Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76c41cd80ccb78c2dda0283816e1476bc531ac0af1905f3746d3338baa0abef9
+oid sha256:92c490e967b7119a0e36e68d0b26f2ec37e439bebbdf164c80ea3a8c9ad34666
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce50f133972be3040bdfbcc18edec5c417eb189b0b38eac50f5d90a8326bf30
+oid sha256:c15227ccd4f1351f53154f0368325b03c3d8a408344160275b1672bfacf502a0
 size 646253418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d2d2c09fbb026b2f24b81f380ba988d6ff2abd15e55c75d11df6ffa23fadb5
+oid sha256:22e687eca9242b0f07b1c65b3c119842dd73d6da9e5ce8c58393f98399a9c55d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
+oid sha256:0f6003820aa1d9b0e6aa1d70309948568223b16abb8759408bc4ed8976518161
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03003453972067878,
+  "epoch": 0.04505180958101817,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 9.645,
       "eval_steps_per_second": 4.829,
       "step": 50
+    },
+    {
+      "epoch": 0.030635230515092357,
+      "grad_norm": 2.3707706928253174,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.1888,
+      "step": 51
+    },
+    {
+      "epoch": 0.03123592130950593,
+      "grad_norm": 5.998414039611816,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 1.524,
+      "step": 52
+    },
+    {
+      "epoch": 0.031836612103919505,
+      "grad_norm": 5.471394062042236,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 0.873,
+      "step": 53
+    },
+    {
+      "epoch": 0.03243730289833308,
+      "grad_norm": 3.3917829990386963,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.2994,
+      "step": 54
+    },
+    {
+      "epoch": 0.03303799369274666,
+      "grad_norm": 9.54757022857666,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 1.9844,
+      "step": 55
+    },
+    {
+      "epoch": 0.03363868448716023,
+      "grad_norm": 8.63792896270752,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 1.3101,
+      "step": 56
+    },
+    {
+      "epoch": 0.03423937528157381,
+      "grad_norm": 7.494466304779053,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 1.4655,
+      "step": 57
+    },
+    {
+      "epoch": 0.034840066075987386,
+      "grad_norm": 8.181656837463379,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 1.1139,
+      "step": 58
+    },
+    {
+      "epoch": 0.03544075687040096,
+      "grad_norm": 5.95154333114624,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.7435,
+      "step": 59
+    },
+    {
+      "epoch": 0.036041447664814534,
+      "grad_norm": 5.259947299957275,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.2991,
+      "step": 60
+    },
+    {
+      "epoch": 0.03664213845922811,
+      "grad_norm": 6.347657203674316,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 1.0288,
+      "step": 61
+    },
+    {
+      "epoch": 0.03724282925364169,
+      "grad_norm": 17.088783264160156,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 1.2506,
+      "step": 62
+    },
+    {
+      "epoch": 0.03784352004805527,
+      "grad_norm": 18.076190948486328,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.8921,
+      "step": 63
+    },
+    {
+      "epoch": 0.03844421084246884,
+      "grad_norm": 18.846956253051758,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 0.656,
+      "step": 64
+    },
+    {
+      "epoch": 0.039044901636882415,
+      "grad_norm": 12.805015563964844,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 1.0612,
+      "step": 65
+    },
+    {
+      "epoch": 0.03964559243129599,
+      "grad_norm": 15.975397109985352,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.4972,
+      "step": 66
+    },
+    {
+      "epoch": 0.04024628322570956,
+      "grad_norm": 6.866183757781982,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.2505,
+      "step": 67
+    },
+    {
+      "epoch": 0.04084697402012314,
+      "grad_norm": 7.4063849449157715,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 1.6947,
+      "step": 68
+    },
+    {
+      "epoch": 0.04144766481453672,
+      "grad_norm": 5.28386116027832,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.8198,
+      "step": 69
+    },
+    {
+      "epoch": 0.042048355608950296,
+      "grad_norm": 6.2205376625061035,
+      "learning_rate": 5.925998220016659e-07,
+      "loss": 0.7195,
+      "step": 70
+    },
+    {
+      "epoch": 0.042649046403363866,
+      "grad_norm": 3.0729503631591797,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.15,
+      "step": 71
+    },
+    {
+      "epoch": 0.043249737197777444,
+      "grad_norm": 4.537116050720215,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.631,
+      "step": 72
+    },
+    {
+      "epoch": 0.04385042799219102,
+      "grad_norm": 5.137740612030029,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 0.5103,
+      "step": 73
+    },
+    {
+      "epoch": 0.0444511187866046,
+      "grad_norm": 7.137504577636719,
+      "learning_rate": 2.3794460453555047e-08,
+      "loss": 0.9672,
+      "step": 74
+    },
+    {
+      "epoch": 0.04505180958101817,
+      "grad_norm": 6.272600173950195,
+      "learning_rate": 0.0,
+      "loss": 0.7572,
+      "step": 75
+    },
+    {
+      "epoch": 0.04505180958101817,
+      "eval_loss": 0.7467929124832153,
+      "eval_runtime": 72.7355,
+      "eval_samples_per_second": 9.638,
+      "eval_steps_per_second": 4.826,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.51503621554176e+16,
+  "total_flos": 5.27255432331264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null