Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8621b618b301f865cadc91959441872f5434678c1ac6424423e50c3e9e10cf52
+oid sha256:5787ba009af86f1a7239b3beb2ab60528788a4de3b198109ebb7db1b5aab0ca5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c287583a4d39a4a8f3665ea1201526cd6abc65cda2be60f1f30c4992b325d2
+oid sha256:e54e74ade3010c0ee6372f151aaa049a2a128e05c4b5bc14a43045214753657d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826e666b3f1881e003df1e799293232a6d3ede1a55e213829eb507201e9190b8
+oid sha256:fdf18d6697609a27a0b488fa23bfd024570519524cd30dfeaa261a878e17c189
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9707e13ab424365dde92daf30c033711d2caa0fada77309f65d41532581807
+oid sha256:dfdc0543e9ce40f0d0b0ee9752d10d130598c759cc5a2bd973736f6096894d17
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.041567332966562745,
+  "epoch": 0.04401247019988997,
   "eval_steps": 34,
-  "global_step": 85,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -626,6 +626,41 @@
       "learning_rate": 0.0001526432162877356,
       "loss": 1.0248,
       "step": 85
+    },
+    {
+      "epoch": 0.042056360413228196,
+      "grad_norm": 1.3093312978744507,
+      "learning_rate": 0.0001510631193180907,
+      "loss": 1.017,
+      "step": 86
+    },
+    {
+      "epoch": 0.04254538785989364,
+      "grad_norm": 2.124237537384033,
+      "learning_rate": 0.0001494655843399779,
+      "loss": 0.9459,
+      "step": 87
+    },
+    {
+      "epoch": 0.04303441530655908,
+      "grad_norm": 1.416883111000061,
+      "learning_rate": 0.00014785115691012864,
+      "loss": 1.0393,
+      "step": 88
+    },
+    {
+      "epoch": 0.04352344275322453,
+      "grad_norm": 1.1954100131988525,
+      "learning_rate": 0.00014622038835403133,
+      "loss": 1.4326,
+      "step": 89
+    },
+    {
+      "epoch": 0.04401247019988997,
+      "grad_norm": 1.1562423706054688,
+      "learning_rate": 0.00014457383557765386,
+      "loss": 0.9829,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -645,7 +680,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.773111066217677e+17,
+  "total_flos": 3.995058775995187e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null