Upload Step 80/9427
Browse files- adapter_config.json +1 -1
- adapter_model.safetensors +3 -0
- tokenizer_config.json +0 -1
- trainer_state.json +666 -0
adapter_config.json
CHANGED
|
@@ -6,7 +6,7 @@
|
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
| 8 |
"fan_in_fan_out": null,
|
| 9 |
-
"inference_mode":
|
| 10 |
"init_lora_weights": true,
|
| 11 |
"layer_replication": null,
|
| 12 |
"layers_pattern": null,
|
|
|
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
| 8 |
"fan_in_fan_out": null,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
"init_lora_weights": true,
|
| 11 |
"layer_replication": null,
|
| 12 |
"layers_pattern": null,
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d58e8b70cae140c27869d506ce1fd1f11fba30e54691e644d41e79743eee8cff
|
| 3 |
+
size 1907432232
|
tokenizer_config.json
CHANGED
|
@@ -51325,7 +51325,6 @@
|
|
| 51325 |
},
|
| 51326 |
"boi_token": "<start_of_image>",
|
| 51327 |
"bos_token": "<bos>",
|
| 51328 |
-
"chat_template": "{{- bos_token }}{% for message in messages %}{{ '<start_of_turn>' + ('model' if message['role'] == 'assistant' else message['role']) + '\n' + message['content'] | trim + '<end_of_turn>' }}{% if not loop.last %}{{ '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n<start_of_turn>model\n' }}{% endif %}",
|
| 51329 |
"clean_up_tokenization_spaces": false,
|
| 51330 |
"eoi_token": "<end_of_image>",
|
| 51331 |
"eos_token": "<end_of_turn>",
|
|
|
|
| 51325 |
},
|
| 51326 |
"boi_token": "<start_of_image>",
|
| 51327 |
"bos_token": "<bos>",
|
|
|
|
| 51328 |
"clean_up_tokenization_spaces": false,
|
| 51329 |
"eoi_token": "<end_of_image>",
|
| 51330 |
"eos_token": "<end_of_turn>",
|
trainer_state.json
ADDED
|
@@ -0,0 +1,666 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.008485812781755503,
|
| 6 |
+
"eval_steps": 10,
|
| 7 |
+
"global_step": 80,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00010607265977194378,
|
| 14 |
+
"grad_norm": 1.647079586982727,
|
| 15 |
+
"learning_rate": 4.99994960800331e-07,
|
| 16 |
+
"loss": 2.3252,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00010607265977194378,
|
| 21 |
+
"eval_loss": 2.388094663619995,
|
| 22 |
+
"eval_runtime": 67.0533,
|
| 23 |
+
"eval_samples_per_second": 1.909,
|
| 24 |
+
"eval_steps_per_second": 0.477,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.00021214531954388756,
|
| 29 |
+
"grad_norm": 1.7374595403671265,
|
| 30 |
+
"learning_rate": 4.999899206382888e-07,
|
| 31 |
+
"loss": 2.2091,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.00031821797931583137,
|
| 36 |
+
"grad_norm": 1.4541484117507935,
|
| 37 |
+
"learning_rate": 4.999848795135978e-07,
|
| 38 |
+
"loss": 2.4903,
|
| 39 |
+
"step": 3
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.0004242906390877751,
|
| 43 |
+
"grad_norm": 1.3729519844055176,
|
| 44 |
+
"learning_rate": 4.999798374259822e-07,
|
| 45 |
+
"loss": 2.3478,
|
| 46 |
+
"step": 4
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.0005303632988597189,
|
| 50 |
+
"grad_norm": 2.059835433959961,
|
| 51 |
+
"learning_rate": 4.999747943751658e-07,
|
| 52 |
+
"loss": 2.2294,
|
| 53 |
+
"step": 5
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.0006364359586316627,
|
| 57 |
+
