Commit
•
a48fd04
1
Parent(s):
42d1531
End of training
Browse files- README.md +24 -2
- adapter_model.safetensors +1 -1
- all_results.json +9 -9
- eval_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +252 -12
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -39,12 +39,34 @@ The following hyperparameters were used during training:
|
|
| 39 |
- train_batch_size: 16
|
| 40 |
- eval_batch_size: 16
|
| 41 |
- seed: 42
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- num_epochs: 0
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
|
| 50 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.3584
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 39 |
- train_batch_size: 16
|
| 40 |
- eval_batch_size: 16
|
| 41 |
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- total_train_batch_size: 128
|
| 45 |
+
- total_eval_batch_size: 128
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 1000.0
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 0.3349 | 62.5 | 500 | 0.2107 |
|
| 55 |
+
| 0.1147 | 125.0 | 1000 | 0.2410 |
|
| 56 |
+
| 0.071 | 187.5 | 1500 | 0.2687 |
|
| 57 |
+
| 0.0502 | 250.0 | 2000 | 0.2901 |
|
| 58 |
+
| 0.0373 | 312.5 | 2500 | 0.3033 |
|
| 59 |
+
| 0.0301 | 375.0 | 3000 | 0.3141 |
|
| 60 |
+
| 0.025 | 437.5 | 3500 | 0.3235 |
|
| 61 |
+
| 0.0212 | 500.0 | 4000 | 0.3312 |
|
| 62 |
+
| 0.0187 | 562.5 | 4500 | 0.3404 |
|
| 63 |
+
| 0.017 | 625.0 | 5000 | 0.3371 |
|
| 64 |
+
| 0.0148 | 687.5 | 5500 | 0.3466 |
|
| 65 |
+
| 0.0139 | 750.0 | 6000 | 0.3480 |
|
| 66 |
+
| 0.0124 | 812.5 | 6500 | 0.3552 |
|
| 67 |
+
| 0.0118 | 875.0 | 7000 | 0.3594 |
|
| 68 |
+
| 0.0112 | 937.5 | 7500 | 0.3581 |
|
| 69 |
+
| 0.0106 | 1000.0 | 8000 | 0.3584 |
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2765880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26c9b5c429b5d796727814fd7067d51c53e9ce684027a0f3192ff97b639c9d18
|
| 3 |
size 2765880
|
all_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second":
|
| 7 |
-
"train_loss":
|
| 8 |
-
"train_runtime":
|
| 9 |
-
"train_samples_per_second":
|
| 10 |
-
"train_steps_per_second":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1000.0,
|
| 3 |
+
"eval_loss": 0.35844165086746216,
|
| 4 |
+
"eval_runtime": 1.7584,
|
| 5 |
+
"eval_samples_per_second": 4468.328,
|
| 6 |
+
"eval_steps_per_second": 35.26,
|
| 7 |
+
"train_loss": 0.04967061561346054,
|
| 8 |
+
"train_runtime": 721.4078,
|
| 9 |
+
"train_samples_per_second": 1386.178,
|
| 10 |
+
"train_steps_per_second": 11.089
|
| 11 |
}
|
eval_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1000.0,
|
| 3 |
+
"eval_loss": 0.35844165086746216,
|
| 4 |
+
"eval_runtime": 1.7584,
|
| 5 |
+
"eval_samples_per_second": 4468.328,
|
| 6 |
+
"eval_steps_per_second": 35.26
|
| 7 |
}
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 0
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1000.0,
|
| 3 |
+
"train_loss": 0.04967061561346054,
|
| 4 |
+
"train_runtime": 721.4078,
|
| 5 |
+
"train_samples_per_second": 1386.178,
|
| 6 |
+
"train_steps_per_second": 11.089
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,29 +1,269 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch":
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 500,
|
| 22 |
-
"max_steps":
|
| 23 |
"num_input_tokens_seen": 0,
|
| 24 |
-
"num_train_epochs":
|
| 25 |
"save_steps": 500,
|
| 26 |
-
"total_flos":
|
| 27 |
"train_batch_size": 16,
|
| 28 |
"trial_name": null,
|
| 29 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1000.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 62.5,
|
| 13 |
+
"grad_norm": 0.2072206288576126,
|
| 14 |
+
"learning_rate": 0.0009375,
|
| 15 |
+
"loss": 0.3349,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 62.5,
|
| 20 |
+
