Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1753c72ccb1a9e11a6df65bbb400bf263999aa26bfd6fcf1f8806d8816b064
+oid sha256:ea615d725d352c698298f1aafb52aa98c1a78228e503f077fb1850cd70175e4c
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a17bdd80252dacd4805f6ca57d077838d307db0512aa91161d298af42030ec86
+oid sha256:156dc99a94b1badd12ced5626ab6212100a80b454eb8dd97cf50e94195fdcc09
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17eca7e25974cd391c6342b957032cb7907005ec238e47db0663301f0f4322c3
+oid sha256:9716d25ba59b99bcb755bf9d1d3a4bbfaffe5d4cb0c0c8a773bcf7e9f59b7418
 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": 0.009691096305269533,
+  "epoch": 0.010767884783632815,
   "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": 8.342,
       "eval_steps_per_second": 4.173,
       "step": 36
+    },
+    {
+      "epoch": 0.009960293424860354,
+      "grad_norm": 2.519052267074585,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 3.8805,
+      "step": 37
+    },
+    {
+      "epoch": 0.010229490544451174,
+      "grad_norm": 2.59364652633667,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.0401,
+      "step": 38
+    },
+    {
+      "epoch": 0.010498687664041995,
+      "grad_norm": 2.6932904720306396,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 3.6313,
+      "step": 39
+    },
+    {
+      "epoch": 0.010767884783632815,
+      "grad_norm": 2.4584312438964844,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 3.9238,
+      "step": 40
+    },
+    {
+      "epoch": 0.010767884783632815,
+      "eval_loss": 3.8838305473327637,
+      "eval_runtime": 188.8048,
+      "eval_samples_per_second": 8.289,
+      "eval_steps_per_second": 4.147,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -358,7 +394,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7608197015535616e+16,
+  "total_flos": 3.067577446170624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null