Upload folder using huggingface_hub

.gitattributes

@@ -77,3 +77,4 @@ checkpoints-d1.0/checkpoint-10240/eval_state.json filter=lfs diff=lfs merge=lfs
 checkpoints-d1.1/checkpoint-11264/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-d1.2/checkpoint-20480/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v1.1-d/checkpoint-21504/eval_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoints-d2.0/checkpoint-7168/eval_state.json filter=lfs diff=lfs merge=lfs -text

checkpoints-d2.0/checkpoint-7168/eval_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bbb25f41a655486399046613f82c90c51a3200d15f202e2ad01c8945feab8b0
+size 42265624

checkpoints-d2.0/checkpoint-7168/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b5a2c9f1cb6ae40cc36bfd0b5828f6658ccfe016c588215d988afbc2f307ca
+size 32318104

checkpoints-d2.0/checkpoint-7168/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd233c107be00fb07859cc302e683e7971dbc7a1441cd47117478adee47982a
+size 10010635

checkpoints-d2.0/checkpoint-7168/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a50212d8b4c61fced38c742cff6d1d65f088bf9da8cc2dbccf102e22efb215
+size 14645

checkpoints-d2.0/checkpoint-7168/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d595dc04756955b718dbe40e12e3b42e9a74ec09bbdeec39a22714665de3cd13
+size 1383

checkpoints-d2.0/checkpoint-7168/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f972816bb88a166bd6aef3c4de4da0eb09b504222e799309ef64727152d8b4
+size 1465

