Instructions to use Manikanta21/OceanGPT-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Manikanta21/OceanGPT-v1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("zjunlp/OceanGPT-basic-7B-v0.1") model = PeftModel.from_pretrained(base_model, "Manikanta21/OceanGPT-v1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8048289738430584, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012072434607645875, | |
| "grad_norm": 31.565221786499023, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 11.39139175415039, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02414486921529175, | |
| "grad_norm": 32.498504638671875, | |
| "learning_rate": 2e-05, | |
| "loss": 10.6638552347819, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03621730382293763, | |
| "grad_norm": 35.47499084472656, | |
| "learning_rate": 1.9796610169491527e-05, | |
| "loss": 8.869885762532553, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0482897384305835, | |
| "grad_norm": 36.74094009399414, | |
| "learning_rate": 1.9593220338983052e-05, | |
| "loss": 6.656011581420898, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.060362173038229376, | |
| "grad_norm": 27.099929809570312, | |
| "learning_rate": 1.938983050847458e-05, | |
| "loss": 4.492154757181804, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07243460764587525, | |
| "grad_norm": 20.31853675842285, | |
| "learning_rate": 1.9186440677966102e-05, | |
| "loss": 2.879384676615397, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": 16.151193618774414, | |
| "learning_rate": 1.898305084745763e-05, | |
| "loss": 1.7103803952534993, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.096579476861167, | |
| "grad_norm": 8.316960334777832, | |
| "learning_rate": 1.8779661016949152e-05, | |
| "loss": 0.8944776852925619, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10865191146881288, | |
| "grad_norm": 2.3379435539245605, | |
| "learning_rate": 1.857627118644068e-05, | |
| "loss": 0.4361502726872762, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12072434607645875, | |
| "grad_norm": 0.6751275658607483, | |
| "learning_rate": 1.8372881355932202e-05, | |
| "loss": 0.27574555079142254, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13279678068410464, | |
| "grad_norm": 0.5723764300346375, | |
| "learning_rate": 1.816949152542373e-05, | |
| "loss": 0.23154075940450033, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1448692152917505, | |
| "grad_norm": 0.56374591588974, | |
| "learning_rate": 1.7966101694915256e-05, | |
| "loss": 0.21050381660461426, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15694164989939638, | |
| "grad_norm": 0.5116483569145203, | |
| "learning_rate": 1.776271186440678e-05, | |
| "loss": 0.19474305709203085, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": 0.3521374762058258, | |
| "learning_rate": 1.7559322033898306e-05, | |
| "loss": 0.18379410107930502, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18108651911468812, | |
| "grad_norm": 1.187842607498169, | |
| "learning_rate": 1.735593220338983e-05, | |
| "loss": 0.17135000228881836, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.193158953722334, | |
| "grad_norm": 1.8320320844650269, | |
| "learning_rate": 1.715254237288136e-05, | |
| "loss": 0.15841978788375854, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2052313883299799, | |
| "grad_norm": 3.5149056911468506, | |
| "learning_rate": 1.694915254237288e-05, | |
| "loss": 0.15108935038248697, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.21730382293762576, | |
| "grad_norm": 1.036536693572998, | |
| "learning_rate": 1.674576271186441e-05, | |
| "loss": 0.13653225700060526, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.22937625754527163, | |
| "grad_norm": 0.9628488421440125, | |
| "learning_rate": 1.654237288135593e-05, | |
| "loss": 0.12643237908681235, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2414486921529175, | |
| "grad_norm": 2.743955135345459, | |
| "learning_rate": 1.633898305084746e-05, | |
| "loss": 0.1159747838973999, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2535211267605634, | |
| "grad_norm": 0.41073763370513916, | |
| "learning_rate": 1.6135593220338985e-05, | |
| "loss": 0.11064680417378743, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2655935613682093, | |
