Training in progress, step 42, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151a29e6ec62b8f31f9089aaac57687b174708bb0e095cf7826516d38ecf579f
+oid sha256:9c70bdae6e050f7c78a96da54f61caa66eaf4ea7647a48b9d46850e0dd23132b
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d77876c07251093102774445f4a19ff90861eed79ed38da7b97a835a9b1c5cc
+oid sha256:ed2b8612aa06b23e4191753a32634e336b0482231f7efe5d1416208727f7ef11
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3b9bd0dffcda8b8b5ec7946bbdeb6224fa04c83a48803dee9ff17527305ae0
+oid sha256:5e63e5f9ada1adbfcd7cedb11ee595ff2475f58e2de2c0e34aa77cd256492b97
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14d8c964face54ab8c31fc89a0ca1052585c1be3be44e20d59cccf2370ff6a1
+oid sha256:c6a47b52c7272594b93bc9afee401a9a61dad05ae99778e2fef767ade59fd9f7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa0d50ea5b31167c654bdfe20f16b771f9eaff452352991217d058426067916
+oid sha256:c094ad5b7d5fe1a86f707a60497b9d2adfc55c42e68d535d60ac76e2dd2a7592
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0d6ea1c8d778e7dd688c963f3ce4abdbbed6543ddca71d5a99c215a9d0cec9
+oid sha256:5fbfe199dd1d175d6968a0b0a7887c0b8ec013e1e04e2b9a43c2a1433a9c630a
 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": 1.8419864559819414,
+  "epoch": 3.1422121896162527,
   "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": 288.718,
       "eval_steps_per_second": 75.067,
       "step": 25
+    },
+    {
+      "epoch": 1.9142212189616252,
+      "grad_norm": 0.030451903119683266,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 15.3316,
+      "step": 26
+    },
+    {
+      "epoch": 2.0225733634311513,
+      "grad_norm": 0.03348216786980629,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 16.8198,
+      "step": 27
+    },
+    {
+      "epoch": 2.094808126410835,
+      "grad_norm": 0.02313702367246151,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 11.3532,
+      "step": 28
+    },
+    {
+      "epoch": 2.1670428893905194,
+      "grad_norm": 0.02855922095477581,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 13.9424,
+      "step": 29
+    },
+    {
+      "epoch": 2.239277652370203,
+      "grad_norm": 0.013586718589067459,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 7.0922,
+      "step": 30
+    },
+    {
+      "epoch": 2.311512415349887,
+      "grad_norm": 0.03476588800549507,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 14.6245,
+      "step": 31
+    },
+    {
+      "epoch": 2.383747178329571,
+      "grad_norm": 0.0276983343064785,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 12.0846,
+      "step": 32
+    },
+    {
+      "epoch": 2.455981941309255,
+      "grad_norm": 0.017914237454533577,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 7.768,
+      "step": 33
+    },
+    {
+      "epoch": 2.528216704288939,
+      "grad_norm": 0.03817462921142578,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 16.043,
+      "step": 34
+    },
+    {
+      "epoch": 2.600451467268623,
+      "grad_norm": 0.02697724476456642,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 11.9938,
+      "step": 35
+    },
+    {
+      "epoch": 2.672686230248307,
+      "grad_norm": 0.01927335001528263,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 9.3809,
+      "step": 36
+    },
+    {
+      "epoch": 2.744920993227991,
+      "grad_norm": 0.03292158618569374,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 14.5154,
+      "step": 37
+    },
+    {
+      "epoch": 2.8171557562076748,
+      "grad_norm": 0.03068559244275093,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 12.0212,
+      "step": 38
+    },
+    {
+      "epoch": 2.889390519187359,
+      "grad_norm": 0.03927991911768913,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 16.2666,
+      "step": 39
+    },
+    {
+      "epoch": 2.961625282167043,
+      "grad_norm": 0.032981183379888535,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 14.3015,
+      "step": 40
+    },
+    {
+      "epoch": 3.069977426636569,
+      "grad_norm": 0.02991604059934616,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 12.4303,
+      "step": 41
+    },
+    {
+      "epoch": 3.1422121896162527,
+      "grad_norm": 0.026301313191652298,
+      "learning_rate": 1e-05,
+      "loss": 11.9028,
+      "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": 522224467968.0,
+  "total_flos": 877486964736.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null