Training in progress, step 42, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a5f4d69ef98f96d85ef62e959c511b789ac80b6926f5b5207250d410778f8a8
+oid sha256:06514da0eb15c610c3cec1974eed5f06de40ac94b4921072f7329a44b94d3748
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b95496f96d4ce56660e74c67f8fe76d34c21c492bdd40e8f6f81138472f68ef5
+oid sha256:4babe9608fe860fdf6c9eb5ba2bb866151491b6b28e9d881cf6f1b7daef98057
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f08773135f6f3b1ccb473bddedf248bbe0f93f221d52b2f5e8c66e4f8a675da6
+oid sha256:06e5990d5c191137f2e0cbe87b7c0f53d6455adf4bfee54f77b0f672ce6a5e0a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c902b69959077f1b25492c58692753fcb90792100df2fb944f56d7ba1999df6f
+oid sha256:16a2d6dea43355ffaa27153c0e8a009b7ff825795264f8492b7c7ca81413571a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d61497b68f95bb126b871bfdeefa66a68dbe8089dd6ba113e5c6c600a44cdd71
+oid sha256:c5d98186efceaf694923ca756096afd2d6023dfa26b7c3196ffe233b03efc8a7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb32e6e72470bcb40351f78e8ee0fd0cb32f4d50d8b2bfa5132f137b22b1ba8
+oid sha256:661a43aed25b761f274dcb9e08ee625bb7c4a14e8d9afe10811aa54f72a95d7e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f5af44da266da277e7531f687942d737458dea336c0a84bf03af6d775c87ac
+oid sha256:dde78f0152770b6d9ff9d100a4e49fd7ae2ec975980251062a46af49a9f251c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8310810810810811,
+  "epoch": 3.114864864864865,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,125 @@
       "eval_samples_per_second": 495.946,
       "eval_steps_per_second": 128.946,
       "step": 25
+    },
+    {
+      "epoch": 1.9031531531531531,
+      "grad_norm": 0.6299550533294678,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 11.6034,
+      "step": 26
+    },
+    {
+      "epoch": 2.0045045045045047,
+      "grad_norm": 0.6582178473472595,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 14.3429,
+      "step": 27
+    },
+    {
+      "epoch": 2.0765765765765765,
+      "grad_norm": 0.4390489459037781,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 10.5127,
+      "step": 28
+    },
+    {
+      "epoch": 2.1486486486486487,
+      "grad_norm": 0.5411266088485718,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 10.7874,
+      "step": 29
+    },
+    {
+      "epoch": 2.220720720720721,
+      "grad_norm": 0.5138953328132629,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 9.6413,
+      "step": 30
+    },
+    {
+      "epoch": 2.2927927927927927,
+      "grad_norm": 0.45892640948295593,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 10.7246,
+      "step": 31
+    },
+    {
+      "epoch": 2.364864864864865,
+      "grad_norm": 0.4862615466117859,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.6531,
+      "step": 32
+    },
+    {
+      "epoch": 2.436936936936937,
+      "grad_norm": 0.5631672143936157,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 10.1699,
+      "step": 33
+    },
+    {
+      "epoch": 2.509009009009009,
+      "grad_norm": 0.4757976233959198,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 9.9347,
+      "step": 34
+    },
+    {
+      "epoch": 2.581081081081081,
+      "grad_norm": 0.5032361745834351,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 10.5629,
+      "step": 35
+    },
+    {
+      "epoch": 2.653153153153153,
+      "grad_norm": 0.514340877532959,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 10.7382,
+      "step": 36
+    },
+    {
+      "epoch": 2.725225225225225,
+      "grad_norm": 0.501396656036377,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.0469,
+      "step": 37
+    },
+    {
+      "epoch": 2.7972972972972974,
+      "grad_norm": 0.4644583463668823,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 10.503,
+      "step": 38
+    },
+    {
+      "epoch": 2.8693693693693696,
+      "grad_norm": 0.5667948126792908,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 10.8346,
+      "step": 39
+    },
+    {
+      "epoch": 2.9414414414414414,
+      "grad_norm": 0.5867165923118591,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 10.6693,
+      "step": 40
+    },
+    {
+      "epoch": 3.0427927927927927,
+      "grad_norm": 0.7453739047050476,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 15.0657,
+      "step": 41
+    },
+    {
+      "epoch": 3.114864864864865,
+      "grad_norm": 0.5105739235877991,
+      "learning_rate": 1e-05,
+      "loss": 10.1017,
+      "step": 42
     }
   ],
   "logging_steps": 1,
@@ -212,12 +331,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 21384029798400.0,
+  "total_flos": 35925170061312.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null