diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..a8561e1e175ac1deb33f1cef01dc2ee9652231ba 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +. filter=lfs diff=lfs merge=lfs -text +config.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +special_tokens_map.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-308 filter=lfs diff=lfs merge=lfs -text +generation_config.json filter=lfs diff=lfs merge=lfs -text +checkpoint-100 filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer_config.json filter=lfs diff=lfs merge=lfs -text +checkpoint-200 filter=lfs diff=lfs merge=lfs -text +checkpoint-300 filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoint-100/config.json b/checkpoint-100/config.json new file mode 100644 index 0000000000000000000000000000000000000000..de55730a672c2805e1108109d81a111b0cdb48b1 --- /dev/null +++ b/checkpoint-100/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a +size 915 diff --git a/checkpoint-100/generation_config.json b/checkpoint-100/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1007819213eaa3e36dd0c6354016734419f4a863 --- /dev/null +++ b/checkpoint-100/generation_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169 +size 184 diff --git a/checkpoint-100/model-00001-of-00004.safetensors b/checkpoint-100/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1312e33b2bdaab375f7e25ac9e1b0f5817eafc2 --- /dev/null +++ b/checkpoint-100/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62275b83768b450eaceec040629b66fcc8362137aba5e874d5334c846ac7646 +size 4976698672 diff --git a/checkpoint-100/model-00002-of-00004.safetensors b/checkpoint-100/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9dba2a4b6e065c94c5a37aa9d6d1d44d88cebc1b --- /dev/null +++ b/checkpoint-100/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5b0664bdb88ef83ded2a10b6b37a3517a9db7e0039a688e7351577a3a3a2ed +size 4999802720 diff --git a/checkpoint-100/model-00003-of-00004.safetensors b/checkpoint-100/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3574cdb53e9103641f48bb9ee516b78719f07f1b --- /dev/null +++ b/checkpoint-100/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8726c320884ad49027dbafeaa3db55a378cf5b1b286b3a02bfa6075988cd760b +size 4915916176 diff --git a/checkpoint-100/model-00004-of-00004.safetensors b/checkpoint-100/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df8a62ad868b407fd1edf4b19977870e020f4282 --- /dev/null +++ b/checkpoint-100/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc1f3d37eb965816560312e02d7a7aaac58b22e1978650cb76b59aaa1ab86df +size 1168138808 diff --git a/checkpoint-100/model.safetensors.index.json b/checkpoint-100/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..a054aad8cf0cb5671e2e10b3bf817725a4bec031 --- /dev/null +++ b/checkpoint-100/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b +size 23950 diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..e65bfd5175e229465f1a0b950c76922c641008d0 --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e14320965875e72c6d9efb454e3129b26c88bee6e66cda297c6d78702a4f79a +size 32121299754 diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..4f427f074dcc36845a8b146ca04d57ca91cc33c9 --- /dev/null +++ b/checkpoint-100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c26b481b9cb8c27b6ce66e286d7b2720e0aefc60735ac6e7640899dd50d4bf55 +size 14244 diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c5eaf5575ce5b30f41aa28327c5f0c94a456719 --- /dev/null +++ b/checkpoint-100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190d296d912b9aa1e1918db9af8ef09674f2d36d1e112918274e76c09503d1c5 +size 1064 diff --git a/checkpoint-100/special_tokens_map.json b/checkpoint-100/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92d7fab6729d723f45689803b99006fec945cc47 --- /dev/null +++ b/checkpoint-100/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1835caa5b4d70acaa210fa222b0036f1882f9525c4660fd4810fb3e1e40ff8 +size 325 diff --git a/checkpoint-100/tokenizer.json b/checkpoint-100/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..66cd9d7e0daec95eb10d16a63c615637dbbb7304 --- /dev/null +++ b/checkpoint-100/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4 +size 9085657 diff --git a/checkpoint-100/tokenizer_config.json b/checkpoint-100/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..08ebc9598183a9a76c44ef06813aca75f51de4a5 --- /dev/null +++ b/checkpoint-100/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d0de6d831b5940c3f2eae4e495b9f77612cbb05b5804846733ab617f0dfe9b +size 55380 diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..74d109d1ad4683f913041e596f18ef28d46a9b0b --- /dev/null +++ b/checkpoint-100/trainer_state.json @@ -0,0 +1,823 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.3246753246753247, + "eval_steps": 10, + "global_step": 100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.003246753246753247, + "grad_norm": 16.375, + "learning_rate": 4.0000000000000003e-07, + "loss": 1.4017, + "step": 1 + }, + { + "epoch": 0.006493506493506494, + "grad_norm": 16.25, + "learning_rate": 8.000000000000001e-07, + "loss": 1.4229, + "step": 2 + }, + { + "epoch": 0.00974025974025974, + "grad_norm": 16.75, + "learning_rate": 1.2000000000000002e-06, + "loss": 1.4112, + "step": 3 + }, + { + "epoch": 0.012987012987012988, + "grad_norm": 16.5, + "learning_rate": 1.6000000000000001e-06, + "loss": 1.3959, + "step": 4 + }, + { + "epoch": 0.016233766233766232, + "grad_norm": 16.125, + "learning_rate": 2.0000000000000003e-06, + "loss": 1.3789, + "step": 5 + }, + { + "epoch": 0.01948051948051948, + "grad_norm": 14.4375, + "learning_rate": 2.4000000000000003e-06, + "loss": 1.3618, + "step": 6 + }, + { + "epoch": 0.022727272727272728, + "grad_norm": 10.1875, + "learning_rate": 2.8000000000000003e-06, + "loss": 1.3214, + "step": 7 + }, + { + "epoch": 0.025974025974025976, + "grad_norm": 7.4375, + "learning_rate": 3.2000000000000003e-06, + "loss": 1.2885, + "step": 8 + }, + { + "epoch": 0.02922077922077922, + "grad_norm": 6.28125, + "learning_rate": 3.6000000000000003e-06, + "loss": 1.2436, + "step": 9 + }, + { + "epoch": 0.032467532467532464, + "grad_norm": 5.75, + "learning_rate": 4.000000000000001e-06, + "loss": 1.2269, + "step": 10 + }, + { + "epoch": 0.032467532467532464, + "eval_loss": 1.1976113319396973, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0273, + "eval_samples_per_second": 11.878, + "eval_steps_per_second": 1.485, + "step": 10 + }, + { + "epoch": 0.03571428571428571, + "grad_norm": 5.375, + "learning_rate": 4.4e-06, + "loss": 1.1925, + "step": 11 + }, + { + "epoch": 0.03896103896103896, + "grad_norm": 5.125, + "learning_rate": 4.800000000000001e-06, + "loss": 1.1307, + "step": 12 + }, + { + "epoch": 0.04220779220779221, + "grad_norm": 5.125, + "learning_rate": 5.2e-06, + "loss": 1.0778, + "step": 13 + }, + { + "epoch": 0.045454545454545456, + "grad_norm": 5.0625, + "learning_rate": 5.600000000000001e-06, + "loss": 1.0067, + "step": 14 + }, + { + "epoch": 0.048701298701298704, + "grad_norm": 5.75, + "learning_rate": 6e-06, + "loss": 0.9668, + "step": 15 + }, + { + "epoch": 0.05194805194805195, + "grad_norm": 5.15625, + "learning_rate": 6.4000000000000006e-06, + "loss": 0.875, + "step": 16 + }, + { + "epoch": 0.05519480519480519, + "grad_norm": 4.875, + "learning_rate": 6.800000000000001e-06, + "loss": 0.8297, + "step": 17 + }, + { + "epoch": 0.05844155844155844, + "grad_norm": 4.5625, + "learning_rate": 7.2000000000000005e-06, + "loss": 0.7703, + "step": 18 + }, + { + "epoch": 0.06168831168831169, + "grad_norm": 3.90625, + "learning_rate": 7.600000000000001e-06, + "loss": 0.7327, + "step": 19 + }, + { + "epoch": 0.06493506493506493, + "grad_norm": 2.78125, + "learning_rate": 8.000000000000001e-06, + "loss": 0.6672, + "step": 20 + }, + { + "epoch": 0.06493506493506493, + "eval_loss": 0.6521233320236206, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.999, + "eval_samples_per_second": 11.88, + "eval_steps_per_second": 1.486, + "step": 20 + }, + { + "epoch": 0.06818181818181818, + "grad_norm": 2.140625, + "learning_rate": 8.400000000000001e-06, + "loss": 0.6507, + "step": 21 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.828125, + "learning_rate": 8.8e-06, + "loss": 0.6215, + "step": 22 + }, + { + "epoch": 0.07467532467532467, + "grad_norm": 1.5546875, + "learning_rate": 9.200000000000002e-06, + "loss": 0.5992, + "step": 23 + }, + { + "epoch": 0.07792207792207792, + "grad_norm": 1.4453125, + "learning_rate": 9.600000000000001e-06, + "loss": 0.5748, + "step": 24 + }, + { + "epoch": 0.08116883116883117, + "grad_norm": 1.328125, + "learning_rate": 1e-05, + "loss": 0.5572, + "step": 25 + }, + { + "epoch": 0.08441558441558442, + "grad_norm": 1.4765625, + "learning_rate": 1.04e-05, + "loss": 0.542, + "step": 26 + }, + { + "epoch": 0.08766233766233766, + "grad_norm": 1.1171875, + "learning_rate": 1.0800000000000002e-05, + "loss": 0.5317, + "step": 27 + }, + { + "epoch": 0.09090909090909091, + "grad_norm": 0.90625, + "learning_rate": 1.1200000000000001e-05, + "loss": 0.5173, + "step": 28 + }, + { + "epoch": 0.09415584415584416, + "grad_norm": 0.83984375, + "learning_rate": 1.16e-05, + "loss": 0.4892, + "step": 29 + }, + { + "epoch": 0.09740259740259741, + "grad_norm": 0.828125, + "learning_rate": 1.2e-05, + "loss": 0.491, + "step": 30 + }, + { + "epoch": 0.09740259740259741, + "eval_loss": 0.48583006858825684, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9705, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 30 + }, + { + "epoch": 0.10064935064935066, + "grad_norm": 0.8359375, + "learning_rate": 1.2400000000000002e-05, + "loss": 0.4852, + "step": 31 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 1.0078125, + "learning_rate": 1.2800000000000001e-05, + "loss": 0.4749, + "step": 32 + }, + { + "epoch": 0.10714285714285714, + "grad_norm": 0.99609375, + "learning_rate": 1.3200000000000002e-05, + "loss": 0.467, + "step": 33 + }, + { + "epoch": 0.11038961038961038, + "grad_norm": 0.734375, + "learning_rate": 1.3600000000000002e-05, + "loss": 0.4545, + "step": 34 + }, + { + "epoch": 0.11363636363636363, + "grad_norm": 0.69140625, + "learning_rate": 1.4e-05, + "loss": 0.4609, + "step": 35 + }, + { + "epoch": 0.11688311688311688, + "grad_norm": 0.69921875, + "learning_rate": 1.4400000000000001e-05, + "loss": 0.4497, + "step": 36 + }, + { + "epoch": 0.12012987012987013, + "grad_norm": 0.703125, + "learning_rate": 1.48e-05, + "loss": 0.4607, + "step": 37 + }, + { + "epoch": 0.12337662337662338, + "grad_norm": 0.6328125, + "learning_rate": 1.5200000000000002e-05, + "loss": 0.443, + "step": 38 + }, + { + "epoch": 0.1266233766233766, + "grad_norm": 0.65234375, + "learning_rate": 1.5600000000000003e-05, + "loss": 0.4428, + "step": 39 + }, + { + "epoch": 0.12987012987012986, + "grad_norm": 0.640625, + "learning_rate": 1.6000000000000003e-05, + "loss": 0.435, + "step": 40 + }, + { + "epoch": 0.12987012987012986, + "eval_loss": 0.4367639422416687, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0177, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 40 + }, + { + "epoch": 0.1331168831168831, + "grad_norm": 0.671875, + "learning_rate": 1.64e-05, + "loss": 0.438, + "step": 41 + }, + { + "epoch": 0.13636363636363635, + "grad_norm": 0.6484375, + "learning_rate": 1.6800000000000002e-05, + "loss": 0.4392, + "step": 42 + }, + { + "epoch": 0.1396103896103896, + "grad_norm": 0.65234375, + "learning_rate": 1.72e-05, + "loss": 0.435, + "step": 43 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.62109375, + "learning_rate": 1.76e-05, + "loss": 0.4356, + "step": 44 + }, + { + "epoch": 0.1461038961038961, + "grad_norm": 0.6171875, + "learning_rate": 1.8e-05, + "loss": 0.4172, + "step": 45 + }, + { + "epoch": 0.14935064935064934, + "grad_norm": 0.6015625, + "learning_rate": 1.8400000000000003e-05, + "loss": 0.4162, + "step": 46 + }, + { + "epoch": 0.1525974025974026, + "grad_norm": 0.609375, + "learning_rate": 1.88e-05, + "loss": 0.418, + "step": 47 + }, + { + "epoch": 0.15584415584415584, + "grad_norm": 0.6328125, + "learning_rate": 1.9200000000000003e-05, + "loss": 0.4177, + "step": 48 + }, + { + "epoch": 0.1590909090909091, + "grad_norm": 0.6171875, + "learning_rate": 1.9600000000000002e-05, + "loss": 0.4064, + "step": 49 + }, + { + "epoch": 0.16233766233766234, + "grad_norm": 0.62890625, + "learning_rate": 2e-05, + "loss": 0.4078, + "step": 50 + }, + { + "epoch": 0.16233766233766234, + "eval_loss": 0.4077843129634857, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.8482, + "eval_samples_per_second": 11.89, + "eval_steps_per_second": 1.487, + "step": 50 + }, + { + "epoch": 0.16558441558441558, + "grad_norm": 0.61328125, + "learning_rate": 1.9999258647132645e-05, + "loss": 0.4057, + "step": 51 + }, + { + "epoch": 0.16883116883116883, + "grad_norm": 0.62890625, + "learning_rate": 1.9997034698451396e-05, + "loss": 0.4172, + "step": 52 + }, + { + "epoch": 0.17207792207792208, + "grad_norm": 0.61328125, + "learning_rate": 1.9993328483702393e-05, + "loss": 0.4082, + "step": 53 + }, + { + "epoch": 0.17532467532467533, + "grad_norm": 0.59375, + "learning_rate": 1.998814055240823e-05, + "loss": 0.3973, + "step": 54 + }, + { + "epoch": 0.17857142857142858, + "grad_norm": 0.59375, + "learning_rate": 1.998147167378645e-05, + "loss": 0.3969, + "step": 55 + }, + { + "epoch": 0.18181818181818182, + "grad_norm": 0.609375, + "learning_rate": 1.9973322836635517e-05, + "loss": 0.4032, + "step": 56 + }, + { + "epoch": 0.18506493506493507, + "grad_norm": 0.5859375, + "learning_rate": 1.9963695249188185e-05, + "loss": 0.3956, + "step": 57 + }, + { + "epoch": 0.18831168831168832, + "grad_norm": 0.57421875, + "learning_rate": 1.995259033893236e-05, + "loss": 0.3952, + "step": 58 + }, + { + "epoch": 0.19155844155844157, + "grad_norm": 0.59765625, + "learning_rate": 1.9940009752399462e-05, + "loss": 0.3905, + "step": 59 + }, + { + "epoch": 0.19480519480519481, + "grad_norm": 0.60546875, + "learning_rate": 1.9925955354920265e-05, + "loss": 0.3822, + "step": 60 + }, + { + "epoch": 0.19480519480519481, + "eval_loss": 0.38575297594070435, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9122, + "eval_samples_per_second": 11.886, + "eval_steps_per_second": 1.486, + "step": 60 + }, + { + "epoch": 0.19805194805194806, + "grad_norm": 0.5859375, + "learning_rate": 1.9910429230348348e-05, + "loss": 0.3976, + "step": 61 + }, + { + "epoch": 0.2012987012987013, + "grad_norm": 0.578125, + "learning_rate": 1.9893433680751105e-05, + "loss": 0.3714, + "step": 62 + }, + { + "epoch": 0.20454545454545456, + "grad_norm": 0.5859375, + "learning_rate": 1.9874971226068417e-05, + "loss": 0.3739, + "step": 63 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 0.5859375, + "learning_rate": 1.985504460373903e-05, + "loss": 0.3907, + "step": 64 + }, + { + "epoch": 0.21103896103896103, + "grad_norm": 0.609375, + "learning_rate": 1.983365676829466e-05, + "loss": 0.3803, + "step": 65 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.59765625, + "learning_rate": 1.9810810890921943e-05, + "loss": 0.3902, + "step": 66 + }, + { + "epoch": 0.21753246753246752, + "grad_norm": 0.578125, + "learning_rate": 1.9786510358992213e-05, + "loss": 0.3744, + "step": 67 + }, + { + "epoch": 0.22077922077922077, + "grad_norm": 0.56640625, + "learning_rate": 1.9760758775559275e-05, + "loss": 0.3668, + "step": 68 + }, + { + "epoch": 0.22402597402597402, + "grad_norm": 0.625, + "learning_rate": 1.9733559958825167e-05, + "loss": 0.3755, + "step": 69 + }, + { + "epoch": 0.22727272727272727, + "grad_norm": 0.60546875, + "learning_rate": 1.9704917941574053e-05, + "loss": 0.3733, + "step": 70 + }, + { + "epoch": 0.22727272727272727, + "eval_loss": 0.3694484233856201, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9363, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 70 + }, + { + "epoch": 0.2305194805194805, + "grad_norm": 0.6015625, + "learning_rate": 1.9674836970574253e-05, + "loss": 0.3676, + "step": 71 + }, + { + "epoch": 0.23376623376623376, + "grad_norm": 0.60546875, + "learning_rate": 1.9643321505948588e-05, + "loss": 0.3721, + "step": 72 + }, + { + "epoch": 0.237012987012987, + "grad_norm": 0.60546875, + "learning_rate": 1.9610376220513067e-05, + "loss": 0.3558, + "step": 73 + }, + { + "epoch": 0.24025974025974026, + "grad_norm": 0.625, + "learning_rate": 1.957600599908406e-05, + "loss": 0.357, + "step": 74 + }, + { + "epoch": 0.2435064935064935, + "grad_norm": 0.66015625, + "learning_rate": 1.954021593775401e-05, + "loss": 0.3608, + "step": 75 + }, + { + "epoch": 0.24675324675324675, + "grad_norm": 0.59375, + "learning_rate": 1.9503011343135828e-05, + "loss": 0.3513, + "step": 76 + }, + { + "epoch": 0.25, + "grad_norm": 0.609375, + "learning_rate": 1.9464397731576093e-05, + "loss": 0.3693, + "step": 77 + }, + { + "epoch": 0.2532467532467532, + "grad_norm": 0.59375, + "learning_rate": 1.9424380828337146e-05, + "loss": 0.3605, + "step": 78 + }, + { + "epoch": 0.2564935064935065, + "grad_norm": 0.6171875, + "learning_rate": 1.938296656674817e-05, + "loss": 0.3553, + "step": 79 + }, + { + "epoch": 0.2597402597402597, + "grad_norm": 0.671875, + "learning_rate": 1.9340161087325483e-05, + "loss": 0.3721, + "step": 80 + }, + { + "epoch": 0.2597402597402597, + "eval_loss": 0.3553767800331116, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0277, + "eval_samples_per_second": 11.878, + "eval_steps_per_second": 1.485, + "step": 80 + }, + { + "epoch": 0.262987012987013, + "grad_norm": 0.609375, + "learning_rate": 1.9295970736862063e-05, + "loss": 0.3597, + "step": 81 + }, + { + "epoch": 0.2662337662337662, + "grad_norm": 0.65625, + "learning_rate": 1.9250402067486523e-05, + "loss": 0.3527, + "step": 82 + }, + { + "epoch": 0.2694805194805195, + "grad_norm": 0.61328125, + "learning_rate": 1.9203461835691596e-05, + "loss": 0.3528, + "step": 83 + }, + { + "epoch": 0.2727272727272727, + "grad_norm": 0.6640625, + "learning_rate": 1.9155157001332374e-05, + "loss": 0.356, + "step": 84 + }, + { + "epoch": 0.275974025974026, + "grad_norm": 0.6171875, + "learning_rate": 1.9105494726594344e-05, + "loss": 0.3556, + "step": 85 + }, + { + "epoch": 0.2792207792207792, + "grad_norm": 0.6171875, + "learning_rate": 1.905448237493147e-05, + "loss": 0.3473, + "step": 86 + }, + { + "epoch": 0.2824675324675325, + "grad_norm": 0.5859375, + "learning_rate": 1.9002127509974376e-05, + "loss": 0.3441, + "step": 87 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.6171875, + "learning_rate": 1.894843789440892e-05, + "loss": 0.3492, + "step": 88 + }, + { + "epoch": 0.288961038961039, + "grad_norm": 0.6328125, + "learning_rate": 1.889342148882519e-05, + "loss": 0.3338, + "step": 89 + }, + { + "epoch": 0.2922077922077922, + "grad_norm": 0.67578125, + "learning_rate": 1.8837086450537195e-05, + "loss": 0.3347, + "step": 90 + }, + { + "epoch": 0.2922077922077922, + "eval_loss": 0.34332525730133057, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9257, + "eval_samples_per_second": 11.885, + "eval_steps_per_second": 1.486, + "step": 90 + }, + { + "epoch": 0.29545454545454547, + "grad_norm": 0.6328125, + "learning_rate": 1.877944113237336e-05, + "loss": 0.3438, + "step": 91 + }, + { + "epoch": 0.2987012987012987, + "grad_norm": 0.6328125, + "learning_rate": 1.872049408143808e-05, + "loss": 0.3505, + "step": 92 + }, + { + "epoch": 0.30194805194805197, + "grad_norm": 0.6328125, + "learning_rate": 1.866025403784439e-05, + "loss": 0.3362, + "step": 93 + }, + { + "epoch": 0.3051948051948052, + "grad_norm": 0.640625, + "learning_rate": 1.8598729933418102e-05, + "loss": 0.337, + "step": 94 + }, + { + "epoch": 0.30844155844155846, + "grad_norm": 0.64453125, + "learning_rate": 1.8535930890373467e-05, + "loss": 0.3324, + "step": 95 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 0.6875, + "learning_rate": 1.8471866219960604e-05, + "loss": 0.3461, + "step": 96 + }, + { + "epoch": 0.31493506493506496, + "grad_norm": 0.6328125, + "learning_rate": 1.840654542108494e-05, + "loss": 0.3318, + "step": 97 + }, + { + "epoch": 0.3181818181818182, + "grad_norm": 0.62109375, + "learning_rate": 1.833997817889878e-05, + "loss": 0.3335, + "step": 98 + }, + { + "epoch": 0.32142857142857145, + "grad_norm": 0.61328125, + "learning_rate": 1.82721743633653e-05, + "loss": 0.3291, + "step": 99 + }, + { + "epoch": 0.3246753246753247, + "grad_norm": 0.6171875, + "learning_rate": 1.820314402779511e-05, + "loss": 0.3324, + "step": 100 + }, + { + "epoch": 0.3246753246753247, + "eval_loss": 0.33332687616348267, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9506, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 100 + } + ], + "logging_steps": 1, + "max_steps": 308, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "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": 5.902112919650304e+17, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4684d3c90558d6bfde405c82b58596bc6231bfee --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09f69be12f7ef607f0a1508435a517f5277e3160e5d6a59346e619fcbaa3592 +size 5176 diff --git a/checkpoint-200/config.json b/checkpoint-200/config.json new file mode 100644 index 0000000000000000000000000000000000000000..de55730a672c2805e1108109d81a111b0cdb48b1 --- /dev/null +++ b/checkpoint-200/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a +size 915 diff --git a/checkpoint-200/generation_config.json b/checkpoint-200/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1007819213eaa3e36dd0c6354016734419f4a863 --- /dev/null +++ b/checkpoint-200/generation_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169 +size 184 diff --git a/checkpoint-200/model-00001-of-00004.safetensors b/checkpoint-200/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b93fb6a70ec884fefa8fb9e512f28014f307c5d3 --- /dev/null +++ b/checkpoint-200/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60fb798be6dc6cc800be220165509b7026f9d04bd5a45d6fae8c0cf42cbf3dd +size 4976698672 diff --git a/checkpoint-200/model-00002-of-00004.safetensors b/checkpoint-200/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13989d38402ddcfbe36426f1055a88abed496fcc --- /dev/null +++ b/checkpoint-200/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1161b03770b7cceaea53010a7c38cae4279bc7ba02d9c0f3584d7574226c2f1 +size 4999802720 diff --git a/checkpoint-200/model-00003-of-00004.safetensors b/checkpoint-200/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e18db12e3a7135207816b0dd636a61b5e3f99d02 --- /dev/null +++ b/checkpoint-200/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591b6342c93199d69b2d7dbe15e08a0975ac4bdcc33b07e0b5b542e8b6443413 +size 4915916176 diff --git a/checkpoint-200/model-00004-of-00004.safetensors b/checkpoint-200/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..217828132fe10ef3484b01ebe969c47246643b1f --- /dev/null +++ b/checkpoint-200/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ee9a2f97c92c6b4160444f1a13d52f249d6116c60b9952ae9ad61c992f57f53 +size 1168138808 diff --git a/checkpoint-200/model.safetensors.index.json b/checkpoint-200/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..a054aad8cf0cb5671e2e10b3bf817725a4bec031 --- /dev/null +++ b/checkpoint-200/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b +size 23950 diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..adb85a97d34e21fd969fd25f6211f6315fd4497a --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025f20483fbcef43f00f5dd8acbb4ab663455020f9b7ec9b2086cfadf235d021 +size 32121299754 diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea17f6c5f674e0024fa4c4dc7b8e9d3161488eb2 --- /dev/null +++ b/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aad5da87704f9496a4cad943d2aa8988a987b1e77b57fa4a28ff4c89ee480ac0 +size 14244 diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcaef4e2ef2966c7ebc24289d3f1cf775db9fecb --- /dev/null +++ b/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4565f7ec171134b011efb3a86c834a370c710414c88a26b6961aac2a0ed0d92d +size 1064 diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92d7fab6729d723f45689803b99006fec945cc47 --- /dev/null +++ b/checkpoint-200/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1835caa5b4d70acaa210fa222b0036f1882f9525c4660fd4810fb3e1e40ff8 +size 325 diff --git a/checkpoint-200/tokenizer.json b/checkpoint-200/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..66cd9d7e0daec95eb10d16a63c615637dbbb7304 --- /dev/null +++ b/checkpoint-200/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4 +size 9085657 diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..08ebc9598183a9a76c44ef06813aca75f51de4a5 --- /dev/null +++ b/checkpoint-200/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d0de6d831b5940c3f2eae4e495b9f77612cbb05b5804846733ab617f0dfe9b +size 55380 diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..12d700d76ba184fe64e59008829d6815d563c6db --- /dev/null +++ b/checkpoint-200/trainer_state.json @@ -0,0 +1,1613 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.6493506493506493, + "eval_steps": 10, + "global_step": 200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.003246753246753247, + "grad_norm": 16.375, + "learning_rate": 4.0000000000000003e-07, + "loss": 1.4017, + "step": 1 + }, + { + "epoch": 0.006493506493506494, + "grad_norm": 16.25, + "learning_rate": 8.000000000000001e-07, + "loss": 1.4229, + "step": 2 + }, + { + "epoch": 0.00974025974025974, + "grad_norm": 16.75, + "learning_rate": 1.2000000000000002e-06, + "loss": 1.4112, + "step": 3 + }, + { + "epoch": 0.012987012987012988, + "grad_norm": 16.5, + "learning_rate": 1.6000000000000001e-06, + "loss": 1.3959, + "step": 4 + }, + { + "epoch": 0.016233766233766232, + "grad_norm": 16.125, + "learning_rate": 2.0000000000000003e-06, + "loss": 1.3789, + "step": 5 + }, + { + "epoch": 0.01948051948051948, + "grad_norm": 14.4375, + "learning_rate": 2.4000000000000003e-06, + "loss": 1.3618, + "step": 6 + }, + { + "epoch": 0.022727272727272728, + "grad_norm": 10.1875, + "learning_rate": 2.8000000000000003e-06, + "loss": 1.3214, + "step": 7 + }, + { + "epoch": 0.025974025974025976, + "grad_norm": 7.4375, + "learning_rate": 3.2000000000000003e-06, + "loss": 1.2885, + "step": 8 + }, + { + "epoch": 0.02922077922077922, + "grad_norm": 6.28125, + "learning_rate": 3.6000000000000003e-06, + "loss": 1.2436, + "step": 9 + }, + { + "epoch": 0.032467532467532464, + "grad_norm": 5.75, + "learning_rate": 4.000000000000001e-06, + "loss": 1.2269, + "step": 10 + }, + { + "epoch": 0.032467532467532464, + "eval_loss": 1.1976113319396973, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0273, + "eval_samples_per_second": 11.878, + "eval_steps_per_second": 1.485, + "step": 10 + }, + { + "epoch": 0.03571428571428571, + "grad_norm": 5.375, + "learning_rate": 4.4e-06, + "loss": 1.1925, + "step": 11 + }, + { + "epoch": 0.03896103896103896, + "grad_norm": 5.125, + "learning_rate": 4.800000000000001e-06, + "loss": 1.1307, + "step": 12 + }, + { + "epoch": 0.04220779220779221, + "grad_norm": 5.125, + "learning_rate": 5.2e-06, + "loss": 1.0778, + "step": 13 + }, + { + "epoch": 0.045454545454545456, + "grad_norm": 5.0625, + "learning_rate": 5.600000000000001e-06, + "loss": 1.0067, + "step": 14 + }, + { + "epoch": 0.048701298701298704, + "grad_norm": 5.75, + "learning_rate": 6e-06, + "loss": 0.9668, + "step": 15 + }, + { + "epoch": 0.05194805194805195, + "grad_norm": 5.15625, + "learning_rate": 6.4000000000000006e-06, + "loss": 0.875, + "step": 16 + }, + { + "epoch": 0.05519480519480519, + "grad_norm": 4.875, + "learning_rate": 6.800000000000001e-06, + "loss": 0.8297, + "step": 17 + }, + { + "epoch": 0.05844155844155844, + "grad_norm": 4.5625, + "learning_rate": 7.2000000000000005e-06, + "loss": 0.7703, + "step": 18 + }, + { + "epoch": 0.06168831168831169, + "grad_norm": 3.90625, + "learning_rate": 7.600000000000001e-06, + "loss": 0.7327, + "step": 19 + }, + { + "epoch": 0.06493506493506493, + "grad_norm": 2.78125, + "learning_rate": 8.000000000000001e-06, + "loss": 0.6672, + "step": 20 + }, + { + "epoch": 0.06493506493506493, + "eval_loss": 0.6521233320236206, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.999, + "eval_samples_per_second": 11.88, + "eval_steps_per_second": 1.486, + "step": 20 + }, + { + "epoch": 0.06818181818181818, + "grad_norm": 2.140625, + "learning_rate": 8.400000000000001e-06, + "loss": 0.6507, + "step": 21 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.828125, + "learning_rate": 8.8e-06, + "loss": 0.6215, + "step": 22 + }, + { + "epoch": 0.07467532467532467, + "grad_norm": 1.5546875, + "learning_rate": 9.200000000000002e-06, + "loss": 0.5992, + "step": 23 + }, + { + "epoch": 0.07792207792207792, + "grad_norm": 1.4453125, + "learning_rate": 9.600000000000001e-06, + "loss": 0.5748, + "step": 24 + }, + { + "epoch": 0.08116883116883117, + "grad_norm": 1.328125, + "learning_rate": 1e-05, + "loss": 0.5572, + "step": 25 + }, + { + "epoch": 0.08441558441558442, + "grad_norm": 1.4765625, + "learning_rate": 1.04e-05, + "loss": 0.542, + "step": 26 + }, + { + "epoch": 0.08766233766233766, + "grad_norm": 1.1171875, + "learning_rate": 1.0800000000000002e-05, + "loss": 0.5317, + "step": 27 + }, + { + "epoch": 0.09090909090909091, + "grad_norm": 0.90625, + "learning_rate": 1.1200000000000001e-05, + "loss": 0.5173, + "step": 28 + }, + { + "epoch": 0.09415584415584416, + "grad_norm": 0.83984375, + "learning_rate": 1.16e-05, + "loss": 0.4892, + "step": 29 + }, + { + "epoch": 0.09740259740259741, + "grad_norm": 0.828125, + "learning_rate": 1.2e-05, + "loss": 0.491, + "step": 30 + }, + { + "epoch": 0.09740259740259741, + "eval_loss": 0.48583006858825684, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9705, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 30 + }, + { + "epoch": 0.10064935064935066, + "grad_norm": 0.8359375, + "learning_rate": 1.2400000000000002e-05, + "loss": 0.4852, + "step": 31 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 1.0078125, + "learning_rate": 1.2800000000000001e-05, + "loss": 0.4749, + "step": 32 + }, + { + "epoch": 0.10714285714285714, + "grad_norm": 0.99609375, + "learning_rate": 1.3200000000000002e-05, + "loss": 0.467, + "step": 33 + }, + { + "epoch": 0.11038961038961038, + "grad_norm": 0.734375, + "learning_rate": 1.3600000000000002e-05, + "loss": 0.4545, + "step": 34 + }, + { + "epoch": 0.11363636363636363, + "grad_norm": 0.69140625, + "learning_rate": 1.4e-05, + "loss": 0.4609, + "step": 35 + }, + { + "epoch": 0.11688311688311688, + "grad_norm": 0.69921875, + "learning_rate": 1.4400000000000001e-05, + "loss": 0.4497, + "step": 36 + }, + { + "epoch": 0.12012987012987013, + "grad_norm": 0.703125, + "learning_rate": 1.48e-05, + "loss": 0.4607, + "step": 37 + }, + { + "epoch": 0.12337662337662338, + "grad_norm": 0.6328125, + "learning_rate": 1.5200000000000002e-05, + "loss": 0.443, + "step": 38 + }, + { + "epoch": 0.1266233766233766, + "grad_norm": 0.65234375, + "learning_rate": 1.5600000000000003e-05, + "loss": 0.4428, + "step": 39 + }, + { + "epoch": 0.12987012987012986, + "grad_norm": 0.640625, + "learning_rate": 1.6000000000000003e-05, + "loss": 0.435, + "step": 40 + }, + { + "epoch": 0.12987012987012986, + "eval_loss": 0.4367639422416687, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0177, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 40 + }, + { + "epoch": 0.1331168831168831, + "grad_norm": 0.671875, + "learning_rate": 1.64e-05, + "loss": 0.438, + "step": 41 + }, + { + "epoch": 0.13636363636363635, + "grad_norm": 0.6484375, + "learning_rate": 1.6800000000000002e-05, + "loss": 0.4392, + "step": 42 + }, + { + "epoch": 0.1396103896103896, + "grad_norm": 0.65234375, + "learning_rate": 1.72e-05, + "loss": 0.435, + "step": 43 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.62109375, + "learning_rate": 1.76e-05, + "loss": 0.4356, + "step": 44 + }, + { + "epoch": 0.1461038961038961, + "grad_norm": 0.6171875, + "learning_rate": 1.8e-05, + "loss": 0.4172, + "step": 45 + }, + { + "epoch": 0.14935064935064934, + "grad_norm": 0.6015625, + "learning_rate": 1.8400000000000003e-05, + "loss": 0.4162, + "step": 46 + }, + { + "epoch": 0.1525974025974026, + "grad_norm": 0.609375, + "learning_rate": 1.88e-05, + "loss": 0.418, + "step": 47 + }, + { + "epoch": 0.15584415584415584, + "grad_norm": 0.6328125, + "learning_rate": 1.9200000000000003e-05, + "loss": 0.4177, + "step": 48 + }, + { + "epoch": 0.1590909090909091, + "grad_norm": 0.6171875, + "learning_rate": 1.9600000000000002e-05, + "loss": 0.4064, + "step": 49 + }, + { + "epoch": 0.16233766233766234, + "grad_norm": 0.62890625, + "learning_rate": 2e-05, + "loss": 0.4078, + "step": 50 + }, + { + "epoch": 0.16233766233766234, + "eval_loss": 0.4077843129634857, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.8482, + "eval_samples_per_second": 11.89, + "eval_steps_per_second": 1.487, + "step": 50 + }, + { + "epoch": 0.16558441558441558, + "grad_norm": 0.61328125, + "learning_rate": 1.9999258647132645e-05, + "loss": 0.4057, + "step": 51 + }, + { + "epoch": 0.16883116883116883, + "grad_norm": 0.62890625, + "learning_rate": 1.9997034698451396e-05, + "loss": 0.4172, + "step": 52 + }, + { + "epoch": 0.17207792207792208, + "grad_norm": 0.61328125, + "learning_rate": 1.9993328483702393e-05, + "loss": 0.4082, + "step": 53 + }, + { + "epoch": 0.17532467532467533, + "grad_norm": 0.59375, + "learning_rate": 1.998814055240823e-05, + "loss": 0.3973, + "step": 54 + }, + { + "epoch": 0.17857142857142858, + "grad_norm": 0.59375, + "learning_rate": 1.998147167378645e-05, + "loss": 0.3969, + "step": 55 + }, + { + "epoch": 0.18181818181818182, + "grad_norm": 0.609375, + "learning_rate": 1.9973322836635517e-05, + "loss": 0.4032, + "step": 56 + }, + { + "epoch": 0.18506493506493507, + "grad_norm": 0.5859375, + "learning_rate": 1.9963695249188185e-05, + "loss": 0.3956, + "step": 57 + }, + { + "epoch": 0.18831168831168832, + "grad_norm": 0.57421875, + "learning_rate": 1.995259033893236e-05, + "loss": 0.3952, + "step": 58 + }, + { + "epoch": 0.19155844155844157, + "grad_norm": 0.59765625, + "learning_rate": 1.9940009752399462e-05, + "loss": 0.3905, + "step": 59 + }, + { + "epoch": 0.19480519480519481, + "grad_norm": 0.60546875, + "learning_rate": 1.9925955354920265e-05, + "loss": 0.3822, + "step": 60 + }, + { + "epoch": 0.19480519480519481, + "eval_loss": 0.38575297594070435, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9122, + "eval_samples_per_second": 11.886, + "eval_steps_per_second": 1.486, + "step": 60 + }, + { + "epoch": 0.19805194805194806, + "grad_norm": 0.5859375, + "learning_rate": 1.9910429230348348e-05, + "loss": 0.3976, + "step": 61 + }, + { + "epoch": 0.2012987012987013, + "grad_norm": 0.578125, + "learning_rate": 1.9893433680751105e-05, + "loss": 0.3714, + "step": 62 + }, + { + "epoch": 0.20454545454545456, + "grad_norm": 0.5859375, + "learning_rate": 1.9874971226068417e-05, + "loss": 0.3739, + "step": 63 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 0.5859375, + "learning_rate": 1.985504460373903e-05, + "loss": 0.3907, + "step": 64 + }, + { + "epoch": 0.21103896103896103, + "grad_norm": 0.609375, + "learning_rate": 1.983365676829466e-05, + "loss": 0.3803, + "step": 65 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.59765625, + "learning_rate": 1.9810810890921943e-05, + "loss": 0.3902, + "step": 66 + }, + { + "epoch": 0.21753246753246752, + "grad_norm": 0.578125, + "learning_rate": 1.9786510358992213e-05, + "loss": 0.3744, + "step": 67 + }, + { + "epoch": 0.22077922077922077, + "grad_norm": 0.56640625, + "learning_rate": 1.9760758775559275e-05, + "loss": 0.3668, + "step": 68 + }, + { + "epoch": 0.22402597402597402, + "grad_norm": 0.625, + "learning_rate": 1.9733559958825167e-05, + "loss": 0.3755, + "step": 69 + }, + { + "epoch": 0.22727272727272727, + "grad_norm": 0.60546875, + "learning_rate": 1.9704917941574053e-05, + "loss": 0.3733, + "step": 70 + }, + { + "epoch": 0.22727272727272727, + "eval_loss": 0.3694484233856201, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9363, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 70 + }, + { + "epoch": 0.2305194805194805, + "grad_norm": 0.6015625, + "learning_rate": 1.9674836970574253e-05, + "loss": 0.3676, + "step": 71 + }, + { + "epoch": 0.23376623376623376, + "grad_norm": 0.60546875, + "learning_rate": 1.9643321505948588e-05, + "loss": 0.3721, + "step": 72 + }, + { + "epoch": 0.237012987012987, + "grad_norm": 0.60546875, + "learning_rate": 1.9610376220513067e-05, + "loss": 0.3558, + "step": 73 + }, + { + "epoch": 0.24025974025974026, + "grad_norm": 0.625, + "learning_rate": 1.957600599908406e-05, + "loss": 0.357, + "step": 74 + }, + { + "epoch": 0.2435064935064935, + "grad_norm": 0.66015625, + "learning_rate": 1.954021593775401e-05, + "loss": 0.3608, + "step": 75 + }, + { + "epoch": 0.24675324675324675, + "grad_norm": 0.59375, + "learning_rate": 1.9503011343135828e-05, + "loss": 0.3513, + "step": 76 + }, + { + "epoch": 0.25, + "grad_norm": 0.609375, + "learning_rate": 1.9464397731576093e-05, + "loss": 0.3693, + "step": 77 + }, + { + "epoch": 0.2532467532467532, + "grad_norm": 0.59375, + "learning_rate": 1.9424380828337146e-05, + "loss": 0.3605, + "step": 78 + }, + { + "epoch": 0.2564935064935065, + "grad_norm": 0.6171875, + "learning_rate": 1.938296656674817e-05, + "loss": 0.3553, + "step": 79 + }, + { + "epoch": 0.2597402597402597, + "grad_norm": 0.671875, + "learning_rate": 1.9340161087325483e-05, + "loss": 0.3721, + "step": 80 + }, + { + "epoch": 0.2597402597402597, + "eval_loss": 0.3553767800331116, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0277, + "eval_samples_per_second": 11.878, + "eval_steps_per_second": 1.485, + "step": 80 + }, + { + "epoch": 0.262987012987013, + "grad_norm": 0.609375, + "learning_rate": 1.9295970736862063e-05, + "loss": 0.3597, + "step": 81 + }, + { + "epoch": 0.2662337662337662, + "grad_norm": 0.65625, + "learning_rate": 1.9250402067486523e-05, + "loss": 0.3527, + "step": 82 + }, + { + "epoch": 0.2694805194805195, + "grad_norm": 0.61328125, + "learning_rate": 1.9203461835691596e-05, + "loss": 0.3528, + "step": 83 + }, + { + "epoch": 0.2727272727272727, + "grad_norm": 0.6640625, + "learning_rate": 1.9155157001332374e-05, + "loss": 0.356, + "step": 84 + }, + { + "epoch": 0.275974025974026, + "grad_norm": 0.6171875, + "learning_rate": 1.9105494726594344e-05, + "loss": 0.3556, + "step": 85 + }, + { + "epoch": 0.2792207792207792, + "grad_norm": 0.6171875, + "learning_rate": 1.905448237493147e-05, + "loss": 0.3473, + "step": 86 + }, + { + "epoch": 0.2824675324675325, + "grad_norm": 0.5859375, + "learning_rate": 1.9002127509974376e-05, + "loss": 0.3441, + "step": 87 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.6171875, + "learning_rate": 1.894843789440892e-05, + "loss": 0.3492, + "step": 88 + }, + { + "epoch": 0.288961038961039, + "grad_norm": 0.6328125, + "learning_rate": 1.889342148882519e-05, + "loss": 0.3338, + "step": 89 + }, + { + "epoch": 0.2922077922077922, + "grad_norm": 0.67578125, + "learning_rate": 1.8837086450537195e-05, + "loss": 0.3347, + "step": 90 + }, + { + "epoch": 0.2922077922077922, + "eval_loss": 0.34332525730133057, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9257, + "eval_samples_per_second": 11.885, + "eval_steps_per_second": 1.486, + "step": 90 + }, + { + "epoch": 0.29545454545454547, + "grad_norm": 0.6328125, + "learning_rate": 1.877944113237336e-05, + "loss": 0.3438, + "step": 91 + }, + { + "epoch": 0.2987012987012987, + "grad_norm": 0.6328125, + "learning_rate": 1.872049408143808e-05, + "loss": 0.3505, + "step": 92 + }, + { + "epoch": 0.30194805194805197, + "grad_norm": 0.6328125, + "learning_rate": 1.866025403784439e-05, + "loss": 0.3362, + "step": 93 + }, + { + "epoch": 0.3051948051948052, + "grad_norm": 0.640625, + "learning_rate": 1.8598729933418102e-05, + "loss": 0.337, + "step": 94 + }, + { + "epoch": 0.30844155844155846, + "grad_norm": 0.64453125, + "learning_rate": 1.8535930890373467e-05, + "loss": 0.3324, + "step": 95 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 0.6875, + "learning_rate": 1.8471866219960604e-05, + "loss": 0.3461, + "step": 96 + }, + { + "epoch": 0.31493506493506496, + "grad_norm": 0.6328125, + "learning_rate": 1.840654542108494e-05, + "loss": 0.3318, + "step": 97 + }, + { + "epoch": 0.3181818181818182, + "grad_norm": 0.62109375, + "learning_rate": 1.833997817889878e-05, + "loss": 0.3335, + "step": 98 + }, + { + "epoch": 0.32142857142857145, + "grad_norm": 0.61328125, + "learning_rate": 1.82721743633653e-05, + "loss": 0.3291, + "step": 99 + }, + { + "epoch": 0.3246753246753247, + "grad_norm": 0.6171875, + "learning_rate": 1.820314402779511e-05, + "loss": 0.3324, + "step": 100 + }, + { + "epoch": 0.3246753246753247, + "eval_loss": 0.33332687616348267, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9506, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 100 + }, + { + "epoch": 0.32792207792207795, + "grad_norm": 0.6328125, + "learning_rate": 1.8132897407355657e-05, + "loss": 0.3288, + "step": 101 + }, + { + "epoch": 0.33116883116883117, + "grad_norm": 0.6484375, + "learning_rate": 1.806144491755363e-05, + "loss": 0.3384, + "step": 102 + }, + { + "epoch": 0.3344155844155844, + "grad_norm": 0.6328125, + "learning_rate": 1.798879715269067e-05, + "loss": 0.3329, + "step": 103 + }, + { + "epoch": 0.33766233766233766, + "grad_norm": 0.6171875, + "learning_rate": 