rakhman-llm
commited on
Commit
•
a467fa0
1
Parent(s):
3ee8f10
Training in progress, step 12000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd435d4c565278ca4fe642f0569217eae31db204692f8170a78cc060584eb864
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15f1632c64d76783d8907c3e92a7713d23c2df60b1e1a3079d9b3c7be3413a9f
|
3 |
size 1783272762
|
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:a4f26f933cd5a30682ad42a3de6cd890f8aaa49723c34ab9ccdf6d24b30e628d
|
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:a5d59de19a41db12fa634f2104bc781b1687cd88f74eced8badd275d850b3566
|
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": 2.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -184,6 +184,13 @@
|
|
184 |
"learning_rate": 4.0759213078415074e-06,
|
185 |
"loss": 0.3411,
|
186 |
"step": 11500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
187 |
}
|
188 |
],
|
189 |
"logging_steps": 500,
|
@@ -203,7 +210,7 @@
|
|
203 |
"attributes": {}
|
204 |
}
|
205 |
},
|
206 |
-
"total_flos": 1.
|
207 |
"train_batch_size": 2,
|
208 |
"trial_name": null,
|
209 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.493765586034913,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 12000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
184 |
"learning_rate": 4.0759213078415074e-06,
|
185 |
"loss": 0.3411,
|
186 |
"step": 11500
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 2.493765586034913,
|
190 |
+
"grad_norm": 0.8265316486358643,
|
191 |
+
"learning_rate": 3.3832086450540318e-06,
|
192 |
+
"loss": 0.317,
|
193 |
+
"step": 12000
|
194 |
}
|
195 |
],
|
196 |
"logging_steps": 500,
|
|
|
210 |
"attributes": {}
|
211 |
}
|
212 |
},
|
213 |
+
"total_flos": 1.461377145765888e+16,
|
214 |
"train_batch_size": 2,
|
215 |
"trial_name": null,
|
216 |
"trial_params": null
|