leixa commited on
Commit
aae03cf
·
verified ·
1 Parent(s): 12a483b

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:cc4ddfba4f05b70a74bccacf97746b2330837b8c74ff8ed6b5f9ec2e19efac47
3
  size 891333320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e2366369ce8c38390addfa1542f39cc3aa413336ca1cd4d966ea681d7493ea
3
  size 891333320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50aa1082d9d9744ead9d6fcd18230ccb8b1202e90d57dea30e29ca029657c3c9
3
  size 452984596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d13ca264618193c40dcaea4f30c4de6d69a2b8d01a73e7ec6274118ad1ab617
3
  size 452984596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5a8198e20290002891623b9f5667634ee8ee152ce3b3806833731270e768287
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fef463697b7f776aa8026ba9772a69cf45f54f0e647e6ce67df794c4a72deb5
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": 0.03611412062116288,
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": 2.569,
112
  "eval_steps_per_second": 0.322,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 1.3781132378112e+17,
134
  "train_batch_size": 8,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04333694474539545,
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": 2.569,
112
  "eval_steps_per_second": 0.322,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.0390032502708559,
117
+ "grad_norm": 0.03669508546590805,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 0.0005,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.04333694474539545,
124
+ "grad_norm": 0.5376744270324707,
125
+ "learning_rate": 5e-05,
126
+ "loss": 0.6832,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.04333694474539545,
131
+ "eval_loss": 0.024126915261149406,
132
+ "eval_runtime": 454.0942,
133
+ "eval_samples_per_second": 2.568,
134
+ "eval_steps_per_second": 0.322,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 1.65373588537344e+17,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null