Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7173f2095eaefc6173f2296bc5ca0608b2758d7af43d3295f6d0b0fa07c89c2f
+oid sha256:3a3a51d872cbc355f1bc72a53bded36e02b324e6df182be5bced5a1f4482f394
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe914b1d9853545e2ace71d2ea9f0c4da3dfd1c4d91fbd902fd559e493e92959
+oid sha256:c646af1878b0a3404644fbf386c34a3f2c18caba8a6f21cc4617eb61e1f3f100
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed20cb1e030baf9351dd9705735eda93875b2582f4380baf52cb1cb6e628a469
+oid sha256:183523c0f84bcb5b8b4b0d5dee6822dc6570a5da2635f659d919d0274e8fe059
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa0f75a1f3e346be25756b578158b09a68943f0b9f1cfe29f97939687f864ef
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010779249943858073,
+  "epoch": 0.011976944382064526,
   "eval_steps": 4,
-  "global_step": 36,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -339,6 +339,42 @@
       "eval_samples_per_second": 8.459,
       "eval_steps_per_second": 8.459,
       "step": 36
+    },
+    {
+      "epoch": 0.011078673553409687,
+      "grad_norm": 21.9058895111084,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 2.9877,
+      "step": 37
+    },
+    {
+      "epoch": 0.0113780971629613,
+      "grad_norm": 20.251365661621094,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.4354,
+      "step": 38
+    },
+    {
+      "epoch": 0.011677520772512913,
+      "grad_norm": 31.047348022460938,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 3.9592,
+      "step": 39
+    },
+    {
+      "epoch": 0.011976944382064526,
+      "grad_norm": 20.160734176635742,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.8831,
+      "step": 40
+    },
+    {
+      "epoch": 0.011976944382064526,
+      "eval_loss": 3.2888846397399902,
+      "eval_runtime": 83.3941,
+      "eval_samples_per_second": 8.442,
+      "eval_steps_per_second": 8.442,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -358,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3353971104088064e+16,
+  "total_flos": 1.483774567120896e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null