Bmcbob76's picture
Upload folder using huggingface_hub
df85265 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 348,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.028735632183908046,
"grad_norm": 0.8072805404663086,
"learning_rate": 2e-05,
"loss": 1.7898,
"step": 10
},
{
"epoch": 0.05747126436781609,
"grad_norm": 0.6283612251281738,
"learning_rate": 4e-05,
"loss": 1.6875,
"step": 20
},
{
"epoch": 0.08620689655172414,
"grad_norm": 0.23733901977539062,
"learning_rate": 6e-05,
"loss": 1.4832,
"step": 30
},
{
"epoch": 0.11494252873563218,
"grad_norm": 0.1981637328863144,
"learning_rate": 8e-05,
"loss": 1.345,
"step": 40
},
{
"epoch": 0.14367816091954022,
"grad_norm": 0.1799236387014389,
"learning_rate": 0.0001,
"loss": 1.2702,
"step": 50
},
{
"epoch": 0.1724137931034483,
"grad_norm": 0.18760177493095398,
"learning_rate": 0.00012,
"loss": 1.1828,
"step": 60
},
{
"epoch": 0.20114942528735633,
"grad_norm": 0.20481795072555542,
"learning_rate": 0.00014,
"loss": 1.0705,
"step": 70
},
{
"epoch": 0.22988505747126436,
"grad_norm": 0.1976660043001175,
"learning_rate": 0.00016,
"loss": 1.0142,
"step": 80
},
{
"epoch": 0.25862068965517243,
"grad_norm": 0.19467692077159882,
"learning_rate": 0.00018,
"loss": 0.9836,
"step": 90
},
{
"epoch": 0.28735632183908044,
"grad_norm": 0.2101747691631317,
"learning_rate": 0.0002,
"loss": 0.931,
"step": 100
},
{
"epoch": 0.3160919540229885,
"grad_norm": 0.20452211797237396,
"learning_rate": 0.0001991987177050743,
"loss": 0.9278,
"step": 110
},
{
"epoch": 0.3448275862068966,
"grad_norm": 0.2148609310388565,
"learning_rate": 0.00019680771188662044,
"loss": 0.9256,
"step": 120
},
{
"epoch": 0.3735632183908046,
"grad_norm": 0.22379422187805176,
"learning_rate": 0.00019286529995722623,
"loss": 0.894,
"step": 130
},
{
"epoch": 0.40229885057471265,
"grad_norm": 0.2331877499818802,
"learning_rate": 0.00018743466161445823,
"loss": 0.902,
"step": 140
},
{
"epoch": 0.43103448275862066,
"grad_norm": 0.20595517754554749,
"learning_rate": 0.00018060282634540053,
"loss": 0.8704,
"step": 150
},
{
"epoch": 0.45977011494252873,
"grad_norm": 0.21600735187530518,
"learning_rate": 0.000172479278722912,
"loss": 0.8608,
"step": 160
},
{
"epoch": 0.4885057471264368,
"grad_norm": 0.2313130795955658,
"learning_rate": 0.0001631942038446304,
"loss": 0.8826,
"step": 170
},
{
"epoch": 0.5172413793103449,
"grad_norm": 0.20651616156101227,
"learning_rate": 0.00015289640103269625,
"loss": 0.8572,
"step": 180
},
{
"epoch": 0.5459770114942529,
"grad_norm": 0.20882922410964966,
"learning_rate": 0.00014175089922850633,
"loss": 0.8525,
"step": 190
},
{
"epoch": 0.5747126436781609,
"grad_norm": 0.22696492075920105,
"learning_rate": 0.00012993631229733582,
"loss": 0.8716,
"step": 200
},
{
"epoch": 0.603448275862069,
"grad_norm": 0.22658249735832214,
"learning_rate": 0.00011764197662578086,
"loss": 0.8412,
"step": 210
},
{
"epoch": 0.632183908045977,
"grad_norm": 0.23941652476787567,
"learning_rate": 0.00010506491688387127,
"loss": 0.8365,
"step": 220
},
{
"epoch": 0.6609195402298851,
"grad_norm": 0.22170934081077576,
"learning_rate": 9.24066885774754e-05,
"loss": 0.8233,
"step": 230
},
{
"epoch": 0.6896551724137931,
"grad_norm": 0.2426789551973343,
"learning_rate": 7.987014799113397e-05,
"loss": 0.8493,
"step": 240
},
{
"epoch": 0.7183908045977011,
"grad_norm": 0.22542227804660797,
"learning_rate": 6.765620128507619e-05,
"loss": 0.821,
"step": 250
},
{
"epoch": 0.7471264367816092,
"grad_norm": 0.22178752720355988,
"learning_rate": 5.596058484423656e-05,
"loss": 0.8508,
"step": 260
},
{
"epoch": 0.7758620689655172,
"grad_norm": 0.252038836479187,
"learning_rate": 4.497072847626087e-05,
"loss": 0.7971,
"step": 270
},
{
"epoch": 0.8045977011494253,
"grad_norm": 0.23275329172611237,
"learning_rate": 3.4862751727777797e-05,
"loss": 0.8318,
"step": 280
},
{
"epoch": 0.8333333333333334,
"grad_norm": 0.21456491947174072,
"learning_rate": 2.5798641454908944e-05,
"loss": 0.8173,
"step": 290
},
{
"epoch": 0.8620689655172413,
"grad_norm": 0.2146165668964386,
"learning_rate": 1.7923655879272393e-05,
"loss": 0.8333,
"step": 300
},
{
"epoch": 0.8908045977011494,
"grad_norm": 0.2362869381904602,
"learning_rate": 1.1363996731159188e-05,
"loss": 0.8264,
"step": 310
},
{
"epoch": 0.9195402298850575,
"grad_norm": 0.21657893061637878,
"learning_rate": 6.22478678529197e-06,
"loss": 0.8308,
"step": 320
},
{
"epoch": 0.9482758620689655,
"grad_norm": 0.2201039046049118,
"learning_rate": 2.5883852004613074e-06,
"loss": 0.8094,
"step": 330
},
{
"epoch": 0.9770114942528736,
"grad_norm": 0.22542646527290344,
"learning_rate": 5.130676608104845e-07,
"loss": 0.8295,
"step": 340
}
],
"logging_steps": 10,
"max_steps": 348,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.843723397844173e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}