step 20000 | vovaRL | 5242880000 tok
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- training_state.json +48 -48
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5167420536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49e6f7557d2eeae7c3437e524335b6113290dfbabfc4a7d2ff27b91d6633538b
|
| 3 |
size 5167420536
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10333957008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bd6d3835d3e27da9ce246f993f3bb35f09ff873453725efef511b437ebfbdb9
|
| 3 |
size 10333957008
|
training_state.json
CHANGED
|
@@ -1,70 +1,70 @@
|
|
| 1 |
{
|
| 2 |
-
"step":
|
| 3 |
-
"global_tokens":
|
| 4 |
"contributor": "vovaRL",
|
| 5 |
"cloud": "home",
|
| 6 |
"base_model": "scratch:colibri-nano",
|
| 7 |
-
"wall_clock_s":
|
| 8 |
"history_tail": [
|
| 9 |
{
|
| 10 |
-
"step":
|
| 11 |
-
"t":
|
| 12 |
-
"ntp": 2.
|
| 13 |
-
"zloss": 0.
|
| 14 |
-
"lr": 3.
|
| 15 |
-
"grad_norm": 0.
|
| 16 |
-
"ppl": 9.
|
| 17 |
-
"balance_max_imbalance": 0.
|
| 18 |
"balance_dead_frac": 0.0,
|
| 19 |
-
"tokens":
|
| 20 |
},
|
| 21 |
{
|
| 22 |
-
"step":
|
| 23 |
-
"t":
|
| 24 |
-
"ntp": 2.
|
| 25 |
-
"zloss": 0.
|
| 26 |
-
"lr": 3.
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"ppl":
|
| 29 |
-
"balance_max_imbalance": 0.
|
| 30 |
"balance_dead_frac": 0.0,
|
| 31 |
-
"tokens":
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"step":
|
| 35 |
-
"t":
|
| 36 |
-
"ntp": 2.
|
| 37 |
-
"zloss": 0.
|
| 38 |
-
"lr": 3.
|
| 39 |
-
"grad_norm": 0.
|
| 40 |
-
"ppl":
|
| 41 |
-
"balance_max_imbalance": 0.
|
| 42 |
"balance_dead_frac": 0.0,
|
| 43 |
-
"tokens":
|
| 44 |
},
|
| 45 |
{
|
| 46 |
-
"step":
|
| 47 |
-
"t":
|
| 48 |
-
"ntp": 2.
|
| 49 |
-
"zloss": 0.
|
| 50 |
-
"lr": 3.
|
| 51 |
-
"grad_norm": 0.
|
| 52 |
-
"ppl":
|
| 53 |
-
"balance_max_imbalance": 0.
|
| 54 |
"balance_dead_frac": 0.0,
|
| 55 |
-
"tokens":
|
| 56 |
},
|
| 57 |
{
|
| 58 |
-
"step":
|
| 59 |
-
"t":
|
| 60 |
-
"ntp": 2.
|
| 61 |
-
"zloss": 0.
|
| 62 |
-
"lr":
|
| 63 |
-
"grad_norm": 0.
|
| 64 |
-
"ppl":
|
| 65 |
-
"balance_max_imbalance": 0.
|
| 66 |
"balance_dead_frac": 0.0,
|
| 67 |
-
"tokens":
|
| 68 |
}
|
| 69 |
]
|
| 70 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"step": 20000,
|
| 3 |
+
"global_tokens": 5242880000,
|
| 4 |
"contributor": "vovaRL",
|
| 5 |
"cloud": "home",
|
| 6 |
"base_model": "scratch:colibri-nano",
|
| 7 |
+
"wall_clock_s": 24702.277401924133,
|
| 8 |
"history_tail": [
|
| 9 |
{
|
| 10 |
+
"step": 19960,
|
| 11 |
+
"t": 1785242935.469,
|
| 12 |
+
"ntp": 2.2264950275421143,
|
| 13 |
+
"zloss": 0.28825539350509644,
|
| 14 |
+
"lr": 3.000328985477171e-05,
|
| 15 |
+
"grad_norm": 0.28515625,
|
| 16 |
+
"ppl": 9.267327361978355,
|
| 17 |
+
"balance_max_imbalance": 0.1207275390625,
|
| 18 |
"balance_dead_frac": 0.0,
|
| 19 |
+
"tokens": 5232394240
|
| 20 |
},
|
| 21 |
{
|
| 22 |
+
"step": 19970,
|
| 23 |
+
"t": 1785243058.314,
|
| 24 |
+
"ntp": 2.558842420578003,
|
| 25 |
+
"zloss": 0.3002420961856842,
|
| 26 |
+
"lr": 3.000185054659739e-05,
|
| 27 |
+
"grad_norm": 0.302734375,
|
| 28 |
+
"ppl": 12.920851743202324,
|
| 29 |
+
"balance_max_imbalance": 0.06561279296875,
|
| 30 |
"balance_dead_frac": 0.0,
|
| 31 |
+
"tokens": 5235015680
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"step": 19980,
|
| 35 |
+
"t": 1785243181.299,
|
| 36 |
+
"ntp": 2.413142442703247,
|
| 37 |
+
"zloss": 0.2963441014289856,
|
| 38 |
+
"lr": 3.0000822466198297e-05,
|
| 39 |
+
"grad_norm": 0.2734375,
|
| 40 |
+
"ppl": 11.169004011286283,
|
| 41 |
+
"balance_max_imbalance": 0.09515380859375,
|
| 42 |
"balance_dead_frac": 0.0,
|
| 43 |
+
"tokens": 5237637120
|
| 44 |
},
|
| 45 |
{
|
| 46 |
+
"step": 19990,
|
| 47 |
+
"t": 1785243304.446,
|
| 48 |
+
"ntp": 2.3685061931610107,
|
| 49 |
+
"zloss": 0.292042076587677,
|
| 50 |
+
"lr": 3.000020561670616e-05,
|
| 51 |
+
"grad_norm": 0.291015625,
|
| 52 |
+
"ppl": 10.681424375812318,
|
| 53 |
+
"balance_max_imbalance": 0.2261962890625,
|
| 54 |
"balance_dead_frac": 0.0,
|
| 55 |
+
"tokens": 5240258560
|
| 56 |
},
|
| 57 |
{
|
| 58 |
+
"step": 20000,
|
| 59 |
+
"t": 1785243427.437,
|
| 60 |
+
"ntp": 2.834693670272827,
|
| 61 |
+
"zloss": 0.2698419988155365,
|
| 62 |
+
"lr": 2.9999999999999997e-05,
|
| 63 |
+
"grad_norm": 0.28125,
|
| 64 |
+
"ppl": 17.025184181485457,
|
| 65 |
+
"balance_max_imbalance": 0.1982421875,
|
| 66 |
"balance_dead_frac": 0.0,
|
| 67 |
+
"tokens": 5242880000
|
| 68 |
}
|
| 69 |
]
|
| 70 |
}
|