|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.847457627118644, |
|
"eval_steps": 500, |
|
"global_step": 160, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06779661016949153, |
|
"grad_norm": 3.306018590927124, |
|
"learning_rate": 9.999125804563732e-05, |
|
"loss": 2.1358, |
|
"num_input_tokens_seen": 10896, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.13559322033898305, |
|
"grad_norm": 2.0162065029144287, |
|
"learning_rate": 9.996503523941994e-05, |
|
"loss": 2.3575, |
|
"num_input_tokens_seen": 20512, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.2033898305084746, |
|
"grad_norm": 2.1740899085998535, |
|
"learning_rate": 9.992134075089084e-05, |
|
"loss": 1.4712, |
|
"num_input_tokens_seen": 29984, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.2711864406779661, |
|
"grad_norm": 2.0339269638061523, |
|
"learning_rate": 9.986018985905901e-05, |
|
"loss": 2.3124, |
|
"num_input_tokens_seen": 39760, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.3389830508474576, |
|
"grad_norm": 1.0339545011520386, |
|
"learning_rate": 9.978160394705668e-05, |
|
"loss": 1.8062, |
|
"num_input_tokens_seen": 49856, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.4067796610169492, |
|
"grad_norm": 0.6279817819595337, |
|
"learning_rate": 9.968561049466214e-05, |
|
"loss": 2.0499, |
|
"num_input_tokens_seen": 60208, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.4745762711864407, |
|
"grad_norm": 0.5110039114952087, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 1.1603, |
|
"num_input_tokens_seen": 70816, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.5423728813559322, |
|
"grad_norm": 0.8199847936630249, |
|
"learning_rate": 9.944154131125642e-05, |
|
"loss": 1.9923, |
|
"num_input_tokens_seen": 79968, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.6101694915254238, |
|
"grad_norm": 0.729006290435791, |
|
"learning_rate": 9.92935509259118e-05, |
|
"loss": 1.9688, |
|
"num_input_tokens_seen": 89472, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.6779661016949152, |
|
"grad_norm": 1.2717365026474, |
|
"learning_rate": 9.912832366166442e-05, |
|
"loss": 2.2878, |
|
"num_input_tokens_seen": 100336, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.7457627118644068, |
|
"grad_norm": 0.6771590113639832, |
|
"learning_rate": 9.894591729488242e-05, |
|
"loss": 2.001, |
|
"num_input_tokens_seen": 110640, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.8135593220338984, |
|
"grad_norm": 0.4566394090652466, |
|
"learning_rate": 9.874639560909117e-05, |
|
"loss": 1.8458, |
|
"num_input_tokens_seen": 120304, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.8813559322033898, |
|
"grad_norm": 0.6037254929542542, |
|
"learning_rate": 9.852982837266955e-05, |
|
"loss": 1.8775, |
|
"num_input_tokens_seen": 128288, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.9491525423728814, |
|
"grad_norm": 0.6338982582092285, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 1.9309, |
|
"num_input_tokens_seen": 138624, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 1.0169491525423728, |
|
"grad_norm": 0.5118916630744934, |
|
"learning_rate": 9.804586609725499e-05, |
|
"loss": 1.5507, |
|
"num_input_tokens_seen": 148208, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 1.0847457627118644, |
|
"grad_norm": 0.4119274914264679, |
|
"learning_rate": 9.777864028930705e-05, |
|
"loss": 1.6802, |
|
"num_input_tokens_seen": 159200, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 1.152542372881356, |
|
"grad_norm": 0.5065487623214722, |
|
"learning_rate": 9.74947073336423e-05, |
|
"loss": 1.5648, |
|
"num_input_tokens_seen": 166544, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 1.2203389830508475, |
|
"grad_norm": 0.47032174468040466, |
|
"learning_rate": 9.719416651541839e-05, |
|
"loss": 1.3598, |
|
"num_input_tokens_seen": 177120, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 1.288135593220339, |
|
"grad_norm": 0.38840025663375854, |
|
"learning_rate": 9.687712292719997e-05, |
|
"loss": 1.3238, |
|
"num_input_tokens_seen": 186272, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 1.3559322033898304, |
|
"grad_norm": 0.5947024822235107, |
|
"learning_rate": 9.654368743221022e-05, |
