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:eb071da5e3217b9fd947cfd8f6dc01ce0a729256daaf7d01131729bfc26bcd72
+oid sha256:2c6cc79c2e454f91fb611560404d0ca95cca230d6ebea162ef87b52ba87a3d41
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c148d03b0a1b67ca6cd2df999c87473cddf22f9548df8120a39af899255ef47a
+oid sha256:1d671e5d3229c2be2a2b47bfa1d64e4dc5b904b38f9e364f095704d02be644d5
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b15a65d3c6f2ee78ae4227603d65cdd4407fda8f3e048a5d0c2c1306a7f0bee
+oid sha256:9b62bf246872f7aa12deffa48ad505f9e39dd3908c25eec65f6fac2d3e0890aa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e57f661ef7b85a2b8b02022db3e2d94e9eb2664fc5afb9a2d0ce6dee2ff3d6
+oid sha256:5a640109ec8ad53f014f9d54cda47c4ba5cbc2f810299c640f62a888e89af352
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e6403c79db29fbde6d73186ef5ce40818270effb331d8edfff87a1cc2eda7d
+oid sha256:7d78fadaebe26e7f10b2f8ae27c2b5edfa0b8ee9b3310aab4741b1b6a0d5682c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac31dd946ad96a69d9269203d48e3a772518ef8770dd5f1e9ea6da08ee3398c
+oid sha256:a793fca8bdf7bc6f15fd3aff1d58caf30c99e51c13d957de4443e4b07aefe7ea
 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": 0.20110608345902464,
+  "epoch": 0.4022121669180493,
   "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": 10.532,
       "eval_steps_per_second": 2.738,
       "step": 25
+    },
+    {
+      "epoch": 0.20915032679738563,
+      "grad_norm": 115.21060943603516,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 41.097,
+      "step": 26
+    },
+    {
+      "epoch": 0.2171945701357466,
+      "grad_norm": 158.0090789794922,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 39.4104,
+      "step": 27
+    },
+    {
+      "epoch": 0.2252388134741076,
+      "grad_norm": 111.7906723022461,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 37.6126,
+      "step": 28
+    },
+    {
+      "epoch": 0.23328305681246858,
+      "grad_norm": 123.39836883544922,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 37.3962,
+      "step": 29
+    },
+    {
+      "epoch": 0.24132730015082957,
+      "grad_norm": 124.10353088378906,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 40.8343,
+      "step": 30
+    },
+    {
+      "epoch": 0.24937154348919055,
+      "grad_norm": 106.123291015625,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 39.4761,
+      "step": 31
+    },
+    {
+      "epoch": 0.2574157868275515,
+      "grad_norm": 96.61071014404297,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 37.6884,
+      "step": 32
+    },
+    {
+      "epoch": 0.2654600301659125,
+      "grad_norm": 123.42510986328125,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 36.3759,
+      "step": 33
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 88.63697814941406,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 36.8431,
+      "step": 34
+    },
+    {
+      "epoch": 0.2815485168426345,
+      "grad_norm": 169.19483947753906,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 36.3033,
+      "step": 35
+    },
+    {
+      "epoch": 0.2895927601809955,
+      "grad_norm": 86.78917694091797,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 38.7072,
+      "step": 36
+    },
+    {
+      "epoch": 0.29763700351935646,
+      "grad_norm": 83.58650207519531,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 37.9871,
+      "step": 37
+    },
+    {
+      "epoch": 0.30568124685771747,
+      "grad_norm": 88.43095397949219,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 35.836,
+      "step": 38
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 229.8590850830078,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 39.1167,
+      "step": 39
+    },
+    {
+      "epoch": 0.32176973353443944,
+      "grad_norm": 111.63166046142578,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 36.3088,
+      "step": 40
+    },
+    {
+      "epoch": 0.3298139768728004,
+      "grad_norm": 229.4169158935547,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 35.0117,
+      "step": 41
+    },
+    {
+      "epoch": 0.3378582202111614,
+      "grad_norm": 140.18325805664062,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 38.5012,
+      "step": 42
+    },
+    {
+      "epoch": 0.34590246354952237,
+      "grad_norm": 83.29537200927734,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 36.7094,
+      "step": 43
+    },
+    {
+      "epoch": 0.3539467068878834,
+      "grad_norm": 79.36915588378906,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 37.5578,
+      "step": 44
+    },
+    {
+      "epoch": 0.36199095022624433,
+      "grad_norm": 145.71937561035156,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 37.3472,
+      "step": 45
+    },
+    {
+      "epoch": 0.37003519356460535,
+      "grad_norm": 83.54203796386719,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 38.3822,
+      "step": 46
+    },
+    {
+      "epoch": 0.3780794369029663,
+      "grad_norm": 81.59954071044922,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 36.0854,
+      "step": 47
+    },
+    {
+      "epoch": 0.3861236802413273,
+      "grad_norm": 90.07756042480469,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 36.0527,
+      "step": 48
+    },
+    {
+      "epoch": 0.3941679235796883,
+      "grad_norm": 94.21563720703125,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 36.8875,
+      "step": 49
+    },
+    {
+      "epoch": 0.4022121669180493,
+      "grad_norm": 99.66661834716797,
+      "learning_rate": 1e-05,
+      "loss": 35.0076,
+      "step": 50
+    },
+    {
+      "epoch": 0.4022121669180493,
+      "eval_loss": 1.1387280225753784,
+      "eval_runtime": 4.7523,
+      "eval_samples_per_second": 10.521,
+      "eval_steps_per_second": 2.736,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null