Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0abce668b3eb4d44dc784d9560c9e8eaf1d78e218c11316de74bb009145f23e
+oid sha256:322d27566c97d95eb19d51961c27a563d5536f16940b4a27a9956d7bb2578261
 size 5991064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af9af34cee614f2f3b9fcd4f30272cd7939d050f865cdf0b26c2e35e2ffb59c
+oid sha256:b14f31da3b0eeb58f975f764db512d31a1cb3b846a2d135ff547d999136e23f2
 size 3875258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0823cffba25b0205e4aaa4829d080da287f93b4b12f54638f5eb7ec2af7f34c
+oid sha256:f673b50c9d76e7f4aba905deba6bab9362132836c548cdeb5ff0494bb47b8d67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f1cdaac6e6d07ba74169a3057ad987f49c993cbd8847dc15c52a36f581d092
+oid sha256:d0753cd8573da61b5febd8fa3eea8c43dff8632c42f6883cac9734506ab6aa43
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18791415290277916,
+  "epoch": 0.1912108924273893,
   "eval_steps": 500,
-  "global_step": 2850,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2003,6 +2003,41 @@
       "learning_rate": 0.0002,
       "loss": 0.7436,
       "step": 2850
+    },
+    {
+      "epoch": 0.1885735008077012,
+      "grad_norm": 1.677764892578125,
+      "learning_rate": 0.0002,
+      "loss": 0.6904,
+      "step": 2860
+    },
+    {
+      "epoch": 0.18923284871262322,
+      "grad_norm": 3.1064493656158447,
+      "learning_rate": 0.0002,
+      "loss": 0.7331,
+      "step": 2870
+    },
+    {
+      "epoch": 0.18989219661754525,
+      "grad_norm": 1.320894479751587,
+      "learning_rate": 0.0002,
+      "loss": 0.7432,
+      "step": 2880
+    },
+    {
+      "epoch": 0.19055154452246728,
+      "grad_norm": 2.0653398036956787,
+      "learning_rate": 0.0002,
+      "loss": 0.7793,
+      "step": 2890
+    },
+    {
+      "epoch": 0.1912108924273893,
+      "grad_norm": 1.7600677013397217,
+      "learning_rate": 0.0002,
+      "loss": 0.7675,
+      "step": 2900
     }
   ],
   "logging_steps": 10,
@@ -2022,7 +2057,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4931223928266240.0,
+  "total_flos": 5017928334422016.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null