Nexspear commited on
Commit
8ce7eb3
·
verified ·
1 Parent(s): 72cbfe9

Training in progress, step 35, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8179eb4d79f7aa393f411e50e5c3a1ff84073d8c32d1a3f521a92b60690000c2
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9fe29e10f67118d660bc155691fe35bde8b746f3dcaf54a1370dedbfc6e1c0
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71e743c6e642d4272a6e7f54ee181f1edc1fd7730bed0b4b788cce05061d667e
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19da07f44920f1483d7cbf9adc5f8dfe24784c8ccbf352a78e3d1bbb92a4ac27
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:224afa5218127cd3f7e7e6941d3c3023031e6b092cee08118cf53f23377cd02b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b46966fb28758683b639812794440f8b656b47f578ba67e0ea16235e96cc4296
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
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": 0.014107688690336233,
5
  "eval_steps": 5,
6
- "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -133,6 +133,21 @@
133
  "eval_samples_per_second": 49.3,
134
  "eval_steps_per_second": 6.166,
135
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 3,
@@ -152,7 +167,7 @@
152
  "attributes": {}
153
  }
154
  },
155
- "total_flos": 6399443557416960.0,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.016458970138725604,
5
  "eval_steps": 5,
6
+ "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
133
  "eval_samples_per_second": 49.3,
134
  "eval_steps_per_second": 6.166,
135
  "step": 30
136
+ },
137
+ {
138
+ "epoch": 0.015518457559369857,
139
+ "grad_norm": 0.41411325335502625,
140
+ "learning_rate": 3.832773180720475e-05,
141
+ "loss": 1.1651,
142
+ "step": 33
143
+ },
144
+ {
145
+ "epoch": 0.016458970138725604,
146
+ "eval_loss": 1.1328095197677612,
147
+ "eval_runtime": 72.7319,
148
+ "eval_samples_per_second": 49.249,
149
+ "eval_steps_per_second": 6.16,
150
+ "step": 35
151
  }
152
  ],
153
  "logging_steps": 3,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 7466017483653120.0,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null