gavrilstep commited on
Commit
22fc957
·
verified ·
1 Parent(s): 36373a6

Training in progress, step 25, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:131b26aa741ae9b7f3579f74540df889f9429a69a2ffceaaf1d4b39ba4419e04
3
  size 56662456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7765fc9aeb11ada552ace0860f4cf650c41269cfbc949048dc3e0250e52adb
3
  size 56662456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:854c81facd4ffd9b7a5553f551111cf7fd62696a9458765cd6079d66847c83d3
3
  size 113488058
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f245ead565a0502eb38debd10f0285c2479cdf70677b853944a0d9a466f3659
3
  size 113488058
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2984c51083c54f2a93eb7c7b2418dea66d8f3c5351ed7e42b1e0477edc7c96a3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cebf84eb0db64417eba8e3ecbec260c39548f0e52c1db70bd37d55ece543835d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
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": 0.8163265306122449,
5
  "eval_steps": 5,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -89,6 +89,28 @@
89
  "eval_samples_per_second": 18.597,
90
  "eval_steps_per_second": 10.144,
91
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
  }
93
  ],
94
  "logging_steps": 3,
@@ -103,12 +125,12 @@
103
  "should_evaluate": false,
104
  "should_log": false,
105
  "should_save": true,
106
- "should_training_stop": false
107
  },
108
  "attributes": {}
109
  }
110
  },
111
- "total_flos": 1201875462389760.0,
112
  "train_batch_size": 2,
113
  "trial_name": null,
114
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0204081632653061,
5
  "eval_steps": 5,
6
+ "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
89
  "eval_samples_per_second": 18.597,
90
  "eval_steps_per_second": 10.144,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 0.8571428571428571,
95
+ "grad_norm": 1.9328445196151733,
96
+ "learning_rate": 3.308693936411421e-05,
97
+ "loss": 5.5331,
98
+ "step": 21
99
+ },
100
+ {
101
+ "epoch": 0.9795918367346939,
102
+ "grad_norm": 1.9156503677368164,
103
+ "learning_rate": 2.1852399266194314e-06,
104
+ "loss": 5.4735,
105
+ "step": 24
106
+ },
107
+ {
108
+ "epoch": 1.0204081632653061,
109
+ "eval_loss": 1.3589625358581543,
110
+ "eval_runtime": 0.5912,
111
+ "eval_samples_per_second": 18.607,
112
+ "eval_steps_per_second": 10.149,
113
+ "step": 25
114
  }
115
  ],
116
  "logging_steps": 3,
 
125
  "should_evaluate": false,
126
  "should_log": false,
127
  "should_save": true,
128
+ "should_training_stop": true
129
  },
130
  "attributes": {}
131
  }
132
  },
133
+ "total_flos": 1502344327987200.0,
134
  "train_batch_size": 2,
135
  "trial_name": null,
136
  "trial_params": null