Upload folder using huggingface_hub

.gitattributes

@@ -113,3 +113,4 @@ checkpoints-v2.0a-discrete-condition/checkpoint-21651/eval_state.json filter=lfs
 checkpoints-v2.0b-discrete-condition/checkpoint-8192/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v2.0b-discrete-condition/checkpoint-15360/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v2.0b-discrete-condition/checkpoint-21651/eval_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoints-v2.0c-discrete-condition/checkpoint-5120/eval_state.json filter=lfs diff=lfs merge=lfs -text

checkpoints-v2.0c-discrete-condition/checkpoint-5120/eval_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a90c23039c173d5e321ad16ba151c74a3ae690f99ebeb0eecb7db1e17dd40e
+size 46059895

checkpoints-v2.0c-discrete-condition/checkpoint-5120/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523f9406c297bf15ff34d15e49ff18a23672a30f63420cc0fd486f4953a17b7a
+size 15210032

checkpoints-v2.0c-discrete-condition/checkpoint-5120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7966b2bbde1bb2e4e2dc0781dda898e23a77de803de43ba62c4e6d9c8ceea6f1
+size 13675339

checkpoints-v2.0c-discrete-condition/checkpoint-5120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13610e4928300e84a5d63b12aa084079981888dac54db7000b24c5f5e7cf131
+size 14645

checkpoints-v2.0c-discrete-condition/checkpoint-5120/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c2732f24a4ea69f3f84ae5925396a0123911f56fcc25897eca1b844b50cd340
+size 1383

checkpoints-v2.0c-discrete-condition/checkpoint-5120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b2a0161091dd5d744cc1861e533069c79034fffcaff28f3d39e1edd93159ad
+size 1465

checkpoints-v2.0c-discrete-condition/checkpoint-5120/trainer_state.json

@@ -0,0 +1,309 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.236478684587317,
+  "eval_steps": 1024,
+  "global_step": 5120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011823934229365849,
+      "grad_norm": 0.5773382782936096,
+      "learning_rate": 0.000498046875,
+      "loss": 3.839907646179199,
+      "step": 256
+    },
+    {
+      "epoch": 0.023647868458731697,
+      "grad_norm": 1.2586220502853394,
+      "learning_rate": 0.000998046875,
+      "loss": 2.8118715286254883,
+      "step": 512
+    },
+    {
+      "epoch": 0.03547180268809755,
+      "grad_norm": 1.7730108499526978,
+      "learning_rate": 0.000999640996023194,
+      "loss": 2.415459632873535,
+      "step": 768
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "grad_norm": 2.2911810874938965,
+      "learning_rate": 0.0009985588674043958,
+      "loss": 2.244023084640503,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.0009678500579046042,
+      "eval_cos0_loss": 0.3716520652787326,
+      "eval_cos_loss": 0.37628904168736443,
+      "eval_lcos_loss": 0.37847947033300794,
+      "eval_lmse_loss": 1.3972665550501924,
+      "eval_loss": 2.154246258409056,
+      "eval_mse0_loss": 1.5301919299173572,
+      "eval_mse_loss": 1.3810340264072156,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.0009678500579046042,
+      "eval_cos0_loss": 0.3716520652787326,
+      "eval_cos_loss": 0.37628904168736443,
+      "eval_lcos_loss": 0.37847947033300794,
+      "eval_lmse_loss": 1.3972665550501924,
+      "eval_loss": 2.154246258409056,
+      "eval_mse0_loss": 1.5301919299173572,
+      "eval_mse_loss": 1.3810340264072156,
+      "eval_runtime": 613.4435,
+      "eval_samples_per_second": 45.633,
+      "eval_steps_per_second": 0.714,
+      "step": 1024
+    },
+    {
+      "epoch": 0.05911967114682925,
+      "grad_norm": 1.7562695741653442,
+      "learning_rate": 0.0009967551747861387,
+      "loss": 2.1243996620178223,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0709436053761951,
+      "grad_norm": 1.6881698369979858,
+      "learning_rate": 0.000994232528651847,
+      "loss": 2.0403342247009277,
+      "step": 1536
+    },
+    {
+      "epoch": 0.08276753960556095,
+      "grad_norm": 2.1058273315429688,
+      "learning_rate": 0.0009909945800260092,
+      "loss": 1.9448120594024658,
+      "step": 1792
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "grad_norm": 2.6205785274505615,
+      "learning_rate": 0.0009870460151900522,
+      "loss": 1.8664555549621582,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.002253202053838634,
+      "eval_cos0_loss": 0.30266132699028,
+      "eval_cos_loss": 0.3371365039043775,
+      "eval_lcos_loss": 0.3387556804777825,
+      "eval_lmse_loss": 1.2267555978200206,
+      "eval_loss": 1.827787241434942,
+      "eval_mse0_loss": 1.211973919171721,
+      "eval_mse_loss": 1.2168449740431624,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.002253202053838634,
+      "eval_cos0_loss": 0.30266132699028,
+      "eval_cos_loss": 0.3371365039043775,
+      "eval_lcos_loss": 0.3387556804777825,
+      "eval_lmse_loss": 1.2267555978200206,
+      "eval_loss": 1.827787241434942,
+      "eval_mse0_loss": 1.211973919171721,
+      "eval_mse_loss": 1.2168449740431624,
+      "eval_runtime": 612.9503,
+      "eval_samples_per_second": 45.669,
+      "eval_steps_per_second": 0.715,
+      "step": 2048
+    },
+    {
+      "epoch": 0.10641540806429264,
+      "grad_norm": 2.103069305419922,
+      "learning_rate": 0.0009823925488998885,
+      "loss": 1.7817965745925903,
+      "step": 2304
+    },
+    {
+      "epoch": 0.1182393422936585,
+      "grad_norm": 2.6513352394104004,
+      "learning_rate": 0.0009770409161149525,
+      "loss": 1.700106143951416,
+      "step": 2560
+    },
+    {
+      "epoch": 0.13006327652302435,
+      "grad_norm": 2.6591241359710693,
+      "learning_rate": 0.0009709988622506973,
+      "loss": 1.6390057802200317,
+      "step": 2816
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "grad_norm": 2.2664096355438232,
+      "learning_rate": 0.000964275131968659,
+      "loss": 1.5896209478378296,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.02088055114550435,
+      "eval_cos0_loss": 0.24901231800176238,
+      "eval_cos_loss": 0.30351526511314253,
+      "eval_lcos_loss": 0.3036922022496184,
+      "eval_lmse_loss": 1.0799240483540922,
+      "eval_loss": 1.5640880138906714,
+      "eval_mse0_loss": 0.9713506719020948,
+      "eval_mse_loss": 1.0769013045313152,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.02088055114550435,
+      "eval_cos0_loss": 0.24901231800176238,
+      "eval_cos_loss": 0.30351526511314253,
+      "eval_lcos_loss": 0.3036922022496184,
+      "eval_lmse_loss": 1.0799240483540922,
+      "eval_loss": 1.5640880138906714,
+      "eval_mse0_loss": 0.9713506719020948,
+      "eval_mse_loss": 1.0769013045313152,
+      "eval_runtime": 609.2065,
+      "eval_samples_per_second": 45.95,
+      "eval_steps_per_second": 0.719,
+      "step": 3072
+    },
+    {
+      "epoch": 0.15371114498175603,
+      "grad_norm": 4.887567043304443,
+      "learning_rate": 0.0009568794565203123,
+      "loss": 1.548627495765686,
+      "step": 3328
+    },
+    {
+      "epoch": 0.1655350792111219,
+      "grad_norm": 2.5831308364868164,
+      "learning_rate": 0.0009488225396630347,
+      "loss": 1.5119283199310303,
+      "step": 3584
+    },
+    {
+      "epoch": 0.17735901344048774,
+      "grad_norm": 2.4399147033691406,
+      "learning_rate": 0.0009401160421685646,
+      "loss": 1.4889769554138184,
+      "step": 3840
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "grad_norm": 3.813706636428833,
+      "learning_rate": 0.0009307725649463714,
+      "loss": 1.4559980630874634,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.04036824125921908,
+      "eval_cos0_loss": 0.22499571029590146,
+      "eval_cos_loss": 0.2870930704760225,
+      "eval_lcos_loss": 0.28663786027801635,
+      "eval_lmse_loss": 1.0095530485725839,
+      "eval_loss": 1.4431848909756908,
+      "eval_mse0_loss": 0.8669073336744961,
+      "eval_mse_loss": 1.009909397526963,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.04036824125921908,
+      "eval_cos0_loss": 0.22499571029590146,
+      "eval_cos_loss": 0.2870930704760225,
+      "eval_lcos_loss": 0.28663786027801635,
+      "eval_lmse_loss": 1.0095530485725839,
+      "eval_loss": 1.4431848909756908,
+      "eval_mse0_loss": 0.8669073336744961,
+      "eval_mse_loss": 1.009909397526963,
+      "eval_runtime": 610.7117,
+      "eval_samples_per_second": 45.837,
+      "eval_steps_per_second": 0.717,
+      "step": 4096
+    },
+    {
+      "epoch": 0.20100688189921945,
+      "grad_norm": 2.183851957321167,
+      "learning_rate": 0.0009208056308063659,
+      "loss": 1.4380117654800415,
+      "step": 4352
+    },
+    {
+      "epoch": 0.2128308161285853,
+      "grad_norm": 2.0409207344055176,
+      "learning_rate": 0.0009102296648873445,
+      "loss": 1.4116824865341187,
+      "step": 4608
+    },
+    {
+      "epoch": 0.22465475035795113,
+      "grad_norm": 3.0817489624023438,
+      "learning_rate": 0.0008990599737794927,
+      "loss": 1.3894058465957642,
+      "step": 4864
+    },
+    {
+      "epoch": 0.236478684587317,
+      "grad_norm": 2.6919968128204346,
+      "learning_rate": 0.0008873127233711644,
+      "loss": 1.3580043315887451,
+      "step": 5120
+    },
+    {
+      "epoch": 0.236478684587317,
+      "eval_bleu": 0.05952291809050901,
+      "eval_cos0_loss": 0.20102498530661134,
+      "eval_cos_loss": 0.2724936866120661,
+      "eval_lcos_loss": 0.27243535475779884,
+      "eval_lmse_loss": 0.9554824699822082,
+      "eval_loss": 1.3415723780518798,
+      "eval_mse0_loss": 0.7718455541079448,
+      "eval_mse_loss": 0.955816726978511,
+      "step": 5120
+    },
+    {
+      "epoch": 0.236478684587317,
+      "eval_bleu": 0.05952291809050901,
+      "eval_cos0_loss": 0.20102498530661134,
+      "eval_cos_loss": 0.2724936866120661,
+      "eval_lcos_loss": 0.27243535475779884,
+      "eval_lmse_loss": 0.9554824699822082,
+      "eval_loss": 1.3415723780518798,
+      "eval_mse0_loss": 0.7718455541079448,
+      "eval_mse_loss": 0.955816726978511,
+      "eval_runtime": 608.2141,
+      "eval_samples_per_second": 46.025,
+      "eval_steps_per_second": 0.72,
+      "step": 5120
+    }
+  ],
+  "logging_steps": 256,
+  "max_steps": 21651,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1024,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints-v2.0c-discrete-condition/checkpoint-5120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63a8a711fb280c6320e95476c532b75c862f31d6a218a0d05079e32411a5ae1
+size 5201