End of training
Browse files- README.md +2 -1
- all_results.json +16 -0
- train_results.json +16 -0
- trainer_state.json +674 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen3-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: code_contests-Qwen3-Coder-480B-traces
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# code_contests-Qwen3-Coder-480B-traces
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen3-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: code_contests-Qwen3-Coder-480B-traces
|
|
|
|
| 16 |
|
| 17 |
# code_contests-Qwen3-Coder-480B-traces
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/code_contests-Qwen3-Coder-480B-traces dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"achieved_tflops_per_gpu": 4.949651343267627,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 243.92912852326808,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.2248307466506958,
|
| 7 |
+
"mfu_percent": 0.3497986815030125,
|
| 8 |
+
"mfu_percent_theoretical": 17.23880766948891,
|
| 9 |
+
"total_flos": 3.151185311610962e+17,
|
| 10 |
+
"train_loss": 0.24082276695653013,
|
| 11 |
+
"train_runtime": 3979.0496,
|
| 12 |
+
"train_samples_per_second": 4.505,
|
| 13 |
+
"train_steps_per_second": 0.072,
|
| 14 |
+
"valid_targets_mean": 2971.6,
|
| 15 |
+
"valid_targets_min": 1283
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"achieved_tflops_per_gpu": 4.949651343267627,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 243.92912852326808,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.2248307466506958,
|
| 7 |
+
"mfu_percent": 0.3497986815030125,
|
| 8 |
+
"mfu_percent_theoretical": 17.23880766948891,
|
| 9 |
+
"total_flos": 3.151185311610962e+17,
|
| 10 |
+
"train_loss": 0.24082276695653013,
|
| 11 |
+
"train_runtime": 3979.0496,
|
| 12 |
+
"train_samples_per_second": 4.505,
|
| 13 |
+
"train_steps_per_second": 0.072,
|
| 14 |
+
"valid_targets_mean": 2971.6,
|
| 15 |
+
"valid_targets_min": 1283
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,674 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 285,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.08888888888888889,
|
| 14 |
+
"grad_norm": 7.583328114734628,
|
| 15 |
+
"learning_rate": 5.517241379310345e-06,
|
| 16 |
+
"loss": 0.5653,
|
| 17 |
+
"loss_nan_ranks": 0,
|
| 18 |
+
"loss_rank_avg": 0.166676864027977,
|
| 19 |
+
"step": 5,
|
| 20 |
+
"valid_targets_mean": 3166.7,
|
| 21 |
+
"valid_targets_min": 1420
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.17777777777777778,
|
| 25 |
+
"grad_norm": 3.1401618568879677,
|
| 26 |
+
"learning_rate": 1.2413793103448277e-05,
|
| 27 |
+
"loss": 0.4991,
|
| 28 |
+
"loss_nan_ranks": 0,
|
| 29 |
+
"loss_rank_avg": 0.1019982397556305,
|
| 30 |
+
"step": 10,
|
| 31 |
+
"valid_targets_mean": 2351.6,
|
| 32 |
+
"valid_targets_min": 1195
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.26666666666666666,
|
| 36 |
+
"grad_norm": 1.104245248825641,
|
| 37 |
+
"learning_rate": 1.931034482758621e-05,
|
| 38 |
+
"loss": 0.4163,
|
| 39 |
+
"loss_nan_ranks": 0,
|
| 40 |
+
"loss_rank_avg": 0.11541903018951416,
|
| 41 |
+
"step": 15,
|
