MohamedAhmedAE
commited on
Commit
•
d698718
1
Parent(s):
1cacd76
Training in progress, step 6400, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6787e0eaa9a56e0fa6384e31cadb399d551788e841dc96c421a54c989efc069
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93664eaaa2494807cb13b7289c551278a5569b899724bfce116b35cb065a15b1
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06ae7e7d534fe7c098495e70ee979302efce6ee6dcf9f99dc5c535716646d42a
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61184dac90fcc9cbb0e85bbabd16a1b7709c95fe49eceb7bec3bd299bccf398e
|
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.
|
5 |
"eval_steps": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -224,6 +224,13 @@
|
|
224 |
"learning_rate": 1.9999958185831053e-05,
|
225 |
"loss": 1.5803,
|
226 |
"step": 6200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
227 |
}
|
228 |
],
|
229 |
"logging_steps": 200,
|
@@ -231,7 +238,7 @@
|
|
231 |
"num_input_tokens_seen": 0,
|
232 |
"num_train_epochs": 5,
|
233 |
"save_steps": 200,
|
234 |
-
"total_flos": 8.
|
235 |
"train_batch_size": 1,
|
236 |
"trial_name": null,
|
237 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004759443591297655,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 6400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
224 |
"learning_rate": 1.9999958185831053e-05,
|
225 |
"loss": 1.5803,
|
226 |
"step": 6200
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.0,
|
230 |
+
"grad_norm": 3.5667736530303955,
|
231 |
+
"learning_rate": 1.999995543968414e-05,
|
232 |
+
"loss": 1.6274,
|
233 |
+
"step": 6400
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 200,
|
|
|
238 |
"num_input_tokens_seen": 0,
|
239 |
"num_train_epochs": 5,
|
240 |
"save_steps": 200,
|
241 |
+
"total_flos": 8.403014572720128e+16,
|
242 |
"train_batch_size": 1,
|
243 |
"trial_name": null,
|
244 |
"trial_params": null
|