Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2cbfcdf3415e5870e70223a601075c82598fa66aca66aa85e07867564cfc035
+oid sha256:7ef374d3fe73aa999467d1128baacc374ba01737d6cf572894cf41c93310efcc
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d21ef79ed5d6292d7be01b52ea762095ec921954659de59e0ae0dd1ff7b7d6
+oid sha256:b3815439df283b4fd2e14687524debf23fc769786b24546cd6d84e34ab1a201e
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a1e8ae812270751e7c62a357a455c4cf42b93b949067e2347bf0242adfb165
+oid sha256:8e8daed718fea013cdb528d1985afb8df17afb47a94059b22927f669508f3a08
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ad385f66ed58375cd5801fb450cdca6fd08bb1f08f682b58f70ca0bac965b3
+oid sha256:3340f7450dfdcc50bc6d0d4bdc92576c596624d9dcaaa9f3897735b5ae5c8995
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930d5e9d61dd7315f81a74c4645dd79a59725319d208de7fb8df6b060be74a37
+oid sha256:08fa739c7e2b2fa1210957930f1a841de61df31689db1101ecfa386d28aaa886
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8b620823dc87b6381815fdb4e7291aaf9f9c8052bd66a489a9c8c9891e93baa
+oid sha256:77564156cb82864d91dae341bd260a8bf1eb8fe26265ef0a219dec782a8541de
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015557476231633534,
+  "epoch": 0.01944684528954192,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 118.014,
       "eval_steps_per_second": 3.694,
       "step": 36
+    },
+    {
+      "epoch": 0.016853932584269662,
+      "grad_norm": 0.9101667404174805,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.5658,
+      "step": 39
+    },
+    {
+      "epoch": 0.018150388936905792,
+      "grad_norm": 0.9854418635368347,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.4873,
+      "step": 42
+    },
+    {
+      "epoch": 0.01944684528954192,
+      "grad_norm": 1.0120340585708618,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.5698,
+      "step": 45
+    },
+    {
+      "epoch": 0.01944684528954192,
+      "eval_loss": 1.5253695249557495,
+      "eval_runtime": 132.0927,
+      "eval_samples_per_second": 118.016,
+      "eval_steps_per_second": 3.694,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1369924007664026e+17,
+  "total_flos": 1.4235024213252506e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null