Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a36b71b9f5eba262d22c1e3205584a4af5b92b37cd0f1f2e3ee49247c8c1bdc1
+oid sha256:0967ce6d0c40bcc1ae5dd74cc75451f7fd4fb16619dbdeb273b00a3ae3eb6c69
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c737a14d742da4bca36c82cc97b56e222100702f7696c05e097ef78de33b433
+oid sha256:7fdf604d0f403d12959f6fe6e66b07a3d3a8643fe7c71fd62d3ea4cf6be2af06
 size 332574358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087a2ae65a4a30ca6315e22599816ba4b93588344c447989bc4f3501c2bf67eb
+oid sha256:64ae93a4ba5f02af912777c03226fc1661847332d13b648dfaab26b2512009fa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
+oid sha256:0f6003820aa1d9b0e6aa1d70309948568223b16abb8759408bc4ed8976518161
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04553734061930783,
+  "epoch": 0.06830601092896176,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 12.252,
       "eval_steps_per_second": 6.139,
       "step": 50
+    },
+    {
+      "epoch": 0.04644808743169399,
+      "grad_norm": 1.0157305002212524,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.7862,
+      "step": 51
+    },
+    {
+      "epoch": 0.04735883424408015,
+      "grad_norm": 1.3376152515411377,
+      "learning_rate": 1.1567509791329401e-05,
+      "loss": 1.1578,
+      "step": 52
+    },
+    {
+      "epoch": 0.0482695810564663,
+      "grad_norm": 1.4561330080032349,
+      "learning_rate": 1.0660589091223855e-05,
+      "loss": 1.0865,
+      "step": 53
+    },
+    {
+      "epoch": 0.04918032786885246,
+      "grad_norm": 1.1816233396530151,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.9107,
+      "step": 54
+    },
+    {
+      "epoch": 0.05009107468123861,
+      "grad_norm": 1.1890616416931152,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.8108,
+      "step": 55
+    },
+    {
+      "epoch": 0.051001821493624776,
+      "grad_norm": 1.186021089553833,
+      "learning_rate": 8.110244809608495e-06,
+      "loss": 0.8508,
+      "step": 56
+    },
+    {
+      "epoch": 0.05191256830601093,
+      "grad_norm": 1.1916978359222412,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.8236,
+      "step": 57
+    },
+    {
+      "epoch": 0.052823315118397086,
+      "grad_norm": 1.3242887258529663,
+      "learning_rate": 6.568066579746901e-06,
+      "loss": 0.9529,
+      "step": 58
+    },
+    {
+      "epoch": 0.05373406193078324,
+      "grad_norm": 1.2892563343048096,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.8467,
+      "step": 59
+    },
+    {
+      "epoch": 0.0546448087431694,
+      "grad_norm": 1.4728500843048096,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.9437,
+      "step": 60
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 1.306962490081787,
+      "learning_rate": 4.521198892775203e-06,
+      "loss": 0.7965,
+      "step": 61
+    },
+    {
+      "epoch": 0.056466302367941715,
+      "grad_norm": 1.478961706161499,
+      "learning_rate": 3.9152138546778625e-06,
+      "loss": 0.9545,
+      "step": 62
+    },
+    {
+      "epoch": 0.05737704918032787,
+      "grad_norm": 1.672711730003357,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 1.1629,
+      "step": 63
+    },
+    {
+      "epoch": 0.058287795992714025,
+      "grad_norm": 1.666373610496521,
+      "learning_rate": 2.8247291705444575e-06,
+      "loss": 1.1792,
+      "step": 64
+    },
+    {
+      "epoch": 0.05919854280510018,
+      "grad_norm": 1.9274945259094238,
+      "learning_rate": 2.3423053240837515e-06,
+      "loss": 1.1452,
+      "step": 65
+    },
+    {
+      "epoch": 0.060109289617486336,
+      "grad_norm": 2.060487747192383,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 1.2432,
+      "step": 66
+    },
+    {
+      "epoch": 0.0610200364298725,
+      "grad_norm": 2.072204828262329,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.161,
+      "step": 67
+    },
+    {
+      "epoch": 0.061930783242258654,
+      "grad_norm": 2.055114984512329,
+      "learning_rate": 1.1570762312943295e-06,
+      "loss": 1.0735,
+      "step": 68
+    },
+    {
+      "epoch": 0.06284153005464481,
+      "grad_norm": 2.482335329055786,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 1.1558,
+      "step": 69
+    },
+    {
+      "epoch": 0.06375227686703097,
+      "grad_norm": 2.711244821548462,
+      "learning_rate": 5.925998220016659e-07,
+      "loss": 1.2527,
+      "step": 70
+    },
+    {
+      "epoch": 0.06466302367941712,
+      "grad_norm": 2.62081241607666,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 1.2273,
+      "step": 71
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 2.8418915271759033,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 1.451,
+      "step": 72
+    },
+    {
+      "epoch": 0.06648451730418943,
+      "grad_norm": 2.660665988922119,
+      "learning_rate": 9.513254770636137e-08,
+      "loss": 1.3604,
+      "step": 73
+    },
+    {
+      "epoch": 0.06739526411657559,
+      "grad_norm": 2.826326847076416,
+      "learning_rate": 2.3794460453555047e-08,
+      "loss": 1.0152,
+      "step": 74
+    },
+    {
+      "epoch": 0.06830601092896176,
+      "grad_norm": 3.0708837509155273,
+      "learning_rate": 0.0,
+      "loss": 1.0459,
+      "step": 75
+    },
+    {
+      "epoch": 0.06830601092896176,
+      "eval_loss": 1.2876240015029907,
+      "eval_runtime": 37.5565,
+      "eval_samples_per_second": 12.328,
+      "eval_steps_per_second": 6.177,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.040893187457024e+16,
+  "total_flos": 1.5638785450573824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null