clarxus commited on
Commit
ba673cf
·
verified ·
1 Parent(s): ac3f4ce

Training in progress, step 45, 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:b44225243062c88e47568ad7e33ae051863a9222451ceeb231123684c93addfe
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4afb58cdc8a01b9fbd61b4e0090be64b795ce156f7fe52fc3cbb49497bc653a
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cc9ae53dd8f8b0f56a026ac1a10a905b61a070fcbf30dc01a4d4e8a96cc729a
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a28f18d3346139a5295fffac156b89867d2f8c8963ea2a815d5d34af06480f
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:149ce6f9fed784895c9f3e27043159b254515601069bd04b971d74fdaafd4f26
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34899b4e0c2b02ca41e3b7d529ba4a9f07943c5a443b8133731540fec677b605
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
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": 0.01968019680196802,
5
  "eval_steps": 9,
6
- "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 7.289,
132
  "eval_steps_per_second": 0.913,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 9.453645871448064e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.024600246002460024,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 7.289,
132
  "eval_steps_per_second": 0.913,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.02132021320213202,
137
+ "grad_norm": 0.17544706165790558,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 0.6093,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.022960229602296024,
144
+ "grad_norm": 0.19559617340564728,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 0.6168,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.024600246002460024,
151
+ "grad_norm": 0.17366176843643188,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 0.6461,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.024600246002460024,
158
+ "eval_loss": 0.6172654628753662,
159
+ "eval_runtime": 422.8704,
160
+ "eval_samples_per_second": 7.286,
161
+ "eval_steps_per_second": 0.913,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 1.1833584692232192e+17,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null