oldiday commited on
Commit
1bc4d56
·
verified ·
1 Parent(s): 30a3b28

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 sha256:02a105e05b9e5d14a98427a9d5d7df8ee39b26728d89de9c761d7a3e6548da02
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4c33875e6fe9b2c99172b3029afbc7b22c07b4eb2862bc349614a1494dfb6d
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82ad6b7b15e621f1564528b876460c759220667cb58905f41378ee901ac92f0a
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee3b49445b00f060c8d00b1981dc4990e05cfee931d3a88309735e21cb933b7
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c2114e917b04734ecf6d6c29e2dec4f37e3e775e81af5b53e52453122fa4372
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4f0e8dad369bc7bb59d5e7f497c51f10df0b55006fce373720fb706b727122
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": 0.06279069767441861,
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": 36.43,
103
  "eval_steps_per_second": 4.579,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 7053851718844416.0,
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": 0.08372093023255814,
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": 36.43,
103
  "eval_steps_per_second": 4.579,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.06976744186046512,
108
+ "grad_norm": 4.486081123352051,
109
+ "learning_rate": 4.415111107797445e-05,
110
+ "loss": 3.6693,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.07674418604651163,
115
+ "grad_norm": 3.4287188053131104,
116
+ "learning_rate": 4.2366459261474933e-05,
117
+ "loss": 3.0881,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.08372093023255814,
122
+ "grad_norm": 3.1772103309631348,
123
+ "learning_rate": 4.039153688314145e-05,
124
+ "loss": 3.2421,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.08372093023255814,
129
+ "eval_loss": 3.141343832015991,
130
+ "eval_runtime": 19.8825,
131
+ "eval_samples_per_second": 36.414,
132
+ "eval_steps_per_second": 4.577,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 9405135625125888.0,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null