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:eb8f9c20ff848f97c9be76e903f682cab9928a9e7a4234368fffbc3ae82ae492
+oid sha256:8cc30f1e357080bd583aaba94cad79247586b36f29d35647d75bd19ccc7e18b8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b87fbb9d48467f85b9ed2b65af9f2b02a235337a09f6a5324590cf757d7513
+oid sha256:64885af957151ce4958b0e044f7ed2e3e471dca64d4388e096a94408b85ba248
 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": 1.0845,
       "step": 85
+    },
+    {
+      "epoch": 0.042056360413228196,
+      "grad_norm": 0.2645609378814697,
+      "learning_rate": 0.0001510631193180907,
+      "loss": 0.8387,
+      "step": 86
+    },
+    {
+      "epoch": 0.04254538785989364,
+      "grad_norm": 0.2979009747505188,
+      "learning_rate": 0.0001494655843399779,
+      "loss": 1.0789,
+      "step": 87
+    },
+    {
+      "epoch": 0.04303441530655908,
+      "grad_norm": 0.3363690674304962,
+      "learning_rate": 0.00014785115691012864,
+      "loss": 0.9624,
+      "step": 88
+    },
+    {
+      "epoch": 0.04352344275322453,
+      "grad_norm": 0.700744092464447,
+      "learning_rate": 0.00014622038835403133,
+      "loss": 1.0248,
+      "step": 89
+    },
+    {
+      "epoch": 0.04401247019988997,
+      "grad_norm": 0.4093436300754547,
+      "learning_rate": 0.00014457383557765386,
+      "loss": 0.993,
+      "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