|
"loss": 1.8704, |
|
"num_input_tokens_seen": 196480, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.423728813559322, |
|
"grad_norm": 0.5424012541770935, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 1.8205, |
|
"num_input_tokens_seen": 203856, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 1.4915254237288136, |
|
"grad_norm": 0.45230892300605774, |
|
"learning_rate": 9.582811279349882e-05, |
|
"loss": 1.3595, |
|
"num_input_tokens_seen": 214512, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 1.559322033898305, |
|
"grad_norm": 0.41904568672180176, |
|
"learning_rate": 9.544622387061055e-05, |
|
"loss": 2.0797, |
|
"num_input_tokens_seen": 223792, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 1.6271186440677967, |
|
"grad_norm": 0.5474861264228821, |
|
"learning_rate": 9.504844339512095e-05, |
|
"loss": 2.15, |
|
"num_input_tokens_seen": 233776, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 1.694915254237288, |
|
"grad_norm": 0.4554285407066345, |
|
"learning_rate": 9.463491046218058e-05, |
|
"loss": 2.0059, |
|
"num_input_tokens_seen": 243600, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.7627118644067796, |
|
"grad_norm": 0.4554867744445801, |
|
"learning_rate": 9.420576967523049e-05, |
|
"loss": 1.2697, |
|
"num_input_tokens_seen": 254608, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 1.8305084745762712, |
|
"grad_norm": 0.44335854053497314, |
|
"learning_rate": 9.376117109543769e-05, |
|
"loss": 1.6259, |
|
"num_input_tokens_seen": 265728, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 1.8983050847457628, |
|
"grad_norm": 0.36280569434165955, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 1.0618, |
|
"num_input_tokens_seen": 276624, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 1.9661016949152543, |
|
"grad_norm": 0.4373883306980133, |
|
"learning_rate": 9.282622777389258e-05, |
|
"loss": 1.8557, |
|
"num_input_tokens_seen": 287072, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 2.0338983050847457, |
|
"grad_norm": 0.5854040384292603, |
|
"learning_rate": 9.233620996141421e-05, |
|
"loss": 1.8077, |
|
"num_input_tokens_seen": 296248, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 2.1016949152542375, |
|
"grad_norm": 0.5168242454528809, |
|
"learning_rate": 9.183138810032099e-05, |
|
"loss": 1.767, |
|
"num_input_tokens_seen": 305560, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 2.169491525423729, |
|
"grad_norm": 0.4406554698944092, |
|
"learning_rate": 9.131193871579975e-05, |
|
"loss": 1.5561, |
|
"num_input_tokens_seen": 317176, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 2.23728813559322, |
|
"grad_norm": 0.48960959911346436, |
|
"learning_rate": 9.077804344796302e-05, |
|
"loss": 1.7631, |
|
"num_input_tokens_seen": 327352, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 2.305084745762712, |
|
"grad_norm": 0.4791744351387024, |
|
"learning_rate": 9.022988898833342e-05, |
|
"loss": 1.5754, |
|
"num_input_tokens_seen": 337384, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 2.3728813559322033, |
|
"grad_norm": 0.42596694827079773, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 1.4501, |
|
"num_input_tokens_seen": 346952, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 2.440677966101695, |
|
"grad_norm": 0.46600142121315, |
|
"learning_rate": 8.90915741234015e-05, |
|
"loss": 1.8493, |
|
"num_input_tokens_seen": 356568, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 2.5084745762711864, |
|
"grad_norm": 0.49377578496932983, |
|
"learning_rate": 8.850181176196315e-05, |
|
"loss": 1.6969, |
|
"num_input_tokens_seen": 366504, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 2.576271186440678, |
|
"grad_norm": 0.42628544569015503, |
|
"learning_rate": 8.789858615727265e-05, |
|
"loss": 1.3998, |
|
"num_input_tokens_seen": 377512, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 2.6440677966101696, |
|
"grad_norm": 0.37030258774757385, |
|
"learning_rate": 8.728210824415827e-05, |
|
"loss": 1.1354, |
|
"num_input_tokens_seen": 388728, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 2.711864406779661, |
|
"grad_norm": 0.763684093952179, |
|
"learning_rate": 8.665259359149132e-05, |
|