checkpoints-d2.0/checkpoint-7168/trainer_state.json

@@ -0,0 +1,349 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3310701584222438,
+  "eval_steps": 1024,
+  "global_step": 7168,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011823934229365849,
+      "grad_norm": 0.526302695274353,
+      "learning_rate": 0.000498046875,
+      "loss": 9.227896690368652,
+      "step": 256
+    },
+    {
+      "epoch": 0.023647868458731697,
+      "grad_norm": 0.40557485818862915,
+      "learning_rate": 0.000998046875,
+      "loss": 6.491486072540283,
+      "step": 512
+    },
+    {
+      "epoch": 0.03547180268809755,
+      "grad_norm": 0.2611554265022278,
+      "learning_rate": 0.000999640996023194,
+      "loss": 3.871699333190918,
+      "step": 768
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "grad_norm": 0.3245032727718353,
+      "learning_rate": 0.0009985588674043958,
+      "loss": 2.9131131172180176,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.37680876061744384,
+      "eval_ce_loss": 2.7332340827271273,
+      "eval_loss": 2.7332340827271273,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.37680876061744384,
+      "eval_ce_loss": 2.7332340827271273,
+      "eval_loss": 2.7332340827271273,
+      "eval_runtime": 123.8633,
+      "eval_samples_per_second": 225.999,
+      "eval_steps_per_second": 3.536,
+      "step": 1024
+    },
+    {
+      "epoch": 0.05911967114682925,
+      "grad_norm": 0.40771251916885376,
+      "learning_rate": 0.0009967551747861387,
+      "loss": 2.60915207862854,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0709436053761951,
+      "grad_norm": 0.456460177898407,
+      "learning_rate": 0.000994232528651847,
+      "loss": 2.4321346282958984,
+      "step": 1536
+    },
+    {
+      "epoch": 0.08276753960556095,
+      "grad_norm": 0.583853542804718,
+      "learning_rate": 0.0009909945800260092,
+      "loss": 2.3184077739715576,
+      "step": 1792
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "grad_norm": 0.4923252463340759,
+      "learning_rate": 0.0009870460151900522,
+      "loss": 2.2322187423706055,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.44342304632288854,
+      "eval_ce_loss": 2.180436749164372,
+      "eval_loss": 2.180436749164372,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.44342304632288854,
+      "eval_ce_loss": 2.180436749164372,
+      "eval_loss": 2.180436749164372,
+      "eval_runtime": 112.2247,
+      "eval_samples_per_second": 249.437,
+      "eval_steps_per_second": 3.903,
+      "step": 2048
+    },
+    {
+      "epoch": 0.10641540806429264,
+      "grad_norm": 0.4688430726528168,
+      "learning_rate": 0.0009823925488998885,
+      "loss": 2.177077531814575,
+      "step": 2304
+    },
+    {
+      "epoch": 0.1182393422936585,
+      "grad_norm": 0.559630274772644,
+      "learning_rate": 0.0009770409161149525,
+      "loss": 2.114898920059204,
+      "step": 2560
+    },
+    {
+      "epoch": 0.13006327652302435,
+      "grad_norm": 0.5434157848358154,
+      "learning_rate": 0.0009709988622506973,
+      "loss": 2.0660085678100586,
+      "step": 2816
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "grad_norm": 0.6108939051628113,
+      "learning_rate": 0.000964275131968659,
+      "loss": 2.0337276458740234,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.45990036074581603,
+      "eval_ce_loss": 2.022843875841463,
+      "eval_loss": 2.022843875841463,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.45990036074581603,
+      "eval_ce_loss": 2.022843875841463,
+      "eval_loss": 2.022843875841463,
+      "eval_runtime": 115.2151,
+      "eval_samples_per_second": 242.963,
+      "eval_steps_per_second": 3.802,
+      "step": 3072
+    },
+    {
+      "epoch": 0.15371114498175603,
+      "grad_norm": 0.784342348575592,
+      "learning_rate": 0.0009568794565203123,
+      "loss": 2.0136122703552246,
+      "step": 3328
+    },
+    {
+      "epoch": 0.1655350792111219,
+      "grad_norm": 0.5167074203491211,
+      "learning_rate": 0.0009488225396630347,
+      "loss": 1.9863924980163574,
+      "step": 3584
+    },
+    {
+      "epoch": 0.17735901344048774,
+      "grad_norm": 0.6403853297233582,
+      "learning_rate": 0.0009401160421685646,
+      "loss": 1.9703547954559326,
+      "step": 3840
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "grad_norm": 0.5935908555984497,
+      "learning_rate": 0.0009307725649463714,
+      "loss": 1.9429030418395996,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.47210647699382713,
+      "eval_ce_loss": 1.938350352522445,
+      "eval_loss": 1.938350352522445,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.47210647699382713,
+      "eval_ce_loss": 1.938350352522445,
+      "eval_loss": 1.938350352522445,
+      "eval_runtime": 115.0632,
+      "eval_samples_per_second": 243.284,
+      "eval_steps_per_second": 3.807,
+      "step": 4096
+    },
+    {
+      "epoch": 0.20100688189921945,
+      "grad_norm": 0.6215645670890808,
+      "learning_rate": 0.0009208056308063659,
+      "loss": 1.93471097946167,
+      "step": 4352
+    },
+    {
+      "epoch": 0.2128308161285853,
+      "grad_norm": 0.6367761492729187,
+      "learning_rate": 0.0009102296648873445,
+      "loss": 1.9198952913284302,
+      "step": 4608
+    },
+    {
+      "epoch": 0.22465475035795113,
+      "grad_norm": 0.686975359916687,
+      "learning_rate": 0.0008990599737794927,
+      "loss": 1.905943512916565,
+      "step": 4864
+    },
+    {
+      "epoch": 0.236478684587317,
+      "grad_norm": 0.5950681567192078,
+      "learning_rate": 0.0008873127233711644,
+      "loss": 1.8912562131881714,
+      "step": 5120
+    },
+    {
+      "epoch": 0.236478684587317,
+      "eval_bleu": 0.4805682328833919,
+      "eval_ce_loss": 1.8848687097362187,
+      "eval_loss": 1.8848687097362187,
+      "step": 5120
+    },
+    {
+      "epoch": 0.236478684587317,
+      "eval_bleu": 0.4805682328833919,
+      "eval_ce_loss": 1.8848687097362187,
+      "eval_loss": 1.8848687097362187,
+      "eval_runtime": 115.9176,
+      "eval_samples_per_second": 241.49,
+      "eval_steps_per_second": 3.779,
+      "step": 5120
+    },
+    {
+      "epoch": 0.24830261881668284,
+      "grad_norm": 0.5887701511383057,
+      "learning_rate": 0.0008750049154520011,
+      "loss": 1.868552327156067,
+      "step": 5376
+    },
+    {
+      "epoch": 0.2601265530460487,
+      "grad_norm": 0.6690143942832947,
+      "learning_rate": 0.0008621543631062487,
+      "loss": 1.8647550344467163,
+      "step": 5632
+    },
+    {
+      "epoch": 0.27195048727541454,
+      "grad_norm": 0.6140768527984619,
+      "learning_rate": 0.0008487796649318904,
+      "loss": 1.8564214706420898,
+      "step": 5888
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "grad_norm": 0.720294713973999,
+      "learning_rate": 0.0008349001781229053,
+      "loss": 1.852386236190796,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "eval_bleu": 0.48331258984762954,
+      "eval_ce_loss": 1.8427181676642534,
+      "eval_loss": 1.8427181676642534,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "eval_bleu": 0.48331258984762954,
+      "eval_ce_loss": 1.8427181676642534,
+      "eval_loss": 1.8427181676642534,
+      "eval_runtime": 114.2068,
+      "eval_samples_per_second": 245.108,
+      "eval_steps_per_second": 3.835,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2955983557341462,
+      "grad_norm": 0.6018796563148499,
+      "learning_rate": 0.0008205359904536107,
+      "loss": 1.8348900079727173,
+      "step": 6400
+    },
+    {
+      "epoch": 0.30742228996351206,
+      "grad_norm": 0.5634647607803345,
+      "learning_rate": 0.0008057078912056363,
+      "loss": 1.8397186994552612,
+      "step": 6656
+    },
+    {
+      "epoch": 0.3192462241928779,
+      "grad_norm": 0.7408234477043152,
+      "learning_rate": 0.0007904373410796086,
+      "loss": 1.8375225067138672,
+      "step": 6912
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "grad_norm": 0.7126314043998718,
+      "learning_rate": 0.0007747464411350876,
+      "loss": 1.8180835247039795,
+      "step": 7168
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "eval_bleu": 0.4866456652902785,
+      "eval_ce_loss": 1.8144619418605823,
+      "eval_loss": 1.8144619418605823,
+      "step": 7168
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "eval_bleu": 0.4866456652902785,
+      "eval_ce_loss": 1.8144619418605823,
+      "eval_loss": 1.8144619418605823,
+      "eval_runtime": 113.3842,
+      "eval_samples_per_second": 246.886,
+      "eval_steps_per_second": 3.863,
+      "step": 7168
+    }
+  ],
+  "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-d2.0/checkpoint-7168/training_args.bin

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