Upload folder using huggingface_hub

.gitattributes

@@ -83,3 +83,4 @@ checkpoints-d2.0-t1/checkpoint-17408/eval_state.json filter=lfs diff=lfs merge=l
 checkpoints-d1.3/checkpoint-21504/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-d1.4/checkpoint-20480/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-d3.0/checkpoint-21504/eval_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoints-d3.1/checkpoint-8192/eval_state.json filter=lfs diff=lfs merge=lfs -text

checkpoints-d3.1/checkpoint-8192/eval_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f908e8d74cbb91f5a64c3c6374940831bd52c60bc495cdc3f8f18634f8f260
+size 49040731

checkpoints-d3.1/checkpoint-8192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e555e4249466e23cf780a02565a4d9858f9752130d0da1cc375cc8999a71e5
+size 32318104

checkpoints-d3.1/checkpoint-8192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2d823e33982673a2c6ff40a3445039e3a0892c1cc75f2660853e3289530179
+size 10010635

checkpoints-d3.1/checkpoint-8192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2614a8364df2314827788266204194df25ce233cbf5d026bdc717b2dab088e6
+size 14645

checkpoints-d3.1/checkpoint-8192/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63797d41b8e8000087d2cb16938b6d93a4a808721fe3acbfc105c9bb8b262526
+size 1383

checkpoints-d3.1/checkpoint-8192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633f4a51e3130420dcf105f63b87d79cc31db8e4efd560f5f6c0e0209526c2e9
+size 1465

