Shresthadev403 commited on
Commit
1e865d2
1 Parent(s): 7718c01

End of training

Browse files
README.md CHANGED
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - eval_loss: 0.9228
17
- - eval_runtime: 1365.4307
18
- - eval_samples_per_second: 109.855
19
- - eval_steps_per_second: 1.717
20
- - epoch: 8.3
21
- - step: 350000
22
 
23
  ## Model description
24
 
 
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - eval_loss: 0.9181
17
+ - eval_runtime: 1373.3191
18
+ - eval_samples_per_second: 109.224
19
+ - eval_steps_per_second: 1.707
20
+ - epoch: 9.48
21
+ - step: 400000
22
 
23
  ## Model description
24
 
logs/events.out.tfevents.1708010990.ecce5c21fb5d.27.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc65cb7013b8f2509e3def68792a819e824f8fd3fa9e417ec5982b1afb8a503f
3
+ size 5154
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80c5d2288f11afad155ea8e263f6ab3a3f407be9730db3d7af7b8c2689bf5355
3
  size 497918592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380c6d61973d72a6f2fb8506f90319b6fc18085e94ed9f13614758ca5090a91a
3
  size 497918592
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 8.296197970987011,
5
  "eval_steps": 50000,
6
- "global_step": 350000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -105,6 +105,20 @@
105
  "eval_samples_per_second": 109.855,
106
  "eval_steps_per_second": 1.717,
107
  "step": 350000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108
  }
109
  ],
110
  "logging_steps": 50000,
@@ -112,7 +126,7 @@
112
  "num_input_tokens_seen": 0,
113
  "num_train_epochs": 100,
114
  "save_steps": 50000,
115
- "total_flos": 7.31609328254976e+17,
116
  "train_batch_size": 32,
117
  "trial_name": null,
118
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 9.48136910969944,
5
  "eval_steps": 50000,
6
+ "global_step": 400000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
105
  "eval_samples_per_second": 109.855,
106
  "eval_steps_per_second": 1.717,
107
  "step": 350000
108
+ },
109
+ {
110
+ "epoch": 9.48,
111
+ "learning_rate": 4.940766331658292e-05,
112
+ "loss": 0.9026,
113
+ "step": 400000
114
+ },
115
+ {
116
+ "epoch": 9.48,
117
+ "eval_loss": 0.9180548787117004,
118
+ "eval_runtime": 1373.3191,
119
+ "eval_samples_per_second": 109.224,
120
+ "eval_steps_per_second": 1.707,
121
+ "step": 400000
122
  }
123
  ],
124
  "logging_steps": 50000,
 
126
  "num_input_tokens_seen": 0,
127
  "num_train_epochs": 100,
128
  "save_steps": 50000,
129
+ "total_flos": 8.36125095886848e+17,
130
  "train_batch_size": 32,
131
  "trial_name": null,
132
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e11847e74c240616571649a97da406725778726648f4a5d5ba652545c0ac20df
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb10217ea6ee5a53faf925ba15fc624a98562d0ed446408452fcac3eb4a1b18e
3
  size 4728