| 42 |
+
"valid_targets_mean": 3168.0,
|
| 43 |
+
"valid_targets_min": 1312
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.35555555555555557,
|
| 47 |
+
"grad_norm": 0.732712115494436,
|
| 48 |
+
"learning_rate": 2.620689655172414e-05,
|
| 49 |
+
"loss": 0.3658,
|
| 50 |
+
"loss_nan_ranks": 0,
|
| 51 |
+
"loss_rank_avg": 0.12487722188234329,
|
| 52 |
+
"step": 20,
|
| 53 |
+
"valid_targets_mean": 3523.8,
|
| 54 |
+
"valid_targets_min": 1517
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.4444444444444444,
|
| 58 |
+
"grad_norm": 0.5506644308788069,
|
| 59 |
+
"learning_rate": 3.310344827586207e-05,
|
| 60 |
+
"loss": 0.3378,
|
| 61 |
+
"loss_nan_ranks": 0,
|
| 62 |
+
"loss_rank_avg": 0.08351944386959076,
|
| 63 |
+
"step": 25,
|
| 64 |
+
"valid_targets_mean": 3054.6,
|
| 65 |
+
"valid_targets_min": 1110
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5333333333333333,
|
| 69 |
+
"grad_norm": 0.5212168935643539,
|
| 70 |
+
"learning_rate": 4e-05,
|
| 71 |
+
"loss": 0.3227,
|
| 72 |
+
"loss_nan_ranks": 0,
|
| 73 |
+
"loss_rank_avg": 0.08309619128704071,
|
| 74 |
+
"step": 30,
|
| 75 |
+
"valid_targets_mean": 2739.4,
|
| 76 |
+
"valid_targets_min": 1178
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.6222222222222222,
|
| 80 |
+
"grad_norm": 0.37621279442640654,
|
| 81 |
+
"learning_rate": 3.996236225800298e-05,
|
| 82 |
+
"loss": 0.2841,
|
| 83 |
+
"loss_nan_ranks": 0,
|
| 84 |
+
"loss_rank_avg": 0.058637700974941254,
|
| 85 |
+
"step": 35,
|
| 86 |
+
"valid_targets_mean": 3032.6,
|
| 87 |
+
"valid_targets_min": 962
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.7111111111111111,
|
| 91 |
+
"grad_norm": 0.3740113710680447,
|
| 92 |
+
"learning_rate": 3.9849590691974206e-05,
|
| 93 |
+
"loss": 0.275,
|
| 94 |
+
"loss_nan_ranks": 0,
|
| 95 |
+
"loss_rank_avg": 0.049976594746112823,
|
| 96 |
+
"step": 40,
|
| 97 |
+
"valid_targets_mean": 2221.6,
|
| 98 |
+
"valid_targets_min": 1249
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.8,
|
| 102 |
+
"grad_norm": 0.3555541947187885,
|
| 103 |
+
"learning_rate": 3.966210974862433e-05,
|
| 104 |
+
"loss": 0.2829,
|
| 105 |
+
"loss_nan_ranks": 0,
|
| 106 |
+
"loss_rank_avg": 0.047423090785741806,
|
| 107 |
+
"step": 45,
|
| 108 |
+
"valid_targets_mean": 2186.9,
|
| 109 |
+
"valid_targets_min": 1183
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.8888888888888888,
|
| 113 |
+
"grad_norm": 0.3614830806096002,
|
| 114 |
+
"learning_rate": 3.940062506389089e-05,
|
| 115 |
+
"loss": 0.2688,
|
| 116 |
+
"loss_nan_ranks": 0,
|
| 117 |
+
"loss_rank_avg": 0.07531788945198059,
|
| 118 |
+
"step": 50,
|
| 119 |
+
"valid_targets_mean": 2673.9,
|
| 120 |
+
"valid_targets_min": 1141
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.9777777777777777,
|
| 124 |
+
"grad_norm": 0.35164636779651554,
|
| 125 |
+
"learning_rate": 3.9066120807083875e-05,
|
| 126 |
+
"loss": 0.2583,
|
| 127 |
+
"loss_nan_ranks": 0,
|
| 128 |
+
"loss_rank_avg": 0.0835060328245163,
|
| 129 |
+
"step": 55,
|
| 130 |
+
"valid_targets_mean": 3016.2,
|
| 131 |
+
"valid_targets_min": 1526
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.0533333333333332,
