Training in progress, step 3940, 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 sha256:67a71842616a4677b02d34458645aa12fb6137b2872cedd986360d51d4ad4e1d
|
| 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 sha256:5f1af448ba076823eea24e332dcf9c9ce467a0e0fb62c0340c2000d748d2cda6
|
| 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 sha256:45234e471588cc36ff7664898ecd1cc225bbd0b663638c6c91062c96426e5ef4
|
| 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 sha256:338ca2abead33bd1f1f2eb57903990248de5a037592d4dde0e4c004c95dd856c
|
| 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,
|
|
@@ -3948,6 +3948,16 @@
|
|
| 3948 |
"mean_token_accuracy": 0.767199169844389,
|
| 3949 |
"num_tokens": 18314733.0,
|
| 3950 |
"step": 3930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3951 |
}
|
| 3952 |
],
|
| 3953 |
"logging_steps": 10,
|
|
@@ -3967,7 +3977,7 @@
|
|
| 3967 |
"attributes": {}
|
| 3968 |
}
|
| 3969 |
},
|
| 3970 |
-
"total_flos": 8.
|
| 3971 |
"train_batch_size": 4,
|
| 3972 |
"trial_name": null,
|
| 3973 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8405333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3948 |
"mean_token_accuracy": 0.767199169844389,
|
| 3949 |
"num_tokens": 18314733.0,
|
| 3950 |
"step": 3930
|
| 3951 |
+
},
|
| 3952 |
+
{
|
| 3953 |
+
"entropy": 0.9812062717974186,
|
| 3954 |
+
"epoch": 0.8405333333333334,
|
| 3955 |
+
"grad_norm": 0.2531512677669525,
|
| 3956 |
+
"learning_rate": 6.530922485470531e-05,
|
| 3957 |
+
"loss": 1.0596059799194335,
|
| 3958 |
+
"mean_token_accuracy": 0.764385013282299,
|
| 3959 |
+
"num_tokens": 18367778.0,
|
| 3960 |
+
"step": 3940
|
| 3961 |
}
|
| 3962 |
],
|
| 3963 |
"logging_steps": 10,
|
|
|
|
| 3977 |
"attributes": {}
|
| 3978 |
}
|
| 3979 |
},
|
| 3980 |
+
"total_flos": 8.695267306562765e+16,
|
| 3981 |
"train_batch_size": 4,
|
| 3982 |
"trial_name": null,
|
| 3983 |
"trial_params": null
|