End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +567 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: seed_code_multiple_samples_gpt_verification_scale_up_1K
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# seed_code_multiple_samples_gpt_verification_scale_up_1K
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: seed_code_multiple_samples_gpt_verification_scale_up_1K
|
|
|
|
| 16 |
|
| 17 |
# seed_code_multiple_samples_gpt_verification_scale_up_1K
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/seed_code_multiple_samples_gpt_verification_scale_up_1K dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.8938906752411575,
|
| 3 |
+
"total_flos": 66441907232768.0,
|
| 4 |
+
"train_loss": 0.9123331260681152,
|
| 5 |
+
"train_runtime": 3973.9028,
|
| 6 |
+
"train_samples_per_second": 1.875,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.8938906752411575,
|
| 3 |
+
"total_flos": 66441907232768.0,
|
| 4 |
+
"train_loss": 0.9123331260681152,
|
| 5 |
+
"train_runtime": 3973.9028,
|
| 6 |
+
"train_samples_per_second": 1.875,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,567 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.8938906752411575,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 75,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03858520900321544,
|
| 13 |
+
"grad_norm": 6.827114582061768,
|
| 14 |
+
"learning_rate": 1.25e-06,
|
| 15 |
+
"loss": 1.2682,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07717041800643087,
|
| 20 |
+
"grad_norm": 6.703758239746094,
|
| 21 |
+
"learning_rate": 2.5e-06,
|
| 22 |
+
"loss": 1.2274,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1157556270096463,
|
| 27 |
+
"grad_norm": 6.74079704284668,
|
| 28 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 29 |
+
"loss": 1.2669,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15434083601286175,
|
| 34 |
+
"grad_norm": 5.965632438659668,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 1.2216,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19292604501607716,
|
| 41 |
+
"grad_norm": 4.468871593475342,
|
| 42 |
+
"learning_rate": 6.25e-06,
|
| 43 |
+
"loss": 1.1837,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2315112540192926,
|
| 48 |
+
"grad_norm": 2.849684715270996,
|
| 49 |
+
"learning_rate": 7.500000000000001e-06,
|
| 50 |
+
"loss": 1.1514,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.27009646302250806,
|
| 55 |
+
"grad_norm": 5.281802177429199,
|
| 56 |
+
"learning_rate": 8.750000000000001e-06,
|
| 57 |
+
"loss": 1.1846,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3086816720257235,
|
| 62 |
+
"grad_norm": 5.24518346786499,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 1.1349,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.34726688102893893,
|
| 69 |
+
"grad_norm": 4.561065673828125,
|
| 70 |
+
"learning_rate": 9.994504457428557e-06,
|
| 71 |
+
"loss": 1.0946,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3858520900321543,
|
| 76 |
+
"grad_norm": 4.529706001281738,
|
| 77 |
+
"learning_rate": 9.978029910109491e-06,
|
| 78 |
+
"loss": 1.0995,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.42443729903536975,
|
| 83 |
+
"grad_norm": 3.045126438140869,
|
| 84 |
+
"learning_rate": 9.950612572673255e-06,
|
| 85 |
+
"loss": 1.0659,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4630225080385852,
|
| 90 |
+
"grad_norm": 2.239044666290283,
|
| 91 |
+
"learning_rate": 9.91231271437788e-06,
|
| 92 |
+
"loss": 1.018,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5016077170418006,
|
| 97 |
+
"grad_norm": 2.176582098007202,
|
| 98 |
+
"learning_rate": 9.863214526624065e-06,
|
| 99 |
+
"loss": 1.0193,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5401929260450161,
|
| 104 |
+
"grad_norm": 1.5574040412902832,
|
| 105 |
+
"learning_rate": 9.803425937884202e-06,
|
| 106 |
+
"loss": 0.9824,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5787781350482315,
|
| 111 |
+
"grad_norm": 1.3071755170822144,
|
| 112 |
+
"learning_rate": 9.733078376452172e-06,
|
| 113 |
+
"loss": 0.9843,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.617363344051447,
|
| 118 |
+
"grad_norm": 1.1668739318847656,
|
| 119 |
+
