Nexspear commited on
Commit
2a91601
·
verified ·
1 Parent(s): c44d5b9

Training in progress, step 36, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89d076f90642c4653a4d5d2fff1a3d43d725dc92f8502a80c48c2da71cd77818
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3bc8785bd34aa8bd6e0dfd187508b0896fb0f5c77bd61540483cc64e4db45dd
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:385d05485e929a6c25aef9287332814c8b517524358bc89393fb36a1e0f3b049
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b063ebe00d300b79d73898b1facb9f86b8c96d1f3352f5af73a993cf38a83295
3
  size 37134420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a463d5feac318c09783e529b68d2719872f249d90beddb2b474a4acc955e8e79
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3b39c99c55766448a1e69ea047f8a8a3d0d081a9bb3e8b5358eeffc699cae1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
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": 0.2634146341463415,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 35.409,
103
  "eval_steps_per_second": 4.503,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 9126706384207872.0,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.35121951219512193,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 35.409,
103
  "eval_steps_per_second": 4.503,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.2926829268292683,
108
+ "grad_norm": 0.1518729329109192,
109
+ "learning_rate": 4.415111107797445e-05,
110
+ "loss": 2.7446,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.32195121951219513,
115
+ "grad_norm": 0.16655544936656952,
116
+ "learning_rate": 4.2366459261474933e-05,
117
+ "loss": 2.7515,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.35121951219512193,
122
+ "grad_norm": 0.2755165696144104,
123
+ "learning_rate": 4.039153688314145e-05,
124
+ "loss": 3.1518,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.35121951219512193,
129
+ "eval_loss": 3.039105176925659,
130
+ "eval_runtime": 4.9041,
131
+ "eval_samples_per_second": 35.277,
132
+ "eval_steps_per_second": 4.486,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 1.240911832940544e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null