1.7914964884292543e-05, + "loss": 0.3329, + "step": 104 + }, + { + "epoch": 0.3409090909090909, + "grad_norm": 0.671875, + "learning_rate": 1.7839959059512016e-05, + "loss": 0.3335, + "step": 105 + }, + { + "epoch": 0.34415584415584416, + "grad_norm": 0.609375, + "learning_rate": 1.7763790799505746e-05, + "loss": 0.3201, + "step": 106 + }, + { + "epoch": 0.3474025974025974, + "grad_norm": 0.6171875, + "learning_rate": 1.7686471397785322e-05, + "loss": 0.3327, + "step": 107 + }, + { + "epoch": 0.35064935064935066, + "grad_norm": 0.640625, + "learning_rate": 1.760801231854278e-05, + "loss": 0.3205, + "step": 108 + }, + { + "epoch": 0.3538961038961039, + "grad_norm": 0.6328125, + "learning_rate": 1.7528425194950794e-05, + "loss": 0.334, + "step": 109 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.6015625, + "learning_rate": 1.744772182743782e-05, + "loss": 0.3165, + "step": 110 + }, + { + "epoch": 0.35714285714285715, + "eval_loss": 0.32505103945732117, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0106, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 110 + }, + { + "epoch": 0.36038961038961037, + "grad_norm": 0.62890625, + "learning_rate": 1.736591418193844e-05, + "loss": 0.3236, + "step": 111 + }, + { + "epoch": 0.36363636363636365, + "grad_norm": 0.63671875, + "learning_rate": 1.728301438811916e-05, + "loss": 0.3192, + "step": 112 + }, + { + "epoch": 0.36688311688311687, + "grad_norm": 0.6484375, + "learning_rate": 1.7199034737579962e-05, + "loss": 0.327, + "step": 113 + }, + { + "epoch": 0.37012987012987014, + "grad_norm": 0.62109375, + "learning_rate": 1.711398768203178e-05, + "loss": 0.3169, + "step": 114 + }, + { + "epoch": 0.37337662337662336, + "grad_norm": 0.625, + "learning_rate": 1.7027885831450318e-05, + "loss": 0.3186, + "step": 115 + }, + { + "epoch": 0.37662337662337664, + "grad_norm": 0.60546875, + "learning_rate": 1.6940741952206342e-05, + "loss": 0.3136, + "step": 116 + }, + { + "epoch": 0.37987012987012986, + "grad_norm": 0.62109375, + "learning_rate": 1.6852568965172794e-05, + "loss": 0.3184, + "step": 117 + }, + { + "epoch": 0.38311688311688313, + "grad_norm": 0.60546875, + "learning_rate": 1.676337994380903e-05, + "loss": 0.3114, + "step": 118 + }, + { + "epoch": 0.38636363636363635, + "grad_norm": 0.6640625, + "learning_rate": 1.6673188112222394e-05, + "loss": 0.3329, + "step": 119 + }, + { + "epoch": 0.38961038961038963, + "grad_norm": 0.60546875, + "learning_rate": 1.658200684320748e-05, + "loss": 0.3105, + "step": 120 + }, + { + "epoch": 0.38961038961038963, + "eval_loss": 0.31796982884407043, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9896, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 120 + }, + { + "epoch": 0.39285714285714285, + "grad_norm": 0.58203125, + "learning_rate": 1.6489849656263336e-05, + "loss": 0.3084, + "step": 121 + }, + { + "epoch": 0.3961038961038961, + "grad_norm": 0.57421875, + "learning_rate": 1.6396730215588913e-05, + "loss": 0.3124, + "step": 122 + }, + { + "epoch": 0.39935064935064934, + "grad_norm": 0.609375, + "learning_rate": 1.630266232805709e-05, + "loss": 0.3167, + "step": 123 + }, + { + "epoch": 0.4025974025974026, + "grad_norm": 0.6171875, + "learning_rate": 1.6207659941167485e-05, + "loss": 0.3084, + "step": 124 + }, + { + "epoch": 0.40584415584415584, + "grad_norm": 0.62890625, + "learning_rate": 1.6111737140978495e-05, + "loss": 0.3143, + "step": 125 + }, + { + "epoch": 0.4090909090909091, + "grad_norm": 0.6171875, + "learning_rate": 1.6014908150018703e-05, + "loss": 0.3173, + "step": 126 + }, + { + "epoch": 0.41233766233766234, + "grad_norm": 0.609375, + "learning_rate": 1.591718732517814e-05, + "loss": 0.3199, + "step": 127 + }, + { + "epoch": 0.4155844155844156, + "grad_norm": 0.609375, + "learning_rate": 1.581858915557953e-05, + "loss": 0.312, + "step": 128 + }, + { + "epoch": 0.41883116883116883, + "grad_norm": 0.61328125, + "learning_rate": 1.571912826043003e-05, + "loss": 0.3217, + "step": 129 + }, + { + "epoch": 0.42207792207792205, + "grad_norm": 0.59765625, + "learning_rate": 1.5618819386853607e-05, + "loss": 0.3123, + "step": 130 + }, + { + "epoch": 0.42207792207792205, + "eval_loss": 0.3119741976261139, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9669, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 130 + }, + { + "epoch": 0.4253246753246753, + "grad_norm": 0.61328125, + "learning_rate": 1.551767740770446e-05, + "loss": 0.3088, + "step": 131 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.578125, + "learning_rate": 1.541571731936185e-05, + "loss": 0.3084, + "step": 132 + }, + { + "epoch": 0.4318181818181818, + "grad_norm": 0.6328125, + "learning_rate": 1.5312954239506536e-05, + "loss": 0.3179, + "step": 133 + }, + { + "epoch": 0.43506493506493504, + "grad_norm": 0.60546875, + "learning_rate": 1.5209403404879305e-05, + "loss": 0.3145, + "step": 134 + }, + { + "epoch": 0.4383116883116883, + "grad_norm": 0.59765625, + "learning_rate": 1.5105080169021792e-05, + "loss": 0.3045, + "step": 135 + }, + { + "epoch": 0.44155844155844154, + "grad_norm": 0.5859375, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.314, + "step": 136 + }, + { + "epoch": 0.4448051948051948, + "grad_norm": 0.6484375, + "learning_rate": 1.4894178478110856e-05, + "loss": 0.2985, + "step": 137 + }, + { + "epoch": 0.44805194805194803, + "grad_norm": 0.58984375, + "learning_rate": 1.4787631293572094e-05, + "loss": 0.3114, + "step": 138 + }, + { + "epoch": 0.4512987012987013, + "grad_norm": 0.60546875, + "learning_rate": 1.4680374244195861e-05, + "loss": 0.3129, + "step": 139 + }, + { + "epoch": 0.45454545454545453, + "grad_norm": 0.58984375, + "learning_rate": 1.4572423233046386e-05, + "loss": 0.3007, + "step": 140 + }, + { + "epoch": 0.45454545454545453, + "eval_loss": 0.30710509419441223, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9622, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 140 + }, + { + "epoch": 0.4577922077922078, + "grad_norm": 0.58203125, + "learning_rate": 1.4463794266081994e-05, + "loss": 0.2981, + "step": 141 + }, + { + "epoch": 0.461038961038961, + "grad_norm": 0.5703125, + "learning_rate": 1.4354503449781914e-05, + "loss": 0.2974, + "step": 142 + }, + { + "epoch": 0.4642857142857143, + "grad_norm": 0.5859375, + "learning_rate": 1.4244566988758152e-05, + "loss": 0.3064, + "step": 143 + }, + { + "epoch": 0.4675324675324675, + "grad_norm": 0.56640625, + "learning_rate": 1.4134001183352833e-05, + "loss": 0.298, + "step": 144 + }, + { + "epoch": 0.4707792207792208, + "grad_norm": 0.5703125, + "learning_rate": 1.4022822427221325e-05, + "loss": 0.3037, + "step": 145 + }, + { + "epoch": 0.474025974025974, + "grad_norm": 0.58203125, + "learning_rate": 1.391104720490156e-05, + "loss": 0.3062, + "step": 146 + }, + { + "epoch": 0.4772727272727273, + "grad_norm": 0.609375, + "learning_rate": 1.3798692089369855e-05, + "loss": 0.3019, + "step": 147 + }, + { + "epoch": 0.4805194805194805, + "grad_norm": 0.61328125, + "learning_rate": 1.368577373958362e-05, + "loss": 0.3008, + "step": 148 + }, + { + "epoch": 0.4837662337662338, + "grad_norm": 0.56640625, + "learning_rate": 1.3572308898011328e-05, + "loss": 0.3055, + "step": 149 + }, + { + "epoch": 0.487012987012987, + "grad_norm": 0.5859375, + "learning_rate": 1.3458314388150115e-05, + "loss": 0.2942, + "step": 150 + }, + { + "epoch": 0.487012987012987, + "eval_loss": 0.30315953493118286, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9566, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 150 + }, + { + "epoch": 0.4902597402597403, + "grad_norm": 0.578125, + "learning_rate": 1.3343807112031329e-05, + "loss": 0.3097, + "step": 151 + }, + { + "epoch": 0.4935064935064935, + "grad_norm": 0.56640625, + "learning_rate": 1.3228804047714462e-05, + "loss": 0.3004, + "step": 152 + }, + { + "epoch": 0.4967532467532468, + "grad_norm": 0.58203125, + "learning_rate": 1.3113322246769817e-05, + "loss": 0.3046, + "step": 153 + }, + { + "epoch": 0.5, + "grad_norm": 0.57421875, + "learning_rate": 1.2997378831750242e-05, + "loss": 0.2966, + "step": 154 + }, + { + "epoch": 0.5032467532467533, + "grad_norm": 0.5703125, + "learning_rate": 1.2880990993652379e-05, + "loss": 0.2989, + "step": 155 + }, + { + "epoch": 0.5064935064935064, + "grad_norm": 0.609375, + "learning_rate": 1.2764175989367717e-05, + "loss": 0.3015, + "step": 156 + }, + { + "epoch": 0.5097402597402597, + "grad_norm": 0.5703125, + "learning_rate": 1.2646951139123935e-05, + "loss": 0.2976, + "step": 157 + }, + { + "epoch": 0.512987012987013, + "grad_norm": 0.59765625, + "learning_rate": 1.2529333823916807e-05, + "loss": 0.2919, + "step": 158 + }, + { + "epoch": 0.5162337662337663, + "grad_norm": 0.6328125, + "learning_rate": 1.241134148293311e-05, + "loss": 0.3041, + "step": 159 + }, + { + "epoch": 0.5194805194805194, + "grad_norm": 0.58984375, + "learning_rate": 1.2292991610964902e-05, + "loss": 0.3053, + "step": 160 + }, + { + "epoch": 0.5194805194805194, + "eval_loss": 0.3000594675540924, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9643, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 160 + }, + { + "epoch": 0.5227272727272727, + "grad_norm": 0.5859375, + "learning_rate": 1.2174301755815572e-05, + "loss": 0.3043, + "step": 161 + }, + { + "epoch": 0.525974025974026, + "grad_norm": 0.55859375, + "learning_rate": 1.2055289515698008e-05, + "loss": 0.2988, + "step": 162 + }, + { + "epoch": 0.5292207792207793, + "grad_norm": 0.5703125, + "learning_rate": 1.1935972536625302e-05, + "loss": 0.2871, + "step": 163 + }, + { + "epoch": 0.5324675324675324, + "grad_norm": 0.578125, + "learning_rate": 1.1816368509794365e-05, + "loss": 0.2985, + "step": 164 + }, + { + "epoch": 0.5357142857142857, + "grad_norm": 0.609375, + "learning_rate": 1.1696495168962848e-05, + "loss": 0.3066, + "step": 165 + }, + { + "epoch": 0.538961038961039, + "grad_norm": 0.57421875, + "learning_rate": 1.1576370287819737e-05, + "loss": 0.296, + "step": 166 + }, + { + "epoch": 0.5422077922077922, + "grad_norm": 0.59375, + "learning_rate": 1.1456011677350052e-05, + "loss": 0.2997, + "step": 167 + }, + { + "epoch": 0.5454545454545454, + "grad_norm": 0.58984375, + "learning_rate": 1.133543718319398e-05, + "loss": 0.3011, + "step": 168 + }, + { + "epoch": 0.5487012987012987, + "grad_norm": 0.5703125, + "learning_rate": 1.1214664683000927e-05, + "loss": 0.2898, + "step": 169 + }, + { + "epoch": 0.551948051948052, + "grad_norm": 0.58203125, + "learning_rate": 1.1093712083778748e-05, + "loss": 0.292, + "step": 170 + }, + { + "epoch": 0.551948051948052, + "eval_loss": 0.29717138409614563, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9869, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 170 + }, + { + "epoch": 0.5551948051948052, + "grad_norm": 0.578125, + "learning_rate": 1.0972597319238692e-05, + "loss": 0.2995, + "step": 171 + }, + { + "epoch": 0.5584415584415584, + "grad_norm": 0.58984375, + "learning_rate": 1.0851338347136358e-05, + "loss": 0.3015, + "step": 172 + }, + { + "epoch": 0.5616883116883117, + "grad_norm": 0.5625, + "learning_rate": 1.0729953146609076e-05, + "loss": 0.2953, + "step": 173 + }, + { + "epoch": 0.564935064935065, + "grad_norm": 0.55859375, + "learning_rate": 1.060845971551014e-05, + "loss": 0.3011, + "step": 174 + }, + { + "epoch": 0.5681818181818182, + "grad_norm": 0.58984375, + "learning_rate": 1.0486876067740253e-05, + "loss": 0.3016, + "step": 175 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.5859375, + "learning_rate": 1.0365220230576592e-05, + "loss": 0.2953, + "step": 176 + }, + { + "epoch": 0.5746753246753247, + "grad_norm": 0.5625, + "learning_rate": 1.0243510241999898e-05, + "loss": 0.2948, + "step": 177 + }, + { + "epoch": 0.577922077922078, + "grad_norm": 0.5703125, + "learning_rate": 1.0121764148019977e-05, + "loss": 0.2958, + "step": 178 + }, + { + "epoch": 0.5811688311688312, + "grad_norm": 0.5546875, + "learning_rate": 1e-05, + "loss": 0.2829, + "step": 179 + }, + { + "epoch": 0.5844155844155844, + "grad_norm": 0.58203125, + "learning_rate": 9.878235851980027e-06, + "loss": 0.2917, + "step": 180 + }, + { + "epoch": 0.5844155844155844, + "eval_loss": 0.29469791054725647, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9839, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 180 + }, + { + "epoch": 0.5876623376623377, + "grad_norm": 0.59375, + "learning_rate": 9.756489758000105e-06, + "loss": 0.2994, + "step": 181 + }, + { + "epoch": 0.5909090909090909, + "grad_norm": 0.57421875, + "learning_rate": 9.634779769423412e-06, + "loss": 0.3054, + "step": 182 + }, + { + "epoch": 0.5941558441558441, + "grad_norm": 0.59375, + "learning_rate": 9.51312393225975e-06, + "loss": 0.2925, + "step": 183 + }, + { + "epoch": 0.5974025974025974, + "grad_norm": 0.5703125, + "learning_rate": 9.391540284489862e-06, + "loss": 0.2816, + "step": 184 + }, + { + "epoch": 0.6006493506493507, + "grad_norm": 0.5390625, + "learning_rate": 9.270046853390924e-06, + "loss": 0.2856, + "step": 185 + }, + { + "epoch": 0.6038961038961039, + "grad_norm": 0.5703125, + "learning_rate": 9.148661652863644e-06, + "loss": 0.2936, + "step": 186 + }, + { + "epoch": 0.6071428571428571, + "grad_norm": 0.55078125, + "learning_rate": 9.02740268076131e-06, + "loss": 0.2938, + "step": 187 + }, + { + "epoch": 0.6103896103896104, + "grad_norm": 0.5859375, + "learning_rate": 8.906287916221259e-06, + "loss": 0.3017, + "step": 188 + }, + { + "epoch": 0.6136363636363636, + "grad_norm": 0.578125, + "learning_rate": 8.785335316999078e-06, + "loss": 0.2957, + "step": 189 + }, + { + "epoch": 0.6168831168831169, + "grad_norm": 0.58203125, + "learning_rate": 8.664562816806022e-06, + "loss": 0.2961, + "step": 190 + }, + { + "epoch": 0.6168831168831169, + "eval_loss": 0.2927069365978241, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9405, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 190 + }, + { + "epoch": 0.6201298701298701, + "grad_norm": 0.58203125, + "learning_rate": 8.543988322649954e-06, + "loss": 0.2915, + "step": 191 + }, + { + "epoch": 0.6233766233766234, + "grad_norm": 0.57421875, + "learning_rate": 8.423629712180265e-06, + "loss": 0.2875, + "step": 192 + }, + { + "epoch": 0.6266233766233766, + "grad_norm": 0.5703125, + "learning_rate": 8.303504831037154e-06, + "loss": 0.2979, + "step": 193 + }, + { + "epoch": 0.6298701298701299, + "grad_norm": 0.5703125, + "learning_rate": 8.183631490205636e-06, + "loss": 0.2891, + "step": 194 + }, + { + "epoch": 0.6331168831168831, + "grad_norm": 0.5703125, + "learning_rate": 8.064027463374702e-06, + "loss": 0.2796, + "step": 195 + }, + { + "epoch": 0.6363636363636364, + "grad_norm": 0.57421875, + "learning_rate": 7.944710484301995e-06, + "loss": 0.285, + "step": 196 + }, + { + "epoch": 0.6396103896103896, + "grad_norm": 0.58203125, + "learning_rate": 7.825698244184432e-06, + "loss": 0.295, + "step": 197 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.57421875, + "learning_rate": 7.707008389035102e-06, + "loss": 0.2962, + "step": 198 + }, + { + "epoch": 0.6461038961038961, + "grad_norm": 0.57421875, + "learning_rate": 7.588658517066893e-06, + "loss": 0.2912, + "step": 199 + }, + { + "epoch": 0.6493506493506493, + "grad_norm": 0.57421875, + "learning_rate": 7.470666176083193e-06, + "loss": 0.2917, + "step": 200 + }, + { + "epoch": 0.6493506493506493, + "eval_loss": 0.2912693917751312, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9875, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 200 + } + ], + "logging_steps": 1, + "max_steps": 308, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "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": 1.1804225839300608e+18, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4684d3c90558d6bfde405c82b58596bc6231bfee --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09f69be12f7ef607f0a1508435a517f5277e3160e5d6a59346e619fcbaa3592 +size 5176 diff --git a/checkpoint-300/config.json b/checkpoint-300/config.json new file mode 100644 index 0000000000000000000000000000000000000000..de55730a672c2805e1108109d81a111b0cdb48b1 --- /dev/null +++ b/checkpoint-300/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a +size 915 diff --git a/checkpoint-300/generation_config.json b/checkpoint-300/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1007819213eaa3e36dd0c6354016734419f4a863 --- /dev/null +++ b/checkpoint-300/generation_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169 +size 184 diff --git a/checkpoint-300/model-00001-of-00004.safetensors b/checkpoint-300/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16a7cb28d9d5a8bc030ff58aa7bb2aec9c884506 --- /dev/null +++ b/checkpoint-300/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a3907a94d16ee63bb35418803792e2e7faf7479e9a0ba6c5b6faf863b4007d +size 4976698672 diff --git a/checkpoint-300/model-00002-of-00004.safetensors b/checkpoint-300/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea6d56cc2a5e3faa773bd777c6c8d20e58191164 --- /dev/null +++ b/checkpoint-300/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed5d4c274155ab7efb36612cbbb7e548c1b6b6fdb0e8ef136061e0c5b26b129 +size 4999802720 diff --git a/checkpoint-300/model-00003-of-00004.safetensors b/checkpoint-300/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0ee4f7a839f73a703690a98c80e9ff4f588dd775 --- /dev/null +++ b/checkpoint-300/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06c1356e06091e7d05ca40b62cd7a438c1abb71c6e182bd479804b9bf04e4e2 +size 4915916176 diff --git a/checkpoint-300/model-00004-of-00004.safetensors b/checkpoint-300/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c24ce7664aca02faaeb680746c2c99eec37a0249 --- /dev/null +++ b/checkpoint-300/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeb6b9ac5806653b828e732fba12471ef3f300d4d9daa99da11f1cf958f76402 +size 1168138808 diff --git a/checkpoint-300/model.safetensors.index.json b/checkpoint-300/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..a054aad8cf0cb5671e2e10b3bf817725a4bec031 --- /dev/null +++ b/checkpoint-300/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b +size 23950 diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e5684dac752410d520d02408132a8c1a96f699d --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6d30131aec5e4206a28344f043ab4470213fc7de969421738254b908eb6f93 +size 32121299754 diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..02e6a75cccce6d8b138f83bf61f04a2d82786ce4 --- /dev/null +++ b/checkpoint-300/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374644995be79c967030295cf4e5929f6a33d3b1197b8855bc39718b44686552 +size 14244 diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6726f19244a9d9c1cc38695d2f8e7194d58f3aa2 --- /dev/null +++ b/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:892afc48e852cff639a2b1d3faa9e143f11c0af53826ffadf88b7d4e636251cb +size 1064 diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92d7fab6729d723f45689803b99006fec945cc47 --- /dev/null +++ b/checkpoint-300/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1835caa5b4d70acaa210fa222b0036f1882f9525c4660fd4810fb3e1e40ff8 +size 325 diff --git a/checkpoint-300/tokenizer.json b/checkpoint-300/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..66cd9d7e0daec95eb10d16a63c615637dbbb7304 --- /dev/null +++ b/checkpoint-300/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4 +size 9085657 diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..08ebc9598183a9a76c44ef06813aca75f51de4a5 --- /dev/null +++ b/checkpoint-300/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d0de6d831b5940c3f2eae4e495b9f77612cbb05b5804846733ab617f0dfe9b +size 55380 diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c54de5afde22ae57b327ae39425beaca4aaffb17 --- /dev/null +++ b/checkpoint-300/trainer_state.json @@ -0,0 +1,2403 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.974025974025974, + "eval_steps": 10, + "global_step": 300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.003246753246753247, + "grad_norm": 16.375, + "learning_rate": 4.0000000000000003e-07, + "loss": 1.4017, + "step": 1 + }, + { + "epoch": 0.006493506493506494, + "grad_norm": 16.25, + "learning_rate": 8.000000000000001e-07, + "loss": 1.4229, + "step": 2 + }, + { + "epoch": 0.00974025974025974, + "grad_norm": 16.75, + "learning_rate": 1.2000000000000002e-06, + "loss": 1.4112, + "step": 3 + }, + { + "epoch": 0.012987012987012988, + "grad_norm": 16.5, + "learning_rate": 1.6000000000000001e-06, + "loss": 1.3959, + "step": 4 + }, + { + "epoch": 0.016233766233766232, + "grad_norm": 16.125, + "learning_rate": 2.0000000000000003e-06, + "loss": 1.3789, + "step": 5 + }, + { + "epoch": 0.01948051948051948, + "grad_norm": 14.4375, + "learning_rate": 