Synth-Ecosystem commited on
Commit
5ab8320
·
verified ·
1 Parent(s): 59d92e9

Training in progress, step 150, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:429a474e8038463f9ab7c400c8fdb6e043e07cb02c8401381bf6d8e0c442751a
3
  size 38572808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2762a7c98521bb775714596b9797f764fe0ae5d86f7a3d18c463a3fa245153bc
3
  size 38572808
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ddd05e5fe4356cb088f49258029f07c780909b1bb48b9c3f52aef472f01b122
3
  size 39471301
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e3d226b869c08ed07e5ce3ba06cae36926e24eaef974d2381ad0ea66c47deb
3
  size 39471301
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59aebae97aec79c5b963670026030e995b3872fc31c5845f9d529b166b03d7db
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f61cf452a4e2a8b8645bbfbecde6e74e8b526a5674a38001e6f8e31d1ae89a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a04ac36718c8a3a1c2eafead72ffa9bd93f134b8f17c1eccdf40bf929c611cd
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f5d15dfdf0bae35e489e07f19ab2ec727f69de5711cec803f468caeccac964
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.13333333333333333,
6
  "eval_steps": 500,
7
- "global_step": 100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -108,6 +108,56 @@
108
  "mean_token_accuracy": 0.5880244933068752,
109
  "num_tokens": 248803.0,
110
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
  }
112
  ],
113
  "logging_steps": 10,
@@ -127,7 +177,7 @@
127
  "attributes": {}
128
  }
129
  },
130
- "total_flos": 2723286815293440.0,
131
  "train_batch_size": 2,
132
  "trial_name": null,
133
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2,
6
  "eval_steps": 500,
7
+ "global_step": 150,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
108
  "mean_token_accuracy": 0.5880244933068752,
109
  "num_tokens": 248803.0,
110
  "step": 100
111
+ },
112
+ {
113
+ "entropy": 1.9033766239881516,
114
+ "epoch": 0.14666666666666667,
115
+ "grad_norm": 2.15625,
116
+ "learning_rate": 0.00014162807922604012,
117
+ "loss": 1.968048667907715,
118
+ "mean_token_accuracy": 0.64387002363801,
119
+ "num_tokens": 271791.0,
120
+ "step": 110
121
+ },
122
+ {
123
+ "entropy": 1.9241585657000542,
124
+ "epoch": 0.16,
125
+ "grad_norm": 1.890625,
126
+ "learning_rate": 0.00013189593092980702,
127
+ "loss": 2.0358983993530275,
128
+ "mean_token_accuracy": 0.6207146689295768,
129
+ "num_tokens": 297536.0,
130
+ "step": 120
131
+ },
132
+ {
133
+ "entropy": 1.898452916741371,
134
+ "epoch": 0.17333333333333334,
135
+ "grad_norm": 2.0,
136
+ "learning_rate": 0.00012181432413965428,
137
+ "loss": 2.0305503845214843,
138
+ "mean_token_accuracy": 0.6262554697692394,
139
+ "num_tokens": 322858.0,
140
+ "step": 130
141
+ },
142
+ {
143
+ "entropy": 1.7887109428644181,
144
+ "epoch": 0.18666666666666668,
145
+ "grad_norm": 1.8984375,
146
+ "learning_rate": 0.00011149371504928668,
147
+ "loss": 1.9288850784301759,
148
+ "mean_token_accuracy": 0.6352952517569065,
149
+ "num_tokens": 347720.0,
150
+ "step": 140
151
+ },
152
+ {
153
+ "entropy": 1.5244780972599983,
154
+ "epoch": 0.2,
155
+ "grad_norm": 1.5234375,
156
+ "learning_rate": 0.00010104717841162458,
157
+ "loss": 1.6125946044921875,
158
+ "mean_token_accuracy": 0.6929229475557804,
159
+ "num_tokens": 369639.0,
160
+ "step": 150
161
  }
162
  ],
163
  "logging_steps": 10,
 
177
  "attributes": {}
178
  }
179
  },
180
+ "total_flos": 4060359187169280.0,
181
  "train_batch_size": 2,
182
  "trial_name": null,
183
  "trial_params": null