| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.035623409669211, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05089058524173028, | |
| "grad_norm": 2.2103662490844727, | |
| "learning_rate": 0.0001999771640780308, | |
| "loss": 3.0938, | |
| "num_input_tokens_seen": 190176, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10178117048346055, | |
| "grad_norm": 0.8035047054290771, | |
| "learning_rate": 0.0001998844110196681, | |
| "loss": 1.471, | |
| "num_input_tokens_seen": 378656, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15267175572519084, | |
| "grad_norm": 0.44624239206314087, | |
| "learning_rate": 0.00019972037971811802, | |
| "loss": 1.2452, | |
| "num_input_tokens_seen": 570208, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2035623409669211, | |
| "grad_norm": 0.41621240973472595, | |
| "learning_rate": 0.00019948518722731206, | |
| "loss": 1.1957, | |
| "num_input_tokens_seen": 763040, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2544529262086514, | |
| "grad_norm": 0.3875686824321747, | |
| "learning_rate": 0.0001991790013823246, | |
| "loss": 1.1319, | |
| "num_input_tokens_seen": 959200, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3053435114503817, | |
| "grad_norm": 0.4382984936237335, | |
| "learning_rate": 0.00019880204067960472, | |
| "loss": 1.1209, | |
| "num_input_tokens_seen": 1153728, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.356234096692112, | |
| "grad_norm": 0.45683977007865906, | |
| "learning_rate": 0.00019835457412105528, | |
| "loss": 1.123, | |
| "num_input_tokens_seen": 1351616, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4071246819338422, | |
| "grad_norm": 0.4628298580646515, | |
| "learning_rate": 0.00019783692102207155, | |
| "loss": 1.0532, | |
| "num_input_tokens_seen": 1537696, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4580152671755725, | |
| "grad_norm": 0.5620412826538086, | |
| "learning_rate": 0.00019724945078367513, | |
| "loss": 1.0805, | |
| "num_input_tokens_seen": 1730144, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5089058524173028, | |
| "grad_norm": 0.4734291732311249, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.0572, | |
| "num_input_tokens_seen": 1916608, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5597964376590331, | |
| "grad_norm": 0.46405333280563354, | |
| "learning_rate": 0.00019586678530366606, | |
| "loss": 1.0069, | |
| "num_input_tokens_seen": 2103712, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6106870229007634, | |
| "grad_norm": 0.4856356084346771, | |
| "learning_rate": 0.00019507257674221027, | |
| "loss": 1.0293, | |
| "num_input_tokens_seen": 2289888, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6615776081424937, | |
| "grad_norm": 0.4761466085910797, | |
| "learning_rate": 0.00019421052369755334, | |
| "loss": 0.9994, | |
| "num_input_tokens_seen": 2477888, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.712468193384224, | |
| "grad_norm": 0.5239170789718628, | |
| "learning_rate": 0.0001932812413370265, | |
| "loss": 1.0159, | |
| "num_input_tokens_seen": 2662848, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7633587786259542, | |
| "grad_norm": 0.4161457419395447, | |
| "learning_rate": 0.00019228539280329038, | |
| "loss": 1.0233, | |
| "num_input_tokens_seen": 2861024, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8142493638676844, | |
| "grad_norm": 0.5579718351364136, | |
| "learning_rate": 0.00019122368874111172, | |
| "loss": 1.0109, | |
| "num_input_tokens_seen": 3043712, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8651399491094147, | |
| "grad_norm": 0.4595694839954376, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 1.0132, | |
| "num_input_tokens_seen": 3231840, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.916030534351145, | |
| "grad_norm": 0.49271535873413086, | |
| "learning_rate": 0.00018890579104475995, | |
| "loss": 1.0079, | |
| "num_input_tokens_seen": 3429632, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9669211195928753, | |
| "grad_norm": 0.5259862542152405, | |
| "learning_rate": 0.00018765125147926476, | |
| "loss": 0.9515, | |
| "num_input_tokens_seen": 3620000, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0178117048346056, | |
| "grad_norm": 0.444477379322052, | |
| "learning_rate": 0.00018633416334232753, | |
| "loss": 0.93, | |
| "num_input_tokens_seen": 3809824, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0687022900763359, | |
| "grad_norm": 0.42680156230926514, | |
| "learning_rate": 0.0001849554665176354, | |
| "loss": 0.8925, | |
| "num_input_tokens_seen": 4005472, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.1195928753180662, | |
| "grad_norm": 0.6088462471961975, | |
| "learning_rate": 0.00018351614485328388, | |
| "loss": 0.8715, | |
| "num_input_tokens_seen": 4192480, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.1704834605597965, | |
| "grad_norm": 0.5572230815887451, | |
| "learning_rate": 0.0001820172254596956, | |
| "loss": 0.8569, | |
| "num_input_tokens_seen": 4379296, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.2213740458015268, | |
| "grad_norm": 0.5509177446365356, | |
| "learning_rate": 0.00018045977797666684, | |
| "loss": 0.8269, | |
| "num_input_tokens_seen": 4568352, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.272264631043257, | |
| "grad_norm": 0.67293781042099, | |
| "learning_rate": 0.00017884491381006478, | |
| "loss": 0.84, | |
| "num_input_tokens_seen": 4752928, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.3231552162849873, | |
| "grad_norm": 0.5845524668693542, | |
| "learning_rate": 0.00017717378533872017, | |
| "loss": 0.8243, | |
| "num_input_tokens_seen": 4939008, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3740458015267176, | |
| "grad_norm": 0.5623295307159424, | |
| "learning_rate": 0.00017544758509208146, | |
| "loss": 0.8624, | |
| "num_input_tokens_seen": 5133664, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.424936386768448, | |
| "grad_norm": 0.5870885848999023, | |
| "learning_rate": 0.00017366754489921694, | |
| "loss": 0.8543, | |
| "num_input_tokens_seen": 5332000, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4758269720101782, | |
| "grad_norm": 0.5874502062797546, | |
| "learning_rate": 0.00017183493500977278, | |
| "loss": 0.842, | |
| "num_input_tokens_seen": 5520640, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.5267175572519083, | |
| "grad_norm": 0.5786451101303101, | |
| "learning_rate": 0.0001699510631875134, | |
| "loss": 0.8268, | |
| "num_input_tokens_seen": 5710528, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5776081424936388, | |
| "grad_norm": 0.5929097533226013, | |
| "learning_rate": 0.00016801727377709194, | |
| "loss": 0.8238, | |
| "num_input_tokens_seen": 5907264, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.6284987277353689, | |
| "grad_norm": 0.570965051651001, | |
| "learning_rate": 0.00016603494674471593, | |
| "loss": 0.8324, | |
| "num_input_tokens_seen": 6095776, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6793893129770994, | |
| "grad_norm": 0.6001121401786804, | |
| "learning_rate": 0.0001640054966933935, | |
| "loss": 0.8431, | |
| "num_input_tokens_seen": 6281280, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.7302798982188294, | |
| "grad_norm": 0.5865895748138428, | |
| "learning_rate": 0.00016193037185346224, | |
| "loss": 0.8054, | |
| "num_input_tokens_seen": 6470368, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.78117048346056, | |
| "grad_norm": 0.6706877946853638, | |
| "learning_rate": 0.00015981105304912162, | |
| "loss": 0.8255, | |
| "num_input_tokens_seen": 6658944, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.83206106870229, | |
| "grad_norm": 0.6549966931343079, | |
| "learning_rate": 0.0001576490526417059, | |
| "loss": 0.8334, | |
| "num_input_tokens_seen": 6842880, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8829516539440203, | |
| "grad_norm": 0.6813002228736877, | |
| "learning_rate": 0.0001554459134504523, | |
| "loss": 0.8354, | |
| "num_input_tokens_seen": 7034432, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.9338422391857506, | |
| "grad_norm": 0.6717746257781982, | |
| "learning_rate": 0.00015320320765153367, | |
| "loss": 0.8294, | |
| "num_input_tokens_seen": 7228672, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.984732824427481, | |
| "grad_norm": 0.6509274840354919, | |
| "learning_rate": 0.00015092253565614233, | |
| "loss": 0.8561, | |
| "num_input_tokens_seen": 7414144, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.035623409669211, | |
| "grad_norm": 0.6088241338729858, | |
| "learning_rate": 0.00014860552496842494, | |
| "loss": 0.6968, | |
| "num_input_tokens_seen": 7603104, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 588, | |
| "num_input_tokens_seen": 7603104, | |
| "num_train_epochs": 6, | |
| "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": 3.433210283043062e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |