Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf81dc5473adc8c3f3f7703ad5a166ac280ae2c9d6e48a715c71aa588aefda2
+oid sha256:60f40c657f63d97180569fedb8ef3717968e1d23276bc20563f7ae04ec2a5669
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f4c2380a8eb2ae7d563566451471b88c71fb7d2d1386c0dbef92112304326e
+oid sha256:23fea21c271c3c350208a3ea8810e4c5e1c86c439d0a6c701029bc4650f1661e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feab418b5ec670775ed300321638963cd7dd25ec9e299eef397569d76bf2b72f
+oid sha256:ae761037896b12221f8bf7b4fcbdac93eefcb3f9f793b1f6e94552c17ddb6202
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7894736842105263,
+  "epoch": 1.5789473684210527,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 4.001,
       "eval_steps_per_second": 1.0,
       "step": 25
+    },
+    {
+      "epoch": 0.8210526315789474,
+      "grad_norm": 0.5269589424133301,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9215,
+      "step": 26
+    },
+    {
+      "epoch": 0.8526315789473684,
+      "grad_norm": 0.43179982900619507,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.7455,
+      "step": 27
+    },
+    {
+      "epoch": 0.8842105263157894,
+      "grad_norm": 0.5215819478034973,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.861,
+      "step": 28
+    },
+    {
+      "epoch": 0.9157894736842105,
+      "grad_norm": 0.3976958692073822,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.7871,
+      "step": 29
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.41575056314468384,
+      "learning_rate": 0.0001,
+      "loss": 0.7532,
+      "step": 30
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 0.7560582160949707,
+      "eval_runtime": 9.9942,
+      "eval_samples_per_second": 4.002,
+      "eval_steps_per_second": 1.001,
+      "step": 30
+    },
+    {
+      "epoch": 0.9789473684210527,
+      "grad_norm": 0.49081918597221375,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.6406,
+      "step": 31
+    },
+    {
+      "epoch": 1.0105263157894737,
+      "grad_norm": 0.5961962938308716,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.0858,
+      "step": 32
+    },
+    {
+      "epoch": 1.0421052631578946,
+      "grad_norm": 0.3866117596626282,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.7171,
+      "step": 33
+    },
+    {
+      "epoch": 1.0736842105263158,
+      "grad_norm": 0.4523923695087433,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6907,
+      "step": 34
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.3665292263031006,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.7877,
+      "step": 35
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "eval_loss": 0.7507282495498657,
+      "eval_runtime": 9.999,
+      "eval_samples_per_second": 4.0,
+      "eval_steps_per_second": 1.0,
+      "step": 35
+    },
+    {
+      "epoch": 1.1368421052631579,
+      "grad_norm": 0.3150940239429474,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.61,
+      "step": 36
+    },
+    {
+      "epoch": 1.168421052631579,
+      "grad_norm": 0.39909401535987854,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.7461,
+      "step": 37
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.3504452705383301,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.7198,
+      "step": 38
+    },
+    {
+      "epoch": 1.231578947368421,
+      "grad_norm": 0.3640637993812561,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.5523,
+      "step": 39
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.3753401041030884,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.7139,
+      "step": 40
+    },
+    {
+      "epoch": 1.263157894736842,
+      "eval_loss": 0.752138614654541,
+      "eval_runtime": 9.9936,
+      "eval_samples_per_second": 4.003,
+      "eval_steps_per_second": 1.001,
+      "step": 40
+    },
+    {
+      "epoch": 1.2947368421052632,
+      "grad_norm": 0.3601594865322113,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.6394,
+      "step": 41
+    },
+    {
+      "epoch": 1.3263157894736843,
+      "grad_norm": 0.40832358598709106,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.8728,
+      "step": 42
+    },
+    {
+      "epoch": 1.3578947368421053,
+      "grad_norm": 0.44947680830955505,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.9453,
+      "step": 43
+    },
+    {
+      "epoch": 1.3894736842105262,
+      "grad_norm": 0.3563525080680847,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.5642,
+      "step": 44
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.4350314438343048,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.7842,
+      "step": 45
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "eval_loss": 0.7522160410881042,
+      "eval_runtime": 9.9932,
+      "eval_samples_per_second": 4.003,
+      "eval_steps_per_second": 1.001,
+      "step": 45
+    },
+    {
+      "epoch": 1.4526315789473685,
+      "grad_norm": 0.3606291711330414,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.5951,
+      "step": 46
+    },
+    {
+      "epoch": 1.4842105263157894,
+      "grad_norm": 0.35893508791923523,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.7562,
+      "step": 47
+    },
+    {
+      "epoch": 1.5157894736842106,
+      "grad_norm": 0.4855940341949463,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.9173,
+      "step": 48
+    },
+    {
+      "epoch": 1.5473684210526315,
+      "grad_norm": 0.48101991415023804,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.8475,
+      "step": 49
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.3735427260398865,
+      "learning_rate": 0.0,
+      "loss": 0.8305,
+      "step": 50
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "eval_loss": 0.7518041729927063,
+      "eval_runtime": 9.9913,
+      "eval_samples_per_second": 4.003,
+      "eval_steps_per_second": 1.001,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.56415462670336e+16,
+  "total_flos": 1.112830925340672e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null