devvanshhh
commited on
Commit
·
bad2ad6
1
Parent(s):
1279464
Training in progress, epoch 5, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cce53d8a5b0d52a088989884443b54a18c00e44c84f9fbdccdebd441d1331d4
|
3 |
size 1256
|
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 sha256:0f0257d96340709b9e888279eaade1cdf9691afc5fe622d3ccad602484d2563b
|
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 sha256:378f88de765e5c573b571fa7188be55ecf77d3552c163e27fff15e37fb02e056
|
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,
|
@@ -65,13 +65,26 @@
|
|
65 |
"eval_samples_per_second": 1.964,
|
66 |
"eval_steps_per_second": 0.245,
|
67 |
"step": 716
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
}
|
69 |
],
|
70 |
"logging_steps": 500,
|
71 |
"max_steps": 895,
|
72 |
"num_train_epochs": 5,
|
73 |
"save_steps": 500,
|
74 |
-
"total_flos":
|
75 |
"trial_name": null,
|
76 |
"trial_params": null
|
77 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 895,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
65 |
"eval_samples_per_second": 1.964,
|
66 |
"eval_steps_per_second": 0.245,
|
67 |
"step": 716
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 5.0,
|
71 |
+
"eval_gen_len": 10.85,
|
72 |
+
"eval_loss": 0.684735894203186,
|
73 |
+
"eval_rouge1": 36.2186,
|
74 |
+
"eval_rouge2": 27.5662,
|
75 |
+
"eval_rougeL": 32.6055,
|
76 |
+
"eval_rougeLsum": 32.8805,
|
77 |
+
"eval_runtime": 81.8854,
|
78 |
+
"eval_samples_per_second": 1.954,
|
79 |
+
"eval_steps_per_second": 0.244,
|
80 |
+
"step": 895
|
81 |
}
|
82 |
],
|
83 |
"logging_steps": 500,
|
84 |
"max_steps": 895,
|
85 |
"num_train_epochs": 5,
|
86 |
"save_steps": 500,
|
87 |
+
"total_flos": 6715543070638080.0,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
90 |
}
|