Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b53757c450e806fa0582f6da980220020345670b993e63bf8d59758c647ec13e
+oid sha256:feee0a69dbcd321bf78ea0b4b76e9c5124d68ccf8b93018334bb8f2f734b7ad3
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62f2d146799cdd29e89bf7d951426b0237e01e6e5606f9b041f19bfe0a9ae8c
+oid sha256:9d7c39e6e6222cb74622e3254d42bf0e9b0b3b058c628cd0ef84b4a2e1322e35
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d8ffd5d0306b34d29b48a6526b5741dc24dc3acdbe564b95d57b68075e66c1
+oid sha256:0fb787d7b71a8f1899c8d99ef06e195074c24a984dea6c9926cd15c76a124153
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e900207fcc2d3955802905e12eea3ef81eb975d535a9ef6fb02c7c84a229aca9
+oid sha256:80407f1621aa96065dd58d5f53331105dff3bac7a38e8f9d80f24f4c3788046c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1747007440957619,
+  "epoch": 0.18117114202523454,
   "eval_steps": 386,
-  "global_step": 135,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -960,6 +960,41 @@
       "learning_rate": 9.987724198319148e-05,
       "loss": 0.8631,
       "step": 135
+    },
+    {
+      "epoch": 0.17599482368165642,
+      "grad_norm": 0.882074773311615,
+      "learning_rate": 9.987433778614549e-05,
+      "loss": 0.8997,
+      "step": 136
+    },
+    {
+      "epoch": 0.17728890326755095,
+      "grad_norm": 0.9853332042694092,
+      "learning_rate": 9.987139967916805e-05,
+      "loss": 0.9226,
+      "step": 137
+    },
+    {
+      "epoch": 0.17858298285344548,
+      "grad_norm": 1.151941180229187,
+      "learning_rate": 9.98684276642568e-05,
+      "loss": 1.0486,
+      "step": 138
+    },
+    {
+      "epoch": 0.17987706243934,
+      "grad_norm": 1.0128459930419922,
+      "learning_rate": 9.986542174343245e-05,
+      "loss": 1.0797,
+      "step": 139
+    },
+    {
+      "epoch": 0.18117114202523454,
+      "grad_norm": 0.9798718094825745,
+      "learning_rate": 9.986238191873874e-05,
+      "loss": 0.875,
+      "step": 140
     }
   ],
   "logging_steps": 1,
@@ -979,7 +1014,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5092151817863168e+17,
+  "total_flos": 1.5651120403709952e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null