Training in progress, step 1200, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d03ca2ed55f143d00ee4378fca4e62870ae916ccc591849e66f92d99a77a399
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c86da8e0146feee5bb953abf99d6151fb6866b67fc57d3f90f74d930c942b04
|
| 3 |
size 14709
|
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 sha256:6808914ec3d951e546ff4dbb32812f6f1715200a320bb499e89e56ac8f507d96
|
| 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": 9.
|
| 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,
|
|
@@ -2150,6 +2150,24 @@
|
|
| 2150 |
"mean_token_accuracy": 0.6396621257066727,
|
| 2151 |
"num_tokens": 4341032.0,
|
| 2152 |
"step": 1190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2153 |
}
|
| 2154 |
],
|
| 2155 |
"logging_steps": 5,
|
|
@@ -2169,7 +2187,7 @@
|
|
| 2169 |
"attributes": {}
|
| 2170 |
}
|
| 2171 |
},
|
| 2172 |
-
"total_flos": 2.
|
| 2173 |
"train_batch_size": 4,
|
| 2174 |
"trial_name": null,
|
| 2175 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2150 |
"mean_token_accuracy": 0.6396621257066727,
|
| 2151 |
"num_tokens": 4341032.0,
|
| 2152 |
"step": 1190
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 9.192307692307692,
|
| 2156 |
+
"grad_norm": 0.0,
|
| 2157 |
+
"learning_rate": 4.4030000000000004e-05,
|
| 2158 |
+
"loss": 1.7641,
|
| 2159 |
+
"mean_token_accuracy": 0.644762921333313,
|
| 2160 |
+
"num_tokens": 4358653.0,
|
| 2161 |
+
"step": 1195
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 9.23076923076923,
|
| 2165 |
+
"grad_norm": 0.0,
|
| 2166 |
+
"learning_rate": 4.4005e-05,
|
| 2167 |
+
"loss": 1.8077,
|
| 2168 |
+
"mean_token_accuracy": 0.6364401876926422,
|
| 2169 |
+
"num_tokens": 4376472.0,
|
| 2170 |
+
"step": 1200
|
| 2171 |
}
|
| 2172 |
],
|
| 2173 |
"logging_steps": 5,
|
|
|
|
| 2187 |
"attributes": {}
|
| 2188 |
}
|
| 2189 |
},
|
| 2190 |
+
"total_flos": 2.21858131562496e+17,
|
| 2191 |
"train_batch_size": 4,
|
| 2192 |
"trial_name": null,
|
| 2193 |
"trial_params": null
|