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
85e30ec
·
verified ·
1 Parent(s): 195947e

Training in progress, step 2610, 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:d8e7cadebbae1d54eaf66ccc7b9f5c9ff4dd4bf44b4d8a1f8b8a0084844d5797
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8687c9499c8dfa4261b0eebcd4d4d6977344d6025ebb881e9d485193f3090c9b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad5f8e1609877fa0eb8aa18abf22e51f9d92e64d503e8b3d45179c00ded279ac
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bcf2fa7bc23621db9dbb2c18b0bd7c532f2860d632202ce5a20bd39fe79c89
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d5e082edfc1c825c97152696481c3dec5a3c519176259229a60653e2b9ec26f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5907384589dae04315beaebce35821e4a256f922bf500c935f9571f4eba436e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4376ea4c2891899450d26351d7f334694fcd1845e06b10d3542406ce1aa6a830
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be40234ff8e6330cc9e39f66e1c311009b73515e48fbe9cb20c1bea05dae9f87
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": 0.5546666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2600,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2618,6 +2618,16 @@
2618
  "mean_token_accuracy": 0.7560776218771934,
2619
  "num_tokens": 12082379.0,
2620
  "step": 2600
 
 
 
 
 
 
 
 
 
 
2621
  }
2622
  ],
2623
  "logging_steps": 10,
@@ -2637,7 +2647,7 @@
2637
  "attributes": {}
2638
  }
2639
  },
2640
- "total_flos": 5.727758984615424e+16,
2641
  "train_batch_size": 4,
2642
  "trial_name": null,
2643
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5568,
6
  "eval_steps": 500,
7
+ "global_step": 2610,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2618
  "mean_token_accuracy": 0.7560776218771934,
2619
  "num_tokens": 12082379.0,
2620
  "step": 2600
2621
+ },
2622
+ {
2623
+ "entropy": 0.904555281996727,
2624
+ "epoch": 0.5568,
2625
+ "grad_norm": 0.2646128535270691,
2626
+ "learning_rate": 8.486244594122297e-05,
2627
+ "loss": 1.0139558792114258,
2628
+ "mean_token_accuracy": 0.7750694006681442,
2629
+ "num_tokens": 12125503.0,
2630
+ "step": 2610
2631
  }
2632
  ],
2633
  "logging_steps": 10,
 
2647
  "attributes": {}
2648
  }
2649
  },
2650
+ "total_flos": 5.746905600795955e+16,
2651
  "train_batch_size": 4,
2652
  "trial_name": null,
2653
  "trial_params": null