bhuvanmdev
commited on
Training in progress, step 1380, 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 100697728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b616fe2eb021d20d4875636738be3ca7342fc6db866fd391eb53743dd565cb0
|
3 |
size 100697728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201541754
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5356f6af8453685dfcd2ab29084ffd177cb62b8eaee4a3289a76f99910495ddc
|
3 |
size 201541754
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44f04742b905a4ba4f17b43b2fddc49db3e772b856badc745872559eec73cca5
|
3 |
size 14244
|
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:bc40c38146bda7179f03752fd8672ec7d4feef1519e7b61e194eda1f35f35156
|
3 |
size 1064
|
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,
|
@@ -1095,14 +1095,30 @@
|
|
1095 |
"loss": 0.4049,
|
1096 |
"num_input_tokens_seen": 915272,
|
1097 |
"step": 1360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1098 |
}
|
1099 |
],
|
1100 |
"logging_steps": 10,
|
1101 |
"max_steps": 2795,
|
1102 |
-
"num_input_tokens_seen":
|
1103 |
"num_train_epochs": 1,
|
1104 |
"save_steps": 20,
|
1105 |
-
"total_flos": 2.
|
1106 |
"train_batch_size": 1,
|
1107 |
"trial_name": null,
|
1108 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4937388193202147,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1380,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1095 |
"loss": 0.4049,
|
1096 |
"num_input_tokens_seen": 915272,
|
1097 |
"step": 1360
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 0.49016100178890876,
|
1101 |
+
"grad_norm": 0.249292254447937,
|
1102 |
+
"learning_rate": 0.00010196779964221825,
|
1103 |
+
"loss": 0.4064,
|
1104 |
+
"num_input_tokens_seen": 921729,
|
1105 |
+
"step": 1370
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 0.4937388193202147,
|
1109 |
+
"grad_norm": 0.2855275869369507,
|
1110 |
+
"learning_rate": 0.00010125223613595707,
|
1111 |
+
"loss": 0.4092,
|
1112 |
+
"num_input_tokens_seen": 928645,
|
1113 |
+
"step": 1380
|
1114 |
}
|
1115 |
],
|
1116 |
"logging_steps": 10,
|
1117 |
"max_steps": 2795,
|
1118 |
+
"num_input_tokens_seen": 928645,
|
1119 |
"num_train_epochs": 1,
|
1120 |
"save_steps": 20,
|
1121 |
+
"total_flos": 2.088194664047616e+16,
|
1122 |
"train_batch_size": 1,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|