rakhman-llm
commited on
Training in progress, step 6948, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d056bee8dac2886ced92ff9ac128af3dac1a3c85b3e6187ff0fcb2ea1f07c61
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c83abad64a060d22d33db5c0a8633e6faf59aeb532e9e71346305c184d73ce85
|
3 |
size 1783272762
|
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 sha256:25b6d5721442e3d1371f64bb40d6e230a8d7c3e175d90708e0a2ead580a9ed65
|
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 sha256:44ffc851a9e37cbecb43e190af6ad5f826b8d0fd34fdd71720847fbb519df957
|
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,
|
@@ -39,9 +39,9 @@
|
|
39 |
{
|
40 |
"epoch": 1.0,
|
41 |
"eval_loss": 0.33670297265052795,
|
42 |
-
"eval_runtime": 28.
|
43 |
-
"eval_samples_per_second": 16.
|
44 |
-
"eval_steps_per_second": 4.
|
45 |
"step": 2316
|
46 |
},
|
47 |
{
|
@@ -82,9 +82,9 @@
|
|
82 |
{
|
83 |
"epoch": 2.0,
|
84 |
"eval_loss": 0.3095574975013733,
|
85 |
-
"eval_runtime": 28.
|
86 |
-
"eval_samples_per_second": 16.
|
87 |
-
"eval_steps_per_second": 4.
|
88 |
"step": 4632
|
89 |
},
|
90 |
{
|
@@ -128,12 +128,12 @@
|
|
128 |
"should_evaluate": false,
|
129 |
"should_log": false,
|
130 |
"should_save": true,
|
131 |
-
"should_training_stop":
|
132 |
},
|
133 |
"attributes": {}
|
134 |
}
|
135 |
},
|
136 |
-
"total_flos": 1.
|
137 |
"train_batch_size": 4,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 6948,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
39 |
{
|
40 |
"epoch": 1.0,
|
41 |
"eval_loss": 0.33670297265052795,
|
42 |
+
"eval_runtime": 28.2248,
|
43 |
+
"eval_samples_per_second": 16.723,
|
44 |
+
"eval_steps_per_second": 4.181,
|
45 |
"step": 2316
|
46 |
},
|
47 |
{
|
|
|
82 |
{
|
83 |
"epoch": 2.0,
|
84 |
"eval_loss": 0.3095574975013733,
|
85 |
+
"eval_runtime": 28.2419,
|
86 |
+
"eval_samples_per_second": 16.713,
|
87 |
+
"eval_steps_per_second": 4.178,
|
88 |
"step": 4632
|
89 |
},
|
90 |
{
|
|
|
128 |
"should_evaluate": false,
|
129 |
"should_log": false,
|
130 |
"should_save": true,
|
131 |
+
"should_training_stop": true
|
132 |
},
|
133 |
"attributes": {}
|
134 |
}
|
135 |
},
|
136 |
+
"total_flos": 1.692233082077184e+16,
|
137 |
"train_batch_size": 4,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2d71d788b491a41c54d3b024285748be4a2e443d732e96343f48dd9941e304a
|
3 |
size 5432
|