Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fd61cb4019b150dada128125ec822c5b72137e8c272c68216be4046095f9bc9
+oid sha256:936a8f124e69f5086c48a2582d9038311cb364ef8fde8fa749d4cbce05b9e6e7
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b412be41733f0ebe23c8ad8793df6f7a5b9890c4f38e716c108dd96aaed1234e
+oid sha256:52f6878bcdf34a3a3295f21cce524696024225ad61579822cbd1e44e9a90b28b
 size 25859156

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4337f3fec9046d4a616ecff2e93493e9795821eb9efddbe5a5f6bd96bc45173
+oid sha256:74d7afa62b440c90f966729122eccc770fc041be7df2ccc57757a03618a594f3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f289d0df8ec8a6536b87c21a77c55e71d92cbb6166908d91730d04eca8586dbc
+oid sha256:18e012635bdcfede3439a84da118c2102d32d981c44179e8f36b21e078e3f75c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:943ffa179ca6b61867cc4015d4e97fff8c1eeaecf49793447b4cabca8689aa13
+oid sha256:3c5df06b0a33ba5014796770fdba80324ef5457894a21082ba5c388bbb02b3a1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c735c7d6f164a6fba520861ecf52b6d717d49df96dcf80d2e412f455b551be24
+oid sha256:28d888e390dd0738f0dc877a0ff007dbaed74bf54dc1d72212ce12dc9969b4cb
 size 15024

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": 0.2831215970961887,
+  "epoch": 0.3629764065335753,
   "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": 4.309,
       "step": 35
+    },
+    {
+      "epoch": 0.29038112522686027,
+      "grad_norm": 2.5858254432678223,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.4672,
+      "step": 40
+    },
+    {
+      "epoch": 0.29038112522686027,
+      "eval_loss": 0.9652195572853088,
+      "eval_runtime": 2.2359,
+      "eval_samples_per_second": 103.761,
+      "eval_steps_per_second": 12.97,
+      "step": 40
+    },
+    {
+      "epoch": 0.32667876588021777,
+      "grad_norm": 2.5173561573028564,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.9447,
+      "step": 45
+    },
+    {
+      "epoch": 0.3629764065335753,
+      "grad_norm": 3.130607843399048,
+      "learning_rate": 0.0,
+      "loss": 3.7905,
+      "step": 50
+    },
+    {
+      "epoch": 0.3629764065335753,
+      "eval_loss": 0.9589429497718811,
+      "eval_runtime": 2.1778,
+      "eval_samples_per_second": 106.528,
+      "eval_steps_per_second": 13.316,
+      "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": 1.4939691518263296e+16,
+  "total_flos": 1.916227713970995e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null