|
| 135 |
+
"grad_norm": 0.4004740105789504,
|
| 136 |
+
"learning_rate": 3.865985597669478e-05,
|
| 137 |
+
"loss": 0.2609,
|
| 138 |
+
"loss_nan_ranks": 0,
|
| 139 |
+
"loss_rank_avg": 0.05621650442481041,
|
| 140 |
+
"step": 60,
|
| 141 |
+
"valid_targets_mean": 2221.8,
|
| 142 |
+
"valid_targets_min": 1151
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.1422222222222222,
|
| 146 |
+
"grad_norm": 0.3362478514134072,
|
| 147 |
+
"learning_rate": 3.818335966181045e-05,
|
| 148 |
+
"loss": 0.2418,
|
| 149 |
+
"loss_nan_ranks": 0,
|
| 150 |
+
"loss_rank_avg": 0.06041599065065384,
|
| 151 |
+
"step": 65,
|
| 152 |
+
"valid_targets_mean": 2575.6,
|
| 153 |
+
"valid_targets_min": 1126
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.231111111111111,
|
| 157 |
+
"grad_norm": 0.327805935004158,
|
| 158 |
+
"learning_rate": 3.76384252869671e-05,
|
| 159 |
+
"loss": 0.2527,
|
| 160 |
+
"loss_nan_ranks": 0,
|
| 161 |
+
"loss_rank_avg": 0.05153035372495651,
|
| 162 |
+
"step": 70,
|
| 163 |
+
"valid_targets_mean": 2401.1,
|
| 164 |
+
"valid_targets_min": 1291
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.32,
|
| 168 |
+
"grad_norm": 0.3344211876841236,
|
| 169 |
+
"learning_rate": 3.702710386210531e-05,
|
| 170 |
+
"loss": 0.2363,
|
| 171 |
+
"loss_nan_ranks": 0,
|
| 172 |
+
"loss_rank_avg": 0.0525384359061718,
|
| 173 |
+
"step": 75,
|
| 174 |
+
"valid_targets_mean": 2742.1,
|
| 175 |
+
"valid_targets_min": 1147
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.4088888888888889,
|
| 179 |
+
"grad_norm": 0.3391981121560211,
|
| 180 |
+
"learning_rate": 3.635169626303168e-05,
|
| 181 |
+
"loss": 0.238,
|
| 182 |
+
"loss_nan_ranks": 0,
|
| 183 |
+
"loss_rank_avg": 0.06917819380760193,
|
| 184 |
+
"step": 80,
|
| 185 |
+
"valid_targets_mean": 3123.1,
|
| 186 |
+
"valid_targets_min": 1190
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.4977777777777779,
|
| 190 |
+
"grad_norm": 0.32922754267793913,
|
| 191 |
+
"learning_rate": 3.561474457144189e-05,
|
| 192 |
+
"loss": 0.2449,
|
| 193 |
+
"loss_nan_ranks": 0,
|
| 194 |
+
"loss_rank_avg": 0.05151129886507988,
|
| 195 |
+
"step": 85,
|
| 196 |
+
"valid_targets_mean": 3233.1,
|
| 197 |
+
"valid_targets_min": 1357
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.5866666666666667,
|
| 201 |
+
"grad_norm": 0.32706014931505833,
|
| 202 |
+
"learning_rate": 3.4819022507099184e-05,
|
| 203 |
+
"loss": 0.2223,
|
| 204 |
+
"loss_nan_ranks": 0,
|
| 205 |
+
"loss_rank_avg": 0.05639180168509483,
|
| 206 |
+
"step": 90,
|
| 207 |
+
"valid_targets_mean": 2922.6,
|
| 208 |
+
"valid_targets_min": 1310
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.6755555555555555,
|
| 212 |
+
"grad_norm": 0.341988951356744,
|
| 213 |
+
"learning_rate": 3.3967524988179463e-05,
|
| 214 |
+
"loss": 0.2319,
|
| 215 |
+
"loss_nan_ranks": 0,
|
| 216 |
+
"loss_rank_avg": 0.040721211582422256,
|
| 217 |
+
"step": 95,
|
| 218 |
+
"valid_targets_mean": 2238.1,
|
| 219 |
+
"valid_targets_min": 1199
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.7644444444444445,
|
| 223 |
+
"grad_norm": 0.3543043397710712,
|
| 224 |
+
