Giovanni Monea
commited on
Commit
·
07c6f22
1
Parent(s):
22a3f76
Upload folder using huggingface_hub
Browse files- README.md +3 -0
- adapter_config.json +22 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
- trainer_state.json +562 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
adapter_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 16,
|
| 10 |
+
"lora_dropout": 0.1,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 64,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"query_key_value",
|
| 17 |
+
"dense",
|
| 18 |
+
"dense_h_to_4h",
|
| 19 |
+
"dense_4h_to_h"
|
| 20 |
+
],
|
| 21 |
+
"task_type": "CAUSAL_LM"
|
| 22 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e2bd082c78bf2b1a17d096beac18f311ca6705bec09a697b3011fa8f8e858c1
|
| 3 |
+
size 522284877
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92193c103944e77e6bdbe5a0d418f1211fdead9656b5044fa9a209f25e39643a
|
| 3 |
+
size 1044533445
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2324b71e853defba304049cb88d15d7e9bacb791564b487e32ccc141410eb6ed
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f207060de552e44affda291beb099901e18a29d2a09e9d11c079fa5245a3e660
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
">>TITLE<<",
|
| 4 |
+
">>ABSTRACT<<",
|
| 5 |
+
">>INTRODUCTION<<",
|
| 6 |
+
">>SUMMARY<<",
|
| 7 |
+
">>COMMENT<<",
|
| 8 |
+
">>ANSWER<<",
|
| 9 |
+
">>QUESTION<<",
|
| 10 |
+
">>DOMAIN<<",
|
| 11 |
+
">>PREFIX<<",
|
| 12 |
+
">>SUFFIX<<",
|
| 13 |
+
">>MIDDLE<<"
|
| 14 |
+
],
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"pad_token": "<|endoftext|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"model_max_length": 2048,
|
| 6 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,562 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.136986301369863,
|
| 5 |
+
"global_step": 390,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 4e-05,
|
| 13 |
+
"loss": 1.3902,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"eval_loss": 1.3901418447494507,
|
| 19 |
+
"eval_runtime": 108.6518,
|
| 20 |
+
"eval_samples_per_second": 1.555,
|
| 21 |
+
"eval_steps_per_second": 0.396,
|
| 22 |
+
"step": 10
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.11,
|
| 26 |
+
"learning_rate": 8e-05,
|
| 27 |
+
"loss": 1.3304,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.11,
|
| 32 |
+
"eval_loss": 1.3154278993606567,
|
| 33 |
+
"eval_runtime": 108.7121,
|
| 34 |
+
"eval_samples_per_second": 1.555,
|
| 35 |
+
"eval_steps_per_second": 0.396,
|
| 36 |
+
"step": 20
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.16,
|
| 40 |
+
"learning_rate": 0.00012,
|
| 41 |
+
"loss": 1.2138,
|
| 42 |
+
"step": 30
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.16,
|
| 46 |
+
"eval_loss": 1.2570539712905884,
|
| 47 |
+
"eval_runtime": 108.5686,
|
| 48 |
+
"eval_samples_per_second": 1.557,
|
| 49 |
+
"eval_steps_per_second": 0.396,
|
| 50 |
+
"step": 30
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.22,
|
| 54 |
+
"learning_rate": 0.00016,
|
| 55 |
+
"loss": 1.2281,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.22,
|
| 60 |
+
"eval_loss": 1.237758994102478,
|
| 61 |
+
"eval_runtime": 108.8506,
|
| 62 |
+
"eval_samples_per_second": 1.553,
|
| 63 |
+
"eval_steps_per_second": 0.395,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.27,
|
| 68 |
+
"learning_rate": 0.0002,
|
| 69 |
+
"loss": 1.2155,
|
| 70 |
+
"step": 50
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.27,
|
| 74 |
+
"eval_loss": 1.2247029542922974,
|
| 75 |
+
"eval_runtime": 108.5608,
|
| 76 |
+
"eval_samples_per_second": 1.557,
|
| 77 |
+
"eval_steps_per_second": 0.396,
