Instructions to use cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Phi-3-mini-4k-instruct") model = PeftModel.from_pretrained(base_model, "cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7") - Notebooks
- Google Colab
- Kaggle
Download last-checkpoint/trainer_state.json from cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7: direct link, hf CLI and curl.
- Browser
- Download file 18.7 kB
-
https://huggingface.co/cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7/resolve/2fa0e79387c8ac0e6324552e2a05383c19d8f2d2/last-checkpoint/trainer_state.json
- Command line
-
hf download hf://cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7@2fa0e79387c8ac0e6324552e2a05383c19d8f2d2/last-checkpoint/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/cimol/d64fa5ce-cbf1-455e-ae25-e2961c53f7d7/resolve/2fa0e79387c8ac0e6324552e2a05383c19d8f2d2/last-checkpoint/trainer_state.json
18.7 kB
| { | |
| "best_metric": 0.152464359998703, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.205761316872428, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00205761316872428, | |
| "grad_norm": 2.40505051612854, | |
| "learning_rate": 7e-06, | |
| "loss": 3.9248, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00205761316872428, | |
| "eval_loss": 1.5612297058105469, | |
| "eval_runtime": 38.7459, | |
| "eval_samples_per_second": 21.138, | |
| "eval_steps_per_second": 5.291, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00411522633744856, | |
| "grad_norm": 3.6444056034088135, | |
| "learning_rate": 1.4e-05, | |
| "loss": 4.3553, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006172839506172839, | |
| "grad_norm": 4.6960368156433105, | |
| "learning_rate": 2.1e-05, | |
| "loss": 5.058, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 5.9922943115234375, | |
| "learning_rate": 2.8e-05, | |
| "loss": 5.1701, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0102880658436214, | |
| "grad_norm": 4.798070907592773, | |
| "learning_rate": 3.5e-05, | |
| "loss": 5.3173, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012345679012345678, | |
| "grad_norm": 5.446530818939209, | |
| "learning_rate": 4.2e-05, | |
| "loss": 4.8157, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01440329218106996, | |
| "grad_norm": 4.692366123199463, | |
| "learning_rate": 4.899999999999999e-05, | |
| "loss": 4.4251, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 3.962667942047119, | |
| "learning_rate": 5.6e-05, | |
| "loss": 4.1365, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": 3.6138181686401367, | |
| "learning_rate": 6.3e-05, | |
| "loss": 3.507, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0205761316872428, | |
| "grad_norm": 3.06467604637146, | |
| "learning_rate": 7e-05, | |
| "loss": 3.1751, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02263374485596708, | |
| "grad_norm": 3.0617806911468506, | |
| "learning_rate": 6.999521567473641e-05, | |
| "loss": 2.6366, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": 3.125230550765991, | |
| "learning_rate": 6.998086400693241e-05, | |
| "loss": 1.9493, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026748971193415638, | |
| "grad_norm": 2.617583751678467, | |
| "learning_rate": 6.995694892019065e-05, | |
| "loss": 2.1773, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02880658436213992, | |
| "grad_norm": 2.810847282409668, | |
| "learning_rate": 6.99234769526571e-05, | |
| "loss": 1.7846, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030864197530864196, | |
| "grad_norm": 2.3002936840057373, | |
| "learning_rate": 6.988045725523343e-05, | |
| "loss": 1.5039, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 2.374920606613159, | |
| "learning_rate": 6.982790158907539e-05, | |
| "loss": 1.7564, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03497942386831276, | |
| "grad_norm": 2.1841278076171875, | |
| "learning_rate": 6.976582432237733e-05, | |
| "loss": 1.3906, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 1.971739411354065, | |
| "learning_rate": 6.969424242644413e-05, | |
| "loss": 0.9276, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03909465020576132, | |
| "grad_norm": 1.8726739883422852, | |
| "learning_rate": 6.961317547105138e-05, | |
| "loss": 1.0064, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0411522633744856, | |
| "grad_norm": 1.9627259969711304, | |
| "learning_rate": 6.952264561909527e-05, | |
| "loss": 1.0283, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.043209876543209874, | |
| "grad_norm": 1.958211064338684, | |
| "learning_rate": 6.942267762053337e-05, | |
| "loss": 0.8451, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04526748971193416, | |
| "grad_norm": 1.9346603155136108, | |
