Training in progress, step 6020, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0feb6f64ea3e3b92cc96080a409e4641eb264d332cc20250df4e39a05e662c7
+oid sha256:26556f1abb53ee822dd03ecead2e694e90d90f9f7c06255c3fb3bb5bd95b1e95
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a970c4eb86fbaca60a94a3c845063771d7d39e9087249e399eb948470aed22d1
+oid sha256:5267791793a613d797a09d60c3e5961f54bab0e1981820004fbccdcc8050fd4a
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0fb4f18c5202fb0a998c484ac19f5b59c60044cb935356391104a5e3a4b564
+oid sha256:27c1b58129752e66a4a302f63e7677b4460963afc004711e8b13996046bcd2c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe52a7672d7fe624a4913a1f41e35efbe969e8d4b2f9dcc25e7efb0a77e2b02
+oid sha256:c45e18651ea77eb43c3817495dab8ccf485a98bc6d621a0b971d270fe188b5ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4784,
+  "epoch": 0.4816,
   "eval_steps": 500,
-  "global_step": 5980,
+  "global_step": 6020,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2100,6 +2100,20 @@
       "learning_rate": 2.4658344354035063e-05,
       "loss": 3.5148,
       "step": 5980
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 30.200748443603516,
+      "learning_rate": 2.46211232944671e-05,
+      "loss": 3.6094,
+      "step": 6000
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 36.24076843261719,
+      "learning_rate": 2.4583801313868417e-05,
+      "loss": 3.4601,
+      "step": 6020
     }
   ],
   "logging_steps": 20,
@@ -2107,7 +2121,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1.41590318678016e+16,
+  "total_flos": 1.4256891905015808e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null