Upload folder using huggingface_hub

.gitattributes

@@ -65,3 +65,4 @@ checkpoints-v4.6+/checkpoint-13312/eval_state.json filter=lfs diff=lfs merge=lfs
 checkpoints-v4.6+/checkpoint-21504/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v5.13-c/checkpoint-11264/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v5.14/checkpoint-10240/eval_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoints-v4.6++/checkpoint-2048/eval_state.json filter=lfs diff=lfs merge=lfs -text

checkpoints-v4.6++/checkpoint-2048/ema.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bdff309bd047c91d9b6671dfb9d7b2f2b808a46882009dba72d085b5a92df1
+size 38935592

checkpoints-v4.6++/checkpoint-2048/eval_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632517e00ede0e1a2e94500d2d4e86519ce04c3e07c3f9e30850069167feca12
+size 39791814

checkpoints-v4.6++/checkpoint-2048/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64638beed5584019875fbd782ed10233b20546e16122693ed527f522f52cf402
+size 38935624

checkpoints-v4.6++/checkpoint-2048/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f135a5b597697e4cc529a861cb514bdf8b0a9fd41daa1793546ed5e29ea6751d
+size 77992907

checkpoints-v4.6++/checkpoint-2048/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56cb8a202825f8743a844d6de68716c8837a3b477ac198c9013f94969712b7ab
+size 14645

checkpoints-v4.6++/checkpoint-2048/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1fbd7e12410fdb6bb0abd3113128f3412b14ebe6a73178008f5074beadf68a
+size 1383

checkpoints-v4.6++/checkpoint-2048/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e5169df8f19b5f61983e59731c271cd9fb32c9037d1353a686cddf2dfd24d1
+size 1465

checkpoints-v4.6++/checkpoint-2048/trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.09459147383492679,
+  "eval_steps": 1024,
+  "global_step": 2048,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011823934229365849,
+      "grad_norm": 1.715803623199463,
+      "learning_rate": 0.000498046875,
+      "loss": 6.464813709259033,
+      "step": 256
+    },
+    {
+      "epoch": 0.023647868458731697,
+      "grad_norm": 1.6022182703018188,
+      "learning_rate": 0.000998046875,
+      "loss": 0.8224233388900757,
+      "step": 512
+    },
+    {
+      "epoch": 0.03547180268809755,
+      "grad_norm": 0.9533795714378357,
+      "learning_rate": 0.000999640996023194,
+      "loss": 0.3635375201702118,
+      "step": 768
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "grad_norm": 1.1098988056182861,
+      "learning_rate": 0.0009985588674043958,
+      "loss": 0.2704107463359833,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.3167128854088453,
+      "eval_ce_loss": 3.634030068846054,
+      "eval_cos_loss": 0.05990104354305627,
+      "eval_loss": 0.24878976892118584,
+      "eval_mse_loss": 0.11673666375208663,
+      "eval_rec_loss": 0.01704210073147054,
+      "flow/cos_sim": 0.9400989716727984,
+      "flow/improvement_ratio": 0.9788048792647445,
+      "flow/mag_ratio_mean": 0.9418843064678314,
+      "flow/mag_ratio_std": 0.1509957370182423,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.3167128854088453,
+      "eval_ce_loss": 3.634030068846054,
+      "eval_cos_loss": 0.05990104354305627,
+      "eval_loss": 0.24878976892118584,
+      "eval_mse_loss": 0.11673666375208663,
+      "eval_rec_loss": 0.01704210073147054,
+      "eval_runtime": 142.3025,
+      "eval_samples_per_second": 196.715,
+      "eval_steps_per_second": 3.078,
+      "flow/cos_sim": 0.9400989716727984,
+      "flow/improvement_ratio": 0.9788048792647445,
+      "flow/mag_ratio_mean": 0.9418843064678314,
+      "flow/mag_ratio_std": 0.1509957370182423,
+      "step": 1024
+    },
+    {
+      "epoch": 0.05911967114682925,
+      "grad_norm": 0.6174790859222412,
+      "learning_rate": 0.0009967551747861387,
+      "loss": 0.24305246770381927,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0709436053761951,
+      "grad_norm": 0.410963773727417,
+      "learning_rate": 0.000994232528651847,
+      "loss": 0.22739820182323456,
+      "step": 1536
+    },
+    {
+      "epoch": 0.08276753960556095,
+      "grad_norm": 0.6567087173461914,
+      "learning_rate": 0.0009909945800260092,
+      "loss": 0.21308675408363342,
+      "step": 1792
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "grad_norm": 0.4822954833507538,
+      "learning_rate": 0.0009870460151900522,
+      "loss": 0.2054595947265625,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.34012205471606577,
+      "eval_ce_loss": 3.195375862731237,
+      "eval_cos_loss": 0.05082051334349804,
+      "eval_loss": 0.20106960652761807,
+      "eval_mse_loss": 0.09635995549562315,
+      "eval_rec_loss": 0.0037663264811936274,
+      "flow/cos_sim": 0.9491795030630887,
+      "flow/improvement_ratio": 0.9779014392802704,
+      "flow/mag_ratio_mean": 0.9552222135132307,
+      "flow/mag_ratio_std": 0.10944377392802608,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.34012205471606577,
+      "eval_ce_loss": 3.195375862731237,
+      "eval_cos_loss": 0.05082051334349804,
+      "eval_loss": 0.20106960652761807,
+      "eval_mse_loss": 0.09635995549562315,
+      "eval_rec_loss": 0.0037663264811936274,
+      "eval_runtime": 140.8597,
+      "eval_samples_per_second": 198.73,
+      "eval_steps_per_second": 3.109,
+      "flow/cos_sim": 0.9491795030630887,
+      "flow/improvement_ratio": 0.9779014392802704,
+      "flow/mag_ratio_mean": 0.9552222135132307,
+      "flow/mag_ratio_std": 0.10944377392802608,
+      "step": 2048
+    }
+  ],
+  "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-v4.6++/checkpoint-2048/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a16bb839f687414b8e48611327c4b9cfddeefe38c031ca70808f9a97c476b7
+size 5137