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:dd06fd1403c3b5f372a0469e7913f3f54fef387802ec3e9d3c55e3bf5ee7eaae
+oid sha256:e1d2fc4d3df9df01c720fcacdfd92725712682b41d65d31ac8cc64b5ab708507
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7691b699d8dd956a5612a6e73071a5ce0b772eef04ad1598c298044effda044
+oid sha256:9241cb610f1cb997bc64a1301c78e00555be40838611f19a6d5c9cfe68789133
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e43ca4af8db8c670cfc6134d0c9dc13228e298671b79ac8c7902d71bafaace
+oid sha256:35c65e0c7aaf9f01146531ad13d47f064b46f31d8983cb34ba2a9b2a0ef837af
 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": 0.0877742946708464,
+  "epoch": 0.10031347962382445,
   "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": 13.489,
       "eval_steps_per_second": 1.686,
       "step": 35
+    },
+    {
+      "epoch": 0.090282131661442,
+      "grad_norm": 0.33437755703926086,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.5904,
+      "step": 36
+    },
+    {
+      "epoch": 0.09780564263322884,
+      "grad_norm": 0.3643655776977539,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.5416,
+      "step": 39
+    },
+    {
+      "epoch": 0.10031347962382445,
+      "eval_loss": 1.5517269372940063,
+      "eval_runtime": 49.7995,
+      "eval_samples_per_second": 13.494,
+      "eval_steps_per_second": 1.687,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.7438308048896e+16,
+  "total_flos": 5.4167146070016e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null