End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +609 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-32B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: SWE-BENCH-433-set-claude-3in1-localization-with-reasoning_3in1-32b-433
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# SWE-BENCH-433-set-claude-3in1-localization-with-reasoning_3in1-32b-433
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-32B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: SWE-BENCH-433-set-claude-3in1-localization-with-reasoning_3in1-32b-433
|
|
|
|
| 16 |
|
| 17 |
# SWE-BENCH-433-set-claude-3in1-localization-with-reasoning_3in1-32b-433
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) on the SWE-BENCH-433-set-claude-3in1-localization-with-reasoning dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9230769230769234,
|
| 3 |
+
"total_flos": 1.1553561244178842e+17,
|
| 4 |
+
"train_loss": 0.6321279969480302,
|
| 5 |
+
"train_runtime": 35839.4231,
|
| 6 |
+
"train_samples_per_second": 0.109,
|
| 7 |
+
"train_steps_per_second": 0.002
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9230769230769234,
|
| 3 |
+
"total_flos": 1.1553561244178842e+17,
|
| 4 |
+
"train_loss": 0.6321279969480302,
|
| 5 |
+
"train_runtime": 35839.4231,
|
| 6 |
+
"train_samples_per_second": 0.109,
|
| 7 |
+
"train_steps_per_second": 0.002
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,609 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9230769230769234,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 81,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.036923076923076927,
|
| 13 |
+
"grad_norm": 0.21681749820709229,
|
| 14 |
+
"learning_rate": 1.111111111111111e-06,
|
| 15 |
+
"loss": 0.9664,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07384615384615385,
|
| 20 |
+
"grad_norm": 0.20581862330436707,
|
| 21 |
+
"learning_rate": 2.222222222222222e-06,
|
| 22 |
+
"loss": 1.0015,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11076923076923077,
|
| 27 |
+
"grad_norm": 0.20424745976924896,
|
| 28 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 29 |
+
"loss": 0.9708,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1476923076923077,
|
| 34 |
+
"grad_norm": 0.1970846801996231,
|
| 35 |
+
"learning_rate": 4.444444444444444e-06,
|
| 36 |
+
"loss": 0.9468,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.18461538461538463,
|
| 41 |
+
"grad_norm": 0.18317842483520508,
|
| 42 |
+
"learning_rate": 5.555555555555557e-06,
|
| 43 |
+
"loss": 0.9145,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22153846153846155,
|
| 48 |
+
"grad_norm": 0.14335869252681732,
|
| 49 |
+
"learning_rate": 6.666666666666667e-06,
|
| 50 |
+
"loss": 0.8394,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.25846153846153846,
|
| 55 |
+
"grad_norm": 0.10633772611618042,
|
| 56 |
+
"learning_rate": 7.77777777777778e-06,
|
| 57 |
+
"loss": 0.8204,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2953846153846154,
|
| 62 |
+
"grad_norm": 0.10130001604557037,
|
| 63 |
+
"learning_rate": 8.888888888888888e-06,
|
| 64 |
+
"loss": 0.8514,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3323076923076923,
|
| 69 |
+
"grad_norm": 0.09353858977556229,
|
| 70 |
+
"learning_rate": 1e-05,
|
| 71 |
+
"loss": 0.8185,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.36923076923076925,
|
| 76 |
+
"grad_norm": 0.12077067047357559,
|
| 77 |
+
"learning_rate": 9.99524110790929e-06,
|
| 78 |
+
"loss": 0.7809,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.40615384615384614,
|
| 83 |
+
"grad_norm": 0.12294641882181168,
|
| 84 |
+
"learning_rate": 9.980973490458728e-06,
|
| 85 |
+
