Training in progress, step 1600, 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 12595704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c609c046d334b90f2ca09bb31a513ae88f169388223e657b0e4ee6a0be8642b3
|
3 |
size 12595704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25222341
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba7c94230e156551fc01d34d1cbaa90df354e6ff9057a0568ebd58dd07e1002e
|
3 |
size 25222341
|
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:f3f369c633e7cdbde61c687a519838babc30351943278707f66364f3dc85d9c5
|
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:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -217,6 +217,20 @@
|
|
217 |
"eval_samples_per_second": 10.278,
|
218 |
"eval_steps_per_second": 1.289,
|
219 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 100,
|
@@ -224,7 +238,7 @@
|
|
224 |
"num_input_tokens_seen": 0,
|
225 |
"num_train_epochs": 3,
|
226 |
"save_steps": 100,
|
227 |
-
"total_flos": 2.
|
228 |
"trial_name": null,
|
229 |
"trial_params": null
|
230 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0824370384216309,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1600",
|
4 |
+
"epoch": 2.1333333333333333,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
217 |
"eval_samples_per_second": 10.278,
|
218 |
"eval_steps_per_second": 1.289,
|
219 |
"step": 1500
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.13,
|
223 |
+
"learning_rate": 0.0002,
|
224 |
+
"loss": 0.933,
|
225 |
+
"step": 1600
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 2.13,
|
229 |
+
"eval_loss": 1.0824370384216309,
|
230 |
+
"eval_runtime": 187.7567,
|
231 |
+
"eval_samples_per_second": 10.279,
|
232 |
+
"eval_steps_per_second": 1.289,
|
233 |
+
"step": 1600
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 100,
|
|
|
238 |
"num_input_tokens_seen": 0,
|
239 |
"num_train_epochs": 3,
|
240 |
"save_steps": 100,
|
241 |
+
"total_flos": 2.2614230595981312e+17,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
244 |
}
|