Training in progress, step 1180, 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:cf7ba55347be3009d65b0f6e45243c095cb0115dd9730e83831a737d420ed7d8
|
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 sha256:8ce7a1b50c1cfa308c27e5cb3651542491d426a9f882fb92cb544cabeb70bb31
|
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:ecb8413f834d7aea22eaaf4929929d97571a7bcc98ba8e7df76bc3dfd61eff41
|
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:db27570aff99c68af4609f5f7c05632809723cb9d1da7a19356fc2b24a3fe3ec
|
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,
|
@@ -935,14 +935,30 @@
|
|
935 |
"loss": 0.3937,
|
936 |
"num_input_tokens_seen": 778619,
|
937 |
"step": 1160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
938 |
}
|
939 |
],
|
940 |
"logging_steps": 10,
|
941 |
"max_steps": 2795,
|
942 |
-
"num_input_tokens_seen":
|
943 |
"num_train_epochs": 1,
|
944 |
"save_steps": 20,
|
945 |
-
"total_flos": 1.
|
946 |
"train_batch_size": 1,
|
947 |
"trial_name": null,
|
948 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4221824686940966,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1180,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
935 |
"loss": 0.3937,
|
936 |
"num_input_tokens_seen": 778619,
|
937 |
"step": 1160
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 0.4186046511627907,
|
941 |
+
"grad_norm": 0.24456287920475006,
|
942 |
+
"learning_rate": 0.00011627906976744187,
|
943 |
+
"loss": 0.4264,
|
944 |
+
"num_input_tokens_seen": 787085,
|
945 |
+
"step": 1170
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.4221824686940966,
|
949 |
+
"grad_norm": 0.2968457341194153,
|
950 |
+
"learning_rate": 0.00011556350626118069,
|
951 |
+
"loss": 0.4196,
|
952 |
+
"num_input_tokens_seen": 794103,
|
953 |
+
"step": 1180
|
954 |
}
|
955 |
],
|
956 |
"logging_steps": 10,
|
957 |
"max_steps": 2795,
|
958 |
+
"num_input_tokens_seen": 794103,
|
959 |
"num_train_epochs": 1,
|
960 |
"save_steps": 20,
|
961 |
+
"total_flos": 1.7856572181018624e+16,
|
962 |
"train_batch_size": 1,
|
963 |
"trial_name": null,
|
964 |
"trial_params": null
|