2.4000000000000003e-06, + "loss": 1.3618, + "step": 6 + }, + { + "epoch": 0.022727272727272728, + "grad_norm": 10.1875, + "learning_rate": 2.8000000000000003e-06, + "loss": 1.3214, + "step": 7 + }, + { + "epoch": 0.025974025974025976, + "grad_norm": 7.4375, + "learning_rate": 3.2000000000000003e-06, + "loss": 1.2885, + "step": 8 + }, + { + "epoch": 0.02922077922077922, + "grad_norm": 6.28125, + "learning_rate": 3.6000000000000003e-06, + "loss": 1.2436, + "step": 9 + }, + { + "epoch": 0.032467532467532464, + "grad_norm": 5.75, + "learning_rate": 4.000000000000001e-06, + "loss": 1.2269, + "step": 10 + }, + { + "epoch": 0.032467532467532464, + "eval_loss": 1.1976113319396973, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0273, + "eval_samples_per_second": 11.878, + "eval_steps_per_second": 1.485, + "step": 10 + }, + { + "epoch": 0.03571428571428571, + "grad_norm": 5.375, + "learning_rate": 4.4e-06, + "loss": 1.1925, + "step": 11 + }, + { + "epoch": 0.03896103896103896, + "grad_norm": 5.125, + "learning_rate": 4.800000000000001e-06, + "loss": 1.1307, + "step": 12 + }, + { + "epoch": 0.04220779220779221, + "grad_norm": 5.125, + "learning_rate": 5.2e-06, + "loss": 1.0778, + "step": 13 + }, + { + "epoch": 0.045454545454545456, + "grad_norm": 5.0625, + "learning_rate": 5.600000000000001e-06, + "loss": 1.0067, + "step": 14 + }, + { + "epoch": 0.048701298701298704, + "grad_norm": 5.75, + "learning_rate": 6e-06, + "loss": 0.9668, + "step": 15 + }, + { + "epoch": 0.05194805194805195, + "grad_norm": 5.15625, + "learning_rate": 6.4000000000000006e-06, + "loss": 0.875, + "step": 16 + }, + { + "epoch": 0.05519480519480519, + "grad_norm": 4.875, + "learning_rate": 6.800000000000001e-06, + "loss": 0.8297, + "step": 17 + }, + { + "epoch": 0.05844155844155844, + "grad_norm": 4.5625, + "learning_rate": 7.2000000000000005e-06, + "loss": 0.7703, + "step": 18 + }, + { + "epoch": 0.06168831168831169, + "grad_norm": 3.90625, + "learning_rate": 7.600000000000001e-06, + "loss": 0.7327, + "step": 19 + }, + { + "epoch": 0.06493506493506493, + "grad_norm": 2.78125, + "learning_rate": 8.000000000000001e-06, + "loss": 0.6672, + "step": 20 + }, + { + "epoch": 0.06493506493506493, + "eval_loss": 0.6521233320236206, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.999, + "eval_samples_per_second": 11.88, + "eval_steps_per_second": 1.486, + "step": 20 + }, + { + "epoch": 0.06818181818181818, + "grad_norm": 2.140625, + "learning_rate": 8.400000000000001e-06, + "loss": 0.6507, + "step": 21 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.828125, + "learning_rate": 8.8e-06, + "loss": 0.6215, + "step": 22 + }, + { + "epoch": 0.07467532467532467, + "grad_norm": 1.5546875, + "learning_rate": 9.200000000000002e-06, + "loss": 0.5992, + "step": 23 + }, + { + "epoch": 0.07792207792207792, + "grad_norm": 1.4453125, + "learning_rate": 9.600000000000001e-06, + "loss": 0.5748, + "step": 24 + }, + { + "epoch": 0.08116883116883117, + "grad_norm": 1.328125, + "learning_rate": 1e-05, + "loss": 0.5572, + "step": 25 + }, + { + "epoch": 0.08441558441558442, + "grad_norm": 1.4765625, + "learning_rate": 1.04e-05, + "loss": 0.542, + "step": 26 + }, + { + "epoch": 0.08766233766233766, + "grad_norm": 1.1171875, + "learning_rate": 1.0800000000000002e-05, + "loss": 0.5317, + "step": 27 + }, + { + "epoch": 0.09090909090909091, + "grad_norm": 0.90625, + "learning_rate": 1.1200000000000001e-05, + "loss": 0.5173, + "step": 28 + }, + { + "epoch": 0.09415584415584416, + "grad_norm": 0.83984375, + "learning_rate": 1.16e-05, + "loss": 0.4892, + "step": 29 + }, + { + "epoch": 0.09740259740259741, + "grad_norm": 0.828125, + "learning_rate": 1.2e-05, + "loss": 0.491, + "step": 30 + }, + { + "epoch": 0.09740259740259741, + "eval_loss": 0.48583006858825684, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9705, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 30 + }, + { + "epoch": 0.10064935064935066, + "grad_norm": 0.8359375, + "learning_rate": 1.2400000000000002e-05, + "loss": 0.4852, + "step": 31 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 1.0078125, + "learning_rate": 1.2800000000000001e-05, + "loss": 0.4749, + "step": 32 + }, + { + "epoch": 0.10714285714285714, + "grad_norm": 0.99609375, + "learning_rate": 1.3200000000000002e-05, + "loss": 0.467, + "step": 33 + }, + { + "epoch": 0.11038961038961038, + "grad_norm": 0.734375, + "learning_rate": 1.3600000000000002e-05, + "loss": 0.4545, + "step": 34 + }, + { + "epoch": 0.11363636363636363, + "grad_norm": 0.69140625, + "learning_rate": 1.4e-05, + "loss": 0.4609, + "step": 35 + }, + { + "epoch": 0.11688311688311688, + "grad_norm": 0.69921875, + "learning_rate": 1.4400000000000001e-05, + "loss": 0.4497, + "step": 36 + }, + { + "epoch": 0.12012987012987013, + "grad_norm": 0.703125, + "learning_rate": 1.48e-05, + "loss": 0.4607, + "step": 37 + }, + { + "epoch": 0.12337662337662338, + "grad_norm": 0.6328125, + "learning_rate": 1.5200000000000002e-05, + "loss": 0.443, + "step": 38 + }, + { + "epoch": 0.1266233766233766, + "grad_norm": 0.65234375, + "learning_rate": 1.5600000000000003e-05, + "loss": 0.4428, + "step": 39 + }, + { + "epoch": 0.12987012987012986, + "grad_norm": 0.640625, + "learning_rate": 1.6000000000000003e-05, + "loss": 0.435, + "step": 40 + }, + { + "epoch": 0.12987012987012986, + "eval_loss": 0.4367639422416687, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0177, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 40 + }, + { + "epoch": 0.1331168831168831, + "grad_norm": 0.671875, + "learning_rate": 1.64e-05, + "loss": 0.438, + "step": 41 + }, + { + "epoch": 0.13636363636363635, + "grad_norm": 0.6484375, + "learning_rate": 1.6800000000000002e-05, + "loss": 0.4392, + "step": 42 + }, + { + "epoch": 0.1396103896103896, + "grad_norm": 0.65234375, + "learning_rate": 1.72e-05, + "loss": 0.435, + "step": 43 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.62109375, + "learning_rate": 1.76e-05, + "loss": 0.4356, + "step": 44 + }, + { + "epoch": 0.1461038961038961, + "grad_norm": 0.6171875, + "learning_rate": 1.8e-05, + "loss": 0.4172, + "step": 45 + }, + { + "epoch": 0.14935064935064934, + "grad_norm": 0.6015625, + "learning_rate": 1.8400000000000003e-05, + "loss": 0.4162, + "step": 46 + }, + { + "epoch": 0.1525974025974026, + "grad_norm": 0.609375, + "learning_rate": 1.88e-05, + "loss": 0.418, + "step": 47 + }, + { + "epoch": 0.15584415584415584, + "grad_norm": 0.6328125, + "learning_rate": 1.9200000000000003e-05, + "loss": 0.4177, + "step": 48 + }, + { + "epoch": 0.1590909090909091, + "grad_norm": 0.6171875, + "learning_rate": 1.9600000000000002e-05, + "loss": 0.4064, + "step": 49 + }, + { + "epoch": 0.16233766233766234, + "grad_norm": 0.62890625, + "learning_rate": 2e-05, + "loss": 0.4078, + "step": 50 + }, + { + "epoch": 0.16233766233766234, + "eval_loss": 0.4077843129634857, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.8482, + "eval_samples_per_second": 11.89, + "eval_steps_per_second": 1.487, + "step": 50 + }, + { + "epoch": 0.16558441558441558, + "grad_norm": 0.61328125, + "learning_rate": 1.9999258647132645e-05, + "loss": 0.4057, + "step": 51 + }, + { + "epoch": 0.16883116883116883, + "grad_norm": 0.62890625, + "learning_rate": 1.9997034698451396e-05, + "loss": 0.4172, + "step": 52 + }, + { + "epoch": 0.17207792207792208, + "grad_norm": 0.61328125, + "learning_rate": 1.9993328483702393e-05, + "loss": 0.4082, + "step": 53 + }, + { + "epoch": 0.17532467532467533, + "grad_norm": 0.59375, + "learning_rate": 1.998814055240823e-05, + "loss": 0.3973, + "step": 54 + }, + { + "epoch": 0.17857142857142858, + "grad_norm": 0.59375, + "learning_rate": 1.998147167378645e-05, + "loss": 0.3969, + "step": 55 + }, + { + "epoch": 0.18181818181818182, + "grad_norm": 0.609375, + "learning_rate": 1.9973322836635517e-05, + "loss": 0.4032, + "step": 56 + }, + { + "epoch": 0.18506493506493507, + "grad_norm": 0.5859375, + "learning_rate": 1.9963695249188185e-05, + "loss": 0.3956, + "step": 57 + }, + { + "epoch": 0.18831168831168832, + "grad_norm": 0.57421875, + "learning_rate": 1.995259033893236e-05, + "loss": 0.3952, + "step": 58 + }, + { + "epoch": 0.19155844155844157, + "grad_norm": 0.59765625, + "learning_rate": 1.9940009752399462e-05, + "loss": 0.3905, + "step": 59 + }, + { + "epoch": 0.19480519480519481, + "grad_norm": 0.60546875, + "learning_rate": 1.9925955354920265e-05, + "loss": 0.3822, + "step": 60 + }, + { + "epoch": 0.19480519480519481, + "eval_loss": 0.38575297594070435, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9122, + "eval_samples_per_second": 11.886, + "eval_steps_per_second": 1.486, + "step": 60 + }, + { + "epoch": 0.19805194805194806, + "grad_norm": 0.5859375, + "learning_rate": 1.9910429230348348e-05, + "loss": 0.3976, + "step": 61 + }, + { + "epoch": 0.2012987012987013, + "grad_norm": 0.578125, + "learning_rate": 1.9893433680751105e-05, + "loss": 0.3714, + "step": 62 + }, + { + "epoch": 0.20454545454545456, + "grad_norm": 0.5859375, + "learning_rate": 1.9874971226068417e-05, + "loss": 0.3739, + "step": 63 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 0.5859375, + "learning_rate": 1.985504460373903e-05, + "loss": 0.3907, + "step": 64 + }, + { + "epoch": 0.21103896103896103, + "grad_norm": 0.609375, + "learning_rate": 1.983365676829466e-05, + "loss": 0.3803, + "step": 65 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.59765625, + "learning_rate": 1.9810810890921943e-05, + "loss": 0.3902, + "step": 66 + }, + { + "epoch": 0.21753246753246752, + "grad_norm": 0.578125, + "learning_rate": 1.9786510358992213e-05, + "loss": 0.3744, + "step": 67 + }, + { + "epoch": 0.22077922077922077, + "grad_norm": 0.56640625, + "learning_rate": 1.9760758775559275e-05, + "loss": 0.3668, + "step": 68 + }, + { + "epoch": 0.22402597402597402, + "grad_norm": 0.625, + "learning_rate": 1.9733559958825167e-05, + "loss": 0.3755, + "step": 69 + }, + { + "epoch": 0.22727272727272727, + "grad_norm": 0.60546875, + "learning_rate": 1.9704917941574053e-05, + "loss": 0.3733, + "step": 70 + }, + { + "epoch": 0.22727272727272727, + "eval_loss": 0.3694484233856201, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9363, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 70 + }, + { + "epoch": 0.2305194805194805, + "grad_norm": 0.6015625, + "learning_rate": 1.9674836970574253e-05, + "loss": 0.3676, + "step": 71 + }, + { + "epoch": 0.23376623376623376, + "grad_norm": 0.60546875, + "learning_rate": 1.9643321505948588e-05, + "loss": 0.3721, + "step": 72 + }, + { + "epoch": 0.237012987012987, + "grad_norm": 0.60546875, + "learning_rate": 1.9610376220513067e-05, + "loss": 0.3558, + "step": 73 + }, + { + "epoch": 0.24025974025974026, + "grad_norm": 0.625, + "learning_rate": 1.957600599908406e-05, + "loss": 0.357, + "step": 74 + }, + { + "epoch": 0.2435064935064935, + "grad_norm": 0.66015625, + "learning_rate": 1.954021593775401e-05, + "loss": 0.3608, + "step": 75 + }, + { + "epoch": 0.24675324675324675, + "grad_norm": 0.59375, + "learning_rate": 1.9503011343135828e-05, + "loss": 0.3513, + "step": 76 + }, + { + "epoch": 0.25, + "grad_norm": 0.609375, + "learning_rate": 1.9464397731576093e-05, + "loss": 0.3693, + "step": 77 + }, + { + "epoch": 0.2532467532467532, + "grad_norm": 0.59375, + "learning_rate": 1.9424380828337146e-05, + "loss": 0.3605, + "step": 78 + }, + { + "epoch": 0.2564935064935065, + "grad_norm": 0.6171875, + "learning_rate": 1.938296656674817e-05, + "loss": 0.3553, + "step": 79 + }, + { + "epoch": 0.2597402597402597, + "grad_norm": 0.671875, + "learning_rate": 1.9340161087325483e-05, + "loss": 0.3721, + "step": 80 + }, + { + "epoch": 0.2597402597402597, + "eval_loss": 0.3553767800331116, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0277, + "eval_samples_per_second": 11.878, + "eval_steps_per_second": 1.485, + "step": 80 + }, + { + "epoch": 0.262987012987013, + "grad_norm": 0.609375, + "learning_rate": 1.9295970736862063e-05, + "loss": 0.3597, + "step": 81 + }, + { + "epoch": 0.2662337662337662, + "grad_norm": 0.65625, + "learning_rate": 1.9250402067486523e-05, + "loss": 0.3527, + "step": 82 + }, + { + "epoch": 0.2694805194805195, + "grad_norm": 0.61328125, + "learning_rate": 1.9203461835691596e-05, + "loss": 0.3528, + "step": 83 + }, + { + "epoch": 0.2727272727272727, + "grad_norm": 0.6640625, + "learning_rate": 1.9155157001332374e-05, + "loss": 0.356, + "step": 84 + }, + { + "epoch": 0.275974025974026, + "grad_norm": 0.6171875, + "learning_rate": 1.9105494726594344e-05, + "loss": 0.3556, + "step": 85 + }, + { + "epoch": 0.2792207792207792, + "grad_norm": 0.6171875, + "learning_rate": 1.905448237493147e-05, + "loss": 0.3473, + "step": 86 + }, + { + "epoch": 0.2824675324675325, + "grad_norm": 0.5859375, + "learning_rate": 1.9002127509974376e-05, + "loss": 0.3441, + "step": 87 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.6171875, + "learning_rate": 1.894843789440892e-05, + "loss": 0.3492, + "step": 88 + }, + { + "epoch": 0.288961038961039, + "grad_norm": 0.6328125, + "learning_rate": 1.889342148882519e-05, + "loss": 0.3338, + "step": 89 + }, + { + "epoch": 0.2922077922077922, + "grad_norm": 0.67578125, + "learning_rate": 1.8837086450537195e-05, + "loss": 0.3347, + "step": 90 + }, + { + "epoch": 0.2922077922077922, + "eval_loss": 0.34332525730133057, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9257, + "eval_samples_per_second": 11.885, + "eval_steps_per_second": 1.486, + "step": 90 + }, + { + "epoch": 0.29545454545454547, + "grad_norm": 0.6328125, + "learning_rate": 1.877944113237336e-05, + "loss": 0.3438, + "step": 91 + }, + { + "epoch": 0.2987012987012987, + "grad_norm": 0.6328125, + "learning_rate": 1.872049408143808e-05, + "loss": 0.3505, + "step": 92 + }, + { + "epoch": 0.30194805194805197, + "grad_norm": 0.6328125, + "learning_rate": 1.866025403784439e-05, + "loss": 0.3362, + "step": 93 + }, + { + "epoch": 0.3051948051948052, + "grad_norm": 0.640625, + "learning_rate": 1.8598729933418102e-05, + "loss": 0.337, + "step": 94 + }, + { + "epoch": 0.30844155844155846, + "grad_norm": 0.64453125, + "learning_rate": 1.8535930890373467e-05, + "loss": 0.3324, + "step": 95 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 0.6875, + "learning_rate": 1.8471866219960604e-05, + "loss": 0.3461, + "step": 96 + }, + { + "epoch": 0.31493506493506496, + "grad_norm": 0.6328125, + "learning_rate": 1.840654542108494e-05, + "loss": 0.3318, + "step": 97 + }, + { + "epoch": 0.3181818181818182, + "grad_norm": 0.62109375, + "learning_rate": 1.833997817889878e-05, + "loss": 0.3335, + "step": 98 + }, + { + "epoch": 0.32142857142857145, + "grad_norm": 0.61328125, + "learning_rate": 1.82721743633653e-05, + "loss": 0.3291, + "step": 99 + }, + { + "epoch": 0.3246753246753247, + "grad_norm": 0.6171875, + "learning_rate": 1.820314402779511e-05, + "loss": 0.3324, + "step": 100 + }, + { + "epoch": 0.3246753246753247, + "eval_loss": 0.33332687616348267, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9506, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 100 + }, + { + "epoch": 0.32792207792207795, + "grad_norm": 0.6328125, + "learning_rate": 1.8132897407355657e-05, + "loss": 0.3288, + "step": 101 + }, + { + "epoch": 0.33116883116883117, + "grad_norm": 0.6484375, + "learning_rate": 1.806144491755363e-05, + "loss": 0.3384, + "step": 102 + }, + { + "epoch": 0.3344155844155844, + "grad_norm": 0.6328125, + "learning_rate": 1.798879715269067e-05, + "loss": 0.3329, + "step": 103 + }, + { + "epoch": 0.33766233766233766, + "grad_norm": 0.6171875, + "learning_rate": 1.7914964884292543e-05, + "loss": 0.3329, + "step": 104 + }, + { + "epoch": 0.3409090909090909, + "grad_norm": 0.671875, + "learning_rate": 1.7839959059512016e-05, + "loss": 0.3335, + "step": 105 + }, + { + "epoch": 0.34415584415584416, + "grad_norm": 0.609375, + "learning_rate": 1.7763790799505746e-05, + "loss": 0.3201, + "step": 106 + }, + { + "epoch": 0.3474025974025974, + "grad_norm": 0.6171875, + "learning_rate": 1.7686471397785322e-05, + "loss": 0.3327, + "step": 107 + }, + { + "epoch": 0.35064935064935066, + "grad_norm": 0.640625, + "learning_rate": 1.760801231854278e-05, + "loss": 0.3205, + "step": 108 + }, + { + "epoch": 0.3538961038961039, + "grad_norm": 0.6328125, + "learning_rate": 1.7528425194950794e-05, + "loss": 0.334, + "step": 109 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.6015625, + "learning_rate": 1.744772182743782e-05, + "loss": 0.3165, + "step": 110 + }, + { + "epoch": 0.35714285714285715, + "eval_loss": 0.32505103945732117, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0106, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 110 + }, + { + "epoch": 0.36038961038961037, + "grad_norm": 0.62890625, + "learning_rate": 1.736591418193844e-05, + "loss": 0.3236, + "step": 111 + }, + { + "epoch": 0.36363636363636365, + "grad_norm": 0.63671875, + "learning_rate": 1.728301438811916e-05, + "loss": 0.3192, + "step": 112 + }, + { + "epoch": 0.36688311688311687, + "grad_norm": 0.6484375, + "learning_rate": 1.7199034737579962e-05, + "loss": 0.327, + "step": 113 + }, + { + "epoch": 0.37012987012987014, + "grad_norm": 0.62109375, + "learning_rate": 1.711398768203178e-05, + "loss": 0.3169, + "step": 114 + }, + { + "epoch": 0.37337662337662336, + "grad_norm": 0.625, + "learning_rate": 1.7027885831450318e-05, + "loss": 0.3186, + "step": 115 + }, + { + "epoch": 0.37662337662337664, + "grad_norm": 0.60546875, + "learning_rate": 1.6940741952206342e-05, + "loss": 0.3136, + "step": 116 + }, + { + "epoch": 0.37987012987012986, + "grad_norm": 0.62109375, + "learning_rate": 1.6852568965172794e-05, + "loss": 0.3184, + "step": 117 + }, + { + "epoch": 0.38311688311688313, + "grad_norm": 0.60546875, + "learning_rate": 1.676337994380903e-05, + "loss": 0.3114, + "step": 118 + }, + { + "epoch": 0.38636363636363635, + "grad_norm": 0.6640625, + "learning_rate": 1.6673188112222394e-05, + "loss": 0.3329, + "step": 119 + }, + { + "epoch": 0.38961038961038963, + "grad_norm": 0.60546875, + "learning_rate": 1.658200684320748e-05, + "loss": 0.3105, + "step": 120 + }, + { + "epoch": 0.38961038961038963, + "eval_loss": 0.31796982884407043, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9896, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 120 + }, + { + "epoch": 0.39285714285714285, + "grad_norm": 0.58203125, + "learning_rate": 1.6489849656263336e-05, + "loss": 0.3084, + "step": 121 + }, + { + "epoch": 0.3961038961038961, + "grad_norm": 0.57421875, + "learning_rate": 1.6396730215588913e-05, + "loss": 0.3124, + "step": 122 + }, + { + "epoch": 0.39935064935064934, + "grad_norm": 0.609375, + "learning_rate": 1.630266232805709e-05, + "loss": 0.3167, + "step": 123 + }, + { + "epoch": 0.4025974025974026, + "grad_norm": 0.6171875, + "learning_rate": 1.6207659941167485e-05, + "loss": 0.3084, + "step": 124 + }, + { + "epoch": 0.40584415584415584, + "grad_norm": 0.62890625, + "learning_rate": 1.6111737140978495e-05, + "loss": 0.3143, + "step": 125 + }, + { + "epoch": 0.4090909090909091, + "grad_norm": 0.6171875, + "learning_rate": 1.6014908150018703e-05, + "loss": 0.3173, + "step": 126 + }, + { + "epoch": 0.41233766233766234, + "grad_norm": 0.609375, + "learning_rate": 1.591718732517814e-05, + "loss": 0.3199, + "step": 127 + }, + { + "epoch": 0.4155844155844156, + "grad_norm": 0.609375, + "learning_rate": 1.581858915557953e-05, + "loss": 0.312, + "step": 128 + }, + { + "epoch": 0.41883116883116883, + "grad_norm": 0.61328125, + "learning_rate": 1.571912826043003e-05, + "loss": 0.3217, + "step": 129 + }, + { + "epoch": 0.42207792207792205, + "grad_norm": 0.59765625, + "learning_rate": 1.5618819386853607e-05, + "loss": 0.3123, + "step": 130 + }, + { + "epoch": 0.42207792207792205, + "eval_loss": 0.3119741976261139, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9669, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 130 + }, + { + "epoch": 0.4253246753246753, + "grad_norm": 0.61328125, + "learning_rate": 1.551767740770446e-05, + "loss": 0.3088, + "step": 131 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.578125, + "learning_rate": 1.541571731936185e-05, + "loss": 0.3084, + "step": 132 + }, + { + "epoch": 0.4318181818181818, + "grad_norm": 0.6328125, + "learning_rate": 1.5312954239506536e-05, + "loss": 0.3179, + "step": 133 + }, + { + "epoch": 0.43506493506493504, + "grad_norm": 0.60546875, + "learning_rate": 1.5209403404879305e-05, + "loss": 0.3145, + "step": 134 + }, + { + "epoch": 0.4383116883116883, + "grad_norm": 0.59765625, + "learning_rate": 1.5105080169021792e-05, + "loss": 0.3045, + "step": 135 + }, + { + "epoch": 0.44155844155844154, + "grad_norm": 0.5859375, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.314, + "step": 136 + }, + { + "epoch": 0.4448051948051948, + "grad_norm": 0.6484375, + "learning_rate": 1.4894178478110856e-05, + "loss": 0.2985, + "step": 137 + }, + { + "epoch": 0.44805194805194803, + "grad_norm": 0.58984375, + "learning_rate": 1.4787631293572094e-05, + "loss": 0.3114, + "step": 138 + }, + { + "epoch": 0.4512987012987013, + "grad_norm": 0.60546875, + "learning_rate": 1.4680374244195861e-05, + "loss": 0.3129, + "step": 139 + }, + { + "epoch": 0.45454545454545453, + "grad_norm": 0.58984375, + "learning_rate": 1.4572423233046386e-05, + "loss": 0.3007, + "step": 140 + }, + { + "epoch": 0.45454545454545453, + "eval_loss": 0.30710509419441223, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9622, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 140 + }, + { + "epoch": 0.4577922077922078, + "grad_norm": 0.58203125, + "learning_rate": 1.4463794266081994e-05, + "loss": 0.2981, + "step": 141 + }, + { + "epoch": 0.461038961038961, + "grad_norm": 0.5703125, + "learning_rate": 1.4354503449781914e-05, + "loss": 0.2974, + "step": 142 + }, + { + "epoch": 0.4642857142857143, + "grad_norm": 0.5859375, + "learning_rate": 1.4244566988758152e-05, + "loss": 0.3064, + "step": 143 + }, + { + "epoch": 0.4675324675324675, + "grad_norm": 0.56640625, + "learning_rate": 1.4134001183352833e-05, + "loss": 0.298, + "step": 144 + }, + { + "epoch": 0.4707792207792208, + "grad_norm": 0.5703125, + "learning_rate": 1.4022822427221325e-05, + "loss": 0.3037, + "step": 145 + }, + { + "epoch": 0.474025974025974, + "grad_norm": 0.58203125, + "learning_rate": 1.391104720490156e-05, + "loss": 0.3062, + "step": 146 + }, + { + "epoch": 0.4772727272727273, + "grad_norm": 0.609375, + "learning_rate": 1.3798692089369855e-05, + "loss": 0.3019, + "step": 147 + }, + { + "epoch": 0.4805194805194805, + "grad_norm": 0.61328125, + "learning_rate": 1.368577373958362e-05, + "loss": 0.3008, + "step": 148 + }, + { + "epoch": 0.4837662337662338, + "grad_norm": 0.56640625, + "learning_rate": 1.3572308898011328e-05, + "loss": 0.3055, + "step": 149 + }, + { + "epoch": 0.487012987012987, + "grad_norm": 0.5859375, + "learning_rate": 1.3458314388150115e-05, + "loss": 0.2942, + "step": 150 + }, + { + "epoch": 0.487012987012987, + "eval_loss": 0.30315953493118286, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9566, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 150 + }, + { + "epoch": 0.4902597402597403, + "grad_norm": 0.578125, + "learning_rate": 1.3343807112031329e-05, + "loss": 0.3097, + "step": 151 + }, + { + "epoch": 0.4935064935064935, + "grad_norm": 0.56640625, + "learning_rate": 1.3228804047714462e-05, + "loss": 0.3004, + "step": 152 + }, + { + "epoch": 0.4967532467532468, + "grad_norm": 0.58203125, + "learning_rate": 1.3113322246769817e-05, + "loss": 0.3046, + "step": 153 + }, + { + "epoch": 0.5, + "grad_norm": 0.57421875, + "learning_rate": 1.2997378831750242e-05, + "loss": 0.2966, + "step": 154 + }, + { + "epoch": 0.5032467532467533, + "grad_norm": 0.5703125, + "learning_rate": 1.2880990993652379e-05, + "loss": 0.2989, + "step": 155 + }, + { + "epoch": 0.5064935064935064, + "grad_norm": 0.609375, + "learning_rate": 1.2764175989367717e-05, + "loss": 0.3015, + "step": 156 + }, + { + "epoch": 0.5097402597402597, + "grad_norm": 0.5703125, + "learning_rate": 1.2646951139123935e-05, + "loss": 0.2976, + "step": 157 + }, + { + "epoch": 0.512987012987013, + "grad_norm": 0.59765625, + "learning_rate": 1.2529333823916807e-05, + "loss": 0.2919, + "step": 158 + }, + { + "epoch": 0.5162337662337663, + "grad_norm": 0.6328125, + "learning_rate": 1.241134148293311e-05, + "loss": 0.3041, + "step": 159 + }, + { + "epoch": 0.5194805194805194, + "grad_norm": 0.58984375, + "learning_rate": 1.2292991610964902e-05, + "loss": 0.3053, + "step": 160 + }, + { + "epoch": 0.5194805194805194, + "eval_loss": 0.3000594675540924, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9643, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 160 + }, + { + "epoch": 0.5227272727272727, + "grad_norm": 0.5859375, + "learning_rate": 1.2174301755815572e-05, + "loss": 0.3043, + "step": 161 + }, + { + "epoch": 0.525974025974026, + "grad_norm": 0.55859375, + "learning_rate": 1.2055289515698008e-05, + "loss": 0.2988, + "step": 162 + }, + { + "epoch": 0.5292207792207793, + "grad_norm": 0.5703125, + "learning_rate": 1.1935972536625302e-05, + "loss": 0.2871, + "step": 163 + }, + { + "epoch": 0.5324675324675324, + "grad_norm": 0.578125, + "learning_rate": 1.1816368509794365e-05, + "loss": 0.2985, + "step": 164 + }, + { + "epoch": 0.5357142857142857, + "grad_norm": 0.609375, + "learning_rate": 1.1696495168962848e-05, + "loss": 0.3066, + "step": 165 + }, + { + "epoch": 0.538961038961039, + "grad_norm": 0.57421875, + "learning_rate": 1.1576370287819737e-05, + "loss": 0.296, + "step": 166 + }, + { + "epoch": 0.5422077922077922, + "grad_norm": 0.59375, + "learning_rate": 1.1456011677350052e-05, + "loss": 0.2997, + "step": 167 + }, + { + "epoch": 0.5454545454545454, + "grad_norm": 0.58984375, + "learning_rate": 1.133543718319398e-05, + "loss": 0.3011, + "step": 168 + }, + { + "epoch": 0.5487012987012987, + "grad_norm": 0.5703125, + "learning_rate": 1.1214664683000927e-05, + "loss": 0.2898, + "step": 169 + }, + { + "epoch": 0.551948051948052, + "grad_norm": 0.58203125, + "learning_rate": 1.1093712083778748e-05, + "loss": 0.292, + "step": 170 + }, + { + "epoch": 0.551948051948052, + "eval_loss": 0.29717138409614563, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9869, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 170 + }, + { + "epoch": 0.5551948051948052, + "grad_norm": 0.578125, + "learning_rate": 1.0972597319238692e-05, + "loss": 0.2995, + "step": 171 + }, + { + "epoch": 0.5584415584415584, + "grad_norm": 0.58984375, + "learning_rate": 1.0851338347136358e-05, + "loss": 0.3015, + "step": 172 + }, + { + "epoch": 0.5616883116883117, + "grad_norm": 0.5625, + "learning_rate": 1.0729953146609076e-05, + "loss": 0.2953, + "step": 173 + }, + { + "epoch": 0.564935064935065, + "grad_norm": 0.55859375, + "learning_rate": 1.060845971551014e-05, + "loss": 0.3011, + "step": 174 + }, + { + "epoch": 0.5681818181818182, + "grad_norm": 0.58984375, + "learning_rate": 1.0486876067740253e-05, + "loss": 0.3016, + "step": 175 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.5859375, + "learning_rate": 1.0365220230576592e-05, + "loss": 0.2953, + "step": 176 + }, + { + "epoch": 0.5746753246753247, + "grad_norm": 0.5625, + "learning_rate": 1.0243510241999898e-05, + "loss": 0.2948, + "step": 177 + }, + { + "epoch": 0.577922077922078, + "grad_norm": 0.5703125, + "learning_rate": 1.0121764148019977e-05, + "loss": 0.2958, + "step": 178 + }, + { + "epoch": 0.5811688311688312, + "grad_norm": 0.5546875, + "learning_rate": 1e-05, + "loss": 0.2829, + "step": 179 + }, + { + "epoch": 0.5844155844155844, + "grad_norm": 0.58203125, + "learning_rate": 9.878235851980027e-06, + "loss": 0.2917, + "step": 180 + }, + { + "epoch": 0.5844155844155844, + "eval_loss": 0.29469791054725647, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9839, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 180 + }, + { + "epoch": 0.5876623376623377, + "grad_norm": 0.59375, + "learning_rate": 9.756489758000105e-06, + "loss": 0.2994, + "step": 181 + }, + { + "epoch": 0.5909090909090909, + "grad_norm": 0.57421875, + "learning_rate": 9.634779769423412e-06, + "loss": 0.3054, + "step": 182 + }, + { + "epoch": 0.5941558441558441, + "grad_norm": 0.59375, + "learning_rate": 9.51312393225975e-06, + "loss": 0.2925, + "step": 183 + }, + { + "epoch": 0.5974025974025974, + "grad_norm": 0.5703125, + "learning_rate": 9.391540284489862e-06, + "loss": 0.2816, + "step": 184 + }, + { + "epoch": 0.6006493506493507, + "grad_norm": 0.5390625, + "learning_rate": 9.270046853390924e-06, + "loss": 0.2856, + "step": 185 + }, + { + "epoch": 0.6038961038961039, + "grad_norm": 0.5703125, + "learning_rate": 9.148661652863644e-06, + "loss": 0.2936, + "step": 186 + }, + { + "epoch": 0.6071428571428571, + "grad_norm": 0.55078125, + "learning_rate": 9.02740268076131e-06, + "loss": 0.2938, + "step": 187 + }, + { + "epoch": 0.6103896103896104, + "grad_norm": 0.5859375, + "learning_rate": 8.906287916221259e-06, + "loss": 0.3017, + "step": 188 + }, + { + "epoch": 0.6136363636363636, + "grad_norm": 0.578125, + "learning_rate": 8.785335316999078e-06, + "loss": 0.2957, + "step": 189 + }, + { + "epoch": 0.6168831168831169, + "grad_norm": 0.58203125, + "learning_rate": 8.664562816806022e-06, + "loss": 0.2961, + "step": 190 + }, + { + "epoch": 0.6168831168831169, + "eval_loss": 0.2927069365978241, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9405, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 190 + }, + { + "epoch": 0.6201298701298701, + "grad_norm": 0.58203125, + "learning_rate": 8.543988322649954e-06, + "loss": 0.2915, + "step": 191 + }, + { + "epoch": 0.6233766233766234, + "grad_norm": 0.57421875, + "learning_rate": 8.423629712180265e-06, + "loss": 0.2875, + "step": 192 + }, + { + "epoch": 0.6266233766233766, + "grad_norm": 0.5703125, + "learning_rate": 8.303504831037154e-06, + "loss": 0.2979, + "step": 193 + }, + { + "epoch": 0.6298701298701299, + "grad_norm": 0.5703125, + "learning_rate": 8.183631490205636e-06, + "loss": 0.2891, + "step": 194 + }, + { + "epoch": 0.6331168831168831, + "grad_norm": 0.5703125, + "learning_rate": 8.064027463374702e-06, + "loss": 0.2796, + "step": 195 + }, + { + "epoch": 0.6363636363636364, + "grad_norm": 0.57421875, + "learning_rate": 7.944710484301995e-06, + "loss": 0.285, + "step": 196 + }, + { + "epoch": 0.6396103896103896, + "grad_norm": 0.58203125, + "learning_rate": 7.825698244184432e-06, + "loss": 0.295, + "step": 197 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.57421875, + "learning_rate": 7.707008389035102e-06, + "loss": 0.2962, + "step": 198 + }, + { + "epoch": 0.6461038961038961, + "grad_norm": 0.57421875, + "learning_rate": 7.588658517066893e-06, + "loss": 0.2912, + "step": 199 + }, + { + "epoch": 0.6493506493506493, + "grad_norm": 0.57421875, + "learning_rate": 7.470666176083193e-06, + "loss": 0.2917, + "step": 200 + }, + { + "epoch": 0.6493506493506493, + "eval_loss": 0.2912693917751312, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9875, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 200 + }, + { + "epoch": 0.6525974025974026, + "grad_norm": 0.6015625, + "learning_rate": 7.3530488608760645e-06, + "loss": 0.291, + "step": 201 + }, + { + "epoch": 0.6558441558441559, + "grad_norm": 0.5625, + "learning_rate": 7.235824010632284e-06, + "loss": 0.2862, + "step": 202 + }, + { + "epoch": 0.6590909090909091, + "grad_norm": 0.5546875, + "learning_rate": 7.119009006347625e-06, + "loss": 0.2936, + "step": 203 + }, + { + "epoch": 0.6623376623376623, + "grad_norm": 0.5546875, + "learning_rate": 7.002621168249759e-06, + "loss": 0.2934, + "step": 204 + }, + { + "epoch": 0.6655844155844156, + "grad_norm": 0.578125, + "learning_rate": 6.886677753230184e-06, + "loss": 0.2783, + "step": 205 + }, + { + "epoch": 0.6688311688311688, + "grad_norm": 0.546875, + "learning_rate": 6.771195952285541e-06, + "loss": 0.2844, + "step": 206 + }, + { + "epoch": 0.672077922077922, + "grad_norm": 0.5546875, + "learning_rate": 6.656192887968675e-06, + "loss": 0.2835, + "step": 207 + }, + { + "epoch": 0.6753246753246753, + "grad_norm": 0.56640625, + "learning_rate": 6.5416856118498874e-06, + "loss": 0.2887, + "step": 208 + }, + { + "epoch": 0.6785714285714286, + "grad_norm": 0.5625, + "learning_rate": 6.427691101988673e-06, + "loss": 0.2925, + "step": 209 + }, + { + "epoch": 0.6818181818181818, + "grad_norm": 0.58203125, + "learning_rate": 6.314226260416383e-06, + "loss": 0.29, + "step": 210 + }, + { + "epoch": 0.6818181818181818, + "eval_loss": 0.29015374183654785, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.8645, + "eval_samples_per_second": 11.889, + "eval_steps_per_second": 1.487, + "step": 210 + }, + { + "epoch": 0.685064935064935, + "grad_norm": 0.5625, + "learning_rate": 6.2013079106301454e-06, + "loss": 0.2858, + "step": 211 + }, + { + "epoch": 0.6883116883116883, + "grad_norm": 0.5703125, + "learning_rate": 6.088952795098442e-06, + "loss": 0.2828, + "step": 212 + }, + { + "epoch": 0.6915584415584416, + "grad_norm": 0.578125, + "learning_rate": 5.977177572778679e-06, + "loss": 0.2947, + "step": 213 + }, + { + "epoch": 0.6948051948051948, + "grad_norm": 0.578125, + "learning_rate": 5.8659988166471715e-06, + "loss": 0.2795, + "step": 214 + }, + { + "epoch": 0.698051948051948, + "grad_norm": 0.56640625, + "learning_rate": 5.755433011241851e-06, + "loss": 0.2899, + "step": 215 + }, + { + "epoch": 0.7012987012987013, + "grad_norm": 0.578125, + "learning_rate": 5.645496550218089e-06, + "loss": 0.2881, + "step": 216 + }, + { + "epoch": 0.7045454545454546, + "grad_norm": 0.56640625, + "learning_rate": 5.5362057339180075e-06, + "loss": 0.2937, + "step": 217 + }, + { + "epoch": 0.7077922077922078, + "grad_norm": 0.5625, + "learning_rate": 5.427576766953615e-06, + "loss": 0.2828, + "step": 218 + }, + { + "epoch": 0.711038961038961, + "grad_norm": 0.57421875, + "learning_rate": 5.3196257558041386e-06, + "loss": 0.2863, + "step": 219 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 0.5859375, + "learning_rate": 5.212368706427913e-06, + "loss": 0.2876, + "step": 220 + }, + { + "epoch": 0.7142857142857143, + "eval_loss": 0.2891963720321655, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9738, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 220 + }, + { + "epoch": 0.7175324675324676, + "grad_norm": 0.5859375, + "learning_rate": 5.105821521889147e-06, + "loss": 0.2955, + "step": 221 + }, + { + "epoch": 0.7207792207792207, + "grad_norm": 0.56640625, + "learning_rate": 5.000000000000003e-06, + "loss": 0.2873, + "step": 222 + }, + { + "epoch": 0.724025974025974, + "grad_norm": 0.5625, + "learning_rate": 4.894919830978212e-06, + "loss": 0.2813, + "step": 223 + }, + { + "epoch": 0.7272727272727273, + "grad_norm": 0.59375, + "learning_rate": 4.790596595120699e-06, + "loss": 0.2912, + "step": 224 + }, + { + "epoch": 0.7305194805194806, + "grad_norm": 0.5859375, + "learning_rate": 4.687045760493468e-06, + "loss": 0.2921, + "step": 225 + }, + { + "epoch": 0.7337662337662337, + "grad_norm": 0.55078125, + "learning_rate": 4.584282680638155e-06, + "loss": 0.288, + "step": 226 + }, + { + "epoch": 0.737012987012987, + "grad_norm": 0.5546875, + "learning_rate": 4.482322592295541e-06, + "loss": 0.2914, + "step": 227 + }, + { + "epoch": 0.7402597402597403, + "grad_norm": 0.56640625, + "learning_rate": 4.381180613146396e-06, + "loss": 0.2901, + "step": 228 + }, + { + "epoch": 0.7435064935064936, + "grad_norm": 0.56640625, + "learning_rate": 4.280871739569972e-06, + "loss": 0.2941, + "step": 229 + }, + { + "epoch": 0.7467532467532467, + "grad_norm": 0.54296875, + "learning_rate": 4.181410844420473e-06, + "loss": 0.2836, + "step": 230 + }, + { + "epoch": 0.7467532467532467, + "eval_loss": 0.2885654866695404, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9437, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 230 + }, + { + "epoch": 0.75, + "grad_norm": 0.58203125, + "learning_rate": 4.082812674821865e-06, + "loss": 0.2882, + "step": 231 + }, + { + "epoch": 0.7532467532467533, + "grad_norm": 0.56640625, + "learning_rate": 3.9850918499812976e-06, + "loss": 0.293, + "step": 232 + }, + { + "epoch": 0.7564935064935064, + "grad_norm": 0.56640625, + "learning_rate": 3.888262859021508e-06, + "loss": 0.2818, + "step": 233 + }, + { + "epoch": 0.7597402597402597, + "grad_norm": 0.5703125, + "learning_rate": 3.7923400588325156e-06, + "loss": 0.2836, + "step": 234 + }, + { + "epoch": 0.762987012987013, + "grad_norm": 0.6015625, + "learning_rate": 3.6973376719429134e-06, + "loss": 0.2833, + "step": 235 + }, + { + "epoch": 0.7662337662337663, + "grad_norm": 0.5625, + "learning_rate": 3.6032697844110896e-06, + "loss": 0.2956, + "step": 236 + }, + { + "epoch": 0.7694805194805194, + "grad_norm": 0.578125, + "learning_rate": 3.5101503437366678e-06, + "loss": 0.288, + "step": 237 + }, + { + "epoch": 0.7727272727272727, + "grad_norm": 0.578125, + "learning_rate": 3.4179931567925216e-06, + "loss": 0.2898, + "step": 238 + }, + { + "epoch": 0.775974025974026, + "grad_norm": 0.55859375, + "learning_rate": 3.326811887777607e-06, + "loss": 0.2809, + "step": 239 + }, + { + "epoch": 0.7792207792207793, + "grad_norm": 0.546875, + "learning_rate": 3.236620056190972e-06, + "loss": 0.285, + "step": 240 + }, + { + "epoch": 0.7792207792207793, + "eval_loss": 0.2881048321723938, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9387, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 240 + }, + { + "epoch": 0.7824675324675324, + "grad_norm": 0.56640625, + "learning_rate": 3.1474310348272084e-06, + "loss": 0.2888, + "step": 241 + }, + { + "epoch": 0.7857142857142857, + "grad_norm": 0.56640625, + "learning_rate": 3.0592580477936606e-06, + "loss": 0.2875, + "step": 242 + }, + { + "epoch": 0.788961038961039, + "grad_norm": 0.5625, + "learning_rate": 2.9721141685496825e-06, + "loss": 0.2828, + "step": 243 + }, + { + "epoch": 0.7922077922077922, + "grad_norm": 0.55859375, + "learning_rate": 2.8860123179682244e-06, + "loss": 0.2866, + "step": 244 + }, + { + "epoch": 0.7954545454545454, + "grad_norm": 0.5703125, + "learning_rate": 2.8009652624200436e-06, + "loss": 0.289, + "step": 245 + }, + { + "epoch": 0.7987012987012987, + "grad_norm": 0.5625, + "learning_rate": 2.7169856118808414e-06, + "loss": 0.2832, + "step": 246 + }, + { + "epoch": 0.801948051948052, + "grad_norm": 0.56640625, + "learning_rate": 2.634085818061565e-06, + "loss": 0.2913, + "step": 247 + }, + { + "epoch": 0.8051948051948052, + "grad_norm": 0.58203125, + "learning_rate": 2.5522781725621814e-06, + "loss": 0.2917, + "step": 248 + }, + { + "epoch": 0.8084415584415584, + "grad_norm": 0.56640625, + "learning_rate": 2.471574805049206e-06, + "loss": 0.2937, + "step": 249 + }, + { + "epoch": 0.8116883116883117, + "grad_norm": 0.5625, + "learning_rate": 2.3919876814572197e-06, + "loss": 0.2932, + "step": 250 + }, + { + "epoch": 0.8116883116883117, + "eval_loss": 0.28785035014152527, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.993, + "eval_samples_per_second": 11.88, + "eval_steps_per_second": 1.486, + "step": 250 + }, + { + "epoch": 0.814935064935065, + "grad_norm": 0.56640625, + "learning_rate": 2.3135286022146785e-06, + "loss": 0.2973, + "step": 251 + }, + { + "epoch": 0.8181818181818182, + "grad_norm": 0.5703125, + "learning_rate": 2.2362092004942583e-06, + "loss": 0.2862, + "step": 252 + }, + { + "epoch": 0.8214285714285714, + "grad_norm": 0.57421875, + "learning_rate": 2.1600409404879875e-06, + "loss": 0.279, + "step": 253 + }, + { + "epoch": 0.8246753246753247, + "grad_norm": 0.55859375, + "learning_rate": 2.08503511570746e-06, + "loss": 0.2844, + "step": 254 + }, + { + "epoch": 0.827922077922078, + "grad_norm": 0.5546875, + "learning_rate": 2.0112028473093294e-06, + "loss": 0.2792, + "step": 255 + }, + { + "epoch": 0.8311688311688312, + "grad_norm": 0.5703125, + "learning_rate": 1.9385550824463727e-06, + "loss": 0.2921, + "step": 256 + }, + { + "epoch": 0.8344155844155844, + "grad_norm": 0.5625, + "learning_rate": 1.8671025926443464e-06, + "loss": 0.2891, + "step": 257 + }, + { + "epoch": 0.8376623376623377, + "grad_norm": 0.5625, + "learning_rate": 1.7968559722048906e-06, + "loss": 0.2848, + "step": 258 + }, + { + "epoch": 0.8409090909090909, + "grad_norm": 0.55078125, + "learning_rate": 1.7278256366347034e-06, + "loss": 0.2921, + "step": 259 + }, + { + "epoch": 0.8441558441558441, + "grad_norm": 0.56640625, + "learning_rate": 1.660021821101222e-06, + "loss": 0.2907, + "step": 260 + }, + { + "epoch": 0.8441558441558441, + "eval_loss": 0.2877131402492523, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.008, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 260 + }, + { + "epoch": 0.8474025974025974, + "grad_norm": 0.5625, + "learning_rate": 1.5934545789150625e-06, + "loss": 0.2979, + "step": 261 + }, + { + "epoch": 0.8506493506493507, + "grad_norm": 0.5625, + "learning_rate": 1.528133780039397e-06, + "loss": 0.2847, + "step": 262 + }, + { + "epoch": 0.8538961038961039, + "grad_norm": 0.55078125, + "learning_rate": 1.4640691096265358e-06, + "loss": 0.2902, + "step": 263 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 0.5703125, + "learning_rate": 1.401270066581899e-06, + "loss": 0.2861, + "step": 264 + }, + { + "epoch": 0.8603896103896104, + "grad_norm": 0.5625, + "learning_rate": 1.339745962155613e-06, + "loss": 0.2823, + "step": 265 + }, + { + "epoch": 0.8636363636363636, + "grad_norm": 0.5703125, + "learning_rate": 