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:c6d05a09290e08374ba471884c0ee6e1ac03bb5db58669cae1a410f49cb1fdd2
+oid sha256:0f07f53588e51f38743190f04977460e90472f441f86f11d0316279112c49bd4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b861e65db7e13b9bb0b6916a9106be085e299f76d798c6908b3c36ddf04aae
+oid sha256:85882e52a84d3d037db3444bd0614a90f8a932e802ac241fb01e3c623663aaee
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e309f5ce24036f3e6dfbcef1917f6169844aee863fe7def3368b41adabbc042
+oid sha256:125e06bc6886fe16739325d4827ddfdb2a79ab0b603a75168c11ddc9e965ab31
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006775483758953696,
+  "epoch": 0.000846935469869212,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,92 @@
       "eval_samples_per_second": 9.692,
       "eval_steps_per_second": 4.846,
       "step": 40
+    },
+    {
+      "epoch": 0.0006944870852927538,
+      "grad_norm": 17.339757919311523,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 14.7313,
+      "step": 41
+    },
+    {
+      "epoch": 0.000711425794690138,
+      "grad_norm": 15.278409957885742,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 14.637,
+      "step": 42
+    },
+    {
+      "epoch": 0.0007283645040875223,
+      "grad_norm": 15.347859382629395,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 16.3984,
+      "step": 43
+    },
+    {
+      "epoch": 0.0007453032134849065,
+      "grad_norm": 15.566729545593262,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 15.9272,
+      "step": 44
+    },
+    {
+      "epoch": 0.0007622419228822908,
+      "grad_norm": 15.312088012695312,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 14.5249,
+      "step": 45
+    },
+    {
+      "epoch": 0.0007622419228822908,
+      "eval_loss": 2.008061170578003,
+      "eval_runtime": 5125.393,
+      "eval_samples_per_second": 9.7,
+      "eval_steps_per_second": 4.85,
+      "step": 45
+    },
+    {
+      "epoch": 0.000779180632279675,
+      "grad_norm": 18.034000396728516,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 16.604,
+      "step": 46
+    },
+    {
+      "epoch": 0.0007961193416770592,
+      "grad_norm": 25.57406997680664,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 19.8734,
+      "step": 47
+    },
+    {
+      "epoch": 0.0008130580510744435,
+      "grad_norm": 15.575130462646484,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 15.871,
+      "step": 48
+    },
+    {
+      "epoch": 0.0008299967604718277,
+      "grad_norm": 21.707000732421875,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 16.6486,
+      "step": 49
+    },
+    {
+      "epoch": 0.000846935469869212,
+      "grad_norm": 19.565614700317383,
+      "learning_rate": 0.0,
+      "loss": 14.055,
+      "step": 50
+    },
+    {
+      "epoch": 0.000846935469869212,
+      "eval_loss": 2.0067672729492188,
+      "eval_runtime": 5122.5703,
+      "eval_samples_per_second": 9.705,
+      "eval_steps_per_second": 4.853,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -373,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.608543315034112e+16,
+  "total_flos": 7.01067914379264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null