checkpoints-d3.1/checkpoint-8192/trainer_state.json

@@ -0,0 +1,394 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.37836589533970716,
+  "eval_steps": 1024,
+  "global_step": 8192,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011823934229365849,
+      "grad_norm": 0.0007770129013806581,
+      "learning_rate": 0.000498046875,
+      "loss": 0.638597846031189,
+      "step": 256
+    },
+    {
+      "epoch": 0.023647868458731697,
+      "grad_norm": 0.0036502168513834476,
+      "learning_rate": 0.000998046875,
+      "loss": 0.6255820393562317,
+      "step": 512
+    },
+    {
+      "epoch": 0.03547180268809755,
+      "grad_norm": 0.00819552130997181,
+      "learning_rate": 0.000999640996023194,
+      "loss": 0.5880061388015747,
+      "step": 768
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "grad_norm": 0.014988946728408337,
+      "learning_rate": 0.0009985588674043958,
+      "loss": 0.5405965447425842,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.020278462916643203,
+      "eval_ce_loss": 0.4954925418988755,
+      "eval_loss": 0.4954925418988755,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.020278462916643203,
+      "eval_ce_loss": 0.4954925418988755,
+      "eval_loss": 0.4954925418988755,
+      "eval_runtime": 131.1195,
+      "eval_samples_per_second": 213.492,
+      "eval_steps_per_second": 3.34,
+      "step": 1024
+    },
+    {
+      "epoch": 0.05911967114682925,
+      "grad_norm": 0.018301010131835938,
+      "learning_rate": 0.0009967551747861387,
+      "loss": 0.4193720519542694,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0709436053761951,
+      "grad_norm": 0.02350299246609211,
+      "learning_rate": 0.000994232528651847,
+      "loss": 0.32118111848831177,
+      "step": 1536
+    },
+    {
+      "epoch": 0.08276753960556095,
+      "grad_norm": 0.024243628606200218,
+      "learning_rate": 0.0009909945800260092,
+      "loss": 0.27625754475593567,
+      "step": 1792
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "grad_norm": 0.022370202466845512,
+      "learning_rate": 0.0009870460151900522,
+      "loss": 0.25225532054901123,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.16173067052738044,
+      "eval_ce_loss": 0.24119392792655997,
+      "eval_loss": 0.24119392792655997,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.16173067052738044,
+      "eval_ce_loss": 0.24119392792655997,
+      "eval_loss": 0.24119392792655997,
+      "eval_runtime": 124.4827,
+      "eval_samples_per_second": 224.875,
+      "eval_steps_per_second": 3.519,
+      "step": 2048
+    },
+    {
+      "epoch": 0.10641540806429264,
+      "grad_norm": 0.025183985009789467,
+      "learning_rate": 0.0009823925488998885,
+      "loss": 0.23278099298477173,
+      "step": 2304
+    },
+    {
+      "epoch": 0.1182393422936585,
+      "grad_norm": 0.025138691067695618,
+      "learning_rate": 0.0009770409161149525,
+      "loss": 0.21929927170276642,
+      "step": 2560
+    },
+    {
+      "epoch": 0.13006327652302435,
+      "grad_norm": 0.02561408467590809,
+      "learning_rate": 0.0009709988622506973,
+      "loss": 0.20501913130283356,
+      "step": 2816
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "grad_norm": 0.028821036219596863,
+      "learning_rate": 0.000964275131968659,
+      "loss": 0.19426275789737701,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.19048343372542764,
+      "eval_ce_loss": 0.18918462373214226,
+      "eval_loss": 0.18918462373214226,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.19048343372542764,
+      "eval_ce_loss": 0.18918462373214226,
+      "eval_loss": 0.18918462373214226,
+      "eval_runtime": 125.1618,
+      "eval_samples_per_second": 223.654,
+      "eval_steps_per_second": 3.499,
+      "step": 3072
+    },
+    {
+      "epoch": 0.15371114498175603,
+      "grad_norm": 0.030421536415815353,
+      "learning_rate": 0.0009568794565203123,
+      "loss": 0.1839032918214798,
+      "step": 3328
+    },
+    {
+      "epoch": 0.1655350792111219,
+      "grad_norm": 0.032538577914237976,
+      "learning_rate": 0.0009488225396630347,
+      "loss": 0.17660538852214813,
+      "step": 3584
+    },
+    {
+      "epoch": 0.17735901344048774,
+      "grad_norm": 0.030282698571681976,
+      "learning_rate": 0.0009401160421685646,
+      "loss": 0.1695183515548706,
+      "step": 3840
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "grad_norm": 0.029157549142837524,
+      "learning_rate": 0.0009307725649463714,
+      "loss": 0.16315339505672455,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.20316795180629035,
+      "eval_ce_loss": 0.16114722188885353,
+      "eval_loss": 0.16114722188885353,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.20316795180629035,
+      "eval_ce_loss": 0.16114722188885353,
+      "eval_loss": 0.16114722188885353,
+      "eval_runtime": 124.8908,
+      "eval_samples_per_second": 224.14,
+      "eval_steps_per_second": 3.507,
+      "step": 4096
+    },
+    {
+      "epoch": 0.20100688189921945,
+      "grad_norm": 0.033927738666534424,
