Training in progress, step 9500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d0ea7a0f35f6452822d7ef39333323a4dfb3a99f01b82a901680f98583ce5e
+oid sha256:74dbc4fc66a0521c67117b743d8dee6d8791965619a98835f3f2c1874b66cb9c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6381172a935f4d2ce146c253e91ff2c61e7331f3ee0f502a280fb40f35dedbb
+oid sha256:38b14e9e9ec67fc84b17a0cf8ac4351485843887f3332aa843d88f8792e88c06
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343cbf433a49823c26aa4dd9334fa3e204370732996c7bb60db1a7158c5badde
+oid sha256:f2b67c05f37b4606592392a2a2e3555caf2c285ee68c702566e4cb3524218561
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b8133c0078c9773a22c7a49b5547dc88d96e16d710eff8078381e482ecc029
+oid sha256:54ecb14aafa347554d588d4693c91cb65e2015d07059f19d3a2e8bd39a45c1a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8703241895261846,
+  "epoch": 1.9742310889443058,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -141,6 +141,13 @@
       "learning_rate": 7.536713771127737e-06,
       "loss": 0.3495,
       "step": 9000
+    },
+    {
+      "epoch": 1.9742310889443058,
+      "grad_norm": 1.4501579999923706,
+      "learning_rate": 6.845386533665836e-06,
+      "loss": 0.3385,
+      "step": 9500
     }
   ],
   "logging_steps": 500,
@@ -160,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.096063307218944e+16,
+  "total_flos": 1.156959096274944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null