Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c5486924c28fb8b45a51bc6a26c11818220c54aedd55f4f0ee4ff0b29b033f
+oid sha256:1a5649af37a5b41c63084768a1b97fe2c7824ba93d6b701d238e6d3eb5057cb5
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1926d939738c1f543eb396a753c5529fd33032ac9cb09f7109d86df9f91b3460
+oid sha256:33abc0744ee37e39335b097f2fa677c00f83290e70905490de1e9fa653eed444
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a915056b5468bb17c9260fc7fecb56a8e2bf64a3c75a0d68b1c61984b1d9f3
+oid sha256:da34c78130291294db5a3fabc49ae2052c77c00d49d84a9bcfb5b2ecf075aeed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5511811023622047,
+  "epoch": 0.6299212598425197,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 5.266,
       "eval_steps_per_second": 0.689,
       "step": 35
+    },
+    {
+      "epoch": 0.5669291338582677,
+      "grad_norm": 0.6373382210731506,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 7.7433,
+      "step": 36
+    },
+    {
+      "epoch": 0.6141732283464567,
+      "grad_norm": 0.6322449445724487,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 7.9635,
+      "step": 39
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "eval_loss": 1.9487825632095337,
+      "eval_runtime": 20.3222,
+      "eval_samples_per_second": 5.265,
+      "eval_steps_per_second": 0.689,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.030418891538432e+17,
+  "total_flos": 1.1785416071970816e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null