"loss": 0.784,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4430769230769231,
|
| 90 |
+
"grad_norm": 0.11815817654132843,
|
| 91 |
+
"learning_rate": 9.957224306869053e-06,
|
| 92 |
+
"loss": 0.8003,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.48,
|
| 97 |
+
"grad_norm": 0.10775472223758698,
|
| 98 |
+
"learning_rate": 9.924038765061042e-06,
|
| 99 |
+
"loss": 0.733,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5169230769230769,
|
| 104 |
+
"grad_norm": 0.0963093712925911,
|
| 105 |
+
"learning_rate": 9.881480035599667e-06,
|
| 106 |
+
"loss": 0.7513,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5538461538461539,
|
| 111 |
+
"grad_norm": 0.09446723014116287,
|
| 112 |
+
"learning_rate": 9.829629131445342e-06,
|
| 113 |
+
"loss": 0.7309,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5907692307692308,
|
| 118 |
+
"grad_norm": 0.09027356654405594,
|
| 119 |
+
"learning_rate": 9.768584753741134e-06,
|
| 120 |
+
"loss": 0.7399,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6276923076923077,
|
| 125 |
+
"grad_norm": 0.07244273275136948,
|
| 126 |
+
"learning_rate": 9.698463103929542e-06,
|
| 127 |
+
"loss": 0.7074,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6646153846153846,
|
| 132 |
+
"grad_norm": 0.06840907782316208,
|
| 133 |
+
"learning_rate": 9.619397662556434e-06,
|
| 134 |
+
"loss": 0.7126,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7015384615384616,
|
| 139 |
+
"grad_norm": 0.06375812739133835,
|
| 140 |
+
"learning_rate": 9.531538935183252e-06,
|
| 141 |
+
"loss": 0.7005,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7384615384615385,
|
| 146 |
+
"grad_norm": 0.061204273253679276,
|
| 147 |
+
"learning_rate": 9.43505416589111e-06,
|
| 148 |
+
"loss": 0.7,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7753846153846153,
|
| 153 |
+
"grad_norm": 0.060263749212026596,
|
| 154 |
+
"learning_rate": 9.330127018922195e-06,
|
| 155 |
+
"loss": 0.6898,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8123076923076923,
|
| 160 |
+
"grad_norm": 0.06793916970491409,
|
| 161 |
+
"learning_rate": 9.21695722906443e-06,
|
| 162 |
+
"loss": 0.7244,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8492307692307692,
|
| 167 |
+
"grad_norm": 0.06098642200231552,
|
| 168 |
+
"learning_rate": 9.09576022144496e-06,
|
| 169 |
+
"loss": 0.7293,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8861538461538462,
|
| 174 |
+
"grad_norm": 0.056117311120033264,
|
| 175 |
+
"learning_rate": 8.966766701456177e-06,
|
| 176 |
+
"loss": 0.7052,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9230769230769231,
|
| 181 |
+
"grad_norm": 0.0726504996418953,
|
| 182 |
+
"learning_rate": 8.83022221559489e-06,
|
| 183 |
+
"loss": 0.6922,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.96,
|
| 188 |
+
"grad_norm": 0.0630849152803421,
|
| 189 |
+
"learning_rate": 8.68638668405062e-06,
|
| 190 |
+
"loss": 0.6911,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.9969230769230769,
|
| 195 |
+
"grad_norm": 0.058306001126766205,
|
| 196 |
+
"learning_rate": 8.535533905932739e-06,
|
| 197 |
+
"loss": 0.6993,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.0,
|
| 202 |
+
"grad_norm": 0.058306001126766205,
|
| 203 |
+
"learning_rate": 8.377951038078303e-06,
|
| 204 |
+
"loss": 0.6409,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.0369230769230768,
|
| 209 |
+
"grad_norm": 0.15839476883411407,
|
| 210 |
+
"learning_rate": 8.213938048432697e-06,
|
| 211 |
+
"loss": 0.6214,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.073846153846154,
|
| 216 |
+
"grad_norm": 0.0509660542011261,
|
| 217 |
+
"learning_rate": 8.043807145043604e-06,
|
| 218 |
+
