initial model
Browse files- adapter_config.json +18 -0
- adapter_model.bin +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/pytorch_model.bin +3 -0
- checkpoint-200/rng_state_0.pth +3 -0
- checkpoint-200/rng_state_1.pth +3 -0
- checkpoint-200/scaler.pt +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/trainer_state.json +144 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/pytorch_model.bin +3 -0
- checkpoint-400/rng_state_0.pth +3 -0
- checkpoint-400/rng_state_1.pth +3 -0
- checkpoint-400/scaler.pt +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/trainer_state.json +272 -0
- checkpoint-400/training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"merge_weights": false,
|
| 10 |
+
"modules_to_save": null,
|
| 11 |
+
"peft_type": "LORA",
|
| 12 |
+
"r": 8,
|
| 13 |
+
"target_modules": [
|
| 14 |
+
"q_proj",
|
| 15 |
+
"v_proj"
|
| 16 |
+
],
|
| 17 |
+
"task_type": "CAUSAL_LM"
|
| 18 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccdbcad69869bf594f349e4eccc108fb999870727d443e0c305cdc6780b9d8a5
|
| 3 |
+
size 16822989
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a454a55399dbcc7bf6cee202de695a5af937e2213e0924c69116bf9656574470
|
| 3 |
+
size 33661637
|
checkpoint-200/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67b74b143ee9d64be02f59dfc2f7476d27b729facf4d59d1717f3b8597bd868f
|
| 3 |
+
size 16822989
|
checkpoint-200/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9fb021d61dc03b443f46484dbcc9ff4a4b4b033533973ad9f2919552bebc035
|
| 3 |
+
size 14583
|
checkpoint-200/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:596bb9d532f79a5e882c32e4abe9adcc647c4a8b1e20f9e26eb0dd531136123a
|
| 3 |
+
size 14583
|
checkpoint-200/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fccf0f9be1bb8f24861e4393745b3e09cc2687125a69e3757955fb0f0925ea5
|
| 3 |
+
size 557
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a54726405c25312619dafb87a6ce7677b28a287da713b7e5d18fb8509cff4d34
|
| 3 |
+
size 627
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6641973853111267,
|
| 3 |
+
"best_model_checkpoint": "./lora-alpaca/checkpoint-200",
|
| 4 |
+
"epoch": 0.47058823529411764,
|
| 5 |
+
"global_step": 200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 2.0163,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 1.9284,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 1.77,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 0.00011999999999999999,
|
| 31 |
+
"loss": 1.3452,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 0.00015,
|
| 37 |
+
"loss": 0.9243,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.14,
|
| 42 |
+
"learning_rate": 0.00017999999999999998,
|
| 43 |
+
"loss": 0.8385,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"learning_rate": 0.00020999999999999998,
|
| 49 |
+
"loss": 0.7986,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"learning_rate": 0.00023999999999999998,
|
| 55 |
+
"loss": 0.7786,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.21,
|
| 60 |
+
"learning_rate": 0.00027,
|
| 61 |
+
"loss": 0.75,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.24,
|
| 66 |
+
"learning_rate": 0.0003,
|
| 67 |
+
"loss": 0.7389,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.26,
|
| 72 |
+
"learning_rate": 0.00029076923076923073,
|
| 73 |
+
"loss": 0.7248,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.28,
|
| 78 |
+
"learning_rate": 0.0002815384615384615,
|
| 79 |
+
"loss": 0.7199,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.31,
|
| 84 |
+
"learning_rate": 0.0002723076923076923,
|
| 85 |
+
"loss": 0.7159,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.33,
|
| 90 |
+
"learning_rate": 0.00026307692307692306,
|
| 91 |
+
"loss": 0.7029,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.35,
|
| 96 |
+
"learning_rate": 0.0002538461538461538,
|
| 97 |
+
"loss": 0.6851,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.38,
|
| 102 |
+
"learning_rate": 0.0002446153846153846,
|
| 103 |
+
"loss": 0.6935,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.4,
|
| 108 |
+
"learning_rate": 0.00023538461538461536,
|
| 109 |
+
"loss": 0.6737,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.42,
|
| 114 |
+
"learning_rate": 0.00022615384615384614,
|
| 115 |
+