| "grad_norm": 0.6691092252731323, | |
| "learning_rate": 1.593220338983051e-05, | |
| "loss": 0.10705698529879253, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2776659959758551, | |
| "grad_norm": 0.42705169320106506, | |
| "learning_rate": 1.5728813559322035e-05, | |
| "loss": 0.10355836153030396, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.289738430583501, | |
| "grad_norm": 0.6782660484313965, | |
| "learning_rate": 1.552542372881356e-05, | |
| "loss": 0.10028706987698872, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.30181086519114686, | |
| "grad_norm": 0.1919354647397995, | |
| "learning_rate": 1.5322033898305085e-05, | |
| "loss": 0.09786097208658855, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.31388329979879276, | |
| "grad_norm": 0.19268283247947693, | |
| "learning_rate": 1.511864406779661e-05, | |
| "loss": 0.09490699569384257, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.32595573440643866, | |
| "grad_norm": 0.1897154301404953, | |
| "learning_rate": 1.4915254237288137e-05, | |
| "loss": 0.09219396114349365, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": 0.16722449660301208, | |
| "learning_rate": 1.4711864406779662e-05, | |
| "loss": 0.08906848231951396, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3501006036217304, | |
| "grad_norm": 0.13802577555179596, | |
| "learning_rate": 1.4508474576271187e-05, | |
| "loss": 0.08599668741226196, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.36217303822937624, | |
| "grad_norm": 0.11041229963302612, | |
| "learning_rate": 1.4305084745762714e-05, | |
| "loss": 0.08312974373499553, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.37424547283702214, | |
| "grad_norm": 0.31502974033355713, | |
| "learning_rate": 1.4101694915254239e-05, | |
| "loss": 0.08116496602694194, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.386317907444668, | |
| "grad_norm": 0.0854659155011177, | |
| "learning_rate": 1.3898305084745764e-05, | |
| "loss": 0.07955464720726013, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.3983903420523139, | |
| "grad_norm": 0.08523856848478317, | |
| "learning_rate": 1.3694915254237289e-05, | |
| "loss": 0.07785432537396748, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.4104627766599598, | |
| "grad_norm": 0.09225258231163025, | |
| "learning_rate": 1.3491525423728816e-05, | |
| "loss": 0.07649004459381104, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4225352112676056, | |
| "grad_norm": 0.09481494128704071, | |
| "learning_rate": 1.328813559322034e-05, | |
| "loss": 0.07524276276429494, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4346076458752515, | |
| "grad_norm": 0.10402938723564148, | |
| "learning_rate": 1.3084745762711866e-05, | |
| "loss": 0.07400999466578166, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.44668008048289737, | |
| "grad_norm": 0.11167366057634354, | |
| "learning_rate": 1.288135593220339e-05, | |
| "loss": 0.07269691427548726, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.45875251509054327, | |
| "grad_norm": 0.1135065034031868, | |
| "learning_rate": 1.2677966101694916e-05, | |
| "loss": 0.0711974302927653, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.4708249496981891, | |
| "grad_norm": 0.11799220740795135, | |
| "learning_rate": 1.2474576271186443e-05, | |
| "loss": 0.06939153869946797, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.482897384305835, | |
| "grad_norm": 0.12809021770954132, | |
| "learning_rate": 1.2271186440677966e-05, | |
| "loss": 0.0675096462170283, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4949698189134809, | |
| "grad_norm": 0.13876567780971527, | |
| "learning_rate": 1.2067796610169493e-05, | |
| "loss": 0.06532351672649384, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": 0.15365397930145264, | |
| "learning_rate": 1.1864406779661018e-05, | |
| "loss": 0.06267779072125752, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5191146881287726, | |
| "grad_norm": 0.196734219789505, | |
| "learning_rate": 1.1661016949152543e-05, | |
| "loss": 0.05952953298886617, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.5311871227364185, | |
| "grad_norm": 0.19224287569522858, | |
| "learning_rate": 1.1457627118644068e-05, | |
| "loss": 0.055368090669314064, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.5432595573440644, | |
