ardaspear commited on
Commit
e1f0328
·
verified ·
1 Parent(s): 97af32b

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:ef6ee9b4fa312dc8d2b1ac0d9bacd3b6868eb8fd5db2204b95d2f173a3359aaa
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b354ff9d8086f102d78ac1b4410140ae0821f5d58369988cc23b55f4df6e3e0f
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7127605096f8d1648931add3c1995fda8931947b6f52052ff0aa196b19231f0
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3306b30b4c68ad4666500d8f14f48d9f137e393f538db0c0d8f6d1e186666b
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:bb40773f3e0d9ff84c1a29aea2fad96cc8c7e46be03bcae9e0e2ce0f7eb2757a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbde4306ca4c19db5e9ccc802bd241b3575e068082d6a97ce7b5a436af01c9a
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": 0.05446293494704992,
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": 17.561,
103
  "eval_steps_per_second": 2.208,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1.7292706833235968e+16,
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": 0.07261724659606657,
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": 17.561,
103
  "eval_steps_per_second": 2.208,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.060514372163388806,
108
+ "grad_norm": 0.07119950652122498,
109
+ "learning_rate": 4.415111107797445e-05,
110
+ "loss": 1.4393,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.06656580937972768,
115
+ "grad_norm": 0.06678444892168045,
116
+ "learning_rate": 4.2366459261474933e-05,
117
+ "loss": 1.3122,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.07261724659606657,
122
+ "grad_norm": 0.06940136104822159,
123
+ "learning_rate": 4.039153688314145e-05,
124
+ "loss": 1.3441,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.07261724659606657,
129
+ "eval_loss": 1.3346147537231445,
130
+ "eval_runtime": 47.518,
131
+ "eval_samples_per_second": 17.572,
132
+ "eval_steps_per_second": 2.21,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 2.3056942444314624e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null