Upload folder using huggingface_hub
Browse files- README.md +4 -107
- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- optimizer.pt +2 -2
- scheduler.pt +1 -1
- trainer_state.json +393 -393
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,11 +3,7 @@ base_model: meta-llama/Llama-2-7b-hf
|
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
| 6 |
-
# Model Card for
|
| 7 |
-
|
| 8 |
-
This is a LLaMA-2-7B model fine-tuned using FourierFT on alpaca dataset. Only K and V projections are set to be trainable.
|
| 9 |
-
|
| 10 |
-
|
| 11 |
|
| 12 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
|
|
@@ -81,7 +77,6 @@ Use the code below to get started with the model.
|
|
| 81 |
|
| 82 |
### Training Data
|
| 83 |
|
| 84 |
-
Alpaca
|
| 85 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 86 |
|
| 87 |
[More Information Needed]
|
|
@@ -97,25 +92,8 @@ Alpaca
|
|
| 97 |
|
| 98 |
#### Training Hyperparameters
|
| 99 |
|
| 100 |
-
- **Training regime:**
|
| 101 |
-
|
| 102 |
-
```
|
| 103 |
-
python fourierft-alpaca.py \
|
| 104 |
-
--warmup_ratio 0.06 \
|
| 105 |
-
--num_train_epochs 2 \
|
| 106 |
-
--seed 0 \
|
| 107 |
-
--per_device_train_batch_size 2 \
|
| 108 |
-
--gradient_accumulation_steps 32 \
|
| 109 |
-
--output_dir './results' \
|
| 110 |
-
--eval_strategy "epoch" \
|
| 111 |
-
--mixed_precision "bf16" \
|
| 112 |
-
--lr_scheduler_type "linear" \
|
| 113 |
-
--learning_rate 3e-4 \
|
| 114 |
-
--logging_steps 10 \
|
| 115 |
-
--report_to "none" \
|
| 116 |
-
--fourier_scale 512 \
|
| 117 |
-
--fourier_n_frequency 10000
|
| 118 |
-
```
|
| 119 |
#### Speeds, Sizes, Times [optional]
|
| 120 |
|
| 121 |
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
|
@@ -123,88 +101,7 @@ python fourierft-alpaca.py \
|
|
| 123 |
[More Information Needed]
|
| 124 |
|
| 125 |
## Evaluation
|
| 126 |
-
|
| 127 |
-
```
|
| 128 |
-
Average accuracy 0.280 - abstract_algebra
|
| 129 |
-
Average accuracy 0.474 - anatomy
|
| 130 |
-
Average accuracy 0.434 - astronomy
|
| 131 |
-
Average accuracy 0.490 - business_ethics
|
| 132 |
-
Average accuracy 0.491 - clinical_knowledge
|
| 133 |
-
Average accuracy 0.438 - college_biology
|
| 134 |
-
Average accuracy 0.330 - college_chemistry
|
| 135 |
-
Average accuracy 0.400 - college_computer_science
|
| 136 |
-
Average accuracy 0.350 - college_mathematics
|
| 137 |
-
Average accuracy 0.445 - college_medicine
|
| 138 |
-
Average accuracy 0.157 - college_physics
|
| 139 |
-
Average accuracy 0.550 - computer_security
|
| 140 |
-
Average accuracy 0.426 - conceptual_physics
|
| 141 |
-
Average accuracy 0.254 - econometrics
|
| 142 |
-
Average accuracy 0.503 - electrical_engineering
|
| 143 |
-
Average accuracy 0.312 - elementary_mathematics
|
| 144 |
-
Average accuracy 0.262 - formal_logic
|
| 145 |
-
Average accuracy 0.320 - global_facts
|
| 146 |
-
Average accuracy 0.500 - high_school_biology
|
| 147 |
-
Average accuracy 0.330 - high_school_chemistry
|
| 148 |
-
Average accuracy 0.420 - high_school_computer_science
|
| 149 |
-
Average accuracy 0.588 - high_school_european_history
|
| 150 |
-
Average accuracy 0.540 - high_school_geography
|
| 151 |
-
Average accuracy 0.663 - high_school_government_and_politics
|
| 152 |
-
Average accuracy 0.441 - high_school_macroeconomics
|
| 153 |
-
Average accuracy 0.326 - high_school_mathematics
|
| 154 |
-
Average accuracy 0.429 - high_school_microeconomics
|
| 155 |
-
Average accuracy 0.258 - high_school_physics
|
| 156 |
-
Average accuracy 0.622 - high_school_psychology
|
| 157 |
-
Average accuracy 0.306 - high_school_statistics
|
| 158 |
-
Average accuracy 0.588 - high_school_us_history
|
| 159 |
-
Average accuracy 0.624 - high_school_world_history
|
| 160 |
-
Average accuracy 0.570 - human_aging
|
| 161 |
-
Average accuracy 0.481 - human_sexuality
|
| 162 |
-
Average accuracy 0.628 - international_law
|
| 163 |
-
Average accuracy 0.528 - jurisprudence
|
| 164 |
-
Average accuracy 0.479 - logical_fallacies
|
| 165 |
-
Average accuracy 0.402 - machine_learning
|
| 166 |
-
Average accuracy 0.592 - management
|
| 167 |
-
Average accuracy 0.641 - marketing
|
| 168 |
-
Average accuracy 0.520 - medical_genetics
|
| 169 |
-
Average accuracy 0.621 - miscellaneous
|
| 170 |
-
Average accuracy 0.474 - moral_disputes
|
| 171 |
-
Average accuracy 0.241 - moral_scenarios
|
| 172 |
-
Average accuracy 0.484 - nutrition
|
| 173 |
-
Average accuracy 0.579 - philosophy
|
| 174 |
-
Average accuracy 0.485 - prehistory
|
| 175 |
-
Average accuracy 0.372 - professional_accounting
|
| 176 |
-
Average accuracy 0.345 - professional_law
|
| 177 |
-
Average accuracy 0.537 - professional_medicine
|
| 178 |
-
Average accuracy 0.428 - professional_psychology
|
| 179 |
-
Average accuracy 0.545 - public_relations
|
| 180 |
-
Average accuracy 0.514 - security_studies
|
| 181 |
-
Average accuracy 0.632 - sociology
|
| 182 |
-
Average accuracy 0.710 - us_foreign_policy
|
| 183 |
-
Average accuracy 0.470 - virology
|
| 184 |
-
Average accuracy 0.673 - world_religions
|
| 185 |
-
Average accuracy 0.315 - math
|
| 186 |
-
Average accuracy 0.501 - health
|
| 187 |
-
Average accuracy 0.345 - physics
|
| 188 |
-
Average accuracy 0.595 - business
|
| 189 |
-
Average accuracy 0.480 - biology
|
| 190 |
-
Average accuracy 0.330 - chemistry
|
| 191 |
-
Average accuracy 0.442 - computer science
|
| 192 |
-
Average accuracy 0.408 - economics
|
| 193 |
-
Average accuracy 0.503 - engineering
|
| 194 |
-
Average accuracy 0.391 - philosophy
|
| 195 |
-
Average accuracy 0.535 - other
|
| 196 |
-
Average accuracy 0.561 - history
|
| 197 |
-
Average accuracy 0.540 - geography
|
| 198 |
-
Average accuracy 0.594 - politics
|
| 199 |
-
Average accuracy 0.519 - psychology
|
| 200 |
-
Average accuracy 0.572 - culture
|
| 201 |
-
Average accuracy 0.375 - law
|
| 202 |
-
Average accuracy 0.374 - STEM
|
| 203 |
-
Average accuracy 0.419 - humanities
|
| 204 |
-
Average accuracy 0.515 - social sciences
|
| 205 |
-
Average accuracy 0.526 - other (business, health, misc.)