|
| 78 |
+
"step": 50
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.33,
|
| 82 |
+
"learning_rate": 0.00019994532573409262,
|
| 83 |
+
"loss": 1.1823,
|
| 84 |
+
"step": 60
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.33,
|
| 88 |
+
"eval_loss": 1.2180429697036743,
|
| 89 |
+
"eval_runtime": 108.7983,
|
| 90 |
+
"eval_samples_per_second": 1.553,
|
| 91 |
+
"eval_steps_per_second": 0.395,
|
| 92 |
+
"step": 60
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.38,
|
| 96 |
+
"learning_rate": 0.00019978136272187747,
|
| 97 |
+
"loss": 1.2289,
|
| 98 |
+
"step": 70
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.38,
|
| 102 |
+
"eval_loss": 1.2121814489364624,
|
| 103 |
+
"eval_runtime": 108.4495,
|
| 104 |
+
"eval_samples_per_second": 1.558,
|
| 105 |
+
"eval_steps_per_second": 0.396,
|
| 106 |
+
"step": 70
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.44,
|
| 110 |
+
"learning_rate": 0.00019950829025450114,
|
| 111 |
+
"loss": 1.1623,
|
| 112 |
+
"step": 80
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.44,
|
| 116 |
+
"eval_loss": 1.2073330879211426,
|
| 117 |
+
"eval_runtime": 108.7996,
|
| 118 |
+
"eval_samples_per_second": 1.553,
|
| 119 |
+
"eval_steps_per_second": 0.395,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.49,
|
| 124 |
+
"learning_rate": 0.00019912640693269752,
|
| 125 |
+
"loss": 1.2067,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.49,
|
| 130 |
+
"eval_loss": 1.204315423965454,
|
| 131 |
+
"eval_runtime": 108.8942,
|
| 132 |
+
"eval_samples_per_second": 1.552,
|
| 133 |
+
"eval_steps_per_second": 0.395,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.55,
|
| 138 |
+
"learning_rate": 0.00019863613034027224,
|
| 139 |
+
"loss": 1.1499,
|
| 140 |
+
"step": 100
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.55,
|
| 144 |
+
"eval_loss": 1.2012346982955933,
|
| 145 |
+
"eval_runtime": 108.7573,
|
| 146 |
+
"eval_samples_per_second": 1.554,
|
| 147 |
+
"eval_steps_per_second": 0.395,
|
| 148 |
+
"step": 100
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.6,
|
| 152 |
+
"learning_rate": 0.00019803799658748094,
|
| 153 |
+
"loss": 1.2184,
|
| 154 |
+
"step": 110
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.6,
|
| 158 |
+
"eval_loss": 1.200089454650879,
|
| 159 |
+
"eval_runtime": 108.5135,
|
| 160 |
+
"eval_samples_per_second": 1.557,
|
| 161 |
+
"eval_steps_per_second": 0.396,
|
| 162 |
+
"step": 110
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.66,
|
| 166 |
+
"learning_rate": 0.0001973326597248006,
|
| 167 |
+
"loss": 1.1758,
|
| 168 |
+
"step": 120
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.66,
|
| 172 |
+
"eval_loss": 1.1969162225723267,
|
| 173 |
+
"eval_runtime": 108.562,
|
| 174 |
+
"eval_samples_per_second": 1.557,
|
| 175 |
+
"eval_steps_per_second": 0.396,
|
| 176 |
+
"step": 120
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.71,
|
| 180 |
+
"learning_rate": 0.00019652089102773488,
|
| 181 |
+
"loss": 1.1931,
|
| 182 |
+
"step": 130
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.71,
|
| 186 |
+
"eval_loss": 1.1960800886154175,
|
| 187 |
+
"eval_runtime": 108.6308,
|
| 188 |
+
"eval_samples_per_second": 1.556,
|
| 189 |
+
"eval_steps_per_second": 0.396,
|
| 190 |
+
"step": 130
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.77,
|
| 194 |
+
"learning_rate": 0.00019560357815343577,
|
| 195 |
+
"loss": 1.1334,
|
| 196 |
+
"step": 140
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.77,
|
| 200 |
+
"eval_loss": 1.1931264400482178,
|
| 201 |
+
"eval_runtime": 108.6207,
|
| 202 |
+
"eval_samples_per_second": 1.556,
