tuantmdev commited on
Commit
13ad66e
·
verified ·
1 Parent(s): e201ad0

Training in progress, step 400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8479e96980dfe84bd67a52f617ea8ea83c29af8221c12ca40c9a794d529df52f
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1411b500683ada1fec6d2059f34a8fe742d4ae071f46882c179103136c21ef2b
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83334d49a28bae3229c9e1c601348ed0a17ce397e392fcde2188878e194722d2
3
  size 170920532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88543ef84f7ae0d0b55c13151ce65bad41501863263f063d87d5284570523051
3
  size 170920532
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b8102c4fa5704c0cf29aa353c5d198a149efa45b3b748cc0a18c699c2efe093
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6d9b2e9a6e3f55d43f619623f702c5f47f3bc6819f578d8e56ea2eb8788be5e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.524484872817993,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.15929002161793152,
5
  "eval_steps": 50,
6
- "global_step": 350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -127,6 +127,28 @@
127
  "eval_samples_per_second": 8.948,
128
  "eval_steps_per_second": 4.477,
129
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  }
131
  ],
132
  "logging_steps": 40,
@@ -150,12 +172,12 @@
150
  "should_evaluate": false,
151
  "should_log": false,
152
  "should_save": true,
153
- "should_training_stop": false
154
  },
155
  "attributes": {}
156
  }
157
  },
158
- "total_flos": 2.4571719268171776e+17,
159
  "train_batch_size": 2,
160
  "trial_name": null,
161
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.5238912105560303,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-400",
4
+ "epoch": 0.18204573899192172,
5
  "eval_steps": 50,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
127
  "eval_samples_per_second": 8.948,
128
  "eval_steps_per_second": 4.477,
129
  "step": 350
130
+ },
131
+ {
132
+ "epoch": 0.16384116509272956,
133
+ "grad_norm": 0.6024050116539001,
134
+ "learning_rate": 3.8060233744356633e-06,
135
+ "loss": 2.5026,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.18204573899192172,
140
+ "grad_norm": 1.6859347820281982,
141
+ "learning_rate": 0.0,
142
+ "loss": 2.5167,
143
+ "step": 400
144
+ },
145
+ {
146
+ "epoch": 0.18204573899192172,
147
+ "eval_loss": 2.5238912105560303,
148
+ "eval_runtime": 206.9848,
149
+ "eval_samples_per_second": 8.943,
150
+ "eval_steps_per_second": 4.474,
151
+ "step": 400
152
  }
153
  ],
154
  "logging_steps": 40,
 
172
  "should_evaluate": false,
173
  "should_log": false,
174
  "should_save": true,
175
+ "should_training_stop": true
176
  },
177
  "attributes": {}
178
  }
179
  },
180
+ "total_flos": 2.8077968393345434e+17,
181
  "train_batch_size": 2,
182
  "trial_name": null,
183
  "trial_params": null