rakhman-llm commited on
Commit
fe5bf30
·
verified ·
1 Parent(s): 34d03b3

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84ce5f5e3ad779f586e26075dbfc17debe31caf534f8485635c22741e6b17c58
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85815e61243cca853ce597f3dd255d1edeabd5ef8f72c45c2ce72bb0d9ad0bd
3
  size 891558696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56f9727dc07c5bc389be4899ef0032159124294011cc13d105222913c92d85d0
3
  size 1783272762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d50d0681c463a7d840244d2948c84848c87c2efaaf79c0db4a77174ac8f9e6
3
  size 1783272762
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7240fd7a7fef23174636d23a112dffe186d187eae2f35ae7e0e17c53ea3679db
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2aa0a679fd9b985f20fc73a4b26c11f7f4f8e724cefce7fed3d2c20549aa497
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93943bccc582002e393297195c9250188e6670053bc276c333b5b6ec7a12b16e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f10853fba0de0cc442d7091c6f2905c41b6f09944c21256911c835caa91508
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": 0.3117206982543641,
5
  "eval_steps": 500,
6
- "global_step": 1500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -28,6 +28,13 @@
28
  "learning_rate": 1.7924632862288724e-05,
29
  "loss": 0.4832,
30
  "step": 1500
 
 
 
 
 
 
 
31
  }
32
  ],
33
  "logging_steps": 500,
@@ -47,7 +54,7 @@
47
  "attributes": {}
48
  }
49
  },
50
- "total_flos": 1826873671680000.0,
51
  "train_batch_size": 2,
52
  "trial_name": null,
53
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.41562759767248547,
5
  "eval_steps": 500,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
28
  "learning_rate": 1.7924632862288724e-05,
29
  "loss": 0.4832,
30
  "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.41562759767248547,
34
+ "grad_norm": 1.3559819459915161,
35
+ "learning_rate": 1.7233305624826823e-05,
36
+ "loss": 0.4518,
37
+ "step": 2000
38
  }
39
  ],
40
  "logging_steps": 500,
 
54
  "attributes": {}
55
  }
56
  },
57
+ "total_flos": 2435831562240000.0,
58
  "train_batch_size": 2,
59
  "trial_name": null,
60
  "trial_params": null