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:fe257bb2d320a13fb6a46e253fccc308cd41a92d980201c75431e574b0646bd0
+oid sha256:e4b221f6b66ffb9180b6c54e1dff03b69db1164be72054c8a5194cb2015bda42
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79917a945eea812fc19fc8ae9c39ab3eaa5c5b83fcad034173f526ea6cdb4fcc
+oid sha256:64d9300fd28540b4a8fe5c9acaeed33551f09155a0b7eea30f4220490937197d
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564def47bc5d4793c8b50718fc9889a4c9623488a26ef288bcdefc3877c63fff
+oid sha256:184367d15a486b9dc5528e885a06051de2e54e5682681d323bfb82f4ca550e83
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eeb7f00cb5be44af14577e01a9e226ba6490cc18b754ad7a39f10cd84bbb98b
+oid sha256:d40a356d672ecc30ea762eccca226b8b320ae068e336df06d802a629dcb349fc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8e8e811b4d8e7d256018390223607de04d56627012005e2e35362e8aa0a93f
+oid sha256:28faaa9b549e41de771d05a55c2deb3b8abe5048b001d28d03c4b606aa2bcd94
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff523f618714e646e5a5558811c6ce4f7035532fc38ad4950fae2d8f03d1fa3
+oid sha256:93245ddd6ffbe1e543a8a8c774aaef82ab27222b1c93599011f760d98a04e758
 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": 0.012520149615787908,
+  "epoch": 0.025040299231575816,
   "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": 12.471,
       "eval_steps_per_second": 3.242,
       "step": 25
+    },
+    {
+      "epoch": 0.013020955600419425,
+      "grad_norm": 12.907711029052734,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 40.5466,
+      "step": 26
+    },
+    {
+      "epoch": 0.013521761585050942,
+      "grad_norm": 14.298810958862305,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 39.6971,
+      "step": 27
+    },
+    {
+      "epoch": 0.014022567569682457,
+      "grad_norm": 8.840272903442383,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 33.8011,
+      "step": 28
+    },
+    {
+      "epoch": 0.014523373554313974,
+      "grad_norm": 8.240339279174805,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 34.7336,
+      "step": 29
+    },
+    {
+      "epoch": 0.015024179538945491,
+      "grad_norm": 7.267547607421875,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 39.301,
+      "step": 30
+    },
+    {
+      "epoch": 0.015524985523577006,
+      "grad_norm": 6.603776931762695,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 34.2265,
+      "step": 31
+    },
+    {
+      "epoch": 0.01602579150820852,
+      "grad_norm": 8.114143371582031,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 35.1166,
+      "step": 32
+    },
+    {
+      "epoch": 0.01652659749284004,
+      "grad_norm": 9.130178451538086,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 34.9486,
+      "step": 33
+    },
+    {
+      "epoch": 0.017027403477471555,
+      "grad_norm": 10.9686861038208,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 37.1661,
+      "step": 34
+    },
+    {
+      "epoch": 0.01752820946210307,
+      "grad_norm": 11.460497856140137,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 35.1148,
+      "step": 35
+    },
+    {
+      "epoch": 0.01802901544673459,
+      "grad_norm": 9.752028465270996,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 31.4821,
+      "step": 36
+    },
+    {
+      "epoch": 0.018529821431366104,
+      "grad_norm": 12.186714172363281,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 31.2477,
+      "step": 37
+    },
+    {
+      "epoch": 0.01903062741599762,
+      "grad_norm": 13.641959190368652,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 43.8177,
+      "step": 38
+    },
+    {
+      "epoch": 0.01953143340062914,
+      "grad_norm": 18.16305160522461,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 42.221,
+      "step": 39
+    },
+    {
+      "epoch": 0.020032239385260654,
+      "grad_norm": 8.292379379272461,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 33.8687,
+      "step": 40
+    },
+    {
+      "epoch": 0.02053304536989217,
+      "grad_norm": 7.936122894287109,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 30.5119,
+      "step": 41
+    },
+    {
+      "epoch": 0.021033851354523687,
+      "grad_norm": 9.7647705078125,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 34.835,
+      "step": 42
+    },
+    {
+      "epoch": 0.021534657339155203,
+      "grad_norm": 11.5134859085083,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 33.8628,
+      "step": 43
+    },
+    {
+      "epoch": 0.022035463323786718,
+      "grad_norm": 11.015727043151855,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 34.5979,
+      "step": 44
+    },
+    {
+      "epoch": 0.022536269308418237,
+      "grad_norm": 8.781559944152832,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 35.5065,
+      "step": 45
+    },
+    {
+      "epoch": 0.023037075293049752,
+      "grad_norm": 7.820028781890869,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 33.935,
+      "step": 46
+    },
+    {
+      "epoch": 0.023537881277681267,
+      "grad_norm": 6.9192352294921875,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 32.8078,
+      "step": 47
+    },
+    {
+      "epoch": 0.024038687262312786,
+      "grad_norm": 7.588488578796387,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 32.1488,
+      "step": 48
+    },
+    {
+      "epoch": 0.0245394932469443,
+      "grad_norm": 7.037163734436035,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 29.7435,
+      "step": 49
+    },
+    {
+      "epoch": 0.025040299231575816,
+      "grad_norm": 12.27120304107666,
+      "learning_rate": 1e-05,
+      "loss": 32.5584,
+      "step": 50
+    },
+    {
+      "epoch": 0.025040299231575816,
+      "eval_loss": 1.0642402172088623,
+      "eval_runtime": 3.8404,
+      "eval_samples_per_second": 13.02,
+      "eval_steps_per_second": 3.385,
+      "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": 2.9582754301188506e+17,
+  "total_flos": 5.904224712120074e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null