Femboyuwu2000 commited on
Commit
a55dce0
1 Parent(s): 95270cd

Training in progress, step 60, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d1b8936336ff610c11541b9799877d17a6fd74ef7458f9355dbb1999c703751
3
  size 12803224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c13c1fb05d548b619e4ea3b6565286621267c5c8ce62890c4968c123b771070
3
  size 12803224
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:762ed4b62d3d7382ea3206d02ee40276f37d5242792631ff4df50c8ed09cf2fd
3
  size 6472698
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68903178a78f75a3d0256b3cd6634ad0163adbc4d74cda491a06a4482ccf1d07
3
  size 6472698
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df81fc9d078b3589f3e74ce10344ae2b9ba2f47edb0c855a81de1c3ca1991673
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd37aad04b91620e0c3483fdbb04450826c4bfc1adad9bf38a9c80870ce97622
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54c4686d2e20000478760f5dd836e2034bc43011ed2dd8768bdce121428ce020
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b207be31c66d2c120e6fb6b0a2aa4e289fca3c6de3dc048cad8998306d1d4ca
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": 3.1130100472399276e-05,
5
  "eval_steps": 500,
6
- "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -21,6 +21,13 @@
21
  "learning_rate": 5.333333333333334e-06,
22
  "loss": 3.7962,
23
  "step": 40
 
 
 
 
 
 
 
24
  }
25
  ],
26
  "logging_steps": 20,
@@ -28,7 +35,7 @@
28
  "num_input_tokens_seen": 0,
29
  "num_train_epochs": 1,
30
  "save_steps": 20,
31
- "total_flos": 167893794816000.0,
32
  "train_batch_size": 1,
33
  "trial_name": null,
34
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.669515070859891e-05,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
21
  "learning_rate": 5.333333333333334e-06,
22
  "loss": 3.7962,
23
  "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "grad_norm": 108.40189361572266,
28
+ "learning_rate": 8.666666666666668e-06,
29
+ "loss": 3.5164,
30
+ "step": 60
31
  }
32
  ],
33
  "logging_steps": 20,
 
35
  "num_input_tokens_seen": 0,
36
  "num_train_epochs": 1,
37
  "save_steps": 20,
38
+ "total_flos": 253168758374400.0,
39
  "train_batch_size": 1,
40
  "trial_name": null,
41
  "trial_params": null