"loss": 1.5526, |
|
"num_input_tokens_seen": 393800, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.7796610169491527, |
|
"grad_norm": 0.5274456143379211, |
|
"learning_rate": 8.601026232680634e-05, |
|
"loss": 1.671, |
|
"num_input_tokens_seen": 404072, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 2.847457627118644, |
|
"grad_norm": 0.4358402192592621, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 1.1851, |
|
"num_input_tokens_seen": 415336, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 2.915254237288136, |
|
"grad_norm": 0.6406439542770386, |
|
"learning_rate": 8.468805280142709e-05, |
|
"loss": 1.8113, |
|
"num_input_tokens_seen": 425288, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 2.983050847457627, |
|
"grad_norm": 0.48384496569633484, |
|
"learning_rate": 8.400863688854597e-05, |
|
"loss": 1.2456, |
|
"num_input_tokens_seen": 436584, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 3.0508474576271185, |
|
"grad_norm": 0.6171286702156067, |
|
"learning_rate": 8.33173288976002e-05, |
|
"loss": 1.479, |
|
"num_input_tokens_seen": 445072, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 3.1186440677966103, |
|
"grad_norm": 0.5578075051307678, |
|
"learning_rate": 8.261437056390606e-05, |
|
"loss": 1.8757, |
|
"num_input_tokens_seen": 453696, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 3.1864406779661016, |
|
"grad_norm": 0.5808205604553223, |
|
"learning_rate": 8.190000769665044e-05, |
|
"loss": 1.4613, |
|
"num_input_tokens_seen": 462976, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 3.2542372881355934, |
|
"grad_norm": 0.46899017691612244, |
|
"learning_rate": 8.117449009293668e-05, |
|
"loss": 1.2657, |
|
"num_input_tokens_seen": 474016, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 3.3220338983050848, |
|
"grad_norm": 0.677277147769928, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 1.7769, |
|
"num_input_tokens_seen": 482960, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 3.389830508474576, |
|
"grad_norm": 0.543119490146637, |
|
"learning_rate": 7.969100927867507e-05, |
|
"loss": 1.3444, |
|
"num_input_tokens_seen": 493200, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 3.457627118644068, |
|
"grad_norm": 0.5538585782051086, |
|
"learning_rate": 7.89335648089903e-05, |
|
"loss": 1.4113, |
|
"num_input_tokens_seen": 503168, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 3.5254237288135593, |
|
"grad_norm": 0.6398975253105164, |
|
"learning_rate": 7.81660029031811e-05, |
|
"loss": 1.5596, |
|
"num_input_tokens_seen": 513776, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 3.593220338983051, |
|
"grad_norm": 0.8313115835189819, |
|
"learning_rate": 7.738859196089358e-05, |
|
"loss": 1.7417, |
|
"num_input_tokens_seen": 521376, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 3.6610169491525424, |
|
"grad_norm": 0.777786910533905, |
|
"learning_rate": 7.660160382576683e-05, |
|
"loss": 1.7439, |
|
"num_input_tokens_seen": 531504, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 3.7288135593220337, |
|
"grad_norm": 0.7124835848808289, |
|
"learning_rate": 7.580531369037533e-05, |
|
"loss": 1.2392, |
|
"num_input_tokens_seen": 542832, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 3.7966101694915255, |
|
"grad_norm": 0.7158543467521667, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 1.4463, |
|
"num_input_tokens_seen": 554128, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 3.864406779661017, |
|
"grad_norm": 0.6232526898384094, |
|
"learning_rate": 7.4185944355262e-05, |
|
"loss": 1.1846, |
|
"num_input_tokens_seen": 564576, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 3.9322033898305087, |
|
"grad_norm": 0.6178350448608398, |
|
"learning_rate": 7.33634314136531e-05, |
|
"loss": 1.1875, |
|
"num_input_tokens_seen": 574464, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"grad_norm": 0.720112144947052, |
|
"learning_rate": 7.253274878999727e-05, |
|
"loss": 1.1346, |
|
"num_input_tokens_seen": 584192, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 4.067796610169491, |
|
"grad_norm": 0.8956817388534546, |
|
"learning_rate": 7.169418695587791e-05, |
|
"loss": 1.6462, |
|