|
| 203 |
+
"eval_steps_per_second": 0.396,
|
| 204 |
+
"step": 140
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.82,
|
| 208 |
+
"learning_rate": 0.00019458172417006347,
|
| 209 |
+
"loss": 1.1321,
|
| 210 |
+
"step": 150
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.82,
|
| 214 |
+
"eval_loss": 1.1918461322784424,
|
| 215 |
+
"eval_runtime": 108.4723,
|
| 216 |
+
"eval_samples_per_second": 1.558,
|
| 217 |
+
"eval_steps_per_second": 0.396,
|
| 218 |
+
"step": 150
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.88,
|
| 222 |
+
"learning_rate": 0.0001934564464599461,
|
| 223 |
+
"loss": 1.181,
|
| 224 |
+
"step": 160
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.88,
|
| 228 |
+
"eval_loss": 1.1898659467697144,
|
| 229 |
+
"eval_runtime": 108.5621,
|
| 230 |
+
"eval_samples_per_second": 1.557,
|
| 231 |
+
"eval_steps_per_second": 0.396,
|
| 232 |
+
"step": 160
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.93,
|
| 236 |
+
"learning_rate": 0.00019222897549773848,
|
| 237 |
+
"loss": 1.2347,
|
| 238 |
+
"step": 170
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.93,
|
| 242 |
+
"eval_loss": 1.1882331371307373,
|
| 243 |
+
"eval_runtime": 108.6542,
|
| 244 |
+
"eval_samples_per_second": 1.555,
|
| 245 |
+
"eval_steps_per_second": 0.396,
|
| 246 |
+
"step": 170
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.99,
|
| 250 |
+
"learning_rate": 0.00019090065350491626,
|
| 251 |
+
"loss": 1.0926,
|
| 252 |
+
"step": 180
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.99,
|
| 256 |
+
"eval_loss": 1.1871733665466309,
|
| 257 |
+
"eval_runtime": 108.5395,
|
| 258 |
+
"eval_samples_per_second": 1.557,
|
| 259 |
+
"eval_steps_per_second": 0.396,
|
| 260 |
+
"step": 180
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.04,
|
| 264 |
+
"learning_rate": 0.00018947293298207635,
|
| 265 |
+
"loss": 1.1425,
|
| 266 |
+
"step": 190
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.04,
|
| 270 |
+
"eval_loss": 1.1867098808288574,
|
| 271 |
+
"eval_runtime": 108.4877,
|
| 272 |
+
"eval_samples_per_second": 1.558,
|
| 273 |
+
"eval_steps_per_second": 0.396,
|
| 274 |
+
"step": 190
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.1,
|
| 278 |
+
"learning_rate": 0.0001879473751206489,
|
| 279 |
+
"loss": 1.128,
|
| 280 |
+
"step": 200
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.1,
|
| 284 |
+
"eval_loss": 1.1867098808288574,
|
| 285 |
+
"eval_runtime": 108.7001,
|
| 286 |
+
"eval_samples_per_second": 1.555,
|
| 287 |
+
"eval_steps_per_second": 0.396,
|
| 288 |
+
"step": 200
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.15,
|
| 292 |
+
"learning_rate": 0.00018632564809575742,
|
| 293 |
+
"loss": 1.1237,
|
| 294 |
+
"step": 210
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.15,
|
| 298 |
+
"eval_loss": 1.1867098808288574,
|
| 299 |
+
"eval_runtime": 108.5929,
|
| 300 |
+
"eval_samples_per_second": 1.556,
|
| 301 |
+
"eval_steps_per_second": 0.396,
|
| 302 |
+
"step": 210
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.21,
|
| 306 |
+
"learning_rate": 0.00018460952524209355,
|
| 307 |
+
"loss": 1.0939,
|
| 308 |
+
"step": 220
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.21,
|
| 312 |
+
"eval_loss": 1.1867098808288574,
|
| 313 |
+
"eval_runtime": 108.8988,
|
| 314 |
+
"eval_samples_per_second": 1.552,
|
| 315 |
+
"eval_steps_per_second": 0.395,
|
| 316 |
+
"step": 220
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.26,
|
| 320 |
+
"learning_rate": 0.00018280088311480201,
|
| 321 |
+
"loss": 1.093,
|
| 322 |
+
"step": 230
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.26,
