Nexspear commited on
Commit
f704dd9
·
verified ·
1 Parent(s): c4d17a4

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 sha256:16eab95c72d7050cd10cde6ae33b3c294e2e99afe35d805c85087b620d9e2790
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f219fbf16ba234b91044c43497dadb6cee964004206e450b4f872f92155fa255
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a307ac5548b8045a5cac545ee22b1e045cddb35ce36629af8609ca2ff115101d
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca66f9d913e880b20017bae536c3ee1ac25843c634f0d320eccd17dd292697a2
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7ddb5f96e8997ff677a7d342c9ecea63898d5ee55783ff6fe95b3021b82d16d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2642c248ba3d9d51f677f7dd1e6e05c7877cfb78ca7e21f6c16b445d5efe576
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
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": 0.6260869565217392,
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": 35.859,
132
  "eval_steps_per_second": 4.806,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 9535762508808192.0,
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": 0.782608695652174,
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": 35.859,
132
  "eval_steps_per_second": 4.806,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.6782608695652174,
137
+ "grad_norm": 0.5637620687484741,
138
+ "learning_rate": 3.824798160583012e-05,
139
+ "loss": 1.2329,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.7304347826086957,
144
+ "grad_norm": 0.5909444689750671,
145
+ "learning_rate": 3.5959278669726935e-05,
146
+ "loss": 1.1362,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.782608695652174,
151
+ "grad_norm": 0.4471411406993866,
152
+ "learning_rate": 3.355050358314172e-05,
153
+ "loss": 1.3341,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.782608695652174,
158
+ "eval_loss": 1.0226554870605469,
159
+ "eval_runtime": 2.6701,
160
+ "eval_samples_per_second": 36.328,
161
+ "eval_steps_per_second": 4.869,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 1.1887046415089664e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null