1.279505918561923e-06, + "loss": 0.2855, + "step": 266 + }, + { + "epoch": 0.8668831168831169, + "grad_norm": 0.58203125, + "learning_rate": 1.220558867626639e-06, + "loss": 0.2853, + "step": 267 + }, + { + "epoch": 0.8701298701298701, + "grad_norm": 0.5703125, + "learning_rate": 1.1629135494628097e-06, + "loss": 0.2891, + "step": 268 + }, + { + "epoch": 0.8733766233766234, + "grad_norm": 0.56640625, + "learning_rate": 1.1065785111748117e-06, + "loss": 0.2853, + "step": 269 + }, + { + "epoch": 0.8766233766233766, + "grad_norm": 0.5625, + "learning_rate": 1.051562105591082e-06, + "loss": 0.292, + "step": 270 + }, + { + "epoch": 0.8766233766233766, + "eval_loss": 0.28765836358070374, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.932, + "eval_samples_per_second": 11.885, + "eval_steps_per_second": 1.486, + "step": 270 + }, + { + "epoch": 0.8798701298701299, + "grad_norm": 0.55859375, + "learning_rate": 9.978724900256265e-07, + "loss": 0.2825, + "step": 271 + }, + { + "epoch": 0.8831168831168831, + "grad_norm": 0.5546875, + "learning_rate": 9.455176250685338e-07, + "loss": 0.2836, + "step": 272 + }, + { + "epoch": 0.8863636363636364, + "grad_norm": 0.58203125, + "learning_rate": 8.945052734056581e-07, + "loss": 0.2959, + "step": 273 + }, + { + "epoch": 0.8896103896103896, + "grad_norm": 0.57421875, + "learning_rate": 8.448429986676298e-07, + "loss": 0.3003, + "step": 274 + }, + { + "epoch": 0.8928571428571429, + "grad_norm": 0.56640625, + "learning_rate": 7.965381643084069e-07, + "loss": 0.295, + "step": 275 + }, + { + "epoch": 0.8961038961038961, + "grad_norm": 0.5625, + "learning_rate": 7.495979325134806e-07, + "loss": 0.2873, + "step": 276 + }, + { + "epoch": 0.8993506493506493, + "grad_norm": 0.55078125, + "learning_rate": 7.040292631379386e-07, + "loss": 0.2827, + "step": 277 + }, + { + "epoch": 0.9025974025974026, + "grad_norm": 0.54296875, + "learning_rate": 6.598389126745209e-07, + "loss": 0.2797, + "step": 278 + }, + { + "epoch": 0.9058441558441559, + "grad_norm": 0.53125, + "learning_rate": 6.170334332518325e-07, + "loss": 0.272, + "step": 279 + }, + { + "epoch": 0.9090909090909091, + "grad_norm": 0.58203125, + "learning_rate": 5.756191716628556e-07, + "loss": 0.292, + "step": 280 + }, + { + "epoch": 0.9090909090909091, + "eval_loss": 0.28761279582977295, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9741, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 280 + }, + { + "epoch": 0.9123376623376623, + "grad_norm": 0.5703125, + "learning_rate": 5.35602268423906e-07, + "loss": 0.2961, + "step": 281 + }, + { + "epoch": 0.9155844155844156, + "grad_norm": 0.578125, + "learning_rate": 4.969886568641757e-07, + "loss": 0.2904, + "step": 282 + }, + { + "epoch": 0.9188311688311688, + "grad_norm": 0.5625, + "learning_rate": 4.597840622459937e-07, + "loss": 0.2874, + "step": 283 + }, + { + "epoch": 0.922077922077922, + "grad_norm": 0.546875, + "learning_rate": 4.2399400091594154e-07, + "loss": 0.2794, + "step": 284 + }, + { + "epoch": 0.9253246753246753, + "grad_norm": 0.578125, + "learning_rate": 3.8962377948693395e-07, + "loss": 0.2962, + "step": 285 + }, + { + "epoch": 0.9285714285714286, + "grad_norm": 0.56640625, + "learning_rate": 3.566784940514145e-07, + "loss": 0.2914, + "step": 286 + }, + { + "epoch": 0.9318181818181818, + "grad_norm": 0.5703125, + "learning_rate": 3.2516302942574794e-07, + "loss": 0.2838, + "step": 287 + }, + { + "epoch": 0.935064935064935, + "grad_norm": 0.55859375, + "learning_rate": 2.9508205842594727e-07, + "loss": 0.2812, + "step": 288 + }, + { + "epoch": 0.9383116883116883, + "grad_norm": 0.5625, + "learning_rate": 2.6644004117483357e-07, + "loss": 0.2827, + "step": 289 + }, + { + "epoch": 0.9415584415584416, + "grad_norm": 0.5546875, + "learning_rate": 2.392412244407294e-07, + "loss": 0.2791, + "step": 290 + }, + { + "epoch": 0.9415584415584416, + "eval_loss": 0.28759849071502686, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0075, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 290 + }, + { + "epoch": 0.9448051948051948, + "grad_norm": 0.55859375, + "learning_rate": 2.1348964100778914e-07, + "loss": 0.285, + "step": 291 + }, + { + "epoch": 0.948051948051948, + "grad_norm": 0.55859375, + "learning_rate": 1.8918910907805733e-07, + "loss": 0.288, + "step": 292 + }, + { + "epoch": 0.9512987012987013, + "grad_norm": 0.57421875, + "learning_rate": 1.6634323170533928e-07, + "loss": 0.2854, + "step": 293 + }, + { + "epoch": 0.9545454545454546, + "grad_norm": 0.57421875, + "learning_rate": 1.4495539626097289e-07, + "loss": 0.2873, + "step": 294 + }, + { + "epoch": 0.9577922077922078, + "grad_norm": 0.56640625, + "learning_rate": 1.2502877393158587e-07, + "loss": 0.2841, + "step": 295 + }, + { + "epoch": 0.961038961038961, + "grad_norm": 0.62109375, + "learning_rate": 1.0656631924889749e-07, + "loss": 0.2994, + "step": 296 + }, + { + "epoch": 0.9642857142857143, + "grad_norm": 0.5546875, + "learning_rate": 8.957076965165234e-08, + "loss": 0.2797, + "step": 297 + }, + { + "epoch": 0.9675324675324676, + "grad_norm": 0.56640625, + "learning_rate": 7.404464507973608e-08, + "loss": 0.2868, + "step": 298 + }, + { + "epoch": 0.9707792207792207, + "grad_norm": 0.56640625, + "learning_rate": 5.999024760054095e-08, + "loss": 0.2867, + "step": 299 + }, + { + "epoch": 0.974025974025974, + "grad_norm": 0.56640625, + "learning_rate": 4.740966106764222e-08, + "loss": 0.2832, + "step": 300 + }, + { + "epoch": 0.974025974025974, + "eval_loss": 0.287624329328537, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9045, + "eval_samples_per_second": 11.886, + "eval_steps_per_second": 1.487, + "step": 300 + } + ], + "logging_steps": 1, + "max_steps": 308, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "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": 1.7706338758950912e+18, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4684d3c90558d6bfde405c82b58596bc6231bfee --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09f69be12f7ef607f0a1508435a517f5277e3160e5d6a59346e619fcbaa3592 +size 5176 diff --git a/checkpoint-308/config.json b/checkpoint-308/config.json new file mode 100644 index 0000000000000000000000000000000000000000..de55730a672c2805e1108109d81a111b0cdb48b1 --- /dev/null +++ b/checkpoint-308/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a +size 915 diff --git a/checkpoint-308/generation_config.json b/checkpoint-308/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1007819213eaa3e36dd0c6354016734419f4a863 --- /dev/null +++ b/checkpoint-308/generation_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169 +size 184 diff --git a/checkpoint-308/model-00001-of-00004.safetensors b/checkpoint-308/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..616bb67b1f5310e3c9955e638763bdeff0fb55c8 --- /dev/null +++ b/checkpoint-308/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abfe37c12d3907a891b3b7282c09590bedc9a560e05339e0aebfba26341dc1b +size 4976698672 diff --git a/checkpoint-308/model-00002-of-00004.safetensors b/checkpoint-308/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c1a59736868aa002e16da3948c4b68be6d97a71 --- /dev/null +++ b/checkpoint-308/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584021d05e0ffd6879fcb1af88d896f418db0a6656a6c799d17e6a28e6540c8b +size 4999802720 diff --git a/checkpoint-308/model-00003-of-00004.safetensors b/checkpoint-308/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..075dada5dcfe243936f5583203b90ba80f0935e1 --- /dev/null +++ b/checkpoint-308/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced290d33c8beefb926d706c895d70bd58e0d89ba90daca1d637367a6e9163ae +size 4915916176 diff --git a/checkpoint-308/model-00004-of-00004.safetensors b/checkpoint-308/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1e38fdf23d6ff664ce00189e3dc1ab419ed8545 --- /dev/null +++ b/checkpoint-308/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03dad76ab9974b3c84fcd8067e459ff22c49e10e1408ea16637a06df0b9b71c4 +size 1168138808 diff --git a/checkpoint-308/model.safetensors.index.json b/checkpoint-308/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..a054aad8cf0cb5671e2e10b3bf817725a4bec031 --- /dev/null +++ b/checkpoint-308/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b +size 23950 diff --git a/checkpoint-308/optimizer.pt b/checkpoint-308/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..81d9520226370e1855c92fe28bb828c9ac7e5cdc --- /dev/null +++ b/checkpoint-308/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7c39b809a656f112d5f086526a410b408bd0992a7598ccf39a1595172d1717 +size 32121299754 diff --git a/checkpoint-308/rng_state.pth b/checkpoint-308/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..02e6a75cccce6d8b138f83bf61f04a2d82786ce4 --- /dev/null +++ b/checkpoint-308/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374644995be79c967030295cf4e5929f6a33d3b1197b8855bc39718b44686552 +size 14244 diff --git a/checkpoint-308/scheduler.pt b/checkpoint-308/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..cfb0140e43a2ea276537b0c933e85d359f3ef68f --- /dev/null +++ b/checkpoint-308/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7d6a70f369c23098e0581c238ab3095159ad5894f8b6e0d4e2094eec5204ed6 +size 1064 diff --git a/checkpoint-308/special_tokens_map.json b/checkpoint-308/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92d7fab6729d723f45689803b99006fec945cc47 --- /dev/null +++ b/checkpoint-308/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1835caa5b4d70acaa210fa222b0036f1882f9525c4660fd4810fb3e1e40ff8 +size 325 diff --git a/checkpoint-308/tokenizer.json b/checkpoint-308/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..66cd9d7e0daec95eb10d16a63c615637dbbb7304 --- /dev/null +++ b/checkpoint-308/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4 +size 9085657 diff --git a/checkpoint-308/tokenizer_config.json b/checkpoint-308/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..08ebc9598183a9a76c44ef06813aca75f51de4a5 --- /dev/null +++ b/checkpoint-308/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d0de6d831b5940c3f2eae4e495b9f77612cbb05b5804846733ab617f0dfe9b +size 55380 diff --git a/checkpoint-308/trainer_state.json b/checkpoint-308/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..959072709d27771c0774876b2d02d45de908928e --- /dev/null +++ b/checkpoint-308/trainer_state.json @@ -0,0 +1,2459 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 10, + "global_step": 308, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.003246753246753247, + "grad_norm": 16.375, + "learning_rate": 4.0000000000000003e-07, + "loss": 1.4017, + "step": 1 + }, + { + "epoch": 0.006493506493506494, + "grad_norm": 16.25, + "learning_rate": 8.000000000000001e-07, + "loss": 1.4229, + "step": 2 + }, + { + "epoch": 0.00974025974025974, + "grad_norm": 16.75, + "learning_rate": 1.2000000000000002e-06, + "loss": 1.4112, + "step": 3 + }, + { + "epoch": 0.012987012987012988, + "grad_norm": 16.5, + "learning_rate": 1.6000000000000001e-06, + "loss": 1.3959, + "step": 4 + }, + { + "epoch": 0.016233766233766232, + "grad_norm": 16.125, + "learning_rate": 2.0000000000000003e-06, + "loss": 1.3789, + "step": 5 + }, + { + "epoch": 0.01948051948051948, + "grad_norm": 14.4375, + "learning_rate": 2.4000000000000003e-06, + "loss": 1.3618, + "step": 6 + }, + { + "epoch": 0.022727272727272728, + "grad_norm": 10.1875, + "learning_rate": 2.8000000000000003e-06, + "loss": 1.3214, + "step": 7 + }, + { + "epoch": 0.025974025974025976, + "grad_norm": 7.4375, + "learning_rate": 3.2000000000000003e-06, + "loss": 1.2885, + "step": 8 + }, + { + "epoch": 0.02922077922077922, + "grad_norm": 6.28125, + "learning_rate": 3.6000000000000003e-06, + "loss": 1.2436, + "step": 9 + }, + { + "epoch": 0.032467532467532464, + "grad_norm": 5.75, + "learning_rate": 4.000000000000001e-06, + "loss": 1.2269, + "step": 10 + }, + { + "epoch": 0.032467532467532464, + "eval_loss": 1.1976113319396973, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0273, + "eval_samples_per_second": 11.878, + "eval_steps_per_second": 1.485, + "step": 10 + }, + { + "epoch": 0.03571428571428571, + "grad_norm": 5.375, + "learning_rate": 4.4e-06, + "loss": 1.1925, + "step": 11 + }, + { + "epoch": 0.03896103896103896, + "grad_norm": 5.125, + "learning_rate": 4.800000000000001e-06, + "loss": 1.1307, + "step": 12 + }, + { + "epoch": 0.04220779220779221, + "grad_norm": 5.125, + "learning_rate": 5.2e-06, + "loss": 1.0778, + "step": 13 + }, + { + "epoch": 0.045454545454545456, + "grad_norm": 5.0625, + "learning_rate": 5.600000000000001e-06, + "loss": 1.0067, + "step": 14 + }, + { + "epoch": 0.048701298701298704, + "grad_norm": 5.75, + "learning_rate": 6e-06, + "loss": 0.9668, + "step": 15 + }, + { + "epoch": 0.05194805194805195, + "grad_norm": 5.15625, + "learning_rate": 6.4000000000000006e-06, + "loss": 0.875, + "step": 16 + }, + { + "epoch": 0.05519480519480519, + "grad_norm": 4.875, + "learning_rate": 6.800000000000001e-06, + "loss": 0.8297, + "step": 17 + }, + { + "epoch": 0.05844155844155844, + "grad_norm": 4.5625, + "learning_rate": 7.2000000000000005e-06, + "loss": 0.7703, + "step": 18 + }, + { + "epoch": 0.06168831168831169, + "grad_norm": 3.90625, + "learning_rate": 7.600000000000001e-06, + "loss": 0.7327, + "step": 19 + }, + { + "epoch": 0.06493506493506493, + "grad_norm": 2.78125, + "learning_rate": 8.000000000000001e-06, + "loss": 0.6672, + "step": 20 + }, + { + "epoch": 0.06493506493506493, + "eval_loss": 0.6521233320236206, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.999, + "eval_samples_per_second": 11.88, + "eval_steps_per_second": 1.486, + "step": 20 + }, + { + "epoch": 0.06818181818181818, + "grad_norm": 2.140625, + "learning_rate": 8.400000000000001e-06, + "loss": 0.6507, + "step": 21 + }, + { + "epoch": 0.07142857142857142, + "grad_norm": 1.828125, + "learning_rate": 8.8e-06, + "loss": 0.6215, + "step": 22 + }, + { + "epoch": 0.07467532467532467, + "grad_norm": 1.5546875, + "learning_rate": 9.200000000000002e-06, + "loss": 0.5992, + "step": 23 + }, + { + "epoch": 0.07792207792207792, + "grad_norm": 1.4453125, + "learning_rate": 9.600000000000001e-06, + "loss": 0.5748, + "step": 24 + }, + { + "epoch": 0.08116883116883117, + "grad_norm": 1.328125, + "learning_rate": 1e-05, + "loss": 0.5572, + "step": 25 + }, + { + "epoch": 0.08441558441558442, + "grad_norm": 1.4765625, + "learning_rate": 1.04e-05, + "loss": 0.542, + "step": 26 + }, + { + "epoch": 0.08766233766233766, + "grad_norm": 1.1171875, + "learning_rate": 1.0800000000000002e-05, + "loss": 0.5317, + "step": 27 + }, + { + "epoch": 0.09090909090909091, + "grad_norm": 0.90625, + "learning_rate": 1.1200000000000001e-05, + "loss": 0.5173, + "step": 28 + }, + { + "epoch": 0.09415584415584416, + "grad_norm": 0.83984375, + "learning_rate": 1.16e-05, + "loss": 0.4892, + "step": 29 + }, + { + "epoch": 0.09740259740259741, + "grad_norm": 0.828125, + "learning_rate": 1.2e-05, + "loss": 0.491, + "step": 30 + }, + { + "epoch": 0.09740259740259741, + "eval_loss": 0.48583006858825684, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9705, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 30 + }, + { + "epoch": 0.10064935064935066, + "grad_norm": 0.8359375, + "learning_rate": 1.2400000000000002e-05, + "loss": 0.4852, + "step": 31 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 1.0078125, + "learning_rate": 1.2800000000000001e-05, + "loss": 0.4749, + "step": 32 + }, + { + "epoch": 0.10714285714285714, + "grad_norm": 0.99609375, + "learning_rate": 1.3200000000000002e-05, + "loss": 0.467, + "step": 33 + }, + { + "epoch": 0.11038961038961038, + "grad_norm": 0.734375, + "learning_rate": 1.3600000000000002e-05, + "loss": 0.4545, + "step": 34 + }, + { + "epoch": 0.11363636363636363, + "grad_norm": 0.69140625, + "learning_rate": 1.4e-05, + "loss": 0.4609, + "step": 35 + }, + { + "epoch": 0.11688311688311688, + "grad_norm": 0.69921875, + "learning_rate": 1.4400000000000001e-05, + "loss": 0.4497, + "step": 36 + }, + { + "epoch": 0.12012987012987013, + "grad_norm": 0.703125, + "learning_rate": 1.48e-05, + "loss": 0.4607, + "step": 37 + }, + { + "epoch": 0.12337662337662338, + "grad_norm": 0.6328125, + "learning_rate": 1.5200000000000002e-05, + "loss": 0.443, + "step": 38 + }, + { + "epoch": 0.1266233766233766, + "grad_norm": 0.65234375, + "learning_rate": 1.5600000000000003e-05, + "loss": 0.4428, + "step": 39 + }, + { + "epoch": 0.12987012987012986, + "grad_norm": 0.640625, + "learning_rate": 1.6000000000000003e-05, + "loss": 0.435, + "step": 40 + }, + { + "epoch": 0.12987012987012986, + "eval_loss": 0.4367639422416687, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0177, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 40 + }, + { + "epoch": 0.1331168831168831, + "grad_norm": 0.671875, + "learning_rate": 1.64e-05, + "loss": 0.438, + "step": 41 + }, + { + "epoch": 0.13636363636363635, + "grad_norm": 0.6484375, + "learning_rate": 1.6800000000000002e-05, + "loss": 0.4392, + "step": 42 + }, + { + "epoch": 0.1396103896103896, + "grad_norm": 0.65234375, + "learning_rate": 1.72e-05, + "loss": 0.435, + "step": 43 + }, + { + "epoch": 0.14285714285714285, + "grad_norm": 0.62109375, + "learning_rate": 1.76e-05, + "loss": 0.4356, + "step": 44 + }, + { + "epoch": 0.1461038961038961, + "grad_norm": 0.6171875, + "learning_rate": 1.8e-05, + "loss": 0.4172, + "step": 45 + }, + { + "epoch": 0.14935064935064934, + "grad_norm": 0.6015625, + "learning_rate": 1.8400000000000003e-05, + "loss": 0.4162, + "step": 46 + }, + { + "epoch": 0.1525974025974026, + "grad_norm": 0.609375, + "learning_rate": 1.88e-05, + "loss": 0.418, + "step": 47 + }, + { + "epoch": 0.15584415584415584, + "grad_norm": 0.6328125, + "learning_rate": 1.9200000000000003e-05, + "loss": 0.4177, + "step": 48 + }, + { + "epoch": 0.1590909090909091, + "grad_norm": 0.6171875, + "learning_rate": 1.9600000000000002e-05, + "loss": 0.4064, + "step": 49 + }, + { + "epoch": 0.16233766233766234, + "grad_norm": 0.62890625, + "learning_rate": 2e-05, + "loss": 0.4078, + "step": 50 + }, + { + "epoch": 0.16233766233766234, + "eval_loss": 0.4077843129634857, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.8482, + "eval_samples_per_second": 11.89, + "eval_steps_per_second": 1.487, + "step": 50 + }, + { + "epoch": 0.16558441558441558, + "grad_norm": 0.61328125, + "learning_rate": 1.9999258647132645e-05, + "loss": 0.4057, + "step": 51 + }, + { + "epoch": 0.16883116883116883, + "grad_norm": 0.62890625, + "learning_rate": 1.9997034698451396e-05, + "loss": 0.4172, + "step": 52 + }, + { + "epoch": 0.17207792207792208, + "grad_norm": 0.61328125, + "learning_rate": 1.9993328483702393e-05, + "loss": 0.4082, + "step": 53 + }, + { + "epoch": 0.17532467532467533, + "grad_norm": 0.59375, + "learning_rate": 1.998814055240823e-05, + "loss": 0.3973, + "step": 54 + }, + { + "epoch": 0.17857142857142858, + "grad_norm": 0.59375, + "learning_rate": 1.998147167378645e-05, + "loss": 0.3969, + "step": 55 + }, + { + "epoch": 0.18181818181818182, + "grad_norm": 0.609375, + "learning_rate": 1.9973322836635517e-05, + "loss": 0.4032, + "step": 56 + }, + { + "epoch": 0.18506493506493507, + "grad_norm": 0.5859375, + "learning_rate": 1.9963695249188185e-05, + "loss": 0.3956, + "step": 57 + }, + { + "epoch": 0.18831168831168832, + "grad_norm": 0.57421875, + "learning_rate": 1.995259033893236e-05, + "loss": 0.3952, + "step": 58 + }, + { + "epoch": 0.19155844155844157, + "grad_norm": 0.59765625, + "learning_rate": 1.9940009752399462e-05, + "loss": 0.3905, + "step": 59 + }, + { + "epoch": 0.19480519480519481, + "grad_norm": 0.60546875, + "learning_rate": 1.9925955354920265e-05, + "loss": 0.3822, + "step": 60 + }, + { + "epoch": 0.19480519480519481, + "eval_loss": 0.38575297594070435, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9122, + "eval_samples_per_second": 11.886, + "eval_steps_per_second": 1.486, + "step": 60 + }, + { + "epoch": 0.19805194805194806, + "grad_norm": 0.5859375, + "learning_rate": 1.9910429230348348e-05, + "loss": 0.3976, + "step": 61 + }, + { + "epoch": 0.2012987012987013, + "grad_norm": 0.578125, + "learning_rate": 1.9893433680751105e-05, + "loss": 0.3714, + "step": 62 + }, + { + "epoch": 0.20454545454545456, + "grad_norm": 0.5859375, + "learning_rate": 1.9874971226068417e-05, + "loss": 0.3739, + "step": 63 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 0.5859375, + "learning_rate": 1.985504460373903e-05, + "loss": 0.3907, + "step": 64 + }, + { + "epoch": 0.21103896103896103, + "grad_norm": 0.609375, + "learning_rate": 1.983365676829466e-05, + "loss": 0.3803, + "step": 65 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.59765625, + "learning_rate": 