MohamedAhmedAE
commited on
Commit
•
7a9c7cc
1
Parent(s):
b87fed0
Training in progress, step 2800, 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 sha256:6ef73a291946fa1b7764cea2ecbc9fb77d4295b4d1578ccb60c70197fd1f94e0
|
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 sha256:252696ba8ca13bef82ddb30f526624e5c4c347f19be2f1f8993e43be3ee58755
|
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 sha256:4ede67e859d756961386f4ff0eca77ffa5be243d151041e5152a2d4e13ba7209
|
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:a588f27f213b00969be40ec01aa5e05f45eda8ba0131c7afc4b942f061603955
|
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,
|
@@ -98,6 +98,13 @@
|
|
98 |
"learning_rate": 1.9999992671458023e-05,
|
99 |
"loss": 1.5586,
|
100 |
"step": 2600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 200,
|
@@ -105,7 +112,7 @@
|
|
105 |
"num_input_tokens_seen": 0,
|
106 |
"num_train_epochs": 5,
|
107 |
"save_steps": 200,
|
108 |
-
"total_flos": 3.
|
109 |
"train_batch_size": 1,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.002082256571192724,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 2800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
98 |
"learning_rate": 1.9999992671458023e-05,
|
99 |
"loss": 1.5586,
|
100 |
"step": 2600
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.0,
|
104 |
+
"grad_norm": 2.3063032627105713,
|
105 |
+
"learning_rate": 1.999999149640793e-05,
|
106 |
+
"loss": 1.6118,
|
107 |
+
"step": 2800
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 200,
|
|
|
112 |
"num_input_tokens_seen": 0,
|
113 |
"num_train_epochs": 5,
|
114 |
"save_steps": 200,
|
115 |
+
"total_flos": 3.630755793784013e+16,
|
116 |
"train_batch_size": 1,
|
117 |
"trial_name": null,
|
118 |
"trial_params": null
|