"num_input_tokens_seen": 593440, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 4.135593220338983, |
|
"grad_norm": 0.9503009915351868, |
|
"learning_rate": 7.084803913806641e-05, |
|
"loss": 1.0892, |
|
"num_input_tokens_seen": 603168, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 4.203389830508475, |
|
"grad_norm": 0.843825101852417, |
|
"learning_rate": 6.999460121598704e-05, |
|
"loss": 1.4054, |
|
"num_input_tokens_seen": 611888, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 4.271186440677966, |
|
"grad_norm": 0.7209855318069458, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 0.9302, |
|
"num_input_tokens_seen": 623312, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 4.338983050847458, |
|
"grad_norm": 0.884834885597229, |
|
"learning_rate": 6.826705121831976e-05, |
|
"loss": 1.2218, |
|
"num_input_tokens_seen": 634768, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 4.406779661016949, |
|
"grad_norm": 1.0309629440307617, |
|
"learning_rate": 6.739354322926136e-05, |
|
"loss": 1.1605, |
|
"num_input_tokens_seen": 644848, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 4.47457627118644, |
|
"grad_norm": 1.097214698791504, |
|
"learning_rate": 6.651395309775837e-05, |
|
"loss": 1.7099, |
|
"num_input_tokens_seen": 654672, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 4.5423728813559325, |
|
"grad_norm": 0.7945898175239563, |
|
"learning_rate": 6.562858839728223e-05, |
|
"loss": 0.8147, |
|
"num_input_tokens_seen": 665584, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 4.610169491525424, |
|
"grad_norm": 1.2936004400253296, |
|
"learning_rate": 6.473775872054521e-05, |
|
"loss": 1.5787, |
|
"num_input_tokens_seen": 674096, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 4.677966101694915, |
|
"grad_norm": 1.0135834217071533, |
|
"learning_rate": 6.384177557124247e-05, |
|
"loss": 1.2265, |
|
"num_input_tokens_seen": 683968, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 4.745762711864407, |
|
"grad_norm": 0.9531109929084778, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 1.2753, |
|
"num_input_tokens_seen": 694368, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 4.813559322033898, |
|
"grad_norm": 1.0897727012634277, |
|
"learning_rate": 6.203560377044866e-05, |
|
"loss": 1.6676, |
|
"num_input_tokens_seen": 703440, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 4.88135593220339, |
|
"grad_norm": 1.4037953615188599, |
|
"learning_rate": 6.112604669781572e-05, |
|
"loss": 1.4984, |
|
"num_input_tokens_seen": 711264, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 4.9491525423728815, |
|
"grad_norm": 1.1747398376464844, |
|
"learning_rate": 6.021259908948402e-05, |
|
"loss": 1.6282, |
|
"num_input_tokens_seen": 722624, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 5.016949152542373, |
|
"grad_norm": 0.8543111085891724, |
|
"learning_rate": 5.9295580358145744e-05, |
|
"loss": 0.8916, |
|
"num_input_tokens_seen": 730976, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 5.084745762711864, |
|
"grad_norm": 0.9056837558746338, |
|
"learning_rate": 5.837531116523682e-05, |
|
"loss": 0.7409, |
|
"num_input_tokens_seen": 740160, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 5.1525423728813555, |
|
"grad_norm": 1.1560508012771606, |
|
"learning_rate": 5.745211330880872e-05, |
|
"loss": 1.3499, |
|
"num_input_tokens_seen": 750544, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 5.220338983050848, |
|
"grad_norm": 0.9036076664924622, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 0.901, |
|
"num_input_tokens_seen": 761744, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 5.288135593220339, |
|
"grad_norm": 1.3706295490264893, |
|
"learning_rate": 5.559822380516539e-05, |
|
"loss": 1.1879, |
|
"num_input_tokens_seen": 772944, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 5.3559322033898304, |
|
"grad_norm": 1.5141230821609497, |
|
"learning_rate": 5.466818042264753e-05, |
|
"loss": 1.0959, |
|
"num_input_tokens_seen": 781296, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 5.423728813559322, |
|
"grad_norm": 1.3105418682098389, |
|
"learning_rate": 5.373650467932122e-05, |
|
"loss": 1.2333, |
|
"num_input_tokens_seen": 792416, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 5.491525423728813, |