|
| 206 |
-
Average accuracy: 0.455
|
| 207 |
-
```
|
| 208 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 209 |
|
| 210 |
### Testing Data, Factors & Metrics
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
| 6 |
+
# Model Card for Model ID
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
|
|
|
|
| 77 |
|
| 78 |
### Training Data
|
| 79 |
|
|
|
|
| 80 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
|
| 82 |
[More Information Needed]
|
|
|
|
| 92 |
|
| 93 |
#### Training Hyperparameters
|
| 94 |
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 97 |
#### Speeds, Sizes, Times [optional]
|
| 98 |
|
| 99 |
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
|
|
|
| 101 |
[More Information Needed]
|
| 102 |
|
| 103 |
## Evaluation
|
| 104 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
|
| 107 |
### Testing Data, Factors & Metrics
|
adapter_config.json
CHANGED
|
@@ -9,15 +9,15 @@
|
|
| 9 |
"layers_pattern": null,
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"modules_to_save": null,
|
| 12 |
-
"n_frequency":
|
| 13 |
"n_frequency_pattern": {},
|
| 14 |
"peft_type": "FOURIERFT",
|
| 15 |
"random_loc_seed": 777,
|
| 16 |
"revision": null,
|
| 17 |
"scaling": 512.0,
|
| 18 |
"target_modules": [
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
],
|
| 22 |
"task_type": "CAUSAL_LM"
|
| 23 |
}
|
|
|
|
| 9 |
"layers_pattern": null,
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"modules_to_save": null,
|
| 12 |
+
"n_frequency": 100000,
|
| 13 |
"n_frequency_pattern": {},
|
| 14 |
"peft_type": "FOURIERFT",
|
| 15 |
"random_loc_seed": 777,
|
| 16 |
"revision": null,
|
| 17 |
"scaling": 512.0,
|
| 18 |
"target_modules": [
|
| 19 |
+
"v_proj",
|
| 20 |
+
"q_proj"
|
| 21 |
],
|
| 22 |
"task_type": "CAUSAL_LM"
|
| 23 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:507161a3f89ad75ea3966c069b78d88e570a4e1f7c4ad1a46566be6cc816af58
|
| 3 |
+
size 25608864
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a97188994f5cc07ad3d7ff2867bef896967ca6367687c302e4983343e578113a
|
| 3 |
+
size 51254010
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f401f38a09da5324949ad9c68ac0e2b02df016ef05210c0508136cfa8255b836
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -10,913 +10,913 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.015455950540958269,
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.030911901081916538,
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.04636785162287481,
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss":
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.061823802163833076,
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.07727975270479134,
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss":
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.09273570324574962,
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss":
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.10819165378670788,
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss":
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.12364760432766615,
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss":
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.1391035548686244,
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.1545595054095827,
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss":
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.17001545595054096,
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.18547140649149924,
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.2009273570324575,
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate": 0.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.21638330757341576,
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate": 0.
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.23183925811437403,
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.2472952086553323,
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate": 0.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.26275115919629055,
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.2782071097372488,
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.2936630602782071,
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate": 0.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.3091190108191654,
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate": 0.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.32457496136012365,
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 0.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.3400309119010819,
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate": 0.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.3554868624420402,
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 0.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.37094281298299847,
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.38639876352395675,
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate": 0.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.401854714064915,
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate": 0.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.41731066460587324,
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate": 0.
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.4327666151468315,
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate": 0.
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.4482225656877898,
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
-
"learning_rate": 0.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.46367851622874806,
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate": 0.
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.47913446676970634,
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate": 0.
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.4945904173106646,
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
-
"learning_rate": 0.
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.5100463678516228,
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.5255023183925811,
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
-
"learning_rate": 0.
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 340
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 0.5409582689335394,
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
-
"learning_rate": 0.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 350
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.5564142194744977,
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
-
"learning_rate": 0.
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 360
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.5718701700154559,
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
-
"learning_rate": 0.
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 370
|
| 269 |
},
|
| 270 |
{
|
| 271 |
"epoch": 0.5873261205564142,
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
-
"learning_rate": 0.
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 380
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 0.6027820710973725,
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate": 0.
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 390
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 0.6182380216383307,
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
-
"learning_rate": 0.
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 400
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 0.633693972179289,
|
| 293 |
-
"grad_norm": 0.
|
| 294 |
-
"learning_rate": 0.
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 410
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.6491499227202473,
|
| 300 |
-
"grad_norm": 0.
|
| 301 |
-
"learning_rate": 0.
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 420
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.6646058732612056,
|
| 307 |
-
"grad_norm": 0.
|
| 308 |
-
"learning_rate": 0.
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 430
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.6800618238021638,
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
-
"learning_rate": 0.
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 440
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.6955177743431221,
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
-
"learning_rate": 0.
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 450
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.7109737248840804,
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
-
"learning_rate": 0.
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 460
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.7264296754250387,
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate": 0.
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 470
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.7418856259659969,
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
-
"learning_rate": 0.
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 480
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.7573415765069552,
|
| 349 |
-
"grad_norm": 0.
|
| 350 |
-
"learning_rate": 0.
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 490
|
| 353 |
},
|
| 354 |
{
|
| 355 |
"epoch": 0.7727975270479135,
|
| 356 |
-
"grad_norm": 0.
|
| 357 |
-
"learning_rate": 0.
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 500
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 0.7882534775888718,
|
| 363 |
-
"grad_norm": 0.
|
| 364 |
-
"learning_rate": 0.
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 510
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 0.80370942812983,
|
| 370 |
-
"grad_norm": 0.
|
| 371 |
-
"learning_rate": 0.
|
| 372 |
-
"loss": 0.
|
| 373 |
"step": 520
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"epoch": 0.8191653786707882,
|
| 377 |
-
"grad_norm": 0.
|
| 378 |
-
"learning_rate": 0.
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 530
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 0.8346213292117465,
|
| 384 |
-
"grad_norm": 0.
|
| 385 |
-
"learning_rate": 0.
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 540
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 0.8500772797527048,
|
| 391 |
-
"grad_norm": 0.
|
| 392 |
-
"learning_rate": 0.
|
| 393 |
-
"loss": 0.
|
| 394 |
"step": 550
|
| 395 |
},
|
| 396 |
{
|
| 397 |
"epoch": 0.865533230293663,
|
| 398 |
-
"grad_norm": 0.
|
| 399 |
-
"learning_rate": 0.
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 560
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 0.8809891808346213,
|
| 405 |
-
"grad_norm": 0.
|
| 406 |
-
"learning_rate": 0.
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 570
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 0.8964451313755796,
|
| 412 |
-
"grad_norm": 0.
|
| 413 |
-
"learning_rate": 0.
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 580
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 0.9119010819165378,
|
| 419 |
-
"grad_norm": 0.
|
| 420 |
-
"learning_rate": 0.
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 590
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 0.9273570324574961,
|
| 426 |
-
"grad_norm": 0.
|
| 427 |
-
"learning_rate": 0.
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 600
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.9428129829984544,
|
| 433 |
-
"grad_norm": 0.
|
| 434 |
-
"learning_rate": 0.
|
| 435 |
-
"loss": 0.
|
| 436 |
"step": 610
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"epoch": 0.9582689335394127,
|
| 440 |
-
"grad_norm": 0.
|
| 441 |
-
"learning_rate": 0.
|
| 442 |
-
"loss": 0.
|
| 443 |
"step": 620
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 0.973724884080371,
|
| 447 |
-
"grad_norm": 0.
|
| 448 |
-
"learning_rate": 0.
|
| 449 |
-
"loss": 0.
|
| 450 |
"step": 630
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"epoch": 0.9891808346213292,
|
| 454 |
-
"grad_norm": 0.
|
| 455 |
-
"learning_rate": 0.
|
| 456 |
-
"loss": 0.
|
| 457 |
"step": 640
|
| 458 |
},
|
| 459 |
{
|
| 460 |
"epoch": 1.0,
|
| 461 |
-
"eval_loss": 0.
|
| 462 |
-
"eval_runtime":
|
| 463 |
-
"eval_samples_per_second":
|
| 464 |
-
"eval_steps_per_second": 0.
|
| 465 |
"step": 647
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 1.0046367851622875,
|
| 469 |
-
"grad_norm": 0.
|
| 470 |
-
"learning_rate": 0.
|
| 471 |
-
"loss": 0.
|
| 472 |
"step": 650
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 1.0200927357032457,
|
| 476 |
-
"grad_norm": 0.
|
| 477 |
-
"learning_rate": 0.
|
| 478 |
-
"loss": 0.
