rakhman-llm
commited on
Commit
•
43567c0
1
Parent(s):
27109a9
Training in progress, step 3500, 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:a4415a57ed1e906d7ff833556b8a11f027662dd448248d9ae50f44e7e62ce6cf
|
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 sha256:5ae503b116281a5be4ce2cb1c0c2285ad2f47b8c195efb474680b2c075e541be
|
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:b11c05638bda866f239e62be186f5d45223ea93c75579fa732877ff4152241e3
|
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:ba54f9fe023975b85168af100e7732b40b2c7c545baa0b2edcf89745104d9360
|
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,
|
@@ -49,6 +49,13 @@
|
|
49 |
"learning_rate": 1.584788029925187e-05,
|
50 |
"loss": 0.4193,
|
51 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 500,
|
@@ -68,7 +75,7 @@
|
|
68 |
"attributes": {}
|
69 |
}
|
70 |
},
|
71 |
-
"total_flos":
|
72 |
"train_batch_size": 2,
|
73 |
"trial_name": null,
|
74 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7273482959268496,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
49 |
"learning_rate": 1.584788029925187e-05,
|
50 |
"loss": 0.4193,
|
51 |
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.7273482959268496,
|
55 |
+
"grad_norm": 1.0217444896697998,
|
56 |
+
"learning_rate": 1.5155167636464397e-05,
|
57 |
+
"loss": 0.4215,
|
58 |
+
"step": 3500
|
59 |
}
|
60 |
],
|
61 |
"logging_steps": 500,
|
|
|
75 |
"attributes": {}
|
76 |
}
|
77 |
},
|
78 |
+
"total_flos": 4262705233920000.0,
|
79 |
"train_batch_size": 2,
|
80 |
"trial_name": null,
|
81 |
"trial_params": null
|