MohamedAhmedAE
commited on
Commit
•
de1e84b
1
Parent(s):
3fa09ac
Training in progress, step 1400, 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:de0a235f3533624d434eb2d4d1fc3cb99011c3c8700866ddf368ac7140d739a8
|
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 sha256:8381471a40e6579f72ce5916fb91b4c9d44dc18b662e96d8ec470ca08ac11f3f
|
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:e60fc8f32eff402dbfdf1f21a411fe615eb6cdc026d0f67f4f85662b0ad8390e
|
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 sha256:13c6fd8dd9ac5f94a3fddc347a180544a422ef0ac785334b57fd9dde62a57e91
|
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,
|
@@ -49,6 +49,13 @@
|
|
49 |
"learning_rate": 1.9999998448916044e-05,
|
50 |
"loss": 1.6922,
|
51 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 200,
|
@@ -56,7 +63,7 @@
|
|
56 |
"num_input_tokens_seen": 0,
|
57 |
"num_train_epochs": 5,
|
58 |
"save_steps": 200,
|
59 |
-
"total_flos": 1.
|
60 |
"train_batch_size": 1,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.001041128285596362,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 1400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
49 |
"learning_rate": 1.9999998448916044e-05,
|
50 |
"loss": 1.6922,
|
51 |
"step": 1200
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0,
|
55 |
+
"grad_norm": 3.6168997287750244,
|
56 |
+
"learning_rate": 1.9999997884752155e-05,
|
57 |
+
"loss": 1.6211,
|
58 |
+
"step": 1400
|
59 |
}
|
60 |
],
|
61 |
"logging_steps": 200,
|
|
|
63 |
"num_input_tokens_seen": 0,
|
64 |
"num_train_epochs": 5,
|
65 |
"save_steps": 200,
|
66 |
+
"total_flos": 1.8055337626484736e+16,
|
67 |
"train_batch_size": 1,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|