"grad_norm": 1.4303361177444458,
|
| 58 |
+
"learning_rate": 4.999697503608729e-07,
|
| 59 |
+
"loss": 2.3702,
|
| 60 |
+
"step": 6
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.0007425086184036064,
|
| 64 |
+
"grad_norm": 1.506787657737732,
|
| 65 |
+
"learning_rate": 4.999647053828272e-07,
|
| 66 |
+
"loss": 2.2794,
|
| 67 |
+
"step": 7
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.0008485812781755502,
|
| 71 |
+
"grad_norm": 1.1569323539733887,
|
| 72 |
+
"learning_rate": 4.999596594407525e-07,
|
| 73 |
+
"loss": 2.2048,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.0009546539379474941,
|
| 78 |
+
"grad_norm": 1.0063825845718384,
|
| 79 |
+
"learning_rate": 4.999546125343724e-07,
|
| 80 |
+
"loss": 2.0392,
|
| 81 |
+
"step": 9
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.0010607265977194379,
|
| 85 |
+
"grad_norm": 1.2020900249481201,
|
| 86 |
+
"learning_rate": 4.999495646634105e-07,
|
| 87 |
+
"loss": 2.1371,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.0010607265977194379,
|
| 92 |
+
"eval_loss": 1.957827091217041,
|
| 93 |
+
"eval_runtime": 70.5284,
|
| 94 |
+
"eval_samples_per_second": 1.815,
|
| 95 |
+
"eval_steps_per_second": 0.454,
|
| 96 |
+
"step": 10
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.0011667992574913816,
|
| 100 |
+
"grad_norm": 0.9959272742271423,
|
| 101 |
+
"learning_rate": 4.999445158275902e-07,
|
| 102 |
+
"loss": 2.0418,
|
| 103 |
+
"step": 11
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.0012728719172633255,
|
| 107 |
+
"grad_norm": 0.8702138662338257,
|
| 108 |
+
"learning_rate": 4.999394660266349e-07,
|
| 109 |
+
"loss": 1.97,
|
| 110 |
+
"step": 12
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.0013789445770352692,
|
| 114 |
+
"grad_norm": 0.6772508025169373,
|
| 115 |
+
"learning_rate": 4.999344152602678e-07,
|
| 116 |
+
"loss": 1.6033,
|
| 117 |
+
"step": 13
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.0014850172368072129,
|
| 121 |
+
"grad_norm": 1.0128448009490967,
|
| 122 |
+
"learning_rate": 4.99929363528212e-07,
|
| 123 |
+
"loss": 2.1025,
|
| 124 |
+
"step": 14
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.0015910898965791568,
|
| 128 |
+
"grad_norm": 0.9335213899612427,
|
| 129 |
+
"learning_rate": 4.999243108301906e-07,
|
| 130 |
+
"loss": 1.9303,
|
| 131 |
+
"step": 15
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.0016971625563511005,
|
| 135 |
+
"grad_norm": 0.9497168660163879,
|
| 136 |
+
"learning_rate": 4.999192571659265e-07,
|
| 137 |
+
"loss": 1.8389,
|
| 138 |
+
"step": 16
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.0018032352161230442,
|
| 142 |
+
"grad_norm": 0.8370901346206665,
|
| 143 |
+
"learning_rate": 4.999142025351424e-07,
|
| 144 |
+
"loss": 1.8423,
|
| 145 |
+
"step": 17
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.0019093078758949881,
|
| 149 |
+
"grad_norm": 1.1051160097122192,
|
| 150 |
+
"learning_rate": 4.999091469375611e-07,
|
| 151 |
+
"loss": 1.9193,
|
| 152 |
+
"step": 18
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.002015380535666932,
|
| 156 |
+
"grad_norm": 1.2687193155288696,
|
| 157 |
+
"learning_rate": 4.999040903729051e-07,
|
| 158 |
+
"loss": 2.1474,
|
| 159 |
+
"step": 19
