Hugging Face's logo

moos124
/
code-reasoning-0.5b

Transformers
Safetensors
Generated from Trainer
trl
hf_jobs
sft
Model card Files
xet
 Community
moos124 commited on
Commit
dbbbb2b
·
verified ·
1 Parent(s): 8c13cdb

Training in progress, step 4190, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +13 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2114c8dcd45ec33a775a5a4a697a58657507a16b2a8175b54c74eeec7acbde21
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec81f683bae58a32b9c850ec01311d3f9c0abf57df3e2d9dccd2795572234e9
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28ac86085fe63dc55718775aeefd05456a3af744a9347f5b65128becf2457502
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4d9cd4a73d43b418eceac48d993754a2bdcdab634418316974905214406720
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:976c1aa93153db4d76a2109bdb54936f079dcd39ed97e5f392f47382120bde9e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620e7ade3025e6d116d8700bd6a8b78e2dc8a33d4b594ced9949b90dddd04b51
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21ea95aee2e57549cdc344d0b62fe336b0c6bcde2640b7a55e4e0c10cbd7f52e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0272f897db42cd067c48d6c6f6c90f4f1b58ccaa291e797c7cb2869f975a0058
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.8917333333333334,
6
  "eval_steps": 500,
7
- "global_step": 4180,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4198,6 +4198,16 @@
4198
  "mean_token_accuracy": 0.780048543214798,
4199
  "num_tokens": 19476928.0,
4200
  "step": 4180
 
 
 
 
 
 
 
 
 
 
4201
  }
4202
  ],
4203
  "logging_steps": 10,
@@ -4217,7 +4227,7 @@
4217
  "attributes": {}
4218
  }
4219
  },
4220
- "total_flos": 9.215352160679424e+16,
4221
  "train_batch_size": 4,
4222
  "trial_name": null,
4223
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8938666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 4190,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4198
  "mean_token_accuracy": 0.780048543214798,
4199
  "num_tokens": 19476928.0,
4200
  "step": 4180
4201
+ },
4202
+ {
4203
+ "entropy": 0.9338957525789737,
4204
+ "epoch": 0.8938666666666667,
4205
+ "grad_norm": 0.3184056282043457,
4206
+ "learning_rate": 6.113809865554853e-05,
4207
+ "loss": 1.0237668991088866,
4208
+ "mean_token_accuracy": 0.7652892589569091,
4209
+ "num_tokens": 19522534.0,
4210
+ "step": 4190
4211
  }
4212
  ],
4213
  "logging_steps": 10,
 
4227
  "attributes": {}
4228
  }
4229
  },
4230
+ "total_flos": 9.23705904874967e+16,
4231
  "train_batch_size": 4,
4232
  "trial_name": null,
4233
  "trial_params": null