Training in progress, step 1030, 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 sha256:467a2819de33d13cd3ec6c1d329884b789a6ebd587b70a4aeef7547662b8c67a
|
| 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 sha256:2826672e1a760302c409493097e81d6c446eb19f5305b4def04adf0dc1424d3b
|
| 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:a48398753797982f57132e4a985d57b2f06dc0a69fa03baa04266aa47eed7a3f
|
| 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 sha256:110b2198a6eb8399c829026bd40642ad3b90a8a396ba65aeafa58208cd8b7210
|
| 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,
|
|
@@ -1038,6 +1038,16 @@
|
|
| 1038 |
"mean_token_accuracy": 0.7686716303229332,
|
| 1039 |
"num_tokens": 4754969.0,
|
| 1040 |
"step": 1020
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1041 |
}
|
| 1042 |
],
|
| 1043 |
"logging_steps": 10,
|
|
@@ -1057,7 +1067,7 @@
|
|
| 1057 |
"attributes": {}
|
| 1058 |
}
|
| 1059 |
},
|
| 1060 |
-
"total_flos": 2.
|
| 1061 |
"train_batch_size": 4,
|
| 1062 |
"trial_name": null,
|
| 1063 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.21973333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1030,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1038 |
"mean_token_accuracy": 0.7686716303229332,
|
| 1039 |
"num_tokens": 4754969.0,
|
| 1040 |
"step": 1020
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"entropy": 0.9788610845804214,
|
| 1044 |
+
"epoch": 0.21973333333333334,
|
| 1045 |
+
"grad_norm": 0.22762160003185272,
|
| 1046 |
+
"learning_rate": 9.841656531558163e-05,
|
| 1047 |
+
"loss": 1.0857264518737793,
|
| 1048 |
+
"mean_token_accuracy": 0.755905470252037,
|
| 1049 |
+
"num_tokens": 4799172.0,
|
| 1050 |
+
"step": 1030
|
| 1051 |
}
|
| 1052 |
],
|
| 1053 |
"logging_steps": 10,
|
|
|
|
| 1067 |
"attributes": {}
|
| 1068 |
}
|
| 1069 |
},
|
| 1070 |
+
"total_flos": 2.2688577960293376e+16,
|
| 1071 |
"train_batch_size": 4,
|
| 1072 |
"trial_name": null,
|
| 1073 |
"trial_params": null
|