"learning_rate": 9.652326481535434e-06,
|
| 120 |
+
"loss": 0.9856,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6559485530546624,
|
| 125 |
+
"grad_norm": 1.3676371574401855,
|
| 126 |
+
"learning_rate": 9.561347763324484e-06,
|
| 127 |
+
"loss": 0.9434,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6945337620578779,
|
| 132 |
+
"grad_norm": 1.3451117277145386,
|
| 133 |
+
"learning_rate": 9.460342212786933e-06,
|
| 134 |
+
"loss": 0.9642,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7331189710610932,
|
| 139 |
+
"grad_norm": 0.9681344032287598,
|
| 140 |
+
"learning_rate": 9.349531862043952e-06,
|
| 141 |
+
"loss": 0.9553,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7717041800643086,
|
| 146 |
+
"grad_norm": 1.0520753860473633,
|
| 147 |
+
"learning_rate": 9.229160296295488e-06,
|
| 148 |
+
"loss": 0.9128,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8102893890675241,
|
| 153 |
+
"grad_norm": 0.9027125239372253,
|
| 154 |
+
"learning_rate": 9.099492118367123e-06,
|
| 155 |
+
"loss": 0.9291,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8488745980707395,
|
| 160 |
+
"grad_norm": 0.8002101182937622,
|
| 161 |
+
"learning_rate": 8.960812367055646e-06,
|
| 162 |
+
"loss": 0.9195,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.887459807073955,
|
| 167 |
+
"grad_norm": 0.787247896194458,
|
| 168 |
+
"learning_rate": 8.81342589055191e-06,
|
| 169 |
+
"loss": 0.9461,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9260450160771704,
|
| 174 |
+
"grad_norm": 0.7884970903396606,
|
| 175 |
+
"learning_rate": 8.657656676318346e-06,
|
| 176 |
+
"loss": 0.9381,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9646302250803859,
|
| 181 |
+
"grad_norm": 0.6913259625434875,
|
| 182 |
+
"learning_rate": 8.49384713889421e-06,
|
| 183 |
+
"loss": 0.8714,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0032154340836013,
|
| 188 |
+
"grad_norm": 0.7232531309127808,
|
| 189 |
+
"learning_rate": 8.32235736719411e-06,
|
| 190 |
+
"loss": 0.9519,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0418006430868167,
|
| 195 |
+
"grad_norm": 0.7492582201957703,
|
| 196 |
+
"learning_rate": 8.143564332954426e-06,
|
| 197 |
+
"loss": 0.8788,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.0803858520900322,
|
| 202 |
+
"grad_norm": 0.6388415694236755,
|
| 203 |
+
"learning_rate": 7.957861062067614e-06,
|
| 204 |
+
"loss": 0.9166,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.1189710610932475,
|
| 209 |
+
"grad_norm": 0.6874092817306519,
|
| 210 |
+
"learning_rate": 7.765655770625997e-06,
|
| 211 |
+
"loss": 0.8655,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.157556270096463,
|
| 216 |
+
"grad_norm": 0.6590151190757751,
|
| 217 |
+
"learning_rate": 7.56737096757421e-06,
|
| 218 |
+
"loss": 0.8655,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.1961414790996785,
|
| 223 |
+
"grad_norm": 0.6995782852172852,
|
| 224 |
+
"learning_rate": 7.363442525942827e-06,
|
| 225 |
+
"loss": 0.8524,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.234726688102894,
|
| 230 |
+
"grad_norm": 0.8694888949394226,
|
| 231 |
+
"learning_rate": 7.1543187247048525e-06,
|
| 232 |
+
"loss": 0.9178,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2733118971061093,
|
| 237 |
+
"grad_norm": 0.72708660364151,
|
| 238 |
+
"learning_rate": 6.9404592633612486e-06,
|
| 239 |
+
"loss": 0.8379,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.3118971061093248,
|
| 244 |
+
"grad_norm": 0.6599162220954895,
|
| 245 |
+
"learning_rate": 6.722334251421665e-06,
|
| 246 |
+
"loss": 0.9048,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.3504823151125402,
|
| 251 |
+
"grad_norm": 0.7191936373710632,
|
| 252 |
+
"learning_rate": 6.500423175001705e-06,
|
| 253 |
+
"loss": 0.8702,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.3890675241157555,
|
| 258 |
+
"grad_norm": 0.7617672085762024,
|
| 259 |
+
"learning_rate": 6.275213842808383e-06,
|
| 260 |
+
"loss": 0.875,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.427652733118971,
|
| 265 |
+
"grad_norm": 0.5834156274795532,
|
| 266 |
+
"learning_rate": 6.047201313830724e-06,
|
| 267 |
+
"loss": 0.855,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.4662379421221865,
