Training in progress, step 2080, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:757ffee9f035309f3e94d8424db99c14c9982a0e399cd49f9d7e57587c6ef344
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c44d01af45036adc5956b69e7802d64494e76fde68065df05f22cd16030d787
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d30953a6c4219b232dc932b47c5da22b3be2325bb0f179a417955c84590a05a
|
| 3 |
size 14645
|
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 sha256:9d57873271a065bcbd42a222528b35e0e783b73a43db85ec19de91f186457823
|
| 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": 0.
|
| 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,
|
|
@@ -2088,6 +2088,16 @@
|
|
| 2088 |
"mean_token_accuracy": 0.7708904504776001,
|
| 2089 |
"num_tokens": 9581893.0,
|
| 2090 |
"step": 2070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2091 |
}
|
| 2092 |
],
|
| 2093 |
"logging_steps": 10,
|
|
@@ -2107,7 +2117,7 @@
|
|
| 2107 |
"attributes": {}
|
| 2108 |
}
|
| 2109 |
},
|
| 2110 |
-
"total_flos": 4.
|
| 2111 |
"train_batch_size": 4,
|
| 2112 |
"trial_name": null,
|
| 2113 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4437333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2088 |
"mean_token_accuracy": 0.7708904504776001,
|
| 2089 |
"num_tokens": 9581893.0,
|
| 2090 |
"step": 2070
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"entropy": 0.8260227806866169,
|
| 2094 |
+
"epoch": 0.4437333333333333,
|
| 2095 |
+
"grad_norm": 0.31099778413772583,
|
| 2096 |
+
"learning_rate": 9.081592291152252e-05,
|
| 2097 |
+
"loss": 0.9264348983764649,
|
| 2098 |
+
"mean_token_accuracy": 0.7857892021536828,
|
| 2099 |
+
"num_tokens": 9624465.0,
|
| 2100 |
+
"step": 2080
|
| 2101 |
}
|
| 2102 |
],
|
| 2103 |
"logging_steps": 10,
|
|
|
|
| 2117 |
"attributes": {}
|
| 2118 |
}
|
| 2119 |
},
|
| 2120 |
+
"total_flos": 4.568532578169446e+16,
|
| 2121 |
"train_batch_size": 4,
|
| 2122 |
"trial_name": null,
|
| 2123 |
"trial_params": null
|