|
| 326 |
+
"eval_loss": 1.1867098808288574,
|
| 327 |
+
"eval_runtime": 108.817,
|
| 328 |
+
"eval_samples_per_second": 1.553,
|
| 329 |
+
"eval_steps_per_second": 0.395,
|
| 330 |
+
"step": 230
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.32,
|
| 334 |
+
"learning_rate": 0.00018090169943749476,
|
| 335 |
+
"loss": 1.0988,
|
| 336 |
+
"step": 240
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.32,
|
| 340 |
+
"eval_loss": 1.1867098808288574,
|
| 341 |
+
"eval_runtime": 108.6088,
|
| 342 |
+
"eval_samples_per_second": 1.556,
|
| 343 |
+
"eval_steps_per_second": 0.396,
|
| 344 |
+
"step": 240
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.37,
|
| 348 |
+
"learning_rate": 0.00017891405093963938,
|
| 349 |
+
"loss": 1.1054,
|
| 350 |
+
"step": 250
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.37,
|
| 354 |
+
"eval_loss": 1.1867098808288574,
|
| 355 |
+
"eval_runtime": 108.4026,
|
| 356 |
+
"eval_samples_per_second": 1.559,
|
| 357 |
+
"eval_steps_per_second": 0.397,
|
| 358 |
+
"step": 250
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.42,
|
| 362 |
+
"learning_rate": 0.00017684011108568592,
|
| 363 |
+
"loss": 1.1051,
|
| 364 |
+
"step": 260
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.42,
|
| 368 |
+
"eval_loss": 1.1867098808288574,
|
| 369 |
+
"eval_runtime": 108.6345,
|
| 370 |
+
"eval_samples_per_second": 1.556,
|
| 371 |
+
"eval_steps_per_second": 0.396,
|
| 372 |
+
"step": 260
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.48,
|
| 376 |
+
"learning_rate": 0.0001746821476984154,
|
| 377 |
+
"loss": 1.1373,
|
| 378 |
+
"step": 270
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.48,
|
| 382 |
+
"eval_loss": 1.1867098808288574,
|
| 383 |
+
"eval_runtime": 108.873,
|
| 384 |
+
"eval_samples_per_second": 1.552,
|
| 385 |
+
"eval_steps_per_second": 0.395,
|
| 386 |
+
"step": 270
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.53,
|
| 390 |
+
"learning_rate": 0.00017244252047910892,
|
| 391 |
+
"loss": 1.119,
|
| 392 |
+
"step": 280
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.53,
|
| 396 |
+
"eval_loss": 1.1867098808288574,
|
| 397 |
+
"eval_runtime": 108.5863,
|
| 398 |
+
"eval_samples_per_second": 1.556,
|
| 399 |
+
"eval_steps_per_second": 0.396,
|
| 400 |
+
"step": 280
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.59,
|
| 404 |
+
"learning_rate": 0.00017012367842724887,
|
| 405 |
+
"loss": 1.1399,
|
| 406 |
+
"step": 290
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.59,
|
| 410 |
+
"eval_loss": 1.1867098808288574,
|
| 411 |
+
"eval_runtime": 108.7422,
|
| 412 |
+
"eval_samples_per_second": 1.554,
|
| 413 |
+
"eval_steps_per_second": 0.395,
|
| 414 |
+
"step": 290
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.64,
|
| 418 |
+
"learning_rate": 0.00016772815716257412,
|
| 419 |
+
"loss": 1.0744,
|
| 420 |
+
"step": 300
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.64,
|
| 424 |
+
"eval_loss": 1.1867098808288574,
|
| 425 |
+
"eval_runtime": 108.7961,
|
| 426 |
+
"eval_samples_per_second": 1.553,
|
| 427 |
+
"eval_steps_per_second": 0.395,
|
| 428 |
+
"step": 300
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.7,
|
| 432 |
+
"learning_rate": 0.00016525857615241687,
|
| 433 |
+
"loss": 1.0797,
|
| 434 |
+
"step": 310
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.7,
|
| 438 |
+
"eval_loss": 1.1867098808288574,
|
| 439 |
+
"eval_runtime": 108.4529,
|
| 440 |
+
"eval_samples_per_second": 1.558,
|
| 441 |
+
"eval_steps_per_second": 0.396,
|
| 442 |
+
"step": 310
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.75,
|
| 446 |
+
