Training in progress, step 1170, 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 sha256:4b237e58e8e7227fbe9fcea56e97d1c2014c27bf6316e62203b8cdb3666bb72e
|
| 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 sha256:8b94d21ff9c9b00fbf47c68b10902e5a751546ebb4055dd8f254011cb29c3a24
|
| 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 sha256:6b422a26b1ab6b2d13cdeff23327b63843a9c3716070fd2f9005fad1eb285bc3
|
| 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":
|
| 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,
|
|
@@ -2096,6 +2096,24 @@
|
|
| 2096 |
"mean_token_accuracy": 0.6474886476993561,
|
| 2097 |
"num_tokens": 4230913.0,
|
| 2098 |
"step": 1160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2099 |
}
|
| 2100 |
],
|
| 2101 |
"logging_steps": 5,
|
|
@@ -2115,7 +2133,7 @@
|
|
| 2115 |
"attributes": {}
|
| 2116 |
}
|
| 2117 |
},
|
| 2118 |
-
"total_flos": 2.
|
| 2119 |
"train_batch_size": 4,
|
| 2120 |
"trial_name": null,
|
| 2121 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2096 |
"mean_token_accuracy": 0.6474886476993561,
|
| 2097 |
"num_tokens": 4230913.0,
|
| 2098 |
"step": 1160
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 8.961538461538462,
|
| 2102 |
+
"grad_norm": 0.0,
|
| 2103 |
+
"learning_rate": 4.418000000000001e-05,
|
| 2104 |
+
"loss": 1.763,
|
| 2105 |
+
"mean_token_accuracy": 0.6492164492607116,
|
| 2106 |
+
"num_tokens": 4248472.0,
|
| 2107 |
+
"step": 1165
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 9.0,
|
| 2111 |
+
"grad_norm": 0.0,
|
| 2112 |
+
"learning_rate": 4.4155e-05,
|
| 2113 |
+
"loss": 1.6968,
|
| 2114 |
+
"mean_token_accuracy": 0.661212831735611,
|
| 2115 |
+
"num_tokens": 4266945.0,
|
| 2116 |
+
"step": 1170
|
| 2117 |
}
|
| 2118 |
],
|
| 2119 |
"logging_steps": 5,
|
|
|
|
| 2133 |
"attributes": {}
|
| 2134 |
}
|
| 2135 |
},
|
| 2136 |
+
"total_flos": 2.1633992111407104e+17,
|
| 2137 |
"train_batch_size": 4,
|
| 2138 |
"trial_name": null,
|
| 2139 |
"trial_params": null
|