|
| 272 |
+
"grad_norm": 0.6282949447631836,
|
| 273 |
+
"learning_rate": 5.816886809092651e-06,
|
| 274 |
+
"loss": 0.8703,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.504823151125402,
|
| 279 |
+
"grad_norm": 0.6048595905303955,
|
| 280 |
+
"learning_rate": 5.584776609860414e-06,
|
| 281 |
+
"loss": 0.8615,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.5434083601286175,
|
| 286 |
+
"grad_norm": 0.5948866605758667,
|
| 287 |
+
"learning_rate": 5.351380944726465e-06,
|
| 288 |
+
"loss": 0.8744,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.5819935691318328,
|
| 293 |
+
"grad_norm": 0.5789873600006104,
|
| 294 |
+
"learning_rate": 5.117212868016303e-06,
|
| 295 |
+
"loss": 0.8056,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6205787781350482,
|
| 300 |
+
"grad_norm": 0.5074349045753479,
|
| 301 |
+
"learning_rate": 4.882787131983698e-06,
|
| 302 |
+
"loss": 0.8465,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.6591639871382635,
|
| 307 |
+
"grad_norm": 0.5655978322029114,
|
| 308 |
+
"learning_rate": 4.6486190552735375e-06,
|
| 309 |
+
"loss": 0.9188,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.697749196141479,
|
| 314 |
+
"grad_norm": 0.5455473065376282,
|
| 315 |
+
"learning_rate": 4.415223390139588e-06,
|
| 316 |
+
"loss": 0.8093,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.7363344051446945,
|
| 321 |
+
"grad_norm": 0.6158671379089355,
|
| 322 |
+
"learning_rate": 4.183113190907349e-06,
|
| 323 |
+
"loss": 0.9393,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.77491961414791,
|
| 328 |
+
"grad_norm": 0.5077454447746277,
|
| 329 |
+
"learning_rate": 3.952798686169279e-06,
|
| 330 |
+
"loss": 0.8114,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.8135048231511255,
|
| 335 |
+
"grad_norm": 0.47759971022605896,
|
| 336 |
+
"learning_rate": 3.7247861571916183e-06,
|
| 337 |
+
"loss": 0.8585,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.852090032154341,
|
| 342 |
+
"grad_norm": 0.4739689230918884,
|
| 343 |
+
"learning_rate": 3.4995768249982975e-06,
|
| 344 |
+
"loss": 0.8259,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.8906752411575563,
|
| 349 |
+
"grad_norm": 0.5395683646202087,
|
| 350 |
+
"learning_rate": 3.2776657485783357e-06,
|
| 351 |
+
"loss": 0.8673,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.9292604501607717,
|
| 356 |
+
"grad_norm": 0.5374310612678528,
|
| 357 |
+
"learning_rate": 3.059540736638751e-06,
|
| 358 |
+
"loss": 0.7906,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.967845659163987,
|
| 363 |
+
"grad_norm": 0.4914711117744446,
|
| 364 |
+
"learning_rate": 2.8456812752951483e-06,
|
| 365 |
+
"loss": 0.9054,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.0064308681672025,
|
| 370 |
+
"grad_norm": 0.521967887878418,
|
| 371 |
+
"learning_rate": 2.636557474057173e-06,
|
| 372 |
+
"loss": 0.8763,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.045016077170418,
|
| 377 |
+
"grad_norm": 0.4540090262889862,
|
| 378 |
+
"learning_rate": 2.4326290324257896e-06,
|
| 379 |
+
"loss": 0.8473,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.0836012861736335,
|
| 384 |
+
"grad_norm": 0.4512139856815338,
|
| 385 |
+
"learning_rate": 2.234344229374003e-06,
|
| 386 |
+
"loss": 0.7919,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.122186495176849,
|
| 391 |
+
"grad_norm": 0.5352345705032349,
|
| 392 |
+
"learning_rate": 2.042138937932388e-06,
|
| 393 |
+
"loss": 0.8196,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.1607717041800645,
|
| 398 |
+
"grad_norm": 0.44427061080932617,
|
| 399 |
+
"learning_rate": 1.856435667045577e-06,
|
| 400 |
+
"loss": 0.7881,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.19935691318328,
|
| 405 |
+
"grad_norm": 0.5240706205368042,
|
| 406 |
+
"learning_rate": 1.677642632805892e-06,
|
| 407 |
+
"loss": 0.8631,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.237942122186495,
|
| 412 |
+
"grad_norm": 0.5195144414901733,
|
| 413 |
+
"learning_rate": 1.5061528611057917e-06,
|
| 414 |
+
"loss": 0.7746,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.2765273311897105,
|
| 419 |
+
"grad_norm": 0.43310004472732544,
|
| 420 |
+
"learning_rate": 1.3423433236816563e-06,