| "learning_rate": 6.931329880561832e-05, | |
| "loss": 0.8608, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.047325102880658436, | |
| "grad_norm": 1.9274400472640991, | |
| "learning_rate": 6.919453907742597e-05, | |
| "loss": 0.8977, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": 1.5571010112762451, | |
| "learning_rate": 6.90664309036802e-05, | |
| "loss": 0.7522, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.051440329218107, | |
| "grad_norm": 1.8345186710357666, | |
| "learning_rate": 6.892900930787656e-05, | |
| "loss": 0.8573, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.053497942386831275, | |
| "grad_norm": 2.217470645904541, | |
| "learning_rate": 6.87823118597072e-05, | |
| "loss": 1.1688, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 2.0658411979675293, | |
| "learning_rate": 6.862637866478969e-05, | |
| "loss": 1.2216, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05761316872427984, | |
| "grad_norm": 2.4393527507781982, | |
| "learning_rate": 6.846125235370252e-05, | |
| "loss": 1.6207, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.059670781893004114, | |
| "grad_norm": 2.7012267112731934, | |
| "learning_rate": 6.828697807033038e-05, | |
| "loss": 1.263, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06172839506172839, | |
| "grad_norm": 2.90848445892334, | |
| "learning_rate": 6.81036034595222e-05, | |
| "loss": 1.7342, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06378600823045268, | |
| "grad_norm": 2.188056468963623, | |
| "learning_rate": 6.791117865406564e-05, | |
| "loss": 1.2297, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "grad_norm": 2.465306520462036, | |
| "learning_rate": 6.770975626098112e-05, | |
| "loss": 1.2353, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06790123456790123, | |
| "grad_norm": 2.3670384883880615, | |
| "learning_rate": 6.749939134713974e-05, | |
| "loss": 1.2893, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06995884773662552, | |
| "grad_norm": 3.023275375366211, | |
| "learning_rate": 6.728014142420846e-05, | |
| "loss": 1.5351, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0720164609053498, | |
| "grad_norm": 2.6416513919830322, | |
| "learning_rate": 6.7052066432927e-05, | |
| "loss": 1.0203, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 2.6644809246063232, | |
| "learning_rate": 6.681522872672069e-05, | |
| "loss": 1.013, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07613168724279835, | |
| "grad_norm": 1.9997481107711792, | |
| "learning_rate": 6.656969305465356e-05, | |
| "loss": 0.8877, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07818930041152264, | |
| "grad_norm": 2.4777352809906006, | |
| "learning_rate": 6.631552654372672e-05, | |
| "loss": 0.8846, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08024691358024691, | |
| "grad_norm": 2.6934351921081543, | |
| "learning_rate": 6.60527986805264e-05, | |
| "loss": 0.926, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0823045267489712, | |
| "grad_norm": 3.536698341369629, | |
| "learning_rate": 6.578158129222711e-05, | |
| "loss": 0.6958, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08436213991769548, | |
| "grad_norm": 3.0982742309570312, | |
| "learning_rate": 6.550194852695469e-05, | |
| "loss": 0.6446, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08641975308641975, | |
| "grad_norm": 3.977778434753418, | |
| "learning_rate": 6.521397683351509e-05, | |
| "loss": 0.7436, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08847736625514403, | |
| "grad_norm": 3.3363654613494873, | |
| "learning_rate": 6.491774494049386e-05, | |
| "loss": 0.7582, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09053497942386832, | |
| "grad_norm": 3.820716142654419, | |
| "learning_rate": 6.461333383473272e-05, | |
| "loss": 0.7784, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": 6.108582019805908, | |
| "learning_rate": 6.430082673918849e-05, | |
| "loss": 0.5698, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09465020576131687, | |
| "grad_norm": 5.08290958404541, | |
| "learning_rate": 6.398030909018069e-05, | |
| "loss": 0.6677, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09670781893004116, | |
| "grad_norm": 2.945241689682007, | |
| "learning_rate": 6.365186851403423e-05, | |
| "loss": 0.6415, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09876543209876543, | |
| "grad_norm": 2.914973020553589, | |
| "learning_rate": 6.331559480312315e-05, | |
| "loss": 0.6783, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10082304526748971, | |
| "grad_norm": 2.141970634460449, | |
| "learning_rate": 6.297157989132236e-05, | |
| "loss": 0.6053, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.102880658436214, | |
