Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f7a9f360eb15ef8032c202290c707d1df64a3d10525e0c15d46fe1644dd31a
+oid sha256:6a8fd5a7536117c9c062de23e712483ef97335539634fc37acbd2b48196af6f9
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:197947dadcfe6503c806222f71cfee81601d016a96a32defcefb3be24e841898
+oid sha256:3dc4f6740a3132d96407fcd57d951c890a713b0cea99fcd07cb7ea2d7143d7ef
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10350b5619e7d96fb7f3bffab3732b8b921da553987e25ecf13af945b954a09e
+oid sha256:49324b9e90e4a3300216fe09ec318d103f16e5de8c543c825c0b873b9acee835
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02340702210663199,
+  "epoch": 0.029258777633289986,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 11.046,
       "eval_steps_per_second": 1.381,
       "step": 36
+    },
+    {
+      "epoch": 0.025357607282184655,
+      "grad_norm": 0.858078122138977,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 4.6663,
+      "step": 39
+    },
+    {
+      "epoch": 0.027308192457737322,
+      "grad_norm": 0.7847902774810791,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 4.5735,
+      "step": 42
+    },
+    {
+      "epoch": 0.029258777633289986,
+      "grad_norm": 1.3613299131393433,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 4.6346,
+      "step": 45
+    },
+    {
+      "epoch": 0.029258777633289986,
+      "eval_loss": 1.1611473560333252,
+      "eval_runtime": 234.5632,
+      "eval_samples_per_second": 11.046,
+      "eval_steps_per_second": 1.381,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.704945439349146e+16,
+  "total_flos": 5.881181799186432e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null