Add files using upload-large-folder tool

base/90e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a01e727182477329f5946ae902cc50991e34f121483318dbf8492e657da769
+size 995642298

base/90e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326975747dd10edc351c77c4095432ea4cdd92399819fc8bb79b275ff9bc369c
+size 995642298

base/90e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d33d981a37d1abfad5e29b1f00037cc6404c57d6d56aa237bb4cec0e9a844f2
+size 995642298

dedup/100e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92300d7a3bad92d9904d90834f6c83b0c6f70ed3e4e6849f08380c48bfc7fa97
+size 995642298

dedup/100e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948360e282e7f958a2fcd78d2482ce0208dd207ef5c28494de90ded0dae40ece
+size 995642298

dedup/100e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5de43972f24f10f40468a233efffefa201cebdf9969dbe48fbd8e56cbb0d0d
+size 497774208

dedup/100e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bcfe7397088392531e03d6af7f83ce02629ecc6ee33c6959623b01aa7ba930f
+size 995642298

dedup/10e1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451185845a1f087cb86c4315046a11958e9a8a2a5053227e4a80c93983dce59f
+size 497774208

dedup/10e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68cda1faefde111cb760cf99e5d7ec87352da749467a5f0fcd5bec88eca9513b
+size 995642298

dedup/10e1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5270b66746ccf1e310349359cd6cc2841c679918c7fa9177182c8b4ff76c9b8
+size 14244

dedup/10e1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/10e2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6f03cd4f37cf911eaa2289dd37698c4c250a876c2e66899f349e79a7af37e1
+size 497774208

dedup/10e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1d9fd80f0a793e04d35b463d46f7f3d5c17dc3cb2c9456582c6835dc04e643
+size 995642298

dedup/10e2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16c436c2a396e9b92acfb8b4fe8eae48f04f44470e4c6bf754220c1572ee337
+size 14244

dedup/10e2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b5d9ba0556334c5e06c979f040b262cf4898d7fb64f0ddf7faa4cbff9c0b65
+size 1064

dedup/10e2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/10e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb4427e038932c9e07bf994f9726fbea6e24fa789f1dd02fd6ce44411d12302
+size 497774208

dedup/10e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9f1606a2364e403e35b72c8aae0eb4b6ec1a1e07450df7ce1584f761fe09b4
+size 995642298

dedup/10e3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a009c06f2be7b1db2b751740be33385cf45a1a9df812b331861a34d496259ab0
+size 14244

dedup/10e3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:753da20ffcc126b018a4c3122211c879a9f5f19dbdfffb5ab6156e6be76561bb
+size 1064

dedup/10e3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/110e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3760613ac6909723e392b6f11871d3bab00619385e0f0a8494d1332ef4ca0ba
+size 497774208

dedup/110e3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63a85bc5bc0c3cc6a90fe7b7aa1266956e0a7b9fc9f4f40698e3a91241e3191
+size 14244

dedup/110e3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b86edaaff2037851d7fb99fbd109c2770e14fd3c59439d1dd73504f7c18c7b
+size 1064

dedup/110e3/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

dedup/110e3/trainer_state.json

@@ -0,0 +1,565 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 38058,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03941352672237112,
+      "grad_norm": 9.434146881103516,
+      "learning_rate": 1.9840000000000003e-05,
+      "loss": 3.5972,
+      "step": 500
+    },
+    {
+      "epoch": 0.07882705344474224,
+      "grad_norm": 8.484919548034668,
+      "learning_rate": 1.973587517972203e-05,
+      "loss": 3.0731,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11824058016711335,
+      "grad_norm": 8.578750610351562,
+      "learning_rate": 1.9469620320570853e-05,
+      "loss": 2.9624,
+      "step": 1500
+    },
+    {
+      "epoch": 0.15765410688948447,
+      "grad_norm": 6.2477827072143555,
+      "learning_rate": 1.920336546141967e-05,
+      "loss": 2.8351,
+      "step": 2000
+    },
+    {
+      "epoch": 0.19706763361185559,
+      "grad_norm": 6.6669602394104,
+      "learning_rate": 1.8937110602268492e-05,
+      "loss": 2.817,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2364811603342267,
+      "grad_norm": 4.857083797454834,
+      "learning_rate": 1.8670855743117314e-05,
+      "loss": 2.7781,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2758946870565978,
+      "grad_norm": 5.961228847503662,
+      "learning_rate": 1.8404600883966135e-05,
+      "loss": 2.7681,
+      "step": 3500
+    },
+    {
+      "epoch": 0.31530821377896895,
+      "grad_norm": 3.896094560623169,
+      "learning_rate": 1.8138346024814953e-05,
+      "loss": 2.6833,
+      "step": 4000
+    },
+    {
+      "epoch": 0.35472174050134003,
+      "grad_norm": 4.19826078414917,
+      "learning_rate": 1.7872091165663774e-05,
+      "loss": 2.7317,
+      "step": 4500
+    },
+    {
+      "epoch": 0.39413526722371117,
+      "grad_norm": 4.363683223724365,
+      "learning_rate": 1.7605836306512596e-05,
+      "loss": 2.6456,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4335487939460823,
+      "grad_norm": 4.608914852142334,
+      "learning_rate": 1.7339581447361414e-05,
+      "loss": 2.6575,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4729623206684534,
+      "grad_norm": 5.031886577606201,
+      "learning_rate": 1.707332658821024e-05,
+      "loss": 2.6423,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5123758473908245,
+      "grad_norm": 4.503154277801514,
+      "learning_rate": 1.6807071729059057e-05,
+      "loss": 2.6062,
+      "step": 6500
+    },
+    {
+      "epoch": 0.5517893741131956,
+      "grad_norm": 3.5765438079833984,
+      "learning_rate": 1.654134937962618e-05,
+      "loss": 2.6487,
+      "step": 7000
+    },
+    {
+      "epoch": 0.5912029008355668,
+      "grad_norm": 3.3804619312286377,
+      "learning_rate": 1.6275094520475e-05,
+      "loss": 2.6378,
+      "step": 7500
+    },
+    {
+      "epoch": 0.6306164275579379,
+      "grad_norm": 4.173604965209961,
+      "learning_rate": 1.600883966132382e-05,
+      "loss": 2.5821,
+      "step": 8000
+    },
+    {
+      "epoch": 0.670029954280309,
+      "grad_norm": 3.0175459384918213,
+      "learning_rate": 1.5743117311890943e-05,
+      "loss": 2.5756,
+      "step": 8500
+    },
+    {
+      "epoch": 0.7094434810026801,
+      "grad_norm": 4.371723651885986,
+      "learning_rate": 1.5476862452739764e-05,
+      "loss": 2.5365,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7488570077250513,
+      "grad_norm": 3.797525644302368,
+      "learning_rate": 1.5210607593588584e-05,
+      "loss": 2.5734,
+      "step": 9500
+    },
+    {
+      "epoch": 0.7882705344474223,
+      "grad_norm": 2.7907519340515137,
+      "learning_rate": 1.4944352734437404e-05,
+      "loss": 2.5801,
+      "step": 10000
+    },
+    {
+      "epoch": 0.8276840611697934,
+      "grad_norm": 3.6856374740600586,
+      "learning_rate": 1.4678097875286225e-05,
+      "loss": 2.5198,
+      "step": 10500
+    },
+    {
+      "epoch": 0.8670975878921646,
+      "grad_norm": 3.692336320877075,
+      "learning_rate": 1.4411843016135045e-05,
+      "loss": 2.5294,
+      "step": 11000
+    },
+    {
+      "epoch": 0.9065111146145357,
+      "grad_norm": 3.4679853916168213,
+      "learning_rate": 1.4145588156983866e-05,
+      "loss": 2.5818,
+      "step": 11500
+    },
+    {
+      "epoch": 0.9459246413369068,
+      "grad_norm": 3.318463087081909,
+      "learning_rate": 1.3879333297832686e-05,
+      "loss": 2.5145,
+      "step": 12000
+    },
+    {
+      "epoch": 0.985338168059278,
+      "grad_norm": 3.9721946716308594,
+      "learning_rate": 1.361361094839981e-05,
+      "loss": 2.5793,
+      "step": 12500
+    },
+    {
+      "epoch": 1.024751694781649,
+      "grad_norm": 4.008026123046875,
+      "learning_rate": 1.3347356089248631e-05,
+      "loss": 2.4809,
+      "step": 13000
+    },
+    {
+      "epoch": 1.0641652215040203,
+      "grad_norm": 2.818800926208496,
+      "learning_rate": 1.308110123009745e-05,
+      "loss": 2.4303,
+      "step": 13500
+    },
+    {
+      "epoch": 1.1035787482263912,
+      "grad_norm": 2.989525556564331,
+      "learning_rate": 1.281484637094627e-05,
+      "loss": 2.4062,
+      "step": 14000
+    },
+    {
+      "epoch": 1.1429922749487624,
+      "grad_norm": 3.570216178894043,
+      "learning_rate": 1.2548591511795092e-05,
+      "loss": 2.4559,
+      "step": 14500
+    },
+    {
+      "epoch": 1.1824058016711336,
+      "grad_norm": 3.4571452140808105,
+      "learning_rate": 1.2282336652643912e-05,
+      "loss": 2.4451,
+      "step": 15000
+    },
+    {
+      "epoch": 1.2218193283935046,
+      "grad_norm": 3.5280067920684814,
+      "learning_rate": 1.2016081793492733e-05,
+      "loss": 2.4488,
+      "step": 15500
+    },
+    {
+      "epoch": 1.2612328551158758,
+      "grad_norm": 3.444591999053955,
+      "learning_rate": 1.1749826934341553e-05,
+      "loss": 2.4949,
+      "step": 16000
+    },
+    {
+      "epoch": 1.3006463818382468,
+      "grad_norm": 3.746109962463379,
+      "learning_rate": 1.1484104584908674e-05,
+      "loss": 2.4157,
+      "step": 16500
+    },
+    {
+      "epoch": 1.340059908560618,
+      "grad_norm": 3.2765095233917236,
+      "learning_rate": 1.1217849725757498e-05,
+      "loss": 2.442,
+      "step": 17000
+    },
+    {
+      "epoch": 1.3794734352829892,
+      "grad_norm": 3.1070899963378906,
+      "learning_rate": 1.0951594866606317e-05,
+      "loss": 2.4619,
+      "step": 17500
+    },
+    {
+      "epoch": 1.4188869620053604,
+      "grad_norm": 3.6844067573547363,
+      "learning_rate": 1.0685340007455135e-05,
+      "loss": 2.4091,
+      "step": 18000
+    },
+    {
+      "epoch": 1.4583004887277313,
+      "grad_norm": 3.408829927444458,
+      "learning_rate": 1.0419085148303958e-05,
+      "loss": 2.4427,
+      "step": 18500
+    },
+    {
+      "epoch": 1.4977140154501025,
+      "grad_norm": 3.1087682247161865,
+      "learning_rate": 1.0152830289152778e-05,
+      "loss": 2.4273,
+      "step": 19000
+    },
+    {
+      "epoch": 1.5371275421724735,
+      "grad_norm": 3.229764223098755,
+      "learning_rate": 9.886575430001598e-06,
+      "loss": 2.4041,
+      "step": 19500
+    },
+    {
+      "epoch": 1.5765410688948447,
+      "grad_norm": 2.389808416366577,
+      "learning_rate": 9.620853080568721e-06,
+      "loss": 2.4336,
+      "step": 20000
+    },
+    {
+      "epoch": 1.6159545956172159,
+      "grad_norm": 3.6460657119750977,
+      "learning_rate": 9.354598221417541e-06,
+      "loss": 2.4151,
+      "step": 20500
+    },
+    {
+      "epoch": 1.655368122339587,
+      "grad_norm": 3.6286749839782715,
+      "learning_rate": 9.088343362266362e-06,
+      "loss": 2.4395,
+      "step": 21000
+    },
+    {
+      "epoch": 1.694781649061958,
+      "grad_norm": 3.662971258163452,
+      "learning_rate": 8.822088503115182e-06,
+      "loss": 2.4143,
+      "step": 21500
+    },
+    {
+      "epoch": 1.734195175784329,
+      "grad_norm": 3.5085411071777344,
+      "learning_rate": 8.555833643964004e-06,
+      "loss": 2.4443,
+      "step": 22000
+    },
+    {
+      "epoch": 1.7736087025067002,
+      "grad_norm": 2.7148663997650146,
+      "learning_rate": 8.289578784812823e-06,
+      "loss": 2.3879,
+      "step": 22500
+    },
+    {
+      "epoch": 1.8130222292290714,
+      "grad_norm": 3.083752155303955,
+      "learning_rate": 8.023323925661643e-06,
+      "loss": 2.3917,
+      "step": 23000
+    },
+    {
+      "epoch": 1.8524357559514426,
+      "grad_norm": 3.1884474754333496,
+      "learning_rate": 7.757069066510464e-06,
+      "loss": 2.3965,
+      "step": 23500
+    },
+    {
+      "epoch": 1.8918492826738138,
+      "grad_norm": 3.8930094242095947,
+      "learning_rate": 7.490814207359285e-06,
+      "loss": 2.3829,
+      "step": 24000
+    },
+    {
+      "epoch": 1.9312628093961848,
+      "grad_norm": 3.560189723968506,
+      "learning_rate": 7.225091857926408e-06,
+      "loss": 2.3792,
+      "step": 24500
+    },
+    {
+      "epoch": 1.9706763361185557,
+      "grad_norm": 3.2734220027923584,
+      "learning_rate": 6.958836998775228e-06,
+      "loss": 2.3858,
+      "step": 25000
+    },
+    {
+      "epoch": 2.010089862840927,
+      "grad_norm": 3.381345272064209,
+      "learning_rate": 6.692582139624049e-06,
+      "loss": 2.4046,
+      "step": 25500
+    },
+    {
+      "epoch": 2.049503389563298,
+      "grad_norm": 3.241978406906128,
+      "learning_rate": 6.426327280472869e-06,
+      "loss": 2.3169,
+      "step": 26000
+    },
+    {
+      "epoch": 2.0889169162856693,
+      "grad_norm": 2.8808765411376953,
+      "learning_rate": 6.160604931039992e-06,
+      "loss": 2.3297,
+      "step": 26500
+    },
+    {
+      "epoch": 2.1283304430080405,
+      "grad_norm": 3.5440902709960938,
+      "learning_rate": 5.8943500718888125e-06,
+      "loss": 2.3492,
+      "step": 27000
+    },
+    {
+      "epoch": 2.1677439697304113,
+      "grad_norm": 2.809176206588745,
+      "learning_rate": 5.628095212737633e-06,
+      "loss": 2.3777,
+      "step": 27500
+    },
+    {
+      "epoch": 2.2071574964527825,
+      "grad_norm": 3.0675675868988037,
+      "learning_rate": 5.361840353586454e-06,
+      "loss": 2.3456,
+      "step": 28000
+    },
+    {
+      "epoch": 2.2465710231751537,
+      "grad_norm": 2.9990875720977783,
+      "learning_rate": 5.096118004153576e-06,
+      "loss": 2.3657,
+      "step": 28500
+    },
+    {
+      "epoch": 2.285984549897525,
+      "grad_norm": 3.575359582901001,
+      "learning_rate": 4.829863145002397e-06,
+      "loss": 2.3882,
+      "step": 29000
+    },
+    {
+      "epoch": 2.325398076619896,
+      "grad_norm": 3.6486237049102783,
+      "learning_rate": 4.563608285851217e-06,
+      "loss": 2.3967,
+      "step": 29500
+    },
+    {
+      "epoch": 2.3648116033422673,
+      "grad_norm": 3.3127598762512207,
+      "learning_rate": 4.297353426700038e-06,
+      "loss": 2.3611,
+      "step": 30000
+    },
+    {
+      "epoch": 2.404225130064638,
+      "grad_norm": 3.7743148803710938,
+      "learning_rate": 4.031631077267161e-06,
+      "loss": 2.3496,
+      "step": 30500
+    },
+    {
+      "epoch": 2.443638656787009,
+      "grad_norm": 3.7068562507629395,
+      "learning_rate": 3.7653762181159807e-06,
+      "loss": 2.3628,
+      "step": 31000
+    },
+    {
+      "epoch": 2.4830521835093804,
+      "grad_norm": 3.449821710586548,
+      "learning_rate": 3.4991213589648017e-06,
+      "loss": 2.3415,
+      "step": 31500
+    },
+    {
+      "epoch": 2.5224657102317516,
+      "grad_norm": 3.7589163780212402,
+      "learning_rate": 3.232866499813622e-06,
+      "loss": 2.3764,
+      "step": 32000
+    },
+    {
+      "epoch": 2.561879236954123,
+      "grad_norm": 3.74432110786438,
+      "learning_rate": 2.9671441503807445e-06,
+      "loss": 2.2692,
+      "step": 32500
+    },
+    {
+      "epoch": 2.6012927636764935,
+      "grad_norm": 3.302215576171875,
+      "learning_rate": 2.7008892912295655e-06,
+      "loss": 2.3327,
+      "step": 33000
+    },
+    {
+      "epoch": 2.6407062903988647,
+      "grad_norm": 3.3547306060791016,
+      "learning_rate": 2.4346344320783856e-06,
+      "loss": 2.3206,
+      "step": 33500
+    },
+    {
+      "epoch": 2.680119817121236,
+      "grad_norm": 2.628941059112549,
+      "learning_rate": 2.168379572927206e-06,
+      "loss": 2.3426,
+      "step": 34000
+    },
+    {
+      "epoch": 2.719533343843607,
+      "grad_norm": 3.6259102821350098,
+      "learning_rate": 1.9021247137760265e-06,
+      "loss": 2.3492,
+      "step": 34500
+    },
+    {
+      "epoch": 2.7589468705659783,
+      "grad_norm": 3.3363823890686035,
+      "learning_rate": 1.6364023643431496e-06,
+      "loss": 2.2767,
+      "step": 35000
+    },
+    {
+      "epoch": 2.7983603972883495,
+      "grad_norm": 3.094226121902466,
+      "learning_rate": 1.37014750519197e-06,
+      "loss": 2.3461,
+      "step": 35500
+    },
+    {
+      "epoch": 2.8377739240107207,
+      "grad_norm": 3.562486171722412,
+      "learning_rate": 1.1038926460407903e-06,
+      "loss": 2.3504,
+      "step": 36000
+    },
+    {
+      "epoch": 2.8771874507330915,
+      "grad_norm": 3.6450047492980957,
+      "learning_rate": 8.376377868896108e-07,
+      "loss": 2.3222,
+      "step": 36500
+    },
+    {
+      "epoch": 2.9166009774554627,
+      "grad_norm": 2.8702635765075684,
+      "learning_rate": 5.719154374567337e-07,
+      "loss": 2.3599,
+      "step": 37000
+    },
+    {
+      "epoch": 2.956014504177834,
+      "grad_norm": 3.4599852561950684,
+      "learning_rate": 3.056605783055541e-07,
+      "loss": 2.3358,
+      "step": 37500
+    },
+    {
+      "epoch": 2.995428030900205,
+      "grad_norm": 3.3014168739318848,
+      "learning_rate": 3.9405719154374576e-08,
+      "loss": 2.2861,
+      "step": 38000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 38058,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1268,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9943860215808000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

