
+ "grad_norm": 0.3079950213432312,
87
+ "learning_rate": 4.12214747707527e-05,
88
+ "loss": 10.8132,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.10631229235880399,
93
+ "eval_loss": 10.809435844421387,
94
+ "eval_runtime": 0.336,
95
+ "eval_samples_per_second": 282.732,
96
+ "eval_steps_per_second": 142.854,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.11960132890365449,
101
+ "grad_norm": 0.30177101492881775,
102
+ "learning_rate": 1.0899347581163221e-05,
103
+ "loss": 10.8113,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.132890365448505,
108
+ "grad_norm": 0.32695475220680237,
109
+ "learning_rate": 0.0,
110
+ "loss": 10.803,
111
+ "step": 30
112
  }
113
  ],
114
  "logging_steps": 3,
 
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": 4950557982720.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null