Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5f1aef1168392bc2c89ee1837efb6f7b8234e4a01dba2aba7a2ff076eab3b9
+oid sha256:7069659ae43a5be752be501c48a1ecb3370ac8dc699a03b3900b63a455ce1111
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce270bdd01ccd91d8d330b06b2ab4503aa0dc1923c1d40e487d84208136b7cc
+oid sha256:cbf773ed030bf1428a088d0db7003c2391c9f7bd8dea644029eeb162f5ae7916
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67eee6b9041ea4d2d4db1e0a702faa93b21073c9ba1ada6a27f4c9f53b3e852a
+oid sha256:cce571ab52d784adc7a6b4f92e525bc646eaed159b8874aca0d68738a5eacabf
 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": 0.07439198855507868,
+  "epoch": 0.09537434430138293,
   "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": 0.1948,
       "step": 35
+    },
+    {
+      "epoch": 0.07629947544110634,
+      "grad_norm": 0.2277861088514328,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2392,
+      "step": 40
+    },
+    {
+      "epoch": 0.07629947544110634,
+      "eval_loss": 0.21202053129673004,
+      "eval_runtime": 26.8186,
+      "eval_samples_per_second": 8.241,
+      "eval_steps_per_second": 4.139,
+      "step": 40
+    },
+    {
+      "epoch": 0.08583690987124463,
+      "grad_norm": 0.2093382477760315,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2891,
+      "step": 45
+    },
+    {
+      "epoch": 0.09537434430138293,
+      "grad_norm": 0.18690498173236847,
+      "learning_rate": 0.0,
+      "loss": 0.1954,
+      "step": 50
+    },
+    {
+      "epoch": 0.09537434430138293,
+      "eval_loss": 0.21119874715805054,
+      "eval_runtime": 26.7271,
+      "eval_samples_per_second": 8.269,
+      "eval_steps_per_second": 4.153,
+      "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": 1.3825492754890752e+16,
+  "total_flos": 1.7709577675997184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null