Training in progress, step 11200, 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 sha256:7d98df63972fc2e4daaf1bd1e0ab297746f7a42f2ae676738162e55aab2f233e
|
| 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 sha256:1976977350f5c06ce05fd495ce5eaf67c2815489ff2ffbbd80f76afdedb9bb1a
|
| 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:f9c475e1510f960f87a6874d3ed5ae40a4b21f142d5011bcc012b7d12e77f66e
|
| 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 sha256:0d2b56a873b62edf08353311a2201583d72f44f872314034d3be94b7c12f3e4d
|
| 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 sha256:88f0371238d70128fe141263becf02bdfcbfba1d0e867268958035a7e3bb8475
|
| 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:b0688c8441a9e4642075bb058465b7aefcd27cf469f26322931a1567c5d2fb8f
|
| 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 sha256:784a2938c290d5b3c2d1c5901e3fd434067031b6ab7697365d4278701489564f
|
| 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 sha256:2f9249a45d30a112fd8cd68af77ed8efdc0969042dc1616fb5742280ead2095a
|
| 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 sha256:0398926fab265216a618d307e026fbf996d06e83fa3ee6b51d9b15aea231b5bf
|
| 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 sha256:0eeee6408ad97126e72aa43e82b1d5996ea3b49775211b279199c49d1997f1a7
|
| 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:a92e6498d5f72094ee0b67eed3d450cbc8b1d525879162859225a9eaea2d9b41
|
| 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,
|
|
@@ -2153,6 +2153,45 @@
|
|
| 2153 |
"eval_samples_per_second": 1678.189,
|
| 2154 |
"eval_steps_per_second": 26.222,
|
| 2155 |
"step": 11000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2156 |
}
|
| 2157 |
],
|
| 2158 |
"logging_steps": 50,
|
|
@@ -2172,7 +2211,7 @@
|
|
| 2172 |
"attributes": {}
|
| 2173 |
}
|
| 2174 |
},
|
| 2175 |
-
"total_flos": 1.
|
| 2176 |
"train_batch_size": 256,
|
| 2177 |
"trial_name": null,
|
| 2178 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": 9800,
|
| 3 |
"best_metric": 0.7528361702207996,
|
| 4 |
"best_model_checkpoint": "model/checkpoint-9800",
|
| 5 |
+
"epoch": 2.866649603276171,
|
| 6 |
"eval_steps": 200,
|
| 7 |
+
"global_step": 11200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2153 |
"eval_samples_per_second": 1678.189,
|
| 2154 |
"eval_steps_per_second": 26.222,
|
| 2155 |
"step": 11000
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 2.828256974660865,
|
| 2159 |
+
"grad_norm": 0.20614302158355713,
|
| 2160 |
+
"learning_rate": 2.1489458302748483e-07,
|
| 2161 |
+
"loss": 0.0777,
|
| 2162 |
+
"step": 11050
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 2.841054517532634,
|
| 2166 |
+
"grad_norm": 0.229073628783226,
|
| 2167 |
+
"learning_rate": 1.8418174564098223e-07,
|
| 2168 |
+
"loss": 0.0792,
|
| 2169 |
+
"step": 11100
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 2.853852060404402,
|
| 2173 |
+
"grad_norm": 0.272368848323822,
|
| 2174 |
+
"learning_rate": 1.5581990259524588e-07,
|
| 2175 |
+
"loss": 0.0797,
|
| 2176 |
+
"step": 11150
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 2.866649603276171,
|
| 2180 |
+
"grad_norm": 0.2054791897535324,
|
| 2181 |
+
"learning_rate": 1.2981446794649576e-07,
|
| 2182 |
+
"loss": 0.0798,
|
| 2183 |
+
"step": 11200
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 2.866649603276171,
|
| 2187 |
+
"eval_entity_f1": 0.7498967902853477,
|
| 2188 |
+
"eval_entity_precision": 0.673780188544089,
|
| 2189 |
+
"eval_entity_recall": 0.8842643173961255,
|
| 2190 |
+
"eval_loss": 0.08130218833684921,
|
| 2191 |
+
"eval_runtime": 477.8516,
|
| 2192 |
+
"eval_samples_per_second": 1674.16,
|
| 2193 |
+
"eval_steps_per_second": 26.159,
|
| 2194 |
+
"step": 11200
|
| 2195 |
}
|
| 2196 |
],
|
| 2197 |
"logging_steps": 50,
|
|
|
|
| 2211 |
"attributes": {}
|
| 2212 |
}
|
| 2213 |
},
|
| 2214 |
+
"total_flos": 1.416591358310744e+18,
|
| 2215 |
"train_batch_size": 256,
|
| 2216 |
"trial_name": null,
|
| 2217 |
"trial_params": null
|