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:b5a1958c57fa8a3e075e39de100457523fe983665ef747cd214c2060014226c0
+oid sha256:8c2339429b084817c8ec1dcdd90823551440e8a1769932ed2814cb205703f033
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7bab43b300f4949a336e8d5f11c091fb566f7cad43eb09ab5f37c35196c0d97
+oid sha256:d259240220390315d076babc40dae07105b817ed871cd9519c55c0c6d39db661
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87cdd914cacce0bf0f2d3377e1ea0cf41243706dad7f4209963b8c2a7ac5a75
+oid sha256:0aa299d6b618ba4f73d7d6c4d99f3591b3ed1a9520f2ccb1ca96d7f9f3c7936d
 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": 0.02040816326530612,
+  "epoch": 0.04081632653061224,
   "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": 3.367,
       "eval_steps_per_second": 1.684,
       "step": 25
+    },
+    {
+      "epoch": 0.02122448979591837,
+      "grad_norm": 0.45318421721458435,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.331,
+      "step": 26
+    },
+    {
+      "epoch": 0.022040816326530613,
+      "grad_norm": 0.4632524251937866,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.4417,
+      "step": 27
+    },
+    {
+      "epoch": 0.022857142857142857,
+      "grad_norm": 0.4687122404575348,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.3466,
+      "step": 28
+    },
+    {
+      "epoch": 0.0236734693877551,
+      "grad_norm": 0.41113656759262085,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.3353,
+      "step": 29
+    },
+    {
+      "epoch": 0.024489795918367346,
+      "grad_norm": 0.41863101720809937,
+      "learning_rate": 0.0001,
+      "loss": 0.3414,
+      "step": 30
+    },
+    {
+      "epoch": 0.024489795918367346,
+      "eval_loss": 0.36513009667396545,
+      "eval_runtime": 306.2051,
+      "eval_samples_per_second": 3.37,
+      "eval_steps_per_second": 1.685,
+      "step": 30
+    },
+    {
+      "epoch": 0.025306122448979593,
+      "grad_norm": 0.4296859800815582,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.411,
+      "step": 31
+    },
+    {
+      "epoch": 0.026122448979591838,
+      "grad_norm": 0.3878820538520813,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.2489,
+      "step": 32
+    },
+    {
+      "epoch": 0.026938775510204082,
+      "grad_norm": 0.4258907437324524,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.3211,
+      "step": 33
+    },
+    {
+      "epoch": 0.027755102040816326,
+      "grad_norm": 0.5517330169677734,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4105,
+      "step": 34
+    },
+    {
+      "epoch": 0.02857142857142857,
+      "grad_norm": 0.4672947824001312,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.3589,
+      "step": 35
+    },
+    {
+      "epoch": 0.02857142857142857,
+      "eval_loss": 0.3595900535583496,
+      "eval_runtime": 306.5235,
+      "eval_samples_per_second": 3.367,
+      "eval_steps_per_second": 1.683,
+      "step": 35
+    },
+    {
+      "epoch": 0.029387755102040815,
+      "grad_norm": 0.3918313682079315,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.314,
+      "step": 36
+    },
+    {
+      "epoch": 0.030204081632653063,
+      "grad_norm": 0.40090271830558777,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.3451,
+      "step": 37
+    },
+    {
+      "epoch": 0.031020408163265307,
+      "grad_norm": 0.4959544241428375,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.3831,
+      "step": 38
+    },
+    {
+      "epoch": 0.03183673469387755,
+      "grad_norm": 0.44812849164009094,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.4219,
+      "step": 39
+    },
+    {
+      "epoch": 0.0326530612244898,
+      "grad_norm": 0.5515211820602417,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.5255,
+      "step": 40
+    },
+    {
+      "epoch": 0.0326530612244898,
+      "eval_loss": 0.3551081120967865,
+      "eval_runtime": 305.9895,
+      "eval_samples_per_second": 3.373,
+      "eval_steps_per_second": 1.686,
+      "step": 40
+    },
+    {
+      "epoch": 0.03346938775510204,
+      "grad_norm": 0.5151244401931763,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.3823,
+      "step": 41
+    },
+    {
+      "epoch": 0.03428571428571429,
+      "grad_norm": 0.4395885765552521,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.3138,
+      "step": 42
+    },
+    {
+      "epoch": 0.03510204081632653,
+      "grad_norm": 0.3345911204814911,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.3134,
+      "step": 43
+    },
+    {
+      "epoch": 0.035918367346938776,
+      "grad_norm": 0.44604966044425964,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.3128,
+      "step": 44
+    },
+    {
+      "epoch": 0.036734693877551024,
+      "grad_norm": 0.40180206298828125,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.3261,
+      "step": 45
+    },
+    {
+      "epoch": 0.036734693877551024,
+      "eval_loss": 0.355383962392807,
+      "eval_runtime": 306.185,
+      "eval_samples_per_second": 3.371,
+      "eval_steps_per_second": 1.685,
+      "step": 45
+    },
+    {
+      "epoch": 0.037551020408163265,
+      "grad_norm": 0.35214531421661377,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.2845,
+      "step": 46
+    },
+    {
+      "epoch": 0.03836734693877551,
+      "grad_norm": 0.4088071286678314,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.2965,
+      "step": 47
+    },
+    {
+      "epoch": 0.03918367346938775,
+      "grad_norm": 0.38135460019111633,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.3156,
+      "step": 48
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.4034852683544159,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.3078,
+      "step": 49
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 0.41931870579719543,
+      "learning_rate": 0.0,
+      "loss": 0.3163,
+      "step": 50
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "eval_loss": 0.35439395904541016,
+      "eval_runtime": 306.6971,
+      "eval_samples_per_second": 3.365,
+      "eval_steps_per_second": 1.682,
+      "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": 3.83447180771328e+16,
+  "total_flos": 7.707288333503693e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null