Next checkpoint

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad439aaf5874d60533bb5051bf6acffc2930733aa6dd485866dc6c59a9bdaed
+oid sha256:292555bf57b7d881f8568c1c9d316985a560f7a3fba0c349e2e6e74496a2bdbf
 size 609389712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff5e52256242d1b94c0b8d00e3ca518af4c033014b02970af183aa3537805bc
+oid sha256:5b3e3c0dfcc7a9a3a687735fca7b5141ec74f8dca1cf1c800633ba84e3c30d52
 size 43127132

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429b3c2a10fda7e387ef37f4109ca176f0c7db526d8d6c6307e136f1be354272
+oid sha256:b9ec94ca69dbb37242aaf2273b31165048fd94ab689588c866a967379270ab2c
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e19f6ca67131719fb6829118206971ea3850a7bbb4adfc8a62cee3bb0ae50d
+oid sha256:f8d0c3f88fd0aeaad407c1feb2d3894cb2996e0a702e779e1e893a9f6acacb88
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9248554913294798,
+  "epoch": 0.9458749343142406,
   "eval_steps": 500,
-  "global_step": 4400,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -535,6 +535,18 @@
       "learning_rate": 1.8781565656565657e-06,
       "loss": 3.4524,
       "step": 4400
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6151094276094277e-06,
+      "loss": 3.4321,
+      "step": 4450
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.3520622895622895e-06,
+      "loss": 3.4518,
+      "step": 4500
     }
   ],
   "logging_steps": 50,
@@ -542,7 +554,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
-  "total_flos": 1.0803018319304393e+19,
+  "total_flos": 1.104838456586335e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null