Training in progress, step 8000, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
@@ -286,9 +286,9 @@ print(embeddings.shape)
|
|
286 |
# Get the similarity scores for the embeddings
|
287 |
similarities = model.similarity(embeddings, embeddings)
|
288 |
print(similarities)
|
289 |
-
# tensor([[1.0000, 0.
|
290 |
-
# [0.
|
291 |
-
# [0.
|
292 |
```
|
293 |
|
294 |
<!--
|
@@ -1272,6 +1272,10 @@ You can finetune this model on your own dataset.
|
|
1272 |
| 0.1361 | 7700 | 0.3508 |
|
1273 |
| 0.1369 | 7750 | 0.5145 |
|
1274 |
| 0.1378 | 7800 | 0.3505 |
|
|
|
|
|
|
|
|
|
1275 |
|
1276 |
|
1277 |
### Framework Versions
|
|
|
286 |
# Get the similarity scores for the embeddings
|
287 |
similarities = model.similarity(embeddings, embeddings)
|
288 |
print(similarities)
|
289 |
+
# tensor([[1.0000, 0.7084, 0.1070],
|
290 |
+
# [0.7084, 1.0000, 0.1535],
|
291 |
+
# [0.1070, 0.1535, 1.0000]])
|
292 |
```
|
293 |
|
294 |
<!--
|
|
|
1272 |
| 0.1361 | 7700 | 0.3508 |
|
1273 |
| 0.1369 | 7750 | 0.5145 |
|
1274 |
| 0.1378 | 7800 | 0.3505 |
|
1275 |
+
| 0.1387 | 7850 | 0.3354 |
|
1276 |
+
| 0.1396 | 7900 | 0.4474 |
|
1277 |
+
| 0.1405 | 7950 | 0.3524 |
|
1278 |
+
| 0.1414 | 8000 | 0.4957 |
|
1279 |
|
1280 |
|
1281 |
### Framework Versions
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 90864192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2da1461ee3c2c456dcf6f8e527f2db46ecd02b950cb9f11180de998e104b262
|
3 |
size 90864192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 180609611
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bb3ac284c860eb3e450dfee8fb9c59f3e73309b53d4441e8ab3eca7e6fd0c1f
|
3 |
size 180609611
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14645
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:924de27a7d312b976334871f5500b60f3ac826256585b053482668db5a3e0fd8
|
3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1383
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ef2fcd6c891b91eb5bdb472a78ed689674800853972656dbbbd1178ed4b062
|
3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1465
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d965eb3daad0b2a439e895ad852db3800ac9a1641cf69b4958e035a573e3539
|
3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
@@ -2,9 +2,9 @@
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
-
"epoch": 0.
|
6 |
"eval_steps": 500,
|
7 |
-
"global_step":
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
@@ -1100,6 +1100,34 @@
|
|
1100 |
"learning_rate": 4.790010013547741e-05,
|
1101 |
"loss": 0.3505,
|
1102 |
"step": 7800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1103 |
}
|
1104 |
],
|
1105 |
"logging_steps": 50,
|
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.14136523475464297,
|
6 |
"eval_steps": 500,
|
7 |
+
"global_step": 8000,
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
|
|
1100 |
"learning_rate": 4.790010013547741e-05,
|
1101 |
"loss": 0.3505,
|
1102 |
"step": 7800
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.1387146366029934,
|
1106 |
+
"grad_norm": 1.761982798576355,
|
1107 |
+
"learning_rate": 4.7851014117138874e-05,
|
1108 |
+
"loss": 0.3354,
|
1109 |
+
"step": 7850
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.13959816932020994,
|
1113 |
+
"grad_norm": 3.417602777481079,
|
1114 |
+
"learning_rate": 4.780192809880034e-05,
|
1115 |
+
"loss": 0.4474,
|
1116 |
+
"step": 7900
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.14048170203742644,
|
1120 |
+
"grad_norm": 1.7687017917633057,
|
1121 |
+
"learning_rate": 4.7752842080461804e-05,
|
1122 |
+
"loss": 0.3524,
|
1123 |
+
"step": 7950
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.14136523475464297,
|
1127 |
+
"grad_norm": 3.2442593574523926,
|
1128 |
+
"learning_rate": 4.770375606212327e-05,
|
1129 |
+
"loss": 0.4957,
|
1130 |
+
"step": 8000
|
1131 |
}
|
1132 |
],
|
1133 |
"logging_steps": 50,
|