|
"grad_norm": 1.5772976875305176, |
|
"learning_rate": 5.2803522361859594e-05, |
|
"loss": 1.1665, |
|
"num_input_tokens_seen": 802688, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 5.559322033898305, |
|
"grad_norm": 1.1764063835144043, |
|
"learning_rate": 5.18695597138163e-05, |
|
"loss": 1.0339, |
|
"num_input_tokens_seen": 813376, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 5.627118644067797, |
|
"grad_norm": 1.3924024105072021, |
|
"learning_rate": 5.0934943321545115e-05, |
|
"loss": 1.0024, |
|
"num_input_tokens_seen": 822752, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 5.694915254237288, |
|
"grad_norm": 1.2736717462539673, |
|
"learning_rate": 5e-05, |
|
"loss": 0.9337, |
|
"num_input_tokens_seen": 832720, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 5.762711864406779, |
|
"grad_norm": 1.5381358861923218, |
|
"learning_rate": 4.9065056678454904e-05, |
|
"loss": 1.0879, |
|
"num_input_tokens_seen": 842880, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 5.830508474576272, |
|
"grad_norm": 1.6273722648620605, |
|
"learning_rate": 4.813044028618373e-05, |
|
"loss": 1.3822, |
|
"num_input_tokens_seen": 851968, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 5.898305084745763, |
|
"grad_norm": 1.8411167860031128, |
|
"learning_rate": 4.7196477638140404e-05, |
|
"loss": 1.3801, |
|
"num_input_tokens_seen": 861632, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 5.966101694915254, |
|
"grad_norm": 1.8025944232940674, |
|
"learning_rate": 4.626349532067879e-05, |
|
"loss": 1.3577, |
|
"num_input_tokens_seen": 872352, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 6.033898305084746, |
|
"grad_norm": 1.44851815700531, |
|
"learning_rate": 4.5331819577352474e-05, |
|
"loss": 0.7063, |
|
"num_input_tokens_seen": 881072, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 6.101694915254237, |
|
"grad_norm": 1.7997266054153442, |
|
"learning_rate": 4.4401776194834613e-05, |
|
"loss": 1.35, |
|
"num_input_tokens_seen": 891840, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 6.169491525423728, |
|
"grad_norm": 2.1974358558654785, |
|
"learning_rate": 4.347369038899744e-05, |
|
"loss": 1.2183, |
|
"num_input_tokens_seen": 901232, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 6.237288135593221, |
|
"grad_norm": 2.028881072998047, |
|
"learning_rate": 4.254788669119127e-05, |
|
"loss": 1.0497, |
|
"num_input_tokens_seen": 910496, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 6.305084745762712, |
|
"grad_norm": 1.7718591690063477, |
|
"learning_rate": 4.162468883476319e-05, |
|
"loss": 0.6885, |
|
"num_input_tokens_seen": 919856, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 6.372881355932203, |
|
"grad_norm": 2.046247720718384, |
|
"learning_rate": 4.0704419641854274e-05, |
|
"loss": 0.9335, |
|
"num_input_tokens_seen": 931104, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 6.440677966101695, |
|
"grad_norm": 2.308433771133423, |
|
"learning_rate": 3.978740091051599e-05, |
|
"loss": 1.0183, |
|
"num_input_tokens_seen": 940976, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 6.508474576271187, |
|
"grad_norm": 2.1246485710144043, |
|
"learning_rate": 3.887395330218429e-05, |
|
"loss": 1.0591, |
|
"num_input_tokens_seen": 949248, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 6.576271186440678, |
|
"grad_norm": 2.154073715209961, |
|
"learning_rate": 3.7964396229551364e-05, |
|
"loss": 1.0101, |
|
"num_input_tokens_seen": 960336, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 6.6440677966101696, |
|
"grad_norm": 1.561721920967102, |
|
"learning_rate": 3.705904774487396e-05, |
|
"loss": 0.6923, |
|
"num_input_tokens_seen": 970480, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 6.711864406779661, |
|
"grad_norm": 2.500340461730957, |
|
"learning_rate": 3.6158224428757535e-05, |
|
"loss": 0.9599, |
|
"num_input_tokens_seen": 979104, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 6.779661016949152, |
|
"grad_norm": 2.429661512374878, |
|
"learning_rate": 3.5262241279454785e-05, |
|
"loss": 1.0911, |
|
"num_input_tokens_seen": 989312, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 6.847457627118644, |