1.9810810890921943e-05, + "loss": 0.3902, + "step": 66 + }, + { + "epoch": 0.21753246753246752, + "grad_norm": 0.578125, + "learning_rate": 1.9786510358992213e-05, + "loss": 0.3744, + "step": 67 + }, + { + "epoch": 0.22077922077922077, + "grad_norm": 0.56640625, + "learning_rate": 1.9760758775559275e-05, + "loss": 0.3668, + "step": 68 + }, + { + "epoch": 0.22402597402597402, + "grad_norm": 0.625, + "learning_rate": 1.9733559958825167e-05, + "loss": 0.3755, + "step": 69 + }, + { + "epoch": 0.22727272727272727, + "grad_norm": 0.60546875, + "learning_rate": 1.9704917941574053e-05, + "loss": 0.3733, + "step": 70 + }, + { + "epoch": 0.22727272727272727, + "eval_loss": 0.3694484233856201, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9363, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 70 + }, + { + "epoch": 0.2305194805194805, + "grad_norm": 0.6015625, + "learning_rate": 1.9674836970574253e-05, + "loss": 0.3676, + "step": 71 + }, + { + "epoch": 0.23376623376623376, + "grad_norm": 0.60546875, + "learning_rate": 1.9643321505948588e-05, + "loss": 0.3721, + "step": 72 + }, + { + "epoch": 0.237012987012987, + "grad_norm": 0.60546875, + "learning_rate": 1.9610376220513067e-05, + "loss": 0.3558, + "step": 73 + }, + { + "epoch": 0.24025974025974026, + "grad_norm": 0.625, + "learning_rate": 1.957600599908406e-05, + "loss": 0.357, + "step": 74 + }, + { + "epoch": 0.2435064935064935, + "grad_norm": 0.66015625, + "learning_rate": 1.954021593775401e-05, + "loss": 0.3608, + "step": 75 + }, + { + "epoch": 0.24675324675324675, + "grad_norm": 0.59375, + "learning_rate": 1.9503011343135828e-05, + "loss": 0.3513, + "step": 76 + }, + { + "epoch": 0.25, + "grad_norm": 0.609375, + "learning_rate": 1.9464397731576093e-05, + "loss": 0.3693, + "step": 77 + }, + { + "epoch": 0.2532467532467532, + "grad_norm": 0.59375, + "learning_rate": 1.9424380828337146e-05, + "loss": 0.3605, + "step": 78 + }, + { + "epoch": 0.2564935064935065, + "grad_norm": 0.6171875, + "learning_rate": 1.938296656674817e-05, + "loss": 0.3553, + "step": 79 + }, + { + "epoch": 0.2597402597402597, + "grad_norm": 0.671875, + "learning_rate": 1.9340161087325483e-05, + "loss": 0.3721, + "step": 80 + }, + { + "epoch": 0.2597402597402597, + "eval_loss": 0.3553767800331116, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0277, + "eval_samples_per_second": 11.878, + "eval_steps_per_second": 1.485, + "step": 80 + }, + { + "epoch": 0.262987012987013, + "grad_norm": 0.609375, + "learning_rate": 1.9295970736862063e-05, + "loss": 0.3597, + "step": 81 + }, + { + "epoch": 0.2662337662337662, + "grad_norm": 0.65625, + "learning_rate": 1.9250402067486523e-05, + "loss": 0.3527, + "step": 82 + }, + { + "epoch": 0.2694805194805195, + "grad_norm": 0.61328125, + "learning_rate": 1.9203461835691596e-05, + "loss": 0.3528, + "step": 83 + }, + { + "epoch": 0.2727272727272727, + "grad_norm": 0.6640625, + "learning_rate": 1.9155157001332374e-05, + "loss": 0.356, + "step": 84 + }, + { + "epoch": 0.275974025974026, + "grad_norm": 0.6171875, + "learning_rate": 1.9105494726594344e-05, + "loss": 0.3556, + "step": 85 + }, + { + "epoch": 0.2792207792207792, + "grad_norm": 0.6171875, + "learning_rate": 1.905448237493147e-05, + "loss": 0.3473, + "step": 86 + }, + { + "epoch": 0.2824675324675325, + "grad_norm": 0.5859375, + "learning_rate": 1.9002127509974376e-05, + "loss": 0.3441, + "step": 87 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 0.6171875, + "learning_rate": 1.894843789440892e-05, + "loss": 0.3492, + "step": 88 + }, + { + "epoch": 0.288961038961039, + "grad_norm": 0.6328125, + "learning_rate": 1.889342148882519e-05, + "loss": 0.3338, + "step": 89 + }, + { + "epoch": 0.2922077922077922, + "grad_norm": 0.67578125, + "learning_rate": 1.8837086450537195e-05, + "loss": 0.3347, + "step": 90 + }, + { + "epoch": 0.2922077922077922, + "eval_loss": 0.34332525730133057, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9257, + "eval_samples_per_second": 11.885, + "eval_steps_per_second": 1.486, + "step": 90 + }, + { + "epoch": 0.29545454545454547, + "grad_norm": 0.6328125, + "learning_rate": 1.877944113237336e-05, + "loss": 0.3438, + "step": 91 + }, + { + "epoch": 0.2987012987012987, + "grad_norm": 0.6328125, + "learning_rate": 1.872049408143808e-05, + "loss": 0.3505, + "step": 92 + }, + { + "epoch": 0.30194805194805197, + "grad_norm": 0.6328125, + "learning_rate": 1.866025403784439e-05, + "loss": 0.3362, + "step": 93 + }, + { + "epoch": 0.3051948051948052, + "grad_norm": 0.640625, + "learning_rate": 1.8598729933418102e-05, + "loss": 0.337, + "step": 94 + }, + { + "epoch": 0.30844155844155846, + "grad_norm": 0.64453125, + "learning_rate": 1.8535930890373467e-05, + "loss": 0.3324, + "step": 95 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 0.6875, + "learning_rate": 1.8471866219960604e-05, + "loss": 0.3461, + "step": 96 + }, + { + "epoch": 0.31493506493506496, + "grad_norm": 0.6328125, + "learning_rate": 1.840654542108494e-05, + "loss": 0.3318, + "step": 97 + }, + { + "epoch": 0.3181818181818182, + "grad_norm": 0.62109375, + "learning_rate": 1.833997817889878e-05, + "loss": 0.3335, + "step": 98 + }, + { + "epoch": 0.32142857142857145, + "grad_norm": 0.61328125, + "learning_rate": 1.82721743633653e-05, + "loss": 0.3291, + "step": 99 + }, + { + "epoch": 0.3246753246753247, + "grad_norm": 0.6171875, + "learning_rate": 1.820314402779511e-05, + "loss": 0.3324, + "step": 100 + }, + { + "epoch": 0.3246753246753247, + "eval_loss": 0.33332687616348267, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9506, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 100 + }, + { + "epoch": 0.32792207792207795, + "grad_norm": 0.6328125, + "learning_rate": 1.8132897407355657e-05, + "loss": 0.3288, + "step": 101 + }, + { + "epoch": 0.33116883116883117, + "grad_norm": 0.6484375, + "learning_rate": 1.806144491755363e-05, + "loss": 0.3384, + "step": 102 + }, + { + "epoch": 0.3344155844155844, + "grad_norm": 0.6328125, + "learning_rate": 1.798879715269067e-05, + "loss": 0.3329, + "step": 103 + }, + { + "epoch": 0.33766233766233766, + "grad_norm": 0.6171875, + "learning_rate": 1.7914964884292543e-05, + "loss": 0.3329, + "step": 104 + }, + { + "epoch": 0.3409090909090909, + "grad_norm": 0.671875, + "learning_rate": 1.7839959059512016e-05, + "loss": 0.3335, + "step": 105 + }, + { + "epoch": 0.34415584415584416, + "grad_norm": 0.609375, + "learning_rate": 1.7763790799505746e-05, + "loss": 0.3201, + "step": 106 + }, + { + "epoch": 0.3474025974025974, + "grad_norm": 0.6171875, + "learning_rate": 1.7686471397785322e-05, + "loss": 0.3327, + "step": 107 + }, + { + "epoch": 0.35064935064935066, + "grad_norm": 0.640625, + "learning_rate": 1.760801231854278e-05, + "loss": 0.3205, + "step": 108 + }, + { + "epoch": 0.3538961038961039, + "grad_norm": 0.6328125, + "learning_rate": 1.7528425194950794e-05, + "loss": 0.334, + "step": 109 + }, + { + "epoch": 0.35714285714285715, + "grad_norm": 0.6015625, + "learning_rate": 1.744772182743782e-05, + "loss": 0.3165, + "step": 110 + }, + { + "epoch": 0.35714285714285715, + "eval_loss": 0.32505103945732117, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0106, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 110 + }, + { + "epoch": 0.36038961038961037, + "grad_norm": 0.62890625, + "learning_rate": 1.736591418193844e-05, + "loss": 0.3236, + "step": 111 + }, + { + "epoch": 0.36363636363636365, + "grad_norm": 0.63671875, + "learning_rate": 1.728301438811916e-05, + "loss": 0.3192, + "step": 112 + }, + { + "epoch": 0.36688311688311687, + "grad_norm": 0.6484375, + "learning_rate": 1.7199034737579962e-05, + "loss": 0.327, + "step": 113 + }, + { + "epoch": 0.37012987012987014, + "grad_norm": 0.62109375, + "learning_rate": 1.711398768203178e-05, + "loss": 0.3169, + "step": 114 + }, + { + "epoch": 0.37337662337662336, + "grad_norm": 0.625, + "learning_rate": 1.7027885831450318e-05, + "loss": 0.3186, + "step": 115 + }, + { + "epoch": 0.37662337662337664, + "grad_norm": 0.60546875, + "learning_rate": 1.6940741952206342e-05, + "loss": 0.3136, + "step": 116 + }, + { + "epoch": 0.37987012987012986, + "grad_norm": 0.62109375, + "learning_rate": 1.6852568965172794e-05, + "loss": 0.3184, + "step": 117 + }, + { + "epoch": 0.38311688311688313, + "grad_norm": 0.60546875, + "learning_rate": 1.676337994380903e-05, + "loss": 0.3114, + "step": 118 + }, + { + "epoch": 0.38636363636363635, + "grad_norm": 0.6640625, + "learning_rate": 1.6673188112222394e-05, + "loss": 0.3329, + "step": 119 + }, + { + "epoch": 0.38961038961038963, + "grad_norm": 0.60546875, + "learning_rate": 1.658200684320748e-05, + "loss": 0.3105, + "step": 120 + }, + { + "epoch": 0.38961038961038963, + "eval_loss": 0.31796982884407043, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9896, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 120 + }, + { + "epoch": 0.39285714285714285, + "grad_norm": 0.58203125, + "learning_rate": 1.6489849656263336e-05, + "loss": 0.3084, + "step": 121 + }, + { + "epoch": 0.3961038961038961, + "grad_norm": 0.57421875, + "learning_rate": 1.6396730215588913e-05, + "loss": 0.3124, + "step": 122 + }, + { + "epoch": 0.39935064935064934, + "grad_norm": 0.609375, + "learning_rate": 1.630266232805709e-05, + "loss": 0.3167, + "step": 123 + }, + { + "epoch": 0.4025974025974026, + "grad_norm": 0.6171875, + "learning_rate": 1.6207659941167485e-05, + "loss": 0.3084, + "step": 124 + }, + { + "epoch": 0.40584415584415584, + "grad_norm": 0.62890625, + "learning_rate": 1.6111737140978495e-05, + "loss": 0.3143, + "step": 125 + }, + { + "epoch": 0.4090909090909091, + "grad_norm": 0.6171875, + "learning_rate": 1.6014908150018703e-05, + "loss": 0.3173, + "step": 126 + }, + { + "epoch": 0.41233766233766234, + "grad_norm": 0.609375, + "learning_rate": 1.591718732517814e-05, + "loss": 0.3199, + "step": 127 + }, + { + "epoch": 0.4155844155844156, + "grad_norm": 0.609375, + "learning_rate": 1.581858915557953e-05, + "loss": 0.312, + "step": 128 + }, + { + "epoch": 0.41883116883116883, + "grad_norm": 0.61328125, + "learning_rate": 1.571912826043003e-05, + "loss": 0.3217, + "step": 129 + }, + { + "epoch": 0.42207792207792205, + "grad_norm": 0.59765625, + "learning_rate": 1.5618819386853607e-05, + "loss": 0.3123, + "step": 130 + }, + { + "epoch": 0.42207792207792205, + "eval_loss": 0.3119741976261139, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9669, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 130 + }, + { + "epoch": 0.4253246753246753, + "grad_norm": 0.61328125, + "learning_rate": 1.551767740770446e-05, + "loss": 0.3088, + "step": 131 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.578125, + "learning_rate": 1.541571731936185e-05, + "loss": 0.3084, + "step": 132 + }, + { + "epoch": 0.4318181818181818, + "grad_norm": 0.6328125, + "learning_rate": 1.5312954239506536e-05, + "loss": 0.3179, + "step": 133 + }, + { + "epoch": 0.43506493506493504, + "grad_norm": 0.60546875, + "learning_rate": 1.5209403404879305e-05, + "loss": 0.3145, + "step": 134 + }, + { + "epoch": 0.4383116883116883, + "grad_norm": 0.59765625, + "learning_rate": 1.5105080169021792e-05, + "loss": 0.3045, + "step": 135 + }, + { + "epoch": 0.44155844155844154, + "grad_norm": 0.5859375, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.314, + "step": 136 + }, + { + "epoch": 0.4448051948051948, + "grad_norm": 0.6484375, + "learning_rate": 1.4894178478110856e-05, + "loss": 0.2985, + "step": 137 + }, + { + "epoch": 0.44805194805194803, + "grad_norm": 0.58984375, + "learning_rate": 1.4787631293572094e-05, + "loss": 0.3114, + "step": 138 + }, + { + "epoch": 0.4512987012987013, + "grad_norm": 0.60546875, + "learning_rate": 1.4680374244195861e-05, + "loss": 0.3129, + "step": 139 + }, + { + "epoch": 0.45454545454545453, + "grad_norm": 0.58984375, + "learning_rate": 1.4572423233046386e-05, + "loss": 0.3007, + "step": 140 + }, + { + "epoch": 0.45454545454545453, + "eval_loss": 0.30710509419441223, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9622, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 140 + }, + { + "epoch": 0.4577922077922078, + "grad_norm": 0.58203125, + "learning_rate": 1.4463794266081994e-05, + "loss": 0.2981, + "step": 141 + }, + { + "epoch": 0.461038961038961, + "grad_norm": 0.5703125, + "learning_rate": 1.4354503449781914e-05, + "loss": 0.2974, + "step": 142 + }, + { + "epoch": 0.4642857142857143, + "grad_norm": 0.5859375, + "learning_rate": 1.4244566988758152e-05, + "loss": 0.3064, + "step": 143 + }, + { + "epoch": 0.4675324675324675, + "grad_norm": 0.56640625, + "learning_rate": 1.4134001183352833e-05, + "loss": 0.298, + "step": 144 + }, + { + "epoch": 0.4707792207792208, + "grad_norm": 0.5703125, + "learning_rate": 1.4022822427221325e-05, + "loss": 0.3037, + "step": 145 + }, + { + "epoch": 0.474025974025974, + "grad_norm": 0.58203125, + "learning_rate": 1.391104720490156e-05, + "loss": 0.3062, + "step": 146 + }, + { + "epoch": 0.4772727272727273, + "grad_norm": 0.609375, + "learning_rate": 1.3798692089369855e-05, + "loss": 0.3019, + "step": 147 + }, + { + "epoch": 0.4805194805194805, + "grad_norm": 0.61328125, + "learning_rate": 1.368577373958362e-05, + "loss": 0.3008, + "step": 148 + }, + { + "epoch": 0.4837662337662338, + "grad_norm": 0.56640625, + "learning_rate": 1.3572308898011328e-05, + "loss": 0.3055, + "step": 149 + }, + { + "epoch": 0.487012987012987, + "grad_norm": 0.5859375, + "learning_rate": 1.3458314388150115e-05, + "loss": 0.2942, + "step": 150 + }, + { + "epoch": 0.487012987012987, + "eval_loss": 0.30315953493118286, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9566, + "eval_samples_per_second": 11.883, + "eval_steps_per_second": 1.486, + "step": 150 + }, + { + "epoch": 0.4902597402597403, + "grad_norm": 0.578125, + "learning_rate": 1.3343807112031329e-05, + "loss": 0.3097, + "step": 151 + }, + { + "epoch": 0.4935064935064935, + "grad_norm": 0.56640625, + "learning_rate": 1.3228804047714462e-05, + "loss": 0.3004, + "step": 152 + }, + { + "epoch": 0.4967532467532468, + "grad_norm": 0.58203125, + "learning_rate": 1.3113322246769817e-05, + "loss": 0.3046, + "step": 153 + }, + { + "epoch": 0.5, + "grad_norm": 0.57421875, + "learning_rate": 1.2997378831750242e-05, + "loss": 0.2966, + "step": 154 + }, + { + "epoch": 0.5032467532467533, + "grad_norm": 0.5703125, + "learning_rate": 1.2880990993652379e-05, + "loss": 0.2989, + "step": 155 + }, + { + "epoch": 0.5064935064935064, + "grad_norm": 0.609375, + "learning_rate": 1.2764175989367717e-05, + "loss": 0.3015, + "step": 156 + }, + { + "epoch": 0.5097402597402597, + "grad_norm": 0.5703125, + "learning_rate": 1.2646951139123935e-05, + "loss": 0.2976, + "step": 157 + }, + { + "epoch": 0.512987012987013, + "grad_norm": 0.59765625, + "learning_rate": 1.2529333823916807e-05, + "loss": 0.2919, + "step": 158 + }, + { + "epoch": 0.5162337662337663, + "grad_norm": 0.6328125, + "learning_rate": 1.241134148293311e-05, + "loss": 0.3041, + "step": 159 + }, + { + "epoch": 0.5194805194805194, + "grad_norm": 0.58984375, + "learning_rate": 1.2292991610964902e-05, + "loss": 0.3053, + "step": 160 + }, + { + "epoch": 0.5194805194805194, + "eval_loss": 0.3000594675540924, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9643, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 160 + }, + { + "epoch": 0.5227272727272727, + "grad_norm": 0.5859375, + "learning_rate": 1.2174301755815572e-05, + "loss": 0.3043, + "step": 161 + }, + { + "epoch": 0.525974025974026, + "grad_norm": 0.55859375, + "learning_rate": 1.2055289515698008e-05, + "loss": 0.2988, + "step": 162 + }, + { + "epoch": 0.5292207792207793, + "grad_norm": 0.5703125, + "learning_rate": 1.1935972536625302e-05, + "loss": 0.2871, + "step": 163 + }, + { + "epoch": 0.5324675324675324, + "grad_norm": 0.578125, + "learning_rate": 1.1816368509794365e-05, + "loss": 0.2985, + "step": 164 + }, + { + "epoch": 0.5357142857142857, + "grad_norm": 0.609375, + "learning_rate": 1.1696495168962848e-05, + "loss": 0.3066, + "step": 165 + }, + { + "epoch": 0.538961038961039, + "grad_norm": 0.57421875, + "learning_rate": 1.1576370287819737e-05, + "loss": 0.296, + "step": 166 + }, + { + "epoch": 0.5422077922077922, + "grad_norm": 0.59375, + "learning_rate": 1.1456011677350052e-05, + "loss": 0.2997, + "step": 167 + }, + { + "epoch": 0.5454545454545454, + "grad_norm": 0.58984375, + "learning_rate": 1.133543718319398e-05, + "loss": 0.3011, + "step": 168 + }, + { + "epoch": 0.5487012987012987, + "grad_norm": 0.5703125, + "learning_rate": 1.1214664683000927e-05, + "loss": 0.2898, + "step": 169 + }, + { + "epoch": 0.551948051948052, + "grad_norm": 0.58203125, + "learning_rate": 1.1093712083778748e-05, + "loss": 0.292, + "step": 170 + }, + { + "epoch": 0.551948051948052, + "eval_loss": 0.29717138409614563, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9869, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 170 + }, + { + "epoch": 0.5551948051948052, + "grad_norm": 0.578125, + "learning_rate": 1.0972597319238692e-05, + "loss": 0.2995, + "step": 171 + }, + { + "epoch": 0.5584415584415584, + "grad_norm": 0.58984375, + "learning_rate": 1.0851338347136358e-05, + "loss": 0.3015, + "step": 172 + }, + { + "epoch": 0.5616883116883117, + "grad_norm": 0.5625, + "learning_rate": 1.0729953146609076e-05, + "loss": 0.2953, + "step": 173 + }, + { + "epoch": 0.564935064935065, + "grad_norm": 0.55859375, + "learning_rate": 1.060845971551014e-05, + "loss": 0.3011, + "step": 174 + }, + { + "epoch": 0.5681818181818182, + "grad_norm": 0.58984375, + "learning_rate": 1.0486876067740253e-05, + "loss": 0.3016, + "step": 175 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 0.5859375, + "learning_rate": 1.0365220230576592e-05, + "loss": 0.2953, + "step": 176 + }, + { + "epoch": 0.5746753246753247, + "grad_norm": 0.5625, + "learning_rate": 1.0243510241999898e-05, + "loss": 0.2948, + "step": 177 + }, + { + "epoch": 0.577922077922078, + "grad_norm": 0.5703125, + "learning_rate": 1.0121764148019977e-05, + "loss": 0.2958, + "step": 178 + }, + { + "epoch": 0.5811688311688312, + "grad_norm": 0.5546875, + "learning_rate": 1e-05, + "loss": 0.2829, + "step": 179 + }, + { + "epoch": 0.5844155844155844, + "grad_norm": 0.58203125, + "learning_rate": 9.878235851980027e-06, + "loss": 0.2917, + "step": 180 + }, + { + "epoch": 0.5844155844155844, + "eval_loss": 0.29469791054725647, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9839, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 180 + }, + { + "epoch": 0.5876623376623377, + "grad_norm": 0.59375, + "learning_rate": 9.756489758000105e-06, + "loss": 0.2994, + "step": 181 + }, + { + "epoch": 0.5909090909090909, + "grad_norm": 0.57421875, + "learning_rate": 9.634779769423412e-06, + "loss": 0.3054, + "step": 182 + }, + { + "epoch": 0.5941558441558441, + "grad_norm": 0.59375, + "learning_rate": 9.51312393225975e-06, + "loss": 0.2925, + "step": 183 + }, + { + "epoch": 0.5974025974025974, + "grad_norm": 0.5703125, + "learning_rate": 9.391540284489862e-06, + "loss": 0.2816, + "step": 184 + }, + { + "epoch": 0.6006493506493507, + "grad_norm": 0.5390625, + "learning_rate": 9.270046853390924e-06, + "loss": 0.2856, + "step": 185 + }, + { + "epoch": 0.6038961038961039, + "grad_norm": 0.5703125, + "learning_rate": 9.148661652863644e-06, + "loss": 0.2936, + "step": 186 + }, + { + "epoch": 0.6071428571428571, + "grad_norm": 0.55078125, + "learning_rate": 9.02740268076131e-06, + "loss": 0.2938, + "step": 187 + }, + { + "epoch": 0.6103896103896104, + "grad_norm": 0.5859375, + "learning_rate": 8.906287916221259e-06, + "loss": 0.3017, + "step": 188 + }, + { + "epoch": 0.6136363636363636, + "grad_norm": 0.578125, + "learning_rate": 8.785335316999078e-06, + "loss": 0.2957, + "step": 189 + }, + { + "epoch": 0.6168831168831169, + "grad_norm": 0.58203125, + "learning_rate": 8.664562816806022e-06, + "loss": 0.2961, + "step": 190 + }, + { + "epoch": 0.6168831168831169, + "eval_loss": 0.2927069365978241, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9405, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 190 + }, + { + "epoch": 0.6201298701298701, + "grad_norm": 0.58203125, + "learning_rate": 8.543988322649954e-06, + "loss": 0.2915, + "step": 191 + }, + { + "epoch": 0.6233766233766234, + "grad_norm": 0.57421875, + "learning_rate": 8.423629712180265e-06, + "loss": 0.2875, + "step": 192 + }, + { + "epoch": 0.6266233766233766, + "grad_norm": 0.5703125, + "learning_rate": 8.303504831037154e-06, + "loss": 0.2979, + "step": 193 + }, + { + "epoch": 0.6298701298701299, + "grad_norm": 0.5703125, + "learning_rate": 8.183631490205636e-06, + "loss": 0.2891, + "step": 194 + }, + { + "epoch": 0.6331168831168831, + "grad_norm": 0.5703125, + "learning_rate": 