Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d28d1d93cb365f1b1d63c7f9d6993c3a5cd4c8f6b6629f8fa8264b972b20f4f
+oid sha256:7544780b6b688de80786ccc4f1efacb9ca8575e174176f48b9c4d04d6a67e681
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34996d31417d757b16e72f2534fbb6f2c8307dddf5067c51b7aa895258bbde5d
+oid sha256:aa0f6dfd119cc33fe2bdeea47555199761e69f1f73fb4ac26788d02b38e458cc
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51101ca99b71fe8ecea9b73575d1e8ed9a01a356eb3b821a7ba84218a8b93e59
+oid sha256:afd8e10f250d5066f313d27fb98693209148cafd63ccdb7f369d3878c65c77e3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd07499a2e29da62aafe08d1c2b3c0fbbfde2b19d8a8b2390318c547314d97d
+oid sha256:26ec26e7c33a010d580dd539dae8f4819a309489be4ac7975872fd1fe217ba4b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b630b9325a618b9a18d83b0c0112023504b529629cb4c3c7b840af251149af
+oid sha256:c5c4eb625ae9319e05493220ff17b698259293cb56e7efba6abb0852a02797aa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b0c0541387cd9c96cd35835eb7cb42724a49a1fd9169b8092f804390bebc85
+oid sha256:ed59d489309ba67fcd700fa6b4fff90dd1b2c46c9f7e02d74100b001ab5c40f8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18930430667297682,
+  "epoch": 0.37860861334595364,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 15.175,
       "eval_steps_per_second": 3.946,
       "step": 25
+    },
+    {
+      "epoch": 0.19687647893989588,
+      "grad_norm": 0.5425540208816528,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.4719,
+      "step": 26
+    },
+    {
+      "epoch": 0.20444865120681496,
+      "grad_norm": 0.835626482963562,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.6482,
+      "step": 27
+    },
+    {
+      "epoch": 0.21202082347373402,
+      "grad_norm": 1.7947323322296143,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.7267,
+      "step": 28
+    },
+    {
+      "epoch": 0.2195929957406531,
+      "grad_norm": 4.438429832458496,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.6783,
+      "step": 29
+    },
+    {
+      "epoch": 0.22716516800757217,
+      "grad_norm": 4.250818252563477,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.7994,
+      "step": 30
+    },
+    {
+      "epoch": 0.23473734027449125,
+      "grad_norm": 2.890430450439453,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.8081,
+      "step": 31
+    },
+    {
+      "epoch": 0.2423095125414103,
+      "grad_norm": 2.2607815265655518,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.6962,
+      "step": 32
+    },
+    {
+      "epoch": 0.2498816848083294,
+      "grad_norm": 0.9068285822868347,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.6694,
+      "step": 33
+    },
+    {
+      "epoch": 0.2574538570752485,
+      "grad_norm": 0.7581325173377991,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.661,
+      "step": 34
+    },
+    {
+      "epoch": 0.2650260293421675,
+      "grad_norm": 0.9279335737228394,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.6437,
+      "step": 35
+    },
+    {
+      "epoch": 0.2725982016090866,
+      "grad_norm": 0.7952417731285095,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.5672,
+      "step": 36
+    },
+    {
+      "epoch": 0.2801703738760057,
+      "grad_norm": 1.2510565519332886,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.4211,
+      "step": 37
+    },
+    {
+      "epoch": 0.28774254614292477,
+      "grad_norm": 0.6021161675453186,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.4254,
+      "step": 38
+    },
+    {
+      "epoch": 0.2953147184098438,
+      "grad_norm": 0.6810365319252014,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.6075,
+      "step": 39
+    },
+    {
+      "epoch": 0.3028868906767629,
+      "grad_norm": 0.8788719177246094,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.6724,
+      "step": 40
+    },
+    {
+      "epoch": 0.310459062943682,
+      "grad_norm": 0.9619131088256836,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.647,
+      "step": 41
+    },
+    {
+      "epoch": 0.31803123521060106,
+      "grad_norm": 0.925391435623169,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.6874,
+      "step": 42
+    },
+    {
+      "epoch": 0.3256034074775201,
+      "grad_norm": 0.825603723526001,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.7573,
+      "step": 43
+    },
+    {
+      "epoch": 0.3331755797444392,
+      "grad_norm": 0.6580988764762878,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.7402,
+      "step": 44
+    },
+    {
+      "epoch": 0.34074775201135826,
+      "grad_norm": 0.567483127117157,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.6631,
+      "step": 45
+    },
+    {
+      "epoch": 0.34831992427827735,
+      "grad_norm": 0.555555522441864,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.7038,
+      "step": 46
+    },
+    {
+      "epoch": 0.3558920965451964,
+      "grad_norm": 0.7060038447380066,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.5818,
+      "step": 47
+    },
+    {
+      "epoch": 0.36346426881211547,
+      "grad_norm": 0.8900313377380371,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.5252,
+      "step": 48
+    },
+    {
+      "epoch": 0.37103644107903455,
+      "grad_norm": 1.1769415140151978,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.4474,
+      "step": 49
+    },
+    {
+      "epoch": 0.37860861334595364,
+      "grad_norm": 2.9755210876464844,
+      "learning_rate": 1e-05,
+      "loss": 2.4783,
+      "step": 50
+    },
+    {
+      "epoch": 0.37860861334595364,
+      "eval_loss": 2.5627858638763428,
+      "eval_runtime": 3.3177,
+      "eval_samples_per_second": 15.071,
+      "eval_steps_per_second": 3.918,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null