Training in progress, step 660, 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:
|
3 |
size 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2fee34e436bfdc1b45fe527b7b6e314d82be54f5d3704100e80abaabeebe548
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20524127
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bd3d7fedb9ca5313ce3d67c2e1d2e18d2292fa93459779a6cdd3d05da441564
|
3 |
size 20524127
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:536f6998a0cf4f87667e26598fc94f45ff6dfebff5801eb4e93440099d70b583
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51369d5d5a10a5f755e9d6af3e8d642b7f48b8fdaa2a2aaf554c9ea06a70e2e0
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 60,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -137,13 +137,26 @@
|
|
137 |
"eval_samples_per_second": 1.92,
|
138 |
"eval_steps_per_second": 0.24,
|
139 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
140 |
}
|
141 |
],
|
142 |
"logging_steps": 60,
|
143 |
"max_steps": 1011,
|
144 |
"num_train_epochs": 3,
|
145 |
"save_steps": 60,
|
146 |
-
"total_flos":
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
149 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9555555555555557,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 660,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
137 |
"eval_samples_per_second": 1.92,
|
138 |
"eval_steps_per_second": 0.24,
|
139 |
"step": 600
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 1.96,
|
143 |
+
"learning_rate": 0.0002,
|
144 |
+
"loss": 0.5531,
|
145 |
+
"step": 660
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 1.96,
|
149 |
+
"eval_runtime": 312.6322,
|
150 |
+
"eval_samples_per_second": 1.919,
|
151 |
+
"eval_steps_per_second": 0.24,
|
152 |
+
"step": 660
|
153 |
}
|
154 |
],
|
155 |
"logging_steps": 60,
|
156 |
"max_steps": 1011,
|
157 |
"num_train_epochs": 3,
|
158 |
"save_steps": 60,
|
159 |
+
"total_flos": 1.0962671423717376e+17,
|
160 |
"trial_name": null,
|
161 |
"trial_params": null
|
162 |
}
|