| "grad_norm": 2.8987009525299072, | |
| "learning_rate": 6.261991782887377e-05, | |
| "loss": 0.5968, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.102880658436214, | |
| "eval_loss": 0.3833325207233429, | |
| "eval_runtime": 39.56, | |
| "eval_samples_per_second": 20.703, | |
| "eval_steps_per_second": 5.182, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10493827160493827, | |
| "grad_norm": 21.277009963989258, | |
| "learning_rate": 6.226070475667393e-05, | |
| "loss": 7.9373, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.10699588477366255, | |
| "grad_norm": 12.284491539001465, | |
| "learning_rate": 6.189403887999006e-05, | |
| "loss": 5.3044, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.10905349794238683, | |
| "grad_norm": 10.717970848083496, | |
| "learning_rate": 6.152002044161171e-05, | |
| "loss": 2.2028, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 6.60059118270874, | |
| "learning_rate": 6.113875169444539e-05, | |
| "loss": 1.7998, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.11316872427983539, | |
| "grad_norm": 4.140441417694092, | |
| "learning_rate": 6.0750336873559605e-05, | |
| "loss": 1.008, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.11522633744855967, | |
| "grad_norm": 2.533043622970581, | |
| "learning_rate": 6.035488216768811e-05, | |
| "loss": 0.7792, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.11728395061728394, | |
| "grad_norm": 1.9595946073532104, | |
| "learning_rate": 5.9952495690198894e-05, | |
| "loss": 0.7045, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.11934156378600823, | |
| "grad_norm": 1.5208021402359009, | |
| "learning_rate": 5.954328744953709e-05, | |
| "loss": 0.604, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.12139917695473251, | |
| "grad_norm": 1.1410841941833496, | |
| "learning_rate": 5.91273693191498e-05, | |
| "loss": 0.4636, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.12345679012345678, | |
| "grad_norm": 1.3440451622009277, | |
| "learning_rate": 5.870485500690094e-05, | |
| "loss": 0.5507, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12551440329218108, | |
| "grad_norm": 1.9705235958099365, | |
| "learning_rate": 5.827586002398468e-05, | |
| "loss": 0.6043, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.12757201646090535, | |
| "grad_norm": 1.21955406665802, | |
| "learning_rate": 5.784050165334589e-05, | |
| "loss": 0.4929, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.12962962962962962, | |
| "grad_norm": 1.155280351638794, | |
| "learning_rate": 5.739889891761608e-05, | |
| "loss": 0.4327, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.13168724279835392, | |
| "grad_norm": 1.0522754192352295, | |
| "learning_rate": 5.6951172546573794e-05, | |
| "loss": 0.3859, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1337448559670782, | |
| "grad_norm": 0.9591506719589233, | |
| "learning_rate": 5.6497444944138376e-05, | |
| "loss": 0.4154, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.13580246913580246, | |
| "grad_norm": 1.126166820526123, | |
| "learning_rate": 5.603784015490587e-05, | |
| "loss": 0.4482, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.13786008230452676, | |
| "grad_norm": 1.1399197578430176, | |
| "learning_rate": 5.557248383023655e-05, | |
| "loss": 0.3882, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.13991769547325103, | |
| "grad_norm": 1.0086866617202759, | |
| "learning_rate": 5.510150319390302e-05, | |
| "loss": 0.3451, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1419753086419753, | |
| "grad_norm": 1.1888667345046997, | |
| "learning_rate": 5.4625027007308546e-05, | |
| "loss": 0.4558, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1440329218106996, | |
| "grad_norm": 1.1290650367736816, | |
| "learning_rate": 5.414318553428494e-05, | |
| "loss": 0.4067, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.14609053497942387, | |
| "grad_norm": 1.6422878503799438, | |
| "learning_rate": 5.3656110505479776e-05, | |
| "loss": 0.3683, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 1.2845423221588135, | |
| "learning_rate": 5.316393508234253e-05, | |
| "loss": 0.2984, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.15020576131687244, | |
| "grad_norm": 1.0456984043121338, | |
| "learning_rate": 5.266679382071953e-05, | |
| "loss": 0.3511, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1522633744855967, | |
| "grad_norm": 0.9409389495849609, | |
| "learning_rate": 5.216482263406778e-05, | |
| "loss": 0.307, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.15432098765432098, | |
| "grad_norm": 1.100905418395996, | |
| "learning_rate": 5.1658158756297576e-05, | |
