Training in progress, step 8000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8230b48ad5d2d47bded13d0b4a225a6fe458e88f0dfffee4ef6138e3578b7cb7
+oid sha256:a38420795d5d0d50e960f49d06adbc5c6bdd8169cb909db6fc15ce6766e6ef0e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ebd683f88765c7f3684d4f1b999d5a7d937536c2acc21fbea1dd5a504ff4c8
+oid sha256:8275e665b6929f18028bebc898bdfbc6c0a222deb0f41fb9bf83f931ffb4e789
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5815229928c679da2154333af4c0852e138211519132990800c387aec8269b78
+oid sha256:c603634c267f29bf2d121dbeedb38074ba961e12d7046289f8ab33d4f4a419be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3961966af58db2c2b54115da864b0f30cc2f3fd3fe289e5c948d2dbcbffbe9d4
+oid sha256:78825347619efcca6295a2a1e8c4e9f6bdf3806b28ce14630667667fc69bc6a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005800571876894017,
+  "epoch": 0.005949304489122068,
   "eval_steps": 2000,
-  "global_step": 7800,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -280,6 +280,13 @@
       "learning_rate": 1.9999933771375512e-05,
       "loss": 1.5566,
       "step": 7800
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.320197582244873,
+      "learning_rate": 1.9999930326577432e-05,
+      "loss": 1.5593,
+      "step": 8000
     }
   ],
   "logging_steps": 200,
@@ -287,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.0229934649090867e+17,
+  "total_flos": 1.0490681947287552e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null