"learning_rate": 3.306345685907553e-05,
|
| 225 |
+
"loss": 0.2313,
|
| 226 |
+
"loss_nan_ranks": 0,
|
| 227 |
+
"loss_rank_avg": 0.03705868870019913,
|
| 228 |
+
"step": 100,
|
| 229 |
+
"valid_targets_mean": 2039.1,
|
| 230 |
+
"valid_targets_min": 1054
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.8533333333333335,
|
| 234 |
+
"grad_norm": 0.3169475427171822,
|
| 235 |
+
"learning_rate": 3.211022082808652e-05,
|
| 236 |
+
"loss": 0.2231,
|
| 237 |
+
"loss_nan_ranks": 0,
|
| 238 |
+
"loss_rank_avg": 0.03866267204284668,
|
| 239 |
+
"step": 105,
|
| 240 |
+
"valid_targets_mean": 2269.2,
|
| 241 |
+
"valid_targets_min": 1244
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.942222222222222,
|
| 245 |
+
"grad_norm": 0.3626154274513678,
|
| 246 |
+
"learning_rate": 3.111140466039205e-05,
|
| 247 |
+
"loss": 0.2454,
|
| 248 |
+
"loss_nan_ranks": 0,
|
| 249 |
+
"loss_rank_avg": 0.05644143745303154,
|
| 250 |
+
"step": 110,
|
| 251 |
+
"valid_targets_mean": 2740.2,
|
| 252 |
+
"valid_targets_min": 1249
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.017777777777778,
|
| 256 |
+
"grad_norm": 0.3229168931990422,
|
| 257 |
+
"learning_rate": 3.0070767674514355e-05,
|
| 258 |
+
"loss": 0.231,
|
| 259 |
+
"loss_nan_ranks": 0,
|
| 260 |
+
"loss_rank_avg": 0.045998841524124146,
|
| 261 |
+
"step": 115,
|
| 262 |
+
"valid_targets_mean": 2432.6,
|
| 263 |
+
"valid_targets_min": 1365
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.1066666666666665,
|
| 267 |
+
"grad_norm": 0.4074227847296487,
|
| 268 |
+
"learning_rate": 2.8992226593092135e-05,
|
| 269 |
+
"loss": 0.2261,
|
| 270 |
+
"loss_nan_ranks": 0,
|
| 271 |
+
"loss_rank_avg": 0.041235923767089844,
|
| 272 |
+
"step": 120,
|
| 273 |
+
"valid_targets_mean": 2494.5,
|
| 274 |
+
"valid_targets_min": 1151
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.1955555555555555,
|
| 278 |
+
"grad_norm": 0.3124502564340804,
|
| 279 |
+
"learning_rate": 2.7879840801220967e-05,
|
| 280 |
+
"loss": 0.2109,
|
| 281 |
+
"loss_nan_ranks": 0,
|
| 282 |
+
"loss_rank_avg": 0.04943722486495972,
|
| 283 |
+
"step": 125,
|
| 284 |
+
"valid_targets_mean": 2937.8,
|
| 285 |
+
"valid_targets_min": 1162
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.2844444444444445,
|
| 289 |
+
"grad_norm": 0.36347414667971645,
|
| 290 |
+
"learning_rate": 2.6737797067844403e-05,
|
| 291 |
+
"loss": 0.2205,
|
| 292 |
+
"loss_nan_ranks": 0,
|
| 293 |
+
"loss_rank_avg": 0.041548021137714386,
|
| 294 |
+
"step": 130,
|
| 295 |
+
"valid_targets_mean": 2297.9,
|
| 296 |
+
"valid_targets_min": 1539
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.3733333333333335,
|
| 300 |
+
"grad_norm": 0.3397949895260685,
|
| 301 |
+
"learning_rate": 2.5570393787701063e-05,
|
| 302 |
+
"loss": 0.2151,
|
| 303 |
+
"loss_nan_ranks": 0,
|
| 304 |
+
"loss_rank_avg": 0.07428301870822906,
|
| 305 |
+
"step": 135,
|
| 306 |
+
"valid_targets_mean": 3256.2,
|
| 307 |
+
"valid_targets_min": 1340
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.462222222222222,
|
| 311 |
+
"grad_norm": 0.3409669850928538,
|
| 312 |
+
"learning_rate": 2.4382024803137396e-05,
|
| 313 |
+
