Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1368f26d749c926a03092ec498deaf08a2ad54127599df47628f795f28e34632
+oid sha256:ce5919e70d5e7b9c4ca98536edf34f264b5a584191ee94b6e79ab58079aee0a2
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3208704531c5f44dca6151413170d6a6df7e252d74a1689d88aebefe59e99a6d
+oid sha256:e09f3a3788449b80799e21ad612b3ebabbb5967103a0dc06084028450c105087
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b49347475bc642ab719c98ac65f8cfd14867cc100c9208e704116b69aa264c7
+oid sha256:178a5f111ced7fdc25dd55d5b66ba78d396771eb88b4fe57851d378236eb2ff9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1497839654344695,
+  "epoch": 0.19203072491598655,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 48.207,
       "eval_steps_per_second": 6.043,
       "step": 30
+    },
+    {
+      "epoch": 0.15362457993278925,
+      "grad_norm": 0.26648080348968506,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4895,
+      "step": 40
+    },
+    {
+      "epoch": 0.15362457993278925,
+      "eval_loss": 1.5210355520248413,
+      "eval_runtime": 36.2375,
+      "eval_samples_per_second": 48.431,
+      "eval_steps_per_second": 6.071,
+      "step": 40
+    },
+    {
+      "epoch": 0.19203072491598655,
+      "grad_norm": 0.2611956000328064,
+      "learning_rate": 0.0,
+      "loss": 1.5052,
+      "step": 50
+    },
+    {
+      "epoch": 0.19203072491598655,
+      "eval_loss": 1.5189955234527588,
+      "eval_runtime": 36.3828,
+      "eval_samples_per_second": 48.237,
+      "eval_steps_per_second": 6.047,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9575130564919296.0,
+  "total_flos": 1.22758084165632e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null