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:d405e2ee3ba92bafdd5b014aeb0c1d0504cb05fd561d7d6a42fa05e921acb8a3
+oid sha256:db8bce836731b32eee6a5100a91ebddfdd96030422dd282232a078851a7120f7
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a89eb81c970c05fd0bec3161de9211c0c314ecda087f84cc7d8cec8cc0195e3
+oid sha256:7755727c7a4c5e294051f148cc2a44f2e1ffde5f0e5632a789c01679046b0ae2
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc940837d9afbc0223097d82695a1b91df9895bd268e592c8f4e38ce5ea878e3
+oid sha256:c4c830fec9e27c12fc71c2025cf004f703dfa92fd22ae1cff560c494ff1dc8eb
 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": 0.014138118542686243,
+  "epoch": 0.0181257930034439,
   "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": 2.8624,
       "step": 35
+    },
+    {
+      "epoch": 0.014500634402755121,
+      "grad_norm": 0.6210654377937317,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.8442,
+      "step": 40
+    },
+    {
+      "epoch": 0.014500634402755121,
+      "eval_loss": 2.8301546573638916,
+      "eval_runtime": 44.938,
+      "eval_samples_per_second": 25.858,
+      "eval_steps_per_second": 12.929,
+      "step": 40
+    },
+    {
+      "epoch": 0.01631321370309951,
+      "grad_norm": 0.6846694946289062,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.831,
+      "step": 45
+    },
+    {
+      "epoch": 0.0181257930034439,
+      "grad_norm": 0.5996302366256714,
+      "learning_rate": 0.0,
+      "loss": 2.8464,
+      "step": 50
+    },
+    {
+      "epoch": 0.0181257930034439,
+      "eval_loss": 2.8290905952453613,
+      "eval_runtime": 44.6395,
+      "eval_samples_per_second": 26.031,
+      "eval_steps_per_second": 13.015,
+      "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": 678915999006720.0,
+  "total_flos": 872574005280768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null