| "grad_norm": 0.22132018208503723, | |
| "learning_rate": 1.1254237288135595e-05, | |
| "loss": 0.05075469116369883, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5553319919517102, | |
| "grad_norm": 0.2849789261817932, | |
| "learning_rate": 1.1050847457627118e-05, | |
| "loss": 0.043954809506734215, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.5674044265593562, | |
| "grad_norm": 0.3531913459300995, | |
| "learning_rate": 1.0847457627118645e-05, | |
| "loss": 0.033663809299468994, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.579476861167002, | |
| "grad_norm": 0.16163581609725952, | |
| "learning_rate": 1.0644067796610172e-05, | |
| "loss": 0.021554974218209583, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.5915492957746479, | |
| "grad_norm": 0.14978717267513275, | |
| "learning_rate": 1.0440677966101695e-05, | |
| "loss": 0.01815607522924741, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.6036217303822937, | |
| "grad_norm": 0.13460315763950348, | |
| "learning_rate": 1.0237288135593222e-05, | |
| "loss": 0.014825550218423208, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6156941649899397, | |
| "grad_norm": 0.1262596696615219, | |
| "learning_rate": 1.0033898305084746e-05, | |
| "loss": 0.012043482313553492, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6277665995975855, | |
| "grad_norm": 0.12274110317230225, | |
| "learning_rate": 9.830508474576272e-06, | |
| "loss": 0.00944417342543602, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.6398390342052314, | |
| "grad_norm": 0.11508777737617493, | |
| "learning_rate": 9.627118644067797e-06, | |
| "loss": 0.006922641769051552, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.6519114688128773, | |
| "grad_norm": 0.09775592386722565, | |
| "learning_rate": 9.423728813559322e-06, | |
| "loss": 0.004721511155366898, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.6639839034205232, | |
| "grad_norm": 0.0729842260479927, | |
| "learning_rate": 9.220338983050847e-06, | |
| "loss": 0.0028886919220288596, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": 0.04806124418973923, | |
| "learning_rate": 9.016949152542374e-06, | |
| "loss": 0.0016856035217642784, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.6881287726358148, | |
| "grad_norm": 0.03200242295861244, | |
| "learning_rate": 8.8135593220339e-06, | |
| "loss": 0.0009991055509696405, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.7002012072434608, | |
| "grad_norm": 0.02607228048145771, | |
| "learning_rate": 8.610169491525424e-06, | |
| "loss": 0.0006594751806308826, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.7122736418511066, | |
| "grad_norm": 0.01632210798561573, | |
| "learning_rate": 8.40677966101695e-06, | |
| "loss": 0.0004556536829719941, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.7243460764587525, | |
| "grad_norm": 0.011822426691651344, | |
| "learning_rate": 8.203389830508475e-06, | |
| "loss": 0.0003539823616544406, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7364185110663984, | |
| "grad_norm": 0.01042755413800478, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0002809216578801473, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.7484909456740443, | |
| "grad_norm": 0.008660788647830486, | |
| "learning_rate": 7.796610169491526e-06, | |
| "loss": 0.00023905226650337377, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.7605633802816901, | |
| "grad_norm": 0.007257130928337574, | |
| "learning_rate": 7.5932203389830515e-06, | |
| "loss": 0.0002122444372313718, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.772635814889336, | |
| "grad_norm": 0.007221721112728119, | |
| "learning_rate": 7.3898305084745766e-06, | |
| "loss": 0.00019281627222274741, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.7847082494969819, | |
| "grad_norm": 0.005890133790671825, | |
| "learning_rate": 7.1864406779661025e-06, | |
| "loss": 0.0001794119404318432, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7967806841046278, | |
| "grad_norm": 0.0055551244877278805, | |
| "learning_rate": 6.9830508474576275e-06, | |
| "loss": 0.00016860844334587455, | |
| "step": 198 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.62794393567232e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |