Training in progress, step 3740, 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:bbc1b89622751f053e7ff2346b133b3028758569564d88fe887d3e0eba781ce0
|
| 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:f40a889ff8bde7aa5f57989276fd833f13b31db95555cdd2efa4d8045ba54a8e
|
| 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 sha256:0565aab051b221c8329a27b9f3b009b32f3d27668dd77b90453c64515c758093
|
| 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 sha256:996645c7cd1b60a8b146fecd5fbe97bf4e16e497389a1e7205228f62963234f5
|
| 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,
|
|
@@ -3748,6 +3748,16 @@
|
|
| 3748 |
"mean_token_accuracy": 0.7779143631458283,
|
| 3749 |
"num_tokens": 17370948.0,
|
| 3750 |
"step": 3730
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3751 |
}
|
| 3752 |
],
|
| 3753 |
"logging_steps": 10,
|
|
@@ -3767,7 +3777,7 @@
|
|
| 3767 |
"attributes": {}
|
| 3768 |
}
|
| 3769 |
},
|
| 3770 |
-
"total_flos": 8.
|
| 3771 |
"train_batch_size": 4,
|
| 3772 |
"trial_name": null,
|
| 3773 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7978666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3740,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3748 |
"mean_token_accuracy": 0.7779143631458283,
|
| 3749 |
"num_tokens": 17370948.0,
|
| 3750 |
"step": 3730
|
| 3751 |
+
},
|
| 3752 |
+
{
|
| 3753 |
+
"entropy": 0.9536221623420715,
|
| 3754 |
+
"epoch": 0.7978666666666666,
|
| 3755 |
+
"grad_norm": 0.2456534057855606,
|
| 3756 |
+
"learning_rate": 6.856510642384499e-05,
|
| 3757 |
+
"loss": 1.0342220306396483,
|
| 3758 |
+
"mean_token_accuracy": 0.7630825422704219,
|
| 3759 |
+
"num_tokens": 17421511.0,
|
| 3760 |
+
"step": 3740
|
| 3761 |
}
|
| 3762 |
],
|
| 3763 |
"logging_steps": 10,
|
|
|
|
| 3777 |
"attributes": {}
|
| 3778 |
}
|
| 3779 |
},
|
| 3780 |
+
"total_flos": 8.245690411748966e+16,
|
| 3781 |
"train_batch_size": 4,
|
| 3782 |
"trial_name": null,
|
| 3783 |
"trial_params": null
|