Hugging Face's logo

DeepDream2045
/
472f800b-4cef-46e8-98bb-9034a1edc4c6

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files
xet
 Community
DeepDream2045 commited on
Commit
4f21fe9
·
verified ·
1 Parent(s): dcc5556

Training in progress, step 9, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_config.json +3 -3
  2. last-checkpoint/adapter_model.safetensors +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/trainer_state.json +11 -11
  5. last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "up_proj",
24
- "gate_proj",
25
  "v_proj",
 
26
  "k_proj",
27
- "q_proj",
28
  "down_proj",
 
29
  "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "v_proj",
24
+ "gate_proj",
25
  "k_proj",
26
+ "up_proj",
27
  "down_proj",
28
+ "q_proj",
29
  "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3293a8a1eb1d98f95ae6a8e8eb8951ff87094792bb9a7203c4c68eb0e1b7fa27
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8c3f21ac0274f31126ab156bf1bf105e6f1a3ebf53cbf8431e0ff2f37014ba
3
  size 73911112
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:200e6fcd481c16b4f3d1cbb24a0867b14067141b424637d8e0b176938ed6cbb2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f0ea8cc29e523749f6c9f11b383e5e13088a31f18b3e1fc21280d12b0a49f6
3
  size 14244
last-checkpoint/trainer_state.json CHANGED
@@ -18,9 +18,9 @@
18
  {
19
  "epoch": 0.00016649323621227888,
20
  "eval_loss": NaN,
21
- "eval_runtime": 541.5183,
22
- "eval_samples_per_second": 4.67,
23
- "eval_steps_per_second": 2.336,
24
  "step": 1
25
  },
26
  {
@@ -40,9 +40,9 @@
40
  {
41
  "epoch": 0.0004994797086368366,
42
  "eval_loss": NaN,
43
- "eval_runtime": 540.5845,
44
- "eval_samples_per_second": 4.678,
45
- "eval_steps_per_second": 2.34,
46
  "step": 3
47
  },
48
  {
@@ -69,9 +69,9 @@
69
  {
70
  "epoch": 0.0009989594172736733,
71
  "eval_loss": NaN,
72
- "eval_runtime": 540.514,
73
- "eval_samples_per_second": 4.679,
74
- "eval_steps_per_second": 2.34,
75
  "step": 6
76
  },
77
  {
@@ -98,9 +98,9 @@
98
  {
99
  "epoch": 0.00149843912591051,
100
  "eval_loss": NaN,
101
- "eval_runtime": 540.6919,
102
  "eval_samples_per_second": 4.677,
103
- "eval_steps_per_second": 2.34,
104
  "step": 9
105
  }
106
  ],
 
18
  {
19
  "epoch": 0.00016649323621227888,
20
  "eval_loss": NaN,
21
+ "eval_runtime": 543.5334,
22
+ "eval_samples_per_second": 4.653,
23
+ "eval_steps_per_second": 2.327,
24
  "step": 1
25
  },
26
  {
 
40
  {
41
  "epoch": 0.0004994797086368366,
42
  "eval_loss": NaN,
43
+ "eval_runtime": 540.7666,
44
+ "eval_samples_per_second": 4.677,
45
+ "eval_steps_per_second": 2.339,
46
  "step": 3
47
  },
48
  {
 
69
  {
70
  "epoch": 0.0009989594172736733,
71
  "eval_loss": NaN,
72
+ "eval_runtime": 541.4238,
73
+ "eval_samples_per_second": 4.671,
74
+ "eval_steps_per_second": 2.336,
75
  "step": 6
76
  },
77
  {
 
98
  {
99
  "epoch": 0.00149843912591051,
100
  "eval_loss": NaN,
101
+ "eval_runtime": 540.7763,
102
  "eval_samples_per_second": 4.677,
103
+ "eval_steps_per_second": 2.339,
104
  "step": 9
105
  }
106
  ],
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edd5c8003dc212a5d55ed2476be46f188433095a148c73d1f0610fae7d6df834
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a25691fb6a6b3d2d3ebf285b08a1fc54e133279caff6a277ec551d3b09b830
3
  size 6776