Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256fd79fac443a8e9241674ca463486fda3f888ab5e074d66311bd3c815c34c9
+oid sha256:90c9e63fc18c98643630d6fd026cc5415f8e893a2f2eaca0c95bf5f3a7191321
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928ad91d86587a61aeb7010be11055612c77948816e0c8270df16a48d7f36954
+oid sha256:c43d8eaf69ebc263037b3e9b143740ae259b658e668f1a3cf0bb523f7b7cca35
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1867c722d8452179900fe4b9d6b4199826e5d5f2f1301385633d5f5fa01ac344
+oid sha256:0d86881722353f35e2b0cf8a5fa9fd22dbe9fbd227cfbda5b93edbcfe7b8f0f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005295319996187369,
+  "epoch": 0.0010590639992374739,
   "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": 148.263,
       "eval_steps_per_second": 74.131,
       "step": 25
+    },
+    {
+      "epoch": 0.0005507132796034864,
+      "grad_norm": 0.29744622111320496,
+      "learning_rate": 5e-05,
+      "loss": 10.3543,
+      "step": 26
+    },
+    {
+      "epoch": 0.0005718945595882359,
+      "grad_norm": 0.3198077380657196,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3582,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005930758395729854,
+      "grad_norm": 0.3042125105857849,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3503,
+      "step": 28
+    },
+    {
+      "epoch": 0.0006142571195577349,
+      "grad_norm": 0.31835922598838806,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3759,
+      "step": 29
+    },
+    {
+      "epoch": 0.0006354383995424844,
+      "grad_norm": 0.3096944987773895,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3664,
+      "step": 30
+    },
+    {
+      "epoch": 0.0006566196795272338,
+      "grad_norm": 0.32308197021484375,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3584,
+      "step": 31
+    },
+    {
+      "epoch": 0.0006778009595119833,
+      "grad_norm": 0.343171626329422,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3525,
+      "step": 32
+    },
+    {
+      "epoch": 0.0006989822394967328,
+      "grad_norm": 0.32908880710601807,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.374,
+      "step": 33
+    },
+    {
+      "epoch": 0.0007201635194814823,
+      "grad_norm": 0.34512171149253845,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.391,
+      "step": 34
+    },
+    {
+      "epoch": 0.0007413447994662317,
+      "grad_norm": 0.30201077461242676,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3747,
+      "step": 35
+    },
+    {
+      "epoch": 0.0007625260794509812,
+      "grad_norm": 0.32104218006134033,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3582,
+      "step": 36
+    },
+    {
+      "epoch": 0.0007837073594357307,
+      "grad_norm": 0.3781031370162964,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3578,
+      "step": 37
+    },
+    {
+      "epoch": 0.0008048886394204801,
+      "grad_norm": 0.3561527729034424,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3755,
+      "step": 38
+    },
+    {
+      "epoch": 0.0008260699194052297,
+      "grad_norm": 0.37884965538978577,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3643,
+      "step": 39
+    },
+    {
+      "epoch": 0.0008472511993899792,
+      "grad_norm": 0.3193395435810089,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3406,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008684324793747286,
+      "grad_norm": 0.34663599729537964,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3519,
+      "step": 41
+    },
+    {
+      "epoch": 0.0008896137593594781,
+      "grad_norm": 0.3503679931163788,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3813,
+      "step": 42
+    },
+    {
+      "epoch": 0.0009107950393442276,
+      "grad_norm": 0.3438533544540405,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3496,
+      "step": 43
+    },
+    {
+      "epoch": 0.000931976319328977,
+      "grad_norm": 0.3700442314147949,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3515,
+      "step": 44
+    },
+    {
+      "epoch": 0.0009531575993137265,
+      "grad_norm": 0.35162249207496643,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3779,
+      "step": 45
+    },
+    {
+      "epoch": 0.000974338879298476,
+      "grad_norm": 0.37360620498657227,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.363,
+      "step": 46
+    },
+    {
+      "epoch": 0.0009955201592832255,
+      "grad_norm": 0.4056940972805023,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3698,
+      "step": 47
+    },
+    {
+      "epoch": 0.001016701439267975,
+      "grad_norm": 0.36040621995925903,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3676,
+      "step": 48
+    },
+    {
+      "epoch": 0.0010378827192527244,
+      "grad_norm": 0.43919169902801514,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3687,
+      "step": 49
+    },
+    {
+      "epoch": 0.0010590639992374739,
+      "grad_norm": 0.482573539018631,
+      "learning_rate": 0.0,
+      "loss": 10.4012,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010590639992374739,
+      "eval_loss": 10.36749267578125,
+      "eval_runtime": 268.1107,
+      "eval_samples_per_second": 148.289,
+      "eval_steps_per_second": 74.145,
+      "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": 2673003724800.0,
+  "total_flos": 5346007449600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null