OscarXZQ commited on
Commit
099ef20
·
verified ·
1 Parent(s): 9de9135

Training in progress, step 250

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15ab6d53f86a358ee5df321f4b7a089a1640a875f053cda5bfe5c041e0b9f108
3
  size 18915328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a378b6eb3ef94fe5e0fe0232b088bc46401b578c8996d011311fa144e77ab67b
3
  size 18915328
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 5.0,
3
- "total_flos": 12502279618560.0,
4
- "train_loss": 1.1522993087768554,
5
- "train_runtime": 5.217,
6
- "train_samples_per_second": 3.834,
7
- "train_steps_per_second": 0.958
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "total_flos": 122531399884800.0,
4
+ "train_loss": 0.3025847053527832,
5
+ "train_runtime": 63.1156,
6
+ "train_samples_per_second": 3.169,
7
+ "train_steps_per_second": 3.169
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 5.0,
3
- "total_flos": 12502279618560.0,
4
- "train_loss": 1.1522993087768554,
5
- "train_runtime": 5.217,
6
- "train_samples_per_second": 3.834,
7
- "train_steps_per_second": 0.958
8
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "total_flos": 122531399884800.0,
4
+ "train_loss": 0.3025847053527832,
5
+ "train_runtime": 63.1156,
6
+ "train_samples_per_second": 3.169,
7
+ "train_steps_per_second": 3.169
8
  }
trainer_state.json CHANGED
@@ -1,27 +1,27 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 5.0,
5
  "eval_steps": 500,
6
- "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 5.0,
13
- "step": 5,
14
- "total_flos": 12502279618560.0,
15
- "train_loss": 1.1522993087768554,
16
- "train_runtime": 5.217,
17
- "train_samples_per_second": 3.834,
18
- "train_steps_per_second": 0.958
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 5,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 5,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
@@ -35,8 +35,8 @@
35
  "attributes": {}
36
  }
37
  },
38
- "total_flos": 12502279618560.0,
39
- "train_batch_size": 4,
40
  "trial_name": null,
41
  "trial_params": null
42
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
  "eval_steps": 500,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 10.0,
13
+ "step": 200,
14
+ "total_flos": 122531399884800.0,
15
+ "train_loss": 0.3025847053527832,
16
+ "train_runtime": 63.1156,
17
+ "train_samples_per_second": 3.169,
18
+ "train_steps_per_second": 3.169
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 200,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 10,
25
  "save_steps": 500,
26
  "stateful_callbacks": {
27
  "TrainerControl": {
 
35
  "attributes": {}
36
  }
37
  },
38
+ "total_flos": 122531399884800.0,
39
+ "train_batch_size": 1,
40
  "trial_name": null,
41
  "trial_params": null
42
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78217b65b5bd4d0c9c0f663c5b1d78d9e274c81fdd94f8fbd0ad858ed500c640
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f1cbe973f169051d1c78945511b0e6eb73a6057cd99ce7bd3c87275d1a4d80
3
  size 5496