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.0021214531954388757,
|
| 163 |
+
"grad_norm": 0.9469927549362183,
|
| 164 |
+
"learning_rate": 4.99899032840897e-07,
|
| 165 |
+
"loss": 1.6744,
|
| 166 |
+
"step": 20
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.0021214531954388757,
|
| 170 |
+
"eval_loss": 1.7858046293258667,
|
| 171 |
+
"eval_runtime": 68.1877,
|
| 172 |
+
"eval_samples_per_second": 1.877,
|
| 173 |
+
"eval_steps_per_second": 0.469,
|
| 174 |
+
"step": 20
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.0022275258552108194,
|
| 178 |
+
"grad_norm": 0.9844200015068054,
|
| 179 |
+
"learning_rate": 4.998939743412591e-07,
|
| 180 |
+
"loss": 1.9173,
|
| 181 |
+
"step": 21
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.002333598514982763,
|
| 185 |
+
"grad_norm": 1.1347674131393433,
|
| 186 |
+
"learning_rate": 4.998889148737137e-07,
|
| 187 |
+
"loss": 1.8158,
|
| 188 |
+
"step": 22
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.002439671174754707,
|
| 192 |
+
"grad_norm": 1.0652062892913818,
|
| 193 |
+
"learning_rate": 4.99883854437983e-07,
|
| 194 |
+
"loss": 1.9189,
|
| 195 |
+
"step": 23
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.002545743834526651,
|
| 199 |
+
"grad_norm": 1.247801661491394,
|
| 200 |
+
"learning_rate": 4.998787930337891e-07,
|
| 201 |
+
"loss": 1.6044,
|
| 202 |
+
"step": 24
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.0026518164942985947,
|
| 206 |
+
"grad_norm": 0.856572151184082,
|
| 207 |
+
"learning_rate": 4.998737306608538e-07,
|
| 208 |
+
"loss": 1.9368,
|
| 209 |
+
"step": 25
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.0027578891540705384,
|
| 213 |
+
"grad_norm": 0.8902915716171265,
|
| 214 |
+
"learning_rate": 4.998686673188991e-07,
|
| 215 |
+
"loss": 1.7691,
|
| 216 |
+
"step": 26
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.002863961813842482,
|
| 220 |
+
"grad_norm": 0.9449676871299744,
|
| 221 |
+
"learning_rate": 4.998636030076468e-07,
|
| 222 |
+
"loss": 1.7605,
|
| 223 |
+
"step": 27
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.0029700344736144258,
|
| 227 |
+
"grad_norm": 0.7392516136169434,
|
| 228 |
+
"learning_rate": 4.998585377268183e-07,
|
| 229 |
+
"loss": 1.7255,
|
| 230 |
+
"step": 28
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.0030761071333863695,
|
| 234 |
+
"grad_norm": 0.8038751482963562,
|
| 235 |
+
"learning_rate": 4.998534714761353e-07,
|
| 236 |
+
"loss": 1.7689,
|
| 237 |
+
"step": 29
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.0031821797931583136,
|
| 241 |
+
"grad_norm": 0.8447410464286804,
|
| 242 |
+
"learning_rate": 4.998484042553191e-07,
|
| 243 |
+
"loss": 2.0482,
|
| 244 |
+
"step": 30
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.0031821797931583136,
|
| 248 |
+
"eval_loss": 1.6817430257797241,
|
| 249 |
+
"eval_runtime": 67.9443,
|
| 250 |
+
"eval_samples_per_second": 1.884,
|
| 251 |
+
"eval_steps_per_second": 0.471,
|
| 252 |
+
"step": 30
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.0032882524529302573,
|
| 256 |
+
"grad_norm": 0.8365817070007324,
|
| 257 |
+
"learning_rate": 4.998433360640912e-07,
|
| 258 |
+
"loss": 1.8075,
|
| 259 |
+
"step": 31
