Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447309dc885d278eb35674b5eefd11b405ca47ac1c8d198281aa6e1047de3a35
+oid sha256:c2cbfcdf3415e5870e70223a601075c82598fa66aca66aa85e07867564cfc035
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291e2154c0098ea1ea9516ff777c7632133b5f52f5a83fd08c6d4e86ef0dcbf4
+oid sha256:a6d21ef79ed5d6292d7be01b52ea762095ec921954659de59e0ae0dd1ff7b7d6
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96838db1f6dcd841a541dc77ceefe86d5a4c3e639cd7f052bbc8ee139ede8aba
+oid sha256:39a1e8ae812270751e7c62a357a455c4cf42b93b949067e2347bf0242adfb165
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355a460711dc6eab66bb0655236c2708df3c07df7d8bf7e6f8f41354a94b58a1
+oid sha256:b2ad385f66ed58375cd5801fb450cdca6fd08bb1f08f682b58f70ca0bac965b3
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5110c40a1b5d19f3f5b67f0074ec266a111249673957df3492769e973ff860bf
+oid sha256:930d5e9d61dd7315f81a74c4645dd79a59725319d208de7fb8df6b060be74a37
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8214b098707513f003bf5712464cd5e11584d435a57e63e399fb305105d8731b
+oid sha256:c8b620823dc87b6381815fdb4e7291aaf9f9c8052bd66a489a9c8c9891e93baa
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011668107173725151,
+  "epoch": 0.015557476231633534,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 118.021,
       "eval_steps_per_second": 3.695,
       "step": 27
+    },
+    {
+      "epoch": 0.01296456352636128,
+      "grad_norm": 0.888576865196228,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.578,
+      "step": 30
+    },
+    {
+      "epoch": 0.014261019878997408,
+      "grad_norm": 0.9320745468139648,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.5553,
+      "step": 33
+    },
+    {
+      "epoch": 0.015557476231633534,
+      "grad_norm": 0.9765816330909729,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.5462,
+      "step": 36
+    },
+    {
+      "epoch": 0.015557476231633534,
+      "eval_loss": 1.5527358055114746,
+      "eval_runtime": 132.0946,
+      "eval_samples_per_second": 118.014,
+      "eval_steps_per_second": 3.694,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.524929725104128e+16,
+  "total_flos": 1.1369924007664026e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null