Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:966aa2eef72f7f1bf43377fa2fc305b11751d0ffe4ff9b0d9c31a525b53055c1
+oid sha256:9e4d068ad2bbd99801d9d0e72e16357ea266ba29b0e535e1b98d3182b72aaf95
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d4ee7edd1605baf69fee71f22df33f213d43d74775689908c7472beb6104d4
+oid sha256:9e2ffa5b4b5275e6845c2490878407779da9efd61d29a52a19a1d88fdd747841
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d119126267194af793d63127d10340d3f3bb4ac76d871af58281d54f59c44a0e
+oid sha256:239232cf7c5031833b038c630b77e099bb2bf58f2bd57a48368600792c74cee2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.037257824143070044,
+  "epoch": 0.07451564828614009,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 1.6416,
       "step": 25
+    },
+    {
+      "epoch": 0.038748137108792845,
+      "grad_norm": 2.1552388668060303,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.3777,
+      "step": 26
+    },
+    {
+      "epoch": 0.040238450074515646,
+      "grad_norm": 2.4514808654785156,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.3392,
+      "step": 27
+    },
+    {
+      "epoch": 0.040238450074515646,
+      "eval_loss": 1.2882710695266724,
+      "eval_runtime": 2.7452,
+      "eval_samples_per_second": 205.816,
+      "eval_steps_per_second": 25.864,
+      "step": 27
+    },
+    {
+      "epoch": 0.041728763040238454,
+      "grad_norm": 2.4231464862823486,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.3952,
+      "step": 28
+    },
+    {
+      "epoch": 0.043219076005961254,
+      "grad_norm": 2.0393948554992676,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.1851,
+      "step": 29
+    },
+    {
+      "epoch": 0.044709388971684055,
+      "grad_norm": 1.9575780630111694,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.1068,
+      "step": 30
+    },
+    {
+      "epoch": 0.046199701937406856,
+      "grad_norm": 1.8777871131896973,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.0618,
+      "step": 31
+    },
+    {
+      "epoch": 0.04769001490312966,
+      "grad_norm": 2.131181001663208,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.9559,
+      "step": 32
+    },
+    {
+      "epoch": 0.04918032786885246,
+      "grad_norm": 2.0089690685272217,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.903,
+      "step": 33
+    },
+    {
+      "epoch": 0.05067064083457526,
+      "grad_norm": 1.756807565689087,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.8165,
+      "step": 34
+    },
+    {
+      "epoch": 0.05216095380029806,
+      "grad_norm": 2.0079643726348877,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.8495,
+      "step": 35
+    },
+    {
+      "epoch": 0.05365126676602087,
+      "grad_norm": 2.026780366897583,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.8717,
+      "step": 36
+    },
+    {
+      "epoch": 0.05365126676602087,
+      "eval_loss": 0.7020303606987,
+      "eval_runtime": 2.7139,
+      "eval_samples_per_second": 208.188,
+      "eval_steps_per_second": 26.162,
+      "step": 36
+    },
+    {
+      "epoch": 0.05514157973174367,
+      "grad_norm": 2.029473304748535,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.6712,
+      "step": 37
+    },
+    {
+      "epoch": 0.05663189269746647,
+      "grad_norm": 1.649437427520752,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.6271,
+      "step": 38
+    },
+    {
+      "epoch": 0.05812220566318927,
+      "grad_norm": 1.7296348810195923,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.714,
+      "step": 39
+    },
+    {
+      "epoch": 0.05961251862891207,
+      "grad_norm": 1.313446044921875,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.5392,
+      "step": 40
+    },
+    {
+      "epoch": 0.06110283159463487,
+      "grad_norm": 1.2067147493362427,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.5773,
+      "step": 41
+    },
+    {
+      "epoch": 0.06259314456035768,
+      "grad_norm": 1.3863986730575562,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.5832,
+      "step": 42
+    },
+    {
+      "epoch": 0.06408345752608048,
+      "grad_norm": 1.4204689264297485,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.4459,
+      "step": 43
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 1.5218064785003662,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.6278,
+      "step": 44
+    },
+    {
+      "epoch": 0.06706408345752608,
+      "grad_norm": 1.6203991174697876,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.4472,
+      "step": 45
+    },
+    {
+      "epoch": 0.06706408345752608,
+      "eval_loss": 0.4401513338088989,
+      "eval_runtime": 2.6576,
+      "eval_samples_per_second": 212.596,
+      "eval_steps_per_second": 26.716,
+      "step": 45
+    },
+    {
+      "epoch": 0.06855439642324888,
+      "grad_norm": 1.0682734251022339,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.3199,
+      "step": 46
+    },
+    {
+      "epoch": 0.07004470938897168,
+      "grad_norm": 1.1575658321380615,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.3394,
+      "step": 47
+    },
+    {
+      "epoch": 0.07153502235469449,
+      "grad_norm": 1.2181802988052368,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.3898,
+      "step": 48
+    },
+    {
+      "epoch": 0.07302533532041729,
+      "grad_norm": 1.1372705698013306,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.468,
+      "step": 49
+    },
+    {
+      "epoch": 0.07451564828614009,
+      "grad_norm": 0.888025164604187,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.3541,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 347093965209600.0,
+  "total_flos": 694187930419200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null