Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a596952a755848526806b101a15aad6409b94e5d8dd61209401c389cd63bc79
+oid sha256:e2cfe5175104b9c5e95fef44afa1ea47fe673e9a3281ce1ade3da9e9163401e8
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb9b9a04703bde00cad0ed92e4973bd3ad8a5d3ab9c824895b2288817de7fa5
+oid sha256:ef03827ee81c85cc3b3a60483f3e794d91ae00ad60b9c78cb3d952350536c127
 size 19859140

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1856571c9f63580e6243020b361b841ebfe2d647d3b41923d8d56c5cf10f335d
+oid sha256:a158bffde00f3b94fbe226ffc89c21785c62a0b48b7ab6bf6dd1d421c4f5ce89
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccf4fa2e66fa2eb880947e5ce3f0e3fa84d2b93d9a85ab9cc3309f55cc2a3536
+oid sha256:0e89d752b894b87b981f26606c63e6f55fbe84443217a4159158f16cdb81e546
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb7600c2911b865f76ad32da8fb785e4e6ac0f7bdbbb2b6be5a75386820b99d
+oid sha256:4b79f93b4aa40498616453343fdc042d292a4ae365d28d9b1bdacb21b821d26b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25f479a71303159a97fc8fbd96e9f7f3d96839c6ec2cf72cc92f7b7a335b060
+oid sha256:332162ff9f40bd49f2f8ffc76c63a65f38986b3628c470c2d9c174f20c576962
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d454b2e47703d9a490003b78eb31842c728d1e2654946fbd519e4aacc06f260b
+oid sha256:29dcce5b4e99bb2b262d1c5632dd9a42dd47914e79e63421d496b4752acba6d9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.935064935064935,
+  "epoch": 1.0389610389610389,
   "eval_steps": 2,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -47,6 +47,21 @@
       "eval_samples_per_second": 343.701,
       "eval_steps_per_second": 11.943,
       "step": 8
+    },
+    {
+      "epoch": 1.0389610389610389,
+      "grad_norm": 0.516305148601532,
+      "learning_rate": 0.0,
+      "loss": 2.7971,
+      "step": 10
+    },
+    {
+      "epoch": 1.0389610389610389,
+      "eval_loss": 2.6704092025756836,
+      "eval_runtime": 0.773,
+      "eval_samples_per_second": 335.078,
+      "eval_steps_per_second": 11.644,
+      "step": 10
     }
   ],
   "logging_steps": 10,
@@ -61,12 +76,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.884172946977587e+16,
+  "total_flos": 2.091723832426496e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null