Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0eeae5d0bad680cc137a8478659f61e169009131b874e94497482c82943a5b
+oid sha256:34410a29025509af716b74f8f8e5e594616ec96042ec3c844e69738ed53ee00d
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f1cd2840a4f0b9b6f6c26974d02c6b354c89f90c34c21d56ba51ebe0799f308
+oid sha256:0bfc7fa8494a7d0b19676a339c8110ea263a3bc6118c004bbafd199930580826
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c3752ce98bfc3ec197e65d611692cfd440b987d3ddcbb16981cae0698d7e0b
+oid sha256:4a039ad76f0746f8ff052e22511b41b8352036173c7caa7a0153574149fda9e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3160dd3097641f3bf4d4036c0ddfd8673184925120f088b5ebecc6a1e5c953dd
+oid sha256:07b8a5b9aaab52c529e8225a8efdb5ee4b1c103decfe1101828eac45305d759c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.048460116049225274,
+  "epoch": 0.05101064847286871,
   "eval_steps": 34,
-  "global_step": 95,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -696,6 +696,41 @@
       "learning_rate": 0.00013612416661871533,
       "loss": 0.4754,
       "step": 95
+    },
+    {
+      "epoch": 0.048970222533953965,
+      "grad_norm": 0.3616621494293213,
+      "learning_rate": 0.00013439489186339282,
+      "loss": 0.6012,
+      "step": 96
+    },
+    {
+      "epoch": 0.04948032901868265,
+      "grad_norm": 0.44421911239624023,
+      "learning_rate": 0.0001326538712840083,
+      "loss": 0.4534,
+      "step": 97
+    },
+    {
+      "epoch": 0.04999043550341134,
+      "grad_norm": 0.35028621554374695,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5802,
+      "step": 98
+    },
+    {
+      "epoch": 0.050500541988140024,
+      "grad_norm": 0.38989895582199097,
+      "learning_rate": 0.00012913897468893248,
+      "loss": 0.5838,
+      "step": 99
+    },
+    {
+      "epoch": 0.05101064847286871,
+      "grad_norm": 0.4552973210811615,
+      "learning_rate": 0.0001273662990072083,
+      "loss": 0.7394,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -715,7 +750,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.586248544157696e+17,
+  "total_flos": 1.66973530963968e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null