|
"grad_norm": 1.9327709674835205, |
|
"learning_rate": 3.4371411602717784e-05, |
|
"loss": 0.9246, |
|
"num_input_tokens_seen": 999312, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 6.915254237288136, |
|
"grad_norm": 2.1729629039764404, |
|
"learning_rate": 3.3486046902241664e-05, |
|
"loss": 0.811, |
|
"num_input_tokens_seen": 1010096, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 6.983050847457627, |
|
"grad_norm": 2.6227834224700928, |
|
"learning_rate": 3.2606456770738636e-05, |
|
"loss": 0.8122, |
|
"num_input_tokens_seen": 1018704, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 7.0508474576271185, |
|
"grad_norm": 2.424504041671753, |
|
"learning_rate": 3.173294878168025e-05, |
|
"loss": 0.6868, |
|
"num_input_tokens_seen": 1027008, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 7.11864406779661, |
|
"grad_norm": 2.2759225368499756, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 0.8705, |
|
"num_input_tokens_seen": 1038016, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 7.186440677966102, |
|
"grad_norm": 2.652327299118042, |
|
"learning_rate": 3.000539878401296e-05, |
|
"loss": 1.0279, |
|
"num_input_tokens_seen": 1046912, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 7.254237288135593, |
|
"grad_norm": 2.538667678833008, |
|
"learning_rate": 2.9151960861933614e-05, |
|
"loss": 0.9108, |
|
"num_input_tokens_seen": 1056480, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 7.322033898305085, |
|
"grad_norm": 3.2955853939056396, |
|
"learning_rate": 2.8305813044122097e-05, |
|
"loss": 0.9454, |
|
"num_input_tokens_seen": 1066080, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 7.389830508474576, |
|
"grad_norm": 2.35931134223938, |
|
"learning_rate": 2.746725121000273e-05, |
|
"loss": 0.7537, |
|
"num_input_tokens_seen": 1075376, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 7.4576271186440675, |
|
"grad_norm": 2.282921552658081, |
|
"learning_rate": 2.66365685863469e-05, |
|
"loss": 0.87, |
|
"num_input_tokens_seen": 1086448, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 7.52542372881356, |
|
"grad_norm": 1.762494683265686, |
|
"learning_rate": 2.581405564473801e-05, |
|
"loss": 0.5695, |
|
"num_input_tokens_seen": 1098192, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 7.593220338983051, |
|
"grad_norm": 1.9810832738876343, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 0.5695, |
|
"num_input_tokens_seen": 1108912, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 7.661016949152542, |
|
"grad_norm": 2.754438877105713, |
|
"learning_rate": 2.4194686309624663e-05, |
|
"loss": 0.7164, |
|
"num_input_tokens_seen": 1116672, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 7.728813559322034, |
|
"grad_norm": 2.1492197513580322, |
|
"learning_rate": 2.3398396174233178e-05, |
|
"loss": 0.8342, |
|
"num_input_tokens_seen": 1126640, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 7.796610169491525, |
|
"grad_norm": 2.815870761871338, |
|
"learning_rate": 2.261140803910644e-05, |
|
"loss": 0.8934, |
|
"num_input_tokens_seen": 1135920, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 7.864406779661017, |
|
"grad_norm": 2.1932082176208496, |
|
"learning_rate": 2.1833997096818898e-05, |
|
"loss": 0.8654, |
|
"num_input_tokens_seen": 1147216, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 7.932203389830509, |
|
"grad_norm": 2.1254825592041016, |
|
"learning_rate": 2.1066435191009715e-05, |
|
"loss": 0.4848, |
|
"num_input_tokens_seen": 1158288, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"grad_norm": 3.3997814655303955, |
|
"learning_rate": 2.0308990721324927e-05, |
|
"loss": 0.9819, |
|
"num_input_tokens_seen": 1167328, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 8.067796610169491, |
|
"grad_norm": 2.623171329498291, |
|
"learning_rate": 1.9561928549563968e-05, |
|
"loss": 0.7783, |
|
"num_input_tokens_seen": 1177600, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 8.135593220338983, |
|
"grad_norm": 3.17315936088562, |
|
"learning_rate": 1.8825509907063327e-05, |
|
"loss": 0.7392, |
|
"num_input_tokens_seen": 1186256, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 8.203389830508474, |
|
"grad_norm": 2.5170342922210693, |