|
| 479 |
"step": 660
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 1.035548686244204,
|
| 483 |
-
"grad_norm": 0.
|
| 484 |
-
"learning_rate": 0.
|
| 485 |
-
"loss": 0.
|
| 486 |
"step": 670
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 1.0510046367851622,
|
| 490 |
-
"grad_norm": 0.
|
| 491 |
-
"learning_rate": 0.
|
| 492 |
-
"loss": 0.
|
| 493 |
"step": 680
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 1.0664605873261206,
|
| 497 |
-
"grad_norm": 0.
|
| 498 |
-
"learning_rate": 0.
|
| 499 |
-
"loss": 0.
|
| 500 |
"step": 690
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 1.0819165378670788,
|
| 504 |
-
"grad_norm": 0.
|
| 505 |
-
"learning_rate": 0.
|
| 506 |
-
"loss": 0.
|
| 507 |
"step": 700
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 1.0973724884080371,
|
| 511 |
-
"grad_norm": 0.
|
| 512 |
-
"learning_rate": 0.
|
| 513 |
-
"loss": 0.
|
| 514 |
"step": 710
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"epoch": 1.1128284389489953,
|
| 518 |
-
"grad_norm": 0.
|
| 519 |
-
"learning_rate": 0.
|
| 520 |
-
"loss": 0.
|
| 521 |
"step": 720
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 1.1282843894899537,
|
| 525 |
-
"grad_norm": 0.
|
| 526 |
-
"learning_rate": 0.
|
| 527 |
-
"loss": 0.
|
| 528 |
"step": 730
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 1.1437403400309119,
|
| 532 |
-
"grad_norm": 0.
|
| 533 |
-
"learning_rate": 0.
|
| 534 |
-
"loss": 0.
|
| 535 |
"step": 740
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 1.1591962905718702,
|
| 539 |
-
"grad_norm": 0.
|
| 540 |
-
"learning_rate": 0.
|
| 541 |
-
"loss": 0.
|
| 542 |
"step": 750
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 1.1746522411128284,
|
| 546 |
-
"grad_norm": 0.
|
| 547 |
-
"learning_rate": 0.
|
| 548 |
-
"loss": 0.
|
| 549 |
"step": 760
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 1.1901081916537868,
|
| 553 |
-
"grad_norm": 0.
|
| 554 |
-
"learning_rate": 0.
|
| 555 |
-
"loss": 0.
|
| 556 |
"step": 770
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 1.205564142194745,
|
| 560 |
-
"grad_norm": 0.
|
| 561 |
-
"learning_rate": 0.
|
| 562 |
-
"loss": 0.
|
| 563 |
"step": 780
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 1.2210200927357033,
|
| 567 |
-
"grad_norm": 0.
|
| 568 |
-
"learning_rate": 0.
|
| 569 |
-
"loss": 0.
|
| 570 |
"step": 790
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 1.2364760432766615,
|
| 574 |
-
"grad_norm": 0.
|
| 575 |
-
"learning_rate": 0.
|
| 576 |
-
"loss": 0.
|
| 577 |
"step": 800
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 1.2519319938176197,
|
| 581 |
-
"grad_norm": 0.
|
| 582 |
-
"learning_rate": 0.
|
| 583 |
-
"loss": 0.
|
| 584 |
"step": 810
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 1.267387944358578,
|
| 588 |
-
"grad_norm": 0.
|
| 589 |
-
"learning_rate": 0.
|
| 590 |
-
"loss": 0.
|
| 591 |
"step": 820
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 1.2828438948995364,
|
| 595 |
-
"grad_norm": 0.
|
| 596 |
-
"learning_rate": 0.
|
| 597 |
-
"loss": 0.
|
| 598 |
"step": 830
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 1.2982998454404946,
|
| 602 |
-
"grad_norm": 0.
|
| 603 |
-
"learning_rate": 0.
|
| 604 |
-
"loss": 0.
|
| 605 |
"step": 840
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 1.3137557959814528,
|
| 609 |
-
"grad_norm": 0.
|
| 610 |
-
"learning_rate": 0.
|
| 611 |
-
"loss": 0.
|
| 612 |
"step": 850
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 1.3292117465224111,
|
| 616 |
-
"grad_norm": 0.
|
| 617 |
-
"learning_rate": 0.
|
| 618 |
-
"loss": 0.
|
| 619 |
"step": 860
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 1.3446676970633695,
|
| 623 |
-
"grad_norm": 0.
|
| 624 |
-
"learning_rate": 0.
|
| 625 |
-
"loss": 0.
|
| 626 |
"step": 870
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 1.3601236476043277,
|
| 630 |
-
"grad_norm": 0.
|
| 631 |
-
"learning_rate": 0.
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 880
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 1.3755795981452859,
|
| 637 |
-
"grad_norm": 0.
|
| 638 |
-
"learning_rate":
|
| 639 |
-
"loss": 0.
|
| 640 |
"step": 890
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 1.3910355486862442,
|
| 644 |
-
"grad_norm": 0.
|
| 645 |
-
"learning_rate":
|
| 646 |
-
"loss": 0.
|
| 647 |
"step": 900
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 1.4064914992272024,
|
| 651 |
-
"grad_norm": 0.
|
| 652 |
-
"learning_rate":
|
| 653 |
-
"loss": 0.
|
| 654 |
"step": 910
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 1.4219474497681608,
|
| 658 |
-
"grad_norm": 0.
|
| 659 |
-
"learning_rate":
|
| 660 |
-
"loss": 0.
|
| 661 |
"step": 920
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 1.437403400309119,
|
| 665 |
-
"grad_norm": 0.
|
| 666 |
-
"learning_rate":
|
| 667 |
-
"loss": 0.
|
| 668 |
"step": 930
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 1.4528593508500773,
|
| 672 |
-
"grad_norm": 0.
|
| 673 |
-
"learning_rate":
|
| 674 |
-
"loss": 0.
|
| 675 |
"step": 940
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 1.4683153013910355,
|
| 679 |
-
"grad_norm": 0.
|
| 680 |
-
"learning_rate":
|
| 681 |
-
"loss": 0.
|
| 682 |
"step": 950
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 1.4837712519319939,
|
| 686 |
-
"grad_norm": 0.
|
| 687 |
-
"learning_rate":
|
| 688 |
-
"loss": 0.
|
| 689 |
"step": 960
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 1.499227202472952,
|
| 693 |
-
"grad_norm": 0.
|
| 694 |
-
"learning_rate":
|
| 695 |
-
"loss": 0.
|
| 696 |
"step": 970
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 1.5146831530139102,
|
| 700 |
-
"grad_norm": 0.
|
| 701 |
-
"learning_rate":
|
| 702 |
-
"loss": 0.
|
| 703 |
"step": 980
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 1.5301391035548686,
|
| 707 |
-
"grad_norm": 0.
|
| 708 |
-
"learning_rate":
|
| 709 |
-
"loss": 0.
|
| 710 |
"step": 990
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 1.545595054095827,
|
| 714 |
-
"grad_norm": 0.
|
| 715 |
-
"learning_rate":
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 1000
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 1.5610510046367851,
|
| 721 |
-
"grad_norm": 0.
|
| 722 |
-
"learning_rate":
|
| 723 |
-
"loss": 0.
|
| 724 |
"step": 1010
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"epoch": 1.5765069551777433,
|
| 728 |
-
"grad_norm": 0.
|
| 729 |
-
"learning_rate":
|
| 730 |
-
"loss": 0.
|
| 731 |
"step": 1020
|
| 732 |
},
|
| 733 |
{
|
| 734 |
"epoch": 1.5919629057187017,
|
| 735 |
-
"grad_norm": 0.
|
| 736 |
-
"learning_rate":
|
| 737 |
-
"loss": 0.
|
| 738 |
"step": 1030
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 1.60741885625966,
|
| 742 |
-
"grad_norm": 0.
|
| 743 |
-
"learning_rate":
|
| 744 |
-
"loss": 0.
|
| 745 |
"step": 1040
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 1.6228748068006182,
|
| 749 |
-
"grad_norm": 0.
|
| 750 |
-
"learning_rate":
|
| 751 |
-
"loss": 0.
|
| 752 |
"step": 1050
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 1.6383307573415764,
|
| 756 |
-
"grad_norm": 0.
|
| 757 |
-
"learning_rate":
|
| 758 |
-
"loss": 0.
|
| 759 |
"step": 1060
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 1.6537867078825348,
|
| 763 |
-
"grad_norm": 0.
|
| 764 |
-
"learning_rate":
|
| 765 |
-
"loss": 0.
|
| 766 |
"step": 1070
|
| 767 |
},
|
| 768 |
{
|
| 769 |
"epoch": 1.6692426584234932,
|
| 770 |
-
"grad_norm": 0.
|
| 771 |
-
"learning_rate":
|
| 772 |
-
"loss": 0.
|
| 773 |
"step": 1080
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 1.6846986089644513,
|
| 777 |
-
"grad_norm": 0.
|
| 778 |
-
"learning_rate":
|
| 779 |
-
"loss": 0.
|
| 780 |
"step": 1090
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 1.7001545595054095,
|
| 784 |
-
"grad_norm": 0.
|
| 785 |
-
"learning_rate":
|
| 786 |
-
"loss": 0.
|
| 787 |
"step": 1100
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 1.7156105100463679,
|
| 791 |
-
"grad_norm": 0.
|
| 792 |
-
"learning_rate":
|
| 793 |
-
"loss": 0.
|
| 794 |
"step": 1110
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 1.7310664605873263,
|
| 798 |
-
"grad_norm": 0.
|
| 799 |
-
"learning_rate":
|
| 800 |
-
"loss": 0.
|
| 801 |
"step": 1120
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 1.7465224111282844,
|
| 805 |
-
"grad_norm": 0.
|
| 806 |
-
"learning_rate":
|
| 807 |
-
"loss": 0.
|
| 808 |
"step": 1130
|
| 809 |
},
|
| 810 |
{
|
| 811 |
"epoch": 1.7619783616692426,
|
| 812 |
-
"grad_norm": 0.
|
| 813 |
-
"learning_rate":
|
| 814 |
-
"loss": 0.
|
| 815 |
"step": 1140
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 1.7774343122102008,
|
| 819 |
-
"grad_norm": 0.
|
| 820 |
-
"learning_rate":
|
| 821 |
-
"loss": 0.
|
| 822 |
"step": 1150
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 1.7928902627511591,
|
| 826 |
-
"grad_norm": 0.
|
| 827 |
-
"learning_rate":
|
| 828 |
-
"loss": 0.
|
| 829 |
"step": 1160
|
| 830 |
},
|
| 831 |
{
|
| 832 |
"epoch": 1.8083462132921175,
|
| 833 |
-
"grad_norm": 0.
|
| 834 |
-
"learning_rate":
|
| 835 |
-
"loss": 0.
|
| 836 |
"step": 1170
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 1.8238021638330757,
|
| 840 |
-
"grad_norm": 0.
|
| 841 |
-
"learning_rate":
|
| 842 |
-
"loss": 0.
|
| 843 |
"step": 1180
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 1.8392581143740339,
|
| 847 |
-
"grad_norm": 0.
|
| 848 |
-
"learning_rate":
|
| 849 |
-
"loss": 0.
|
| 850 |
"step": 1190
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"epoch": 1.8547140649149922,
|
| 854 |
-
"grad_norm": 0.
|
| 855 |
-
"learning_rate":
|
| 856 |
-
"loss": 0.
|
| 857 |
"step": 1200
|
| 858 |
},
|
| 859 |
{
|
| 860 |
"epoch": 1.8701700154559506,
|
| 861 |
-
"grad_norm": 0.
|
| 862 |
-
"learning_rate":
|
| 863 |
-
"loss": 0.
|
| 864 |
"step": 1210
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"epoch": 1.8856259659969088,
|
| 868 |
-
"grad_norm": 0.
|
| 869 |
-
"learning_rate":
|
| 870 |
-
"loss": 0.
|
| 871 |
"step": 1220
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 1.901081916537867,
|
| 875 |
-
"grad_norm": 0.
|
| 876 |
-
"learning_rate":
|
| 877 |
-
"loss": 0.
|
| 878 |
"step": 1230
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 1.9165378670788253,
|
| 882 |
-
"grad_norm": 0.
|
| 883 |
-
"learning_rate":
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 1240
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 1.9319938176197837,
|
| 889 |
-
"grad_norm": 0.
|
| 890 |
-
"learning_rate":
|
| 891 |
-
"loss": 0.
|
| 892 |
"step": 1250
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 1.947449768160742,
|
| 896 |
-
"grad_norm": 0.
|
| 897 |
-
"learning_rate": 8.
|
| 898 |
-
"loss": 0.
|
| 899 |
"step": 1260
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 1.9629057187017,
|
| 903 |
-
"grad_norm": 0.
|
| 904 |
-
"learning_rate": 5.921052631578947e-
|
| 905 |
-
"loss": 0.
|
| 906 |
"step": 1270
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 1.9783616692426584,
|
| 910 |
-
"grad_norm": 0.
|
| 911 |
-
"learning_rate": 3.
|
| 912 |
-
"loss": 0.
|
| 913 |
"step": 1280
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 1.9938176197836168,
|
| 917 |
-
"grad_norm": 0.
|
| 918 |
-
"learning_rate": 9.
|
| 919 |
-
"loss": 0.
|
| 920 |
"step": 1290
|
| 921 |
}
|
| 922 |
],
|
|
@@ -937,8 +937,8 @@
|
|
| 937 |
"attributes": {}
|
| 938 |
}
|
| 939 |
},
|
| 940 |
-
"total_flos": 1.
|
| 941 |
-
"train_batch_size":
|
| 942 |
"trial_name": null,
|
| 943 |
"trial_params": null
|
| 944 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.015455950540958269,
|
| 13 |
+
"grad_norm": 0.357046514749527,
|
| 14 |
+
"learning_rate": 0.0003846153846153846,
|
| 15 |
+
"loss": 1.5383,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.030911901081916538,
|
| 20 |
+
"grad_norm": 0.11198900640010834,
|
| 21 |
+
"learning_rate": 0.0007692307692307692,
|
| 22 |
+
"loss": 1.1091,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.04636785162287481,
|
| 27 |
+
"grad_norm": 0.056582603603601456,
|
| 28 |
+
"learning_rate": 0.001153846153846154,
|
| 29 |
+
"loss": 0.7939,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.061823802163833076,
|
| 34 |
+
"grad_norm": 0.0210476852953434,
|
| 35 |
+
"learning_rate": 0.0015384615384615385,
|
| 36 |
+
"loss": 0.6165,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.07727975270479134,
|
| 41 |
+
"grad_norm": 0.012083015404641628,
|
| 42 |
+
"learning_rate": 0.0019230769230769232,
|
| 43 |
+
"loss": 0.5624,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.09273570324574962,
|
| 48 |
+
"grad_norm": 0.008505144156515598,
|
| 49 |
+
"learning_rate": 0.002307692307692308,
|
| 50 |
+
"loss": 0.5269,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.10819165378670788,
|
| 55 |
+
"grad_norm": 0.0063809980638325214,
|
| 56 |
+
"learning_rate": 0.0026923076923076926,
|
| 57 |
+
"loss": 0.5059,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.12364760432766615,
|
| 62 |
+
"grad_norm": 0.005832094699144363,
|
| 63 |
+
"learning_rate": 0.0029950657894736842,
|
| 64 |
+
"loss": 0.5202,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.1391035548686244,
|
| 69 |
+
"grad_norm": 0.004662094172090292,
|
| 70 |
+
"learning_rate": 0.0029703947368421055,
|
| 71 |
+
"loss": 0.5087,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.1545595054095827,
|
| 76 |
+
"grad_norm": 0.004813206382095814,
|
| 77 |
+
"learning_rate": 0.0029457236842105267,
|
| 78 |
+
"loss": 0.4979,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.17001545595054096,
|
| 83 |
+
