Training in progress, step 1120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d69499c5af363db9c69800142daa202a40720097dcebdb876bc14cde7f5d13
+oid sha256:93756c662435c89f0b33aea427588c404b58d5be37cf76c3f9e4bc0ff1bd939a
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47615466b0123bdcca71dd3dc26a2fef0b8c8f7445ddb63eaee76e7d029bd403
+oid sha256:a88dc8585ef97f13c62f73031c2660812fe3125beba7cb9ca7b650ca2dd9be0e
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133aae226bbaac66725e376492ee3f542023abc66dd7536ee6fe5913c3f55ef4
+oid sha256:10612cfe26142bef77beb908186e256524851aa5a76ff5646d1e0e1c8e9ff68c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:050a05f863436bace20199741dad316727f622e89a1193b9d3f3a77dd7cb7646
+oid sha256:827f3733c0f4c8564e6bc69cab6741789e52e80ec29e9f5a0f4d2f148dfac06d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3935599284436494,
+  "epoch": 0.4007155635062612,
   "eval_steps": 500,
-  "global_step": 1100,
+  "global_step": 1120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -887,14 +887,30 @@
       "loss": 0.4208,
       "num_input_tokens_seen": 739112,
       "step": 1100
+    },
+    {
+      "epoch": 0.39713774597495527,
+      "grad_norm": 0.3873242437839508,
+      "learning_rate": 0.00012057245080500895,
+      "loss": 0.3798,
+      "num_input_tokens_seen": 744478,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4007155635062612,
+      "grad_norm": 0.31334424018859863,
+      "learning_rate": 0.00011985688729874778,
+      "loss": 0.4179,
+      "num_input_tokens_seen": 753315,
+      "step": 1120
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 739112,
+  "num_input_tokens_seen": 753315,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.6620018785796096e+16,
+  "total_flos": 1.693939409943552e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null