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.003394325112702201,
|
| 263 |
+
"grad_norm": 0.7525676488876343,
|
| 264 |
+
"learning_rate": 4.998382669021727e-07,
|
| 265 |
+
"loss": 1.6026,
|
| 266 |
+
"step": 32
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.0035003977724741447,
|
| 270 |
+
"grad_norm": 0.9553101658821106,
|
| 271 |
+
"learning_rate": 4.998331967692847e-07,
|
| 272 |
+
"loss": 1.743,
|
| 273 |
+
"step": 33
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.0036064704322460884,
|
| 277 |
+
"grad_norm": 0.966307520866394,
|
| 278 |
+
"learning_rate": 4.998281256651483e-07,
|
| 279 |
+
"loss": 1.7075,
|
| 280 |
+
"step": 34
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.0037125430920180325,
|
| 284 |
+
"grad_norm": 0.8701184988021851,
|
| 285 |
+
"learning_rate": 4.998230535894843e-07,
|
| 286 |
+
"loss": 1.6257,
|
| 287 |
+
"step": 35
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.0038186157517899762,
|
| 291 |
+
"grad_norm": 0.8450726866722107,
|
| 292 |
+
"learning_rate": 4.998179805420135e-07,
|
| 293 |
+
"loss": 1.8127,
|
| 294 |
+
"step": 36
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.00392468841156192,
|
| 298 |
+
"grad_norm": 0.8065881133079529,
|
| 299 |
+
"learning_rate": 4.998129065224565e-07,
|
| 300 |
+
"loss": 1.7574,
|
| 301 |
+
"step": 37
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.004030761071333864,
|
| 305 |
+
"grad_norm": 0.7674804925918579,
|
| 306 |
+
"learning_rate": 4.99807831530534e-07,
|
| 307 |
+
"loss": 1.6796,
|
| 308 |
+
"step": 38
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.004136833731105807,
|
| 312 |
+
"grad_norm": 0.8442147970199585,
|
| 313 |
+
"learning_rate": 4.998027555659665e-07,
|
| 314 |
+
"loss": 1.5551,
|
| 315 |
+
"step": 39
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.0042429063908777515,
|
| 319 |
+
"grad_norm": 0.7327367663383484,
|
| 320 |
+
"learning_rate": 4.99797678628474e-07,
|
| 321 |
+
"loss": 1.075,
|
| 322 |
+
"step": 40
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.0042429063908777515,
|
| 326 |
+
"eval_loss": 1.6100257635116577,
|
| 327 |
+
"eval_runtime": 67.9157,
|
| 328 |
+
"eval_samples_per_second": 1.885,
|
| 329 |
+
"eval_steps_per_second": 0.471,
|
| 330 |
+
"step": 40
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.004348979050649695,
|
| 334 |
+
"grad_norm": 0.8727586269378662,
|
| 335 |
+
"learning_rate": 4.997926007177772e-07,
|
| 336 |
+
"loss": 1.6814,
|
| 337 |
+
"step": 41
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.004455051710421639,
|
| 341 |
+
"grad_norm": 1.0420920848846436,
|
| 342 |
+
"learning_rate": 4.99787521833596e-07,
|
| 343 |
+
"loss": 1.6025,
|
| 344 |
+
"step": 42
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.004561124370193583,
|
| 348 |
+
"grad_norm": 0.757056713104248,
|
| 349 |
+
"learning_rate": 4.997824419756506e-07,
|
| 350 |
+
"loss": 1.7756,
|
| 351 |
+
"step": 43
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.004667197029965526,
|
| 355 |
+
"grad_norm": 0.9350019693374634,
|
| 356 |
+
"learning_rate": 4.997773611436606e-07,
|
| 357 |
+
"loss": 1.6165,
|
| 358 |
+
"step": 44
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.00477326968973747,
|
| 362 |
+