"grad_norm": 0.003981301095336676,
|
| 84 |
+
"learning_rate": 0.0029210526315789475,
|
| 85 |
+
"loss": 0.4833,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.18547140649149924,
|
| 90 |
+
"grad_norm": 0.0037942214403301477,
|
| 91 |
+
"learning_rate": 0.0028963815789473687,
|
| 92 |
+
"loss": 0.4842,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.2009273570324575,
|
| 97 |
+
"grad_norm": 0.0041742450557649136,
|
| 98 |
+
"learning_rate": 0.0028717105263157895,
|
| 99 |
+
"loss": 0.4818,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.21638330757341576,
|
| 104 |
+
"grad_norm": 0.005099099595099688,
|
| 105 |
+
"learning_rate": 0.0028470394736842108,
|
| 106 |
+
"loss": 0.4809,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.23183925811437403,
|
| 111 |
+
"grad_norm": 0.0031047100201249123,
|
| 112 |
+
"learning_rate": 0.0028223684210526316,
|
| 113 |
+
"loss": 0.5016,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.2472952086553323,
|
| 118 |
+
"grad_norm": 0.0036040199920535088,
|
| 119 |
+
"learning_rate": 0.002797697368421053,
|
| 120 |
+
"loss": 0.4775,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.26275115919629055,
|
| 125 |
+
"grad_norm": 0.0033861789852380753,
|
| 126 |
+
"learning_rate": 0.0027730263157894736,
|
| 127 |
+
"loss": 0.4784,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.2782071097372488,
|
| 132 |
+
"grad_norm": 0.003118926426395774,
|
| 133 |
+
"learning_rate": 0.002748355263157895,
|
| 134 |
+
"loss": 0.4962,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.2936630602782071,
|
| 139 |
+
"grad_norm": 0.0035265563055872917,
|
| 140 |
+
"learning_rate": 0.002723684210526316,
|
| 141 |
+
"loss": 0.4829,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.3091190108191654,
|
| 146 |
+
"grad_norm": 0.0035475995391607285,
|
| 147 |
+
"learning_rate": 0.002699013157894737,
|
| 148 |
+
"loss": 0.485,
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.32457496136012365,
|
| 153 |
+
"grad_norm": 0.0030264686793088913,
|
| 154 |
+
"learning_rate": 0.002674342105263158,
|
| 155 |
+
"loss": 0.4681,
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.3400309119010819,
|
| 160 |
+
"grad_norm": 0.0033854299690574408,
|
| 161 |
+
"learning_rate": 0.002649671052631579,
|
| 162 |
+
"loss": 0.4805,
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.3554868624420402,
|
| 167 |
+
"grad_norm": 0.0029569112230092287,
|
| 168 |
+
"learning_rate": 0.002625,
|
| 169 |
+
"loss": 0.4688,
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.37094281298299847,
|
| 174 |
+
"grad_norm": 0.0032272525131702423,
|
| 175 |
+
"learning_rate": 0.002600328947368421,
|
| 176 |
+
"loss": 0.4752,
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.38639876352395675,
|
| 181 |
+
"grad_norm": 0.003502602456137538,
|
| 182 |
+
"learning_rate": 0.002575657894736842,
|
| 183 |
+
"loss": 0.4699,
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.401854714064915,
|
| 188 |
+
"grad_norm": 0.0031522298231720924,
|
| 189 |
+
"learning_rate": 0.002550986842105263,
|
| 190 |
+
"loss": 0.4756,
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.41731066460587324,
|
| 195 |
+
"grad_norm": 0.003098264569416642,
|
| 196 |
+
"learning_rate": 0.0025263157894736842,
|
| 197 |
+
"loss": 0.4574,
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.4327666151468315,
|
| 202 |
+
"grad_norm": 0.0025676521472632885,
|
| 203 |
+
"learning_rate": 0.0025016447368421055,
|
| 204 |
+
"loss": 0.4779,
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.4482225656877898,
|
| 209 |
+
"grad_norm": 0.0034302272833883762,
|
| 210 |
+
"learning_rate": 0.0024769736842105263,
|
| 211 |
+
"loss": 0.4729,
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.46367851622874806,
|
| 216 |
+
"grad_norm": 0.003159865504130721,
|
| 217 |
+
"learning_rate": 0.0024523026315789475,
|
| 218 |
+
"loss": 0.4715,
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.47913446676970634,
|
| 223 |
+
"grad_norm": 0.003168923780322075,
|
| 224 |
+
"learning_rate": 0.0024276315789473683,
|
| 225 |
+
"loss": 0.4764,
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.4945904173106646,
|
| 230 |
+
"grad_norm": 0.0034859515726566315,
|
| 231 |
+
"learning_rate": 0.0024029605263157896,
|
| 232 |
+
"loss": 0.4652,
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.5100463678516228,
|
| 237 |
+
"grad_norm": 0.003067239187657833,
|
| 238 |
+
"learning_rate": 0.0023782894736842104,
|
| 239 |
+
"loss": 0.4648,
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.5255023183925811,
|
| 244 |
+
"grad_norm": 0.0032223982270807028,
|
| 245 |
+
"learning_rate": 0.0023536184210526316,
|
| 246 |
+
"loss": 0.4725,
|
| 247 |
"step": 340
|
| 248 |
},
|
| 249 |
{
|
| 250 |
"epoch": 0.5409582689335394,
|
| 251 |
+
"grad_norm": 0.0027090355288237333,
|
| 252 |
+
"learning_rate": 0.0023289473684210524,
|
| 253 |
+
"loss": 0.4704,
|
| 254 |
"step": 350
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.5564142194744977,
|
| 258 |
+
"grad_norm": 0.003484300570562482,
|
| 259 |
+
"learning_rate": 0.0023042763157894736,
|
| 260 |
+
"loss": 0.4616,
|
| 261 |
"step": 360
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 0.5718701700154559,
|
| 265 |
+
"grad_norm": 0.003339330432936549,
|
| 266 |
+
"learning_rate": 0.0022796052631578944,
|
| 267 |
+
"loss": 0.4665,
|
| 268 |
"step": 370
|
| 269 |
},
|
| 270 |
{
|
| 271 |
"epoch": 0.5873261205564142,
|
| 272 |
+
"grad_norm": 0.0029797593597322702,
|
| 273 |
+
"learning_rate": 0.002254934210526316,
|
| 274 |
+
"loss": 0.4573,
|
| 275 |
"step": 380
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 0.6027820710973725,
|
| 279 |
+
"grad_norm": 0.0030033981893211603,
|
| 280 |
+
"learning_rate": 0.002230263157894737,
|
| 281 |
+
"loss": 0.4618,
|
| 282 |
"step": 390
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 0.6182380216383307,
|
| 286 |
+
"grad_norm": 0.005113155115395784,
|
| 287 |
+
"learning_rate": 0.002205592105263158,
|
| 288 |
+
"loss": 0.4589,
|
| 289 |
"step": 400
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 0.633693972179289,
|
| 293 |
+
"grad_norm": 0.002975397277623415,
|
| 294 |
+
"learning_rate": 0.002180921052631579,
|
| 295 |
+
"loss": 0.4765,
|
| 296 |
"step": 410
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.6491499227202473,
|
| 300 |
+
"grad_norm": 0.004753004759550095,
|
| 301 |
+
"learning_rate": 0.00215625,
|
| 302 |
+
"loss": 0.4631,
|
| 303 |
"step": 420
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 0.6646058732612056,
|
| 307 |
+
"grad_norm": 0.003564928425475955,
