Upload full trainer checkpoint step=5864 (profile=llama3_1_8b_base_lessdata, run_type=sft)
Browse files- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/adapter_config.json +5 -5
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/adapter_model.safetensors +1 -1
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/optimizer.pt +1 -1
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/rng_state.pth +1 -1
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/scheduler.pt +1 -1
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/trainer_state.json +0 -0
- meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/training_args.bin +1 -1
- meta-llama__meta-llama-3.1-8b/sft/run_manifest.json +8 -2
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/adapter_config.json
CHANGED
|
@@ -33,13 +33,13 @@
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"gate_proj",
|
| 39 |
"up_proj",
|
|
|
|
|
|
|
| 40 |
"o_proj",
|
| 41 |
-
"
|
| 42 |
-
"k_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
+
"q_proj",
|
| 37 |
+
"k_proj",
|
|
|
|
| 38 |
"up_proj",
|
| 39 |
+
"gate_proj",
|
| 40 |
+
"down_proj",
|
| 41 |
"o_proj",
|
| 42 |
+
"v_proj"
|
|
|
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63ed200008632a72ecf5f1c49f3162c8077f10e113e1cfe5e2c5172e9d8e49c1
|
| 3 |
size 83945296
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43127973
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21c5c2f3a786b5428eac85789f33e6b387c99842b1885678e132267001552d6b
|
| 3 |
size 43127973
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2df993afae23610a148cbb90d0d2fcfd8b5e755873f80c30cdbe027d950c3c
|
| 3 |
size 14645
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d506f17dab2155fb813d265a9159693ebe483f329035970ccda3f9613a1b7ae0
|
| 3 |
size 1465
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc6915d8d9dd9b5c9c17756c87ba7ec8221fd06789232d79225f9518167f0aa1
|
| 3 |
size 5841
|
meta-llama__meta-llama-3.1-8b/sft/run_manifest.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"best_metric_value": 0.051675114780664444,
|
| 10 |
"best_step": 2928,
|
| 11 |
"best_checkpoint_step": 2928,
|
| 12 |
-
"latest_checkpoint_step":
|
| 13 |
"checkpoints": [
|
| 14 |
{
|
| 15 |
"step": 366,
|
|
@@ -106,6 +106,12 @@
|
|
| 106 |
"epoch": 3.9945429740791267,
|
| 107 |
"repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5856",
|
| 108 |
"timestamp": "2026-04-09T22:26:47.857624+00:00"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
}
|
| 110 |
],
|
| 111 |
"epoch_artifacts": [
|
|
@@ -130,5 +136,5 @@
|
|
| 130 |
],
|
| 131 |
"resume_history": [],
|
| 132 |
"created_at": "2026-04-09T22:12:40.588264+00:00",
|
| 133 |
-
"updated_at": "2026-04-09T22:26:
|
| 134 |
}
|
|
|
|
| 9 |
"best_metric_value": 0.051675114780664444,
|
| 10 |
"best_step": 2928,
|
| 11 |
"best_checkpoint_step": 2928,
|
| 12 |
+
"latest_checkpoint_step": 5864,
|
| 13 |
"checkpoints": [
|
| 14 |
{
|
| 15 |
"step": 366,
|
|
|
|
| 106 |
"epoch": 3.9945429740791267,
|
| 107 |
"repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5856",
|
| 108 |
"timestamp": "2026-04-09T22:26:47.857624+00:00"
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"step": 5864,
|
| 112 |
+
"epoch": 4.0,
|
| 113 |
+
"repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864",
|
| 114 |
+
"timestamp": "2026-04-09T22:26:52.090907+00:00"
|
| 115 |
}
|
| 116 |
],
|
| 117 |
"epoch_artifacts": [
|
|
|
|
| 136 |
],
|
| 137 |
"resume_history": [],
|
| 138 |
"created_at": "2026-04-09T22:12:40.588264+00:00",
|
| 139 |
+
"updated_at": "2026-04-09T22:26:52.090921+00:00"
|
| 140 |
}
|