MohamedAhmedAE
commited on
Commit
•
f3e26b4
1
Parent(s):
c119bc0
Training in progress, step 3800, 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:dad49df5b2df7646aa362b89959fb3a68f02e445d91649201aa7875d14451182
|
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 sha256:267a2036f4138e7cda6f843ad4f4096f8ff700ae0fe86cbe32da71d427faaf00
|
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 sha256:872e352590e3a4a2cb815be063d894442037481619a588e6b703cf8f8edc317a
|
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 sha256:3a02c00cee72ba53cc6916bd67dc0363d3b2574076a95ff3d48c5db212f6a902
|
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,
|
@@ -133,6 +133,13 @@
|
|
133 |
"learning_rate": 1.9999985922889644e-05,
|
134 |
"loss": 1.5725,
|
135 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 200,
|
@@ -140,7 +147,7 @@
|
|
140 |
"num_input_tokens_seen": 0,
|
141 |
"num_train_epochs": 5,
|
142 |
"save_steps": 200,
|
143 |
-
"total_flos": 4.
|
144 |
"train_batch_size": 1,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0028259196323329825,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 3800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
133 |
"learning_rate": 1.9999985922889644e-05,
|
134 |
"loss": 1.5725,
|
135 |
"step": 3600
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.0,
|
139 |
+
"grad_norm": 2.9052414894104004,
|
140 |
+
"learning_rate": 1.9999984311180655e-05,
|
141 |
+
"loss": 1.5804,
|
142 |
+
"step": 3800
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 200,
|
|
|
147 |
"num_input_tokens_seen": 0,
|
148 |
"num_train_epochs": 5,
|
149 |
"save_steps": 200,
|
150 |
+
"total_flos": 4.986484165808947e+16,
|
151 |
"train_batch_size": 1,
|
152 |
"trial_name": null,
|
153 |
"trial_params": null
|