grids / r1_s2_lr1e-6 /trainer_state.json
Linksome's picture
Upload folder using huggingface_hub
eb7af77 verified
raw
history blame
7.32 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.32,
"grad_norm": 0.016585721146764668,
"learning_rate": 0.0,
"loss": 1.855,
"step": 1
},
{
"epoch": 0.64,
"grad_norm": 0.01677702929181964,
"learning_rate": 1e-06,
"loss": 1.9926,
"step": 2
},
{
"epoch": 0.96,
"grad_norm": 0.05073890028052113,
"learning_rate": 9.98378654067105e-07,
"loss": 1.9849,
"step": 3
},
{
"epoch": 1.0,
"grad_norm": 0.05073890028052113,
"learning_rate": 9.935251313189563e-07,
"loss": 1.9371,
"step": 4
},
{
"epoch": 1.32,
"grad_norm": 0.1536509017148004,
"learning_rate": 9.85470908713026e-07,
"loss": 1.8549,
"step": 5
},
{
"epoch": 1.6400000000000001,
"grad_norm": 0.015792830580800027,
"learning_rate": 9.742682209735727e-07,
"loss": 1.9926,
"step": 6
},
{
"epoch": 1.96,
"grad_norm": 0.05261997433384393,
"learning_rate": 9.599897218294121e-07,
"loss": 1.9848,
"step": 7
},
{
"epoch": 2.0,
"grad_norm": 0.05261997433384393,
"learning_rate": 9.427280128266049e-07,
"loss": 1.9361,
"step": 8
},
{
"epoch": 2.32,
"grad_norm": 0.2987070312238438,
"learning_rate": 9.225950427718974e-07,
"loss": 1.8548,
"step": 9
},
{
"epoch": 2.64,
"grad_norm": 0.017241858336362693,
"learning_rate": 8.997213817017506e-07,
"loss": 1.9925,
"step": 10
},
{
"epoch": 2.96,
"grad_norm": 0.05300382819081621,
"learning_rate": 8.742553740855505e-07,
"loss": 1.9848,
"step": 11
},
{
"epoch": 3.0,
"grad_norm": 0.05300382819081621,
"learning_rate": 8.463621767547997e-07,
"loss": 1.937,
"step": 12
},
{
"epoch": 3.32,
"grad_norm": 0.11174785150926758,
"learning_rate": 8.162226877976886e-07,
"loss": 1.8547,
"step": 13
},
{
"epoch": 3.64,
"grad_norm": 0.016349349252879262,
"learning_rate": 7.840323733655778e-07,
"loss": 1.9926,
"step": 14
},
{
"epoch": 3.96,
"grad_norm": 0.03459460400919377,
"learning_rate": 7.5e-07,
"loss": 1.9848,
"step": 15
},
{
"epoch": 4.0,
"grad_norm": 0.03459460400919377,
"learning_rate": 7.14346280701527e-07,
"loss": 1.9362,
"step": 16
},
{
"epoch": 4.32,
"grad_norm": 0.3422091567988848,
"learning_rate": 6.773024435212677e-07,
"loss": 1.855,
"step": 17
},
{
"epoch": 4.64,
"grad_norm": 0.01652565440862823,
"learning_rate": 6.391087319582263e-07,
"loss": 1.9925,
"step": 18
},
{
"epoch": 4.96,
"grad_norm": 0.028052540792361507,
"learning_rate": 6.000128468880222e-07,
"loss": 1.9848,
"step": 19
},
{
"epoch": 5.0,
"grad_norm": 0.028052540792361507,
"learning_rate": 5.602683401276614e-07,
"loss": 1.937,
"step": 20
},
{
"epoch": 5.32,
"grad_norm": 0.15562528914810267,
"learning_rate": 5.201329700547076e-07,
"loss": 1.8548,
"step": 21
},
{
"epoch": 5.64,
"grad_norm": 0.019674143915993505,
"learning_rate": 4.798670299452926e-07,
"loss": 1.9924,
"step": 22
},
{
"epoch": 5.96,
"grad_norm": 0.09623527051626159,
"learning_rate": 4.397316598723385e-07,
"loss": 1.9849,
"step": 23
},
{
"epoch": 6.0,
"grad_norm": 0.09623527051626159,
"learning_rate": 3.9998715311197783e-07,
"loss": 1.9368,
"step": 24
},
{
"epoch": 6.32,
"grad_norm": 0.11985804134909249,
"learning_rate": 3.6089126804177364e-07,
"loss": 1.8548,
"step": 25
},
{
"epoch": 6.64,
"grad_norm": 0.019682397443786706,
"learning_rate": 3.2269755647873214e-07,
"loss": 1.9925,
"step": 26
},
{
"epoch": 6.96,
"grad_norm": 0.023053888216924723,
"learning_rate": 2.856537192984728e-07,
"loss": 1.985,
"step": 27
},
{
"epoch": 7.0,
"grad_norm": 0.023053888216924723,
"learning_rate": 2.500000000000001e-07,
"loss": 1.9369,
"step": 28
},
{
"epoch": 7.32,
"grad_norm": 0.21719404416250201,
"learning_rate": 2.1596762663442213e-07,
"loss": 1.8548,
"step": 29
},
{
"epoch": 7.64,
"grad_norm": 0.021249978280051787,
"learning_rate": 1.837773122023114e-07,
"loss": 1.9924,
"step": 30
},
{
"epoch": 7.96,
"grad_norm": 0.019648806884757328,
"learning_rate": 1.536378232452003e-07,
"loss": 1.9849,
"step": 31
},
{
"epoch": 8.0,
"grad_norm": 0.410349000849933,
"learning_rate": 1.257446259144494e-07,
"loss": 1.9361,
"step": 32
},
{
"epoch": 8.32,
"grad_norm": 0.018918373716908438,
"learning_rate": 1.0027861829824952e-07,
"loss": 1.8548,
"step": 33
},
{
"epoch": 8.64,
"grad_norm": 0.016569819767445457,
"learning_rate": 7.740495722810269e-08,
"loss": 1.9925,
"step": 34
},
{
"epoch": 8.96,
"grad_norm": 0.107009520948546,
"learning_rate": 5.72719871733951e-08,
"loss": 1.9847,
"step": 35
},
{
"epoch": 9.0,
"grad_norm": 0.107009520948546,
"learning_rate": 4.0010278170587884e-08,
"loss": 1.9376,
"step": 36
},
{
"epoch": 9.32,
"grad_norm": 0.08365770322839408,
"learning_rate": 2.5731779026427257e-08,
"loss": 1.8548,
"step": 37
},
{
"epoch": 9.64,
"grad_norm": 0.016124977942298727,
"learning_rate": 1.4529091286973993e-08,
"loss": 1.9923,
"step": 38
},
{
"epoch": 9.96,
"grad_norm": 0.0871056137523833,
"learning_rate": 6.474868681043577e-09,
"loss": 1.9847,
"step": 39
},
{
"epoch": 10.0,
"grad_norm": 0.0871056137523833,
"learning_rate": 1.6213459328950352e-09,
"loss": 1.9372,
"step": 40
},
{
"epoch": 10.0,
"step": 40,
"total_flos": 174553779142656.0,
"train_loss": 1.942233791947365,
"train_runtime": 1437.3222,
"train_samples_per_second": 0.689,
"train_steps_per_second": 0.028
}
],
"logging_steps": 1,
"max_steps": 40,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 174553779142656.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}