Hugging Face's logo

owl-agent
/
gaia_qwen2_7B

Text Generation
Transformers
Safetensors
qwen2
llama-factory
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
yuzhounie commited on
Commit
5ac7adc
·
verified ·
1 Parent(s): 58dd497

Training in progress, step 6

Browse files
Files changed (9) hide show
  1. all_results.json +8 -0
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. train_results.json +8 -0
  7. trainer_log.jsonl +4 -0
  8. trainer_state.json +63 -0
  9. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 247280173056.0,
4
+ "train_loss": 0.6713302036126455,
5
+ "train_runtime": 144.6833,
6
+ "train_samples_per_second": 0.083,
7
+ "train_steps_per_second": 0.021
8
+ }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:180f7e7c4491b24d1a8a415fda7da061c052a85a6af1850cebf4ffcdbca0fad8
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc19435d964ece00dc5ecddecc6e9659ddeb5d628400682a47b36750f1c82a3
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cafaa206a66393a43fe3ffaccb4f04bdac272195255d4738bab5723f2d7ea551
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81da1fa8c36103e482a541ff95c4e867538c24e46bba3e99a34a3dfdf58ea61
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:665df71fd3aa45c78e72c6f03b5fa1482f476dc0171979caa81cc696cb9ee37b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4a494933112df9c624f87d536954a3280178756e5122dcbf85e65796277728
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ba542d4cb3b649d09a7da1d4ed42124b3cb9463ee1e541eec1046789004143f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e23c7a39bc2fabfa11b06e0899ff21ded71385791371dd14ced0766c8d96d6
3
  size 1089994880
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 247280173056.0,
4
+ "train_loss": 0.6713302036126455,
5
+ "train_runtime": 144.6833,
6
+ "train_samples_per_second": 0.083,
7
+ "train_steps_per_second": 0.021
8
+ }
trainer_log.jsonl CHANGED
@@ -2,3 +2,7 @@
2
  {"current_steps": 2, "total_steps": 3, "loss": 0.7883, "lr": 1e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:00:55", "remaining_time": "0:00:27"}
3
  {"current_steps": 3, "total_steps": 3, "loss": 0.4374, "lr": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:01:22", "remaining_time": "0:00:00"}
4
  {"current_steps": 3, "total_steps": 3, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:02:23", "remaining_time": "0:00:00"}
 
 
 
 
 
2
  {"current_steps": 2, "total_steps": 3, "loss": 0.7883, "lr": 1e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:00:55", "remaining_time": "0:00:27"}
3
  {"current_steps": 3, "total_steps": 3, "loss": 0.4374, "lr": 5e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:01:22", "remaining_time": "0:00:00"}
4
  {"current_steps": 3, "total_steps": 3, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:02:23", "remaining_time": "0:00:00"}
5
+ {"current_steps": 4, "total_steps": 6, "loss": 0.4374, "lr": 0.0, "epoch": 4.0, "percentage": 66.67, "elapsed_time": "0:00:29", "remaining_time": "0:00:14"}
6
+ {"current_steps": 5, "total_steps": 6, "loss": 0.4374, "lr": 3.4549150281252635e-06, "epoch": 5.0, "percentage": 83.33, "elapsed_time": "0:00:56", "remaining_time": "0:00:11"}
7
+ {"current_steps": 6, "total_steps": 6, "loss": 0.3766, "lr": 9.549150281252633e-07, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "0:01:20", "remaining_time": "0:00:00"}
8
+ {"current_steps": 6, "total_steps": 6, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "0:02:45", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "learning_rate": 0.0,
15
+ "loss": 0.7883,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 2.0,
20
+ "grad_norm": 24.690817322034423,
21
+ "learning_rate": 1e-05,
22
+ "loss": 0.7883,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 3.0,
27
+ "grad_norm": 24.690817322034423,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.4374,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 3.0,
34
+ "step": 3,
35
+ "total_flos": 247280173056.0,
36
+ "train_loss": 0.6713302036126455,
37
+ "train_runtime": 144.6833,
38
+ "train_samples_per_second": 0.083,
39
+ "train_steps_per_second": 0.021
40
+ }
41
+ ],
42
+ "logging_steps": 1,
43
+ "max_steps": 3,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 20,
47
+ "stateful_callbacks": {
48
+ "TrainerControl": {
49
+ "args": {
50
+ "should_epoch_stop": false,
51
+ "should_evaluate": false,
52
+ "should_log": false,
53
+ "should_save": true,
54
+ "should_training_stop": true
55
+ },
56
+ "attributes": {}
57
+ }
58
+ },
59
+ "total_flos": 247280173056.0,
60
+ "train_batch_size": 1,
61
+ "trial_name": null,
62
+ "trial_params": null
63
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d591d2aa4195669d37dacb8b8f12633557e9b648cde625fc3583b530205fb8c
3
  size 7608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b8c9e2a763a087603937d1ab764f1900fe3afa1cd3155f36f65d2dd76037bb
3
  size 7608