"loss": 0.682,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.45,
|
| 120 |
+
"learning_rate": 0.0002169230769230769,
|
| 121 |
+
"loss": 0.667,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.47,
|
| 126 |
+
"learning_rate": 0.00020769230769230766,
|
| 127 |
+
"loss": 0.6731,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.47,
|
| 132 |
+
"eval_loss": 0.6641973853111267,
|
| 133 |
+
"eval_runtime": 178.902,
|
| 134 |
+
"eval_samples_per_second": 11.179,
|
| 135 |
+
"eval_steps_per_second": 0.699,
|
| 136 |
+
"step": 200
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"max_steps": 425,
|
| 140 |
+
"num_train_epochs": 1,
|
| 141 |
+
"total_flos": 2.5997626021249024e+17,
|
| 142 |
+
"trial_name": null,
|
| 143 |
+
"trial_params": null
|
| 144 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679c6089ef028b124c19113a1558bfe7f60e15c0767946619f59895cd9ea231
|
| 3 |
+
size 3579
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:338e35e2f2224170dac24ad577310705caa21aa0f26e94b16829a5d035341b89
|
| 3 |
+
size 33661637
|
checkpoint-400/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a85d1b931da72a087062454739e905aac3c49d14c2342c365dd8c2abf823a4f
|
| 3 |
+
size 16822989
|
checkpoint-400/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c1988d1563ea62c5063e73d71f22375abe0e35e54465f2e96b0be2b018dd560
|
| 3 |
+
size 14583
|
checkpoint-400/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3b3edb3825dbf1201ee57ee4e624ef7a3ee91ae3c454ddf106a03a8d9791ec7
|
| 3 |
+
size 14583
|
checkpoint-400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc40a4be6a52cee4d7658df4041e660ffa02b0d8b5bd143bb8bb397f7b71b1a5
|
| 3 |
+
size 557
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:843d000e05e858072d27fb3f24005b2f559c8a83f79eb5942b2002574a2452c2
|
| 3 |
+
size 627
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,272 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6302221417427063,
|
| 3 |
+
"best_model_checkpoint": "./lora-alpaca/checkpoint-400",
|
| 4 |
+
"epoch": 0.9411764705882353,
|
| 5 |
+
"global_step": 400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 2.0163,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 1.9284,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 1.77,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 0.00011999999999999999,
|
| 31 |
+
"loss": 1.3452,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 0.00015,
|
| 37 |
+
"loss": 0.9243,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.14,
|
| 42 |
+
"learning_rate": 0.00017999999999999998,
|
| 43 |
+
"loss": 0.8385,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"learning_rate": 0.00020999999999999998,
|
| 49 |
+
"loss": 0.7986,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.19,
|
| 54 |
+
"learning_rate": 0.00023999999999999998,
|
| 55 |
+
"loss": 0.7786,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.21,
|
| 60 |
+
"learning_rate": 0.00027,
|
| 61 |
+
"loss": 0.75,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.24,
|
| 66 |
+
"learning_rate": 0.0003,
|
| 67 |
+
"loss": 0.7389,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.26,
|
| 72 |
+
"learning_rate": 0.00029076923076923073,
|
| 73 |
+
"loss": 0.7248,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.28,
|
| 78 |
+
"learning_rate": 0.0002815384615384615,
|
| 79 |
+
"loss": 0.7199,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.31,
|
| 84 |
+
"learning_rate": 0.0002723076923076923,
|
| 85 |
+
"loss": 0.7159,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.33,
|
| 90 |
+
"learning_rate": 0.00026307692307692306,
|
| 91 |
+
"loss": 0.7029,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.35,
|
| 96 |
+
"learning_rate": 0.0002538461538461538,
|
| 97 |
+
"loss": 0.6851,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.38,
|
| 102 |
+
"learning_rate": 0.0002446153846153846,
|
| 103 |
+
"loss": 0.6935,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.4,
|
| 108 |
+
"learning_rate": 0.00023538461538461536,
|
| 109 |
+
"loss": 0.6737,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.42,
|
| 114 |
+
"learning_rate": 0.00022615384615384614,
|
| 115 |
+
"loss": 0.682,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.45,
|
| 120 |
+
"learning_rate": 0.0002169230769230769,
