Training in progress, step 115, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797691a5c1bede0a3013242e12ad082cf5b59954a8a0fc0dd7a75224b4282d66
+oid sha256:c302e89b218f98577e052fd6f9ae6583d00c39f84fff987a701313ab02e477ae
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6da235d2be338d88881dc48554c3fe142c62bdbac18c080cd1bbe05a538c5e
+oid sha256:fef6524a33a4c5d88382f225ea87d038cc2a45b3239e2c50653ef19cfd0fcfeb
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4992a0a541377e74f550ef72fa9af6f8fee0ce175cbdc61ec06b94024e86a4
+oid sha256:d4e6470455f66907a19173307202d571c6c3f1f8cd4ddcc5b663dc15013ec0cd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802e09b6cc63e64e726d0b68ba37b81d6a6fcf54cdf00e4821b3e38426a8a5c4
+oid sha256:d445cf5235925cca1a6d5e57200162b082b481744bf739a511d532ac296ab841
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05379301913319885,
+  "epoch": 0.05623815636652607,
   "eval_steps": 34,
-  "global_step": 110,
+  "global_step": 115,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -809,6 +809,41 @@
       "learning_rate": 0.00010922683594633021,
       "loss": 1.11,
       "step": 110
+    },
+    {
+      "epoch": 0.054282046579864296,
+      "grad_norm": 1.154991865158081,
+      "learning_rate": 0.00010738525274748741,
+      "loss": 0.9469,
+      "step": 111
+    },
+    {
+      "epoch": 0.05477107402652974,
+      "grad_norm": 1.1687790155410767,
+      "learning_rate": 0.000105541147491597,
+      "loss": 1.1575,
+      "step": 112
+    },
+    {
+      "epoch": 0.05526010147319518,
+      "grad_norm": 1.1781808137893677,
+      "learning_rate": 0.00010369514993891452,
+      "loss": 1.0453,
+      "step": 113
+    },
+    {
+      "epoch": 0.05574912891986063,
+      "grad_norm": 1.1359920501708984,
+      "learning_rate": 0.00010184789049591299,
+      "loss": 1.072,
+      "step": 114
+    },
+    {
+      "epoch": 0.05623815636652607,
+      "grad_norm": 1.2046093940734863,
+      "learning_rate": 0.0001,
+      "loss": 0.921,
+      "step": 115
     }
   ],
   "logging_steps": 1,
@@ -828,7 +863,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.882849615105229e+17,
+  "total_flos": 5.104797324882739e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null