Hugging Face's logo

CesarChaMal
/
jvm_troubleshooting_dialogpt-large_full

Safetensors
gpt2
Model card Files
xet
 Community
CesarChaMal commited on
Commit
9ed4610
·
verified ·
1 Parent(s): e5858ad

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. checkpoint-25/model.safetensors +1 -1
  2. checkpoint-25/optimizer.pt +1 -1
  3. checkpoint-25/scheduler.pt +1 -1
  4. checkpoint-25/tokenizer.json +2 -16
  5. checkpoint-25/trainer_state.json +5 -12
  6. checkpoint-25/training_args.bin +1 -1
  7. model.safetensors +1 -1
  8. tokenizer.json +2 -16
  9. training_args.bin +1 -1
  10. training_log.json +7 -14
checkpoint-25/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a42f0dfd4f35726809bedde33d43533382f05320f51b34559ecd66a6ab4a95e
3
  size 3096165928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7f81ce579291f35875ee78d87e54977deb1632985cbffd19debfc87c16f319
3
  size 3096165928
checkpoint-25/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a019a20f8d1b33458efcd6e1f31b87ea5952b2ebfe815c5567bf655d0ab6514
3
  size 6192618087
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7094b0c32b0faa650ffcabfbe4735ee60882c6777682a46b78575578f97c45fd
3
  size 6192618087
checkpoint-25/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:455bb13072703b4695b8fce97607013bd45e6425447d095dda8121451f9cfe1d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f60de87fc4b9114f17c73a8e4d7386c49c9ed3c3573c42fb30bcaad96a4b33
3
  size 1465
checkpoint-25/tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 768,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 768
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 50256,
16
- "pad_type_id": 0,
17
- "pad_token": "<|endoftext|>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 50256,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 50256,
checkpoint-25/trainer_state.json CHANGED
@@ -9,26 +9,19 @@
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
- {
13
- "epoch": 0.4,
14
- "grad_norm": 19.882919311523438,
15
- "learning_rate": 8e-07,
16
- "loss": 8.5763,
17
- "step": 10
18
- },
19
  {
20
  "epoch": 0.8,
21
- "grad_norm": 10.610285758972168,
22
- "learning_rate": 3e-07,
23
- "loss": 8.2046,
24
  "step": 20
25
  }
26
  ],
27
- "logging_steps": 10,
28
  "max_steps": 25,
29
  "num_input_tokens_seen": 0,
30
  "num_train_epochs": 1,
31
- "save_steps": 50,
32
  "stateful_callbacks": {
33
  "TrainerControl": {
34
  "args": {
 
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
 
 
 
 
 
 
 
12
  {
13
  "epoch": 0.8,
14
+ "grad_norm": 11.499434471130371,
15
+ "learning_rate": 2.608695652173913e-09,
16
+ "loss": 8.5489,
17
  "step": 20
18
  }
19
  ],
20
+ "logging_steps": 20,
21
  "max_steps": 25,
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
+ "save_steps": 100,
25
  "stateful_callbacks": {
26
  "TrainerControl": {
27
  "args": {
checkpoint-25/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a0e5595bc52473e018b00453670eb5d577d810e5ddec260ef9e96ae80799b79
3
  size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8764a662c742fe562180326e706ddcaa952662d13772979a9bd2edb6a466fb8d
3
  size 5841
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a42f0dfd4f35726809bedde33d43533382f05320f51b34559ecd66a6ab4a95e
3
  size 3096165928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7f81ce579291f35875ee78d87e54977deb1632985cbffd19debfc87c16f319
3
  size 3096165928
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 768,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 768
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 50256,
16
- "pad_type_id": 0,
17
- "pad_token": "<|endoftext|>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 50256,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 50256,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a0e5595bc52473e018b00453670eb5d577d810e5ddec260ef9e96ae80799b79
3
  size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8764a662c742fe562180326e706ddcaa952662d13772979a9bd2edb6a466fb8d
3
  size 5841
training_log.json CHANGED
@@ -1,24 +1,17 @@
1
  [
2
  {
3
- "loss": 8.5763,
4
- "grad_norm": 19.882919311523438,
5
- "learning_rate": 8e-07,
6
- "epoch": 0.4,
7
- "step": 10
8
- },
9
- {
10
- "loss": 8.2046,
11
- "grad_norm": 10.610285758972168,
12
- "learning_rate": 3e-07,
13
  "epoch": 0.8,
14
  "step": 20
15
  },
16
  {
17
- "train_runtime": 619.8465,
18
- "train_samples_per_second": 0.161,
19
- "train_steps_per_second": 0.04,
20
  "total_flos": 326426296320000.0,
21
- "train_loss": 8.485690612792968,
22
  "epoch": 1.0,
23
  "step": 25
24
  }
 
1
  [
2
  {
3
+ "loss": 8.5489,
4
+ "grad_norm": 11.499434471130371,
5
+ "learning_rate": 2.608695652173913e-09,
 
 
 
 
 
 
 
6
  "epoch": 0.8,
7
  "step": 20
8
  },
9
  {
10
+ "train_runtime": 648.8694,
11
+ "train_samples_per_second": 0.154,
12
+ "train_steps_per_second": 0.039,
13
  "total_flos": 326426296320000.0,
14
+ "train_loss": 8.712354888916016,
15
  "epoch": 1.0,
16
  "step": 25
17
  }