MohamedAhmedAE
commited on
Commit
•
8f2a57e
1
Parent(s):
b3db7b4
Training in progress, step 2200, 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:bcab562e1493fe477a7c20ee6a0a13264f4074f59fe17386f1f54313e0affd31
|
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 sha256:541ed47aef8de3fc9ecaad697a0d31b1c0a1072555098f060f3ddcaf5be9e36e
|
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 sha256:6d8e5a18dcaad5f8475df8da26bc9a7d22093bbe9d0a345c2378f89417d170e6
|
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 sha256:7810aa3073ddaced1f3726a0a416fba70e639094f5582e572c65214d83662981
|
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,
|
@@ -77,6 +77,13 @@
|
|
77 |
"learning_rate": 1.9999995668269356e-05,
|
78 |
"loss": 1.5658,
|
79 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 200,
|
@@ -84,7 +91,7 @@
|
|
84 |
"num_input_tokens_seen": 0,
|
85 |
"num_train_epochs": 5,
|
86 |
"save_steps": 200,
|
87 |
-
"total_flos": 2.
|
88 |
"train_batch_size": 1,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.001636058734508569,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 2200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
77 |
"learning_rate": 1.9999995668269356e-05,
|
78 |
"loss": 1.5658,
|
79 |
"step": 2000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.0,
|
83 |
+
"grad_norm": 4.401742935180664,
|
84 |
+
"learning_rate": 1.999999475956276e-05,
|
85 |
+
"loss": 1.6152,
|
86 |
+
"step": 2200
|
87 |
}
|
88 |
],
|
89 |
"logging_steps": 200,
|
|
|
91 |
"num_input_tokens_seen": 0,
|
92 |
"num_train_epochs": 5,
|
93 |
"save_steps": 200,
|
94 |
+
"total_flos": 2.860341350272205e+16,
|
95 |
"train_batch_size": 1,
|
96 |
"trial_name": null,
|
97 |
"trial_params": null
|