|
| 308 |
+
"learning_rate": 0.002131578947368421,
|
| 309 |
+
"loss": 0.4488,
|
| 310 |
"step": 430
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 0.6800618238021638,
|
| 314 |
+
"grad_norm": 0.0032665496692061424,
|
| 315 |
+
"learning_rate": 0.0021069078947368422,
|
| 316 |
+
"loss": 0.457,
|
| 317 |
"step": 440
|
| 318 |
},
|
| 319 |
{
|
| 320 |
"epoch": 0.6955177743431221,
|
| 321 |
+
"grad_norm": 0.0030079709831625223,
|
| 322 |
+
"learning_rate": 0.002082236842105263,
|
| 323 |
+
"loss": 0.4667,
|
| 324 |
"step": 450
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 0.7109737248840804,
|
| 328 |
+
"grad_norm": 0.0025733078364282846,
|
| 329 |
+
"learning_rate": 0.0020575657894736843,
|
| 330 |
+
"loss": 0.4667,
|
| 331 |
"step": 460
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 0.7264296754250387,
|
| 335 |
+
"grad_norm": 0.00270587345585227,
|
| 336 |
+
"learning_rate": 0.0020328947368421055,
|
| 337 |
+
"loss": 0.4679,
|
| 338 |
"step": 470
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.7418856259659969,
|
| 342 |
+
"grad_norm": 0.00273908581584692,
|
| 343 |
+
"learning_rate": 0.0020082236842105263,
|
| 344 |
+
"loss": 0.4694,
|
| 345 |
"step": 480
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 0.7573415765069552,
|
| 349 |
+
"grad_norm": 0.002720112446695566,
|
| 350 |
+
"learning_rate": 0.0019835526315789475,
|
| 351 |
+
"loss": 0.4513,
|
| 352 |
"step": 490
|
| 353 |
},
|
| 354 |
{
|
| 355 |
"epoch": 0.7727975270479135,
|
| 356 |
+
"grad_norm": 0.0028910296969115734,
|
| 357 |
+
"learning_rate": 0.0019588815789473683,
|
| 358 |
+
"loss": 0.4592,
|
| 359 |
"step": 500
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 0.7882534775888718,
|
| 363 |
+
"grad_norm": 0.003034258494153619,
|
| 364 |
+
"learning_rate": 0.0019342105263157896,
|
| 365 |
+
"loss": 0.4611,
|
| 366 |
"step": 510
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 0.80370942812983,
|
| 370 |
+
"grad_norm": 0.0030727661214768887,
|
| 371 |
+
"learning_rate": 0.0019095394736842106,
|
| 372 |
+
"loss": 0.463,
|
| 373 |
"step": 520
|
| 374 |
},
|
| 375 |
{
|
| 376 |
"epoch": 0.8191653786707882,
|
| 377 |
+
"grad_norm": 0.0026562565471976995,
|
| 378 |
+
"learning_rate": 0.0018848684210526316,
|
| 379 |
+
"loss": 0.469,
|
| 380 |
"step": 530
|
| 381 |
},
|
| 382 |
{
|
| 383 |
"epoch": 0.8346213292117465,
|
| 384 |
+
"grad_norm": 0.002964869374409318,
|
| 385 |
+
"learning_rate": 0.0018601973684210526,
|
| 386 |
+
"loss": 0.462,
|
| 387 |
"step": 540
|
| 388 |
},
|
| 389 |
{
|
| 390 |
"epoch": 0.8500772797527048,
|
| 391 |
+
"grad_norm": 0.0029133500065654516,
|
| 392 |
+
"learning_rate": 0.0018355263157894736,
|
| 393 |
+
"loss": 0.4678,
|
| 394 |
"step": 550
|
| 395 |
},
|
| 396 |
{
|
| 397 |
"epoch": 0.865533230293663,
|
| 398 |
+
"grad_norm": 0.002890991512686014,
|
| 399 |
+
"learning_rate": 0.0018108552631578947,
|
| 400 |
+
"loss": 0.4646,
|
| 401 |
"step": 560
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 0.8809891808346213,
|
| 405 |
+
"grad_norm": 0.0025943962391465902,
|
| 406 |
+
"learning_rate": 0.001786184210526316,
|
| 407 |
+
"loss": 0.4645,
|
| 408 |
"step": 570
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 0.8964451313755796,
|
| 412 |
+
"grad_norm": 0.0027450553607195616,
|
| 413 |
+
"learning_rate": 0.001761513157894737,
|
| 414 |
+
"loss": 0.4691,
|
| 415 |
"step": 580
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 0.9119010819165378,
|
| 419 |
+
"grad_norm": 0.0027814917266368866,
|
| 420 |
+
"learning_rate": 0.001736842105263158,
|
| 421 |
+
"loss": 0.4549,
|
| 422 |
"step": 590
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 0.9273570324574961,
|
| 426 |
+
"grad_norm": 0.0030699821654707193,
|
| 427 |
+
"learning_rate": 0.001712171052631579,
|
| 428 |
+
"loss": 0.4694,
|
| 429 |
"step": 600
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 0.9428129829984544,
|
| 433 |
+
"grad_norm": 0.002675461582839489,
|
| 434 |
+
"learning_rate": 0.0016875,
|
| 435 |
+
"loss": 0.4593,
|
| 436 |
"step": 610
|
| 437 |
},
|
| 438 |
{
|
| 439 |
"epoch": 0.9582689335394127,
|
| 440 |
+
"grad_norm": 0.0026055267080664635,
|
| 441 |
+
"learning_rate": 0.001662828947368421,
|
| 442 |
+
"loss": 0.4681,
|
| 443 |
"step": 620
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 0.973724884080371,
|
| 447 |
+
"grad_norm": 0.002623435575515032,
|
| 448 |
+
"learning_rate": 0.001638157894736842,
|
| 449 |
+
"loss": 0.46,
|
| 450 |
"step": 630
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"epoch": 0.9891808346213292,
|
| 454 |
+
"grad_norm": 0.0023981425911188126,
|
| 455 |
+
"learning_rate": 0.001613486842105263,
|
| 456 |
+
"loss": 0.4587,
|
| 457 |
"step": 640
|
| 458 |
},
|
| 459 |
{
|
| 460 |
"epoch": 1.0,
|
| 461 |
+
"eval_loss": 0.9165626764297485,
|
| 462 |
+
"eval_runtime": 1353.6255,
|
| 463 |
+
"eval_samples_per_second": 7.648,
|
| 464 |
+
"eval_steps_per_second": 0.478,
|
| 465 |
"step": 647
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 1.0046367851622875,
|
| 469 |
+
"grad_norm": 0.002703867619857192,
|
| 470 |
+
"learning_rate": 0.001588815789473684,
|
| 471 |
+
"loss": 0.4565,
|
| 472 |
"step": 650
|
| 473 |
},
|
| 474 |
{
|
| 475 |
"epoch": 1.0200927357032457,
|
| 476 |
+
"grad_norm": 0.002686214866116643,
|
| 477 |
+
"learning_rate": 0.0015641447368421055,
|
| 478 |
+
"loss": 0.4656,
|
| 479 |
"step": 660
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 1.035548686244204,
|
| 483 |
+
"grad_norm": 0.002944634296000004,
|
| 484 |
+
"learning_rate": 0.0015394736842105265,
|
| 485 |
+
"loss": 0.4609,
|
| 486 |
"step": 670
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 1.0510046367851622,
|
| 490 |
+
"grad_norm": 0.002919598249718547,
|
| 491 |
+
"learning_rate": 0.0015148026315789475,
|
| 492 |
+
"loss": 0.462,
|
| 493 |
"step": 680
|
| 494 |
},
|
| 495 |
{
|
| 496 |
"epoch": 1.0664605873261206,
|
| 497 |
+
"grad_norm": 0.0027975935954600573,
|
| 498 |
+
"learning_rate": 0.0014901315789473686,
|
| 499 |
+
"loss": 0.455,
|
| 500 |
"step": 690
|
| 501 |
},
|
| 502 |
{
|
| 503 |
"epoch": 1.0819165378670788,
|
| 504 |
+
"grad_norm": 0.002747561549767852,
|
| 505 |
+
"learning_rate": 0.0014654605263157896,
|
| 506 |
+
"loss": 0.4556,
|
| 507 |
"step": 700
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 1.0973724884080371,
|
| 511 |
+
"grad_norm": 0.0029210918582975864,
|
| 512 |
+
"learning_rate": 0.0014407894736842106,
|
| 513 |
+
"loss": 0.4486,
|
| 514 |
"step": 710
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"epoch": 1.1128284389489953,