"loss": 0.214,
|
| 314 |
+
"loss_nan_ranks": 0,
|
| 315 |
+
"loss_rank_avg": 0.05983541160821915,
|
| 316 |
+
"step": 140,
|
| 317 |
+
"valid_targets_mean": 2922.6,
|
| 318 |
+
"valid_targets_min": 1264
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.551111111111111,
|
| 322 |
+
"grad_norm": 0.33002068625976483,
|
| 323 |
+
"learning_rate": 2.317716286667723e-05,
|
| 324 |
+
"loss": 0.2169,
|
| 325 |
+
"loss_nan_ranks": 0,
|
| 326 |
+
"loss_rank_avg": 0.05062925070524216,
|
| 327 |
+
"step": 145,
|
| 328 |
+
"valid_targets_mean": 2481.7,
|
| 329 |
+
"valid_targets_min": 1088
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.64,
|
| 333 |
+
"grad_norm": 0.3116815064192726,
|
| 334 |
+
"learning_rate": 2.196034280659122e-05,
|
| 335 |
+
"loss": 0.2099,
|
| 336 |
+
"loss_nan_ranks": 0,
|
| 337 |
+
"loss_rank_avg": 0.03972204774618149,
|
| 338 |
+
"step": 150,
|
| 339 |
+
"valid_targets_mean": 2388.9,
|
| 340 |
+
"valid_targets_min": 1028
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.728888888888889,
|
| 344 |
+
"grad_norm": 0.32691657273888747,
|
| 345 |
+
"learning_rate": 2.073614445882718e-05,
|
| 346 |
+
"loss": 0.2243,
|
| 347 |
+
"loss_nan_ranks": 0,
|
| 348 |
+
"loss_rank_avg": 0.05966932699084282,
|
| 349 |
+
"step": 155,
|
| 350 |
+
"valid_targets_mean": 2523.2,
|
| 351 |
+
"valid_targets_min": 1338
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.8177777777777777,
|
| 355 |
+
"grad_norm": 0.32702194667234424,
|
| 356 |
+
"learning_rate": 1.950917542954176e-05,
|
| 357 |
+
"loss": 0.22,
|
| 358 |
+
"loss_nan_ranks": 0,
|
| 359 |
+
"loss_rank_avg": 0.05485967546701431,
|
| 360 |
+
"step": 160,
|
| 361 |
+
"valid_targets_mean": 2835.8,
|
| 362 |
+
"valid_targets_min": 1045
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.9066666666666667,
|
| 366 |
+
"grad_norm": 0.3371678153197184,
|
| 367 |
+
"learning_rate": 1.8284053753111205e-05,
|
| 368 |
+
"loss": 0.2104,
|
| 369 |
+
"loss_nan_ranks": 0,
|
| 370 |
+
"loss_rank_avg": 0.034001681953668594,
|
| 371 |
+
"step": 165,
|
| 372 |
+
"valid_targets_mean": 2010.9,
|
| 373 |
+
"valid_targets_min": 1203
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.9955555555555557,
|
| 377 |
+
"grad_norm": 0.3400453584476225,
|
| 378 |
+
"learning_rate": 1.7065390510892767e-05,
|
| 379 |
+
"loss": 0.2065,
|
| 380 |
+
"loss_nan_ranks": 0,
|
| 381 |
+
"loss_rank_avg": 0.04110487177968025,
|
| 382 |
+
"step": 170,
|
| 383 |
+
"valid_targets_mean": 2373.1,
|
| 384 |
+
"valid_targets_min": 1131
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.071111111111111,
|
| 388 |
+
"grad_norm": 0.29868424312125685,
|
| 389 |
+
"learning_rate": 1.5857772476155634e-05,
|
| 390 |
+
"loss": 0.2018,
|
| 391 |
+
"loss_nan_ranks": 0,
|
| 392 |
+
"loss_rank_avg": 0.05249975621700287,
|
| 393 |
+
"step": 175,
|
| 394 |
+
"valid_targets_mean": 3154.9,
|
| 395 |
+
"valid_targets_min": 1178
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.16,
|
| 399 |
+
"grad_norm": 0.3706098125869751,
|
| 400 |
+
"learning_rate": 1.4665744850502035e-05,
|
| 401 |
+
"loss": 0.2145,
|
| 402 |
+
"loss_nan_ranks": 0,
|
| 403 |
+
