ardaspear commited on
Commit
8179738
·
verified ·
1 Parent(s): 330ab16

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 sha256:7068b4d49f74c005b145bd8b806126380d7eac664f708c39604d1ddada929a84
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5216e77fc08dc74d0a86755a5b9e127ada877002de09090546ccba0f5346873c
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d00d9c4876a0e22cecc42603fb92a0d9fcf925594c2ac6c4b0b57fadce84857a
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2121ce4edf234d72a57bac554fbdab4eea282cfc34cd28b3d20f57fd4b0aad
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d27065c456970240a93dd508456ad4cae86737b3d23ff535ff52a8c41bbae99
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
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": 0.004608188751411258,
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,
@@ -111,6 +111,28 @@
111
  "eval_samples_per_second": 468.329,
112
  "eval_steps_per_second": 117.121,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 2788766515200.0,
134
  "train_batch_size": 4,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0055298265016935095,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
111
  "eval_samples_per_second": 468.329,
112
  "eval_steps_per_second": 117.121,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.004976843851524158,
117
+ "grad_norm": 0.11614447087049484,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 10.3667,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.0055298265016935095,
124
+ "grad_norm": 0.13167273998260498,
125
+ "learning_rate": 5e-05,
126
+ "loss": 10.3669,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.0055298265016935095,
131
+ "eval_loss": 10.363195419311523,
132
+ "eval_runtime": 19.4376,
133
+ "eval_samples_per_second": 470.068,
134
+ "eval_steps_per_second": 117.556,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 3346519818240.0,
156
  "train_batch_size": 4,
157
  "trial_name": null,
158
  "trial_params": null