Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:501a387b8f3f43af1f49c4a5f85b8a640da5baa0235389a76f5a9766055e2ba1
+oid sha256:605d26a356418db799c67e3e8c3ec9e859f4c9e0cd19a3ba940d83c4b06de078
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62fed03cbe31b6ff20a4bbfac19fe8bd9e8acc5452cb446c7aa1977182bf847d
+oid sha256:e4a1ade4a3e28f97c474c0b96e2eaa9daaf7b389e56243b47985308e9cfa858b
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe97d8531e36851bcdb6fbedf0ffcd29f83a49697e0dc9a3b364b5fc32ee8c3b
+oid sha256:a19ca7599b2860e95c36f48c4c8a131ccee3fc8904908690a9409db0aea3b387
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04094165813715456,
+  "epoch": 0.05458887751620607,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,43 @@
       "eval_samples_per_second": 12.114,
       "eval_steps_per_second": 6.076,
       "step": 30
+    },
+    {
+      "epoch": 0.04503582395087001,
+      "grad_norm": 5.698742389678955,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 1.7932,
+      "step": 33
+    },
+    {
+      "epoch": 0.047765267826680315,
+      "eval_loss": 1.5948125123977661,
+      "eval_runtime": 25.5924,
+      "eval_samples_per_second": 12.074,
+      "eval_steps_per_second": 6.056,
+      "step": 35
+    },
+    {
+      "epoch": 0.04912998976458546,
+      "grad_norm": 1.6342817544937134,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.6323,
+      "step": 36
+    },
+    {
+      "epoch": 0.05322415557830092,
+      "grad_norm": 1.7538115978240967,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 1.5856,
+      "step": 39
+    },
+    {
+      "epoch": 0.05458887751620607,
+      "eval_loss": 1.5928868055343628,
+      "eval_runtime": 25.4997,
+      "eval_samples_per_second": 12.118,
+      "eval_steps_per_second": 6.079,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -147,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2951326036131840.0,
+  "total_flos": 3935101381509120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null