suhani-sarvam commited on
Commit
3b8ce8d
·
verified ·
1 Parent(s): 4f98ae1

Training in progress, step 1100, 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:f65f7da278a10edb8cfa792691645c214e3285f75d4d85476649a8a5dadf0865
3
  size 399673504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23f1b17884a36178833aa0f45ba2fc1df8092671a8ae8eb73d8d8524bf05a3f5
3
  size 399673504
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60d95e28bd69606ba08a2132e3b9b80b425c8e91b377ad04ad4e31cb20b90281
3
  size 35917596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba124bca5b4a0f6fd3a20b71745278c1ca0ab6b8fb4b4a44707470eb1fb8536
3
  size 35917596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6897f4d9267af104da450818f98b0607ac33a201132638656fe8f2d6e4637393
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd1b15d9e4f4e8cd815f14a3dfeb7f311372b70eec8b00a42bf65573ba954a8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef4cc0b5ec9c1a30996ddab63bfe1fbdec4230855ee2f25408f5073c0b388401
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb55ec1feadc5ce4d46bceba8e5c73976867e9a19125eefaf2c5c252267fa06
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": 1.7271157167530224,
5
  "eval_steps": 1000,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -84,6 +84,13 @@
84
  "eval_samples_per_second": 1.907,
85
  "eval_steps_per_second": 0.239,
86
  "step": 1000
 
 
 
 
 
 
 
87
  }
88
  ],
89
  "logging_steps": 100,
@@ -103,7 +110,7 @@
103
  "attributes": {}
104
  }
105
  },
106
- "total_flos": 5.93300940620759e+16,
107
  "train_batch_size": 16,
108
  "trial_name": null,
109
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8998272884283247,
5
  "eval_steps": 1000,
6
+ "global_step": 1100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
84
  "eval_samples_per_second": 1.907,
85
  "eval_steps_per_second": 0.239,
86
  "step": 1000
87
+ },
88
+ {
89
+ "epoch": 1.8998272884283247,
90
+ "grad_norm": 2.7425153255462646,
91
+ "learning_rate": 4.407294832826748e-06,
92
+ "loss": 1.3114,
93
+ "step": 1100
94
  }
95
  ],
96
  "logging_steps": 100,
 
110
  "attributes": {}
111
  }
112
  },
113
+ "total_flos": 6.52671852184535e+16,
114
  "train_batch_size": 16,
115
  "trial_name": null,
116
  "trial_params": null