Synth-Ecosystem commited on
Commit
65656b0
·
verified ·
1 Parent(s): 46498fb

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:c87e7474950b1ee16ecd75548c93aea36a344980521b979a0b97c51914d02942
3
  size 38572808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8852b85cef25e842029e84fa550137a9954e7fe36f5e1c712e2e4b250466409d
3
  size 38572808
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6585f555a0c09669158c8ffe6632792273eec8e2438412a5045d637c13549374
3
  size 39471301
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8835ed0f78a2181cf2d0babc8d207814ddf2d4c59367bf6150fff6b64eb75a65
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:e0ce48f7838ef9c6db5df2d123e0c99865ee5b89de2a5ed04fe910b70ca2b12c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f556552f745af78d3e9bfc8ea5c16b9ac5253c3b2307c3bdd26a95ce9f3503a4
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a973502662ad7c5b97bc0ff30c444f8b3459d8504353d705bc19cbe98e9e4af3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f950059b88d91cb60534020a6eb09c701e2d39d53caebb93d7d33fe09801996f
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": 0.16,
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": 0.6229535043239594,
109
  "num_tokens": 244458.0,
110
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
  }
112
  ],
113
  "logging_steps": 10,
@@ -127,7 +177,7 @@
127
  "attributes": {}
128
  }
129
  },
130
- "total_flos": 2714607316131840.0,
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": 0.24,
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": 0.6229535043239594,
109
  "num_tokens": 244458.0,
110
  "step": 100
111
+ },
112
+ {
113
+ "entropy": 1.7916773557662964,
114
+ "epoch": 0.176,
115
+ "grad_norm": 2.4375,
116
+ "learning_rate": 0.00011460000000000002,
117
+ "loss": 1.837610626220703,
118
+ "mean_token_accuracy": 0.6510058090090751,
119
+ "num_tokens": 268597.0,
120
+ "step": 110
121
+ },
122
+ {
123
+ "entropy": 1.6508349940180778,
124
+ "epoch": 0.192,
125
+ "grad_norm": 2.1875,
126
+ "learning_rate": 0.00010860000000000001,
127
+ "loss": 1.7676301956176759,
128
+ "mean_token_accuracy": 0.6538835391402245,
129
+ "num_tokens": 293619.0,
130
+ "step": 120
131
+ },
132
+ {
133
+ "entropy": 1.550324660539627,
134
+ "epoch": 0.208,
135
+ "grad_norm": 2.453125,
136
+ "learning_rate": 0.0001026,
137
+ "loss": 1.6161380767822267,
138
+ "mean_token_accuracy": 0.6810771860182285,
139
+ "num_tokens": 316757.0,
140
+ "step": 130
141
+ },
142
+ {
143
+ "entropy": 1.5475640408694744,
144
+ "epoch": 0.224,
145
+ "grad_norm": 2.859375,
146
+ "learning_rate": 9.66e-05,
147
+ "loss": 1.6725698471069337,
148
+ "mean_token_accuracy": 0.676793497800827,
149
+ "num_tokens": 341371.0,
150
+ "step": 140
151
+ },
152
+ {
153
+ "entropy": 1.5467152088880538,
154
+ "epoch": 0.24,
155
+ "grad_norm": 1.890625,
156
+ "learning_rate": 9.059999999999999e-05,
157
+ "loss": 1.5721678733825684,
158
+ "mean_token_accuracy": 0.6773946091532708,
159
+ "num_tokens": 366204.0,
160
+ "step": 150
161
  }
162
  ],
163
  "logging_steps": 10,
 
177
  "attributes": {}
178
  }
179
  },
180
+ "total_flos": 4072403110748160.0,
181
  "train_batch_size": 2,
182
  "trial_name": null,
183
  "trial_params": null