flytech commited on
Commit
24ebb9c
·
1 Parent(s): 25a7893

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94759173694bbf7a60a3f52bddb12dc03afb78c88a3bce177a1ae0d0c4d03f3e
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8459b9f832ef25a417640bf0233bf837cd58164df9c457efc3e290ab0e68c964
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e95b4ac72a729ab6bdf764d44c65428f20d65e451a3bf477128f921f381d5b65
3
  size 126034975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb024f66bab43727577e41564d8e9829a6ce8f78c8ff35fab9e27a566b312a2
3
  size 126034975
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce521c99b81da8238f477e05f29dbe219c7414268b07ba96840dc9a7b531126a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b0a527772fa484fe0f5b977a5f9514063f30bbaa2addc71ee53b83bf0f23343
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 8.737864077669903,
5
  "eval_steps": 200,
6
- "global_step": 1800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -124,13 +124,26 @@
124
  "eval_samples_per_second": 7.935,
125
  "eval_steps_per_second": 0.505,
126
  "step": 1800
 
 
 
 
 
 
 
 
 
 
 
 
 
127
  }
128
  ],
129
  "logging_steps": 200,
130
  "max_steps": 2472,
131
  "num_train_epochs": 12,
132
  "save_steps": 200,
133
- "total_flos": 5.795595153309696e+17,
134
  "trial_name": null,
135
  "trial_params": null
136
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 9.70873786407767,
5
  "eval_steps": 200,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
124
  "eval_samples_per_second": 7.935,
125
  "eval_steps_per_second": 0.505,
126
  "step": 1800
127
+ },
128
+ {
129
+ "epoch": 9.71,
130
+ "learning_rate": 0.0002,
131
+ "loss": 0.0276,
132
+ "step": 2000
133
+ },
134
+ {
135
+ "epoch": 9.71,
136
+ "eval_runtime": 21.8115,
137
+ "eval_samples_per_second": 7.932,
138
+ "eval_steps_per_second": 0.504,
139
+ "step": 2000
140
  }
141
  ],
142
  "logging_steps": 200,
143
  "max_steps": 2472,
144
  "num_train_epochs": 12,
145
  "save_steps": 200,
146
+ "total_flos": 6.439303461470208e+17,
147
  "trial_name": null,
148
  "trial_params": null
149
  }