Hugging Face's logo

mnoukhov
/
pythia160m-rm-tldr6.9b

Text Classification
Transformers
Safetensors
gpt_neox
trl
reward-trainer
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
mnoukhov commited on
Commit
891c166
•
1 Parent(s): f31338d

Training in progress, step 291, checkpoint

Browse files
Files changed (8) hide show
  1. checkpoint-291/global_step291/mp_rank_00_model_states.pt +1 -1
  2. checkpoint-291/global_step291/zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
  3. checkpoint-291/global_step291/zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
  4. checkpoint-291/global_step291/zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
  5. checkpoint-291/global_step291/zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
  6. checkpoint-291/model.safetensors +1 -1
  7. checkpoint-291/trainer_state.json +9 -9
  8. checkpoint-291/training_args.bin +1 -1
checkpoint-291/global_step291/mp_rank_00_model_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:509415d631d96b192900146bca3664ebc5f03a27852fbfa7ac350456de8a7b48
3
  size 494804600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b5ad259e723c59faadde58a002cd95b700c8a4ab634759d0c0401636733caf
3
  size 494804600
checkpoint-291/global_step291/zero_pp_rank_0_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c614f8ac6bb75c0111d224cbfaa769cb43ef3b225e89025a9243669a7705e98
3
  size 371077364
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8361259c48bd029ec97d756b1e50571c16e05e257742902cc26a794115678a
3
  size 371077364
checkpoint-291/global_step291/zero_pp_rank_1_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c800e85b68bb8566fbdf30ff2e657de4046c6121464a9d37cecd9d6e640cf6b0
3
  size 371078516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e9361b31fff0ee95da6cfec3f17334538c8dbda3f4b99bdd3faed7dcb5ef924
3
  size 371078516
checkpoint-291/global_step291/zero_pp_rank_2_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d2816107f231ed5eca30915aea496c38e0344c83676d6bb482f76670a3e6269
3
  size 371078772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898a27eb69b63455293bf3d42fbd807a2c7393ae49dd819fc1c60487d7b7d315
3
  size 371078772
checkpoint-291/global_step291/zero_pp_rank_3_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f8d8e9fa4cad7c677e62f35f7465ed70f0c719285f8973a6076af2a10d4d47
3
  size 371078836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd09080b11905772abb55512ec95b1918e9a14062f7eb77bceae0f7f71606da9
3
  size 371078836
checkpoint-291/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16af75b79a10becfac1c3ad335d3eedea03732e306e8f8c0a0093b216aa8eb96
3
  size 494777904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa4453f98e7de2db74848c401bbcef86bd87a8ba0483f2441ee3f2804796adf
3
  size 494777904
checkpoint-291/trainer_state.json CHANGED
@@ -10,25 +10,25 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.06891798759476224,
13
- "grad_norm": 5.37721586227417,
14
  "learning_rate": 9.88326321974139e-06,
15
- "loss": 0.6331,
16
  "step": 100
17
  },
18
  {
19
  "epoch": 0.13783597518952448,
20
- "grad_norm": 6.225131988525391,
21
  "learning_rate": 9.53850386931162e-06,
22
- "loss": 0.5923,
23
  "step": 200
24
  },
25
  {
26
  "epoch": 0.2005513439007581,
27
- "eval_accuracy": 0.6812963891076586,
28
- "eval_loss": 0.5887773036956787,
29
- "eval_runtime": 460.7553,
30
- "eval_samples_per_second": 181.88,
31
- "eval_steps_per_second": 5.684,
32
  "step": 291
33
  }
34
  ],
 
10
  "log_history": [
11
  {
12
  "epoch": 0.06891798759476224,
13
+ "grad_norm": 15.229249000549316,
14
  "learning_rate": 9.88326321974139e-06,
15
+ "loss": 0.6365,
16
  "step": 100
17
  },
18
  {
19
  "epoch": 0.13783597518952448,
20
+ "grad_norm": 8.109599113464355,
21
  "learning_rate": 9.53850386931162e-06,
22
+ "loss": 0.596,
23
  "step": 200
24
  },
25
  {
26
  "epoch": 0.2005513439007581,
27
+ "eval_accuracy": 0.6923223789408367,
28
+ "eval_loss": 0.5818617343902588,
29
+ "eval_runtime": 432.05,
30
+ "eval_samples_per_second": 193.964,
31
+ "eval_steps_per_second": 6.062,
32
  "step": 291
33
  }
34
  ],
checkpoint-291/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:953101bb77678ea814f994cf635f3fd92e299c8c5fbc2a0ebf278fb8b37f60a6
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d3646b65f9d825ca595a0b332463330500f3d1a6c47d8c8bf3bdf7a3319feff
3
  size 6200