"eval_loss": 0.21073544025421143,
|
| 21 |
+
"eval_runtime": 1.7576,
|
| 22 |
+
"eval_samples_per_second": 4470.361,
|
| 23 |
+
"eval_steps_per_second": 35.276,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 125.0,
|
| 28 |
+
"grad_norm": 0.20736312866210938,
|
| 29 |
+
"learning_rate": 0.000875,
|
| 30 |
+
"loss": 0.1147,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 125.0,
|
| 35 |
+
"eval_loss": 0.2409573197364807,
|
| 36 |
+
"eval_runtime": 1.7582,
|
| 37 |
+
"eval_samples_per_second": 4468.854,
|
| 38 |
+
"eval_steps_per_second": 35.264,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 187.5,
|
| 43 |
+
"grad_norm": 0.17418691515922546,
|
| 44 |
+
"learning_rate": 0.0008125000000000001,
|
| 45 |
+
"loss": 0.071,
|
| 46 |
+
"step": 1500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 187.5,
|
| 50 |
+
"eval_loss": 0.2686581015586853,
|
| 51 |
+
"eval_runtime": 1.7698,
|
| 52 |
+
"eval_samples_per_second": 4439.56,
|
| 53 |
+
"eval_steps_per_second": 35.033,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 250.0,
|
| 58 |
+
"grad_norm": 0.1891753375530243,
|
| 59 |
+
"learning_rate": 0.00075,
|
| 60 |
+
"loss": 0.0502,
|
| 61 |
+
"step": 2000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 250.0,
|
| 65 |
+
"eval_loss": 0.29014259576797485,
|
| 66 |
+
"eval_runtime": 1.7819,
|
| 67 |
+
"eval_samples_per_second": 4409.274,
|
| 68 |
+
"eval_steps_per_second": 34.794,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 312.5,
|
| 73 |
+
"grad_norm": 0.16434858739376068,
|
| 74 |
+
"learning_rate": 0.0006875,
|
| 75 |
+
"loss": 0.0373,
|
| 76 |
+
"step": 2500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 312.5,
|
| 80 |
+
"eval_loss": 0.3033287525177002,
|
| 81 |
+
"eval_runtime": 1.7585,
|
| 82 |
+
"eval_samples_per_second": 4468.05,
|
| 83 |
+
"eval_steps_per_second": 35.258,
|
| 84 |
+
"step": 2500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 375.0,
|
| 88 |
+
"grad_norm": 0.11065812408924103,
|
| 89 |
+
"learning_rate": 0.000625,
|
| 90 |
+
"loss": 0.0301,
|
| 91 |
+
"step": 3000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 375.0,
|
| 95 |
+
"eval_loss": 0.31410983204841614,
|
| 96 |
+
"eval_runtime": 1.7765,
|
| 97 |
+
"eval_samples_per_second": 4422.629,
|
| 98 |
+
"eval_steps_per_second": 34.899,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 437.5,
|
| 103 |
+
"grad_norm": 0.12541820108890533,
|
| 104 |
+
"learning_rate": 0.0005625000000000001,
|
| 105 |
+
"loss": 0.025,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 437.5,
|
| 110 |
+
"eval_loss": 0.3234836161136627,
|
| 111 |
+
"eval_runtime": 1.8714,
|
| 112 |
+
"eval_samples_per_second": 4198.44,
|
| 113 |
+
"eval_steps_per_second": 33.13,
|
| 114 |
+
"step": 3500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 500.0,
|
| 118 |
+
"grad_norm": 0.12353639304637909,
|
| 119 |
+
"learning_rate": 0.0005,
|
| 120 |
+
"loss": 0.0212,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 500.0,
|
| 125 |
+
"eval_loss": 0.33116382360458374,
|
| 126 |
+
"eval_runtime": 2.0737,
|
| 127 |
+
"eval_samples_per_second": 3788.95,
|
| 128 |
+
"eval_steps_per_second": 29.899,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 562.5,
|
| 133 |
+
"grad_norm": 0.14147008955478668,
|
| 134 |
+
"learning_rate": 0.0004375,
|
| 135 |
+
"loss": 0.0187,
|
| 136 |
+
"step": 4500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 562.5,
|
| 140 |
+
"eval_loss": 0.3403891623020172,
|
| 141 |
+
"eval_runtime": 1.7439,
|
| 142 |
+
"eval_samples_per_second": 4505.522,
|
| 143 |
+
"eval_steps_per_second": 35.553,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 625.0,
|
| 148 |
+
"grad_norm": 0.17466695606708527,
|
| 149 |
+
"learning_rate": 0.000375,
