Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d166edb66ecc6e96dac5a0d7aaef02a0d6938af07ac43d7aea25b7cbd34f8c9
+oid sha256:0fe38e8df34706cee492661fadf4ec76683c6ce2553544918418b4870547c330
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:118357c000ea3ff7aad9795be734915c6def5b2651aae72386aa0f9e60a15f21
+oid sha256:24c8deae60dd8f20bad8fa7ccefb748bc3ab1cd677ac8e1ebb6e64984b298a24
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef36bdc1b35a92e49ed00b8b3f1f22e99127b8d03f4084585183c1c83a3d7dc
+oid sha256:8c5ac15b9ec0aaee9add9f622dc23b79e3c12474ed593f1ea37b0bfe29f692e2
 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": 0.11095305832147938,
+  "epoch": 0.1422475106685633,
   "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": 10.3783,
       "step": 35
+    },
+    {
+      "epoch": 0.11379800853485064,
+      "grad_norm": 0.026645995676517487,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3738,
+      "step": 40
+    },
+    {
+      "epoch": 0.11379800853485064,
+      "eval_loss": 10.373921394348145,
+      "eval_runtime": 0.8687,
+      "eval_samples_per_second": 170.376,
+      "eval_steps_per_second": 85.188,
+      "step": 40
+    },
+    {
+      "epoch": 0.12802275960170698,
+      "grad_norm": 0.028516408056020737,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3772,
+      "step": 45
+    },
+    {
+      "epoch": 0.1422475106685633,
+      "grad_norm": 0.023940356448292732,
+      "learning_rate": 0.0,
+      "loss": 10.3792,
+      "step": 50
+    },
+    {
+      "epoch": 0.1422475106685633,
+      "eval_loss": 10.373919486999512,
+      "eval_runtime": 0.8942,
+      "eval_samples_per_second": 165.508,
+      "eval_steps_per_second": 82.754,
+      "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": 853439938560.0,
+  "total_flos": 1082963558400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null