Training in progress, step 700, 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 161533160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24974b33ce7060765c47ebe903de2b29b88680159505e8d759442f023d21ebb2
|
| 3 |
size 161533160
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 323292202
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fabd0551eb85b24d4c03fb8ae43773f2218d0a50a02e0461e9a6e8798d4d34ae
|
| 3 |
size 323292202
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5049981b79c03cb37c649de09d04121a68a1066cc6a5af0ae36ad8711e478e4a
|
| 3 |
size 1064
|
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": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -108,6 +108,20 @@
|
|
| 108 |
"learning_rate": 3.305739514348786e-05,
|
| 109 |
"loss": 0.8235,
|
| 110 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
}
|
| 112 |
],
|
| 113 |
"logging_steps": 50,
|
|
@@ -127,7 +141,7 @@
|
|
| 127 |
"attributes": {}
|
| 128 |
}
|
| 129 |
},
|
| 130 |
-
"total_flos":
|
| 131 |
"train_batch_size": 1,
|
| 132 |
"trial_name": null,
|
| 133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.11589403973509933,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 108 |
"learning_rate": 3.305739514348786e-05,
|
| 109 |
"loss": 0.8235,
|
| 110 |
"step": 600
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.1076158940397351,
|
| 114 |
+
"grad_norm": 2.4740138053894043,
|
| 115 |
+
"learning_rate": 3.581677704194261e-05,
|
| 116 |
+
"loss": 0.7918,
|
| 117 |
+
"step": 650
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11589403973509933,
|
| 121 |
+
"grad_norm": 2.5529448986053467,
|
| 122 |
+
"learning_rate": 3.8576158940397354e-05,
|
| 123 |
+
"loss": 0.7749,
|
| 124 |
+
"step": 700
|
| 125 |
}
|
| 126 |
],
|
| 127 |
"logging_steps": 50,
|
|
|
|
| 141 |
"attributes": {}
|
| 142 |
}
|
| 143 |
},
|
| 144 |
+
"total_flos": 5469524217298944.0,
|
| 145 |
"train_batch_size": 1,
|
| 146 |
"trial_name": null,
|
| 147 |
"trial_params": null
|