|
| 421 |
+
"loss": 0.8119,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.315112540192926,
|
| 426 |
+
"grad_norm": 0.4922521710395813,
|
| 427 |
+
"learning_rate": 1.186574109448091e-06,
|
| 428 |
+
"loss": 0.8375,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.3536977491961415,
|
| 433 |
+
"grad_norm": 0.4353758692741394,
|
| 434 |
+
"learning_rate": 1.0391876329443534e-06,
|
| 435 |
+
"loss": 0.7619,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.392282958199357,
|
| 440 |
+
"grad_norm": 0.4733580946922302,
|
| 441 |
+
"learning_rate": 9.005078816328772e-07,
|
| 442 |
+
"loss": 0.8132,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.4308681672025725,
|
| 447 |
+
"grad_norm": 0.43942683935165405,
|
| 448 |
+
"learning_rate": 7.708397037045129e-07,
|
| 449 |
+
"loss": 0.7784,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.469453376205788,
|
| 454 |
+
"grad_norm": 0.46390509605407715,
|
| 455 |
+
"learning_rate": 6.50468137956049e-07,
|
| 456 |
+
"loss": 0.8832,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.508038585209003,
|
| 461 |
+
"grad_norm": 0.44283559918403625,
|
| 462 |
+
"learning_rate": 5.396577872130676e-07,
|
| 463 |
+
"loss": 0.8102,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.5466237942122185,
|
| 468 |
+
"grad_norm": 0.4312247037887573,
|
| 469 |
+
"learning_rate": 4.386522366755169e-07,
|
| 470 |
+
"loss": 0.7881,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.585209003215434,
|
| 475 |
+
"grad_norm": 0.46290892362594604,
|
| 476 |
+
"learning_rate": 3.4767351846456744e-07,
|
| 477 |
+
"loss": 0.8807,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.6237942122186495,
|
| 482 |
+
"grad_norm": 0.44196000695228577,
|
| 483 |
+
"learning_rate": 2.669216235478295e-07,
|
| 484 |
+
"loss": 0.7756,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.662379421221865,
|
| 489 |
+
"grad_norm": 0.47514083981513977,
|
| 490 |
+
"learning_rate": 1.9657406211579966e-07,
|
| 491 |
+
"loss": 0.8685,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.7009646302250805,
|
| 496 |
+
"grad_norm": 0.4315619468688965,
|
| 497 |
+
"learning_rate": 1.3678547337593494e-07,
|
| 498 |
+
"loss": 0.7501,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.739549839228296,
|
| 503 |
+
"grad_norm": 0.4595395624637604,
|
| 504 |
+
"learning_rate": 8.768728562211948e-08,
|
| 505 |
+
"loss": 0.8121,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.778135048231511,
|
| 510 |
+
"grad_norm": 0.4295967221260071,
|
| 511 |
+
"learning_rate": 4.9387427326745287e-08,
|
| 512 |
+
"loss": 0.7776,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.816720257234727,
|
| 517 |
+
"grad_norm": 0.44801920652389526,
|
| 518 |
+
"learning_rate": 2.1970089890509527e-08,
|
| 519 |
+
"loss": 0.8149,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.855305466237942,
|
| 524 |
+
"grad_norm": 0.4446917474269867,
|
| 525 |
+
"learning_rate": 5.495542571443135e-09,
|
| 526 |
+
"loss": 0.8291,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.8938906752411575,
|
| 531 |
+
"grad_norm": 0.4660709500312805,
|
| 532 |
+
"learning_rate": 0.0,
|
| 533 |
+
"loss": 0.8268,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.8938906752411575,
|
| 538 |
+
"step": 75,
|
| 539 |
+
"total_flos": 66441907232768.0,
|
| 540 |
+
"train_loss": 0.9123331260681152,
|
| 541 |
+
"train_runtime": 3973.9028,
|
| 542 |
+
"train_samples_per_second": 1.875,
|
| 543 |
+
"train_steps_per_second": 0.019
|
| 544 |
+
}
|
| 545 |
+
],
|
| 546 |
+
"logging_steps": 1.0,
|
| 547 |
+
"max_steps": 75,
|
| 548 |
+
"num_input_tokens_seen": 0,
|
| 549 |
+
"num_train_epochs": 3,
|
| 550 |
+
"save_steps": 500,
|
| 551 |
+
"stateful_callbacks": {
|
| 552 |
+
"TrainerControl": {
|
| 553 |
+
"args": {
|
| 554 |
+
"should_epoch_stop": false,
|
| 555 |
+
"should_evaluate": false,
|
| 556 |
+
"should_log": false,
|
| 557 |
+
"should_save": true,
|
| 558 |
+
"should_training_stop": true
|
| 559 |
+
},
|
| 560 |
+
"attributes": {}
|
| 561 |
+
}
|
| 562 |
+
},
|
| 563 |
+
"total_flos": 66441907232768.0,
|
| 564 |
+
"train_batch_size": 1,
|
| 565 |
+
"trial_name": null,
|
| 566 |
+
"trial_params": null
|
| 567 |
+
}
|
training_loss.png
ADDED
|