|
"learning_rate": 1.8099992303349577e-05, |
|
"loss": 0.5762, |
|
"num_input_tokens_seen": 1195200, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 8.271186440677965, |
|
"grad_norm": 2.4424407482147217, |
|
"learning_rate": 1.738562943609396e-05, |
|
"loss": 0.7936, |
|
"num_input_tokens_seen": 1205776, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 8.338983050847457, |
|
"grad_norm": 2.6299970149993896, |
|
"learning_rate": 1.6682671102399805e-05, |
|
"loss": 0.794, |
|
"num_input_tokens_seen": 1215440, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 8.40677966101695, |
|
"grad_norm": 2.1438987255096436, |
|
"learning_rate": 1.599136311145402e-05, |
|
"loss": 0.3746, |
|
"num_input_tokens_seen": 1226240, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 8.474576271186441, |
|
"grad_norm": 2.2746033668518066, |
|
"learning_rate": 1.531194719857292e-05, |
|
"loss": 0.5889, |
|
"num_input_tokens_seen": 1237296, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 8.542372881355933, |
|
"grad_norm": 2.953768253326416, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 0.8482, |
|
"num_input_tokens_seen": 1247184, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 8.610169491525424, |
|
"grad_norm": 2.8020410537719727, |
|
"learning_rate": 1.398973767319368e-05, |
|
"loss": 0.789, |
|
"num_input_tokens_seen": 1257200, |
|
"step": 127 |
|
}, |
|
{ |
|
"epoch": 8.677966101694915, |
|
"grad_norm": 2.6043848991394043, |
|
"learning_rate": 1.3347406408508695e-05, |
|
"loss": 0.7434, |
|
"num_input_tokens_seen": 1267568, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 8.745762711864407, |
|
"grad_norm": 2.287994384765625, |
|
"learning_rate": 1.2717891755841722e-05, |
|
"loss": 0.5503, |
|
"num_input_tokens_seen": 1278288, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 8.813559322033898, |
|
"grad_norm": 2.889692544937134, |
|
"learning_rate": 1.2101413842727345e-05, |
|
"loss": 0.5, |
|
"num_input_tokens_seen": 1288464, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 8.88135593220339, |
|
"grad_norm": 2.310126304626465, |
|
"learning_rate": 1.1498188238036861e-05, |
|
"loss": 0.7285, |
|
"num_input_tokens_seen": 1298768, |
|
"step": 131 |
|
}, |
|
{ |
|
"epoch": 8.94915254237288, |
|
"grad_norm": 2.0122134685516357, |
|
"learning_rate": 1.090842587659851e-05, |
|
"loss": 0.3758, |
|
"num_input_tokens_seen": 1308912, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 9.016949152542374, |
|
"grad_norm": 2.8011984825134277, |
|
"learning_rate": 1.0332332985438248e-05, |
|
"loss": 0.5785, |
|
"num_input_tokens_seen": 1317368, |
|
"step": 133 |
|
}, |
|
{ |
|
"epoch": 9.084745762711865, |
|
"grad_norm": 2.287930488586426, |
|
"learning_rate": 9.770111011666583e-06, |
|
"loss": 0.4679, |
|
"num_input_tokens_seen": 1328440, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 9.152542372881356, |
|
"grad_norm": 2.4521470069885254, |
|
"learning_rate": 9.221956552036992e-06, |
|
"loss": 0.6424, |
|
"num_input_tokens_seen": 1337928, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 9.220338983050848, |
|
"grad_norm": 2.9559810161590576, |
|
"learning_rate": 8.688061284200266e-06, |
|
"loss": 0.6096, |
|
"num_input_tokens_seen": 1346520, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 9.288135593220339, |
|
"grad_norm": 2.6230311393737793, |
|
"learning_rate": 8.168611899679013e-06, |
|
"loss": 0.5381, |
|
"num_input_tokens_seen": 1357816, |
|
"step": 137 |
|
}, |
|
{ |
|
"epoch": 9.35593220338983, |
|
"grad_norm": 2.8988404273986816, |
|
"learning_rate": 7.663790038585793e-06, |
|
"loss": 0.8004, |
|
"num_input_tokens_seen": 1368280, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 9.423728813559322, |
|
"grad_norm": 1.9839284420013428, |
|
"learning_rate": 7.173772226107434e-06, |
|
"loss": 0.4723, |
|
"num_input_tokens_seen": 1378520, |
|
"step": 139 |
|
}, |
|
{ |
|
"epoch": 9.491525423728813, |
|
"grad_norm": 2.406280517578125, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 0.4489, |
|
"num_input_tokens_seen": 1388440, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 9.559322033898304, |
|
"grad_norm": 3.5145606994628906, |
|
"learning_rate": 6.238828904562316e-06, |
|
"loss": 0.707, |
