Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f474ff4e4a42c1edf2484b62fdee919eab51264326a6020ed10dcf15673439a
+oid sha256:fccedf7bd6165aab9ac7d2f0a710211cf1e6ef803ab06f1be144887f211e2c74
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f1af85178a5296f8bff01f3c7a46f8a98ee35e442d3e514218a5eebe127c4e0
+oid sha256:e6b6282eb1f2e5e841498a3839b0019ace17d34a9d6c5f5446b99bde622cced3
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e4dcb900c8c56a5645da24eb3350a53f6c91cf53b1e92b45f1199862badd156
+oid sha256:6a5d2767352d8215c1a1adc63f493cf0a6208611d018c5cdfa49ee4e461de862
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f629ef6cf58883c1435755f27f710c16e053656612fe2d30855f87cb1c474a91
+oid sha256:cde3ad3558a4f7f0bd3285f394837adc80c51713d2976f64724e9e11c03b168b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0360f63d0bfb1206e8307430bd30711ae1fb32c8b92787d373c208986063dc
+oid sha256:cdb0a4b07025af86e034d2e0f508cf20e86121fe8754690fc36155447f1c7e5f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce39cb2d5d9d413d1a68eac1b8f1313c68155dd35c6f415a24b9b488aa665e93
+oid sha256:9a7b9cf7b0e2560879e550dc35c5de2a41a59d27f2a43dfe1655b69ae2c754a1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18947368421052632,
+  "epoch": 0.21052631578947367,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 16.565,
       "eval_steps_per_second": 4.141,
       "step": 9
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.2985093593597412,
+      "learning_rate": 0.0002,
+      "loss": 0.9404,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.516539235578675e+16,
+  "total_flos": 2.796154706198528e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null