Training in progress, step 89, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b580ddbf09d3d9ae2addf973352cb11707da67742b7b282fde53fde7fbe740
+oid sha256:981264992e2426ae6dd9cd6ab39604f29b4c1b06b3272034c116255bee16bac0
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2da229f251b5f291f941c33cc14eed837857befbbc6c2ca7bccca1a3f0efe5
+oid sha256:ac2b19e2861b1f82518ea74977bab48b2e3e74a4053627d0cb602fc60631b3de
 size 90365754

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:265ac61368277eb3ace99e1735a0a601a5a63864d2a441bc9b97a9c99e0f4c89
+oid sha256:0fd574bca472a6ebfd89e5aa3033f856f2e017ccd1e7f19de76f7298f30a795b
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79d137864c2e1cdce26d7c2feb8d8fbfd9200a245e19ae914aa4b88e97a6687
+oid sha256:78800c5f3e2fa2f4eb40a71d4e5f5b72a3535de84eba9d079818145d24d3aa25
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a045dc546280f3d42f2dc4c02c23ea3301726496c8a8623025df0283d2e3d076
+oid sha256:1200f1351667966f59f2212d75c031c1e7aaf68c3827c1ca68846af01b4ad8ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7677329624478443,
+  "epoch": 0.9902642559109874,
   "eval_steps": 23,
-  "global_step": 69,
+  "global_step": 89,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -522,6 +522,146 @@
       "eval_samples_per_second": 17.482,
       "eval_steps_per_second": 4.37,
       "step": 69
+    },
+    {
+      "epoch": 0.7788595271210014,
+      "grad_norm": 0.2063526213169098,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 0.7032,
+      "step": 70
+    },
+    {
+      "epoch": 0.7899860917941586,
+      "grad_norm": 0.23765341937541962,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.7518,
+      "step": 71
+    },
+    {
+      "epoch": 0.8011126564673157,
+      "grad_norm": 0.26653748750686646,
+      "learning_rate": 7.999743062239557e-05,
+      "loss": 0.8082,
+      "step": 72
+    },
+    {
+      "epoch": 0.8122392211404729,
+      "grad_norm": 0.2505719065666199,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.8035,
+      "step": 73
+    },
+    {
+      "epoch": 0.8233657858136301,
+      "grad_norm": 0.25650104880332947,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.8025,
+      "step": 74
+    },
+    {
+      "epoch": 0.8344923504867872,
+      "grad_norm": 0.270044207572937,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.8659,
+      "step": 75
+    },
+    {
+      "epoch": 0.8456189151599444,
+      "grad_norm": 0.2685801684856415,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.8519,
+      "step": 76
+    },
+    {
+      "epoch": 0.8567454798331016,
+      "grad_norm": 0.2514025568962097,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.8471,
+      "step": 77
+    },
+    {
+      "epoch": 0.8678720445062587,
+      "grad_norm": 0.2761232852935791,
+      "learning_rate": 3.675546244046228e-05,
+      "loss": 0.8711,
+      "step": 78
+    },
+    {
+      "epoch": 0.8789986091794159,
+      "grad_norm": 0.28267714381217957,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.8459,
+      "step": 79
+    },
+    {
+      "epoch": 0.8901251738525731,
+      "grad_norm": 0.29201367497444153,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 0.8672,
+      "step": 80
+    },
+    {
+      "epoch": 0.9012517385257302,
+      "grad_norm": 0.2988654673099518,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.781,
+      "step": 81
+    },
+    {
+      "epoch": 0.9123783031988874,
+      "grad_norm": 0.3167029619216919,
+      "learning_rate": 1.5480991445620542e-05,
+      "loss": 0.8121,
+      "step": 82
+    },
+    {
+      "epoch": 0.9235048678720446,
+      "grad_norm": 0.3307524621486664,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.8358,
+      "step": 83
+    },
+    {
+      "epoch": 0.9346314325452016,
+      "grad_norm": 0.35665422677993774,
+      "learning_rate": 8.002055634117578e-06,
+      "loss": 0.8123,
+      "step": 84
+    },
+    {
+      "epoch": 0.9457579972183588,
+      "grad_norm": 0.36604735255241394,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.8791,
+      "step": 85
+    },
+    {
+      "epoch": 0.9568845618915159,
+      "grad_norm": 0.3705534040927887,
+      "learning_rate": 2.905818257394799e-06,
+      "loss": 0.9042,
+      "step": 86
+    },
+    {
+      "epoch": 0.9680111265646731,
+      "grad_norm": 0.4027464687824249,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.7932,
+      "step": 87
+    },
+    {
+      "epoch": 0.9791376912378303,
+      "grad_norm": 0.505004346370697,
+      "learning_rate": 3.2426918657900704e-07,
+      "loss": 0.8301,
+      "step": 88
+    },
+    {
+      "epoch": 0.9902642559109874,
+      "grad_norm": 0.22385388612747192,
+      "learning_rate": 0.0,
+      "loss": 0.6786,
+      "step": 89
     }
   ],
   "logging_steps": 1,
@@ -536,12 +676,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.341828583994163e+16,
+  "total_flos": 6.890184695296819e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null