Training in progress, step 10200, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +42 -3
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 735396724
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8713f587d8c2de0f5d2143c25048db75c3915db2842308fea5376d39a41f4308
|
| 3 |
size 735396724
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1470915147
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f178e6e3e9cc0892a04a8bf0a1a5a49fb89117226dbce494e8501df1fc95dd95
|
| 3 |
size 1470915147
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4539ebbd96f2aa7f7df4ece7387a123cc7e62446465a52204550291310cc9673
|
| 3 |
size 16325
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2abd277b5c9471b93320941fbc28ed1e0b802dea6507be1a2d1fed167eb2d3a
|
| 3 |
size 16325
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afd70d4d20b2d0f8443eeb250ed5ba2dd766848e4552c631472302a62437057e
|
| 3 |
size 16325
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb6d7cb46ce79a6aa48d2d9541300f4bcf87ececda0533cc74f370d8de82fdce
|
| 3 |
size 16325
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4aa570420d77f8543e4173c9ad60b9cf8d58781ba858c988b07b6b2ba16e172
|
| 3 |
size 16325
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c578e3b57602459b8c3dc95764e9fd946698d00e901c32b0601f7fe16847c044
|
| 3 |
size 16325
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:944af4f170b65f910ba1fc6cfb4614fa2feb535003323d30840c7fd70e16e85c
|
| 3 |
size 16325
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5522d39ceff101d1557a26232b5181c9d750a581e0c05ac5a7025e8b6cf9b2c3
|
| 3 |
size 16325
|
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 sha256:03a202aac98b5e09489a600640b8374ed0c4d649131c9b76a7d50925a164aa1f
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": 9800,
|
| 3 |
"best_metric": 0.7528361702207996,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-9800",
|
| 5 |
-
"epoch": 2.
|
| 6 |
"eval_steps": 200,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1958,6 +1958,45 @@
|
|
| 1958 |
"eval_samples_per_second": 1674.4,
|
| 1959 |
"eval_steps_per_second": 26.162,
|
| 1960 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1961 |
}
|
| 1962 |
],
|
| 1963 |
"logging_steps": 50,
|
|
@@ -1977,7 +2016,7 @@
|
|
| 1977 |
"attributes": {}
|
| 1978 |
}
|
| 1979 |
},
|
| 1980 |
-
"total_flos": 1.
|
| 1981 |
"train_batch_size": 256,
|
| 1982 |
"trial_name": null,
|
| 1983 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 9800,
|
| 3 |
"best_metric": 0.7528361702207996,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-9800",
|
| 5 |
+
"epoch": 2.6106987458407986,
|
| 6 |
"eval_steps": 200,
|
| 7 |
+
"global_step": 10200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1958 |
"eval_samples_per_second": 1674.4,
|
| 1959 |
"eval_steps_per_second": 26.162,
|
| 1960 |
"step": 10000
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 2.5723061172254926,
|
| 1964 |
+
"grad_norm": 0.18073636293411255,
|
| 1965 |
+
"learning_rate": 1.310594711488078e-06,
|
| 1966 |
+
"loss": 0.0755,
|
| 1967 |
+
"step": 10050
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 2.5851036600972614,
|
| 1971 |
+
"grad_norm": 0.2599385976791382,
|
| 1972 |
+
"learning_rate": 1.234679653254088e-06,
|
| 1973 |
+
"loss": 0.0799,
|
| 1974 |
+
"step": 10100
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 2.59790120296903,
|
| 1978 |
+
"grad_norm": 0.17557959258556366,
|
| 1979 |
+
"learning_rate": 1.1609150574445255e-06,
|
| 1980 |
+
"loss": 0.0809,
|
| 1981 |
+
"step": 10150
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 2.6106987458407986,
|
| 1985 |
+
"grad_norm": 0.17557652294635773,
|
| 1986 |
+
"learning_rate": 1.0893150051495562e-06,
|
| 1987 |
+
"loss": 0.0814,
|
| 1988 |
+
"step": 10200
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 2.6106987458407986,
|
| 1992 |
+
"eval_entity_f1": 0.7500700322882474,
|
| 1993 |
+
"eval_entity_precision": 0.6743530583815431,
|
| 1994 |
+
"eval_entity_recall": 0.8843906953232014,
|
| 1995 |
+
"eval_loss": 0.08134948462247849,
|
| 1996 |
+
"eval_runtime": 480.0458,
|
| 1997 |
+
"eval_samples_per_second": 1666.508,
|
| 1998 |
+
"eval_steps_per_second": 26.039,
|
| 1999 |
+
"step": 10200
|
| 2000 |
}
|
| 2001 |
],
|
| 2002 |
"logging_steps": 50,
|
|
|
|
| 2016 |
"attributes": {}
|
| 2017 |
}
|
| 2018 |
},
|
| 2019 |
+
"total_flos": 1.2902474370881946e+18,
|
| 2020 |
"train_batch_size": 256,
|
| 2021 |
"trial_name": null,
|
| 2022 |
"trial_params": null
|