+      "learning_rate": 0.0009208056308063659,
+      "loss": 0.15908151865005493,
+      "step": 4352
+    },
+    {
+      "epoch": 0.2128308161285853,
+      "grad_norm": 0.037180621176958084,
+      "learning_rate": 0.0009102296648873445,
+      "loss": 0.15225762128829956,
+      "step": 4608
+    },
+    {
+      "epoch": 0.22465475035795113,
+      "grad_norm": 0.037015024572610855,
+      "learning_rate": 0.0008990599737794927,
+      "loss": 0.1476851999759674,
+      "step": 4864
+    },
+    {
+      "epoch": 0.236478684587317,
+      "grad_norm": 0.03508929908275604,
+      "learning_rate": 0.0008873127233711644,
+      "loss": 0.14329124987125397,
+      "step": 5120
+    },
+    {
+      "epoch": 0.236478684587317,
+      "eval_bleu": 0.21566794230701403,
+      "eval_ce_loss": 0.14114715776418987,
+      "eval_loss": 0.14114715776418987,
+      "step": 5120
+    },
+    {
+      "epoch": 0.236478684587317,
+      "eval_bleu": 0.21566794230701403,
+      "eval_ce_loss": 0.14114715776418987,
+      "eval_loss": 0.14114715776418987,
+      "eval_runtime": 125.5711,
+      "eval_samples_per_second": 222.926,
+      "eval_steps_per_second": 3.488,
+      "step": 5120
+    },
+    {
+      "epoch": 0.24830261881668284,
+      "grad_norm": 0.03854870796203613,
+      "learning_rate": 0.0008750049154520011,
+      "loss": 0.14005360007286072,
+      "step": 5376
+    },
+    {
+      "epoch": 0.2601265530460487,
+      "grad_norm": 0.03188326954841614,
+      "learning_rate": 0.0008621543631062487,
+      "loss": 0.13561338186264038,
+      "step": 5632
+    },
+    {
+      "epoch": 0.27195048727541454,
+      "grad_norm": 0.03463684767484665,
+      "learning_rate": 0.0008487796649318904,
+      "loss": 0.1329711377620697,
+      "step": 5888
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "grad_norm": 0.0358298160135746,
+      "learning_rate": 0.0008349001781229053,
+      "loss": 0.1301661729812622,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "eval_bleu": 0.22173654323693984,
+      "eval_ce_loss": 0.12855397619000852,
+      "eval_loss": 0.12855397619000852,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "eval_bleu": 0.22173654323693984,
+      "eval_ce_loss": 0.12855397619000852,
+      "eval_loss": 0.12855397619000852,
+      "eval_runtime": 126.9306,
+      "eval_samples_per_second": 220.538,
+      "eval_steps_per_second": 3.451,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2955983557341462,
+      "grad_norm": 0.037201233208179474,
+      "learning_rate": 0.0008205359904536107,
+      "loss": 0.1271919459104538,
+      "step": 6400
+    },
+    {
+      "epoch": 0.30742228996351206,
+      "grad_norm": 0.0340813584625721,
+      "learning_rate": 0.0008057078912056363,
+      "loss": 0.12491822242736816,
+      "step": 6656
+    },
+    {
+      "epoch": 0.3192462241928779,
+      "grad_norm": 0.031119871884584427,
+      "learning_rate": 0.0007904373410796086,
+      "loss": 0.12252337485551834,
+      "step": 6912
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "grad_norm": 0.036261022090911865,
+      "learning_rate": 0.0007747464411350876,
+      "loss": 0.12051380425691605,
+      "step": 7168
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "eval_bleu": 0.228738826346753,
+      "eval_ce_loss": 0.12006643695169933,
+      "eval_loss": 0.12006643695169933,
+      "step": 7168
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "eval_bleu": 0.228738826346753,
+      "eval_ce_loss": 0.12006643695169933,
+      "eval_loss": 0.12006643695169933,
+      "eval_runtime": 128.0461,
+      "eval_samples_per_second": 218.617,
+      "eval_steps_per_second": 3.421,
+      "step": 7168
+    },
+    {
+      "epoch": 0.34289409265160964,
+      "grad_norm": 0.03925757110118866,
+      "learning_rate": 0.000758657900803716,
+      "loss": 0.11830627918243408,
+      "step": 7424
+    },
+    {
+      "epoch": 0.3547180268809755,
+      "grad_norm": 0.03783626854419708,
+      "learning_rate": 0.000742195005021869,
+      "loss": 0.11684451997280121,
+      "step": 7680
+    },
+    {
+      "epoch": 0.3665419611103413,
+      "grad_norm": 0.04456119239330292,
+      "learning_rate": 0.0007253815805303786,
+      "loss": 0.11479435861110687,
+      "step": 7936
+    },
+    {
+      "epoch": 0.37836589533970716,
+      "grad_norm": 0.0406075082719326,
+      "learning_rate": 0.0007082419613901028,
+      "loss": 0.11298805475234985,
+      "step": 8192
+    },
+    {
+      "epoch": 0.37836589533970716,
+      "eval_bleu": 0.23316787828393487,
+      "eval_ce_loss": 0.11301100160501319,
+      "eval_loss": 0.11301100160501319,
+      "step": 8192
+    },
+    {
+      "epoch": 0.37836589533970716,
+      "eval_bleu": 0.23316787828393487,
+      "eval_ce_loss": 0.11301100160501319,
+      "eval_loss": 0.11301100160501319,
+      "eval_runtime": 129.7081,
+      "eval_samples_per_second": 215.815,
+      "eval_steps_per_second": 3.377,
+      "step": 8192
+    }
+  ],
+  "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-d3.1/checkpoint-8192/training_args.bin

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