Hugging Face's logo

appvoid
/
picollama

TensorBoard
Safetensors
English
llama
Model card Files
xet
 Metrics Community
1
appvoid commited on
Commit
be0411c
·
verified ·
1 Parent(s): 0af6fe1

Deep35 continual checkpoint step 100000

Browse files
Files changed (7) hide show
  1. last-checkpoint/continual_state.json +8 -8
  2. last-checkpoint/data_state.pt +2 -2
  3. last-checkpoint/model.safetensors +1 -1
  4. last-checkpoint/optimizer.pt +1 -1
  5. last-checkpoint/rng_state.pth +1 -1
  6. last-checkpoint/scheduler.pt +1 -1
  7. last-checkpoint/trainer_state.json +0 -0
last-checkpoint/continual_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "global_step": 98000,
3
- "sequence_tokens_emitted": 18350325760,
4
  "mix": [
5
  0.8,
6
  0.09,
@@ -32,14 +32,14 @@
32
  "noprompt_format": "stored text field exactly; empty rows skipped",
33
  "curated_sampling": "shuffled exhaustive cycles without replacement",
34
  "curated_progress": {
35
- "rewrite_epoch": 0,
36
- "rewrite_cursor": 194813,
37
  "rewrite_total": 205404,
38
- "rewrite_fraction": 0.9484381998403147,
39
  "noprompt_epoch": 0,
40
- "noprompt_cursor": 38627,
41
  "noprompt_total": 75000,
42
- "noprompt_fraction": 0.5150266666666666
43
  },
44
  "batch_history": [
45
  {
@@ -67,5 +67,5 @@
67
  "current_batch_size": 240,
68
  "current_gradient_accumulation": 1,
69
  "current_tokens_per_update": 245760,
70
- "cumulative_tokens_at_save": 18350080000
71
  }
 
1
  {
2
+ "global_step": 100000,
3
+ "sequence_tokens_emitted": 18841845760,
4
  "mix": [
5
  0.8,
6
  0.09,
 
32
  "noprompt_format": "stored text field exactly; empty rows skipped",
33
  "curated_sampling": "shuffled exhaustive cycles without replacement",
34
  "curated_progress": {
35
+ "rewrite_epoch": 1,
36
+ "rewrite_cursor": 13649,
37
  "rewrite_total": 205404,
38
+ "rewrite_fraction": 0.06644953360207201,
39
  "noprompt_epoch": 0,
40
+ "noprompt_cursor": 43411,
41
  "noprompt_total": 75000,
42
+ "noprompt_fraction": 0.5788133333333333
43
  },
44
  "batch_history": [
45
  {
 
67
  "current_batch_size": 240,
68
  "current_gradient_accumulation": 1,
69
  "current_tokens_per_update": 245760,
70
+ "cumulative_tokens_at_save": 18841600000
71
  }
last-checkpoint/data_state.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c642a475a1c84c49818af14f42a32daeee92339e6a34176079c61a758df0cbb
3
- size 1159807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fa493e430806456206471dec99a63c9c8e82893dd3bd164c1bd49a25d62214
3
+ size 1170559
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9895faebfdb295ed71d852bc49ee4f3fdfe2ce6dcddfc423758ee0f799d245f
3
  size 70326256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febd1e4bfb5bb5ab1bb68d15b6d9cb87cfe62948cd98e4f36906d5e7dc5509a1
3
  size 70326256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:905a2154d42987fdfaf2ef71d1a926da5228a9897144c54ad5633d545c6f6686
3
  size 140740171
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09554129eab71b22281f47e6e3208d9f6b3324a9a9ded3fc479988d3a0fb6463
3
  size 140740171
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49b6b5f1fe0e3c9d8fdc0c4067e4ee9f308f138a93c8e033504404c0483a43ab
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be0d282d6351ae570e2dcc2232bf91c2dbcad80ed7fb991fd9a34644e2fb502
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c3e24eeb8f42de73a98be24b2ce0201e7db62cc42fc0a6f02c92f53164849b7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d544a79bca3ecf5df1d59886369c58e9072117ae18e871662cc3c2fceebc81
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff