Nexspear commited on
Commit
d740392
·
verified ·
1 Parent(s): 3c8f971

Training in progress, step 40, 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:e100428d4bb7c8b68c8857b4a2310cedb615bd51efa607db4eabb665305889fa
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7addb646f632d8b1b4c884bf83af62921e29e3a1f4b3308163fed61febfbc9b
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:759ebfcb6e187fa3ed1d13101a046e93beb51a1eb594e8772ba3f223a922ecf3
3
  size 79968772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dc86fcb24167fde7229c2b36d90fc9578d6bc171f732c9ac2c1e9dc6a503c67
3
  size 79968772
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ca7e8c3dab8c4e7f141e13a8b59074feffd5b4b261d839d2913a26ec3f9e0b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8d896afa577bd1b79700bc2bfee8d915869bd3ba8aaab6ad02f4216eb5a6cd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
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": 0.06578947368421052,
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,
@@ -148,6 +148,28 @@
148
  "eval_samples_per_second": 27.858,
149
  "eval_steps_per_second": 6.964,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 6953904038215680.0,
171
  "train_batch_size": 4,
172
  "trial_name": null,
173
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.07518796992481203,
5
  "eval_steps": 5,
6
+ "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
148
  "eval_samples_per_second": 27.858,
149
  "eval_steps_per_second": 6.964,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 0.06766917293233082,
154
+ "grad_norm": 1.518865704536438,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 1.5894,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 0.07330827067669173,
161
+ "grad_norm": 1.5283524990081787,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 1.592,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 0.07518796992481203,
168
+ "eval_loss": 1.5614439249038696,
169
+ "eval_runtime": 16.0674,
170
+ "eval_samples_per_second": 27.883,
171
+ "eval_steps_per_second": 6.971,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 7947318900817920.0,
193
  "train_batch_size": 4,
194
  "trial_name": null,
195
  "trial_params": null