Training in progress, step 110, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9769b91c0469a97e0c1dfb3eefaf9d734458b7e8b64f2d0033b30307051208c
+oid sha256:11e90cb1227c62dec00086873084cd66a60f8e092ba5d04cf008f35af74bb9f9
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2ebc5d185dff679794f23dcfbb5fa3e43da9d96ae25e9a3de19de0300ceda4
+oid sha256:8cbd86d7bb4028458f06acd973791482cbe7f7a9e432113934e0d5e8b2972256
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6a076a27efe9310ca2d1126f2fd97f6a436090ae30ab5799eaee441f38e4441
+oid sha256:c8bccff553ddf796c56297874a33549d9fa05b99ea8275b995fc72d6e1c7856d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5618857120fccafc89c96d1c790dffa251460363284f4215ca3298967c397b5f
+oid sha256:4276fa00e85ff5423e2bca2a0a2c7a5f8e8110f9fd9dcbe1db6aad4b77cbd607
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1358783565189259,
+  "epoch": 0.1423487544483986,
   "eval_steps": 386,
-  "global_step": 105,
+  "global_step": 110,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -750,6 +750,41 @@
       "learning_rate": 9.994859081188943e-05,
       "loss": 0.867,
       "step": 105
+    },
+    {
+      "epoch": 0.13717243610482044,
+      "grad_norm": 1.04515540599823,
+      "learning_rate": 9.99467047272887e-05,
+      "loss": 0.9693,
+      "step": 106
+    },
+    {
+      "epoch": 0.13846651569071497,
+      "grad_norm": 1.099042534828186,
+      "learning_rate": 9.994478468355369e-05,
+      "loss": 0.8879,
+      "step": 107
+    },
+    {
+      "epoch": 0.1397605952766095,
+      "grad_norm": 0.8710360527038574,
+      "learning_rate": 9.994283068198988e-05,
+      "loss": 0.9018,
+      "step": 108
+    },
+    {
+      "epoch": 0.14105467486250403,
+      "grad_norm": 0.961025059223175,
+      "learning_rate": 9.99408427239258e-05,
+      "loss": 0.8806,
+      "step": 109
+    },
+    {
+      "epoch": 0.1423487544483986,
+      "grad_norm": 0.915665328502655,
+      "learning_rate": 9.993882081071306e-05,
+      "loss": 0.8628,
+      "step": 110
     }
   ],
   "logging_steps": 1,
@@ -769,7 +804,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1738340302782464e+17,
+  "total_flos": 1.2297308888629248e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null