8.064027463374702e-06, + "loss": 0.2796, + "step": 195 + }, + { + "epoch": 0.6363636363636364, + "grad_norm": 0.57421875, + "learning_rate": 7.944710484301995e-06, + "loss": 0.285, + "step": 196 + }, + { + "epoch": 0.6396103896103896, + "grad_norm": 0.58203125, + "learning_rate": 7.825698244184432e-06, + "loss": 0.295, + "step": 197 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.57421875, + "learning_rate": 7.707008389035102e-06, + "loss": 0.2962, + "step": 198 + }, + { + "epoch": 0.6461038961038961, + "grad_norm": 0.57421875, + "learning_rate": 7.588658517066893e-06, + "loss": 0.2912, + "step": 199 + }, + { + "epoch": 0.6493506493506493, + "grad_norm": 0.57421875, + "learning_rate": 7.470666176083193e-06, + "loss": 0.2917, + "step": 200 + }, + { + "epoch": 0.6493506493506493, + "eval_loss": 0.2912693917751312, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9875, + "eval_samples_per_second": 11.881, + "eval_steps_per_second": 1.486, + "step": 200 + }, + { + "epoch": 0.6525974025974026, + "grad_norm": 0.6015625, + "learning_rate": 7.3530488608760645e-06, + "loss": 0.291, + "step": 201 + }, + { + "epoch": 0.6558441558441559, + "grad_norm": 0.5625, + "learning_rate": 7.235824010632284e-06, + "loss": 0.2862, + "step": 202 + }, + { + "epoch": 0.6590909090909091, + "grad_norm": 0.5546875, + "learning_rate": 7.119009006347625e-06, + "loss": 0.2936, + "step": 203 + }, + { + "epoch": 0.6623376623376623, + "grad_norm": 0.5546875, + "learning_rate": 7.002621168249759e-06, + "loss": 0.2934, + "step": 204 + }, + { + "epoch": 0.6655844155844156, + "grad_norm": 0.578125, + "learning_rate": 6.886677753230184e-06, + "loss": 0.2783, + "step": 205 + }, + { + "epoch": 0.6688311688311688, + "grad_norm": 0.546875, + "learning_rate": 6.771195952285541e-06, + "loss": 0.2844, + "step": 206 + }, + { + "epoch": 0.672077922077922, + "grad_norm": 0.5546875, + "learning_rate": 6.656192887968675e-06, + "loss": 0.2835, + "step": 207 + }, + { + "epoch": 0.6753246753246753, + "grad_norm": 0.56640625, + "learning_rate": 6.5416856118498874e-06, + "loss": 0.2887, + "step": 208 + }, + { + "epoch": 0.6785714285714286, + "grad_norm": 0.5625, + "learning_rate": 6.427691101988673e-06, + "loss": 0.2925, + "step": 209 + }, + { + "epoch": 0.6818181818181818, + "grad_norm": 0.58203125, + "learning_rate": 6.314226260416383e-06, + "loss": 0.29, + "step": 210 + }, + { + "epoch": 0.6818181818181818, + "eval_loss": 0.29015374183654785, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.8645, + "eval_samples_per_second": 11.889, + "eval_steps_per_second": 1.487, + "step": 210 + }, + { + "epoch": 0.685064935064935, + "grad_norm": 0.5625, + "learning_rate": 6.2013079106301454e-06, + "loss": 0.2858, + "step": 211 + }, + { + "epoch": 0.6883116883116883, + "grad_norm": 0.5703125, + "learning_rate": 6.088952795098442e-06, + "loss": 0.2828, + "step": 212 + }, + { + "epoch": 0.6915584415584416, + "grad_norm": 0.578125, + "learning_rate": 5.977177572778679e-06, + "loss": 0.2947, + "step": 213 + }, + { + "epoch": 0.6948051948051948, + "grad_norm": 0.578125, + "learning_rate": 5.8659988166471715e-06, + "loss": 0.2795, + "step": 214 + }, + { + "epoch": 0.698051948051948, + "grad_norm": 0.56640625, + "learning_rate": 5.755433011241851e-06, + "loss": 0.2899, + "step": 215 + }, + { + "epoch": 0.7012987012987013, + "grad_norm": 0.578125, + "learning_rate": 5.645496550218089e-06, + "loss": 0.2881, + "step": 216 + }, + { + "epoch": 0.7045454545454546, + "grad_norm": 0.56640625, + "learning_rate": 5.5362057339180075e-06, + "loss": 0.2937, + "step": 217 + }, + { + "epoch": 0.7077922077922078, + "grad_norm": 0.5625, + "learning_rate": 5.427576766953615e-06, + "loss": 0.2828, + "step": 218 + }, + { + "epoch": 0.711038961038961, + "grad_norm": 0.57421875, + "learning_rate": 5.3196257558041386e-06, + "loss": 0.2863, + "step": 219 + }, + { + "epoch": 0.7142857142857143, + "grad_norm": 0.5859375, + "learning_rate": 5.212368706427913e-06, + "loss": 0.2876, + "step": 220 + }, + { + "epoch": 0.7142857142857143, + "eval_loss": 0.2891963720321655, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9738, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 220 + }, + { + "epoch": 0.7175324675324676, + "grad_norm": 0.5859375, + "learning_rate": 5.105821521889147e-06, + "loss": 0.2955, + "step": 221 + }, + { + "epoch": 0.7207792207792207, + "grad_norm": 0.56640625, + "learning_rate": 5.000000000000003e-06, + "loss": 0.2873, + "step": 222 + }, + { + "epoch": 0.724025974025974, + "grad_norm": 0.5625, + "learning_rate": 4.894919830978212e-06, + "loss": 0.2813, + "step": 223 + }, + { + "epoch": 0.7272727272727273, + "grad_norm": 0.59375, + "learning_rate": 4.790596595120699e-06, + "loss": 0.2912, + "step": 224 + }, + { + "epoch": 0.7305194805194806, + "grad_norm": 0.5859375, + "learning_rate": 4.687045760493468e-06, + "loss": 0.2921, + "step": 225 + }, + { + "epoch": 0.7337662337662337, + "grad_norm": 0.55078125, + "learning_rate": 4.584282680638155e-06, + "loss": 0.288, + "step": 226 + }, + { + "epoch": 0.737012987012987, + "grad_norm": 0.5546875, + "learning_rate": 4.482322592295541e-06, + "loss": 0.2914, + "step": 227 + }, + { + "epoch": 0.7402597402597403, + "grad_norm": 0.56640625, + "learning_rate": 4.381180613146396e-06, + "loss": 0.2901, + "step": 228 + }, + { + "epoch": 0.7435064935064936, + "grad_norm": 0.56640625, + "learning_rate": 4.280871739569972e-06, + "loss": 0.2941, + "step": 229 + }, + { + "epoch": 0.7467532467532467, + "grad_norm": 0.54296875, + "learning_rate": 4.181410844420473e-06, + "loss": 0.2836, + "step": 230 + }, + { + "epoch": 0.7467532467532467, + "eval_loss": 0.2885654866695404, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9437, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 230 + }, + { + "epoch": 0.75, + "grad_norm": 0.58203125, + "learning_rate": 4.082812674821865e-06, + "loss": 0.2882, + "step": 231 + }, + { + "epoch": 0.7532467532467533, + "grad_norm": 0.56640625, + "learning_rate": 3.9850918499812976e-06, + "loss": 0.293, + "step": 232 + }, + { + "epoch": 0.7564935064935064, + "grad_norm": 0.56640625, + "learning_rate": 3.888262859021508e-06, + "loss": 0.2818, + "step": 233 + }, + { + "epoch": 0.7597402597402597, + "grad_norm": 0.5703125, + "learning_rate": 3.7923400588325156e-06, + "loss": 0.2836, + "step": 234 + }, + { + "epoch": 0.762987012987013, + "grad_norm": 0.6015625, + "learning_rate": 3.6973376719429134e-06, + "loss": 0.2833, + "step": 235 + }, + { + "epoch": 0.7662337662337663, + "grad_norm": 0.5625, + "learning_rate": 3.6032697844110896e-06, + "loss": 0.2956, + "step": 236 + }, + { + "epoch": 0.7694805194805194, + "grad_norm": 0.578125, + "learning_rate": 3.5101503437366678e-06, + "loss": 0.288, + "step": 237 + }, + { + "epoch": 0.7727272727272727, + "grad_norm": 0.578125, + "learning_rate": 3.4179931567925216e-06, + "loss": 0.2898, + "step": 238 + }, + { + "epoch": 0.775974025974026, + "grad_norm": 0.55859375, + "learning_rate": 3.326811887777607e-06, + "loss": 0.2809, + "step": 239 + }, + { + "epoch": 0.7792207792207793, + "grad_norm": 0.546875, + "learning_rate": 3.236620056190972e-06, + "loss": 0.285, + "step": 240 + }, + { + "epoch": 0.7792207792207793, + "eval_loss": 0.2881048321723938, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9387, + "eval_samples_per_second": 11.884, + "eval_steps_per_second": 1.486, + "step": 240 + }, + { + "epoch": 0.7824675324675324, + "grad_norm": 0.56640625, + "learning_rate": 3.1474310348272084e-06, + "loss": 0.2888, + "step": 241 + }, + { + "epoch": 0.7857142857142857, + "grad_norm": 0.56640625, + "learning_rate": 3.0592580477936606e-06, + "loss": 0.2875, + "step": 242 + }, + { + "epoch": 0.788961038961039, + "grad_norm": 0.5625, + "learning_rate": 2.9721141685496825e-06, + "loss": 0.2828, + "step": 243 + }, + { + "epoch": 0.7922077922077922, + "grad_norm": 0.55859375, + "learning_rate": 2.8860123179682244e-06, + "loss": 0.2866, + "step": 244 + }, + { + "epoch": 0.7954545454545454, + "grad_norm": 0.5703125, + "learning_rate": 2.8009652624200436e-06, + "loss": 0.289, + "step": 245 + }, + { + "epoch": 0.7987012987012987, + "grad_norm": 0.5625, + "learning_rate": 2.7169856118808414e-06, + "loss": 0.2832, + "step": 246 + }, + { + "epoch": 0.801948051948052, + "grad_norm": 0.56640625, + "learning_rate": 2.634085818061565e-06, + "loss": 0.2913, + "step": 247 + }, + { + "epoch": 0.8051948051948052, + "grad_norm": 0.58203125, + "learning_rate": 2.5522781725621814e-06, + "loss": 0.2917, + "step": 248 + }, + { + "epoch": 0.8084415584415584, + "grad_norm": 0.56640625, + "learning_rate": 2.471574805049206e-06, + "loss": 0.2937, + "step": 249 + }, + { + "epoch": 0.8116883116883117, + "grad_norm": 0.5625, + "learning_rate": 2.3919876814572197e-06, + "loss": 0.2932, + "step": 250 + }, + { + "epoch": 0.8116883116883117, + "eval_loss": 0.28785035014152527, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.993, + "eval_samples_per_second": 11.88, + "eval_steps_per_second": 1.486, + "step": 250 + }, + { + "epoch": 0.814935064935065, + "grad_norm": 0.56640625, + "learning_rate": 2.3135286022146785e-06, + "loss": 0.2973, + "step": 251 + }, + { + "epoch": 0.8181818181818182, + "grad_norm": 0.5703125, + "learning_rate": 2.2362092004942583e-06, + "loss": 0.2862, + "step": 252 + }, + { + "epoch": 0.8214285714285714, + "grad_norm": 0.57421875, + "learning_rate": 2.1600409404879875e-06, + "loss": 0.279, + "step": 253 + }, + { + "epoch": 0.8246753246753247, + "grad_norm": 0.55859375, + "learning_rate": 2.08503511570746e-06, + "loss": 0.2844, + "step": 254 + }, + { + "epoch": 0.827922077922078, + "grad_norm": 0.5546875, + "learning_rate": 2.0112028473093294e-06, + "loss": 0.2792, + "step": 255 + }, + { + "epoch": 0.8311688311688312, + "grad_norm": 0.5703125, + "learning_rate": 1.9385550824463727e-06, + "loss": 0.2921, + "step": 256 + }, + { + "epoch": 0.8344155844155844, + "grad_norm": 0.5625, + "learning_rate": 1.8671025926443464e-06, + "loss": 0.2891, + "step": 257 + }, + { + "epoch": 0.8376623376623377, + "grad_norm": 0.5625, + "learning_rate": 1.7968559722048906e-06, + "loss": 0.2848, + "step": 258 + }, + { + "epoch": 0.8409090909090909, + "grad_norm": 0.55078125, + "learning_rate": 1.7278256366347034e-06, + "loss": 0.2921, + "step": 259 + }, + { + "epoch": 0.8441558441558441, + "grad_norm": 0.56640625, + "learning_rate": 1.660021821101222e-06, + "loss": 0.2907, + "step": 260 + }, + { + "epoch": 0.8441558441558441, + "eval_loss": 0.2877131402492523, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.008, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 260 + }, + { + "epoch": 0.8474025974025974, + "grad_norm": 0.5625, + "learning_rate": 1.5934545789150625e-06, + "loss": 0.2979, + "step": 261 + }, + { + "epoch": 0.8506493506493507, + "grad_norm": 0.5625, + "learning_rate": 1.528133780039397e-06, + "loss": 0.2847, + "step": 262 + }, + { + "epoch": 0.8538961038961039, + "grad_norm": 0.55078125, + "learning_rate": 1.4640691096265358e-06, + "loss": 0.2902, + "step": 263 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 0.5703125, + "learning_rate": 1.401270066581899e-06, + "loss": 0.2861, + "step": 264 + }, + { + "epoch": 0.8603896103896104, + "grad_norm": 0.5625, + "learning_rate": 1.339745962155613e-06, + "loss": 0.2823, + "step": 265 + }, + { + "epoch": 0.8636363636363636, + "grad_norm": 0.5703125, + "learning_rate": 1.279505918561923e-06, + "loss": 0.2855, + "step": 266 + }, + { + "epoch": 0.8668831168831169, + "grad_norm": 0.58203125, + "learning_rate": 1.220558867626639e-06, + "loss": 0.2853, + "step": 267 + }, + { + "epoch": 0.8701298701298701, + "grad_norm": 0.5703125, + "learning_rate": 1.1629135494628097e-06, + "loss": 0.2891, + "step": 268 + }, + { + "epoch": 0.8733766233766234, + "grad_norm": 0.56640625, + "learning_rate": 1.1065785111748117e-06, + "loss": 0.2853, + "step": 269 + }, + { + "epoch": 0.8766233766233766, + "grad_norm": 0.5625, + "learning_rate": 1.051562105591082e-06, + "loss": 0.292, + "step": 270 + }, + { + "epoch": 0.8766233766233766, + "eval_loss": 0.28765836358070374, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.932, + "eval_samples_per_second": 11.885, + "eval_steps_per_second": 1.486, + "step": 270 + }, + { + "epoch": 0.8798701298701299, + "grad_norm": 0.55859375, + "learning_rate": 9.978724900256265e-07, + "loss": 0.2825, + "step": 271 + }, + { + "epoch": 0.8831168831168831, + "grad_norm": 0.5546875, + "learning_rate": 9.455176250685338e-07, + "loss": 0.2836, + "step": 272 + }, + { + "epoch": 0.8863636363636364, + "grad_norm": 0.58203125, + "learning_rate": 8.945052734056581e-07, + "loss": 0.2959, + "step": 273 + }, + { + "epoch": 0.8896103896103896, + "grad_norm": 0.57421875, + "learning_rate": 8.448429986676298e-07, + "loss": 0.3003, + "step": 274 + }, + { + "epoch": 0.8928571428571429, + "grad_norm": 0.56640625, + "learning_rate": 7.965381643084069e-07, + "loss": 0.295, + "step": 275 + }, + { + "epoch": 0.8961038961038961, + "grad_norm": 0.5625, + "learning_rate": 7.495979325134806e-07, + "loss": 0.2873, + "step": 276 + }, + { + "epoch": 0.8993506493506493, + "grad_norm": 0.55078125, + "learning_rate": 7.040292631379386e-07, + "loss": 0.2827, + "step": 277 + }, + { + "epoch": 0.9025974025974026, + "grad_norm": 0.54296875, + "learning_rate": 6.598389126745209e-07, + "loss": 0.2797, + "step": 278 + }, + { + "epoch": 0.9058441558441559, + "grad_norm": 0.53125, + "learning_rate": 6.170334332518325e-07, + "loss": 0.272, + "step": 279 + }, + { + "epoch": 0.9090909090909091, + "grad_norm": 0.58203125, + "learning_rate": 5.756191716628556e-07, + "loss": 0.292, + "step": 280 + }, + { + "epoch": 0.9090909090909091, + "eval_loss": 0.28761279582977295, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9741, + "eval_samples_per_second": 11.882, + "eval_steps_per_second": 1.486, + "step": 280 + }, + { + "epoch": 0.9123376623376623, + "grad_norm": 0.5703125, + "learning_rate": 5.35602268423906e-07, + "loss": 0.2961, + "step": 281 + }, + { + "epoch": 0.9155844155844156, + "grad_norm": 0.578125, + "learning_rate": 4.969886568641757e-07, + "loss": 0.2904, + "step": 282 + }, + { + "epoch": 0.9188311688311688, + "grad_norm": 0.5625, + "learning_rate": 4.597840622459937e-07, + "loss": 0.2874, + "step": 283 + }, + { + "epoch": 0.922077922077922, + "grad_norm": 0.546875, + "learning_rate": 4.2399400091594154e-07, + "loss": 0.2794, + "step": 284 + }, + { + "epoch": 0.9253246753246753, + "grad_norm": 0.578125, + "learning_rate": 3.8962377948693395e-07, + "loss": 0.2962, + "step": 285 + }, + { + "epoch": 0.9285714285714286, + "grad_norm": 0.56640625, + "learning_rate": 3.566784940514145e-07, + "loss": 0.2914, + "step": 286 + }, + { + "epoch": 0.9318181818181818, + "grad_norm": 0.5703125, + "learning_rate": 3.2516302942574794e-07, + "loss": 0.2838, + "step": 287 + }, + { + "epoch": 0.935064935064935, + "grad_norm": 0.55859375, + "learning_rate": 2.9508205842594727e-07, + "loss": 0.2812, + "step": 288 + }, + { + "epoch": 0.9383116883116883, + "grad_norm": 0.5625, + "learning_rate": 2.6644004117483357e-07, + "loss": 0.2827, + "step": 289 + }, + { + "epoch": 0.9415584415584416, + "grad_norm": 0.5546875, + "learning_rate": 2.392412244407294e-07, + "loss": 0.2791, + "step": 290 + }, + { + "epoch": 0.9415584415584416, + "eval_loss": 0.28759849071502686, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 175.0075, + "eval_samples_per_second": 11.879, + "eval_steps_per_second": 1.486, + "step": 290 + }, + { + "epoch": 0.9448051948051948, + "grad_norm": 0.55859375, + "learning_rate": 2.1348964100778914e-07, + "loss": 0.285, + "step": 291 + }, + { + "epoch": 0.948051948051948, + "grad_norm": 0.55859375, + "learning_rate": 1.8918910907805733e-07, + "loss": 0.288, + "step": 292 + }, + { + "epoch": 0.9512987012987013, + "grad_norm": 0.57421875, + "learning_rate": 1.6634323170533928e-07, + "loss": 0.2854, + "step": 293 + }, + { + "epoch": 0.9545454545454546, + "grad_norm": 0.57421875, + "learning_rate": 1.4495539626097289e-07, + "loss": 0.2873, + "step": 294 + }, + { + "epoch": 0.9577922077922078, + "grad_norm": 0.56640625, + "learning_rate": 1.2502877393158587e-07, + "loss": 0.2841, + "step": 295 + }, + { + "epoch": 0.961038961038961, + "grad_norm": 0.62109375, + "learning_rate": 1.0656631924889749e-07, + "loss": 0.2994, + "step": 296 + }, + { + "epoch": 0.9642857142857143, + "grad_norm": 0.5546875, + "learning_rate": 8.957076965165234e-08, + "loss": 0.2797, + "step": 297 + }, + { + "epoch": 0.9675324675324676, + "grad_norm": 0.56640625, + "learning_rate": 7.404464507973608e-08, + "loss": 0.2868, + "step": 298 + }, + { + "epoch": 0.9707792207792207, + "grad_norm": 0.56640625, + "learning_rate": 5.999024760054095e-08, + "loss": 0.2867, + "step": 299 + }, + { + "epoch": 0.974025974025974, + "grad_norm": 0.56640625, + "learning_rate": 4.740966106764222e-08, + "loss": 0.2832, + "step": 300 + }, + { + "epoch": 0.974025974025974, + "eval_loss": 0.287624329328537, + "eval_model_preparation_time": 0.0003, + "eval_runtime": 174.9045, + "eval_samples_per_second": 11.886, + "eval_steps_per_second": 1.487, + "step": 300 + }, + { + "epoch": 0.9772727272727273, + "grad_norm": 0.5625, + "learning_rate": 3.630475081181861e-08, + "loss": 0.2818, + "step": 301 + }, + { + "epoch": 0.9805194805194806, + "grad_norm": 0.57421875, + "learning_rate": 2.667716336448356e-08, + "loss": 0.2874, + "step": 302 + }, + { + "epoch": 0.9837662337662337, + "grad_norm": 0.5546875, + "learning_rate": 1.8528326213548276e-08, + "loss": 0.2839, + "step": 303 + }, + { + "epoch": 0.987012987012987, + "grad_norm": 0.5625, + "learning_rate": 1.1859447591769934e-08, + "loss": 0.2911, + "step": 304 + }, + { + "epoch": 0.9902597402597403, + "grad_norm": 0.59765625, + "learning_rate": 6.671516297606095e-09, + "loss": 0.2934, + "step": 305 + }, + { + "epoch": 0.9935064935064936, + "grad_norm": 0.55859375, + "learning_rate": 2.9653015486064143e-09, + "loss": 0.287, + "step": 306 + }, + { + "epoch": 0.9967532467532467, + "grad_norm": 0.5859375, + "learning_rate": 7.413528673549941e-10, + "loss": 0.2909, + "step": 307 + }, + { + "epoch": 1.0, + "grad_norm": 0.58984375, + "learning_rate": 0.0, + "loss": 0.2824, + "step": 308 + } + ], + "logging_steps": 1, + "max_steps": 308, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.8176663382235546e+18, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-308/training_args.bin b/checkpoint-308/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..4684d3c90558d6bfde405c82b58596bc6231bfee --- /dev/null +++ b/checkpoint-308/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09f69be12f7ef607f0a1508435a517f5277e3160e5d6a59346e619fcbaa3592 +size 5176 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..de55730a672c2805e1108109d81a111b0cdb48b1 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b621112eddc9da772fae3f70d672f4d949cc5cb1d580f135d66b3836598c1a +size 915 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1007819213eaa3e36dd0c6354016734419f4a863 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7327788370b7783e29852cf19b4a1f40cd31af5962c94bba76c336d491b4169 +size 184 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..616bb67b1f5310e3c9955e638763bdeff0fb55c8 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abfe37c12d3907a891b3b7282c09590bedc9a560e05339e0aebfba26341dc1b +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c1a59736868aa002e16da3948c4b68be6d97a71 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584021d05e0ffd6879fcb1af88d896f418db0a6656a6c799d17e6a28e6540c8b +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..075dada5dcfe243936f5583203b90ba80f0935e1 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced290d33c8beefb926d706c895d70bd58e0d89ba90daca1d637367a6e9163ae +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1e38fdf23d6ff664ce00189e3dc1ab419ed8545 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03dad76ab9974b3c84fcd8067e459ff22c49e10e1408ea16637a06df0b9b71c4 +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..a054aad8cf0cb5671e2e10b3bf817725a4bec031 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..92d7fab6729d723f45689803b99006fec945cc47 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1835caa5b4d70acaa210fa222b0036f1882f9525c4660fd4810fb3e1e40ff8 +size 325 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..66cd9d7e0daec95eb10d16a63c615637dbbb7304 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4 +size 9085657 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..08ebc9598183a9a76c44ef06813aca75f51de4a5 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d0de6d831b5940c3f2eae4e495b9f77612cbb05b5804846733ab617f0dfe9b +size 55380