MohamedAhmedAE
commited on
Commit
•
32dd5bc
1
Parent(s):
feb752d
Training in progress, step 3600, 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 sha256:1f67821ac1225d4d6ddda4314d6a5229d5d7e025037b4629626781330dcd8ba7
|
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 sha256:36c6cf5fc78cecc2d7df7b5890bb7f1585faa029834b2a8424b07945ae424657
|
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 sha256:9291966c403e7bde3e2744cb48c547f09f71e192a421d27ace1f464288c63654
|
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:d5ef771961ae1ef92dd7080688347888d76bf3cdf936856cea7f523a48bc1bee
|
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,
|
@@ -126,6 +126,13 @@
|
|
126 |
"learning_rate": 1.9999987447266877e-05,
|
127 |
"loss": 1.5533,
|
128 |
"step": 3400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
129 |
}
|
130 |
],
|
131 |
"logging_steps": 200,
|
@@ -133,7 +140,7 @@
|
|
133 |
"num_input_tokens_seen": 0,
|
134 |
"num_train_epochs": 5,
|
135 |
"save_steps": 200,
|
136 |
-
"total_flos": 4.
|
137 |
"train_batch_size": 1,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.002677187020104931,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 3600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
126 |
"learning_rate": 1.9999987447266877e-05,
|
127 |
"loss": 1.5533,
|
128 |
"step": 3400
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0,
|
132 |
+
"grad_norm": 2.193918466567993,
|
133 |
+
"learning_rate": 1.9999985922889644e-05,
|
134 |
+
"loss": 1.5725,
|
135 |
+
"step": 3600
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 200,
|
|
|
140 |
"num_input_tokens_seen": 0,
|
141 |
"num_train_epochs": 5,
|
142 |
"save_steps": 200,
|
143 |
+
"total_flos": 4.69863606565847e+16,
|
144 |
"train_batch_size": 1,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|