Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d5ac296835703bdc3c1a3c436f4e042077f8ff2207f21a42845599b150465cd
+oid sha256:e040b6712f4f02f3af0e6cf17e1abf8c852049851fdc9372d82257e736141a88
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326ce36e880fdf80442d7e107374bbba3c913c50d60dbba23a74aef105e63766
+oid sha256:9514e506380a652b0b7153f66236493a6b0f40250ab18b87923f8ca5cdffe4e1
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82d0ecbef671f1b5140c84a3f715e2cd9b406b289691cdaa674439f4ae0105c1
+oid sha256:67c26bb6236eec96d4c00c6a30c86ba7ada080a5ae93db3f8feb6d572392cde2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594dcf1d063251cca4c3b70569456a468140193c0f517d256489d095068b4748
+oid sha256:4bcb6468c96e42ca9e19eeef69577865d7a693066e16690bd13303c9f6654183
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019681620839363242,
+  "epoch": 0.038205499276410995,
   "eval_steps": 5,
-  "global_step": 17,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,72 @@
       "eval_samples_per_second": 17.935,
       "eval_steps_per_second": 8.967,
       "step": 15
+    },
+    {
+      "epoch": 0.020839363241678725,
+      "grad_norm": 1.1826555728912354,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 1.1934,
+      "step": 18
+    },
+    {
+      "epoch": 0.023154848046309694,
+      "eval_loss": 0.9056394696235657,
+      "eval_runtime": 20.314,
+      "eval_samples_per_second": 17.919,
+      "eval_steps_per_second": 8.959,
+      "step": 20
+    },
+    {
+      "epoch": 0.02431259044862518,
+      "grad_norm": 0.8417156338691711,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.0504,
+      "step": 21
+    },
+    {
+      "epoch": 0.027785817655571636,
+      "grad_norm": 0.6047336459159851,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 0.8442,
+      "step": 24
+    },
+    {
+      "epoch": 0.02894356005788712,
+      "eval_loss": 0.8459122180938721,
+      "eval_runtime": 20.3486,
+      "eval_samples_per_second": 17.888,
+      "eval_steps_per_second": 8.944,
+      "step": 25
+    },
+    {
+      "epoch": 0.03125904486251809,
+      "grad_norm": 0.5935313701629639,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.8208,
+      "step": 27
+    },
+    {
+      "epoch": 0.03473227206946455,
+      "grad_norm": 0.587660014629364,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.8746,
+      "step": 30
+    },
+    {
+      "epoch": 0.03473227206946455,
+      "eval_loss": 0.8241384029388428,
+      "eval_runtime": 20.3415,
+      "eval_samples_per_second": 17.894,
+      "eval_steps_per_second": 8.947,
+      "step": 30
+    },
+    {
+      "epoch": 0.038205499276410995,
+      "grad_norm": 0.7653340697288513,
+      "learning_rate": 0.0,
+      "loss": 0.9263,
+      "step": 33
     }
   ],
   "logging_steps": 3,
@@ -88,12 +154,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1672418087141376.0,
+  "total_flos": 3246458639745024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null