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:cbfbbcf254b2c7dd3341bc482e9b23158b506f080293f9683e47915f3a22781c
+oid sha256:d33f501d6826cdb1550c4047433f980b1760d6fa6fe2c870db51d5297b14b93e
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6f0e6a22914176983ceac42f5e62ebf5f04a5a29ec1633e6fee6f1f0efd6fb4
+oid sha256:7f24db99ea590cbfae7026e72cb2bbb29319134bc65940848a54d3c5a3dc26d2
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7808cb0e7a9a53a55f7fc8ff3859ecc608ae873365de5169023497dec309097d
+oid sha256:3cc99e3c86c23bc06f9edea71bf79408a653efdd9c70206d352ea0930325b808
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace7d9261627dad8e5d02bdc95c3c7010f9df4e690a32a20b33f20a891f4c4ca
+oid sha256:6046da47f7977c6bfabb64b81914420e9038822db7731d6904a5269fcfa7e2cd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f293953cd9c8d20980a81ca205850f530e5f87f87de2b74a3378d562e2b0c3
+oid sha256:c8df66b253ef810988ddc8e8c4e4e2efef8a63ac11c44f55dc4f06eefe917ade
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435337fa7b08c4a9d2acfe9f9ad384ae20707bb4dd0c64b16c7ea7133d22f7b8
+oid sha256:85a63a38f235517d88c6bd233439c6b41f0fc62393792fec98812a0a99d51488
 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": 0.34873583260680036,
+  "epoch": 0.6974716652136007,
   "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": 24.112,
       "eval_steps_per_second": 6.269,
       "step": 25
+    },
+    {
+      "epoch": 0.36268526591107236,
+      "grad_norm": 3.976642370223999,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.4711,
+      "step": 26
+    },
+    {
+      "epoch": 0.37663469921534437,
+      "grad_norm": 4.475371360778809,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.4931,
+      "step": 27
+    },
+    {
+      "epoch": 0.3905841325196164,
+      "grad_norm": 4.376916885375977,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.662,
+      "step": 28
+    },
+    {
+      "epoch": 0.4045335658238884,
+      "grad_norm": 3.5628089904785156,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.5019,
+      "step": 29
+    },
+    {
+      "epoch": 0.4184829991281604,
+      "grad_norm": 3.14534854888916,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.5237,
+      "step": 30
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 2.6178762912750244,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.405,
+      "step": 31
+    },
+    {
+      "epoch": 0.44638186573670446,
+      "grad_norm": 2.1331136226654053,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.1528,
+      "step": 32
+    },
+    {
+      "epoch": 0.46033129904097647,
+      "grad_norm": 1.9061111211776733,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.347,
+      "step": 33
+    },
+    {
+      "epoch": 0.4742807323452485,
+      "grad_norm": 1.8948556184768677,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.0309,
+      "step": 34
+    },
+    {
+      "epoch": 0.4882301656495205,
+      "grad_norm": 2.3290843963623047,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.1429,
+      "step": 35
+    },
+    {
+      "epoch": 0.5021795989537925,
+      "grad_norm": 3.0071651935577393,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.8502,
+      "step": 36
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 3.767021656036377,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.8187,
+      "step": 37
+    },
+    {
+      "epoch": 0.5300784655623365,
+      "grad_norm": 1.1453721523284912,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.0583,
+      "step": 38
+    },
+    {
+      "epoch": 0.5440278988666085,
+      "grad_norm": 1.1263549327850342,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.1802,
+      "step": 39
+    },
+    {
+      "epoch": 0.5579773321708805,
+      "grad_norm": 1.0567845106124878,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.1979,
+      "step": 40
+    },
+    {
+      "epoch": 0.5719267654751525,
+      "grad_norm": 1.0829411745071411,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.2523,
+      "step": 41
+    },
+    {
+      "epoch": 0.5858761987794245,
+      "grad_norm": 1.121140480041504,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.27,
+      "step": 42
+    },
+    {
+      "epoch": 0.5998256320836965,
+      "grad_norm": 1.2229188680648804,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.193,
+      "step": 43
+    },
+    {
+      "epoch": 0.6137750653879687,
+      "grad_norm": 1.2727962732315063,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.2052,
+      "step": 44
+    },
+    {
+      "epoch": 0.6277244986922407,
+      "grad_norm": 1.4603536128997803,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.1933,
+      "step": 45
+    },
+    {
+      "epoch": 0.6416739319965127,
+      "grad_norm": 1.4937858581542969,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.0251,
+      "step": 46
+    },
+    {
+      "epoch": 0.6556233653007847,
+      "grad_norm": 1.6102039813995361,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.0256,
+      "step": 47
+    },
+    {
+      "epoch": 0.6695727986050567,
+      "grad_norm": 1.9616433382034302,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.9568,
+      "step": 48
+    },
+    {
+      "epoch": 0.6835222319093287,
+      "grad_norm": 2.3991916179656982,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.7399,
+      "step": 49
+    },
+    {
+      "epoch": 0.6974716652136007,
+      "grad_norm": 4.19977331161499,
+      "learning_rate": 1e-05,
+      "loss": 3.6125,
+      "step": 50
+    },
+    {
+      "epoch": 0.6974716652136007,
+      "eval_loss": 4.018064022064209,
+      "eval_runtime": 2.0767,
+      "eval_samples_per_second": 24.076,
+      "eval_steps_per_second": 6.26,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null