| "loss": 0.4262, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.15637860082304528, | |
| "grad_norm": 1.0456651449203491, | |
| "learning_rate": 5.114694070425407e-05, | |
| "loss": 0.4237, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.15843621399176955, | |
| "grad_norm": 1.660601258277893, | |
| "learning_rate": 5.063130823984823e-05, | |
| "loss": 0.635, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.16049382716049382, | |
| "grad_norm": 1.9623562097549438, | |
| "learning_rate": 5.011140233184724e-05, | |
| "loss": 0.6901, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.16255144032921812, | |
| "grad_norm": 1.5435357093811035, | |
| "learning_rate": 4.958736511733516e-05, | |
| "loss": 0.5541, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.1646090534979424, | |
| "grad_norm": 1.3062795400619507, | |
| "learning_rate": 4.905933986285393e-05, | |
| "loss": 0.4875, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 1.2251200675964355, | |
| "learning_rate": 4.8527470925235824e-05, | |
| "loss": 0.4161, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.16872427983539096, | |
| "grad_norm": 1.052963137626648, | |
| "learning_rate": 4.799190371213772e-05, | |
| "loss": 0.3798, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.17078189300411523, | |
| "grad_norm": 1.3962211608886719, | |
| "learning_rate": 4.745278464228808e-05, | |
| "loss": 0.4614, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.1728395061728395, | |
| "grad_norm": 1.0526316165924072, | |
| "learning_rate": 4.69102611054575e-05, | |
| "loss": 0.3336, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1748971193415638, | |
| "grad_norm": 1.447713017463684, | |
| "learning_rate": 4.6364481422163926e-05, | |
| "loss": 0.3422, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.17695473251028807, | |
| "grad_norm": 1.987180233001709, | |
| "learning_rate": 4.581559480312316e-05, | |
| "loss": 0.4365, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.17901234567901234, | |
| "grad_norm": 2.7361459732055664, | |
| "learning_rate": 4.526375130845627e-05, | |
| "loss": 0.3779, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.18106995884773663, | |
| "grad_norm": 2.2039506435394287, | |
| "learning_rate": 4.4709101806664554e-05, | |
| "loss": 0.3907, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.1831275720164609, | |
| "grad_norm": 1.2355520725250244, | |
| "learning_rate": 4.4151797933383685e-05, | |
| "loss": 0.2849, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 2.4810612201690674, | |
| "learning_rate": 4.359199204992797e-05, | |
| "loss": 0.4476, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.18724279835390947, | |
| "grad_norm": 2.8064424991607666, | |
| "learning_rate": 4.30298372016363e-05, | |
| "loss": 0.5126, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.18930041152263374, | |
| "grad_norm": 1.7459629774093628, | |
| "learning_rate": 4.246548707603114e-05, | |
| "loss": 0.3313, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.19135802469135801, | |
| "grad_norm": 1.216896414756775, | |
| "learning_rate": 4.1899095960801805e-05, | |
| "loss": 0.2666, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1934156378600823, | |
| "grad_norm": 1.6271848678588867, | |
| "learning_rate": 4.133081870162385e-05, | |
| "loss": 0.3523, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.19547325102880658, | |
| "grad_norm": 2.0596134662628174, | |
| "learning_rate": 4.076081065982569e-05, | |
| "loss": 0.3127, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 1.5387978553771973, | |
| "learning_rate": 4.018922766991447e-05, | |
| "loss": 0.268, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.19958847736625515, | |
| "grad_norm": 1.8610491752624512, | |
| "learning_rate": 3.961622599697241e-05, | |
| "loss": 0.2759, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.20164609053497942, | |
| "grad_norm": 1.53598952293396, | |
| "learning_rate": 3.9041962293935516e-05, | |
| "loss": 0.2989, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2037037037037037, | |
| "grad_norm": 1.305046796798706, | |
| "learning_rate": 3.84665935587662e-05, | |
| "loss": 0.2431, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.205761316872428, | |
| "grad_norm": 1.9852741956710815, | |
| "learning_rate": 3.7890277091531636e-05, | |
| "loss": 0.276, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.205761316872428, | |
| "eval_loss": 0.152464359998703, | |
| "eval_runtime": 39.5141, | |
| "eval_samples_per_second": 20.727, | |
| "eval_steps_per_second": 5.188, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 4, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.55390862065664e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |