Training in progress, step 4070, 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 sha256:93ef1f07c11a6b90609b8645142cc53829e92b3caff7920e5d03b8d02384b1b0
|
| 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 sha256:2813a9854b37407768cfc611a6fce15a56bfa23a08144ae15296c551f230a0d7
|
| 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:ab8c3cb4f9d852761b66d2cf9068feaf1e95c33532bc68ce82647b882e9fdf10
|
| 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 sha256:869bc43bd5ce66a990e097b9d9594cc766e3ea51ea3aa0b58c8fd4323f1ef782
|
| 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,
|
|
@@ -4078,6 +4078,16 @@
|
|
| 4078 |
"mean_token_accuracy": 0.7723157353699207,
|
| 4079 |
"num_tokens": 18938986.0,
|
| 4080 |
"step": 4060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4081 |
}
|
| 4082 |
],
|
| 4083 |
"logging_steps": 10,
|
|
@@ -4097,7 +4107,7 @@
|
|
| 4097 |
"attributes": {}
|
| 4098 |
}
|
| 4099 |
},
|
| 4100 |
-
"total_flos": 8.
|
| 4101 |
"train_batch_size": 4,
|
| 4102 |
"trial_name": null,
|
| 4103 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8682666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4070,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4078 |
"mean_token_accuracy": 0.7723157353699207,
|
| 4079 |
"num_tokens": 18938986.0,
|
| 4080 |
"step": 4060
|
| 4081 |
+
},
|
| 4082 |
+
{
|
| 4083 |
+
"entropy": 0.9397155575454235,
|
| 4084 |
+
"epoch": 0.8682666666666666,
|
| 4085 |
+
"grad_norm": 0.2758144736289978,
|
| 4086 |
+
"learning_rate": 6.315258113571876e-05,
|
| 4087 |
+
"loss": 1.0858741760253907,
|
| 4088 |
+
"mean_token_accuracy": 0.7691247522830963,
|
| 4089 |
+
"num_tokens": 18984144.0,
|
| 4090 |
+
"step": 4070
|
| 4091 |
}
|
| 4092 |
],
|
| 4093 |
"logging_steps": 10,
|
|
|
|
| 4107 |
"attributes": {}
|
| 4108 |
}
|
| 4109 |
},
|
| 4110 |
+
"total_flos": 8.98662282310226e+16,
|
| 4111 |
"train_batch_size": 4,
|
| 4112 |
"trial_name": null,
|
| 4113 |
"trial_params": null
|