devvanshhh commited on
Commit
b6811a6
·
1 Parent(s): 4fbf32f

Training in progress, step 350, checkpoint

Browse files
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a20f14db164c17692212d5858de370ffc0ef9edfed58656c48949e0451fad852
3
- size 369214349
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa80fc71eac2f5bdf2c9ef1e6c97b4ff160e5138cbf5543f15a2f5d0427069a
3
+ size 230572032
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e351d9c62d6220a627e18e224ca4abddc55e39d1617fd6e7ba21c0ebf62ce8e
3
  size 369142184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af7c454098e9ee125bb3f67954c372f5211e9bf9340764cf66c931864365fce
3
  size 369142184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1c1bdf4f98adae7838dbe4cb68bdeae77e4323f5c379cb612dd480aaafe7f67
3
  size 738393861
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b26eb7aaf632206a3d5073aa55eebaeaac7532405722ac4ce20aca4a1fd28c
3
  size 738393861
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c9dd26c37219b5c1bddc661447d8b58d02fabacf2155bbc4c46e2ef98d15e5a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3887ff75fcb85e42f6d7a30ca6291c4d606d6a3eb9baf4eff1b44e0a4c642551
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:840e24cad9f717e9dc7387ea92e5c63c97ae1fbdfb0704ed051dd9f95a2737bb
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2f4ac29992561ca9e7c77cd275a6ecba8b5a15c6345d090af6cb9c161a3e73
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.44642857142857145,
5
  "eval_steps": 500,
6
- "global_step": 325,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -85,13 +85,19 @@
85
  "learning_rate": 0.0002,
86
  "loss": 1.0234,
87
  "step": 325
 
 
 
 
 
 
88
  }
89
  ],
90
  "logging_steps": 25,
91
  "max_steps": 728,
92
  "num_train_epochs": 1,
93
  "save_steps": 25,
94
- "total_flos": 3200350359748608.0,
95
  "trial_name": null,
96
  "trial_params": null
97
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.4807692307692308,
5
  "eval_steps": 500,
6
+ "global_step": 350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
85
  "learning_rate": 0.0002,
86
  "loss": 1.0234,
87
  "step": 325
88
+ },
89
+ {
90
+ "epoch": 0.48,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.8,
93
+ "step": 350
94
  }
95
  ],
96
  "logging_steps": 25,
97
  "max_steps": 728,
98
  "num_train_epochs": 1,
99
  "save_steps": 25,
100
+ "total_flos": 3378406907609088.0,
101
  "trial_name": null,
102
  "trial_params": null
103
  }