"loss": 0.6381,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.1107692307692307,
|
| 223 |
+
"grad_norm": 0.06922844797372818,
|
| 224 |
+
"learning_rate": 7.86788218175523e-06,
|
| 225 |
+
"loss": 0.6115,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.1476923076923078,
|
| 230 |
+
"grad_norm": 0.05472060292959213,
|
| 231 |
+
"learning_rate": 7.686498041734121e-06,
|
| 232 |
+
"loss": 0.6063,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.1846153846153846,
|
| 237 |
+
"grad_norm": 0.045574579387903214,
|
| 238 |
+
"learning_rate": 7.500000000000001e-06,
|
| 239 |
+
"loss": 0.6368,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.2215384615384615,
|
| 244 |
+
"grad_norm": 0.046831291168928146,
|
| 245 |
+
"learning_rate": 7.308743066175172e-06,
|
| 246 |
+
"loss": 0.5691,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.2584615384615385,
|
| 251 |
+
"grad_norm": 0.06061406806111336,
|
| 252 |
+
"learning_rate": 7.113091308703498e-06,
|
| 253 |
+
"loss": 0.6092,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.2953846153846154,
|
| 258 |
+
"grad_norm": 0.047307711094617844,
|
| 259 |
+
"learning_rate": 6.913417161825449e-06,
|
| 260 |
+
"loss": 0.5908,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.3323076923076922,
|
| 265 |
+
"grad_norm": 0.045886699110269547,
|
| 266 |
+
"learning_rate": 6.710100716628345e-06,
|
| 267 |
+
"loss": 0.556,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.3692307692307693,
|
| 272 |
+
"grad_norm": 0.04732011258602142,
|
| 273 |
+
"learning_rate": 6.503528997521365e-06,
|
| 274 |
+
"loss": 0.5791,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.406153846153846,
|
| 279 |
+
"grad_norm": 0.046997807919979095,
|
| 280 |
+
"learning_rate": 6.294095225512604e-06,
|
| 281 |
+
"loss": 0.5807,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.4430769230769231,
|
| 286 |
+
"grad_norm": 0.04648653045296669,
|
| 287 |
+
"learning_rate": 6.0821980696905145e-06,
|
| 288 |
+
"loss": 0.5639,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.48,
|
| 293 |
+
"grad_norm": 0.04808522015810013,
|
| 294 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 295 |
+
"loss": 0.5761,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.516923076923077,
|
| 300 |
+
"grad_norm": 0.05137162283062935,
|
| 301 |
+
"learning_rate": 5.65263096110026e-06,
|
| 302 |
+
"loss": 0.6208,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.5538461538461539,
|
| 307 |
+
"grad_norm": 0.045391231775283813,
|
| 308 |
+
"learning_rate": 5.435778713738292e-06,
|
| 309 |
+
"loss": 0.5752,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.5907692307692307,
|
| 314 |
+
"grad_norm": 0.0464605912566185,
|
| 315 |
+
"learning_rate": 5.218096936826681e-06,
|
| 316 |
+
"loss": 0.5814,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.6276923076923078,
|
| 321 |
+
"grad_norm": 0.0495469830930233,
|
| 322 |
+
"learning_rate": 5e-06,
|
| 323 |
+
"loss": 0.5854,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.6646153846153846,
|
| 328 |
+
"grad_norm": 0.05236586183309555,
|
| 329 |
+
"learning_rate": 4.781903063173321e-06,
|
| 330 |
+
"loss": 0.5511,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.7015384615384614,
|
| 335 |
+
"grad_norm": 0.05185966193675995,
|
| 336 |
+
"learning_rate": 4.564221286261709e-06,
|
| 337 |
+
"loss": 0.6112,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.7384615384615385,
|
| 342 |
+
"grad_norm": 0.05059949681162834,
|
| 343 |
+
"learning_rate": 4.347369038899744e-06,
|
| 344 |
+
"loss": 0.5683,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.7753846153846153,
|
| 349 |
+
"grad_norm": 0.04454224929213524,
|
| 350 |
+
"learning_rate": 4.131759111665349e-06,
