emdemor commited on
Commit
39c7abf
1 Parent(s): 45defd3

Training in progress, step 100

Browse files
Files changed (3) hide show
  1. adapter_model.safetensors +1 -1
  2. metrics.json +1 -0
  3. state.json +21 -5
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bf964742964d2ec503f25da4ead7a6c8a5691fc8d1cb60aa46b3a6fe8d444f8
3
  size 35668592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a204f7ba1263f6a7e60e5f98f50f704c1b55953c604ab0c7cc48edce48deaa24
3
  size 35668592
metrics.json CHANGED
@@ -1 +1,2 @@
1
  {"Step":50,"eval_loss":1.7071695328,"eval_runtime":27.6118,"eval_samples_per_second":3.622,"eval_steps_per_second":0.471,"epoch":0.08}
 
 
1
  {"Step":50,"eval_loss":1.7071695328,"eval_runtime":27.6118,"eval_samples_per_second":3.622,"eval_steps_per_second":0.471,"epoch":0.08}
2
+ {"Step":100,"eval_loss":1.4855879545,"eval_runtime":27.6396,"eval_samples_per_second":3.618,"eval_steps_per_second":0.47,"epoch":0.16}
state.json CHANGED
@@ -1,13 +1,29 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.08,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
- "log_history": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "logging_steps": 50,
12
  "max_steps": 1875,
13
  "num_input_tokens_seen": 0,
@@ -19,13 +35,13 @@
19
  "should_epoch_stop": false,
20
  "should_evaluate": false,
21
  "should_log": false,
22
- "should_save": false,
23
  "should_training_stop": false
24
  },
25
  "attributes": {}
26
  }
27
  },
28
- "total_flos": 0,
29
  "train_batch_size": 8,
30
  "trial_name": null,
31
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.16,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "grad_norm": 0.05632242560386658,
14
+ "learning_rate": 0.00013297872340425532,
15
+ "loss": 1.8852,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.08,
20
+ "eval_loss": 1.707169532775879,
21
+ "eval_runtime": 27.6118,
22
+ "eval_samples_per_second": 3.622,
23
+ "eval_steps_per_second": 0.471,
24
+ "step": 50
25
+ }
26
+ ],
27
  "logging_steps": 50,
28
  "max_steps": 1875,
29
  "num_input_tokens_seen": 0,
 
35
  "should_epoch_stop": false,
36
  "should_evaluate": false,
37
  "should_log": false,
38
+ "should_save": true,
39
  "should_training_stop": false
40
  },
41
  "attributes": {}
42
  }
43
  },
44
+ "total_flos": 4002786222735360.0,
45
  "train_batch_size": 8,
46
  "trial_name": null,
47
  "trial_params": null