Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de76b5b5cad9b4e3b60620c8f4f947060b37fc321cd3715d41684f723b0c91a
+oid sha256:bb018a6bc89d37a9785dcf2ef98350b6ba5ebebe161449113ff51d9761fd10a5
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257974e900d8399af4fb854c26ebd36ea08082bc5ac030a718f6525c5c238ab9
+oid sha256:548f4c683499e56024c573e7d4234e8720f1693dd95d21f979396a61096d82ba
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb9955c0207bd5d1c6d3af9509ac14a015ee9cf72249d8bfe0cc55e85840133
+oid sha256:7d76914e2a837166eb9627083b3a984601a67ecae80a4d6f5c196fb10e037ca3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382818626a39df1b36d8be3c8fe8590184c2c1a2f6b5f3c41cd7c4bd7ac720bd
+oid sha256:5987a52817fab6ff4139e5b0d8a0cde25043cfeaac1214b82073a20521a1cd5a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bae60e025e270392f16d2dc2d3aa60542f4354db7fcda0bd12428acb4f8fe568
+oid sha256:04a3ed833ab6da1d976e5718f3eeb51cb8b34c39442de590182d6cd58a54b180
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2acf4a09e3f831dfb0f4d9e9af942f1c4329ea44e69c09fd9ba59f0618e6554f
+oid sha256:87c3caa5fb63121a9740ab1573407e712d12e6ea8b3872a9262cd074299383c9
 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": 0.37825059101654845,
+  "epoch": 0.7565011820330969,
   "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": 247.551,
       "eval_steps_per_second": 64.363,
       "step": 25
+    },
+    {
+      "epoch": 0.3933806146572104,
+      "grad_norm": 0.011090955697000027,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9304,
+      "step": 26
+    },
+    {
+      "epoch": 0.4085106382978723,
+      "grad_norm": 0.011664253659546375,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9306,
+      "step": 27
+    },
+    {
+      "epoch": 0.4236406619385343,
+      "grad_norm": 0.014071961864829063,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9306,
+      "step": 28
+    },
+    {
+      "epoch": 0.43877068557919624,
+      "grad_norm": 0.013513321988284588,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9313,
+      "step": 29
+    },
+    {
+      "epoch": 0.45390070921985815,
+      "grad_norm": 0.01655971258878708,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9318,
+      "step": 30
+    },
+    {
+      "epoch": 0.4690307328605201,
+      "grad_norm": 0.014017711393535137,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9305,
+      "step": 31
+    },
+    {
+      "epoch": 0.484160756501182,
+      "grad_norm": 0.011544297449290752,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9314,
+      "step": 32
+    },
+    {
+      "epoch": 0.49929078014184397,
+      "grad_norm": 0.012642547488212585,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9314,
+      "step": 33
+    },
+    {
+      "epoch": 0.5144208037825059,
+      "grad_norm": 0.01794467680156231,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9302,
+      "step": 34
+    },
+    {
+      "epoch": 0.5295508274231678,
+      "grad_norm": 0.013963800854980946,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9299,
+      "step": 35
+    },
+    {
+      "epoch": 0.5446808510638298,
+      "grad_norm": 0.021733710542321205,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9303,
+      "step": 36
+    },
+    {
+      "epoch": 0.5598108747044918,
+      "grad_norm": 0.02163160964846611,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9305,
+      "step": 37
+    },
+    {
+      "epoch": 0.5749408983451537,
+      "grad_norm": 0.014926633797585964,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9306,
+      "step": 38
+    },
+    {
+      "epoch": 0.5900709219858156,
+      "grad_norm": 0.015309125185012817,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9299,
+      "step": 39
+    },
+    {
+      "epoch": 0.6052009456264775,
+      "grad_norm": 0.01804831251502037,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9294,
+      "step": 40
+    },
+    {
+      "epoch": 0.6203309692671395,
+      "grad_norm": 0.017892878502607346,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9306,
+      "step": 41
+    },
+    {
+      "epoch": 0.6354609929078014,
+      "grad_norm": 0.016832858324050903,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9301,
+      "step": 42
+    },
+    {
+      "epoch": 0.6505910165484634,
+      "grad_norm": 0.020296163856983185,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9303,
+      "step": 43
+    },
+    {
+      "epoch": 0.6657210401891253,
+      "grad_norm": 0.018417399376630783,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9303,
+      "step": 44
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.018799107521772385,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9308,
+      "step": 45
+    },
+    {
+      "epoch": 0.6959810874704492,
+      "grad_norm": 0.01869620941579342,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9309,
+      "step": 46
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0199186522513628,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9309,
+      "step": 47
+    },
+    {
+      "epoch": 0.7262411347517731,
+      "grad_norm": 0.01802201010286808,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9306,
+      "step": 48
+    },
+    {
+      "epoch": 0.741371158392435,
+      "grad_norm": 0.015932127833366394,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9317,
+      "step": 49
+    },
+    {
+      "epoch": 0.7565011820330969,
+      "grad_norm": 0.021696912124753,
+      "learning_rate": 1e-05,
+      "loss": 11.9307,
+      "step": 50
+    },
+    {
+      "epoch": 0.7565011820330969,
+      "eval_loss": 11.932082176208496,
+      "eval_runtime": 0.2066,
+      "eval_samples_per_second": 242.043,
+      "eval_steps_per_second": 62.931,
+      "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": 531183403008.0,
+  "total_flos": 1064973041664.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null