ardaspear commited on
Commit
738c8d9
·
verified ·
1 Parent(s): 6890684

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 sha256:324f253d74695d6f8d7068dad75a5ced96b74245853b061f2bca8cb6ea7fc5af
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e3163f3899145e0f0e28f2932b67f5ab953c710aa461c467cdefccad1a9b84
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bd468a4f3a308f43aeb33cd5e4ec1d30c6ba47ec372304844a689b613ab4516
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb21c9c263ef113295dc9fdf36f0a74b25669fe25ed8b567eced058980334c4
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bed93a2e65e6f7f288ceb2480c39cf708867cb9206bda3a09d1768ac454687b5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b0e17f1b3f4c88dd025eb12291194693982d72306ba4cc4b2b5b44dba1dd344
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": 0.3185840707964602,
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": 7.77,
132
  "eval_steps_per_second": 1.963,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 5.184295048052736e+16,
154
  "train_batch_size": 4,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.39823008849557523,
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": 7.77,
132
  "eval_steps_per_second": 1.963,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.34513274336283184,
137
+ "grad_norm": 0.001999981701374054,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 0.0,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.37168141592920356,
144
+ "grad_norm": 0.013748248107731342,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 0.0001,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.39823008849557523,
151
+ "grad_norm": 0.003550400724634528,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 0.0001,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.39823008849557523,
158
+ "eval_loss": 2.637667603266891e-05,
159
+ "eval_runtime": 12.2233,
160
+ "eval_samples_per_second": 7.772,
161
+ "eval_steps_per_second": 1.963,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 6.407917481754624e+16,
183
  "train_batch_size": 4,
184
  "trial_name": null,
185
  "trial_params": null