"grad_norm": 0.7474361062049866,
|
| 363 |
+
"learning_rate": 4.997722793373462e-07,
|
| 364 |
+
"loss": 1.8263,
|
| 365 |
+
"step": 45
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.004879342349509414,
|
| 369 |
+
"grad_norm": 0.6356221437454224,
|
| 370 |
+
"learning_rate": 4.997671965564268e-07,
|
| 371 |
+
"loss": 1.7313,
|
| 372 |
+
"step": 46
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.004985415009281358,
|
| 376 |
+
"grad_norm": 0.7225522398948669,
|
| 377 |
+
"learning_rate": 4.997621128006223e-07,
|
| 378 |
+
"loss": 1.8336,
|
| 379 |
+
"step": 47
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.005091487669053302,
|
| 383 |
+
"grad_norm": 0.7901801466941833,
|
| 384 |
+
"learning_rate": 4.997570280696519e-07,
|
| 385 |
+
"loss": 1.5573,
|
| 386 |
+
"step": 48
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.005197560328825245,
|
| 390 |
+
"grad_norm": 0.7901318073272705,
|
| 391 |
+
"learning_rate": 4.997519423632353e-07,
|
| 392 |
+
"loss": 1.5356,
|
| 393 |
+
"step": 49
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.005303632988597189,
|
| 397 |
+
"grad_norm": 0.7905575633049011,
|
| 398 |
+
"learning_rate": 4.997468556810914e-07,
|
| 399 |
+
"loss": 1.5592,
|
| 400 |
+
"step": 50
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.005303632988597189,
|
| 404 |
+
"eval_loss": 1.565526008605957,
|
| 405 |
+
"eval_runtime": 68.1883,
|
| 406 |
+
"eval_samples_per_second": 1.877,
|
| 407 |
+
"eval_steps_per_second": 0.469,
|
| 408 |
+
"step": 50
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.005409705648369133,
|
| 412 |
+
"grad_norm": 0.7927577495574951,
|
| 413 |
+
"learning_rate": 4.997417680229397e-07,
|
| 414 |
+
"loss": 1.8136,
|
| 415 |
+
"step": 51
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.005515778308141077,
|
| 419 |
+
"grad_norm": 0.6780912280082703,
|
| 420 |
+
"learning_rate": 4.997366793884992e-07,
|
| 421 |
+
"loss": 1.635,
|
| 422 |
+
"step": 52
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.005621850967913021,
|
| 426 |
+
"grad_norm": 0.6629224419593811,
|
| 427 |
+
"learning_rate": 4.997315897774888e-07,
|
| 428 |
+
"loss": 1.6814,
|
| 429 |
+
"step": 53
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.005727923627684964,
|
| 433 |
+
"grad_norm": 0.6568951606750488,
|
| 434 |
+
"learning_rate": 4.997264991896272e-07,
|
| 435 |
+
"loss": 1.7656,
|
| 436 |
+
"step": 54
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.005833996287456908,
|
| 440 |
+
"grad_norm": 0.9639095664024353,
|
| 441 |
+
"learning_rate": 4.997214076246334e-07,
|
| 442 |
+
"loss": 1.6255,
|
| 443 |
+
"step": 55
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.0059400689472288515,
|
| 447 |
+
"grad_norm": 1.7226521968841553,
|
| 448 |
+
"learning_rate": 4.99716315082226e-07,
|
| 449 |
+
"loss": 1.6617,
|
| 450 |
+
"step": 56
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.006046141607000796,
|
| 454 |
+
"grad_norm": 0.7537712454795837,
|
| 455 |
+
"learning_rate": 4.997112215621234e-07,
|
| 456 |
+
"loss": 1.7756,
|
| 457 |
+
"step": 57
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.006152214266772739,
|
| 461 |
+
"grad_norm": 0.5914387702941895,
|
| 462 |
+
"learning_rate": 4.99706127064044e-07,
