Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2e33725c1ca8376a32f6476107642e97130930fe0642d201bc303347117466
+oid sha256:278dfdfe1310dd64126d777b8b0780cbe6d3193a55d3ebcdf10aaf37489f92d1
 size 800116456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6259957a3d455a3a85cfdd88c3e5f44190e4744ebae0ad37b01a0145d25b716a
+oid sha256:1f20603d32f188c6d414d57e47236810bd977152399648551804568080686bdf
 size 406743412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbbbf68f9d88d65fbd987b53e45b042aee29e33d10cbda9ab4752d65fe82d473
+oid sha256:2db7720d2dec6110baba80f6a210a6b771eb81d5cbc530dd9a8c6a7d6aba5412
 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": 0.00885459490228322,
+  "epoch": 0.010119537031180823,
   "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": 11.25,
       "eval_steps_per_second": 1.408,
       "step": 35
+    },
+    {
+      "epoch": 0.00910758332806274,
+      "grad_norm": 9.735877990722656,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 3.5678,
+      "step": 36
+    },
+    {
+      "epoch": 0.009866548605401303,
+      "grad_norm": 9.53584098815918,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 3.331,
+      "step": 39
+    },
+    {
+      "epoch": 0.010119537031180823,
+      "eval_loss": 3.270254135131836,
+      "eval_runtime": 591.7633,
+      "eval_samples_per_second": 11.251,
+      "eval_steps_per_second": 1.408,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.471487922274304e+16,
+  "total_flos": 6.253129054027776e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null