Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c057a800f17153dc8d2330ef3e3c481646d0fdf46c5de75682287d46efae75d
+oid sha256:a8df46b111a0eddb93d4a61ed336f78864f256525d55d1e924c66d490cd7f0c0
 size 289512208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6110cecf5d28cde14828624167df644412c672b4e1d5672ba9331cfaef994572
+oid sha256:f154bb3fa3f06832482a83ec8b17cc233e2d24c42ed33aca02f7e13d52d5153b
 size 579427154

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c38b924d96affd2cebe5d9f5c799f0d52d9d6764dc74880b92d667a6f89c9693
+oid sha256:a14a061beb1ae9f4133b83dc5bb1e34fea2cc86704b58591c7efed4377b005ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:331327ffbc7ed39953083fcfb43109544a2c95f2cbeeeddcf82da32e370a5c3c
+oid sha256:8c3b774bbcd1ba687ab4df232c8f7b402e86b870fad26efddb8d84525283b77c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a60ed9780ae871b8364114aba36abeb9b143a5d8c28648c5fbcaa55b9c8e190
+oid sha256:57b6e60a6e7d2954049e65e85a58a94b13855c99fa571dec300b1a9a1f2015ad
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:144a4ff0aaf8822d370a4cf444b3931955281bfa5a3b22fe765a61975f2c7844
+oid sha256:a50e2db5860eb34314cff1d12af6741d8e85c8e00383b3d1af3ca071107ba24f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:904e0d2e7e4ae8edab17d01391589ac94dba3507eac1390802136a08db02a0e7
+oid sha256:9def2469cf89d8b64e17b2e5ae1c475955bd4be3a84f1888610c304944b834d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7038123167155426,
+  "epoch": 0.9384164222873901,
   "eval_steps": 250,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,13 @@
       "learning_rate": 0.00012,
       "loss": 0.1136,
       "step": 150
+    },
+    {
+      "epoch": 0.9384164222873901,
+      "grad_norm": 0.08602957427501678,
+      "learning_rate": 0.00016,
+      "loss": 0.1051,
+      "step": 200
     }
   ],
   "logging_steps": 50,
@@ -55,7 +62,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.117735176986165e+18,
+  "total_flos": 4.1569802359815537e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null