ardaspear commited on
Commit
b37b98e
·
verified ·
1 Parent(s): 9a4bec9

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e49043602b6687528192396e68cce5bde976fd5316e48b0bf112643366c6827
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d0e58e69929c75765c86c5f215abbaa5a07cb9baa6ebd329a37eb149f3596d
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a5c33b36f96d01a520b65221383a3f4b0560ce19bfa321d66087d1b32af879f
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f332982aae469f20371c0cff138aa4c3640c4a596afc62c080098b3474b2f5
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62b7e659592cddd3f51c87b74c90fba547c931f31933d3a49da9466abbe8bfce
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa0e883ce353737358cf43e4cbbba45fac49e3b59b9a67c0d812c50c264e8a0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
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": 0.1350844277673546,
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,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 13.674,
132
  "eval_steps_per_second": 3.464,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 2.559399633616896e+16,
154
  "train_batch_size": 4,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.16885553470919323,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 13.674,
132
  "eval_steps_per_second": 3.464,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.14634146341463414,
137
+ "grad_norm": 0.8268300890922546,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 0.0183,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.1575984990619137,
144
+ "grad_norm": 0.09965112060308456,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 0.0271,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.16885553470919323,
151
+ "grad_norm": 2.12029767036438,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 0.0276,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.16885553470919323,
158
+ "eval_loss": 0.039369650185108185,
159
+ "eval_runtime": 16.4644,
160
+ "eval_samples_per_second": 13.666,
161
+ "eval_steps_per_second": 3.462,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 3.19924954202112e+16,
183
  "train_batch_size": 4,
184
  "trial_name": null,
185
  "trial_params": null