|
| 463 |
+
"loss": 1.4576,
|
| 464 |
+
"step": 58
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.006258286926544683,
|
| 468 |
+
"grad_norm": 0.5612177848815918,
|
| 469 |
+
"learning_rate": 4.997010315877063e-07,
|
| 470 |
+
"loss": 1.6828,
|
| 471 |
+
"step": 59
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.006364359586316627,
|
| 475 |
+
"grad_norm": 0.6786366701126099,
|
| 476 |
+
"learning_rate": 4.996959351328284e-07,
|
| 477 |
+
"loss": 1.7288,
|
| 478 |
+
"step": 60
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.006364359586316627,
|
| 482 |
+
"eval_loss": 1.537359356880188,
|
| 483 |
+
"eval_runtime": 67.7518,
|
| 484 |
+
"eval_samples_per_second": 1.889,
|
| 485 |
+
"eval_steps_per_second": 0.472,
|
| 486 |
+
"step": 60
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.0064704322460885704,
|
| 490 |
+
"grad_norm": 0.678156316280365,
|
| 491 |
+
"learning_rate": 4.996908376991283e-07,
|
| 492 |
+
"loss": 1.5268,
|
| 493 |
+
"step": 61
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.006576504905860515,
|
| 497 |
+
"grad_norm": 0.6791099905967712,
|
| 498 |
+
"learning_rate": 4.99685739286324e-07,
|
| 499 |
+
"loss": 1.5498,
|
| 500 |
+
"step": 62
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.006682577565632458,
|
| 504 |
+
"grad_norm": 0.702700674533844,
|
| 505 |
+
"learning_rate": 4.996806398941335e-07,
|
| 506 |
+
"loss": 1.6741,
|
| 507 |
+
"step": 63
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.006788650225404402,
|
| 511 |
+
"grad_norm": 0.8344963788986206,
|
| 512 |
+
"learning_rate": 4.996755395222746e-07,
|
| 513 |
+
"loss": 1.6074,
|
| 514 |
+
"step": 64
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.006894722885176346,
|
| 518 |
+
"grad_norm": 3.9447405338287354,
|
| 519 |
+
"learning_rate": 4.996704381704648e-07,
|
| 520 |
+
"loss": 1.5762,
|
| 521 |
+
"step": 65
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.007000795544948289,
|
| 525 |
+
"grad_norm": 0.870587170124054,
|
| 526 |
+
"learning_rate": 4.996653358384218e-07,
|
| 527 |
+
"loss": 1.6515,
|
| 528 |
+
"step": 66
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.0071068682047202335,
|
| 532 |
+
"grad_norm": 0.5930059552192688,
|
| 533 |
+
"learning_rate": 4.996602325258629e-07,
|
| 534 |
+
"loss": 1.7334,
|
| 535 |
+
"step": 67
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.007212940864492177,
|
| 539 |
+
"grad_norm": 1.2227728366851807,
|
| 540 |
+
"learning_rate": 4.996551282325055e-07,
|
| 541 |
+
"loss": 1.3723,
|
| 542 |
+
"step": 68
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.007319013524264121,
|
| 546 |
+
"grad_norm": 1.1175763607025146,
|
| 547 |
+
"learning_rate": 4.996500229580668e-07,
|
| 548 |
+
"loss": 1.4476,
|
| 549 |
+
"step": 69
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.007425086184036065,
|
| 553 |
+
"grad_norm": 0.591778039932251,
|
| 554 |
+
"learning_rate": 4.99644916702264e-07,
|
| 555 |
+
"loss": 1.2612,
|
| 556 |
+
"step": 70
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.007425086184036065,
|
| 560 |
+
"eval_loss": 1.5133857727050781,
|
| 561 |
+
"eval_runtime": 68.2036,
|
| 562 |
+
"eval_samples_per_second": 1.877,
|
| 563 |
+
"eval_steps_per_second": 0.469,
