Nexspear commited on
Commit
458803d
·
verified ·
1 Parent(s): 7737e5c

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:256645e54d671c516850eb0665bd117ca8987b1a3def02db87bb2cda1784ed38
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72d0b1a02c7f32d6ee2476eba88bf19c1c1fd74fbdc2c66f884819a1caf16f1
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70e18294dc3cdffde1ddf02090030bc9c29650f56f3ab33d4de28d596c82ba12
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0625043c3f4472f5d79e8877f666a6961bf84a6dd23bb018fa03ea5c8d584ec5
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:878f1af5e595d196c540fcad8e7a15e9cba1142d160aa73687fceddf01a60c8d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0e70d08ea56f5ad2634839a7b757ca63b8a8990cb2c71a38ffaae5d1e58948
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
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": 0.0017190991920233798,
5
  "eval_steps": 5,
6
- "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,28 @@
30
  "eval_samples_per_second": 28.489,
31
  "eval_steps_per_second": 3.565,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 2025387794104320.0,
53
  "train_batch_size": 8,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0034381983840467596,
5
  "eval_steps": 5,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
30
  "eval_samples_per_second": 28.489,
31
  "eval_steps_per_second": 3.565,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.0020629190304280558,
36
+ "grad_norm": 10.785271644592285,
37
+ "learning_rate": 6e-05,
38
+ "loss": 2.5669,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.0030943785456420837,
43
+ "grad_norm": 4.260767459869385,
44
+ "learning_rate": 9e-05,
45
+ "loss": 1.0414,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0034381983840467596,
50
+ "eval_loss": 0.7525524497032166,
51
+ "eval_runtime": 171.9965,
52
+ "eval_samples_per_second": 28.483,
53
+ "eval_steps_per_second": 3.564,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 4050775588208640.0,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null