Training in progress, step 2220, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc4b1ee61a97280ee29a7f03d65f0615973d396283c0c1aa8a9c199445811fe
+oid sha256:fe4cb03d3561140a6dc960340bfc20239d79b812171f8665033b7d5950060c16
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012e45346ca36f5757826a56705c7bc60bbc32817df65a5df6cb0bf846ce5a5f
+oid sha256:02194e64ab0e46b57c09b90a41edf3c57c35eb6a761d021610ca25fe7722be96
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7cee742af04b6dcd02cfc87def2192f9af2a689dec2ee074b90937e1adbaf4e
+oid sha256:2417621c0c251f9779f9e28a0066e04b9dea3b724de678a9d2863d36bd10fb07
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d19068f9fb75a389d67a2a6a34b0327497f2ac8cc34c17114479ba846240d9b4
+oid sha256:dcda9d1b5e596e9a16f8101054c6161f73e1500ea7e6c07e8c2aa6c3a698c4fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7871198568872988,
+  "epoch": 0.7942754919499105,
   "eval_steps": 500,
-  "global_step": 2200,
+  "global_step": 2220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1767,14 +1767,30 @@
       "loss": 0.4195,
       "num_input_tokens_seen": 1488275,
       "step": 2200
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "grad_norm": 0.31744202971458435,
+      "learning_rate": 4.186046511627907e-05,
+      "loss": 0.3672,
+      "num_input_tokens_seen": 1496031,
+      "step": 2210
+    },
+    {
+      "epoch": 0.7942754919499105,
+      "grad_norm": 0.3008958697319031,
+      "learning_rate": 4.114490161001789e-05,
+      "loss": 0.3809,
+      "num_input_tokens_seen": 1503138,
+      "step": 2220
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1488275,
+  "num_input_tokens_seen": 1503138,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.34660490675712e+16,
+  "total_flos": 3.3800265450491904e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null