Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4ec6b96f3989633799ef9c6c85213a1bc5d81ea97b7fc483ae326b1c54534d9
+oid sha256:69f06c5f9874569d065748e625261a8bd96c785985a7c3ef712f9ec8b3e8c484
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded7606b8e0f100ac0178a84c08f8b75e7725fbb51a7cdac8cba579a465fcdcf
+oid sha256:5fb44092a1636a18daf0562dadeeed57fa0fd3771bd2d1930f70859e8f29aba8
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012b3b2b1bae7e97243636afca60a311a7f1bb7f71a5d26125718cc46a272c98
+oid sha256:0363ca5edd0e1ae8b993b5309806d5abd1d8117f41ad2b526bbbf0dee2744931
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8181818181818183,
+  "epoch": 2.0,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 36.223,
       "eval_steps_per_second": 4.743,
       "step": 90
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 0.9819637537002563,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 2.0016,
+      "step": 93
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 1.2420907020568848,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 1.9479,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.456129789352417,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 2.2999,
+      "step": 99
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.0743141174316406,
+      "eval_runtime": 2.3243,
+      "eval_samples_per_second": 36.14,
+      "eval_steps_per_second": 4.733,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3504674882584576e+16,
+  "total_flos": 2.5847794608635904e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null