|
| 564 |
+
"step": 70
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.007531158843808008,
|
| 568 |
+
"grad_norm": 0.62836754322052,
|
| 569 |
+
"learning_rate": 4.99639809464814e-07,
|
| 570 |
+
"loss": 1.4586,
|
| 571 |
+
"step": 71
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.0076372315035799524,
|
| 575 |
+
"grad_norm": 0.779591977596283,
|
| 576 |
+
"learning_rate": 4.996347012454338e-07,
|
| 577 |
+
"loss": 1.4937,
|
| 578 |
+
"step": 72
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.007743304163351896,
|
| 582 |
+
"grad_norm": 0.7092106342315674,
|
| 583 |
+
"learning_rate": 4.9962959204384e-07,
|
| 584 |
+
"loss": 1.74,
|
| 585 |
+
"step": 73
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.00784937682312384,
|
| 589 |
+
"grad_norm": 0.5990781188011169,
|
| 590 |
+
"learning_rate": 4.996244818597496e-07,
|
| 591 |
+
"loss": 1.3733,
|
| 592 |
+
"step": 74
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.007955449482895784,
|
| 596 |
+
"grad_norm": 0.7790846824645996,
|
| 597 |
+
"learning_rate": 4.996193706928789e-07,
|
| 598 |
+
"loss": 1.5198,
|
| 599 |
+
"step": 75
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.008061522142667728,
|
| 603 |
+
"grad_norm": 0.746094286441803,
|
| 604 |
+
"learning_rate": 4.996142585429444e-07,
|
| 605 |
+
"loss": 1.3825,
|
| 606 |
+
"step": 76
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.00816759480243967,
|
| 610 |
+
"grad_norm": 1.385066032409668,
|
| 611 |
+
"learning_rate": 4.996091454096626e-07,
|
| 612 |
+
"loss": 1.473,
|
| 613 |
+
"step": 77
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.008273667462211615,
|
| 617 |
+
"grad_norm": 0.6657389402389526,
|
| 618 |
+
"learning_rate": 4.996040312927497e-07,
|
| 619 |
+
"loss": 1.6375,
|
| 620 |
+
"step": 78
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.008379740121983559,
|
| 624 |
+
"grad_norm": 1.1722540855407715,
|
| 625 |
+
"learning_rate": 4.995989161919216e-07,
|
| 626 |
+
"loss": 1.5355,
|
| 627 |
+
"step": 79
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.008485812781755503,
|
| 631 |
+
"grad_norm": 0.7716183066368103,
|
| 632 |
+
"learning_rate": 4.995938001068947e-07,
|
| 633 |
+
"loss": 1.6588,
|
| 634 |
+
"step": 80
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.008485812781755503,
|
| 638 |
+
"eval_loss": 1.4981476068496704,
|
| 639 |
+
"eval_runtime": 67.8094,
|
| 640 |
+
"eval_samples_per_second": 1.888,
|
| 641 |
+
"eval_steps_per_second": 0.472,
|
| 642 |
+
"step": 80
|
| 643 |
+
}
|
| 644 |
+
],
|
| 645 |
+
"logging_steps": 1,
|
| 646 |
+
"max_steps": 9427,
|
| 647 |
+
"num_input_tokens_seen": 0,
|
| 648 |
+
"num_train_epochs": 1,
|
| 649 |
+
"save_steps": 10,
|
| 650 |
+
"stateful_callbacks": {
|
| 651 |
+
"TrainerControl": {
|
| 652 |
+
"args": {
|
| 653 |
+
"should_epoch_stop": false,
|
| 654 |
+
"should_evaluate": false,
|
| 655 |
+
"should_log": false,
|
| 656 |
+
"should_save": true,
|
| 657 |
+
"should_training_stop": false
|
| 658 |
+
},
|
| 659 |
+
"attributes": {}
|
| 660 |
+
}
|
| 661 |
+
},
|
| 662 |
+
"total_flos": 1.2900468007108608e+17,
|
| 663 |
+
"train_batch_size": 4,
|
| 664 |
+
"trial_name": null,
|
| 665 |
+
"trial_params": null
|
| 666 |
+
}
|