Training in progress, step 1190, 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:ce101e3361c28f2def2711c10164c16eab49a08d0e38cf2c2634d3a3a979a397
|
| 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 sha256:77e6770c04e757b1a92dc51f0f5c8d8a59732594bf9e6d97d1604e190e8bffa4
|
| 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:c14883158d1cb7c168533059f62b2bc609703cf55cbe8aeb4f60f77c6aa2e148
|
| 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,
|
|
@@ -2132,6 +2132,24 @@
|
|
| 2132 |
"mean_token_accuracy": 0.6541598349809646,
|
| 2133 |
"num_tokens": 4304365.0,
|
| 2134 |
"step": 1180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2135 |
}
|
| 2136 |
],
|
| 2137 |
"logging_steps": 5,
|
|
@@ -2151,7 +2169,7 @@
|
|
| 2151 |
"attributes": {}
|
| 2152 |
}
|
| 2153 |
},
|
| 2154 |
-
"total_flos": 2.
|
| 2155 |
"train_batch_size": 4,
|
| 2156 |
"trial_name": null,
|
| 2157 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1190,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2132 |
"mean_token_accuracy": 0.6541598349809646,
|
| 2133 |
"num_tokens": 4304365.0,
|
| 2134 |
"step": 1180
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 9.115384615384615,
|
| 2138 |
+
"grad_norm": 0.0,
|
| 2139 |
+
"learning_rate": 4.4080000000000005e-05,
|
| 2140 |
+
"loss": 1.6924,
|
| 2141 |
+
"mean_token_accuracy": 0.6604053825139999,
|
| 2142 |
+
"num_tokens": 4323536.0,
|
| 2143 |
+
"step": 1185
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 9.153846153846153,
|
| 2147 |
+
"grad_norm": 0.0,
|
| 2148 |
+
"learning_rate": 4.4055000000000004e-05,
|
| 2149 |
+
"loss": 1.8026,
|
| 2150 |
+
"mean_token_accuracy": 0.6396621257066727,
|
| 2151 |
+
"num_tokens": 4341032.0,
|
| 2152 |
+
"step": 1190
|
| 2153 |
}
|
| 2154 |
],
|
| 2155 |
"logging_steps": 5,
|
|
|
|
| 2169 |
"attributes": {}
|
| 2170 |
}
|
| 2171 |
},
|
| 2172 |
+
"total_flos": 2.200790112288768e+17,
|
| 2173 |
"train_batch_size": 4,
|
| 2174 |
"trial_name": null,
|
| 2175 |
"trial_params": null
|