player1537
commited on
Commit
•
0321540
1
Parent(s):
daa3535
Training in progress, step 1296
Browse files- .gitignore +1 -0
- config.json +32 -0
- last-checkpoint/config.json +32 -0
- last-checkpoint/generation_config.json +7 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +46 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +3 -0
- runs/Jul31_14-31-05_60cc17a3584f/events.out.tfevents.1690813872.60cc17a3584f.14319.0 +3 -0
- runs/Jul31_14-47-02_60cc17a3584f/events.out.tfevents.1690814825.60cc17a3584f.14319.1 +3 -0
- runs/Jul31_14-51-47_60cc17a3584f/events.out.tfevents.1690815110.60cc17a3584f.14319.2 +3 -0
- runs/Jul31_14-52-29_60cc17a3584f/events.out.tfevents.1690815152.60cc17a3584f.14319.3 +3 -0
- runs/Jul31_14-54-30_60cc17a3584f/events.out.tfevents.1690815276.60cc17a3584f.21618.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigscience/bloom-560m",
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"BloomForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attention_softmax_in_fp32": true,
|
9 |
+
"bias_dropout_fusion": true,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_head": 16,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 24,
|
21 |
+
"offset_alibi": 100,
|
22 |
+
"pad_token_id": 3,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"skip_bias_add": true,
|
25 |
+
"skip_bias_add_qkv": false,
|
26 |
+
"slow_but_exact": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.31.0",
|
29 |
+
"unk_token_id": 0,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250880
|
32 |
+
}
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigscience/bloom-560m",
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"BloomForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attention_softmax_in_fp32": true,
|
9 |
+
"bias_dropout_fusion": true,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"masked_softmax_fusion": true,
|
17 |
+
"model_type": "bloom",
|
18 |
+
"n_head": 16,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 24,
|
21 |
+
"offset_alibi": 100,
|
22 |
+
"pad_token_id": 3,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"skip_bias_add": true,
|
25 |
+
"skip_bias_add_qkv": false,
|
26 |
+
"slow_but_exact": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.31.0",
|
29 |
+
"unk_token_id": 0,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250880
|
32 |
+
}
|
last-checkpoint/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.31.0"
|
7 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c97c840cca9ac13dade2202193097cd582d89d73f16a91c3b4f14337b08ff87b
|
3 |
+
size 4473888693
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2d15bf842dd61f2706406afb1791ed79d8298c609662533a0dfc0a7bfcdb73f
|
3 |
+
size 2236957537
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ded89762a34ef5dcbb84dbca700867360f046a698f69ae6aeb45750ee925335
|
3 |
+
size 14639
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a9f74c6b5373c9d8b98d5263727ff33e3cf54b89bb8b0d0a28e39d4f06324b
|
3 |
+
size 627
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1499652858134691,
|
5 |
+
"global_step": 1296,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.9997685720897943e-05,
|
13 |
+
"loss": 2.316,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 1.9259430687340893e-05,
|
19 |
+
"loss": 2.541,
|
20 |
+
"step": 324
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.07,
|
24 |
+
"learning_rate": 1.850960425827355e-05,
|
25 |
+
"loss": 2.3336,
|
26 |
+
"step": 648
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.11,
|
30 |
+
"learning_rate": 1.7759777829206203e-05,
|
31 |
+
"loss": 2.1896,
|
32 |
+
"step": 972
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.15,
|
36 |
+
"learning_rate": 1.7009951400138856e-05,
|
37 |
+
"loss": 2.2036,
|
38 |
+
"step": 1296
|
39 |
+
}
|
40 |
+
],
|
41 |
+
"max_steps": 8642,
|
42 |
+
"num_train_epochs": 1,
|
43 |
+
"total_flos": 2407208507670528.0,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": null
|
46 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6abac40c8f028827e053ae9056ed066c907b0157c0b9b6ab3bbe46623f64631b
|
3 |
+
size 4027
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2d15bf842dd61f2706406afb1791ed79d8298c609662533a0dfc0a7bfcdb73f
|
3 |
+
size 2236957537
|
runs/Jul31_14-31-05_60cc17a3584f/events.out.tfevents.1690813872.60cc17a3584f.14319.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:622e9a7d2e11b1d0b7196f9fbc317aa05d44cef54aadddff455be045b8b54fe3
|
3 |
+
size 4205
|
runs/Jul31_14-47-02_60cc17a3584f/events.out.tfevents.1690814825.60cc17a3584f.14319.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2402cb8a2855576e511b23db9978e56448e963c1f8cca46c645206281c311e0f
|
3 |
+
size 4205
|
runs/Jul31_14-51-47_60cc17a3584f/events.out.tfevents.1690815110.60cc17a3584f.14319.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5acf7513e6bc73ab122afa06d1aebde92e8506595d965b32f78c71954998afc3
|
3 |
+
size 4184
|
runs/Jul31_14-52-29_60cc17a3584f/events.out.tfevents.1690815152.60cc17a3584f.14319.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f914ed4470c9c3729afe559a9c34dcf1f666c0d7626344a2c7718a0b9ba5d6f
|
3 |
+
size 4359
|
runs/Jul31_14-54-30_60cc17a3584f/events.out.tfevents.1690815276.60cc17a3584f.21618.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06768c1c96b0235da1664af9a3ba8f786b2a08e964a35985934718eb9161d482
|
3 |
+
size 4987
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6abac40c8f028827e053ae9056ed066c907b0157c0b9b6ab3bbe46623f64631b
|
3 |
+
size 4027
|