Training in progress, step 10500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3730a1d878d4053b143d57a57c1fac448e69341b9479dfd3f851a6ab33144e33
+oid sha256:43947f7dff9276008c5ac3a3bb1a1f78045f6daf3ab26be1df501497ecb5a13c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f89d84528008d151b3dd4170e97962e1d6e21f8f9d5216a258aa552ef4052471
+oid sha256:659ad3bb4e988117552420945713bf112a7f8dc606586d8b6b10aff068671da7
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2beb5f3eae46760fe93c244c16d7260ed6d437cc6536ace16b095ba9f37e6d
+oid sha256:f2f8cb1d04d85cb700bc0a165ddfffe857827b34a325813bd7675c23cb4f568a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022b8217d4b55852b997e3b5ca16c9910cfc8e1e5dae3900bbbe1878452b5ee9
+oid sha256:6ac8c1d8a81c24b85fd218732e29aedf5ad8d51951edcda5923c223ea804a4dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0781379883624274,
+  "epoch": 2.1820448877805485,
   "eval_steps": 500,
-  "global_step": 10000,
+  "global_step": 10500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,13 @@
       "learning_rate": 6.15267387087836e-06,
       "loss": 0.3293,
       "step": 10000
+    },
+    {
+      "epoch": 2.1820448877805485,
+      "grad_norm": 1.2724053859710693,
+      "learning_rate": 5.459961208090885e-06,
+      "loss": 0.3369,
+      "step": 10500
     }
   ],
   "logging_steps": 500,
@@ -182,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.217793989541888e+16,
+  "total_flos": 1.278689778597888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null