|
"num_input_tokens_seen": 1398568, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 9.627118644067796, |
|
"grad_norm": 3.3337950706481934, |
|
"learning_rate": 5.794230324769517e-06, |
|
"loss": 0.6449, |
|
"num_input_tokens_seen": 1408856, |
|
"step": 142 |
|
}, |
|
{ |
|
"epoch": 9.694915254237289, |
|
"grad_norm": 2.906613349914551, |
|
"learning_rate": 5.365089537819434e-06, |
|
"loss": 0.5634, |
|
"num_input_tokens_seen": 1419128, |
|
"step": 143 |
|
}, |
|
{ |
|
"epoch": 9.76271186440678, |
|
"grad_norm": 2.9478540420532227, |
|
"learning_rate": 4.951556604879048e-06, |
|
"loss": 0.6285, |
|
"num_input_tokens_seen": 1429944, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 9.830508474576272, |
|
"grad_norm": 2.812126874923706, |
|
"learning_rate": 4.5537761293894535e-06, |
|
"loss": 0.6617, |
|
"num_input_tokens_seen": 1440360, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 9.898305084745763, |
|
"grad_norm": 3.44775390625, |
|
"learning_rate": 4.1718872065011904e-06, |
|
"loss": 0.7798, |
|
"num_input_tokens_seen": 1450328, |
|
"step": 146 |
|
}, |
|
{ |
|
"epoch": 9.966101694915254, |
|
"grad_norm": 2.9694623947143555, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 0.7539, |
|
"num_input_tokens_seen": 1461144, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 10.033898305084746, |
|
"grad_norm": 2.622793674468994, |
|
"learning_rate": 3.4563125677897932e-06, |
|
"loss": 0.3182, |
|
"num_input_tokens_seen": 1469864, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 10.101694915254237, |
|
"grad_norm": 2.6204419136047363, |
|
"learning_rate": 3.1228770728000455e-06, |
|
"loss": 0.6796, |
|
"num_input_tokens_seen": 1480248, |
|
"step": 149 |
|
}, |
|
{ |
|
"epoch": 10.169491525423728, |
|
"grad_norm": 2.793680429458618, |
|
"learning_rate": 2.8058334845816213e-06, |
|
"loss": 0.4411, |
|
"num_input_tokens_seen": 1488056, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 10.23728813559322, |
|
"grad_norm": 2.866830348968506, |
|
"learning_rate": 2.5052926663577e-06, |
|
"loss": 0.6203, |
|
"num_input_tokens_seen": 1496920, |
|
"step": 151 |
|
}, |
|
{ |
|
"epoch": 10.305084745762711, |
|
"grad_norm": 2.5276501178741455, |
|
"learning_rate": 2.221359710692961e-06, |
|
"loss": 0.6025, |
|
"num_input_tokens_seen": 1507144, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 10.372881355932204, |
|
"grad_norm": 3.2329604625701904, |
|
"learning_rate": 1.9541339027450256e-06, |
|
"loss": 0.5943, |
|
"num_input_tokens_seen": 1515560, |
|
"step": 153 |
|
}, |
|
{ |
|
"epoch": 10.440677966101696, |
|
"grad_norm": 2.7045376300811768, |
|
"learning_rate": 1.70370868554659e-06, |
|
"loss": 0.5806, |
|
"num_input_tokens_seen": 1526296, |
|
"step": 154 |
|
}, |
|
{ |
|
"epoch": 10.508474576271187, |
|
"grad_norm": 2.964407444000244, |
|
"learning_rate": 1.4701716273304521e-06, |
|
"loss": 0.7033, |
|
"num_input_tokens_seen": 1537064, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 10.576271186440678, |
|
"grad_norm": 2.5632989406585693, |
|
"learning_rate": 1.2536043909088191e-06, |
|
"loss": 0.629, |
|
"num_input_tokens_seen": 1547816, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 10.64406779661017, |
|
"grad_norm": 2.630671739578247, |
|
"learning_rate": 1.0540827051175818e-06, |
|
"loss": 0.6927, |
|
"num_input_tokens_seen": 1557672, |
|
"step": 157 |
|
}, |
|
{ |
|
"epoch": 10.711864406779661, |
|
"grad_norm": 2.9026784896850586, |
|
"learning_rate": 8.716763383355864e-07, |
|
"loss": 0.4882, |
|
"num_input_tokens_seen": 1568264, |
|
"step": 158 |
|
}, |
|
{ |
|
"epoch": 10.779661016949152, |
|
"grad_norm": 2.553671360015869, |
|
"learning_rate": 7.064490740882057e-07, |
|
"loss": 0.543, |
|
"num_input_tokens_seen": 1578744, |
|
"step": 159 |
|
}, |
|
{ |
|
"epoch": 10.847457627118644, |
|
"grad_norm": 2.838085412979126, |
|
"learning_rate": 5.584586887435739e-07, |
|
"loss": 0.3713, |
|
"num_input_tokens_seen": 1588008, |
|
"step": 160 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 168, |
|
"num_input_tokens_seen": 1588008, |
|
"num_train_epochs": 12, |
|
"save_steps": 10, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 7.170710016039322e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|