|
| 518 |
+
"grad_norm": 0.0026143298018723726,
|
| 519 |
+
"learning_rate": 0.0014161184210526316,
|
| 520 |
+
"loss": 0.4593,
|
| 521 |
"step": 720
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 1.1282843894899537,
|
| 525 |
+
"grad_norm": 0.002351797418668866,
|
| 526 |
+
"learning_rate": 0.0013914473684210526,
|
| 527 |
+
"loss": 0.4419,
|
| 528 |
"step": 730
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 1.1437403400309119,
|
| 532 |
+
"grad_norm": 0.0029544688295572996,
|
| 533 |
+
"learning_rate": 0.0013667763157894737,
|
| 534 |
+
"loss": 0.4535,
|
| 535 |
"step": 740
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 1.1591962905718702,
|
| 539 |
+
"grad_norm": 0.0025962782092392445,
|
| 540 |
+
"learning_rate": 0.0013421052631578947,
|
| 541 |
+
"loss": 0.4454,
|
| 542 |
"step": 750
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 1.1746522411128284,
|
| 546 |
+
"grad_norm": 0.0026020314544439316,
|
| 547 |
+
"learning_rate": 0.0013174342105263157,
|
| 548 |
+
"loss": 0.4569,
|
| 549 |
"step": 760
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 1.1901081916537868,
|
| 553 |
+
"grad_norm": 0.00269780564121902,
|
| 554 |
+
"learning_rate": 0.0012927631578947367,
|
| 555 |
+
"loss": 0.4657,
|
| 556 |
"step": 770
|
| 557 |
},
|
| 558 |
{
|
| 559 |
"epoch": 1.205564142194745,
|
| 560 |
+
"grad_norm": 0.0027555320411920547,
|
| 561 |
+
"learning_rate": 0.001268092105263158,
|
| 562 |
+
"loss": 0.4546,
|
| 563 |
"step": 780
|
| 564 |
},
|
| 565 |
{
|
| 566 |
"epoch": 1.2210200927357033,
|
| 567 |
+
"grad_norm": 0.002603672444820404,
|
| 568 |
+
"learning_rate": 0.001243421052631579,
|
| 569 |
+
"loss": 0.4547,
|
| 570 |
"step": 790
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 1.2364760432766615,
|
| 574 |
+
"grad_norm": 0.002504123141989112,
|
| 575 |
+
"learning_rate": 0.00121875,
|
| 576 |
+
"loss": 0.4627,
|
| 577 |
"step": 800
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 1.2519319938176197,
|
| 581 |
+
"grad_norm": 0.003078003181144595,
|
| 582 |
+
"learning_rate": 0.001194078947368421,
|
| 583 |
+
"loss": 0.4504,
|
| 584 |
"step": 810
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 1.267387944358578,
|
| 588 |
+
"grad_norm": 0.0032601715065538883,
|
| 589 |
+
"learning_rate": 0.001169407894736842,
|
| 590 |
+
"loss": 0.4508,
|
| 591 |
"step": 820
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 1.2828438948995364,
|
| 595 |
+
"grad_norm": 0.003114907769486308,
|
| 596 |
+
"learning_rate": 0.0011447368421052633,
|
| 597 |
+
"loss": 0.4448,
|
| 598 |
"step": 830
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 1.2982998454404946,
|
| 602 |
+
"grad_norm": 0.002611513016745448,
|
| 603 |
+
"learning_rate": 0.0011200657894736843,
|
| 604 |
+
"loss": 0.4611,
|
| 605 |
"step": 840
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 1.3137557959814528,
|
| 609 |
+
"grad_norm": 0.0028356926050037146,
|
| 610 |
+
"learning_rate": 0.0010953947368421053,
|
| 611 |
+
"loss": 0.4543,
|
| 612 |
"step": 850
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 1.3292117465224111,
|
| 616 |
+
"grad_norm": 0.0028607589192688465,
|
| 617 |
+
"learning_rate": 0.0010707236842105263,
|
| 618 |
+
"loss": 0.4729,
|
| 619 |
"step": 860
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 1.3446676970633695,
|
| 623 |
+
"grad_norm": 0.00289659365080297,
|
| 624 |
+
"learning_rate": 0.0010460526315789474,
|
| 625 |
+
"loss": 0.4567,
|
| 626 |
"step": 870
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 1.3601236476043277,
|
| 630 |
+
"grad_norm": 0.002599680330604315,
|
| 631 |
+
"learning_rate": 0.0010213815789473686,
|
| 632 |
+
"loss": 0.456,
|
| 633 |
"step": 880
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 1.3755795981452859,
|
| 637 |
+
"grad_norm": 0.0026973742060363293,
|
| 638 |
+
"learning_rate": 0.0009967105263157896,
|
| 639 |
+
"loss": 0.4552,
|
| 640 |
"step": 890
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 1.3910355486862442,
|
| 644 |
+
"grad_norm": 0.0025935762096196413,
|
| 645 |
+
"learning_rate": 0.0009720394736842105,
|
| 646 |
+
"loss": 0.4589,
|
| 647 |
"step": 900
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 1.4064914992272024,
|
| 651 |
+
"grad_norm": 0.0026942496187984943,
|
| 652 |
+
"learning_rate": 0.0009473684210526315,
|
| 653 |
+
"loss": 0.455,
|
| 654 |
"step": 910
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 1.4219474497681608,
|
| 658 |
+
"grad_norm": 0.0027507098857313395,
|
| 659 |
+
"learning_rate": 0.0009226973684210528,
|
| 660 |
+
"loss": 0.4627,
|
| 661 |
"step": 920
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 1.437403400309119,
|
| 665 |
+
"grad_norm": 0.0029431770090013742,
|
| 666 |
+
"learning_rate": 0.0008980263157894738,
|
| 667 |
+
"loss": 0.4557,
|
| 668 |
"step": 930
|
| 669 |
},
|
| 670 |
{
|
| 671 |
"epoch": 1.4528593508500773,
|
| 672 |
+
"grad_norm": 0.002638396341353655,
|
| 673 |
+
"learning_rate": 0.0008733552631578948,
|
| 674 |
+
"loss": 0.4546,
|
| 675 |
"step": 940
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 1.4683153013910355,
|
| 679 |
+
"grad_norm": 0.0026191219221800566,
|
| 680 |
+
"learning_rate": 0.0008486842105263158,
|
| 681 |
+
"loss": 0.4557,
|
| 682 |
"step": 950
|
| 683 |
},
|
| 684 |
{
|
| 685 |
"epoch": 1.4837712519319939,
|
| 686 |
+
"grad_norm": 0.002677230630069971,
|
| 687 |
+
"learning_rate": 0.0008240131578947368,
|
| 688 |
+
"loss": 0.4632,
|
| 689 |
"step": 960
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 1.499227202472952,
|
| 693 |
+
"grad_norm": 0.00285891885869205,
|
| 694 |
+
"learning_rate": 0.000799342105263158,
|
| 695 |
+
"loss": 0.4581,
|
| 696 |
"step": 970
|
| 697 |
},
|
| 698 |
{
|
| 699 |
"epoch": 1.5146831530139102,
|
| 700 |
+
"grad_norm": 0.0026907038409262896,
|
| 701 |
+
"learning_rate": 0.000774671052631579,
|
| 702 |
+
"loss": 0.4509,
|
| 703 |
"step": 980
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 1.5301391035548686,
|
| 707 |
+
"grad_norm": 0.0024703822564333677,
|
| 708 |
+
"learning_rate": 0.00075,
|
| 709 |
+
"loss": 0.4481,
|
| 710 |
"step": 990
|
| 711 |
},
|
| 712 |
{
|
| 713 |
"epoch": 1.545595054095827,
|
| 714 |
+
"grad_norm": 0.002853216603398323,
|
| 715 |
+
"learning_rate": 0.000725328947368421,
|
| 716 |
+
"loss": 0.4438,
|
| 717 |
"step": 1000
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 1.5610510046367851,
|
| 721 |
+
"grad_norm": 0.002754925051704049,
|
| 722 |
+
"learning_rate": 0.0007006578947368422,
|
| 723 |
+
"loss": 0.4656,
|
| 724 |
"step": 1010
|
| 725 |
},
|
| 726 |
