devvanshhh
commited on
Commit
•
63e2f71
1
Parent(s):
e0effe7
Training in progress, epoch 3, 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 37789864
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4706d3e8332053d7721589e6a38d6595e86581ed760f55cdcf05a85605c87b48
|
3 |
size 37789864
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2621690
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c68ddcf25c5378efef054e524d79bfc5fe4b37c9bb05dcb71e62f44730f761b
|
3 |
size 2621690
|
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:a7a27874f7dc93ced479b2661f0507a486022fb461d136d2fd60f69bdbbfaa50
|
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 sha256:892dd21dc624558e73e516bce349cbb194a290f9f9004ca6804bea2538f6de16
|
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":
|
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,
|
@@ -39,13 +39,26 @@
|
|
39 |
"eval_samples_per_second": 1.872,
|
40 |
"eval_steps_per_second": 0.238,
|
41 |
"step": 656
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|
43 |
],
|
44 |
"logging_steps": 500,
|
45 |
"max_steps": 3936,
|
46 |
"num_train_epochs": 12,
|
47 |
"save_steps": 500,
|
48 |
-
"total_flos":
|
49 |
"trial_name": null,
|
50 |
"trial_params": null
|
51 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 984,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
39 |
"eval_samples_per_second": 1.872,
|
40 |
"eval_steps_per_second": 0.238,
|
41 |
"step": 656
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_gen_len": 13.807560137457045,
|
46 |
+
"eval_loss": 0.7708158493041992,
|
47 |
+
"eval_rouge1": 22.6847,
|
48 |
+
"eval_rouge2": 15.805,
|
49 |
+
"eval_rougeL": 19.6336,
|
50 |
+
"eval_rougeLsum": 19.8945,
|
51 |
+
"eval_runtime": 155.3127,
|
52 |
+
"eval_samples_per_second": 1.874,
|
53 |
+
"eval_steps_per_second": 0.238,
|
54 |
+
"step": 984
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 500,
|
58 |
"max_steps": 3936,
|
59 |
"num_train_epochs": 12,
|
60 |
"save_steps": 500,
|
61 |
+
"total_flos": 7374426541719552.0,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
64 |
}
|