Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f440a00747157282b67f448549a0eceece3082b58ee61b9422f63acb942a04b
+oid sha256:265d7c8ca7f8ddb2bcbcce379d5f3ae8d880b86587f514a96911745ff530f6e4
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2844f12ff9838ef25bd669663821b96fef799b9e75bef1743d98d717c3043aa
+oid sha256:b94cdf92e7ad523531548ef63644867238366d69a4fd2dbda56aad73666a9c0b
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89125b381bd706e47d0969ca57bde232385b184bb6fee985c4b095b282bae7af
+oid sha256:3f04944917c15f265951392f0ad036c49b2e1d3572ae924179abc0eb1dc0ce1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015709336985418514,
+  "epoch": 0.0020140175622331427,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.1454,
       "step": 35
+    },
+    {
+      "epoch": 0.0016112140497865142,
+      "grad_norm": 2.3186516761779785,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1262,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016112140497865142,
+      "eval_loss": 0.11483553051948547,
+      "eval_runtime": 841.3258,
+      "eval_samples_per_second": 12.426,
+      "eval_steps_per_second": 6.213,
+      "step": 40
+    },
+    {
+      "epoch": 0.0018126158060098284,
+      "grad_norm": 1.910662293434143,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1299,
+      "step": 45
+    },
+    {
+      "epoch": 0.0020140175622331427,
+      "grad_norm": 1.3861061334609985,
+      "learning_rate": 0.0,
+      "loss": 0.0962,
+      "step": 50
+    },
+    {
+      "epoch": 0.0020140175622331427,
+      "eval_loss": 0.10776723176240921,
+      "eval_runtime": 839.7271,
+      "eval_samples_per_second": 12.449,
+      "eval_steps_per_second": 6.225,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7453256523448320.0,
+  "total_flos": 9555457081344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null