dedup/110e3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/20e1/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

dedup/20e1/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

dedup/20e1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a864bba06ca55724d213afa4cb29a4cee300aeaed524415dd12aeb93209040
+size 497774208

dedup/20e1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fe58058ff8c941a61e84cb5f17ab17bda28046c174263f7bdf63acb3406810
+size 14244

dedup/20e1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474576e7d457a349dabd5171a444c2c4ddba8677d121d8c46431e89813a81f00
+size 1064

dedup/20e1/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

dedup/20e1/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

dedup/20e1/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1999054075358663,
+  "eval_steps": 500,
+  "global_step": 2536,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03941352672237112,
+      "grad_norm": 9.434146881103516,
+      "learning_rate": 1.9840000000000003e-05,
+      "loss": 3.5972,
+      "step": 500
+    },
+    {
+      "epoch": 0.07882705344474224,
+      "grad_norm": 8.484919548034668,
+      "learning_rate": 1.973587517972203e-05,
+      "loss": 3.0731,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11824058016711335,
+      "grad_norm": 8.578750610351562,
+      "learning_rate": 1.9469620320570853e-05,
+      "loss": 2.9624,
+      "step": 1500
+    },
+    {
+      "epoch": 0.15765410688948447,
+      "grad_norm": 6.2477827072143555,
+      "learning_rate": 1.920336546141967e-05,
+      "loss": 2.8351,
+      "step": 2000
+    },
+    {
+      "epoch": 0.19706763361185559,
+      "grad_norm": 6.6669602394104,
+      "learning_rate": 1.8937110602268492e-05,
+      "loss": 2.817,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 38058,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1268,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 662636593152000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

dedup/20e1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/20e2/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

dedup/20e2/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

dedup/20e2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698237969c6e385b13df17c36e37f680171702489d047ee3a090eceaf2b14718
+size 497774208

dedup/20e2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e93217dc7f9d04879b825e535490fc2e16f80f85bb282eb45939369d6d38979
+size 14244

dedup/20e2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865f265e4ca3b3cedf43e50bfae6397071fb57b8eaedf9ab9afb0d21e5391276
+size 1064

dedup/20e2/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

dedup/20e2/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}