Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94512e54e733d5f25dd1b5cd1985a21e453ddbc4eb6669d065a0de171455737
+oid sha256:f54373cbd6e6809c773448d9082b4a65a863c709e1bd0abdde8859abe8c953fa
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d51b8d0d6db3c87aa8169c1c67d0b06c9fc29db37028160ec0f982401719e113
+oid sha256:d581613e0a2f178ae6e52b17e77b452ba7999de8c49488133e402938d4ba0961
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df1c993556956039bd4246881ff8bd64f81f71ca50a0a2661d2622e1232f420
+oid sha256:58d54903cbebc94f7627186d4584b64b2cc4148d940b1c0fe8ebc728f72bcefa
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8584493dc474b0957c4a15cdc0e3128956510a5909ca458a104b540f615059d7
+oid sha256:88aa36bdc9fbc9bc824ea4d9ba9a556f81fa276dfdf40b48629edf76ec0b5338
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8ae53b575638d385a70746423b4ea42da80e5107ac6c2bf4ab5fe278e71ef1
+oid sha256:da6c5248c43187808c08014530cfbaba66ead150847b6c461aa3b49ad04e940c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6691a5d239ba6e7b56e97451f9ced46cc13af1f2488945919784f21c7f34d7
+oid sha256:ac3a2ab778b2aa0c2d17ea26b77f18c429bc1f92036abdeaef71a61cd256f300
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.056264066016504126,
+  "epoch": 0.07501875468867217,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 1.0,
       "step": 75
+    },
+    {
+      "epoch": 0.05701425356339085,
+      "grad_norm": 1.0105289220809937,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.0618,
+      "step": 76
+    },
+    {
+      "epoch": 0.05776444111027757,
+      "grad_norm": 0.9906763434410095,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.3966,
+      "step": 77
+    },
+    {
+      "epoch": 0.058514628657164294,
+      "grad_norm": 1.0615285634994507,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.119,
+      "step": 78
+    },
+    {
+      "epoch": 0.05926481620405101,
+      "grad_norm": 1.4000828266143799,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.3671,
+      "step": 79
+    },
+    {
+      "epoch": 0.06001500375093773,
+      "grad_norm": 1.228930115699768,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2806,
+      "step": 80
+    },
+    {
+      "epoch": 0.060765191297824456,
+      "grad_norm": 0.9001653790473938,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.2502,
+      "step": 81
+    },
+    {
+      "epoch": 0.060765191297824456,
+      "eval_loss": 1.1089634895324707,
+      "eval_runtime": 101.9954,
+      "eval_samples_per_second": 44.022,
+      "eval_steps_per_second": 1.382,
+      "step": 81
+    },
+    {
+      "epoch": 0.06151537884471118,
+      "grad_norm": 1.1187061071395874,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3192,
+      "step": 82
+    },
+    {
+      "epoch": 0.0622655663915979,
+      "grad_norm": 0.9319303035736084,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.1843,
+      "step": 83
+    },
+    {
+      "epoch": 0.06301575393848462,
+      "grad_norm": 0.8874063491821289,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9317,
+      "step": 84
+    },
+    {
+      "epoch": 0.06376594148537135,
+      "grad_norm": 0.9671034812927246,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0485,
+      "step": 85
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 0.9318347573280334,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.011,
+      "step": 86
+    },
+    {
+      "epoch": 0.06526631657914479,
+      "grad_norm": 1.0970379114151,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.0897,
+      "step": 87
+    },
+    {
+      "epoch": 0.06601650412603151,
+      "grad_norm": 0.9756683707237244,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.1833,
+      "step": 88
+    },
+    {
+      "epoch": 0.06676669167291822,
+      "grad_norm": 1.1624336242675781,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.3335,
+      "step": 89
+    },
+    {
+      "epoch": 0.06751687921980495,
+      "grad_norm": 0.9813941717147827,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0293,
+      "step": 90
+    },
+    {
+      "epoch": 0.06751687921980495,
+      "eval_loss": 1.1063300371170044,
+      "eval_runtime": 102.9191,
+      "eval_samples_per_second": 43.626,
+      "eval_steps_per_second": 1.37,
+      "step": 90
+    },
+    {
+      "epoch": 0.06826706676669167,
+      "grad_norm": 0.882434606552124,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.0447,
+      "step": 91
+    },
+    {
+      "epoch": 0.0690172543135784,
+      "grad_norm": 1.0112385749816895,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.7567,
+      "step": 92
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 1.1317676305770874,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.1961,
+      "step": 93
+    },
+    {
+      "epoch": 0.07051762940735183,
+      "grad_norm": 0.9738214015960693,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.043,
+      "step": 94
+    },
+    {
+      "epoch": 0.07126781695423856,
+      "grad_norm": 0.9306845664978027,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.4558,
+      "step": 95
+    },
+    {
+      "epoch": 0.07201800450112528,
+      "grad_norm": 1.0271937847137451,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.1143,
+      "step": 96
+    },
+    {
+      "epoch": 0.072768192048012,
+      "grad_norm": 1.1768940687179565,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.0726,
+      "step": 97
+    },
+    {
+      "epoch": 0.07351837959489872,
+      "grad_norm": 1.0005249977111816,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1317,
+      "step": 98
+    },
+    {
+      "epoch": 0.07426856714178545,
+      "grad_norm": 0.7808559536933899,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.8203,
+      "step": 99
+    },
+    {
+      "epoch": 0.07426856714178545,
+      "eval_loss": 1.105713129043579,
+      "eval_runtime": 102.0398,
+      "eval_samples_per_second": 44.002,
+      "eval_steps_per_second": 1.382,
+      "step": 99
+    },
+    {
+      "epoch": 0.07501875468867217,
+      "grad_norm": 0.8602554798126221,
+      "learning_rate": 0.0,
+      "loss": 1.0806,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.7857867866793574e+17,
+  "total_flos": 3.690889286044877e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null