{
|
| 727 |
"epoch": 1.5765069551777433,
|
| 728 |
+
"grad_norm": 0.002468267921358347,
|
| 729 |
+
"learning_rate": 0.0006759868421052632,
|
| 730 |
+
"loss": 0.4515,
|
| 731 |
"step": 1020
|
| 732 |
},
|
| 733 |
{
|
| 734 |
"epoch": 1.5919629057187017,
|
| 735 |
+
"grad_norm": 0.002553540049120784,
|
| 736 |
+
"learning_rate": 0.0006513157894736842,
|
| 737 |
+
"loss": 0.4506,
|
| 738 |
"step": 1030
|
| 739 |
},
|
| 740 |
{
|
| 741 |
"epoch": 1.60741885625966,
|
| 742 |
+
"grad_norm": 0.0030136853456497192,
|
| 743 |
+
"learning_rate": 0.0006266447368421052,
|
| 744 |
+
"loss": 0.4552,
|
| 745 |
"step": 1040
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 1.6228748068006182,
|
| 749 |
+
"grad_norm": 0.002497268607839942,
|
| 750 |
+
"learning_rate": 0.0006019736842105263,
|
| 751 |
+
"loss": 0.4506,
|
| 752 |
"step": 1050
|
| 753 |
},
|
| 754 |
{
|
| 755 |
"epoch": 1.6383307573415764,
|
| 756 |
+
"grad_norm": 0.002612602198496461,
|
| 757 |
+
"learning_rate": 0.0005773026315789474,
|
| 758 |
+
"loss": 0.4519,
|
| 759 |
"step": 1060
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 1.6537867078825348,
|
| 763 |
+
"grad_norm": 0.0023622452281415462,
|
| 764 |
+
"learning_rate": 0.0005526315789473684,
|
| 765 |
+
"loss": 0.4446,
|
| 766 |
"step": 1070
|
| 767 |
},
|
| 768 |
{
|
| 769 |
"epoch": 1.6692426584234932,
|
| 770 |
+
"grad_norm": 0.0023850842844694853,
|
| 771 |
+
"learning_rate": 0.0005279605263157895,
|
| 772 |
+
"loss": 0.4533,
|
| 773 |
"step": 1080
|
| 774 |
},
|
| 775 |
{
|
| 776 |
"epoch": 1.6846986089644513,
|
| 777 |
+
"grad_norm": 0.002770961495116353,
|
| 778 |
+
"learning_rate": 0.0005032894736842105,
|
| 779 |
+
"loss": 0.4523,
|
| 780 |
"step": 1090
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 1.7001545595054095,
|
| 784 |
+
"grad_norm": 0.002901398576796055,
|
| 785 |
+
"learning_rate": 0.0004786184210526316,
|
| 786 |
+
"loss": 0.4472,
|
| 787 |
"step": 1100
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 1.7156105100463679,
|
| 791 |
+
"grad_norm": 0.002840624190866947,
|
| 792 |
+
"learning_rate": 0.0004539473684210526,
|
| 793 |
+
"loss": 0.4496,
|
| 794 |
"step": 1110
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 1.7310664605873263,
|
| 798 |
+
"grad_norm": 0.002452421234920621,
|
| 799 |
+
"learning_rate": 0.00042927631578947365,
|
| 800 |
+
"loss": 0.4553,
|
| 801 |
"step": 1120
|
| 802 |
},
|
| 803 |
{
|
| 804 |
"epoch": 1.7465224111282844,
|
| 805 |
+
"grad_norm": 0.0025857773143798113,
|
| 806 |
+
"learning_rate": 0.0004046052631578948,
|
| 807 |
+
"loss": 0.4504,
|
| 808 |
"step": 1130
|
| 809 |
},
|
| 810 |
{
|
| 811 |
"epoch": 1.7619783616692426,
|
| 812 |
+
"grad_norm": 0.002501491457223892,
|
| 813 |
+
"learning_rate": 0.0003799342105263158,
|
| 814 |
+
"loss": 0.4479,
|
| 815 |
"step": 1140
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 1.7774343122102008,
|
| 819 |
+
"grad_norm": 0.002639561193063855,
|
| 820 |
+
"learning_rate": 0.0003552631578947368,
|
| 821 |
+
"loss": 0.4627,
|
| 822 |
"step": 1150
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 1.7928902627511591,
|
| 826 |
+
"grad_norm": 0.002627423033118248,
|
| 827 |
+
"learning_rate": 0.0003305921052631579,
|
| 828 |
+
"loss": 0.4496,
|
| 829 |
"step": 1160
|
| 830 |
},
|
| 831 |
{
|
| 832 |
"epoch": 1.8083462132921175,
|
| 833 |
+
"grad_norm": 0.0027368138544261456,
|
| 834 |
+
"learning_rate": 0.00030592105263157896,
|
| 835 |
+
"loss": 0.4567,
|
| 836 |
"step": 1170
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 1.8238021638330757,
|
| 840 |
+
"grad_norm": 0.0022819822188466787,
|
| 841 |
+
"learning_rate": 0.00028125000000000003,
|
| 842 |
+
"loss": 0.4546,
|
| 843 |
"step": 1180
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 1.8392581143740339,
|
| 847 |
+
"grad_norm": 0.0024920173455029726,
|
| 848 |
+
"learning_rate": 0.00025657894736842105,
|
| 849 |
+
"loss": 0.4571,
|
| 850 |
"step": 1190
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"epoch": 1.8547140649149922,
|
| 854 |
+
"grad_norm": 0.002788729965686798,
|
| 855 |
+
"learning_rate": 0.00023190789473684213,
|
| 856 |
+
"loss": 0.4597,
|
| 857 |
"step": 1200
|
| 858 |
},
|
| 859 |
{
|
| 860 |
"epoch": 1.8701700154559506,
|
| 861 |
+
"grad_norm": 0.00281331455335021,
|
| 862 |
+
"learning_rate": 0.00020723684210526317,
|
| 863 |
+
"loss": 0.4561,
|
| 864 |
"step": 1210
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"epoch": 1.8856259659969088,
|
| 868 |
+
"grad_norm": 0.0028766875620931387,
|
| 869 |
+
"learning_rate": 0.00018256578947368422,
|
| 870 |
+
"loss": 0.4626,
|
| 871 |
"step": 1220
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 1.901081916537867,
|
| 875 |
+
"grad_norm": 0.0027803743723779917,
|
| 876 |
+
"learning_rate": 0.00015789473684210527,
|
| 877 |
+
"loss": 0.4441,
|
| 878 |
"step": 1230
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 1.9165378670788253,
|
| 882 |
+
"grad_norm": 0.0023476784117519855,
|
| 883 |
+
"learning_rate": 0.0001332236842105263,
|
| 884 |
+
"loss": 0.4529,
|
| 885 |
"step": 1240
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 1.9319938176197837,
|
| 889 |
+
"grad_norm": 0.003161880187690258,
|
| 890 |
+
"learning_rate": 0.00010855263157894737,
|
| 891 |
+
"loss": 0.4489,
|
| 892 |
"step": 1250
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 1.947449768160742,
|
| 896 |
+
"grad_norm": 0.0026641101576387882,
|
| 897 |
+
"learning_rate": 8.388157894736842e-05,
|
| 898 |
+
"loss": 0.4608,
|
| 899 |
"step": 1260
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 1.9629057187017,
|
| 903 |
+
"grad_norm": 0.002320705447345972,
|
| 904 |
+
"learning_rate": 5.921052631578947e-05,
|
| 905 |
+
"loss": 0.4608,
|
| 906 |
"step": 1270
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 1.9783616692426584,
|
| 910 |
+
"grad_norm": 0.0025752289220690727,
|
| 911 |
+
"learning_rate": 3.4539473684210524e-05,
|
| 912 |
+
"loss": 0.4466,
|
| 913 |
"step": 1280
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 1.9938176197836168,
|
| 917 |
+
"grad_norm": 0.0026244991458952427,
|
| 918 |
+
"learning_rate": 9.868421052631579e-06,
|
| 919 |
+
"loss": 0.4555,
|
| 920 |
"step": 1290
|
| 921 |
}
|
| 922 |
],
|
|
|
|
| 937 |
"attributes": {}
|
| 938 |
}
|
| 939 |
},
|
| 940 |
+
"total_flos": 1.3257051724162499e+18,
|
| 941 |
+
"train_batch_size": 4,
|
| 942 |
"trial_name": null,
|
| 943 |
"trial_params": null
|
| 944 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:751a143eac84ace0878962d5a6c61e00ae90313081b3e87461034dcd220797a8
|
| 3 |
size 5432
|