|
| 351 |
+
"loss": 0.546,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.8123076923076922,
|
| 356 |
+
"grad_norm": 0.05224916711449623,
|
| 357 |
+
"learning_rate": 3.917801930309486e-06,
|
| 358 |
+
"loss": 0.583,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.8492307692307692,
|
| 363 |
+
"grad_norm": 0.049219761043787,
|
| 364 |
+
"learning_rate": 3.705904774487396e-06,
|
| 365 |
+
"loss": 0.5812,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.8861538461538463,
|
| 370 |
+
"grad_norm": 0.05097327381372452,
|
| 371 |
+
"learning_rate": 3.4964710024786354e-06,
|
| 372 |
+
"loss": 0.557,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.9230769230769231,
|
| 377 |
+
"grad_norm": 0.08201055973768234,
|
| 378 |
+
"learning_rate": 3.289899283371657e-06,
|
| 379 |
+
"loss": 0.5674,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.96,
|
| 384 |
+
"grad_norm": 0.04776069521903992,
|
| 385 |
+
"learning_rate": 3.0865828381745515e-06,
|
| 386 |
+
"loss": 0.566,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.996923076923077,
|
| 391 |
+
"grad_norm": 0.059803545475006104,
|
| 392 |
+
"learning_rate": 2.886908691296504e-06,
|
| 393 |
+
"loss": 0.5868,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.0,
|
| 398 |
+
"grad_norm": 0.059803545475006104,
|
| 399 |
+
"learning_rate": 2.6912569338248317e-06,
|
| 400 |
+
"loss": 0.5562,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.036923076923077,
|
| 405 |
+
"grad_norm": 0.15980705618858337,
|
| 406 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 407 |
+
"loss": 0.5361,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.0738461538461537,
|
| 412 |
+
"grad_norm": 0.060454562306404114,
|
| 413 |
+
"learning_rate": 2.3135019582658803e-06,
|
| 414 |
+
"loss": 0.5284,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.1107692307692307,
|
| 419 |
+
"grad_norm": 0.04204780235886574,
|
| 420 |
+
"learning_rate": 2.132117818244771e-06,
|
| 421 |
+
"loss": 0.4904,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.147692307692308,
|
| 426 |
+
"grad_norm": 0.04754894971847534,
|
| 427 |
+
"learning_rate": 1.956192854956397e-06,
|
| 428 |
+
"loss": 0.5382,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.184615384615385,
|
| 433 |
+
"grad_norm": 0.04658404365181923,
|
| 434 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 435 |
+
"loss": 0.4837,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.2215384615384615,
|
| 440 |
+
"grad_norm": 0.04303783178329468,
|
| 441 |
+
"learning_rate": 1.6220489619216988e-06,
|
| 442 |
+
"loss": 0.513,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.2584615384615385,
|
| 447 |
+
"grad_norm": 0.0559069849550724,
|
| 448 |
+
"learning_rate": 1.4644660940672628e-06,
|
| 449 |
+
"loss": 0.4912,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.2953846153846156,
|
| 454 |
+
"grad_norm": 0.04260304570198059,
|
| 455 |
+
"learning_rate": 1.3136133159493803e-06,
|
| 456 |
+
"loss": 0.5214,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.332307692307692,
|
| 461 |
+
"grad_norm": 0.04139008745551109,
|
| 462 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 463 |
+
"loss": 0.5058,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.3692307692307693,
|
| 468 |
+
"grad_norm": 0.04521390423178673,
|
| 469 |
+
"learning_rate": 1.0332332985438248e-06,
|
| 470 |
+
"loss": 0.5418,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.4061538461538463,
|
| 475 |
+
"grad_norm": 0.04530893266201019,
|
| 476 |
+
"learning_rate": 9.042397785550405e-07,
|
| 477 |
+
"loss": 0.5333,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.443076923076923,
|
| 482 |
+
"grad_norm": 0.045508645474910736,
