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:b32a6a36c81ed7387c963476e60c07e51cbf6882c1c74947ed1b4b63d0ee66b2
+oid sha256:d41d4b5f361dbc60ef8d8155275c7a44a2c5688aba411d36f758a3a3303bc1ed
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:750f472be10a69b47585c6f76583630e14566e9d9ae08bccf6129195bfdc5a83
+oid sha256:aa1277f94dc5c32b25e13808224d48c43691794b7187945f660b2802df0f9591
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039f184abf143747e61afe1d7a1a6373590e9cbf03b399216b13039ffe546270
+oid sha256:3332679b3ee88988abed35f54b3b083a6bcd3ebdd7fecb1d86b77f323c0e95f7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44a36549f56257c710ce842851141f41d8a377e3a699935a55528afc9256ba96
+oid sha256:c1b0789b2b77bd43c969ba87cf6ceaaa57a22249e28d85cae8a9ee17b8f3de72
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c38c6fabed5c6ee8982bd8c1401a4a305f4ccb5aeb65ba26a69abec40e6ce2ed
+oid sha256:1c1598e43b6ee7d5c56c6a6db6e06108c892882d222bec722cab698f7a56a63e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb1d44e3ccc0fa53e29af8e46d94bdfb8aa91234a208d081a9bfda4b139fad5
+oid sha256:a8061a24bdf81171f7f82392c73c916680fab0693c7edc1a1b97775ae29aa93e
 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": 0.34934497816593885,
+  "epoch": 0.6986899563318777,
   "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": 523.321,
       "eval_steps_per_second": 136.064,
       "step": 25
+    },
+    {
+      "epoch": 0.36331877729257644,
+      "grad_norm": 0.13174213469028473,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3622,
+      "step": 26
+    },
+    {
+      "epoch": 0.377292576419214,
+      "grad_norm": 0.13872195780277252,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3582,
+      "step": 27
+    },
+    {
+      "epoch": 0.39126637554585153,
+      "grad_norm": 0.15271404385566711,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3559,
+      "step": 28
+    },
+    {
+      "epoch": 0.4052401746724891,
+      "grad_norm": 0.1431555151939392,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3543,
+      "step": 29
+    },
+    {
+      "epoch": 0.4192139737991266,
+      "grad_norm": 0.16119669377803802,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3538,
+      "step": 30
+    },
+    {
+      "epoch": 0.4331877729257642,
+      "grad_norm": 0.1416635364294052,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3499,
+      "step": 31
+    },
+    {
+      "epoch": 0.44716157205240176,
+      "grad_norm": 0.1621275097131729,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3458,
+      "step": 32
+    },
+    {
+      "epoch": 0.4611353711790393,
+      "grad_norm": 0.1729240119457245,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3441,
+      "step": 33
+    },
+    {
+      "epoch": 0.47510917030567684,
+      "grad_norm": 0.1822398155927658,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.34,
+      "step": 34
+    },
+    {
+      "epoch": 0.4890829694323144,
+      "grad_norm": 0.1940406858921051,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3377,
+      "step": 35
+    },
+    {
+      "epoch": 0.503056768558952,
+      "grad_norm": 0.213682621717453,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3316,
+      "step": 36
+    },
+    {
+      "epoch": 0.5170305676855895,
+      "grad_norm": 0.27538955211639404,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3291,
+      "step": 37
+    },
+    {
+      "epoch": 0.5310043668122271,
+      "grad_norm": 0.12671859562397003,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3527,
+      "step": 38
+    },
+    {
+      "epoch": 0.5449781659388646,
+      "grad_norm": 0.14045991003513336,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3548,
+      "step": 39
+    },
+    {
+      "epoch": 0.5589519650655022,
+      "grad_norm": 0.13294897973537445,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3545,
+      "step": 40
+    },
+    {
+      "epoch": 0.5729257641921397,
+      "grad_norm": 0.1276903599500656,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.35,
+      "step": 41
+    },
+    {
+      "epoch": 0.5868995633187772,
+      "grad_norm": 0.13368958234786987,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3532,
+      "step": 42
+    },
+    {
+      "epoch": 0.6008733624454149,
+      "grad_norm": 0.14260563254356384,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.348,
+      "step": 43
+    },
+    {
+      "epoch": 0.6148471615720524,
+      "grad_norm": 0.17048144340515137,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3475,
+      "step": 44
+    },
+    {
+      "epoch": 0.62882096069869,
+      "grad_norm": 0.15034472942352295,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3471,
+      "step": 45
+    },
+    {
+      "epoch": 0.6427947598253275,
+      "grad_norm": 0.17590156197547913,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3427,
+      "step": 46
+    },
+    {
+      "epoch": 0.6567685589519651,
+      "grad_norm": 0.17019419372081757,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3399,
+      "step": 47
+    },
+    {
+      "epoch": 0.6707423580786026,
+      "grad_norm": 0.18595226109027863,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3372,
+      "step": 48
+    },
+    {
+      "epoch": 0.6847161572052402,
+      "grad_norm": 0.24787795543670654,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3311,
+      "step": 49
+    },
+    {
+      "epoch": 0.6986899563318777,
+      "grad_norm": 0.3069895803928375,
+      "learning_rate": 1e-05,
+      "loss": 10.3215,
+      "step": 50
+    },
+    {
+      "epoch": 0.6986899563318777,
+      "eval_loss": 10.34473991394043,
+      "eval_runtime": 0.1073,
+      "eval_samples_per_second": 465.881,
+      "eval_steps_per_second": 121.129,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null