rakhman-llm commited on
Commit
52ee620
1 Parent(s): b8bacdc

Training in progress, step 3000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48e35633f2ae11afa853118e28ee629cfb8628c6179db15025e9a1b84122c42e
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86700518c18b2ca27a64b2df63c5bedc35fc35869548b1dd06c33bf2b8de1fe8
3
  size 891558696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b50d9f3de0d3aad8b7e0917750078b64ff6448c1761b9393ae240a8879ea9024
3
  size 1783272762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c8bbbb5bdcec2e5b8aeff0c4454a568d3521a064b17b94f41b9d25f06913d84
3
  size 1783272762
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30dc60382167de3458c5c0efd3fe3f40ca4cde794d0fe66663ca9a8bcee0d065
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc617f0a2f1b846390f426514e6959c82d9ccca5a06fae71b1179457baa9dd5f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d9e707c93d930eada5d65eeb12d5abae9fff751224d824839cf7f999a563f5e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:346a20d6aa585567535ead6c7378b42808548809d68f384868746403a054dab0
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": 0.5195344970906068,
5
  "eval_steps": 500,
6
- "global_step": 2500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -42,6 +42,13 @@
42
  "learning_rate": 1.6540592962039347e-05,
43
  "loss": 0.4389,
44
  "step": 2500
 
 
 
 
 
 
 
45
  }
46
  ],
47
  "logging_steps": 500,
@@ -61,7 +68,7 @@
61
  "attributes": {}
62
  }
63
  },
64
- "total_flos": 3044789452800000.0,
65
  "train_batch_size": 2,
66
  "trial_name": null,
67
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.6234413965087282,
5
  "eval_steps": 500,
6
+ "global_step": 3000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
42
  "learning_rate": 1.6540592962039347e-05,
43
  "loss": 0.4389,
44
  "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.6234413965087282,
48
+ "grad_norm": 0.8109046816825867,
49
+ "learning_rate": 1.584788029925187e-05,
50
+ "loss": 0.4193,
51
+ "step": 3000
52
  }
53
  ],
54
  "logging_steps": 500,
 
68
  "attributes": {}
69
  }
70
  },
71
+ "total_flos": 3653747343360000.0,
72
  "train_batch_size": 2,
73
  "trial_name": null,
74
  "trial_params": null