Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ddc5e416a5be2984403244c1cab04a8cbac41160d406ab34957b2e037f6f794
+oid sha256:d8c08146f638d13aa11f36e93f1859d3fa0904a980861e95ae768fa3c32b521e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:609710b5877c5480f547b51e50baf1ca76d7b83fb0de0b7b75219e6653aeaaed
+oid sha256:9e4947aa85e83026d231fab92a6d3a561070053b326742e0b2838fae6e377366
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df89e2660d2a9d2299b1971cbc4628c847fcf59b72c1eefdf6cbee9186f3a0fc
+oid sha256:1062d30bb4ef9b33fcf8c7797e4c20ed9f500422012ab5879dc42554a9c3f139
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5112a8e43e7928d17d47d188e0b6c8bbe9afb80131d6b2265ec546d867784d
+oid sha256:7de55ee15c3cd129cb71af9f4022fb91e841dde31069a141e76369a166ffc5e0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803a6ddac39dfaea7714c2e7f90e21af8fc6d0b78803b6b60a6d92af1c804fed
+oid sha256:3f1a329a4ec18798da8cb5080bf3f3a2d9f3f3248825c58eda272a0e8f8f4b18
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c25d63454b7676ca270672b39fe7bc44213c380f2a5fafb01a6a535e24910c8
+oid sha256:f4f54cc5b434550fe3b22dbd4f48322a14ba45b3ce59212acfa6b4e6a1ac3d05
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b4b471661c3eb42d01d2eddd5ce87605064b91779b5eca26f39b022e99a590
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6945198046663049,
+  "epoch": 0.8681497558328811,
   "eval_steps": 25,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,84 @@
       "learning_rate": 1.9299099686894423e-05,
       "loss": 0.986,
       "step": 40
+    },
+    {
+      "epoch": 0.7118827997829625,
+      "grad_norm": 0.24084554612636566,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0175,
+      "step": 41
+    },
+    {
+      "epoch": 0.7292457948996202,
+      "grad_norm": 0.2267829179763794,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0397,
+      "step": 42
+    },
+    {
+      "epoch": 0.7466087900162778,
+      "grad_norm": 0.2309180051088333,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.0084,
+      "step": 43
+    },
+    {
+      "epoch": 0.7639717851329354,
+      "grad_norm": 0.2305024117231369,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.02,
+      "step": 44
+    },
+    {
+      "epoch": 0.781334780249593,
+      "grad_norm": 0.24496528506278992,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.0425,
+      "step": 45
+    },
+    {
+      "epoch": 0.7986977753662506,
+      "grad_norm": 0.25039851665496826,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.9937,
+      "step": 46
+    },
+    {
+      "epoch": 0.8160607704829083,
+      "grad_norm": 0.29076555371284485,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.0502,
+      "step": 47
+    },
+    {
+      "epoch": 0.8334237655995659,
+      "grad_norm": 0.31782031059265137,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0334,
+      "step": 48
+    },
+    {
+      "epoch": 0.8507867607162235,
+      "grad_norm": 0.3960300385951996,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0323,
+      "step": 49
+    },
+    {
+      "epoch": 0.8681497558328811,
+      "grad_norm": 0.536109447479248,
+      "learning_rate": 1e-05,
+      "loss": 1.1306,
+      "step": 50
+    },
+    {
+      "epoch": 0.8681497558328811,
+      "eval_loss": 0.9419312477111816,
+      "eval_runtime": 3.981,
+      "eval_samples_per_second": 6.28,
+      "eval_steps_per_second": 1.758,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -317,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.774466893853491e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null