"loss_rank_avg": 0.055659279227256775,
|
| 404 |
+
"step": 180,
|
| 405 |
+
"valid_targets_mean": 2609.7,
|
| 406 |
+
"valid_targets_min": 1283
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 3.2488888888888887,
|
| 410 |
+
"grad_norm": 0.34761594185958783,
|
| 411 |
+
"learning_rate": 1.3493794156754744e-05,
|
| 412 |
+
"loss": 0.2129,
|
| 413 |
+
"loss_nan_ranks": 0,
|
| 414 |
+
"loss_rank_avg": 0.03931069374084473,
|
| 415 |
+
"step": 185,
|
| 416 |
+
"valid_targets_mean": 2712.7,
|
| 417 |
+
"valid_targets_min": 1002
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.3377777777777777,
|
| 421 |
+
"grad_norm": 0.3480472578827022,
|
| 422 |
+
"learning_rate": 1.2346331352698206e-05,
|
| 423 |
+
"loss": 0.2032,
|
| 424 |
+
"loss_nan_ranks": 0,
|
| 425 |
+
"loss_rank_avg": 0.06302663683891296,
|
| 426 |
+
"step": 190,
|
| 427 |
+
"valid_targets_mean": 2542.1,
|
| 428 |
+
"valid_targets_min": 1383
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.4266666666666667,
|
| 432 |
+
"grad_norm": 0.35674083440708165,
|
| 433 |
+
"learning_rate": 1.1227675229229453e-05,
|
| 434 |
+
"loss": 0.1997,
|
| 435 |
+
"loss_nan_ranks": 0,
|
| 436 |
+
"loss_rank_avg": 0.06049852818250656,
|
| 437 |
+
"step": 195,
|
| 438 |
+
"valid_targets_mean": 2524.8,
|
| 439 |
+
"valid_targets_min": 993
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.5155555555555553,
|
| 443 |
+
"grad_norm": 0.33660537404764074,
|
| 444 |
+
"learning_rate": 1.0142036155404322e-05,
|
| 445 |
+
"loss": 0.2092,
|
| 446 |
+
"loss_nan_ranks": 0,
|
| 447 |
+
"loss_rank_avg": 0.04671245440840721,
|
| 448 |
+
"step": 200,
|
| 449 |
+
"valid_targets_mean": 2890.4,
|
| 450 |
+
"valid_targets_min": 388
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.6044444444444443,
|
| 454 |
+
"grad_norm": 0.4234454768211141,
|
| 455 |
+
"learning_rate": 9.093500231559076e-06,
|
| 456 |
+
"loss": 0.1932,
|
| 457 |
+
"loss_nan_ranks": 0,
|
| 458 |
+
"loss_rank_avg": 0.039773087948560715,
|
| 459 |
+
"step": 205,
|
| 460 |
+
"valid_targets_mean": 2687.6,
|
| 461 |
+
"valid_targets_min": 1134
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.6933333333333334,
|
| 465 |
+
"grad_norm": 0.3462492949486452,
|
| 466 |
+
"learning_rate": 8.086013910151334e-06,
|
| 467 |
+
"loss": 0.206,
|
| 468 |
+
"loss_nan_ranks": 0,
|
| 469 |
+
"loss_rank_avg": 0.0793825015425682,
|
| 470 |
+
"step": 210,
|
| 471 |
+
"valid_targets_mean": 3072.4,
|
| 472 |
+
"valid_targets_min": 1523
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 3.7822222222222224,
|
| 476 |
+
"grad_norm": 0.33043166323357076,
|
| 477 |
+
"learning_rate": 7.123369142204175e-06,
|
| 478 |
+
"loss": 0.1978,
|
| 479 |
+
"loss_nan_ranks": 0,
|
| 480 |
+
"loss_rank_avg": 0.05091720446944237,
|
| 481 |
+
"step": 215,
|
| 482 |
+
"valid_targets_mean": 2395.9,
|
| 483 |
+
"valid_targets_min": 1181
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.871111111111111,
|
| 487 |
+
"grad_norm": 0.3276021134703391,
|
| 488 |
+
"learning_rate": 6.209189105258661e-06,
|
| 489 |
+
"loss": 0.1978,
|
| 490 |
+
"loss_nan_ranks": 0,
|
| 491 |
+
"loss_rank_avg": 0.04009982943534851,
|
| 492 |
+
"step": 220,
