Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baedaa6b31b62c47a81ada3aeb0b73cca337138c1bcd8269a10c80a6cb3831e8
+oid sha256:6b65c9697051867e89d8036cf5cc0f1eff79e732caf709466e5a77c04bd0f77f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ddabadc0ec33cc4ea2effc4539df2dd30538c9acdcf2855064fef758c7aaea
+oid sha256:985885bfabf15de418681fbb163eaafcf44c59e6503bf54b7e4d8ead46c1bbb9
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d6c6954105413e254c1dc776a27dd427206924cc5f1ee48db29b4f18851c42
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004992511233150275,
+  "epoch": 0.00998502246630055,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 10.102,
       "eval_steps_per_second": 5.055,
       "step": 15
+    },
+    {
+      "epoch": 0.005991013479780329,
+      "grad_norm": 13.16622543334961,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 7.2987,
+      "step": 18
+    },
+    {
+      "epoch": 0.006656681644200366,
+      "eval_loss": 1.8276801109313965,
+      "eval_runtime": 125.3012,
+      "eval_samples_per_second": 10.096,
+      "eval_steps_per_second": 5.052,
+      "step": 20
+    },
+    {
+      "epoch": 0.006989515726410384,
+      "grad_norm": 9.926828384399414,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 7.4413,
+      "step": 21
+    },
+    {
+      "epoch": 0.00798801797304044,
+      "grad_norm": 8.056083679199219,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 7.2979,
+      "step": 24
+    },
+    {
+      "epoch": 0.008320852055250457,
+      "eval_loss": 1.7948994636535645,
+      "eval_runtime": 125.3153,
+      "eval_samples_per_second": 10.095,
+      "eval_steps_per_second": 5.051,
+      "step": 25
+    },
+    {
+      "epoch": 0.008986520219670495,
+      "grad_norm": 7.1463117599487305,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 6.9667,
+      "step": 27
+    },
+    {
+      "epoch": 0.00998502246630055,
+      "grad_norm": 7.61177396774292,
+      "learning_rate": 0.0,
+      "loss": 7.57,
+      "step": 30
+    },
+    {
+      "epoch": 0.00998502246630055,
+      "eval_loss": 1.7903094291687012,
+      "eval_runtime": 125.31,
+      "eval_samples_per_second": 10.095,
+      "eval_steps_per_second": 5.051,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5273471240110080.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null