|
| 121 |
+
"loss": 0.667,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.47,
|
| 126 |
+
"learning_rate": 0.00020769230769230766,
|
| 127 |
+
"loss": 0.6731,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.47,
|
| 132 |
+
"eval_loss": 0.6641973853111267,
|
| 133 |
+
"eval_runtime": 178.902,
|
| 134 |
+
"eval_samples_per_second": 11.179,
|
| 135 |
+
"eval_steps_per_second": 0.699,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.49,
|
| 140 |
+
"learning_rate": 0.00019846153846153844,
|
| 141 |
+
"loss": 0.6631,
|
| 142 |
+
"step": 210
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.52,
|
| 146 |
+
"learning_rate": 0.0001892307692307692,
|
| 147 |
+
"loss": 0.6652,
|
| 148 |
+
"step": 220
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.54,
|
| 152 |
+
"learning_rate": 0.00017999999999999998,
|
| 153 |
+
"loss": 0.6591,
|
| 154 |
+
"step": 230
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.56,
|
| 158 |
+
"learning_rate": 0.00017076923076923074,
|
| 159 |
+
"loss": 0.6605,
|
| 160 |
+
"step": 240
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.59,
|
| 164 |
+
"learning_rate": 0.00016153846153846153,
|
| 165 |
+
"loss": 0.653,
|
| 166 |
+
"step": 250
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.61,
|
| 170 |
+
"learning_rate": 0.00015230769230769228,
|
| 171 |
+
"loss": 0.6574,
|
| 172 |
+
"step": 260
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.64,
|
| 176 |
+
"learning_rate": 0.00014307692307692307,
|
| 177 |
+
"loss": 0.6545,
|
| 178 |
+
"step": 270
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.66,
|
| 182 |
+
"learning_rate": 0.00013384615384615385,
|
| 183 |
+
"loss": 0.6328,
|
| 184 |
+
"step": 280
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.68,
|
| 188 |
+
"learning_rate": 0.0001246153846153846,
|
| 189 |
+
"loss": 0.6485,
|
| 190 |
+
"step": 290
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.71,
|
| 194 |
+
"learning_rate": 0.00011538461538461538,
|
| 195 |
+
"loss": 0.6477,
|
| 196 |
+
"step": 300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.73,
|
| 200 |
+
"learning_rate": 0.00010615384615384615,
|
| 201 |
+
"loss": 0.639,
|
| 202 |
+
"step": 310
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.75,
|
| 206 |
+
"learning_rate": 9.692307692307692e-05,
|
| 207 |
+
"loss": 0.6384,
|
| 208 |
+
"step": 320
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.78,
|
| 212 |
+
"learning_rate": 8.76923076923077e-05,
|
| 213 |
+
"loss": 0.6338,
|
| 214 |
+
"step": 330
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.8,
|
| 218 |
+
"learning_rate": 7.846153846153845e-05,
|
| 219 |
+
"loss": 0.6394,
|
| 220 |
+
"step": 340
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.82,
|
| 224 |
+
"learning_rate": 6.923076923076922e-05,
|
| 225 |
+
"loss": 0.6345,
|
| 226 |
+
"step": 350
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.85,
|
| 230 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 231 |
+
"loss": 0.6424,
|
| 232 |
+
"step": 360
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.87,
|
| 236 |
+
"learning_rate": 5.0769230769230766e-05,
|
| 237 |
+
"loss": 0.6271,
|
| 238 |
+
"step": 370
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.89,
|
| 242 |
+
"learning_rate": 4.153846153846154e-05,
|
| 243 |
+
"loss": 0.6267,
|
| 244 |
+
"step": 380
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.92,
|
| 248 |
+
"learning_rate": 3.230769230769231e-05,
|
| 249 |
+
"loss": 0.642,
|
| 250 |
+
"step": 390
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.94,
|
| 254 |
+
"learning_rate": 2.3076923076923076e-05,
|
| 255 |
+
"loss": 0.6389,
|
| 256 |
+
"step": 400
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.94,
|
| 260 |
+
"eval_loss": 0.6302221417427063,
|
| 261 |
+
"eval_runtime": 177.453,
|
| 262 |
+
"eval_samples_per_second": 11.271,
|
| 263 |
+
"eval_steps_per_second": 0.704,
|
| 264 |
+
"step": 400
|
| 265 |
+
}
|
| 266 |
+
],
|
| 267 |
+
"max_steps": 425,
|
| 268 |
+
"num_train_epochs": 1,
|
| 269 |
+
"total_flos": 5.199525204249805e+17,
|
| 270 |
+
"trial_name": null,
|
| 271 |
+
"trial_params": null
|
| 272 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679c6089ef028b124c19113a1558bfe7f60e15c0767946619f59895cd9ea231
|
| 3 |
+
size 3579
|