|
| 150 |
+
"loss": 0.017,
|
| 151 |
+
"step": 5000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 625.0,
|
| 155 |
+
"eval_loss": 0.3371485471725464,
|
| 156 |
+
"eval_runtime": 1.7727,
|
| 157 |
+
"eval_samples_per_second": 4432.252,
|
| 158 |
+
"eval_steps_per_second": 34.975,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 687.5,
|
| 163 |
+
"grad_norm": 0.1278233528137207,
|
| 164 |
+
"learning_rate": 0.0003125,
|
| 165 |
+
"loss": 0.0148,
|
| 166 |
+
"step": 5500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 687.5,
|
| 170 |
+
"eval_loss": 0.3466494679450989,
|
| 171 |
+
"eval_runtime": 1.7776,
|
| 172 |
+
"eval_samples_per_second": 4420.019,
|
| 173 |
+
"eval_steps_per_second": 34.879,
|
| 174 |
+
"step": 5500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 750.0,
|
| 178 |
+
"grad_norm": 0.08440423011779785,
|
| 179 |
+
"learning_rate": 0.00025,
|
| 180 |
+
"loss": 0.0139,
|
| 181 |
+
"step": 6000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 750.0,
|
| 185 |
+
"eval_loss": 0.34804055094718933,
|
| 186 |
+
"eval_runtime": 1.7744,
|
| 187 |
+
"eval_samples_per_second": 4427.887,
|
| 188 |
+
"eval_steps_per_second": 34.941,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 812.5,
|
| 193 |
+
"grad_norm": 0.1064932644367218,
|
| 194 |
+
"learning_rate": 0.0001875,
|
| 195 |
+
"loss": 0.0124,
|
| 196 |
+
"step": 6500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 812.5,
|
| 200 |
+
"eval_loss": 0.3551761209964752,
|
| 201 |
+
"eval_runtime": 1.7547,
|
| 202 |
+
"eval_samples_per_second": 4477.816,
|
| 203 |
+
"eval_steps_per_second": 35.335,
|
| 204 |
+
"step": 6500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 875.0,
|
| 208 |
+
"grad_norm": 0.07584909349679947,
|
| 209 |
+
"learning_rate": 0.000125,
|
| 210 |
+
"loss": 0.0118,
|
| 211 |
+
"step": 7000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 875.0,
|
| 215 |
+
"eval_loss": 0.3594026267528534,
|
| 216 |
+
"eval_runtime": 1.7559,
|
| 217 |
+
"eval_samples_per_second": 4474.601,
|
| 218 |
+
"eval_steps_per_second": 35.309,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 937.5,
|
| 223 |
+
"grad_norm": 0.04748733341693878,
|
| 224 |
+
"learning_rate": 6.25e-05,
|
| 225 |
+
"loss": 0.0112,
|
| 226 |
+
"step": 7500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 937.5,
|
| 230 |
+
"eval_loss": 0.35810717940330505,
|
| 231 |
+
"eval_runtime": 1.7577,
|
| 232 |
+
"eval_samples_per_second": 4469.966,
|
| 233 |
+
"eval_steps_per_second": 35.273,
|
| 234 |
+
"step": 7500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1000.0,
|
| 238 |
+
"grad_norm": 0.0842234194278717,
|
| 239 |
+
"learning_rate": 0.0,
|
| 240 |
+
"loss": 0.0106,
|
| 241 |
+
"step": 8000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1000.0,
|
| 245 |
+
"eval_loss": 0.35844165086746216,
|
| 246 |
+
"eval_runtime": 1.7498,
|
| 247 |
+
"eval_samples_per_second": 4490.355,
|
| 248 |
+
"eval_steps_per_second": 35.434,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1000.0,
|
| 253 |
+
"step": 8000,
|
| 254 |
+
"total_flos": 3.308878023570227e+16,
|
| 255 |
+
"train_loss": 0.04967061561346054,
|
| 256 |
+
"train_runtime": 721.4078,
|
| 257 |
+
"train_samples_per_second": 1386.178,
|
| 258 |
+
"train_steps_per_second": 11.089
|
| 259 |
}
|
| 260 |
],
|
| 261 |
"logging_steps": 500,
|
| 262 |
+
"max_steps": 8000,
|
| 263 |
"num_input_tokens_seen": 0,
|
| 264 |
+
"num_train_epochs": 1000,
|
| 265 |
"save_steps": 500,
|
| 266 |
+
"total_flos": 3.308878023570227e+16,
|
| 267 |
"train_batch_size": 16,
|
| 268 |
"trial_name": null,
|
| 269 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2897157a51be5f7f915a52c0ce8a7a5dd68d506352b5883c38401d0980d53d43
|
| 3 |
size 5112
|