Training in progress, step 1590, 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 1316913776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c714f24557e0e04842f453ff50a2d6a5ed01514cbf5f840ffbb248af8b718fd1
|
| 3 |
size 1316913776
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8908124
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42c79e7e9054a611d065639508c3028639bf925b01f3ee5ee045da349d0e0350
|
| 3 |
size 8908124
|
last-checkpoint/rng_state.pth
CHANGED
|
Binary files a/last-checkpoint/rng_state.pth and b/last-checkpoint/rng_state.pth differ
|
|
|
last-checkpoint/scheduler.pt
CHANGED
|
Binary files a/last-checkpoint/scheduler.pt and b/last-checkpoint/scheduler.pt differ
|
|
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1099,6 +1099,27 @@
|
|
| 1099 |
"learning_rate": 0.000332546157148991,
|
| 1100 |
"loss": 0.7964,
|
| 1101 |
"step": 1560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1102 |
}
|
| 1103 |
],
|
| 1104 |
"logging_steps": 10,
|
|
@@ -1106,7 +1127,7 @@
|
|
| 1106 |
"num_input_tokens_seen": 0,
|
| 1107 |
"num_train_epochs": 1,
|
| 1108 |
"save_steps": 30,
|
| 1109 |
-
"total_flos": 1.
|
| 1110 |
"train_batch_size": 3,
|
| 1111 |
"trial_name": null,
|
| 1112 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.34134821811936455,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1590,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1099 |
"learning_rate": 0.000332546157148991,
|
| 1100 |
"loss": 0.7964,
|
| 1101 |
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.33705452984113354,
|
| 1105 |
+
"grad_norm": 1.5397554636001587,
|
| 1106 |
+
"learning_rate": 0.0003314727350794333,
|
| 1107 |
+
"loss": 0.7802,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.339201373980249,
|
| 1112 |
+
"grad_norm": 1.2875391244888306,
|
| 1113 |
+
"learning_rate": 0.00033039931300987544,
|
| 1114 |
+
"loss": 0.7764,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.34134821811936455,
|
| 1119 |
+
"grad_norm": 1.0845388174057007,
|
| 1120 |
+
"learning_rate": 0.0003293258909403177,
|
| 1121 |
+
"loss": 0.7839,
|
| 1122 |
+
"step": 1590
|
| 1123 |
}
|
| 1124 |
],
|
| 1125 |
"logging_steps": 10,
|
|
|
|
| 1127 |
"num_input_tokens_seen": 0,
|
| 1128 |
"num_train_epochs": 1,
|
| 1129 |
"save_steps": 30,
|
| 1130 |
+
"total_flos": 1.2016090886217754e+17,
|
| 1131 |
"train_batch_size": 3,
|
| 1132 |
"trial_name": null,
|
| 1133 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
Binary files a/last-checkpoint/training_args.bin and b/last-checkpoint/training_args.bin differ
|
|
|