Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04d2ee0f7546c8480db5f6b7431a5ecf9eddea3854bdd7845dc94b84bfe03f1e
+oid sha256:35d4dacf6ca7235a630206be47c57307ec59d042c586237f5ee3685830f353ca
 size 12803224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b49f44bfe27f33fffa35d6a1b635c18d402e2a88fc86d9dbed22e0915f99bf
+oid sha256:5205fd6548534ff72becdbb489dd70821e6049f447e4343f8253d3626b2c27dd
 size 6472698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb6a083f723a87350cb3b90d9283b4cc20674e7bae0ce04043b935951292bbf
+oid sha256:db81002b0a79810ae6ea06692dfc424400086dbd3dd457addd6b3b0966398690
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a47285efa6c5fa8c4bc001ed2983530f9e5cd23c9aaa5e045805156a46a25d3
+oid sha256:5e578c8608f70526ffbfa08fcf305a3b9476a76b7d3e79b963ae3bc487a64238
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.782525118099818e-05,
+  "epoch": 9.339030141719783e-05,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42,6 +42,13 @@
       "learning_rate": 1.5333333333333334e-05,
       "loss": 3.594,
       "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 17.74490737915039,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 3.6379,
+      "step": 120
     }
   ],
   "logging_steps": 20,
@@ -49,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 426432203366400.0,
+  "total_flos": 511252181299200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null