"learning_rate": 0.0001627176358473537,
|
| 447 |
+
"loss": 1.1281,
|
| 448 |
+
"step": 320
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.75,
|
| 452 |
+
"eval_loss": 1.1867098808288574,
|
| 453 |
+
"eval_runtime": 108.354,
|
| 454 |
+
"eval_samples_per_second": 1.56,
|
| 455 |
+
"eval_steps_per_second": 0.397,
|
| 456 |
+
"step": 320
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.81,
|
| 460 |
+
"learning_rate": 0.00016010811472830252,
|
| 461 |
+
"loss": 1.073,
|
| 462 |
+
"step": 330
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.81,
|
| 466 |
+
"eval_loss": 1.1867098808288574,
|
| 467 |
+
"eval_runtime": 108.3772,
|
| 468 |
+
"eval_samples_per_second": 1.559,
|
| 469 |
+
"eval_steps_per_second": 0.397,
|
| 470 |
+
"step": 330
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.86,
|
| 474 |
+
"learning_rate": 0.00015743286626829437,
|
| 475 |
+
"loss": 1.1053,
|
| 476 |
+
"step": 340
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.86,
|
| 480 |
+
"eval_loss": 1.1867098808288574,
|
| 481 |
+
"eval_runtime": 108.3166,
|
| 482 |
+
"eval_samples_per_second": 1.56,
|
| 483 |
+
"eval_steps_per_second": 0.397,
|
| 484 |
+
"step": 340
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.92,
|
| 488 |
+
"learning_rate": 0.00015469481581224272,
|
| 489 |
+
"loss": 1.1402,
|
| 490 |
+
"step": 350
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.92,
|
| 494 |
+
"eval_loss": 1.1867098808288574,
|
| 495 |
+
"eval_runtime": 108.4029,
|
| 496 |
+
"eval_samples_per_second": 1.559,
|
| 497 |
+
"eval_steps_per_second": 0.397,
|
| 498 |
+
"step": 350
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.97,
|
| 502 |
+
"learning_rate": 0.00015189695737812152,
|
| 503 |
+
"loss": 1.1627,
|
| 504 |
+
"step": 360
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.97,
|
| 508 |
+
"eval_loss": 1.1867098808288574,
|
| 509 |
+
"eval_runtime": 108.4859,
|
| 510 |
+
"eval_samples_per_second": 1.558,
|
| 511 |
+
"eval_steps_per_second": 0.396,
|
| 512 |
+
"step": 360
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.03,
|
| 516 |
+
"learning_rate": 0.00014904235038305083,
|
| 517 |
+
"loss": 1.1064,
|
| 518 |
+
"step": 370
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.03,
|
| 522 |
+
"eval_loss": 1.1901580095291138,
|
| 523 |
+
"eval_runtime": 108.5309,
|
| 524 |
+
"eval_samples_per_second": 1.557,
|
| 525 |
+
"eval_steps_per_second": 0.396,
|
| 526 |
+
"step": 370
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.08,
|
| 530 |
+
"learning_rate": 0.0001461341162978688,
|
| 531 |
+
"loss": 1.0264,
|
| 532 |
+
"step": 380
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.08,
|
| 536 |
+
"eval_loss": 1.187896966934204,
|
| 537 |
+
"eval_runtime": 108.3764,
|
| 538 |
+
"eval_samples_per_second": 1.559,
|
| 539 |
+
"eval_steps_per_second": 0.397,
|
| 540 |
+
"step": 380
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.14,
|
| 544 |
+
"learning_rate": 0.00014317543523384928,
|
| 545 |
+
"loss": 1.1384,
|
| 546 |
+
"step": 390
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.14,
|
| 550 |
+
"eval_loss": 1.1920827627182007,
|
| 551 |
+
"eval_runtime": 108.625,
|
| 552 |
+
"eval_samples_per_second": 1.556,
|
| 553 |
+
"eval_steps_per_second": 0.396,
|
| 554 |
+
"step": 390
|
| 555 |
+
}
|
| 556 |
+
],
|
| 557 |
+
"max_steps": 1000,
|
| 558 |
+
"num_train_epochs": 6,
|
| 559 |
+
"total_flos": 6.601561671204864e+16,
|
| 560 |
+
"trial_name": null,
|
| 561 |
+
"trial_params": null
|
| 562 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa02f3fc73177b98e0b1efb1438bf2dad6a6bccb54f32f1374095d094b7d0574
|
| 3 |
+
size 3899
|