|
| 493 |
+
"valid_targets_mean": 2544.8,
|
| 494 |
+
"valid_targets_min": 1459
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.96,
|
| 498 |
+
"grad_norm": 0.3518358226857207,
|
| 499 |
+
"learning_rate": 5.346914566551746e-06,
|
| 500 |
+
"loss": 0.2057,
|
| 501 |
+
"loss_nan_ranks": 0,
|
| 502 |
+
"loss_rank_avg": 0.05190512537956238,
|
| 503 |
+
"step": 225,
|
| 504 |
+
"valid_targets_mean": 2315.4,
|
| 505 |
+
"valid_targets_min": 1089
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 4.035555555555556,
|
| 509 |
+
"grad_norm": 0.446701948663916,
|
| 510 |
+
"learning_rate": 4.53979093274526e-06,
|
| 511 |
+
"loss": 0.1909,
|
| 512 |
+
"loss_nan_ranks": 0,
|
| 513 |
+
"loss_rank_avg": 0.04597758501768112,
|
| 514 |
+
"step": 230,
|
| 515 |
+
"valid_targets_mean": 2736.4,
|
| 516 |
+
"valid_targets_min": 1155
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 4.124444444444444,
|
| 520 |
+
"grad_norm": 0.3070256238047938,
|
| 521 |
+
"learning_rate": 3.7908560349481072e-06,
|
| 522 |
+
"loss": 0.1998,
|
| 523 |
+
"loss_nan_ranks": 0,
|
| 524 |
+
"loss_rank_avg": 0.05320999398827553,
|
| 525 |
+
"step": 235,
|
| 526 |
+
"valid_targets_mean": 3201.8,
|
| 527 |
+
"valid_targets_min": 1119
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 4.213333333333333,
|
| 531 |
+
"grad_norm": 0.3084555402280151,
|
| 532 |
+
"learning_rate": 3.102928695005858e-06,
|
| 533 |
+
"loss": 0.1975,
|
| 534 |
+
"loss_nan_ranks": 0,
|
| 535 |
+
"loss_rank_avg": 0.029193339869379997,
|
| 536 |
+
"step": 240,
|
| 537 |
+
"valid_targets_mean": 1924.7,
|
| 538 |
+
"valid_targets_min": 1318
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 4.302222222222222,
|
| 542 |
+
"grad_norm": 0.33282212562089014,
|
| 543 |
+
"learning_rate": 2.4785981160918703e-06,
|
| 544 |
+
"loss": 0.2001,
|
| 545 |
+
"loss_nan_ranks": 0,
|
| 546 |
+
"loss_rank_avg": 0.04285688325762749,
|
| 547 |
+
"step": 245,
|
| 548 |
+
"valid_targets_mean": 2463.9,
|
| 549 |
+
"valid_targets_min": 1178
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.391111111111111,
|
| 553 |
+
"grad_norm": 0.3167323683701005,
|
| 554 |
+
"learning_rate": 1.9202141375311335e-06,
|
| 555 |
+
"loss": 0.2013,
|
| 556 |
+
"loss_nan_ranks": 0,
|
| 557 |
+
"loss_rank_avg": 0.04943656548857689,
|
| 558 |
+
"step": 250,
|
| 559 |
+
"valid_targets_mean": 2726.8,
|
| 560 |
+
"valid_targets_min": 1173
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.48,
|
| 564 |
+
"grad_norm": 0.33351932332643597,
|
| 565 |
+
"learning_rate": 1.4298783905356906e-06,
|
| 566 |
+
"loss": 0.1954,
|
| 567 |
+
"loss_nan_ranks": 0,
|
| 568 |
+
"loss_rank_avg": 0.04813677817583084,
|
| 569 |
+
"step": 255,
|
| 570 |
+
"valid_targets_mean": 2432.7,
|
| 571 |
+
"valid_targets_min": 942
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 4.568888888888889,
|
| 575 |
+
"grad_norm": 0.3163118446536364,
|
| 576 |
+
"learning_rate": 1.0094363881392665e-06,
|
| 577 |
+
"loss": 0.1975,
|
| 578 |
+
"loss_nan_ranks": 0,
|
| 579 |
+
"loss_rank_avg": 0.06139428913593292,
|
| 580 |
+
"step": 260,
|
| 581 |
+
"valid_targets_mean": 3001.4,
|
| 582 |
+
"valid_targets_min": 1329
