Nexspear commited on
Commit
5382755
·
verified ·
1 Parent(s): 273f712

Training in progress, step 35, 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:a4f0c0d8d86cef26a072d97f98acadf4578aa0e3357fb39100083acb3e947626
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e100428d4bb7c8b68c8857b4a2310cedb615bd51efa607db4eabb665305889fa
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3822dcf377fc922f395e85094def75a146277d0f294be9f5d4b05f8fc85d4e95
3
  size 79968772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759ebfcb6e187fa3ed1d13101a046e93beb51a1eb594e8772ba3f223a922ecf3
3
  size 79968772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15c0eeda3a62034479ea787479fb6c3516b246ee5930ba976a4814c1c12227b2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca7e8c3dab8c4e7f141e13a8b59074feffd5b4b261d839d2913a26ec3f9e0b1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
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": 0.05639097744360902,
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,
@@ -133,6 +133,21 @@
133
  "eval_samples_per_second": 27.908,
134
  "eval_steps_per_second": 6.977,
135
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 3,
@@ -152,7 +167,7 @@
152
  "attributes": {}
153
  }
154
  },
155
- "total_flos": 5960489175613440.0,
156
  "train_batch_size": 4,
157
  "trial_name": null,
158
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06578947368421052,
5
  "eval_steps": 5,
6
+ "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
133
  "eval_samples_per_second": 27.908,
134
  "eval_steps_per_second": 6.977,
135
  "step": 30
136
+ },
137
+ {
138
+ "epoch": 0.06203007518796992,
139
+ "grad_norm": 1.566185712814331,
140
+ "learning_rate": 3.832773180720475e-05,
141
+ "loss": 1.5506,
142
+ "step": 33
143
+ },
144
+ {
145
+ "epoch": 0.06578947368421052,
146
+ "eval_loss": 1.5798027515411377,
147
+ "eval_runtime": 16.0818,
148
+ "eval_samples_per_second": 27.858,
149
+ "eval_steps_per_second": 6.964,
150
+ "step": 35
151
  }
152
  ],
153
  "logging_steps": 3,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 6953904038215680.0,
171
  "train_batch_size": 4,
172
  "trial_name": null,
173
  "trial_params": null