|
| 483 |
+
"learning_rate": 7.830427709355726e-07,
|
| 484 |
+
"loss": 0.5275,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.48,
|
| 489 |
+
"grad_norm": 0.06673616915941238,
|
| 490 |
+
"learning_rate": 6.698729810778065e-07,
|
| 491 |
+
"loss": 0.5208,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.516923076923077,
|
| 496 |
+
"grad_norm": 0.04433636739850044,
|
| 497 |
+
"learning_rate": 5.649458341088915e-07,
|
| 498 |
+
"loss": 0.5366,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.5538461538461537,
|
| 503 |
+
"grad_norm": 0.04471476748585701,
|
| 504 |
+
"learning_rate": 4.6846106481675035e-07,
|
| 505 |
+
"loss": 0.5235,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.5907692307692307,
|
| 510 |
+
"grad_norm": 0.041670531034469604,
|
| 511 |
+
"learning_rate": 3.8060233744356634e-07,
|
| 512 |
+
"loss": 0.5277,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.6276923076923078,
|
| 517 |
+
"grad_norm": 0.06000512093305588,
|
| 518 |
+
"learning_rate": 3.015368960704584e-07,
|
| 519 |
+
"loss": 0.5477,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.6646153846153844,
|
| 524 |
+
"grad_norm": 0.045167651027441025,
|
| 525 |
+
"learning_rate": 2.314152462588659e-07,
|
| 526 |
+
"loss": 0.5091,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.7015384615384614,
|
| 531 |
+
"grad_norm": 0.048195917159318924,
|
| 532 |
+
"learning_rate": 1.7037086855465902e-07,
|
| 533 |
+
"loss": 0.5306,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.7384615384615385,
|
| 538 |
+
"grad_norm": 0.04413783550262451,
|
| 539 |
+
"learning_rate": 1.185199644003332e-07,
|
| 540 |
+
"loss": 0.5022,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.775384615384615,
|
| 545 |
+
"grad_norm": 0.04231860861182213,
|
| 546 |
+
"learning_rate": 7.59612349389599e-08,
|
| 547 |
+
"loss": 0.5032,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.812307692307692,
|
| 552 |
+
"grad_norm": 0.052823107689619064,
|
| 553 |
+
"learning_rate": 4.2775693130948094e-08,
|
| 554 |
+
"loss": 0.5188,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.8492307692307692,
|
| 559 |
+
"grad_norm": 0.04266749322414398,
|
| 560 |
+
"learning_rate": 1.9026509541272276e-08,
|
| 561 |
+
"loss": 0.5163,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.8861538461538463,
|
| 566 |
+
"grad_norm": 0.04372300207614899,
|
| 567 |
+
"learning_rate": 4.758892090711009e-09,
|
| 568 |
+
"loss": 0.5054,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.9230769230769234,
|
| 573 |
+
"grad_norm": 0.04277525097131729,
|
| 574 |
+
"learning_rate": 0.0,
|
| 575 |
+
"loss": 0.531,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.9230769230769234,
|
| 580 |
+
"step": 81,
|
| 581 |
+
"total_flos": 1.1553561244178842e+17,
|
| 582 |
+
"train_loss": 0.6321279969480302,
|
| 583 |
+
"train_runtime": 35839.4231,
|
| 584 |
+
"train_samples_per_second": 0.109,
|
| 585 |
+
"train_steps_per_second": 0.002
|
| 586 |
+
}
|
| 587 |
+
],
|
| 588 |
+
"logging_steps": 1,
|
| 589 |
+
"max_steps": 81,
|
| 590 |
+
"num_input_tokens_seen": 0,
|
| 591 |
+
"num_train_epochs": 3,
|
| 592 |
+
"save_steps": 200,
|
| 593 |
+
"stateful_callbacks": {
|
| 594 |
+
"TrainerControl": {
|
| 595 |
+
"args": {
|
| 596 |
+
"should_epoch_stop": false,
|
| 597 |
+
"should_evaluate": false,
|
| 598 |
+
"should_log": false,
|
| 599 |
+
"should_save": true,
|
| 600 |
+
"should_training_stop": true
|
| 601 |
+
},
|
| 602 |
+
"attributes": {}
|
| 603 |
+
}
|
| 604 |
+
},
|
| 605 |
+
"total_flos": 1.1553561244178842e+17,
|
| 606 |
+
"train_batch_size": 1,
|
| 607 |
+
"trial_name": null,
|
| 608 |
+
"trial_params": null
|
| 609 |
+
}
|
training_loss.png
ADDED
|