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 4.657777777777778,
|
| 586 |
+
"grad_norm": 0.33335357258605675,
|
| 587 |
+
"learning_rate": 6.604705791029586e-07,
|
| 588 |
+
"loss": 0.1987,
|
| 589 |
+
"loss_nan_ranks": 0,
|
| 590 |
+
"loss_rank_avg": 0.044643834233284,
|
| 591 |
+
"step": 265,
|
| 592 |
+
"valid_targets_mean": 2461.6,
|
| 593 |
+
"valid_targets_min": 1178
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 4.746666666666667,
|
| 597 |
+
"grad_norm": 0.33713590138912286,
|
| 598 |
+
"learning_rate": 3.842943919353914e-07,
|
| 599 |
+
"loss": 0.1881,
|
| 600 |
+
"loss_nan_ranks": 0,
|
| 601 |
+
"loss_rank_avg": 0.03312596306204796,
|
| 602 |
+
"step": 270,
|
| 603 |
+
"valid_targets_mean": 2348.8,
|
| 604 |
+
"valid_targets_min": 1282
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.835555555555556,
|
| 608 |
+
"grad_norm": 0.32804179691400653,
|
| 609 |
+
"learning_rate": 1.819472914443998e-07,
|
| 610 |
+
"loss": 0.207,
|
| 611 |
+
"loss_nan_ranks": 0,
|
| 612 |
+
"loss_rank_avg": 0.03083619847893715,
|
| 613 |
+
"step": 275,
|
| 614 |
+
"valid_targets_mean": 2106.2,
|
| 615 |
+
"valid_targets_min": 1274
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.924444444444444,
|
| 619 |
+
"grad_norm": 0.3250869471276454,
|
| 620 |
+
"learning_rate": 5.4190866426195866e-08,
|
| 621 |
+
"loss": 0.1982,
|
| 622 |
+
"loss_nan_ranks": 0,
|
| 623 |
+
"loss_rank_avg": 0.04578050225973129,
|
| 624 |
+
"step": 280,
|
| 625 |
+
"valid_targets_mean": 2654.6,
|
| 626 |
+
"valid_targets_min": 1454
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 5.0,
|
| 630 |
+
"grad_norm": 0.6141969340231087,
|
| 631 |
+
"learning_rate": 1.5059632171099402e-09,
|
| 632 |
+
"loss": 0.2007,
|
| 633 |
+
"loss_nan_ranks": 0,
|
| 634 |
+
"loss_rank_avg": 0.2248307466506958,
|
| 635 |
+
"step": 285,
|
| 636 |
+
"valid_targets_mean": 2971.6,
|
| 637 |
+
"valid_targets_min": 1283
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 5.0,
|
| 641 |
+
"loss_nan_ranks": 0,
|
| 642 |
+
"loss_rank_avg": 0.2248307466506958,
|
| 643 |
+
"step": 285,
|
| 644 |
+
"total_flos": 3.151185311610962e+17,
|
| 645 |
+
"train_loss": 0.24082276695653013,
|
| 646 |
+
"train_runtime": 3979.0496,
|
| 647 |
+
"train_samples_per_second": 4.505,
|
| 648 |
+
"train_steps_per_second": 0.072,
|
| 649 |
+
"valid_targets_mean": 2971.6,
|
| 650 |
+
"valid_targets_min": 1283
|
| 651 |
+
}
|
| 652 |
+
],
|
| 653 |
+
"logging_steps": 5,
|
| 654 |
+
"max_steps": 285,
|
| 655 |
+
"num_input_tokens_seen": 0,
|
| 656 |
+
"num_train_epochs": 5,
|
| 657 |
+
"save_steps": 500,
|
| 658 |
+
"stateful_callbacks": {
|
| 659 |
+
"TrainerControl": {
|
| 660 |
+
"args": {
|
| 661 |
+
"should_epoch_stop": false,
|
| 662 |
+
"should_evaluate": false,
|
| 663 |
+
"should_log": false,
|
| 664 |
+
"should_save": false,
|
| 665 |
+
"should_training_stop": false
|
| 666 |
+
},
|
| 667 |
+
"attributes": {}
|
| 668 |
+
}
|
| 669 |
+
},
|
| 670 |
+
"total_flos": 3.151185311610962e+17,
|
| 671 |
+
"train_batch_size": 1,
|
| 672 |
+
"trial_name": null,
|
| 673 |
+
"trial_params": null
|
| 674 |
+
}
|
training_loss.png
ADDED
|