Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7865543f6aaefd525a4aa03a410cf4af463b4f3e6d2ae1912538913e26220b7
+oid sha256:fbc4b1ee61a97280ee29a7f03d65f0615973d396283c0c1aa8a9c199445811fe
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d22e73707901787033065e05e6edbc269297b3683cfdbd102a29997da966992
+oid sha256:012e45346ca36f5757826a56705c7bc60bbc32817df65a5df6cb0bf846ce5a5f
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1a9e3708d9d232a77e9549079bba51673bcb8586b714eb42370d58b85c5e90
+oid sha256:b7cee742af04b6dcd02cfc87def2192f9af2a689dec2ee074b90937e1adbaf4e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b259303746656c555078a221a94fa56f648be2579b7ca4ced7c5648c5502f83
+oid sha256:d19068f9fb75a389d67a2a6a34b0327497f2ac8cc34c17114479ba846240d9b4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7799642218246869,
+  "epoch": 0.7871198568872988,
   "eval_steps": 500,
-  "global_step": 2180,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1751,14 +1751,30 @@
       "loss": 0.3971,
       "num_input_tokens_seen": 1475721,
       "step": 2180
+    },
+    {
+      "epoch": 0.7835420393559929,
+      "grad_norm": 0.2836684584617615,
+      "learning_rate": 4.329159212880143e-05,
+      "loss": 0.3814,
+      "num_input_tokens_seen": 1481691,
+      "step": 2190
+    },
+    {
+      "epoch": 0.7871198568872988,
+      "grad_norm": 0.3486209809780121,
+      "learning_rate": 4.257602862254025e-05,
+      "loss": 0.4195,
+      "num_input_tokens_seen": 1488275,
+      "step": 2200
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1475721,
+  "num_input_tokens_seen": 1488275,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.318375394066637e+16,
+  "total_flos": 3.34660490675712e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null