Training in progress, step 10600, 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 sha256:2ccdee280e66e9449e0d0c789f563e569d53e896089bff91eb030761d051fc12
|
| 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 sha256:76dd5668791d9540caf66f5ad0ff4b7248050744e5bfabcd68431711bf15874e
|
| 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:dd376b5510d8d1fc249043490fb694166126a9a99cddc059dd498af7d2606405
|
| 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:e5e55dad713098d0798f53789dd3c2a1c331e28442afa855ae7c41263c90c46f
|
| 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:d2ad5a20e91e646e930632b58a7dabbae5e19de5e9b7e470a7597299a4e87266
|
| 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 sha256:7847322ddd92ecd7317deaeee4ed910560e5d943f70d4e5aa720aebf907a0807
|
| 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 sha256:3d9b680fc6a310ae0fd0071a8170885f57aea7d31c3cbc3701c4ff00abd7b864
|
| 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 sha256:963a677a15d58abd0a62811d678fd654f52d9afc8227478c3977e5c4860d8568
|
| 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 sha256:6cd851df4cdb7d2ae1770e66bb71a00c92a41b10e61a92e928fbb3fb4f11a884
|
| 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 sha256:289e4b6329474c09319d0ca3394c3e7e905b55dcacefb427623da68940beed93
|
| 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 sha256:5b971b4bc08ad301f58b61327461819e6cc4ae873ef355ce42703e3c5bf10ecd
|
| 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,
|
|
@@ -2036,6 +2036,45 @@
|
|
| 2036 |
"eval_samples_per_second": 1667.156,
|
| 2037 |
"eval_steps_per_second": 26.049,
|
| 2038 |
"step": 10400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2039 |
}
|
| 2040 |
],
|
| 2041 |
"logging_steps": 50,
|
|
@@ -2055,7 +2094,7 @@
|
|
| 2055 |
"attributes": {}
|
| 2056 |
}
|
| 2057 |
},
|
| 2058 |
-
"total_flos": 1.
|
| 2059 |
"train_batch_size": 256,
|
| 2060 |
"trial_name": null,
|
| 2061 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 9800,
|
| 3 |
"best_metric": 0.7528361702207996,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-9800",
|
| 5 |
+
"epoch": 2.7130790888149474,
|
| 6 |
"eval_steps": 200,
|
| 7 |
+
"global_step": 10600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2036 |
"eval_samples_per_second": 1667.156,
|
| 2037 |
"eval_steps_per_second": 26.049,
|
| 2038 |
"step": 10400
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 2.6746864601996414,
|
| 2042 |
+
"grad_norm": 0.21106697618961334,
|
| 2043 |
+
"learning_rate": 7.642466670446116e-07,
|
| 2044 |
+
"loss": 0.0798,
|
| 2045 |
+
"step": 10450
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 2.68748400307141,
|
| 2049 |
+
"grad_norm": 0.23310412466526031,
|
| 2050 |
+
"learning_rate": 7.059062616549164e-07,
|
| 2051 |
+
"loss": 0.0784,
|
| 2052 |
+
"step": 10500
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 2.700281545943179,
|
| 2056 |
+
"grad_norm": 0.16842219233512878,
|
| 2057 |
+
"learning_rate": 6.498172574357017e-07,
|
| 2058 |
+
"loss": 0.0776,
|
| 2059 |
+
"step": 10550
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 2.7130790888149474,
|
| 2063 |
+
"grad_norm": 0.254340797662735,
|
| 2064 |
+
"learning_rate": 5.959903613435638e-07,
|
| 2065 |
+
"loss": 0.0789,
|
| 2066 |
+
"step": 10600
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 2.7130790888149474,
|
| 2070 |
+
"eval_entity_f1": 0.7496691802371621,
|
| 2071 |
+
"eval_entity_precision": 0.6731460978984852,
|
| 2072 |
+
"eval_entity_recall": 0.8839167780966669,
|
| 2073 |
+
"eval_loss": 0.0812213197350502,
|
| 2074 |
+
"eval_runtime": 478.1215,
|
| 2075 |
+
"eval_samples_per_second": 1673.215,
|
| 2076 |
+
"eval_steps_per_second": 26.144,
|
| 2077 |
+
"step": 10600
|
| 2078 |
}
|
| 2079 |
],
|
| 2080 |
"logging_steps": 50,
|
|
|
|
| 2094 |
"attributes": {}
|
| 2095 |
}
|
| 2096 |
},
|
| 2097 |
+
"total_flos": 1.3406987906585723e+18,
|
| 2098 |
"train_batch_size": 256,
|
| 2099 |
"trial_name": null,
|
| 2100 |
"trial_params": null
|